ARM queue: mostly patches from me, but also the Smartfusion2 board. thanks -- PMM The following changes since commit 9ee660e7c138595224b65ddc1c5712549f0a278c: Merge remote-tracking branch 'remotes/yongbok/tags/mips-20170921' into staging (2017-09-21 14:40:32 +0100) are available in the git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20170921 for you to fetch changes up to 6d262dcb7d108eda93813574c2061398084dc795: msf2: Add Emcraft's Smartfusion2 SOM kit (2017-09-21 16:36:56 +0100) ---------------------------------------------------------------- target-arm queue: * more preparatory work for v8M support * convert some omap devices away from old_mmio * remove out of date ARM ARM section references in comments * add the Smartfusion2 board ---------------------------------------------------------------- Peter Maydell (26): target/arm: Implement MSR/MRS access to NS banked registers nvic: Add banked exception states nvic: Add cached vectpending_is_s_banked state nvic: Add cached vectpending_prio state nvic: Implement AIRCR changes for v8M nvic: Make ICSR.RETTOBASE handle banked exceptions nvic: Implement NVIC_ITNS<n> registers nvic: Handle banked exceptions in nvic_recompute_state() nvic: Make set_pending and clear_pending take a secure parameter nvic: Make SHPR registers banked nvic: Compare group priority for escalation to HF nvic: In escalation to HardFault, support HF not being priority -1 nvic: Implement v8M changes to fixed priority exceptions nvic: Disable the non-secure HardFault if AIRCR.BFHFNMINS is clear nvic: Handle v8M changes in nvic_exec_prio() target/arm: Handle banking in negative-execution-priority check in cpu_mmu_index() nvic: Make ICSR banked for v8M nvic: Make SHCSR banked for v8M nvic: Support banked exceptions in acknowledge and complete target/arm: Remove out of date ARM ARM section references in A64 decoder hw/arm/palm.c: Don't use old_mmio for static_ops hw/gpio/omap_gpio.c: Don't use old_mmio hw/timer/omap_synctimer.c: Don't use old_mmio hw/timer/omap_gptimer: Don't use old_mmio hw/i2c/omap_i2c.c: Don't use old_mmio hw/arm/omap2.c: Don't use old_mmio Subbaraya Sundeep (5): msf2: Add Smartfusion2 System timer msf2: Microsemi Smartfusion2 System Register block msf2: Add Smartfusion2 SPI controller msf2: Add Smartfusion2 SoC msf2: Add Emcraft's Smartfusion2 SOM kit hw/arm/Makefile.objs | 1 + hw/misc/Makefile.objs | 1 + hw/ssi/Makefile.objs | 1 + hw/timer/Makefile.objs | 1 + include/hw/arm/msf2-soc.h | 67 +++ include/hw/intc/armv7m_nvic.h | 33 +- include/hw/misc/msf2-sysreg.h | 77 ++++ include/hw/ssi/mss-spi.h | 58 +++ include/hw/timer/mss-timer.h | 64 +++ target/arm/cpu.h | 62 ++- hw/arm/msf2-soc.c | 238 +++++++++++ hw/arm/msf2-som.c | 105 +++++ hw/arm/omap2.c | 49 ++- hw/arm/palm.c | 30 +- hw/gpio/omap_gpio.c | 26 +- hw/i2c/omap_i2c.c | 44 +- hw/intc/armv7m_nvic.c | 913 ++++++++++++++++++++++++++++++++++------ hw/misc/msf2-sysreg.c | 160 +++++++ hw/ssi/mss-spi.c | 404 ++++++++++++++++++ hw/timer/mss-timer.c | 289 +++++++++++++ hw/timer/omap_gptimer.c | 49 ++- hw/timer/omap_synctimer.c | 35 +- target/arm/cpu.c | 7 + target/arm/helper.c | 142 ++++++- target/arm/translate-a64.c | 227 +++++----- default-configs/arm-softmmu.mak | 1 + hw/intc/trace-events | 13 +- hw/misc/trace-events | 5 + 28 files changed, 2735 insertions(+), 367 deletions(-) create mode 100644 include/hw/arm/msf2-soc.h create mode 100644 include/hw/misc/msf2-sysreg.h create mode 100644 include/hw/ssi/mss-spi.h create mode 100644 include/hw/timer/mss-timer.h create mode 100644 hw/arm/msf2-soc.c create mode 100644 hw/arm/msf2-som.c create mode 100644 hw/misc/msf2-sysreg.c create mode 100644 hw/ssi/mss-spi.c create mode 100644 hw/timer/mss-timer.c In v8M the MSR and MRS instructions have extra register value encodings to allow secure code to access the non-secure banked version of various special registers. (We don't implement the MSPLIM_NS or PSPLIM_NS aliases, because we don't currently implement the stack limit registers at all.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-2-git-send-email-peter.maydell@linaro.org --- target/arm/helper.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 110 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg) break; case 20: /* CONTROL */ return env->v7m.control[env->v7m.secure]; + case 0x94: /* CONTROL_NS */ + /* We have to handle this here because unprivileged Secure code + * can read the NS CONTROL register. + */ + if (!env->v7m.secure) { + return 0; + } + return env->v7m.control[M_REG_NS]; } if (el == 0) { return 0; /* unprivileged reads others as zero */ } + if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { + switch (reg) { + case 0x88: /* MSP_NS */ + if (!env->v7m.secure) { + return 0; + } + return env->v7m.other_ss_msp; + case 0x89: /* PSP_NS */ + if (!env->v7m.secure) { + return 0; + } + return env->v7m.other_ss_psp; + case 0x90: /* PRIMASK_NS */ + if (!env->v7m.secure) { + return 0; + } + return env->v7m.primask[M_REG_NS]; + case 0x91: /* BASEPRI_NS */ + if (!env->v7m.secure) { + return 0; + } + return env->v7m.basepri[M_REG_NS]; + case 0x93: /* FAULTMASK_NS */ + if (!env->v7m.secure) { + return 0; + } + return env->v7m.faultmask[M_REG_NS]; + case 0x98: /* SP_NS */ + { + /* This gives the non-secure SP selected based on whether we're + * currently in handler mode or not, using the NS CONTROL.SPSEL. + */ + bool spsel = env->v7m.control[M_REG_NS] & R_V7M_CONTROL_SPSEL_MASK; + + if (!env->v7m.secure) { + return 0; + } + if (!arm_v7m_is_handler_mode(env) && spsel) { + return env->v7m.other_ss_psp; + } else { + return env->v7m.other_ss_msp; + } + } + default: + break; + } + } + switch (reg) { case 8: /* MSP */ return (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK) ? @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) return; } + if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { + switch (reg) { + case 0x88: /* MSP_NS */ + if (!env->v7m.secure) { + return; + } + env->v7m.other_ss_msp = val; + return; + case 0x89: /* PSP_NS */ + if (!env->v7m.secure) { + return; + } + env->v7m.other_ss_psp = val; + return; + case 0x90: /* PRIMASK_NS */ + if (!env->v7m.secure) { + return; + } + env->v7m.primask[M_REG_NS] = val & 1; + return; + case 0x91: /* BASEPRI_NS */ + if (!env->v7m.secure) { + return; + } + env->v7m.basepri[M_REG_NS] = val & 0xff; + return; + case 0x93: /* FAULTMASK_NS */ + if (!env->v7m.secure) { + return; + } + env->v7m.faultmask[M_REG_NS] = val & 1; + return; + case 0x98: /* SP_NS */ + { + /* This gives the non-secure SP selected based on whether we're + * currently in handler mode or not, using the NS CONTROL.SPSEL. + */ + bool spsel = env->v7m.control[M_REG_NS] & R_V7M_CONTROL_SPSEL_MASK; + + if (!env->v7m.secure) { + return; + } + if (!arm_v7m_is_handler_mode(env) && spsel) { + env->v7m.other_ss_psp = val; + } else { + env->v7m.other_ss_msp = val; + } + return; + } + default: + break; + } + } + switch (reg) { case 0 ... 7: /* xPSR sub-fields */ /* only APSR is actually writable */ -- 2.7.4 For the v8M security extension, some exceptions must be banked between security states. Add the new vecinfo array which holds the state for the banked exceptions and migrate it if the CPU the NVIC is attached to implements the security extension. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/intc/armv7m_nvic.h | 14 ++++++++++++ hw/intc/armv7m_nvic.c | 53 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 66 insertions(+), 1 deletion(-) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ /* Highest permitted number of exceptions (architectural limit) */ #define NVIC_MAX_VECTORS 512 +/* Number of internal exceptions */ +#define NVIC_INTERNAL_VECTORS 16 typedef struct VecInfo { /* Exception priorities can range from -3 to 255; only the unmodifiable @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { ARMCPU *cpu; VecInfo vectors[NVIC_MAX_VECTORS]; + /* If the v8M security extension is implemented, some of the internal + * exceptions are banked between security states (ie there exists both + * a Secure and a NonSecure version of the exception and its state): + * HardFault, MemManage, UsageFault, SVCall, PendSV, SysTick (R_PJHV) + * The rest (including all the external exceptions) are not banked, though + * they may be configurable to target either Secure or NonSecure state. + * We store the secure exception state in sec_vectors[] for the banked + * exceptions, and otherwise use only vectors[] (including for exceptions + * like SecureFault that unconditionally target Secure state). + * Entries in sec_vectors[] for non-banked exception numbers are unused. + */ + VecInfo sec_vectors[NVIC_INTERNAL_VECTORS]; uint32_t prigroup; /* vectpending and exception_prio are both cached state that can diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ * For historical reasons QEMU tends to use "interrupt" and * "exception" more or less interchangeably. */ -#define NVIC_FIRST_IRQ 16 +#define NVIC_FIRST_IRQ NVIC_INTERNAL_VECTORS #define NVIC_MAX_IRQ (NVIC_MAX_VECTORS - NVIC_FIRST_IRQ) /* Effective running priority of the CPU when no exception is active @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_VecInfo = { } }; +static bool nvic_security_needed(void *opaque) +{ + NVICState *s = opaque; + + return arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY); +} + +static int nvic_security_post_load(void *opaque, int version_id) +{ + NVICState *s = opaque; + int i; + + /* Check for out of range priority settings */ + if (s->sec_vectors[ARMV7M_EXCP_HARD].prio != -1) { + return 1; + } + for (i = ARMV7M_EXCP_MEM; i < ARRAY_SIZE(s->sec_vectors); i++) { + if (s->sec_vectors[i].prio & ~0xff) { + return 1; + } + } + return 0; +} + +static const VMStateDescription vmstate_nvic_security = { + .name = "nvic/m-security", + .version_id = 1, + .minimum_version_id = 1, + .needed = nvic_security_needed, + .post_load = &nvic_security_post_load, + .fields = (VMStateField[]) { + VMSTATE_STRUCT_ARRAY(sec_vectors, NVICState, NVIC_INTERNAL_VECTORS, 1, + vmstate_VecInfo, VecInfo), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_nvic = { .name = "armv7m_nvic", .version_id = 4, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_nvic = { vmstate_VecInfo, VecInfo), VMSTATE_UINT32(prigroup, NVICState), VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription*[]) { + &vmstate_nvic_security, + NULL } }; @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->vectors[ARMV7M_EXCP_NMI].prio = -2; s->vectors[ARMV7M_EXCP_HARD].prio = -1; + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { + s->sec_vectors[ARMV7M_EXCP_HARD].enabled = 1; + s->sec_vectors[ARMV7M_EXCP_SVC].enabled = 1; + s->sec_vectors[ARMV7M_EXCP_PENDSV].enabled = 1; + s->sec_vectors[ARMV7M_EXCP_SYSTICK].enabled = 1; + + /* AIRCR.BFHFNMINS resets to 0 so Secure HF is priority -1 (R_CMTC) */ + s->sec_vectors[ARMV7M_EXCP_HARD].prio = -1; + } + /* Strictly speaking the reset handler should be enabled. * However, we don't simulate soft resets through the NVIC, * and the reset vector should never be pended. -- 2.7.4 With banked exceptions, just the exception number in s->vectpending is no longer sufficient to uniquely identify the pending exception. Add a vectpending_is_s_banked bool which is true if the exception is using the sec_vectors[] array. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1505240046-11454-4-git-send-email-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 11 +++++++++-- hw/intc/armv7m_nvic.c | 1 + 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { VecInfo sec_vectors[NVIC_INTERNAL_VECTORS]; uint32_t prigroup; - /* vectpending and exception_prio are both cached state that can - * be recalculated from the vectors[] array and the prigroup field. + /* The following fields are all cached state that can be recalculated + * from the vectors[] and sec_vectors[] arrays and the prigroup field: + * - vectpending + * - vectpending_is_secure + * - exception_prio */ unsigned int vectpending; /* highest prio pending enabled exception */ + /* true if vectpending is a banked secure exception, ie it is in + * sec_vectors[] rather than vectors[] + */ + bool vectpending_is_s_banked; int exception_prio; /* group prio of the highest prio active exception */ MemoryRegion sysregmem; diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->exception_prio = NVIC_NOEXC_PRIO; s->vectpending = 0; + s->vectpending_is_s_banked = false; } static void nvic_systick_trigger(void *opaque, int n, int level) -- 2.7.4 Instead of looking up the pending priority in nvic_pending_prio(), cache it in a new state struct field. The calculation of the pending priority given the interrupt number is more complicated in v8M with the security extension, so the caching will be worthwhile. This changes nvic_pending_prio() from returning a full (group + subpriority) priority value to returning a group priority. This doesn't require changes to its callsites because we use it only in comparisons of the form execution_prio > nvic_pending_prio() and execution priority is always a group priority, so a test (exec prio > full prio) is true if and only if (execprio > group_prio). (Architecturally the expected comparison is with the group priority for this sort of "would we preempt" test; we were only doing a test with a full priority as an optimisation to avoid the mask, which is possible precisely because the two comparisons always give the same answer.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-5-git-send-email-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 2 ++ hw/intc/armv7m_nvic.c | 23 +++++++++++++---------- hw/intc/trace-events | 2 +- 3 files changed, 16 insertions(+), 11 deletions(-) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { * - vectpending * - vectpending_is_secure * - exception_prio + * - vectpending_prio */ unsigned int vectpending; /* highest prio pending enabled exception */ /* true if vectpending is a banked secure exception, ie it is in @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { */ bool vectpending_is_s_banked; int exception_prio; /* group prio of the highest prio active exception */ + int vectpending_prio; /* group prio of the exeception in vectpending */ MemoryRegion sysregmem; MemoryRegion sysreg_ns_mem; diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const uint8_t nvic_id[] = { static int nvic_pending_prio(NVICState *s) { - /* return the priority of the current pending interrupt, + /* return the group priority of the current pending interrupt, * or NVIC_NOEXC_PRIO if no interrupt is pending */ - return s->vectpending ? s->vectors[s->vectpending].prio : NVIC_NOEXC_PRIO; + return s->vectpending_prio; } /* Return the value of the ISCR RETTOBASE bit: @@ -XXX,XX +XXX,XX @@ static void nvic_recompute_state(NVICState *s) active_prio &= nvic_gprio_mask(s); } + if (pend_prio > 0) { + pend_prio &= nvic_gprio_mask(s); + } + s->vectpending = pend_irq; + s->vectpending_prio = pend_prio; s->exception_prio = active_prio; - trace_nvic_recompute_state(s->vectpending, s->exception_prio); + trace_nvic_recompute_state(s->vectpending, + s->vectpending_prio, + s->exception_prio); } /* Return the current execution priority of the CPU @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_acknowledge_irq(void *opaque) CPUARMState *env = &s->cpu->env; const int pending = s->vectpending; const int running = nvic_exec_prio(s); - int pendgroupprio; VecInfo *vec; assert(pending > ARMV7M_EXCP_RESET && pending < s->num_irq); @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_acknowledge_irq(void *opaque) assert(vec->enabled); assert(vec->pending); - pendgroupprio = vec->prio; - if (pendgroupprio > 0) { - pendgroupprio &= nvic_gprio_mask(s); - } - assert(pendgroupprio < running); + assert(s->vectpending_prio < running); - trace_nvic_acknowledge_irq(pending, vec->prio); + trace_nvic_acknowledge_irq(pending, s->vectpending_prio); vec->active = 1; vec->pending = 0; @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->exception_prio = NVIC_NOEXC_PRIO; s->vectpending = 0; s->vectpending_is_s_banked = false; + s->vectpending_prio = NVIC_NOEXC_PRIO; } static void nvic_systick_trigger(void *opaque, int n, int level) diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_redist_set_irq(uint32_t cpu, int irq, int level) "GICv3 redistributor 0x%x gicv3_redist_send_sgi(uint32_t cpu, int irq) "GICv3 redistributor 0x%x pending SGI %d" # hw/intc/armv7m_nvic.c -nvic_recompute_state(int vectpending, int exception_prio) "NVIC state recomputed: vectpending %d exception_prio %d" +nvic_recompute_state(int vectpending, int vectpending_prio, int exception_prio) "NVIC state recomputed: vectpending %d vectpending_prio %d exception_prio %d" nvic_set_prio(int irq, uint8_t prio) "NVIC set irq %d priority %d" nvic_irq_update(int vectpending, int pendprio, int exception_prio, int level) "NVIC vectpending %d pending prio %d exception_prio %d: setting irq line to %d" nvic_escalate_prio(int irq, int irqprio, int runprio) "NVIC escalating irq %d to HardFault: insufficient priority %d >= %d" -- 2.7.4 The Application Interrupt and Reset Control Register has some changes for v8M: * new bits SYSRESETREQS, BFHFNMINS and PRIS: these all have real state if the security extension is implemented and otherwise are constant * the PRIGROUP field is banked between security states * non-secure code can be blocked from using the SYSRESET bit to reset the system if SYSRESETREQS is set Implement the new state and the changes to register read and write. For the moment we ignore the effects of the secure PRIGROUP. We will implement the effects of PRIS and BFHFNMIS later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-6-git-send-email-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 3 ++- target/arm/cpu.h | 12 +++++++++++ hw/intc/armv7m_nvic.c | 49 +++++++++++++++++++++++++++++++++---------- target/arm/cpu.c | 7 +++++++ 4 files changed, 59 insertions(+), 12 deletions(-) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { * Entries in sec_vectors[] for non-banked exception numbers are unused. */ VecInfo sec_vectors[NVIC_INTERNAL_VECTORS]; - uint32_t prigroup; + /* The PRIGROUP field in AIRCR is banked */ + uint32_t prigroup[M_REG_NUM_BANKS]; /* The following fields are all cached state that can be recalculated * from the vectors[] and sec_vectors[] arrays and the prigroup field: diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { int exception; uint32_t primask[M_REG_NUM_BANKS]; uint32_t faultmask[M_REG_NUM_BANKS]; + uint32_t aircr; /* only holds r/w state if security extn implemented */ uint32_t secure; /* Is CPU in Secure state? (not guest visible) */ } v7m; @@ -XXX,XX +XXX,XX @@ FIELD(V7M_CCR, STKALIGN, 9, 1) FIELD(V7M_CCR, DC, 16, 1) FIELD(V7M_CCR, IC, 17, 1) +/* V7M AIRCR bits */ +FIELD(V7M_AIRCR, VECTRESET, 0, 1) +FIELD(V7M_AIRCR, VECTCLRACTIVE, 1, 1) +FIELD(V7M_AIRCR, SYSRESETREQ, 2, 1) +FIELD(V7M_AIRCR, SYSRESETREQS, 3, 1) +FIELD(V7M_AIRCR, PRIGROUP, 8, 3) +FIELD(V7M_AIRCR, BFHFNMINS, 13, 1) +FIELD(V7M_AIRCR, PRIS, 14, 1) +FIELD(V7M_AIRCR, ENDIANNESS, 15, 1) +FIELD(V7M_AIRCR, VECTKEY, 16, 16) + /* V7M CFSR bits for MMFSR */ FIELD(V7M_CFSR, IACCVIOL, 0, 1) FIELD(V7M_CFSR, DACCVIOL, 1, 1) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static bool nvic_isrpending(NVICState *s) */ static inline uint32_t nvic_gprio_mask(NVICState *s) { - return ~0U << (s->prigroup + 1); + return ~0U << (s->prigroup[M_REG_NS] + 1); } /* Recompute vectpending and exception_prio */ @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) return val; case 0xd08: /* Vector Table Offset. */ return cpu->env.v7m.vecbase[attrs.secure]; - case 0xd0c: /* Application Interrupt/Reset Control. */ - return 0xfa050000 | (s->prigroup << 8); + case 0xd0c: /* Application Interrupt/Reset Control (AIRCR) */ + val = 0xfa050000 | (s->prigroup[attrs.secure] << 8); + if (attrs.secure) { + /* s->aircr stores PRIS, BFHFNMINS, SYSRESETREQS */ + val |= cpu->env.v7m.aircr; + } else { + if (arm_feature(&cpu->env, ARM_FEATURE_V8)) { + /* BFHFNMINS is R/O from NS; other bits are RAZ/WI. If + * security isn't supported then BFHFNMINS is RAO (and + * the bit in env.v7m.aircr is always set). + */ + val |= cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK; + } + } + return val; case 0xd10: /* System Control. */ /* TODO: Implement SLEEPONEXIT. */ return 0; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, case 0xd08: /* Vector Table Offset. */ cpu->env.v7m.vecbase[attrs.secure] = value & 0xffffff80; break; - case 0xd0c: /* Application Interrupt/Reset Control. */ - if ((value >> 16) == 0x05fa) { - if (value & 4) { - qemu_irq_pulse(s->sysresetreq); + case 0xd0c: /* Application Interrupt/Reset Control (AIRCR) */ + if ((value >> R_V7M_AIRCR_VECTKEY_SHIFT) == 0x05fa) { + if (value & R_V7M_AIRCR_SYSRESETREQ_MASK) { + if (attrs.secure || + !(cpu->env.v7m.aircr & R_V7M_AIRCR_SYSRESETREQS_MASK)) { + qemu_irq_pulse(s->sysresetreq); + } } - if (value & 2) { + if (value & R_V7M_AIRCR_VECTCLRACTIVE_MASK) { qemu_log_mask(LOG_GUEST_ERROR, "Setting VECTCLRACTIVE when not in DEBUG mode " "is UNPREDICTABLE\n"); } - if (value & 1) { + if (value & R_V7M_AIRCR_VECTRESET_MASK) { + /* NB: this bit is RES0 in v8M */ qemu_log_mask(LOG_GUEST_ERROR, "Setting VECTRESET when not in DEBUG mode " "is UNPREDICTABLE\n"); } - s->prigroup = extract32(value, 8, 3); + s->prigroup[attrs.secure] = extract32(value, + R_V7M_AIRCR_PRIGROUP_SHIFT, + R_V7M_AIRCR_PRIGROUP_LENGTH); + if (attrs.secure) { + /* These bits are only writable by secure */ + cpu->env.v7m.aircr = value & + (R_V7M_AIRCR_SYSRESETREQS_MASK | + R_V7M_AIRCR_BFHFNMINS_MASK | + R_V7M_AIRCR_PRIS_MASK); + } nvic_irq_update(s); } break; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_nvic_security = { .fields = (VMStateField[]) { VMSTATE_STRUCT_ARRAY(sec_vectors, NVICState, NVIC_INTERNAL_VECTORS, 1, vmstate_VecInfo, VecInfo), + VMSTATE_UINT32(prigroup[M_REG_S], NVICState), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_nvic = { .fields = (VMStateField[]) { VMSTATE_STRUCT_ARRAY(vectors, NVICState, NVIC_MAX_VECTORS, 1, vmstate_VecInfo, VecInfo), - VMSTATE_UINT32(prigroup, NVICState), + VMSTATE_UINT32(prigroup[M_REG_NS], NVICState), VMSTATE_END_OF_LIST() }, .subsections = (const VMStateDescription*[]) { diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { env->v7m.secure = true; + } else { + /* This bit resets to 0 if security is supported, but 1 if + * it is not. The bit is not present in v7M, but we set it + * here so we can avoid having to make checks on it conditional + * on ARM_FEATURE_V8 (we don't let the guest see the bit). + */ + env->v7m.aircr = R_V7M_AIRCR_BFHFNMINS_MASK; } /* In v7M the reset value of this bit is IMPDEF, but ARM recommends -- 2.7.4 Update the code in nvic_rettobase() so that it checks the sec_vectors[] array as well as the vectors[] array if needed. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-7-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static int nvic_pending_prio(NVICState *s) static bool nvic_rettobase(NVICState *s) { int irq, nhand = 0; + bool check_sec = arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY); for (irq = ARMV7M_EXCP_RESET; irq < s->num_irq; irq++) { - if (s->vectors[irq].active) { + if (s->vectors[irq].active || + (check_sec && irq < NVIC_INTERNAL_VECTORS && + s->sec_vectors[irq].active)) { nhand++; if (nhand == 2) { return 0; -- 2.7.4 For v8M, the NVIC has a new set of registers per interrupt, NVIC_ITNS<n>. These determine whether the interrupt targets Secure or Non-secure state. Implement the register read/write code for these, and make them cause NVIC_IABR, NVIC_ICER, NVIC_ISER, NVIC_ICPR, NVIC_IPR and NVIC_ISPR to RAZ/WI for non-secure accesses to fields corresponding to interrupts which are configured to target secure state. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-8-git-send-email-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 3 ++ hw/intc/armv7m_nvic.c | 74 +++++++++++++++++++++++++++++++++++++++---- 2 files changed, 70 insertions(+), 7 deletions(-) diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { /* The PRIGROUP field in AIRCR is banked */ uint32_t prigroup[M_REG_NUM_BANKS]; + /* v8M NVIC_ITNS state (stored as a bool per bit) */ + bool itns[NVIC_MAX_VECTORS]; + /* The following fields are all cached state that can be recalculated * from the vectors[] and sec_vectors[] arrays and the prigroup field: * - vectpending diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) switch (offset) { case 4: /* Interrupt Control Type. */ return ((s->num_irq - NVIC_FIRST_IRQ) / 32) - 1; + case 0x380 ... 0x3bf: /* NVIC_ITNS<n> */ + { + int startvec = 32 * (offset - 0x380) + NVIC_FIRST_IRQ; + int i; + + if (!arm_feature(&cpu->env, ARM_FEATURE_V8)) { + goto bad_offset; + } + if (!attrs.secure) { + return 0; + } + val = 0; + for (i = 0; i < 32 && startvec + i < s->num_irq; i++) { + if (s->itns[startvec + i]) { + val |= (1 << i); + } + } + return val; + } case 0xd00: /* CPUID Base. */ return cpu->midr; case 0xd04: /* Interrupt Control State. */ @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, ARMCPU *cpu = s->cpu; switch (offset) { + case 0x380 ... 0x3bf: /* NVIC_ITNS<n> */ + { + int startvec = 32 * (offset - 0x380) + NVIC_FIRST_IRQ; + int i; + + if (!arm_feature(&cpu->env, ARM_FEATURE_V8)) { + goto bad_offset; + } + if (!attrs.secure) { + break; + } + for (i = 0; i < 32 && startvec + i < s->num_irq; i++) { + s->itns[startvec + i] = (value >> i) & 1; + } + nvic_irq_update(s); + break; + } case 0xd04: /* Interrupt Control State. */ if (value & (1 << 31)) { armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI); @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, startvec = offset - 0x180 + NVIC_FIRST_IRQ; /* vector # */ for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) { - if (s->vectors[startvec + i].enabled) { + if (s->vectors[startvec + i].enabled && + (attrs.secure || s->itns[startvec + i])) { val |= (1 << i); } } @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, val = 0; startvec = offset - 0x280 + NVIC_FIRST_IRQ; /* vector # */ for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) { - if (s->vectors[startvec + i].pending) { + if (s->vectors[startvec + i].pending && + (attrs.secure || s->itns[startvec + i])) { val |= (1 << i); } } @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, startvec = offset - 0x300 + NVIC_FIRST_IRQ; /* vector # */ for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) { - if (s->vectors[startvec + i].active) { + if (s->vectors[startvec + i].active && + (attrs.secure || s->itns[startvec + i])) { val |= (1 << i); } } @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, startvec = offset - 0x400 + NVIC_FIRST_IRQ; /* vector # */ for (i = 0; i < size && startvec + i < s->num_irq; i++) { - val |= s->vectors[startvec + i].prio << (8 * i); + if (attrs.secure || s->itns[startvec + i]) { + val |= s->vectors[startvec + i].prio << (8 * i); + } } break; case 0xd18 ... 0xd23: /* System Handler Priority. */ @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, startvec = 8 * (offset - 0x180) + NVIC_FIRST_IRQ; for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) { - if (value & (1 << i)) { + if (value & (1 << i) && + (attrs.secure || s->itns[startvec + i])) { s->vectors[startvec + i].enabled = setval; } } @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, startvec = 8 * (offset - 0x280) + NVIC_FIRST_IRQ; /* vector # */ for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) { - if (value & (1 << i)) { + if (value & (1 << i) && + (attrs.secure || s->itns[startvec + i])) { s->vectors[startvec + i].pending = setval; } } @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, startvec = 8 * (offset - 0x400) + NVIC_FIRST_IRQ; /* vector # */ for (i = 0; i < size && startvec + i < s->num_irq; i++) { - set_prio(s, startvec + i, (value >> (i * 8)) & 0xff); + if (attrs.secure || s->itns[startvec + i]) { + set_prio(s, startvec + i, (value >> (i * 8)) & 0xff); + } } nvic_irq_update(s); return MEMTX_OK; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_nvic_security = { VMSTATE_STRUCT_ARRAY(sec_vectors, NVICState, NVIC_INTERNAL_VECTORS, 1, vmstate_VecInfo, VecInfo), VMSTATE_UINT32(prigroup[M_REG_S], NVICState), + VMSTATE_BOOL_ARRAY(itns, NVICState, NVIC_MAX_VECTORS), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->vectpending = 0; s->vectpending_is_s_banked = false; s->vectpending_prio = NVIC_NOEXC_PRIO; + + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { + memset(s->itns, 0, sizeof(s->itns)); + } else { + /* This state is constant and not guest accessible in a non-security + * NVIC; we set the bits to true to avoid having to do a feature + * bit check in the NVIC enable/pend/etc register accessors. + */ + int i; + + for (i = NVIC_FIRST_IRQ; i < ARRAY_SIZE(s->itns); i++) { + s->itns[i] = true; + } + } } static void nvic_systick_trigger(void *opaque, int n, int level) -- 2.7.4 Update the nvic_recompute_state() code to handle the security extension and its associated banked registers. Code that uses the resulting cached state (ie the irq acknowledge and complete code) will be updated in a later commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-9-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 151 ++++++++++++++++++++++++++++++++++++++++++++++++-- hw/intc/trace-events | 1 + 2 files changed, 147 insertions(+), 5 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ * (higher than the highest possible priority value) */ #define NVIC_NOEXC_PRIO 0x100 +/* Maximum priority of non-secure exceptions when AIRCR.PRIS is set */ +#define NVIC_NS_PRIO_LIMIT 0x80 static const uint8_t nvic_id[] = { 0x00, 0xb0, 0x1b, 0x00, 0x0d, 0xe0, 0x05, 0xb1 @@ -XXX,XX +XXX,XX @@ static bool nvic_isrpending(NVICState *s) return false; } +static bool exc_is_banked(int exc) +{ + /* Return true if this is one of the limited set of exceptions which + * are banked (and thus have state in sec_vectors[]) + */ + return exc == ARMV7M_EXCP_HARD || + exc == ARMV7M_EXCP_MEM || + exc == ARMV7M_EXCP_USAGE || + exc == ARMV7M_EXCP_SVC || + exc == ARMV7M_EXCP_PENDSV || + exc == ARMV7M_EXCP_SYSTICK; +} + /* Return a mask word which clears the subpriority bits from * a priority value for an M-profile exception, leaving only * the group priority. */ -static inline uint32_t nvic_gprio_mask(NVICState *s) +static inline uint32_t nvic_gprio_mask(NVICState *s, bool secure) +{ + return ~0U << (s->prigroup[secure] + 1); +} + +static bool exc_targets_secure(NVICState *s, int exc) +{ + /* Return true if this non-banked exception targets Secure state. */ + if (!arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { + return false; + } + + if (exc >= NVIC_FIRST_IRQ) { + return !s->itns[exc]; + } + + /* Function shouldn't be called for banked exceptions. */ + assert(!exc_is_banked(exc)); + + switch (exc) { + case ARMV7M_EXCP_NMI: + case ARMV7M_EXCP_BUS: + return !(s->cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK); + case ARMV7M_EXCP_SECURE: + return true; + case ARMV7M_EXCP_DEBUG: + /* TODO: controlled by DEMCR.SDME, which we don't yet implement */ + return false; + default: + /* reset, and reserved (unused) low exception numbers. + * We'll get called by code that loops through all the exception + * numbers, but it doesn't matter what we return here as these + * non-existent exceptions will never be pended or active. + */ + return true; + } +} + +static int exc_group_prio(NVICState *s, int rawprio, bool targets_secure) +{ + /* Return the group priority for this exception, given its raw + * (group-and-subgroup) priority value and whether it is targeting + * secure state or not. + */ + if (rawprio < 0) { + return rawprio; + } + rawprio &= nvic_gprio_mask(s, targets_secure); + /* AIRCR.PRIS causes us to squash all NS priorities into the + * lower half of the total range + */ + if (!targets_secure && + (s->cpu->env.v7m.aircr & R_V7M_AIRCR_PRIS_MASK)) { + rawprio = (rawprio >> 1) + NVIC_NS_PRIO_LIMIT; + } + return rawprio; +} + +/* Recompute vectpending and exception_prio for a CPU which implements + * the Security extension + */ +static void nvic_recompute_state_secure(NVICState *s) { - return ~0U << (s->prigroup[M_REG_NS] + 1); + int i, bank; + int pend_prio = NVIC_NOEXC_PRIO; + int active_prio = NVIC_NOEXC_PRIO; + int pend_irq = 0; + bool pending_is_s_banked = false; + + /* R_CQRV: precedence is by: + * - lowest group priority; if both the same then + * - lowest subpriority; if both the same then + * - lowest exception number; if both the same (ie banked) then + * - secure exception takes precedence + * Compare pseudocode RawExecutionPriority. + * Annoyingly, now we have two prigroup values (for S and NS) + * we can't do the loop comparison on raw priority values. + */ + for (i = 1; i < s->num_irq; i++) { + for (bank = M_REG_S; bank >= M_REG_NS; bank--) { + VecInfo *vec; + int prio; + bool targets_secure; + + if (bank == M_REG_S) { + if (!exc_is_banked(i)) { + continue; + } + vec = &s->sec_vectors[i]; + targets_secure = true; + } else { + vec = &s->vectors[i]; + targets_secure = !exc_is_banked(i) && exc_targets_secure(s, i); + } + + prio = exc_group_prio(s, vec->prio, targets_secure); + if (vec->enabled && vec->pending && prio < pend_prio) { + pend_prio = prio; + pend_irq = i; + pending_is_s_banked = (bank == M_REG_S); + } + if (vec->active && prio < active_prio) { + active_prio = prio; + } + } + } + + s->vectpending_is_s_banked = pending_is_s_banked; + s->vectpending = pend_irq; + s->vectpending_prio = pend_prio; + s->exception_prio = active_prio; + + trace_nvic_recompute_state_secure(s->vectpending, + s->vectpending_is_s_banked, + s->vectpending_prio, + s->exception_prio); } /* Recompute vectpending and exception_prio */ @@ -XXX,XX +XXX,XX @@ static void nvic_recompute_state(NVICState *s) int active_prio = NVIC_NOEXC_PRIO; int pend_irq = 0; + /* In theory we could write one function that handled both + * the "security extension present" and "not present"; however + * the security related changes significantly complicate the + * recomputation just by themselves and mixing both cases together + * would be even worse, so we retain a separate non-secure-only + * version for CPUs which don't implement the security extension. + */ + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { + nvic_recompute_state_secure(s); + return; + } + for (i = 1; i < s->num_irq; i++) { VecInfo *vec = &s->vectors[i]; @@ -XXX,XX +XXX,XX @@ static void nvic_recompute_state(NVICState *s) } if (active_prio > 0) { - active_prio &= nvic_gprio_mask(s); + active_prio &= nvic_gprio_mask(s, false); } if (pend_prio > 0) { - pend_prio &= nvic_gprio_mask(s); + pend_prio &= nvic_gprio_mask(s, false); } s->vectpending = pend_irq; @@ -XXX,XX +XXX,XX @@ static inline int nvic_exec_prio(NVICState *s) } else if (env->v7m.primask[env->v7m.secure]) { running = 0; } else if (env->v7m.basepri[env->v7m.secure] > 0) { - running = env->v7m.basepri[env->v7m.secure] & nvic_gprio_mask(s); + running = env->v7m.basepri[env->v7m.secure] & + nvic_gprio_mask(s, env->v7m.secure); } else { running = NVIC_NOEXC_PRIO; /* lower than any possible priority */ } diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_redist_send_sgi(uint32_t cpu, int irq) "GICv3 redistributor 0x%x pending S # hw/intc/armv7m_nvic.c nvic_recompute_state(int vectpending, int vectpending_prio, int exception_prio) "NVIC state recomputed: vectpending %d vectpending_prio %d exception_prio %d" +nvic_recompute_state_secure(int vectpending, bool vectpending_is_s_banked, int vectpending_prio, int exception_prio) "NVIC state recomputed: vectpending %d is_s_banked %d vectpending_prio %d exception_prio %d" nvic_set_prio(int irq, uint8_t prio) "NVIC set irq %d priority %d" nvic_irq_update(int vectpending, int pendprio, int exception_prio, int level) "NVIC vectpending %d pending prio %d exception_prio %d: setting irq line to %d" nvic_escalate_prio(int irq, int irqprio, int runprio) "NVIC escalating irq %d to HardFault: insufficient priority %d >= %d" -- 2.7.4 Make the armv7m_nvic_set_pending() and armv7m_nvic_clear_pending() functions take a bool indicating whether to pend the secure or non-secure version of a banked interrupt, and update the callsites accordingly. In most callsites we can simply pass the correct security state in; in a couple of cases we use TODO comments to indicate that we will return the code in a subsequent commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-10-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 14 ++++++++++- hw/intc/armv7m_nvic.c | 64 ++++++++++++++++++++++++++++++++++++++------------- target/arm/helper.c | 24 +++++++++++-------- hw/intc/trace-events | 4 ++-- 4 files changed, 77 insertions(+), 29 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool armv7m_nvic_can_take_pending_exception(void *opaque) return true; } #endif -void armv7m_nvic_set_pending(void *opaque, int irq); +/** + * armv7m_nvic_set_pending: mark the specified exception as pending + * @opaque: the NVIC + * @irq: the exception number to mark pending + * @secure: false for non-banked exceptions or for the nonsecure + * version of a banked exception, true for the secure version of a banked + * exception. + * + * Marks the specified exception as pending. Note that we will assert() + * if @secure is true and @irq does not specify one of the fixed set + * of architecturally banked exceptions. + */ +void armv7m_nvic_set_pending(void *opaque, int irq, bool secure); void armv7m_nvic_acknowledge_irq(void *opaque); /** * armv7m_nvic_complete_irq: complete specified interrupt or exception diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void nvic_irq_update(NVICState *s) qemu_set_irq(s->excpout, lvl); } -static void armv7m_nvic_clear_pending(void *opaque, int irq) +/** + * armv7m_nvic_clear_pending: mark the specified exception as not pending + * @opaque: the NVIC + * @irq: the exception number to mark as not pending + * @secure: false for non-banked exceptions or for the nonsecure + * version of a banked exception, true for the secure version of a banked + * exception. + * + * Marks the specified exception as not pending. Note that we will assert() + * if @secure is true and @irq does not specify one of the fixed set + * of architecturally banked exceptions. + */ +static void armv7m_nvic_clear_pending(void *opaque, int irq, bool secure) { NVICState *s = (NVICState *)opaque; VecInfo *vec; assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq); - vec = &s->vectors[irq]; - trace_nvic_clear_pending(irq, vec->enabled, vec->prio); + if (secure) { + assert(exc_is_banked(irq)); + vec = &s->sec_vectors[irq]; + } else { + vec = &s->vectors[irq]; + } + trace_nvic_clear_pending(irq, secure, vec->enabled, vec->prio); if (vec->pending) { vec->pending = 0; nvic_irq_update(s); } } -void armv7m_nvic_set_pending(void *opaque, int irq) +void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) { NVICState *s = (NVICState *)opaque; + bool banked = exc_is_banked(irq); VecInfo *vec; assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq); + assert(!secure || banked); - vec = &s->vectors[irq]; - trace_nvic_set_pending(irq, vec->enabled, vec->prio); + vec = (banked && secure) ? &s->sec_vectors[irq] : &s->vectors[irq]; + trace_nvic_set_pending(irq, secure, vec->enabled, vec->prio); if (irq >= ARMV7M_EXCP_HARD && irq < ARMV7M_EXCP_PENDSV) { /* If a synchronous exception is pending then it may be @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_set_pending(void *opaque, int irq) "(current priority %d)\n", irq, running); } - /* We can do the escalation, so we take HardFault instead */ + /* We can do the escalation, so we take HardFault instead. + * If BFHFNMINS is set then we escalate to the banked HF for + * the target security state of the original exception; otherwise + * we take a Secure HardFault. + */ irq = ARMV7M_EXCP_HARD; - vec = &s->vectors[irq]; + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY) && + (secure || + !(s->cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK))) { + vec = &s->sec_vectors[irq]; + } else { + vec = &s->vectors[irq]; + } + /* HF may be banked but there is only one shared HFSR */ s->cpu->env.v7m.hfsr |= R_V7M_HFSR_FORCED_MASK; } } @@ -XXX,XX +XXX,XX @@ static void set_irq_level(void *opaque, int n, int level) if (level != vec->level) { vec->level = level; if (level) { - armv7m_nvic_set_pending(s, n); + armv7m_nvic_set_pending(s, n, false); } } } @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, } case 0xd04: /* Interrupt Control State. */ if (value & (1 << 31)) { - armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI); + armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI, false); } if (value & (1 << 28)) { - armv7m_nvic_set_pending(s, ARMV7M_EXCP_PENDSV); + armv7m_nvic_set_pending(s, ARMV7M_EXCP_PENDSV, attrs.secure); } else if (value & (1 << 27)) { - armv7m_nvic_clear_pending(s, ARMV7M_EXCP_PENDSV); + armv7m_nvic_clear_pending(s, ARMV7M_EXCP_PENDSV, attrs.secure); } if (value & (1 << 26)) { - armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK); + armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK, attrs.secure); } else if (value & (1 << 25)) { - armv7m_nvic_clear_pending(s, ARMV7M_EXCP_SYSTICK); + armv7m_nvic_clear_pending(s, ARMV7M_EXCP_SYSTICK, attrs.secure); } break; case 0xd08: /* Vector Table Offset. */ @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, { int excnum = (value & 0x1ff) + NVIC_FIRST_IRQ; if (excnum < s->num_irq) { - armv7m_nvic_set_pending(s, excnum); + armv7m_nvic_set_pending(s, excnum, false); } break; } @@ -XXX,XX +XXX,XX @@ static void nvic_systick_trigger(void *opaque, int n, int level) /* SysTick just asked us to pend its exception. * (This is different from an external interrupt line's * behaviour.) + * TODO: when we implement the banked systicks we must make + * this pend the correct banked exception. */ - armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK); + armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK, false); } } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) * stack, directly take a usage fault on the current stack. */ env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK; - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); v7m_exception_taken(cpu, excret); qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " "stackframe: failed exception return integrity check\n"); @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) * exception return excret specified then this is a UsageFault. */ if (return_to_handler != arm_v7m_is_handler_mode(env)) { - /* Take an INVPC UsageFault by pushing the stack again. */ - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE); + /* Take an INVPC UsageFault by pushing the stack again. + * TODO: the v8M version of this code should target the + * background state for this exception. + */ + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, false); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK; v7m_push_stack(cpu); v7m_exception_taken(cpu, excret); @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) handle it. */ switch (cs->exception_index) { case EXCP_UDEF: - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_UNDEFINSTR_MASK; break; case EXCP_NOCP: - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_NOCP_MASK; break; case EXCP_INVSTATE: - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVSTATE_MASK; break; case EXCP_SWI: /* The PC already points to the next instruction. */ - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); break; case EXCP_PREFETCH_ABORT: case EXCP_DATA_ABORT: @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) env->v7m.bfar); break; } - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS, false); break; default: /* All other FSR values are either MPU faults or "can't happen @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) env->v7m.mmfar[env->v7m.secure]); break; } - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM, + env->v7m.secure); break; } break; @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) return; } } - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_DEBUG); + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_DEBUG, false); break; case EXCP_IRQ: break; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ nvic_set_prio(int irq, uint8_t prio) "NVIC set irq %d priority %d" nvic_irq_update(int vectpending, int pendprio, int exception_prio, int level) "NVIC vectpending %d pending prio %d exception_prio %d: setting irq line to %d" nvic_escalate_prio(int irq, int irqprio, int runprio) "NVIC escalating irq %d to HardFault: insufficient priority %d >= %d" nvic_escalate_disabled(int irq) "NVIC escalating irq %d to HardFault: disabled" -nvic_set_pending(int irq, int en, int prio) "NVIC set pending irq %d (enabled: %d priority %d)" -nvic_clear_pending(int irq, int en, int prio) "NVIC clear pending irq %d (enabled: %d priority %d)" +nvic_set_pending(int irq, bool secure, int en, int prio) "NVIC set pending irq %d secure-bank %d (enabled: %d priority %d)" +nvic_clear_pending(int irq, bool secure, int en, int prio) "NVIC clear pending irq %d secure-bank %d (enabled: %d priority %d)" nvic_set_pending_level(int irq) "NVIC set pending: irq %d higher prio than vectpending: setting irq line to 1" nvic_acknowledge_irq(int irq, int prio) "NVIC acknowledge IRQ: %d now active (prio %d)" nvic_complete_irq(int irq) "NVIC complete IRQ %d" -- 2.7.4 Make the set_prio() function take a bool indicating whether to pend the secure or non-secure version of a banked interrupt, and use this to implement the correct banking semantics for the SHPR registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-11-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++----- hw/intc/trace-events | 2 +- 2 files changed, 88 insertions(+), 10 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ int armv7m_nvic_raw_execution_priority(void *opaque) return s->exception_prio; } -/* caller must call nvic_irq_update() after this */ -static void set_prio(NVICState *s, unsigned irq, uint8_t prio) +/* caller must call nvic_irq_update() after this. + * secure indicates the bank to use for banked exceptions (we assert if + * we are passed secure=true for a non-banked exception). + */ +static void set_prio(NVICState *s, unsigned irq, bool secure, uint8_t prio) { assert(irq > ARMV7M_EXCP_NMI); /* only use for configurable prios */ assert(irq < s->num_irq); - s->vectors[irq].prio = prio; + if (secure) { + assert(exc_is_banked(irq)); + s->sec_vectors[irq].prio = prio; + } else { + s->vectors[irq].prio = prio; + } + + trace_nvic_set_prio(irq, secure, prio); +} + +/* Return the current raw priority register value. + * secure indicates the bank to use for banked exceptions (we assert if + * we are passed secure=true for a non-banked exception). + */ +static int get_prio(NVICState *s, unsigned irq, bool secure) +{ + assert(irq > ARMV7M_EXCP_NMI); /* only use for configurable prios */ + assert(irq < s->num_irq); - trace_nvic_set_prio(irq, prio); + if (secure) { + assert(exc_is_banked(irq)); + return s->sec_vectors[irq].prio; + } else { + return s->vectors[irq].prio; + } } /* Recompute state and assert irq line accordingly. @@ -XXX,XX +XXX,XX @@ static bool nvic_user_access_ok(NVICState *s, hwaddr offset, MemTxAttrs attrs) } } +static int shpr_bank(NVICState *s, int exc, MemTxAttrs attrs) +{ + /* Behaviour for the SHPR register field for this exception: + * return M_REG_NS to use the nonsecure vector (including for + * non-banked exceptions), M_REG_S for the secure version of + * a banked exception, and -1 if this field should RAZ/WI. + */ + switch (exc) { + case ARMV7M_EXCP_MEM: + case ARMV7M_EXCP_USAGE: + case ARMV7M_EXCP_SVC: + case ARMV7M_EXCP_PENDSV: + case ARMV7M_EXCP_SYSTICK: + /* Banked exceptions */ + return attrs.secure; + case ARMV7M_EXCP_BUS: + /* Not banked, RAZ/WI from nonsecure if BFHFNMINS is zero */ + if (!attrs.secure && + !(s->cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK)) { + return -1; + } + return M_REG_NS; + case ARMV7M_EXCP_SECURE: + /* Not banked, RAZ/WI from nonsecure */ + if (!attrs.secure) { + return -1; + } + return M_REG_NS; + case ARMV7M_EXCP_DEBUG: + /* Not banked. TODO should RAZ/WI if DEMCR.SDME is set */ + return M_REG_NS; + case 8 ... 10: + case 13: + /* RES0 */ + return -1; + default: + /* Not reachable due to decode of SHPR register addresses */ + g_assert_not_reached(); + } +} + static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, uint64_t *data, unsigned size, MemTxAttrs attrs) @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, } } break; - case 0xd18 ... 0xd23: /* System Handler Priority. */ + case 0xd18 ... 0xd23: /* System Handler Priority (SHPR1, SHPR2, SHPR3) */ val = 0; for (i = 0; i < size; i++) { - val |= s->vectors[(offset - 0xd14) + i].prio << (i * 8); + unsigned hdlidx = (offset - 0xd14) + i; + int sbank = shpr_bank(s, hdlidx, attrs); + + if (sbank < 0) { + continue; + } + val = deposit32(val, i * 8, 8, get_prio(s, hdlidx, sbank)); } break; case 0xfe0 ... 0xfff: /* ID. */ @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, for (i = 0; i < size && startvec + i < s->num_irq; i++) { if (attrs.secure || s->itns[startvec + i]) { - set_prio(s, startvec + i, (value >> (i * 8)) & 0xff); + set_prio(s, startvec + i, false, (value >> (i * 8)) & 0xff); } } nvic_irq_update(s); return MEMTX_OK; - case 0xd18 ... 0xd23: /* System Handler Priority. */ + case 0xd18 ... 0xd23: /* System Handler Priority (SHPR1, SHPR2, SHPR3) */ for (i = 0; i < size; i++) { unsigned hdlidx = (offset - 0xd14) + i; - set_prio(s, hdlidx, (value >> (i * 8)) & 0xff); + int newprio = extract32(value, i * 8, 8); + int sbank = shpr_bank(s, hdlidx, attrs); + + if (sbank < 0) { + continue; + } + set_prio(s, hdlidx, sbank, newprio); } nvic_irq_update(s); return MEMTX_OK; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_redist_send_sgi(uint32_t cpu, int irq) "GICv3 redistributor 0x%x pending S # hw/intc/armv7m_nvic.c nvic_recompute_state(int vectpending, int vectpending_prio, int exception_prio) "NVIC state recomputed: vectpending %d vectpending_prio %d exception_prio %d" nvic_recompute_state_secure(int vectpending, bool vectpending_is_s_banked, int vectpending_prio, int exception_prio) "NVIC state recomputed: vectpending %d is_s_banked %d vectpending_prio %d exception_prio %d" -nvic_set_prio(int irq, uint8_t prio) "NVIC set irq %d priority %d" +nvic_set_prio(int irq, bool secure, uint8_t prio) "NVIC set irq %d secure-bank %d priority %d" nvic_irq_update(int vectpending, int pendprio, int exception_prio, int level) "NVIC vectpending %d pending prio %d exception_prio %d: setting irq line to %d" nvic_escalate_prio(int irq, int irqprio, int runprio) "NVIC escalating irq %d to HardFault: insufficient priority %d >= %d" nvic_escalate_disabled(int irq) "NVIC escalating irq %d to HardFault: disabled" -- 2.7.4 In armv7m_nvic_set_pending() we have to compare the priority of an exception against the execution priority to decide whether it needs to be escalated to HardFault. In the specification this is a comparison against the exception's group priority; for v7M we implemented it as a comparison against the raw exception priority because the two comparisons will always give the same answer. For v8M the existence of AIRCR.PRIS and the possibility of different PRIGROUP values for secure and nonsecure exceptions means we need to explicitly calculate the vector's group priority for this check. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-12-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) int running = nvic_exec_prio(s); bool escalate = false; - if (vec->prio >= running) { + if (exc_group_prio(s, vec->prio, secure) >= running) { trace_nvic_escalate_prio(irq, vec->prio, running); escalate = true; } else if (!vec->enabled) { -- 2.7.4 When escalating to HardFault, we must go into Lockup if we can't take the synchronous HardFault because the current execution priority is already at or below the priority of HardFault. In v7M HF is always priority -1 so a simple < 0 comparison sufficed; in v8M the priority of HardFault can vary depending on whether it is a Secure or NonSecure HardFault, so we must check against the priority of the HardFault exception vector we're about to use. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-13-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) } if (escalate) { - if (running < 0) { - /* We want to escalate to HardFault but we can't take a - * synchronous HardFault at this point either. This is a - * Lockup condition due to a guest bug. We don't model - * Lockup, so report via cpu_abort() instead. - */ - cpu_abort(&s->cpu->parent_obj, - "Lockup: can't escalate %d to HardFault " - "(current priority %d)\n", irq, running); - } - /* We can do the escalation, so we take HardFault instead. + /* We need to escalate this exception to a synchronous HardFault. * If BFHFNMINS is set then we escalate to the banked HF for * the target security state of the original exception; otherwise * we take a Secure HardFault. @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) } else { vec = &s->vectors[irq]; } + if (running <= vec->prio) { + /* We want to escalate to HardFault but we can't take the + * synchronous HardFault at this point either. This is a + * Lockup condition due to a guest bug. We don't model + * Lockup, so report via cpu_abort() instead. + */ + cpu_abort(&s->cpu->parent_obj, + "Lockup: can't escalate %d to HardFault " + "(current priority %d)\n", irq, running); + } + /* HF may be banked but there is only one shared HFSR */ s->cpu->env.v7m.hfsr |= R_V7M_HFSR_FORCED_MASK; } -- 2.7.4 In v7M, the fixed-priority exceptions are: Reset: -3 NMI: -2 HardFault: -1 In v8M, this changes because Secure HardFault may need to be prioritised above NMI: Reset: -4 Secure HardFault if AIRCR.BFHFNMINS == 1: -3 NMI: -2 Secure HardFault if AIRCR.BFHFNMINS == 0: -1 NonSecure HardFault: -1 Make these changes, including support for changing the priority of Secure HardFault as AIRCR.BFHFNMINS changes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-14-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, (R_V7M_AIRCR_SYSRESETREQS_MASK | R_V7M_AIRCR_BFHFNMINS_MASK | R_V7M_AIRCR_PRIS_MASK); + /* BFHFNMINS changes the priority of Secure HardFault */ + if (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) { + s->sec_vectors[ARMV7M_EXCP_HARD].prio = -3; + } else { + s->sec_vectors[ARMV7M_EXCP_HARD].prio = -1; + } } nvic_irq_update(s); } @@ -XXX,XX +XXX,XX @@ static int nvic_post_load(void *opaque, int version_id) { NVICState *s = opaque; unsigned i; + int resetprio; /* Check for out of range priority settings */ - if (s->vectors[ARMV7M_EXCP_RESET].prio != -3 || + resetprio = arm_feature(&s->cpu->env, ARM_FEATURE_V8) ? -4 : -3; + + if (s->vectors[ARMV7M_EXCP_RESET].prio != resetprio || s->vectors[ARMV7M_EXCP_NMI].prio != -2 || s->vectors[ARMV7M_EXCP_HARD].prio != -1) { return 1; @@ -XXX,XX +XXX,XX @@ static int nvic_security_post_load(void *opaque, int version_id) int i; /* Check for out of range priority settings */ - if (s->sec_vectors[ARMV7M_EXCP_HARD].prio != -1) { + if (s->sec_vectors[ARMV7M_EXCP_HARD].prio != -1 + && s->sec_vectors[ARMV7M_EXCP_HARD].prio != -3) { + /* We can't cross-check against AIRCR.BFHFNMINS as we don't know + * if the CPU state has been migrated yet; a mismatch won't + * cause the emulation to blow up, though. + */ return 1; } for (i = ARMV7M_EXCP_MEM; i < ARRAY_SIZE(s->sec_vectors); i++) { @@ -XXX,XX +XXX,XX @@ static Property props_nvic[] = { static void armv7m_nvic_reset(DeviceState *dev) { + int resetprio; NVICState *s = NVIC(dev); s->vectors[ARMV7M_EXCP_NMI].enabled = 1; @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->vectors[ARMV7M_EXCP_PENDSV].enabled = 1; s->vectors[ARMV7M_EXCP_SYSTICK].enabled = 1; - s->vectors[ARMV7M_EXCP_RESET].prio = -3; + resetprio = arm_feature(&s->cpu->env, ARM_FEATURE_V8) ? -4 : -3; + s->vectors[ARMV7M_EXCP_RESET].prio = resetprio; s->vectors[ARMV7M_EXCP_NMI].prio = -2; s->vectors[ARMV7M_EXCP_HARD].prio = -1; -- 2.7.4 If AIRCR.BFHFNMINS is clear, then although NonSecure HardFault can still be pended via SHCSR.HARDFAULTPENDED it mustn't actually preempt execution. The simple way to achieve this is to clear the enable bit for it, since the enable bit isn't guest visible. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-15-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, (R_V7M_AIRCR_SYSRESETREQS_MASK | R_V7M_AIRCR_BFHFNMINS_MASK | R_V7M_AIRCR_PRIS_MASK); - /* BFHFNMINS changes the priority of Secure HardFault */ + /* BFHFNMINS changes the priority of Secure HardFault, and + * allows a pending Non-secure HardFault to preempt (which + * we implement by marking it enabled). + */ if (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) { s->sec_vectors[ARMV7M_EXCP_HARD].prio = -3; + s->vectors[ARMV7M_EXCP_HARD].enabled = 1; } else { s->sec_vectors[ARMV7M_EXCP_HARD].prio = -1; + s->vectors[ARMV7M_EXCP_HARD].enabled = 0; } } nvic_irq_update(s); @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) NVICState *s = NVIC(dev); s->vectors[ARMV7M_EXCP_NMI].enabled = 1; - s->vectors[ARMV7M_EXCP_HARD].enabled = 1; /* MEM, BUS, and USAGE are enabled through * the System Handler Control register */ @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) /* AIRCR.BFHFNMINS resets to 0 so Secure HF is priority -1 (R_CMTC) */ s->sec_vectors[ARMV7M_EXCP_HARD].prio = -1; + /* If AIRCR.BFHFNMINS is 0 then NS HF is (effectively) disabled */ + s->vectors[ARMV7M_EXCP_HARD].enabled = 0; + } else { + s->vectors[ARMV7M_EXCP_HARD].enabled = 1; } /* Strictly speaking the reset handler should be enabled. -- 2.7.4 Update nvic_exec_prio() to support the v8M changes: * BASEPRI, FAULTMASK and PRIMASK are all banked * AIRCR.PRIS can affect NS priorities * AIRCR.BFHFNMINS affects FAULTMASK behaviour These changes mean that it's no longer possible to definitely say that if FAULTMASK is set it overrides PRIMASK, and if PRIMASK is set it overrides BASEPRI (since if PRIMASK_NS is set and AIRCR.PRIS is set then whether that 0x80 priority should take effect or the priority in BASEPRI_S depends on the value of BASEPRI_S, for instance). So we switch to the same approach used by the pseudocode of working through BASEPRI, PRIMASK and FAULTMASK and overriding the previous values if needed. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-16-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 51 ++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 42 insertions(+), 9 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void nvic_recompute_state(NVICState *s) static inline int nvic_exec_prio(NVICState *s) { CPUARMState *env = &s->cpu->env; - int running; + int running = NVIC_NOEXC_PRIO; - if (env->v7m.faultmask[env->v7m.secure]) { - running = -1; - } else if (env->v7m.primask[env->v7m.secure]) { + if (env->v7m.basepri[M_REG_NS] > 0) { + running = exc_group_prio(s, env->v7m.basepri[M_REG_NS], M_REG_NS); + } + + if (env->v7m.basepri[M_REG_S] > 0) { + int basepri = exc_group_prio(s, env->v7m.basepri[M_REG_S], M_REG_S); + if (running > basepri) { + running = basepri; + } + } + + if (env->v7m.primask[M_REG_NS]) { + if (env->v7m.aircr & R_V7M_AIRCR_PRIS_MASK) { + if (running > NVIC_NS_PRIO_LIMIT) { + running = NVIC_NS_PRIO_LIMIT; + } + } else { + running = 0; + } + } + + if (env->v7m.primask[M_REG_S]) { running = 0; - } else if (env->v7m.basepri[env->v7m.secure] > 0) { - running = env->v7m.basepri[env->v7m.secure] & - nvic_gprio_mask(s, env->v7m.secure); - } else { - running = NVIC_NOEXC_PRIO; /* lower than any possible priority */ } + + if (env->v7m.faultmask[M_REG_NS]) { + if (env->v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) { + running = -1; + } else { + if (env->v7m.aircr & R_V7M_AIRCR_PRIS_MASK) { + if (running > NVIC_NS_PRIO_LIMIT) { + running = NVIC_NS_PRIO_LIMIT; + } + } else { + running = 0; + } + } + } + + if (env->v7m.faultmask[M_REG_S]) { + running = (env->v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) ? -3 : -1; + } + /* consider priority of active handler */ return MIN(running, s->exception_prio); } -- 2.7.4 Now that we have a banked FAULTMASK register and banked exceptions, we can implement the correct check in cpu_mmu_index() for whether the MPU_CTRL.HFNMIENA bit's effect should apply. This bit causes handlers which have requested a negative execution priority to run with the MPU disabled. In v8M the test has to check this for the current security state and so takes account of banking. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-17-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 21 ++++++++++++++++----- hw/intc/armv7m_nvic.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+), 5 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ int armv7m_nvic_complete_irq(void *opaque, int irq); * (v8M ARM ARM I_PKLD.) */ int armv7m_nvic_raw_execution_priority(void *opaque); +/** + * armv7m_nvic_neg_prio_requested: return true if the requested execution + * priority is negative for the specified security state. + * @opaque: the NVIC + * @secure: the security state to test + * This corresponds to the pseudocode IsReqExecPriNeg(). + */ +#ifndef CONFIG_USER_ONLY +bool armv7m_nvic_neg_prio_requested(void *opaque, bool secure); +#else +static inline bool armv7m_nvic_neg_prio_requested(void *opaque, bool secure) +{ + return false; +} +#endif /* Interface for defining coprocessor registers. * Registers are defined in tables of arm_cp_reginfo structs @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) if (arm_feature(env, ARM_FEATURE_M)) { ARMMMUIdx mmu_idx = el == 0 ? ARMMMUIdx_MUser : ARMMMUIdx_MPriv; - /* Execution priority is negative if FAULTMASK is set or - * we're in a HardFault or NMI handler. - */ - if ((env->v7m.exception > 0 && env->v7m.exception <= 3) - || env->v7m.faultmask[env->v7m.secure]) { + if (armv7m_nvic_neg_prio_requested(env->nvic, env->v7m.secure)) { mmu_idx = ARMMMUIdx_MNegPri; } diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static inline int nvic_exec_prio(NVICState *s) return MIN(running, s->exception_prio); } +bool armv7m_nvic_neg_prio_requested(void *opaque, bool secure) +{ + /* Return true if the requested execution priority is negative + * for the specified security state, ie that security state + * has an active NMI or HardFault or has set its FAULTMASK. + * Note that this is not the same as whether the execution + * priority is actually negative (for instance AIRCR.PRIS may + * mean we don't allow FAULTMASK_NS to actually make the execution + * priority negative). Compare pseudocode IsReqExcPriNeg(). + */ + NVICState *s = opaque; + + if (s->cpu->env.v7m.faultmask[secure]) { + return true; + } + + if (secure ? s->sec_vectors[ARMV7M_EXCP_HARD].active : + s->vectors[ARMV7M_EXCP_HARD].active) { + return true; + } + + if (s->vectors[ARMV7M_EXCP_NMI].active && + exc_targets_secure(s, ARMV7M_EXCP_NMI) == secure) { + return true; + } + + return false; +} + bool armv7m_nvic_can_take_pending_exception(void *opaque) { NVICState *s = opaque; -- 2.7.4 The ICSR NVIC register is banked for v8M. This doesn't require any new state, but it does mean that some bits are controlled by BFHNFNMINS and some bits must work with the correct banked exception. There is also a new in v8M PENDNMICLR bit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-18-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 45 ++++++++++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 13 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) } case 0xd00: /* CPUID Base. */ return cpu->midr; - case 0xd04: /* Interrupt Control State. */ + case 0xd04: /* Interrupt Control State (ICSR) */ /* VECTACTIVE */ val = cpu->env.v7m.exception; /* VECTPENDING */ @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) if (nvic_rettobase(s)) { val |= (1 << 11); } - /* PENDSTSET */ - if (s->vectors[ARMV7M_EXCP_SYSTICK].pending) { - val |= (1 << 26); - } - /* PENDSVSET */ - if (s->vectors[ARMV7M_EXCP_PENDSV].pending) { - val |= (1 << 28); + if (attrs.secure) { + /* PENDSTSET */ + if (s->sec_vectors[ARMV7M_EXCP_SYSTICK].pending) { + val |= (1 << 26); + } + /* PENDSVSET */ + if (s->sec_vectors[ARMV7M_EXCP_PENDSV].pending) { + val |= (1 << 28); + } + } else { + /* PENDSTSET */ + if (s->vectors[ARMV7M_EXCP_SYSTICK].pending) { + val |= (1 << 26); + } + /* PENDSVSET */ + if (s->vectors[ARMV7M_EXCP_PENDSV].pending) { + val |= (1 << 28); + } } /* NMIPENDSET */ - if (s->vectors[ARMV7M_EXCP_NMI].pending) { + if ((cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) && + s->vectors[ARMV7M_EXCP_NMI].pending) { val |= (1 << 31); } - /* ISRPREEMPT not implemented */ + /* ISRPREEMPT: RES0 when halting debug not implemented */ + /* STTNS: RES0 for the Main Extension */ return val; case 0xd08: /* Vector Table Offset. */ return cpu->env.v7m.vecbase[attrs.secure]; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, nvic_irq_update(s); break; } - case 0xd04: /* Interrupt Control State. */ - if (value & (1 << 31)) { - armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI, false); + case 0xd04: /* Interrupt Control State (ICSR) */ + if (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) { + if (value & (1 << 31)) { + armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI, false); + } else if (value & (1 << 30) && + arm_feature(&cpu->env, ARM_FEATURE_V8)) { + /* PENDNMICLR didn't exist in v7M */ + armv7m_nvic_clear_pending(s, ARMV7M_EXCP_NMI, false); + } } if (value & (1 << 28)) { armv7m_nvic_set_pending(s, ARMV7M_EXCP_PENDSV, attrs.secure); -- 2.7.4 Handle banking of SHCSR: some register bits are banked between Secure and Non-Secure, and some are only accessible to Secure. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-19-git-send-email-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 221 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 169 insertions(+), 52 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) val = cpu->env.v7m.ccr[attrs.secure]; val |= cpu->env.v7m.ccr[M_REG_NS] & R_V7M_CCR_BFHFNMIGN_MASK; return val; - case 0xd24: /* System Handler Status. */ + case 0xd24: /* System Handler Control and State (SHCSR) */ val = 0; - if (s->vectors[ARMV7M_EXCP_MEM].active) { - val |= (1 << 0); - } - if (s->vectors[ARMV7M_EXCP_BUS].active) { - val |= (1 << 1); - } - if (s->vectors[ARMV7M_EXCP_USAGE].active) { - val |= (1 << 3); + if (attrs.secure) { + if (s->sec_vectors[ARMV7M_EXCP_MEM].active) { + val |= (1 << 0); + } + if (s->sec_vectors[ARMV7M_EXCP_HARD].active) { + val |= (1 << 2); + } + if (s->sec_vectors[ARMV7M_EXCP_USAGE].active) { + val |= (1 << 3); + } + if (s->sec_vectors[ARMV7M_EXCP_SVC].active) { + val |= (1 << 7); + } + if (s->sec_vectors[ARMV7M_EXCP_PENDSV].active) { + val |= (1 << 10); + } + if (s->sec_vectors[ARMV7M_EXCP_SYSTICK].active) { + val |= (1 << 11); + } + if (s->sec_vectors[ARMV7M_EXCP_USAGE].pending) { + val |= (1 << 12); + } + if (s->sec_vectors[ARMV7M_EXCP_MEM].pending) { + val |= (1 << 13); + } + if (s->sec_vectors[ARMV7M_EXCP_SVC].pending) { + val |= (1 << 15); + } + if (s->sec_vectors[ARMV7M_EXCP_MEM].enabled) { + val |= (1 << 16); + } + if (s->sec_vectors[ARMV7M_EXCP_USAGE].enabled) { + val |= (1 << 18); + } + if (s->sec_vectors[ARMV7M_EXCP_HARD].pending) { + val |= (1 << 21); + } + /* SecureFault is not banked but is always RAZ/WI to NS */ + if (s->vectors[ARMV7M_EXCP_SECURE].active) { + val |= (1 << 4); + } + if (s->vectors[ARMV7M_EXCP_SECURE].enabled) { + val |= (1 << 19); + } + if (s->vectors[ARMV7M_EXCP_SECURE].pending) { + val |= (1 << 20); + } + } else { + if (s->vectors[ARMV7M_EXCP_MEM].active) { + val |= (1 << 0); + } + if (arm_feature(&cpu->env, ARM_FEATURE_V8)) { + /* HARDFAULTACT, HARDFAULTPENDED not present in v7M */ + if (s->vectors[ARMV7M_EXCP_HARD].active) { + val |= (1 << 2); + } + if (s->vectors[ARMV7M_EXCP_HARD].pending) { + val |= (1 << 21); + } + } + if (s->vectors[ARMV7M_EXCP_USAGE].active) { + val |= (1 << 3); + } + if (s->vectors[ARMV7M_EXCP_SVC].active) { + val |= (1 << 7); + } + if (s->vectors[ARMV7M_EXCP_PENDSV].active) { + val |= (1 << 10); + } + if (s->vectors[ARMV7M_EXCP_SYSTICK].active) { + val |= (1 << 11); + } + if (s->vectors[ARMV7M_EXCP_USAGE].pending) { + val |= (1 << 12); + } + if (s->vectors[ARMV7M_EXCP_MEM].pending) { + val |= (1 << 13); + } + if (s->vectors[ARMV7M_EXCP_SVC].pending) { + val |= (1 << 15); + } + if (s->vectors[ARMV7M_EXCP_MEM].enabled) { + val |= (1 << 16); + } + if (s->vectors[ARMV7M_EXCP_USAGE].enabled) { + val |= (1 << 18); + } } - if (s->vectors[ARMV7M_EXCP_SVC].active) { - val |= (1 << 7); + if (attrs.secure || (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK)) { + if (s->vectors[ARMV7M_EXCP_BUS].active) { + val |= (1 << 1); + } + if (s->vectors[ARMV7M_EXCP_BUS].pending) { + val |= (1 << 14); + } + if (s->vectors[ARMV7M_EXCP_BUS].enabled) { + val |= (1 << 17); + } + if (arm_feature(&cpu->env, ARM_FEATURE_V8) && + s->vectors[ARMV7M_EXCP_NMI].active) { + /* NMIACT is not present in v7M */ + val |= (1 << 5); + } } + + /* TODO: this is RAZ/WI from NS if DEMCR.SDME is set */ if (s->vectors[ARMV7M_EXCP_DEBUG].active) { val |= (1 << 8); } - if (s->vectors[ARMV7M_EXCP_PENDSV].active) { - val |= (1 << 10); - } - if (s->vectors[ARMV7M_EXCP_SYSTICK].active) { - val |= (1 << 11); - } - if (s->vectors[ARMV7M_EXCP_USAGE].pending) { - val |= (1 << 12); - } - if (s->vectors[ARMV7M_EXCP_MEM].pending) { - val |= (1 << 13); - } - if (s->vectors[ARMV7M_EXCP_BUS].pending) { - val |= (1 << 14); - } - if (s->vectors[ARMV7M_EXCP_SVC].pending) { - val |= (1 << 15); - } - if (s->vectors[ARMV7M_EXCP_MEM].enabled) { - val |= (1 << 16); - } - if (s->vectors[ARMV7M_EXCP_BUS].enabled) { - val |= (1 << 17); - } - if (s->vectors[ARMV7M_EXCP_USAGE].enabled) { - val |= (1 << 18); - } return val; case 0xd28: /* Configurable Fault Status. */ /* The BFSR bits [15:8] are shared between security states @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, cpu->env.v7m.ccr[attrs.secure] = value; break; - case 0xd24: /* System Handler Control. */ - s->vectors[ARMV7M_EXCP_MEM].active = (value & (1 << 0)) != 0; - s->vectors[ARMV7M_EXCP_BUS].active = (value & (1 << 1)) != 0; - s->vectors[ARMV7M_EXCP_USAGE].active = (value & (1 << 3)) != 0; - s->vectors[ARMV7M_EXCP_SVC].active = (value & (1 << 7)) != 0; + case 0xd24: /* System Handler Control and State (SHCSR) */ + if (attrs.secure) { + s->sec_vectors[ARMV7M_EXCP_MEM].active = (value & (1 << 0)) != 0; + /* Secure HardFault active bit cannot be written */ + s->sec_vectors[ARMV7M_EXCP_USAGE].active = (value & (1 << 3)) != 0; + s->sec_vectors[ARMV7M_EXCP_SVC].active = (value & (1 << 7)) != 0; + s->sec_vectors[ARMV7M_EXCP_PENDSV].active = + (value & (1 << 10)) != 0; + s->sec_vectors[ARMV7M_EXCP_SYSTICK].active = + (value & (1 << 11)) != 0; + s->sec_vectors[ARMV7M_EXCP_USAGE].pending = + (value & (1 << 12)) != 0; + s->sec_vectors[ARMV7M_EXCP_MEM].pending = (value & (1 << 13)) != 0; + s->sec_vectors[ARMV7M_EXCP_SVC].pending = (value & (1 << 15)) != 0; + s->sec_vectors[ARMV7M_EXCP_MEM].enabled = (value & (1 << 16)) != 0; + s->sec_vectors[ARMV7M_EXCP_BUS].enabled = (value & (1 << 17)) != 0; + s->sec_vectors[ARMV7M_EXCP_USAGE].enabled = + (value & (1 << 18)) != 0; + /* SecureFault not banked, but RAZ/WI to NS */ + s->vectors[ARMV7M_EXCP_SECURE].active = (value & (1 << 4)) != 0; + s->vectors[ARMV7M_EXCP_SECURE].enabled = (value & (1 << 19)) != 0; + s->vectors[ARMV7M_EXCP_SECURE].pending = (value & (1 << 20)) != 0; + } else { + s->vectors[ARMV7M_EXCP_MEM].active = (value & (1 << 0)) != 0; + if (arm_feature(&cpu->env, ARM_FEATURE_V8)) { + /* HARDFAULTPENDED is not present in v7M */ + s->vectors[ARMV7M_EXCP_HARD].pending = (value & (1 << 21)) != 0; + } + s->vectors[ARMV7M_EXCP_USAGE].active = (value & (1 << 3)) != 0; + s->vectors[ARMV7M_EXCP_SVC].active = (value & (1 << 7)) != 0; + s->vectors[ARMV7M_EXCP_PENDSV].active = (value & (1 << 10)) != 0; + s->vectors[ARMV7M_EXCP_SYSTICK].active = (value & (1 << 11)) != 0; + s->vectors[ARMV7M_EXCP_USAGE].pending = (value & (1 << 12)) != 0; + s->vectors[ARMV7M_EXCP_MEM].pending = (value & (1 << 13)) != 0; + s->vectors[ARMV7M_EXCP_SVC].pending = (value & (1 << 15)) != 0; + s->vectors[ARMV7M_EXCP_MEM].enabled = (value & (1 << 16)) != 0; + s->vectors[ARMV7M_EXCP_USAGE].enabled = (value & (1 << 18)) != 0; + } + if (attrs.secure || (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK)) { + s->vectors[ARMV7M_EXCP_BUS].active = (value & (1 << 1)) != 0; + s->vectors[ARMV7M_EXCP_BUS].pending = (value & (1 << 14)) != 0; + s->vectors[ARMV7M_EXCP_BUS].enabled = (value & (1 << 17)) != 0; + } + /* NMIACT can only be written if the write is of a zero, with + * BFHFNMINS 1, and by the CPU in secure state via the NS alias. + */ + if (!attrs.secure && cpu->env.v7m.secure && + (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) && + (value & (1 << 5)) == 0) { + s->vectors[ARMV7M_EXCP_NMI].active = 0; + } + /* HARDFAULTACT can only be written if the write is of a zero + * to the non-secure HardFault state by the CPU in secure state. + * The only case where we can be targeting the non-secure HF state + * when in secure state is if this is a write via the NS alias + * and BFHFNMINS is 1. + */ + if (!attrs.secure && cpu->env.v7m.secure && + (cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK) && + (value & (1 << 2)) == 0) { + s->vectors[ARMV7M_EXCP_HARD].active = 0; + } + + /* TODO: this is RAZ/WI from NS if DEMCR.SDME is set */ s->vectors[ARMV7M_EXCP_DEBUG].active = (value & (1 << 8)) != 0; - s->vectors[ARMV7M_EXCP_PENDSV].active = (value & (1 << 10)) != 0; - s->vectors[ARMV7M_EXCP_SYSTICK].active = (value & (1 << 11)) != 0; - s->vectors[ARMV7M_EXCP_USAGE].pending = (value & (1 << 12)) != 0; - s->vectors[ARMV7M_EXCP_MEM].pending = (value & (1 << 13)) != 0; - s->vectors[ARMV7M_EXCP_BUS].pending = (value & (1 << 14)) != 0; - s->vectors[ARMV7M_EXCP_SVC].pending = (value & (1 << 15)) != 0; - s->vectors[ARMV7M_EXCP_MEM].enabled = (value & (1 << 16)) != 0; - s->vectors[ARMV7M_EXCP_BUS].enabled = (value & (1 << 17)) != 0; - s->vectors[ARMV7M_EXCP_USAGE].enabled = (value & (1 << 18)) != 0; nvic_irq_update(s); break; case 0xd28: /* Configurable Fault Status. */ -- 2.7.4 Update armv7m_nvic_acknowledge_irq() and armv7m_nvic_complete_irq() to handle banked exceptions: * acknowledge needs to use the correct vector, which may be in sec_vectors[] * acknowledge needs to return to its caller whether the exception should be taken to secure or non-secure state * complete needs its caller to tell it whether the exception being completed is a secure one or not Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505240046-11454-20-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 15 +++++++++++++-- hw/intc/armv7m_nvic.c | 26 ++++++++++++++++++++------ target/arm/helper.c | 8 +++++--- hw/intc/trace-events | 4 ++-- 4 files changed, 40 insertions(+), 13 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool armv7m_nvic_can_take_pending_exception(void *opaque) * of architecturally banked exceptions. */ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure); -void armv7m_nvic_acknowledge_irq(void *opaque); +/** + * armv7m_nvic_acknowledge_irq: make highest priority pending exception active + * @opaque: the NVIC + * + * Move the current highest priority pending exception from the pending + * state to the active state, and update v7m.exception to indicate that + * it is the exception currently being handled. + * + * Returns: true if exception should be taken to Secure state, false for NS + */ +bool armv7m_nvic_acknowledge_irq(void *opaque); /** * armv7m_nvic_complete_irq: complete specified interrupt or exception * @opaque: the NVIC * @irq: the exception number to complete + * @secure: true if this exception was secure * * Returns: -1 if the irq was not active * 1 if completing this irq brought us back to base (no active irqs) * 0 if there is still an irq active after this one was completed * (Ignoring -1, this is the same as the RETTOBASE value before completion.) */ -int armv7m_nvic_complete_irq(void *opaque, int irq); +int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure); /** * armv7m_nvic_raw_execution_priority: return the raw execution priority * @opaque: the NVIC diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_set_pending(void *opaque, int irq, bool secure) } /* Make pending IRQ active. */ -void armv7m_nvic_acknowledge_irq(void *opaque) +bool armv7m_nvic_acknowledge_irq(void *opaque) { NVICState *s = (NVICState *)opaque; CPUARMState *env = &s->cpu->env; const int pending = s->vectpending; const int running = nvic_exec_prio(s); VecInfo *vec; + bool targets_secure; assert(pending > ARMV7M_EXCP_RESET && pending < s->num_irq); - vec = &s->vectors[pending]; + if (s->vectpending_is_s_banked) { + vec = &s->sec_vectors[pending]; + targets_secure = true; + } else { + vec = &s->vectors[pending]; + targets_secure = !exc_is_banked(s->vectpending) && + exc_targets_secure(s, s->vectpending); + } assert(vec->enabled); assert(vec->pending); assert(s->vectpending_prio < running); - trace_nvic_acknowledge_irq(pending, s->vectpending_prio); + trace_nvic_acknowledge_irq(pending, s->vectpending_prio, targets_secure); vec->active = 1; vec->pending = 0; @@ -XXX,XX +XXX,XX @@ void armv7m_nvic_acknowledge_irq(void *opaque) env->v7m.exception = s->vectpending; nvic_irq_update(s); + + return targets_secure; } -int armv7m_nvic_complete_irq(void *opaque, int irq) +int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure) { NVICState *s = (NVICState *)opaque; VecInfo *vec; @@ -XXX,XX +XXX,XX @@ int armv7m_nvic_complete_irq(void *opaque, int irq) assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq); - vec = &s->vectors[irq]; + if (secure && exc_is_banked(irq)) { + vec = &s->sec_vectors[irq]; + } else { + vec = &s->vectors[irq]; + } - trace_nvic_complete_irq(irq); + trace_nvic_complete_irq(irq, secure); if (!vec->active) { /* Tell the caller this was an illegal exception return */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) bool return_to_sp_process = false; bool return_to_handler = false; bool rettobase = false; + bool exc_secure = false; /* We can only get here from an EXCP_EXCEPTION_EXIT, and * gen_bx_excret() enforces the architectural rule @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) * which security state's faultmask to clear. (v8M ARM ARM R_KBNF.) */ if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { - int es = excret & R_V7M_EXCRET_ES_MASK; + exc_secure = excret & R_V7M_EXCRET_ES_MASK; if (armv7m_nvic_raw_execution_priority(env->nvic) >= 0) { - env->v7m.faultmask[es] = 0; + env->v7m.faultmask[exc_secure] = 0; } } else { env->v7m.faultmask[M_REG_NS] = 0; } } - switch (armv7m_nvic_complete_irq(env->nvic, env->v7m.exception)) { + switch (armv7m_nvic_complete_irq(env->nvic, env->v7m.exception, + exc_secure)) { case -1: /* attempt to exit an exception that isn't active */ ufault = true; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ nvic_escalate_disabled(int irq) "NVIC escalating irq %d to HardFault: disabled" nvic_set_pending(int irq, bool secure, int en, int prio) "NVIC set pending irq %d secure-bank %d (enabled: %d priority %d)" nvic_clear_pending(int irq, bool secure, int en, int prio) "NVIC clear pending irq %d secure-bank %d (enabled: %d priority %d)" nvic_set_pending_level(int irq) "NVIC set pending: irq %d higher prio than vectpending: setting irq line to 1" -nvic_acknowledge_irq(int irq, int prio) "NVIC acknowledge IRQ: %d now active (prio %d)" -nvic_complete_irq(int irq) "NVIC complete IRQ %d" +nvic_acknowledge_irq(int irq, int prio, bool targets_secure) "NVIC acknowledge IRQ: %d now active (prio %d targets_secure %d)" +nvic_complete_irq(int irq, bool secure) "NVIC complete IRQ %d (secure %d)" nvic_set_irq_level(int irq, int level) "NVIC external irq %d level set to %d" nvic_sysreg_read(uint64_t addr, uint32_t value, unsigned size) "NVIC sysreg read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" nvic_sysreg_write(uint64_t addr, uint32_t value, unsigned size) "NVIC sysreg write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" -- 2.7.4 In the A64 decoder, we have a lot of references to section numbers from version A.a of the v8A ARM ARM (DDI0487). This version of the document is now long obsolete (we are currently on revision B.a), and various intervening versions renumbered all the sections. The most recent B.a version of the document doesn't assign section numbers at all to the individual instruction classes in the way that the various A.x versions did. The simplest thing to do is just to delete all the out of date C.x.x references. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20170915150849.23557-1-peter.maydell@linaro.org --- target/arm/translate-a64.c | 227 +++++++++++++++++++++++---------------------- 1 file changed, 114 insertions(+), 113 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static inline AArch64DecodeFn *lookup_disas_fn(const AArch64DecodeTable *table, } /* - * the instruction disassembly implemented here matches - * the instruction encoding classifications in chapter 3 (C3) - * of the ARM Architecture Reference Manual (DDI0487A_a) + * The instruction disassembly implemented here matches + * the instruction encoding classifications in chapter C4 + * of the ARM Architecture Reference Manual (DDI0487B_a); + * classification names and decode diagrams here should generally + * match up with those in the manual. */ -/* C3.2.7 Unconditional branch (immediate) +/* Unconditional branch (immediate) * 31 30 26 25 0 * +----+-----------+-------------------------------------+ * | op | 0 0 1 0 1 | imm26 | @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_imm(DisasContext *s, uint32_t insn) uint64_t addr = s->pc + sextract32(insn, 0, 26) * 4 - 4; if (insn & (1U << 31)) { - /* C5.6.26 BL Branch with link */ + /* BL Branch with link */ tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); } - /* C5.6.20 B Branch / C5.6.26 BL Branch with link */ + /* B Branch / BL Branch with link */ gen_goto_tb(s, 0, addr); } -/* C3.2.1 Compare & branch (immediate) +/* Compare and branch (immediate) * 31 30 25 24 23 5 4 0 * +----+-------------+----+---------------------+--------+ * | sf | 0 1 1 0 1 0 | op | imm19 | Rt | @@ -XXX,XX +XXX,XX @@ static void disas_comp_b_imm(DisasContext *s, uint32_t insn) gen_goto_tb(s, 1, addr); } -/* C3.2.5 Test & branch (immediate) +/* Test and branch (immediate) * 31 30 25 24 23 19 18 5 4 0 * +----+-------------+----+-------+-------------+------+ * | b5 | 0 1 1 0 1 1 | op | b40 | imm14 | Rt | @@ -XXX,XX +XXX,XX @@ static void disas_test_b_imm(DisasContext *s, uint32_t insn) gen_goto_tb(s, 1, addr); } -/* C3.2.2 / C5.6.19 Conditional branch (immediate) +/* Conditional branch (immediate) * 31 25 24 23 5 4 3 0 * +---------------+----+---------------------+----+------+ * | 0 1 0 1 0 1 0 | o1 | imm19 | o0 | cond | @@ -XXX,XX +XXX,XX @@ static void disas_cond_b_imm(DisasContext *s, uint32_t insn) } } -/* C5.6.68 HINT */ +/* HINT instruction group, including various allocated HINTs */ static void handle_hint(DisasContext *s, uint32_t insn, unsigned int op1, unsigned int op2, unsigned int crm) { @@ -XXX,XX +XXX,XX @@ static void handle_sync(DisasContext *s, uint32_t insn, } } -/* C5.6.130 MSR (immediate) - move immediate to processor state field */ +/* MSR (immediate) - move immediate to processor state field */ static void handle_msr_i(DisasContext *s, uint32_t insn, unsigned int op1, unsigned int op2, unsigned int crm) { @@ -XXX,XX +XXX,XX @@ static void gen_set_nzcv(TCGv_i64 tcg_rt) tcg_temp_free_i32(nzcv); } -/* C5.6.129 MRS - move from system register - * C5.6.131 MSR (register) - move to system register - * C5.6.204 SYS - * C5.6.205 SYSL +/* MRS - move from system register + * MSR (register) - move to system register + * SYS + * SYSL * These are all essentially the same insn in 'read' and 'write' * versions, with varying op0 fields. */ @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, } } -/* C3.2.4 System +/* System * 31 22 21 20 19 18 16 15 12 11 8 7 5 4 0 * +---------------------+---+-----+-----+-------+-------+-----+------+ * | 1 1 0 1 0 1 0 1 0 0 | L | op0 | op1 | CRn | CRm | op2 | Rt | @@ -XXX,XX +XXX,XX @@ static void disas_system(DisasContext *s, uint32_t insn) return; } switch (crn) { - case 2: /* C5.6.68 HINT */ + case 2: /* HINT (including allocated hints like NOP, YIELD, etc) */ handle_hint(s, insn, op1, op2, crm); break; case 3: /* CLREX, DSB, DMB, ISB */ handle_sync(s, insn, op1, op2, crm); break; - case 4: /* C5.6.130 MSR (immediate) */ + case 4: /* MSR (immediate) */ handle_msr_i(s, insn, op1, op2, crm); break; default: @@ -XXX,XX +XXX,XX @@ static void disas_system(DisasContext *s, uint32_t insn) handle_sys(s, insn, l, op0, op1, op2, crn, crm, rt); } -/* C3.2.3 Exception generation +/* Exception generation * * 31 24 23 21 20 5 4 2 1 0 * +-----------------+-----+------------------------+-----+----+ @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) } } -/* C3.2.7 Unconditional branch (register) +/* Unconditional branch (register) * 31 25 24 21 20 16 15 10 9 5 4 0 * +---------------+-------+-------+-------+------+-------+ * | 1 1 0 1 0 1 1 | opc | op2 | op3 | Rn | op4 | @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) s->base.is_jmp = DISAS_JUMP; } -/* C3.2 Branches, exception generating and system instructions */ +/* Branches, exception generating and system instructions */ static void disas_b_exc_sys(DisasContext *s, uint32_t insn) { switch (extract32(insn, 25, 7)) { @@ -XXX,XX +XXX,XX @@ static bool disas_ldst_compute_iss_sf(int size, bool is_signed, int opc) return regsize == 64; } -/* C3.3.6 Load/store exclusive +/* Load/store exclusive * * 31 30 29 24 23 22 21 20 16 15 14 10 9 5 4 0 * +-----+-------------+----+---+----+------+----+-------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } /* - * C3.3.5 Load register (literal) + * Load register (literal) * * 31 30 29 27 26 25 24 23 5 4 0 * +-----+-------+---+-----+-------------------+-------+ @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) } /* - * C5.6.80 LDNP (Load Pair - non-temporal hint) - * C5.6.81 LDP (Load Pair - non vector) - * C5.6.82 LDPSW (Load Pair Signed Word - non vector) - * C5.6.176 STNP (Store Pair - non-temporal hint) - * C5.6.177 STP (Store Pair - non vector) - * C6.3.165 LDNP (Load Pair of SIMD&FP - non-temporal hint) - * C6.3.165 LDP (Load Pair of SIMD&FP) - * C6.3.284 STNP (Store Pair of SIMD&FP - non-temporal hint) - * C6.3.284 STP (Store Pair of SIMD&FP) + * LDNP (Load Pair - non-temporal hint) + * LDP (Load Pair - non vector) + * LDPSW (Load Pair Signed Word - non vector) + * STNP (Store Pair - non-temporal hint) + * STP (Store Pair - non vector) + * LDNP (Load Pair of SIMD&FP - non-temporal hint) + * LDP (Load Pair of SIMD&FP) + * STNP (Store Pair of SIMD&FP - non-temporal hint) + * STP (Store Pair of SIMD&FP) * * 31 30 29 27 26 25 24 23 22 21 15 14 10 9 5 4 0 * +-----+-------+---+---+-------+---+-----------------------------+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) } /* - * C3.3.8 Load/store (immediate post-indexed) - * C3.3.9 Load/store (immediate pre-indexed) - * C3.3.12 Load/store (unscaled immediate) + * Load/store (immediate post-indexed) + * Load/store (immediate pre-indexed) + * Load/store (unscaled immediate) * * 31 30 29 27 26 25 24 23 22 21 20 12 11 10 9 5 4 0 * +----+-------+---+-----+-----+---+--------+-----+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, } /* - * C3.3.10 Load/store (register offset) + * Load/store (register offset) * * 31 30 29 27 26 25 24 23 22 21 20 16 15 13 12 11 10 9 5 4 0 * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, } /* - * C3.3.13 Load/store (unsigned immediate) + * Load/store (unsigned immediate) * * 31 30 29 27 26 25 24 23 22 21 10 9 5 * +----+-------+---+-----+-----+------------+-------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) } } -/* C3.3.1 AdvSIMD load/store multiple structures +/* AdvSIMD load/store multiple structures * * 31 30 29 23 22 21 16 15 12 11 10 9 5 4 0 * +---+---+---------------+---+-------------+--------+------+------+------+ * | 0 | Q | 0 0 1 1 0 0 0 | L | 0 0 0 0 0 0 | opcode | size | Rn | Rt | * +---+---+---------------+---+-------------+--------+------+------+------+ * - * C3.3.2 AdvSIMD load/store multiple structures (post-indexed) + * AdvSIMD load/store multiple structures (post-indexed) * * 31 30 29 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---------------+---+---+---------+--------+------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_addr); } -/* C3.3.3 AdvSIMD load/store single structure +/* AdvSIMD load/store single structure * * 31 30 29 23 22 21 20 16 15 13 12 11 10 9 5 4 0 * +---+---+---------------+-----+-----------+-----+---+------+------+------+ * | 0 | Q | 0 0 1 1 0 1 0 | L R | 0 0 0 0 0 | opc | S | size | Rn | Rt | * +---+---+---------------+-----+-----------+-----+---+------+------+------+ * - * C3.3.4 AdvSIMD load/store single structure (post-indexed) + * AdvSIMD load/store single structure (post-indexed) * * 31 30 29 23 22 21 20 16 15 13 12 11 10 9 5 4 0 * +---+---+---------------+-----+-----------+-----+---+------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_addr); } -/* C3.3 Loads and stores */ +/* Loads and stores */ static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst(DisasContext *s, uint32_t insn) } } -/* C3.4.6 PC-rel. addressing +/* PC-rel. addressing * 31 30 29 28 24 23 5 4 0 * +----+-------+-----------+-------------------+------+ * | op | immlo | 1 0 0 0 0 | immhi | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_pc_rel_adr(DisasContext *s, uint32_t insn) } /* - * C3.4.1 Add/subtract (immediate) + * Add/subtract (immediate) * * 31 30 29 28 24 23 22 21 10 9 5 4 0 * +--+--+--+-----------+-----+-------------+-----+-----+ @@ -XXX,XX +XXX,XX @@ static bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn, return true; } -/* C3.4.4 Logical (immediate) +/* Logical (immediate) * 31 30 29 28 23 22 21 16 15 10 9 5 4 0 * +----+-----+-------------+---+------+------+------+------+ * | sf | opc | 1 0 0 1 0 0 | N | immr | imms | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_logic_imm(DisasContext *s, uint32_t insn) } /* - * C3.4.5 Move wide (immediate) + * Move wide (immediate) * * 31 30 29 28 23 22 21 20 5 4 0 * +--+-----+-------------+-----+----------------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_movw_imm(DisasContext *s, uint32_t insn) } } -/* C3.4.2 Bitfield +/* Bitfield * 31 30 29 28 23 22 21 16 15 10 9 5 4 0 * +----+-----+-------------+---+------+------+------+------+ * | sf | opc | 1 0 0 1 1 0 | N | immr | imms | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_bitfield(DisasContext *s, uint32_t insn) } } -/* C3.4.3 Extract +/* Extract * 31 30 29 28 23 22 21 20 16 15 10 9 5 4 0 * +----+------+-------------+---+----+------+--------+------+------+ * | sf | op21 | 1 0 0 1 1 1 | N | o0 | Rm | imms | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_extract(DisasContext *s, uint32_t insn) } } -/* C3.4 Data processing - immediate */ +/* Data processing - immediate */ static void disas_data_proc_imm(DisasContext *s, uint32_t insn) { switch (extract32(insn, 23, 6)) { @@ -XXX,XX +XXX,XX @@ static void shift_reg_imm(TCGv_i64 dst, TCGv_i64 src, int sf, } } -/* C3.5.10 Logical (shifted register) +/* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ * | sf | opc | 0 1 0 1 0 | shift | N | Rm | imm6 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_logic_reg(DisasContext *s, uint32_t insn) } /* - * C3.5.1 Add/subtract (extended register) + * Add/subtract (extended register) * * 31|30|29|28 24|23 22|21|20 16|15 13|12 10|9 5|4 0| * +--+--+--+-----------+-----+--+-------+------+------+----+----+ @@ -XXX,XX +XXX,XX @@ static void disas_add_sub_ext_reg(DisasContext *s, uint32_t insn) } /* - * C3.5.2 Add/subtract (shifted register) + * Add/subtract (shifted register) * * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +--+--+--+-----------+-----+--+-------+---------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_add_sub_reg(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_result); } -/* C3.5.9 Data-processing (3 source) - - 31 30 29 28 24 23 21 20 16 15 14 10 9 5 4 0 - +--+------+-----------+------+------+----+------+------+------+ - |sf| op54 | 1 1 0 1 1 | op31 | Rm | o0 | Ra | Rn | Rd | - +--+------+-----------+------+------+----+------+------+------+ - +/* Data-processing (3 source) + * + * 31 30 29 28 24 23 21 20 16 15 14 10 9 5 4 0 + * +--+------+-----------+------+------+----+------+------+------+ + * |sf| op54 | 1 1 0 1 1 | op31 | Rm | o0 | Ra | Rn | Rd | + * +--+------+-----------+------+------+----+------+------+------+ */ static void disas_data_proc_3src(DisasContext *s, uint32_t insn) { @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_3src(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_tmp); } -/* C3.5.3 - Add/subtract (with carry) +/* Add/subtract (with carry) * 31 30 29 28 27 26 25 24 23 22 21 20 16 15 10 9 5 4 0 * +--+--+--+------------------------+------+---------+------+-----+ * |sf|op| S| 1 1 0 1 0 0 0 0 | rm | opcode2 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_adc_sbc(DisasContext *s, uint32_t insn) } } -/* C3.5.4 - C3.5.5 Conditional compare (immediate / register) +/* Conditional compare (immediate / register) * 31 30 29 28 27 26 25 24 23 22 21 20 16 15 12 11 10 9 5 4 3 0 * +--+--+--+------------------------+--------+------+----+--+------+--+-----+ * |sf|op| S| 1 1 0 1 0 0 1 0 |imm5/rm | cond |i/r |o2| Rn |o3|nzcv | @@ -XXX,XX +XXX,XX @@ static void disas_cc(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tcg_t2); } -/* C3.5.6 Conditional select +/* Conditional select * 31 30 29 28 21 20 16 15 12 11 10 9 5 4 0 * +----+----+---+-----------------+------+------+-----+------+------+ * | sf | op | S | 1 1 0 1 0 1 0 0 | Rm | cond | op2 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_rbit(DisasContext *s, unsigned int sf, } } -/* C5.6.149 REV with sf==1, opcode==3 ("REV64") */ +/* REV with sf==1, opcode==3 ("REV64") */ static void handle_rev64(DisasContext *s, unsigned int sf, unsigned int rn, unsigned int rd) { @@ -XXX,XX +XXX,XX @@ static void handle_rev64(DisasContext *s, unsigned int sf, tcg_gen_bswap64_i64(cpu_reg(s, rd), cpu_reg(s, rn)); } -/* C5.6.149 REV with sf==0, opcode==2 - * C5.6.151 REV32 (sf==1, opcode==2) +/* REV with sf==0, opcode==2 + * REV32 (sf==1, opcode==2) */ static void handle_rev32(DisasContext *s, unsigned int sf, unsigned int rn, unsigned int rd) @@ -XXX,XX +XXX,XX @@ static void handle_rev32(DisasContext *s, unsigned int sf, } } -/* C5.6.150 REV16 (opcode==1) */ +/* REV16 (opcode==1) */ static void handle_rev16(DisasContext *s, unsigned int sf, unsigned int rn, unsigned int rd) { @@ -XXX,XX +XXX,XX @@ static void handle_rev16(DisasContext *s, unsigned int sf, tcg_temp_free_i64(tcg_tmp); } -/* C3.5.7 Data-processing (1 source) +/* Data-processing (1 source) * 31 30 29 28 21 20 16 15 10 9 5 4 0 * +----+---+---+-----------------+---------+--------+------+------+ * | sf | 1 | S | 1 1 0 1 0 1 1 0 | opcode2 | opcode | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_div(DisasContext *s, bool is_signed, unsigned int sf, } } -/* C5.6.115 LSLV, C5.6.118 LSRV, C5.6.17 ASRV, C5.6.154 RORV */ +/* LSLV, LSRV, ASRV, RORV */ static void handle_shift_reg(DisasContext *s, enum a64_shift_type shift_type, unsigned int sf, unsigned int rm, unsigned int rn, unsigned int rd) @@ -XXX,XX +XXX,XX @@ static void handle_crc32(DisasContext *s, tcg_temp_free_i32(tcg_bytes); } -/* C3.5.8 Data-processing (2 source) +/* Data-processing (2 source) * 31 30 29 28 21 20 16 15 10 9 5 4 0 * +----+---+---+-----------------+------+--------+------+------+ * | sf | 0 | S | 1 1 0 1 0 1 1 0 | Rm | opcode | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) } } -/* C3.5 Data processing - register */ +/* Data processing - register */ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 5)) { @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, bool is_double, tcg_temp_free_i64(tcg_flags); } -/* C3.6.22 Floating point compare +/* Floating point compare * 31 30 29 28 24 23 22 21 20 16 15 14 13 10 9 5 4 0 * +---+---+---+-----------+------+---+------+-----+---------+------+-------+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | op | 1 0 0 0 | Rn | op2 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_compare(DisasContext *s, uint32_t insn) handle_fp_compare(s, type, rn, rm, opc & 1, opc & 2); } -/* C3.6.23 Floating point conditional compare +/* Floating point conditional compare * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 3 0 * +---+---+---+-----------+------+---+------+------+-----+------+----+------+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | cond | 0 1 | Rn | op | nzcv | @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) } } -/* C3.6.24 Floating point conditional select +/* Floating point conditional select * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+------+-----+------+------+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | cond | 1 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) tcg_temp_free_i64(t_true); } -/* C3.6.25 Floating-point data-processing (1 source) - single precision */ +/* Floating-point data-processing (1 source) - single precision */ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) { TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) tcg_temp_free_i32(tcg_res); } -/* C3.6.25 Floating-point data-processing (1 source) - double precision */ +/* Floating-point data-processing (1 source) - double precision */ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) { TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static void handle_fp_fcvt(DisasContext *s, int opcode, } } -/* C3.6.25 Floating point data-processing (1 source) +/* Floating point data-processing (1 source) * 31 30 29 28 24 23 22 21 20 15 14 10 9 5 4 0 * +---+---+---+-----------+------+---+--------+-----------+------+------+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | opcode | 1 0 0 0 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) } } -/* C3.6.26 Floating-point data-processing (2 source) - single precision */ +/* Floating-point data-processing (2 source) - single precision */ static void handle_fp_2src_single(DisasContext *s, int opcode, int rd, int rn, int rm) { @@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_single(DisasContext *s, int opcode, tcg_temp_free_i32(tcg_res); } -/* C3.6.26 Floating-point data-processing (2 source) - double precision */ +/* Floating-point data-processing (2 source) - double precision */ static void handle_fp_2src_double(DisasContext *s, int opcode, int rd, int rn, int rm) { @@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_double(DisasContext *s, int opcode, tcg_temp_free_i64(tcg_res); } -/* C3.6.26 Floating point data-processing (2 source) +/* Floating point data-processing (2 source) * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+--------+-----+------+------+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | opcode | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_fp_2src(DisasContext *s, uint32_t insn) } } -/* C3.6.27 Floating-point data-processing (3 source) - single precision */ +/* Floating-point data-processing (3 source) - single precision */ static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1, int rd, int rn, int rm, int ra) { @@ -XXX,XX +XXX,XX @@ static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1, tcg_temp_free_i32(tcg_res); } -/* C3.6.27 Floating-point data-processing (3 source) - double precision */ +/* Floating-point data-processing (3 source) - double precision */ static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1, int rd, int rn, int rm, int ra) { @@ -XXX,XX +XXX,XX @@ static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1, tcg_temp_free_i64(tcg_res); } -/* C3.6.27 Floating point data-processing (3 source) +/* Floating point data-processing (3 source) * 31 30 29 28 24 23 22 21 20 16 15 14 10 9 5 4 0 * +---+---+---+-----------+------+----+------+----+------+------+------+ * | M | 0 | S | 1 1 1 1 1 | type | o1 | Rm | o0 | Ra | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) } } -/* C3.6.28 Floating point immediate +/* Floating point immediate * 31 30 29 28 24 23 22 21 20 13 12 10 9 5 4 0 * +---+---+---+-----------+------+---+------------+-------+------+------+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | imm8 | 1 0 0 | imm5 | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, tcg_temp_free_i32(tcg_shift); } -/* C3.6.29 Floating point <-> fixed point conversions +/* Floating point <-> fixed point conversions * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0 * +----+---+---+-----------+------+---+-------+--------+-------+------+------+ * | sf | 0 | S | 1 1 1 1 0 | type | 0 | rmode | opcode | scale | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) } } -/* C3.6.30 Floating point <-> integer conversions +/* Floating point <-> integer conversions * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0 * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+ * | sf | 0 | S | 1 1 1 1 0 | type | 1 | rmode | opc | 0 0 0 0 0 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void do_ext64(DisasContext *s, TCGv_i64 tcg_left, TCGv_i64 tcg_right, tcg_temp_free_i64(tcg_tmp); } -/* C3.6.1 EXT +/* EXT * 31 30 29 24 23 22 21 20 16 15 14 11 10 9 5 4 0 * +---+---+-------------+-----+---+------+---+------+---+------+------+ * | 0 | Q | 1 0 1 1 1 0 | op2 | 0 | Rm | 0 | imm4 | 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_ext(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_resh); } -/* C3.6.2 TBL/TBX +/* TBL/TBX * 31 30 29 24 23 22 21 20 16 15 14 13 12 11 10 9 5 4 0 * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+ * | 0 | Q | 0 0 1 1 1 0 | op2 | 0 | Rm | 0 | len | op | 0 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_resh); } -/* C3.6.3 ZIP/UZP/TRN +/* ZIP/UZP/TRN * 31 30 29 24 23 22 21 20 16 15 14 12 11 10 9 5 4 0 * +---+---+-------------+------+---+------+---+------------------+------+ * | 0 | Q | 0 0 1 1 1 0 | size | 0 | Rm | 0 | opc | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void do_minmaxop(DisasContext *s, TCGv_i32 tcg_elt1, TCGv_i32 tcg_elt2, } } -/* C3.6.4 AdvSIMD across lanes +/* AdvSIMD across lanes * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +---+---+---+-----------+------+-----------+--------+-----+------+------+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_res); } -/* C6.3.31 DUP (Element, Vector) +/* DUP (Element, Vector) * * 31 30 29 21 20 16 15 10 9 5 4 0 * +---+---+-------------------+--------+-------------+------+------+ @@ -XXX,XX +XXX,XX @@ static void handle_simd_dupe(DisasContext *s, int is_q, int rd, int rn, tcg_temp_free_i64(tmp); } -/* C6.3.31 DUP (element, scalar) +/* DUP (element, scalar) * 31 21 20 16 15 10 9 5 4 0 * +-----------------------+--------+-------------+------+------+ * | 0 1 0 1 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 0 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_simd_dupes(DisasContext *s, int rd, int rn, tcg_temp_free_i64(tmp); } -/* C6.3.32 DUP (General) +/* DUP (General) * * 31 30 29 21 20 16 15 10 9 5 4 0 * +---+---+-------------------+--------+-------------+------+------+ @@ -XXX,XX +XXX,XX @@ static void handle_simd_dupg(DisasContext *s, int is_q, int rd, int rn, } } -/* C6.3.150 INS (Element) +/* INS (Element) * * 31 21 20 16 15 14 11 10 9 5 4 0 * +-----------------------+--------+------------+---+------+------+ @@ -XXX,XX +XXX,XX @@ static void handle_simd_inse(DisasContext *s, int rd, int rn, } -/* C6.3.151 INS (General) +/* INS (General) * * 31 21 20 16 15 10 9 5 4 0 * +-----------------------+--------+-------------+------+------+ @@ -XXX,XX +XXX,XX @@ static void handle_simd_insg(DisasContext *s, int rd, int rn, int imm5) } /* - * C6.3.321 UMOV (General) - * C6.3.237 SMOV (General) + * UMOV (General) + * SMOV (General) * * 31 30 29 21 20 16 15 12 10 9 5 4 0 * +---+---+-------------------+--------+-------------+------+------+ @@ -XXX,XX +XXX,XX @@ static void handle_simd_umov_smov(DisasContext *s, int is_q, int is_signed, } } -/* C3.6.5 AdvSIMD copy +/* AdvSIMD copy * 31 30 29 28 21 20 16 15 14 11 10 9 5 4 0 * +---+---+----+-----------------+------+---+------+---+------+------+ * | 0 | Q | op | 0 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_copy(DisasContext *s, uint32_t insn) } } -/* C3.6.6 AdvSIMD modified immediate +/* AdvSIMD modified immediate * 31 30 29 28 19 18 16 15 12 11 10 9 5 4 0 * +---+---+----+---------------------+-----+-------+----+---+-------+------+ * | 0 | Q | op | 0 1 1 1 1 0 0 0 0 0 | abc | cmode | o2 | 1 | defgh | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_imm); } -/* C3.6.7 AdvSIMD scalar copy +/* AdvSIMD scalar copy * 31 30 29 28 21 20 16 15 14 11 10 9 5 4 0 * +-----+----+-----------------+------+---+------+---+------+------+ * | 0 1 | op | 1 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_copy(DisasContext *s, uint32_t insn) handle_simd_dupes(s, rd, rn, imm5); } -/* C3.6.8 AdvSIMD scalar pairwise +/* AdvSIMD scalar pairwise * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ * | 0 1 | U | 1 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, tcg_temp_free_i32(tcg_rmode); } -/* C3.6.9 AdvSIMD scalar shift by immediate +/* AdvSIMD scalar shift by immediate * 31 30 29 28 23 22 19 18 16 15 11 10 9 5 4 0 * +-----+---+-------------+------+------+--------+---+------+------+ * | 0 1 | U | 1 1 1 1 1 0 | immh | immb | opcode | 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn) } } -/* C3.6.10 AdvSIMD scalar three different +/* AdvSIMD scalar three different * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +-----+---+-----------+------+---+------+--------+-----+------+------+ * | 0 1 | U | 1 1 1 1 0 | size | 1 | Rm | opcode | 0 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_3same_float(DisasContext *s, int size, int elements, } } -/* C3.6.11 AdvSIMD scalar three same +/* AdvSIMD scalar three same * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0 * +-----+---+-----------+------+---+------+--------+---+------+------+ * | 0 1 | U | 1 1 1 1 0 | size | 1 | Rm | opcode | 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u, } } -/* C3.6.12 AdvSIMD scalar two reg misc +/* AdvSIMD scalar two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ * | 0 1 | U | 1 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shrn(DisasContext *s, bool is_q, } -/* C3.6.14 AdvSIMD shift by immediate +/* AdvSIMD shift by immediate * 31 30 29 28 23 22 19 18 16 15 11 10 9 5 4 0 * +---+---+---+-------------+------+------+--------+---+------+------+ * | 0 | Q | U | 0 1 1 1 1 0 | immh | immb | opcode | 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_pmull_64(DisasContext *s, int is_q, int rd, int rn, int rm) tcg_temp_free_i64(tcg_res); } -/* C3.6.15 AdvSIMD three different +/* AdvSIMD three different * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+--------+-----+------+------+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 | Rm | opcode | 0 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } } -/* C3.6.16 AdvSIMD three same +/* AdvSIMD three same * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+--------+---+------+------+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 | Rm | opcode | 1 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void handle_shll(DisasContext *s, bool is_q, int size, int rn, int rd) } } -/* C3.6.17 AdvSIMD two reg misc +/* AdvSIMD two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +---+---+---+-----------+------+-----------+--------+-----+------+------+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } } -/* C3.6.13 AdvSIMD scalar x indexed element +/* AdvSIMD scalar x indexed element * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0 * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ * | 0 1 | U | 1 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd | * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ - * C3.6.18 AdvSIMD vector x indexed element + * AdvSIMD vector x indexed element * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+ * | 0 | Q | U | 0 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* C3.6.19 Crypto AES +/* Crypto AES * 31 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----------------+------+-----------+--------+-----+------+------+ * | 0 1 0 0 1 1 1 0 | size | 1 0 1 0 0 | opcode | 1 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tcg_decrypt); } -/* C3.6.20 Crypto three-reg SHA +/* Crypto three-reg SHA * 31 24 23 22 21 20 16 15 14 12 11 10 9 5 4 0 * +-----------------+------+---+------+---+--------+-----+------+------+ * | 0 1 0 1 1 1 1 0 | size | 0 | Rm | 0 | opcode | 0 0 | Rn | Rd | @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tcg_rm_regno); } -/* C3.6.21 Crypto two-reg SHA +/* Crypto two-reg SHA * 31 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----------------+------+-----------+--------+-----+------+------+ * | 0 1 0 1 1 1 1 0 | size | 1 0 1 0 0 | opcode | 1 0 | Rn | Rd | -- 2.7.4 Update the static_ops functions to use new-style mmio rather than the legacy old_mmio functions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505580378-9044-2-git-send-email-peter.maydell@linaro.org --- hw/arm/palm.c | 30 ++++++++++-------------------- 1 file changed, 10 insertions(+), 20 deletions(-) diff --git a/hw/arm/palm.c b/hw/arm/palm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/palm.c +++ b/hw/arm/palm.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "cpu.h" -static uint32_t static_readb(void *opaque, hwaddr offset) +static uint64_t static_read(void *opaque, hwaddr offset, unsigned size) { - uint32_t *val = (uint32_t *) opaque; - return *val >> ((offset & 3) << 3); -} + uint32_t *val = (uint32_t *)opaque; + uint32_t sizemask = 7 >> size; -static uint32_t static_readh(void *opaque, hwaddr offset) -{ - uint32_t *val = (uint32_t *) opaque; - return *val >> ((offset & 1) << 3); -} - -static uint32_t static_readw(void *opaque, hwaddr offset) -{ - uint32_t *val = (uint32_t *) opaque; - return *val >> ((offset & 0) << 3); + return *val >> ((offset & sizemask) << 3); } -static void static_write(void *opaque, hwaddr offset, - uint32_t value) +static void static_write(void *opaque, hwaddr offset, uint64_t value, + unsigned size) { #ifdef SPY printf("%s: value %08lx written at " PA_FMT "\n", @@ -XXX,XX +XXX,XX @@ static void static_write(void *opaque, hwaddr offset, } static const MemoryRegionOps static_ops = { - .old_mmio = { - .read = { static_readb, static_readh, static_readw, }, - .write = { static_write, static_write, static_write, }, - }, + .read = static_read, + .write = static_write, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.7.4 Drop the use of old_mmio in the omap2_gpio memory ops. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505580378-9044-3-git-send-email-peter.maydell@linaro.org --- hw/gpio/omap_gpio.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_module_write(void *opaque, hwaddr addr, } } -static uint32_t omap2_gpio_module_readp(void *opaque, hwaddr addr) +static uint64_t omap2_gpio_module_readp(void *opaque, hwaddr addr, + unsigned size) { return omap2_gpio_module_read(opaque, addr & ~3) >> ((addr & 3) << 3); } static void omap2_gpio_module_writep(void *opaque, hwaddr addr, - uint32_t value) + uint64_t value, unsigned size) { uint32_t cur = 0; uint32_t mask = 0xffff; + if (size == 4) { + omap2_gpio_module_write(opaque, addr, value); + return; + } + switch (addr & ~3) { case 0x00: /* GPIO_REVISION */ case 0x14: /* GPIO_SYSSTATUS */ @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_module_writep(void *opaque, hwaddr addr, } static const MemoryRegionOps omap2_gpio_module_ops = { - .old_mmio = { - .read = { - omap2_gpio_module_readp, - omap2_gpio_module_readp, - omap2_gpio_module_read, - }, - .write = { - omap2_gpio_module_writep, - omap2_gpio_module_writep, - omap2_gpio_module_write, - }, - }, + .read = omap2_gpio_module_readp, + .write = omap2_gpio_module_writep, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.7.4 Don't use the old_mmio in the memory region ops struct. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505580378-9044-4-git-send-email-peter.maydell@linaro.org --- hw/timer/omap_synctimer.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/hw/timer/omap_synctimer.c b/hw/timer/omap_synctimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_synctimer.c +++ b/hw/timer/omap_synctimer.c @@ -XXX,XX +XXX,XX @@ static uint32_t omap_synctimer_readh(void *opaque, hwaddr addr) } } -static void omap_synctimer_write(void *opaque, hwaddr addr, - uint32_t value) +static uint64_t omap_synctimer_readfn(void *opaque, hwaddr addr, + unsigned size) +{ + switch (size) { + case 1: + return omap_badwidth_read32(opaque, addr); + case 2: + return omap_synctimer_readh(opaque, addr); + case 4: + return omap_synctimer_readw(opaque, addr); + default: + g_assert_not_reached(); + } +} + +static void omap_synctimer_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) { OMAP_BAD_REG(addr); } static const MemoryRegionOps omap_synctimer_ops = { - .old_mmio = { - .read = { - omap_badwidth_read32, - omap_synctimer_readh, - omap_synctimer_readw, - }, - .write = { - omap_badwidth_write32, - omap_synctimer_write, - omap_synctimer_write, - }, - }, + .read = omap_synctimer_readfn, + .write = omap_synctimer_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.7.4 Don't use the old_mmio struct in memory region ops. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505580378-9044-5-git-send-email-peter.maydell@linaro.org --- hw/timer/omap_gptimer.c | 49 +++++++++++++++++++++++++++++++++++++------------ 1 file changed, 37 insertions(+), 12 deletions(-) diff --git a/hw/timer/omap_gptimer.c b/hw/timer/omap_gptimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_gptimer.c +++ b/hw/timer/omap_gptimer.c @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_writeh(void *opaque, hwaddr addr, s->writeh = (uint16_t) value; } +static uint64_t omap_gp_timer_readfn(void *opaque, hwaddr addr, + unsigned size) +{ + switch (size) { + case 1: + return omap_badwidth_read32(opaque, addr); + case 2: + return omap_gp_timer_readh(opaque, addr); + case 4: + return omap_gp_timer_readw(opaque, addr); + default: + g_assert_not_reached(); + } +} + +static void omap_gp_timer_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + switch (size) { + case 1: + omap_badwidth_write32(opaque, addr, value); + break; + case 2: + omap_gp_timer_writeh(opaque, addr, value); + break; + case 4: + omap_gp_timer_write(opaque, addr, value); + break; + default: + g_assert_not_reached(); + } +} + static const MemoryRegionOps omap_gp_timer_ops = { - .old_mmio = { - .read = { - omap_badwidth_read32, - omap_gp_timer_readh, - omap_gp_timer_readw, - }, - .write = { - omap_badwidth_write32, - omap_gp_timer_writeh, - omap_gp_timer_write, - }, - }, + .read = omap_gp_timer_readfn, + .write = omap_gp_timer_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.7.4 Don't use old_mmio in the memory region ops struct. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505580378-9044-6-git-send-email-peter.maydell@linaro.org --- hw/i2c/omap_i2c.c | 44 ++++++++++++++++++++++++++++++++------------ 1 file changed, 32 insertions(+), 12 deletions(-) diff --git a/hw/i2c/omap_i2c.c b/hw/i2c/omap_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/omap_i2c.c +++ b/hw/i2c/omap_i2c.c @@ -XXX,XX +XXX,XX @@ static void omap_i2c_writeb(void *opaque, hwaddr addr, } } +static uint64_t omap_i2c_readfn(void *opaque, hwaddr addr, + unsigned size) +{ + switch (size) { + case 2: + return omap_i2c_read(opaque, addr); + default: + return omap_badwidth_read16(opaque, addr); + } +} + +static void omap_i2c_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + switch (size) { + case 1: + /* Only the last fifo write can be 8 bit. */ + omap_i2c_writeb(opaque, addr, value); + break; + case 2: + omap_i2c_write(opaque, addr, value); + break; + default: + omap_badwidth_write16(opaque, addr, value); + break; + } +} + static const MemoryRegionOps omap_i2c_ops = { - .old_mmio = { - .read = { - omap_badwidth_read16, - omap_i2c_read, - omap_badwidth_read16, - }, - .write = { - omap_i2c_writeb, /* Only the last fifo write can be 8 bit. */ - omap_i2c_write, - omap_badwidth_write16, - }, - }, + .read = omap_i2c_readfn, + .write = omap_i2c_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.7.4 Don't use old_mmio in the memory region ops struct. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1505580378-9044-7-git-send-email-peter.maydell@linaro.org --- hw/arm/omap2.c | 49 +++++++++++++++++++++++++++++++++++++------------ 1 file changed, 37 insertions(+), 12 deletions(-) diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap2.c +++ b/hw/arm/omap2.c @@ -XXX,XX +XXX,XX @@ static void omap_sysctl_write(void *opaque, hwaddr addr, } } +static uint64_t omap_sysctl_readfn(void *opaque, hwaddr addr, + unsigned size) +{ + switch (size) { + case 1: + return omap_sysctl_read8(opaque, addr); + case 2: + return omap_badwidth_read32(opaque, addr); /* TODO */ + case 4: + return omap_sysctl_read(opaque, addr); + default: + g_assert_not_reached(); + } +} + +static void omap_sysctl_writefn(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + switch (size) { + case 1: + omap_sysctl_write8(opaque, addr, value); + break; + case 2: + omap_badwidth_write32(opaque, addr, value); /* TODO */ + break; + case 4: + omap_sysctl_write(opaque, addr, value); + break; + default: + g_assert_not_reached(); + } +} + static const MemoryRegionOps omap_sysctl_ops = { - .old_mmio = { - .read = { - omap_sysctl_read8, - omap_badwidth_read32, /* TODO */ - omap_sysctl_read, - }, - .write = { - omap_sysctl_write8, - omap_badwidth_write32, /* TODO */ - omap_sysctl_write, - }, - }, + .read = omap_sysctl_readfn, + .write = omap_sysctl_writefn, + .valid.min_access_size = 1, + .valid.max_access_size = 4, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.7.4 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Modelled System Timer in Microsemi's Smartfusion2 Soc. Timer has two 32bit down counters and two interrupts. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Acked-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170920201737.25723-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/Makefile.objs | 1 + include/hw/timer/mss-timer.h | 64 ++++++++++ hw/timer/mss-timer.c | 289 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 354 insertions(+) create mode 100644 include/hw/timer/mss-timer.h create mode 100644 hw/timer/mss-timer.c diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/Makefile.objs +++ b/hw/timer/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ASPEED_SOC) += aspeed_timer.o common-obj-$(CONFIG_SUN4V_RTC) += sun4v-rtc.o common-obj-$(CONFIG_CMSDK_APB_TIMER) += cmsdk-apb-timer.o +common-obj-$(CONFIG_MSF2) += mss-timer.o diff --git a/include/hw/timer/mss-timer.h b/include/hw/timer/mss-timer.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/mss-timer.h @@ -XXX,XX +XXX,XX @@ +/* + * Microsemi SmartFusion2 Timer. + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_MSS_TIMER_H +#define HW_MSS_TIMER_H + +#include "hw/sysbus.h" +#include "hw/ptimer.h" + +#define TYPE_MSS_TIMER "mss-timer" +#define MSS_TIMER(obj) OBJECT_CHECK(MSSTimerState, \ + (obj), TYPE_MSS_TIMER) + +/* + * There are two 32-bit down counting timers. + * Timers 1 and 2 can be concatenated into a single 64-bit Timer + * that operates either in Periodic mode or in One-shot mode. + * Writing 1 to the TIM64_MODE register bit 0 sets the Timers in 64-bit mode. + * In 64-bit mode, writing to the 32-bit registers has no effect. + * Similarly, in 32-bit mode, writing to the 64-bit mode registers + * has no effect. Only two 32-bit timers are supported currently. + */ +#define NUM_TIMERS 2 + +#define R_TIM1_MAX 6 + +struct Msf2Timer { + QEMUBH *bh; + ptimer_state *ptimer; + + uint32_t regs[R_TIM1_MAX]; + qemu_irq irq; +}; + +typedef struct MSSTimerState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + uint32_t freq_hz; + struct Msf2Timer timers[NUM_TIMERS]; +} MSSTimerState; + +#endif /* HW_MSS_TIMER_H */ diff --git a/hw/timer/mss-timer.c b/hw/timer/mss-timer.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/mss-timer.c @@ -XXX,XX +XXX,XX @@ +/* + * Block model of System timer present in + * Microsemi's SmartFusion2 and SmartFusion SoCs. + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com>. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu/main-loop.h" +#include "qemu/log.h" +#include "hw/timer/mss-timer.h" + +#ifndef MSS_TIMER_ERR_DEBUG +#define MSS_TIMER_ERR_DEBUG 0 +#endif + +#define DB_PRINT_L(lvl, fmt, args...) do { \ + if (MSS_TIMER_ERR_DEBUG >= lvl) { \ + qemu_log("%s: " fmt "\n", __func__, ## args); \ + } \ +} while (0); + +#define DB_PRINT(fmt, args...) DB_PRINT_L(1, fmt, ## args) + +#define R_TIM_VAL 0 +#define R_TIM_LOADVAL 1 +#define R_TIM_BGLOADVAL 2 +#define R_TIM_CTRL 3 +#define R_TIM_RIS 4 +#define R_TIM_MIS 5 + +#define TIMER_CTRL_ENBL (1 << 0) +#define TIMER_CTRL_ONESHOT (1 << 1) +#define TIMER_CTRL_INTR (1 << 2) +#define TIMER_RIS_ACK (1 << 0) +#define TIMER_RST_CLR (1 << 6) +#define TIMER_MODE (1 << 0) + +static void timer_update_irq(struct Msf2Timer *st) +{ + bool isr, ier; + + isr = !!(st->regs[R_TIM_RIS] & TIMER_RIS_ACK); + ier = !!(st->regs[R_TIM_CTRL] & TIMER_CTRL_INTR); + qemu_set_irq(st->irq, (ier && isr)); +} + +static void timer_update(struct Msf2Timer *st) +{ + uint64_t count; + + if (!(st->regs[R_TIM_CTRL] & TIMER_CTRL_ENBL)) { + ptimer_stop(st->ptimer); + return; + } + + count = st->regs[R_TIM_LOADVAL]; + ptimer_set_limit(st->ptimer, count, 1); + ptimer_run(st->ptimer, 1); +} + +static uint64_t +timer_read(void *opaque, hwaddr offset, unsigned int size) +{ + MSSTimerState *t = opaque; + hwaddr addr; + struct Msf2Timer *st; + uint32_t ret = 0; + int timer = 0; + int isr; + int ier; + + addr = offset >> 2; + /* + * Two independent timers has same base address. + * Based on address passed figure out which timer is being used. + */ + if ((addr >= R_TIM1_MAX) && (addr < NUM_TIMERS * R_TIM1_MAX)) { + timer = 1; + addr -= R_TIM1_MAX; + } + + st = &t->timers[timer]; + + switch (addr) { + case R_TIM_VAL: + ret = ptimer_get_count(st->ptimer); + break; + + case R_TIM_MIS: + isr = !!(st->regs[R_TIM_RIS] & TIMER_RIS_ACK); + ier = !!(st->regs[R_TIM_CTRL] & TIMER_CTRL_INTR); + ret = ier & isr; + break; + + default: + if (addr < R_TIM1_MAX) { + ret = st->regs[addr]; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + TYPE_MSS_TIMER": 64-bit mode not supported\n"); + return ret; + } + break; + } + + DB_PRINT("timer=%d 0x%" HWADDR_PRIx "=0x%" PRIx32, timer, offset, + ret); + return ret; +} + +static void +timer_write(void *opaque, hwaddr offset, + uint64_t val64, unsigned int size) +{ + MSSTimerState *t = opaque; + hwaddr addr; + struct Msf2Timer *st; + int timer = 0; + uint32_t value = val64; + + addr = offset >> 2; + /* + * Two independent timers has same base address. + * Based on addr passed figure out which timer is being used. + */ + if ((addr >= R_TIM1_MAX) && (addr < NUM_TIMERS * R_TIM1_MAX)) { + timer = 1; + addr -= R_TIM1_MAX; + } + + st = &t->timers[timer]; + + DB_PRINT("addr=0x%" HWADDR_PRIx " val=0x%" PRIx32 " (timer=%d)", offset, + value, timer); + + switch (addr) { + case R_TIM_CTRL: + st->regs[R_TIM_CTRL] = value; + timer_update(st); + break; + + case R_TIM_RIS: + if (value & TIMER_RIS_ACK) { + st->regs[R_TIM_RIS] &= ~TIMER_RIS_ACK; + } + break; + + case R_TIM_LOADVAL: + st->regs[R_TIM_LOADVAL] = value; + if (st->regs[R_TIM_CTRL] & TIMER_CTRL_ENBL) { + timer_update(st); + } + break; + + case R_TIM_BGLOADVAL: + st->regs[R_TIM_BGLOADVAL] = value; + st->regs[R_TIM_LOADVAL] = value; + break; + + case R_TIM_VAL: + case R_TIM_MIS: + break; + + default: + if (addr < R_TIM1_MAX) { + st->regs[addr] = value; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + TYPE_MSS_TIMER": 64-bit mode not supported\n"); + return; + } + break; + } + timer_update_irq(st); +} + +static const MemoryRegionOps timer_ops = { + .read = timer_read, + .write = timer_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 4 + } +}; + +static void timer_hit(void *opaque) +{ + struct Msf2Timer *st = opaque; + + st->regs[R_TIM_RIS] |= TIMER_RIS_ACK; + + if (!(st->regs[R_TIM_CTRL] & TIMER_CTRL_ONESHOT)) { + timer_update(st); + } + timer_update_irq(st); +} + +static void mss_timer_init(Object *obj) +{ + MSSTimerState *t = MSS_TIMER(obj); + int i; + + /* Init all the ptimers. */ + for (i = 0; i < NUM_TIMERS; i++) { + struct Msf2Timer *st = &t->timers[i]; + + st->bh = qemu_bh_new(timer_hit, st); + st->ptimer = ptimer_init(st->bh, PTIMER_POLICY_DEFAULT); + ptimer_set_freq(st->ptimer, t->freq_hz); + sysbus_init_irq(SYS_BUS_DEVICE(obj), &st->irq); + } + + memory_region_init_io(&t->mmio, OBJECT(t), &timer_ops, t, TYPE_MSS_TIMER, + NUM_TIMERS * R_TIM1_MAX * 4); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &t->mmio); +} + +static const VMStateDescription vmstate_timers = { + .name = "mss-timer-block", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_PTIMER(ptimer, struct Msf2Timer), + VMSTATE_UINT32_ARRAY(regs, struct Msf2Timer, R_TIM1_MAX), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_mss_timer = { + .name = TYPE_MSS_TIMER, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(freq_hz, MSSTimerState), + VMSTATE_STRUCT_ARRAY(timers, MSSTimerState, NUM_TIMERS, 0, + vmstate_timers, struct Msf2Timer), + VMSTATE_END_OF_LIST() + } +}; + +static Property mss_timer_properties[] = { + /* Libero GUI shows 100Mhz as default for clocks */ + DEFINE_PROP_UINT32("clock-frequency", MSSTimerState, freq_hz, + 100 * 1000000), + DEFINE_PROP_END_OF_LIST(), +}; + +static void mss_timer_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->props = mss_timer_properties; + dc->vmsd = &vmstate_mss_timer; +} + +static const TypeInfo mss_timer_info = { + .name = TYPE_MSS_TIMER, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MSSTimerState), + .instance_init = mss_timer_init, + .class_init = mss_timer_class_init, +}; + +static void mss_timer_register_types(void) +{ + type_register_static(&mss_timer_info); +} + +type_init(mss_timer_register_types) -- 2.7.4 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Added Sytem register block of Smartfusion2. This block has PLL registers which are accessed by guest. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Acked-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170920201737.25723-3-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/misc/msf2-sysreg.h | 77 ++++++++++++++++++++ hw/misc/msf2-sysreg.c | 160 ++++++++++++++++++++++++++++++++++++++++++ hw/misc/trace-events | 5 ++ 4 files changed, 243 insertions(+) create mode 100644 include/hw/misc/msf2-sysreg.h create mode 100644 hw/misc/msf2-sysreg.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_HYPERV_TESTDEV) += hyperv_testdev.o obj-$(CONFIG_AUX) += auxbus.o obj-$(CONFIG_ASPEED_SOC) += aspeed_scu.o aspeed_sdmc.o obj-y += mmio_interface.o +obj-$(CONFIG_MSF2) += msf2-sysreg.o diff --git a/include/hw/misc/msf2-sysreg.h b/include/hw/misc/msf2-sysreg.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/msf2-sysreg.h @@ -XXX,XX +XXX,XX @@ +/* + * Microsemi SmartFusion2 SYSREG + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_MSF2_SYSREG_H +#define HW_MSF2_SYSREG_H + +#include "hw/sysbus.h" + +enum { + ESRAM_CR = 0x00 / 4, + ESRAM_MAX_LAT, + DDR_CR, + ENVM_CR, + ENVM_REMAP_BASE_CR, + ENVM_REMAP_FAB_CR, + CC_CR, + CC_REGION_CR, + CC_LOCK_BASE_ADDR_CR, + CC_FLUSH_INDX_CR, + DDRB_BUF_TIMER_CR, + DDRB_NB_ADDR_CR, + DDRB_NB_SIZE_CR, + DDRB_CR, + + SOFT_RESET_CR = 0x48 / 4, + M3_CR, + + GPIO_SYSRESET_SEL_CR = 0x58 / 4, + + MDDR_CR = 0x60 / 4, + + MSSDDR_PLL_STATUS_LOW_CR = 0x90 / 4, + MSSDDR_PLL_STATUS_HIGH_CR, + MSSDDR_FACC1_CR, + MSSDDR_FACC2_CR, + + MSSDDR_PLL_STATUS = 0x150 / 4, +}; + +#define MSF2_SYSREG_MMIO_SIZE 0x300 + +#define TYPE_MSF2_SYSREG "msf2-sysreg" +#define MSF2_SYSREG(obj) OBJECT_CHECK(MSF2SysregState, (obj), TYPE_MSF2_SYSREG) + +typedef struct MSF2SysregState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + + uint8_t apb0div; + uint8_t apb1div; + + uint32_t regs[MSF2_SYSREG_MMIO_SIZE / 4]; +} MSF2SysregState; + +#endif /* HW_MSF2_SYSREG_H */ diff --git a/hw/misc/msf2-sysreg.c b/hw/misc/msf2-sysreg.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/msf2-sysreg.c @@ -XXX,XX +XXX,XX @@ +/* + * System Register block model of Microsemi SmartFusion2. + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/log.h" +#include "hw/misc/msf2-sysreg.h" +#include "qemu/error-report.h" +#include "trace.h" + +static inline int msf2_divbits(uint32_t div) +{ + int r = ctz32(div); + + return (div < 8) ? r : r + 1; +} + +static void msf2_sysreg_reset(DeviceState *d) +{ + MSF2SysregState *s = MSF2_SYSREG(d); + + s->regs[MSSDDR_PLL_STATUS_LOW_CR] = 0x021A2358; + s->regs[MSSDDR_PLL_STATUS] = 0x3; + s->regs[MSSDDR_FACC1_CR] = msf2_divbits(s->apb0div) << 5 | + msf2_divbits(s->apb1div) << 2; +} + +static uint64_t msf2_sysreg_read(void *opaque, hwaddr offset, + unsigned size) +{ + MSF2SysregState *s = opaque; + uint32_t ret = 0; + + offset >>= 2; + if (offset < ARRAY_SIZE(s->regs)) { + ret = s->regs[offset]; + trace_msf2_sysreg_read(offset << 2, ret); + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%08" HWADDR_PRIx "\n", __func__, + offset << 2); + } + + return ret; +} + +static void msf2_sysreg_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + MSF2SysregState *s = opaque; + uint32_t newval = val; + + offset >>= 2; + + switch (offset) { + case MSSDDR_PLL_STATUS: + trace_msf2_sysreg_write_pll_status(); + break; + + case ESRAM_CR: + case DDR_CR: + case ENVM_REMAP_BASE_CR: + if (newval != s->regs[offset]) { + qemu_log_mask(LOG_UNIMP, + TYPE_MSF2_SYSREG": remapping not supported\n"); + } + break; + + default: + if (offset < ARRAY_SIZE(s->regs)) { + trace_msf2_sysreg_write(offset << 2, newval, s->regs[offset]); + s->regs[offset] = newval; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%08" HWADDR_PRIx "\n", __func__, + offset << 2); + } + break; + } +} + +static const MemoryRegionOps sysreg_ops = { + .read = msf2_sysreg_read, + .write = msf2_sysreg_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static void msf2_sysreg_init(Object *obj) +{ + MSF2SysregState *s = MSF2_SYSREG(obj); + + memory_region_init_io(&s->iomem, obj, &sysreg_ops, s, TYPE_MSF2_SYSREG, + MSF2_SYSREG_MMIO_SIZE); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->iomem); +} + +static const VMStateDescription vmstate_msf2_sysreg = { + .name = TYPE_MSF2_SYSREG, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, MSF2SysregState, MSF2_SYSREG_MMIO_SIZE / 4), + VMSTATE_END_OF_LIST() + } +}; + +static Property msf2_sysreg_properties[] = { + /* default divisors in Libero GUI */ + DEFINE_PROP_UINT8("apb0divisor", MSF2SysregState, apb0div, 2), + DEFINE_PROP_UINT8("apb1divisor", MSF2SysregState, apb1div, 2), + DEFINE_PROP_END_OF_LIST(), +}; + +static void msf2_sysreg_realize(DeviceState *dev, Error **errp) +{ + MSF2SysregState *s = MSF2_SYSREG(dev); + + if ((s->apb0div > 32 || !is_power_of_2(s->apb0div)) + || (s->apb1div > 32 || !is_power_of_2(s->apb1div))) { + error_setg(errp, "Invalid apb divisor value"); + error_append_hint(errp, "apb divisor must be a power of 2" + " and maximum value is 32\n"); + } +} + +static void msf2_sysreg_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_msf2_sysreg; + dc->reset = msf2_sysreg_reset; + dc->props = msf2_sysreg_properties; + dc->realize = msf2_sysreg_realize; +} + +static const TypeInfo msf2_sysreg_info = { + .name = TYPE_MSF2_SYSREG, + .parent = TYPE_SYS_BUS_DEVICE, + .class_init = msf2_sysreg_class_init, + .instance_size = sizeof(MSF2SysregState), + .instance_init = msf2_sysreg_init, +}; + +static void msf2_sysreg_register_types(void) +{ + type_register_static(&msf2_sysreg_info); +} + +type_init(msf2_sysreg_register_types) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ mps2_scc_reset(void) "MPS2 SCC: reset" mps2_scc_leds(char led7, char led6, char led5, char led4, char led3, char led2, char led1, char led0) "MPS2 SCC LEDs: %c%c%c%c%c%c%c%c" mps2_scc_cfg_write(unsigned function, unsigned device, uint32_t value) "MPS2 SCC config write: function %d device %d data 0x%" PRIx32 mps2_scc_cfg_read(unsigned function, unsigned device, uint32_t value) "MPS2 SCC config read: function %d device %d data 0x%" PRIx32 + +# hw/misc/msf2-sysreg.c +msf2_sysreg_write(uint64_t offset, uint32_t val, uint32_t prev) "msf2-sysreg write: addr 0x%08" HWADDR_PRIx " data 0x%" PRIx32 " prev 0x%" PRIx32 +msf2_sysreg_read(uint64_t offset, uint32_t val) "msf2-sysreg read: addr 0x%08" HWADDR_PRIx " data 0x%08" PRIx32 +msf2_sysreg_write_pll_status(void) "Invalid write to read only PLL status register" -- 2.7.4 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Modelled Microsemi's Smartfusion2 SPI controller. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170920201737.25723-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/Makefile.objs | 1 + include/hw/ssi/mss-spi.h | 58 +++++++ hw/ssi/mss-spi.c | 404 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 463 insertions(+) create mode 100644 include/hw/ssi/mss-spi.h create mode 100644 hw/ssi/mss-spi.c diff --git a/hw/ssi/Makefile.objs b/hw/ssi/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/Makefile.objs +++ b/hw/ssi/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_XILINX_SPI) += xilinx_spi.o common-obj-$(CONFIG_XILINX_SPIPS) += xilinx_spips.o common-obj-$(CONFIG_ASPEED_SOC) += aspeed_smc.o common-obj-$(CONFIG_STM32F2XX_SPI) += stm32f2xx_spi.o +common-obj-$(CONFIG_MSF2) += mss-spi.o obj-$(CONFIG_OMAP) += omap_spi.o obj-$(CONFIG_IMX) += imx_spi.o diff --git a/include/hw/ssi/mss-spi.h b/include/hw/ssi/mss-spi.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/ssi/mss-spi.h @@ -XXX,XX +XXX,XX @@ +/* + * Microsemi SmartFusion2 SPI + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_MSS_SPI_H +#define HW_MSS_SPI_H + +#include "hw/sysbus.h" +#include "hw/ssi/ssi.h" +#include "qemu/fifo32.h" + +#define TYPE_MSS_SPI "mss-spi" +#define MSS_SPI(obj) OBJECT_CHECK(MSSSpiState, (obj), TYPE_MSS_SPI) + +#define R_SPI_MAX 16 + +typedef struct MSSSpiState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + qemu_irq irq; + + qemu_irq cs_line; + + SSIBus *spi; + + Fifo32 rx_fifo; + Fifo32 tx_fifo; + + int fifo_depth; + uint32_t frame_count; + bool enabled; + + uint32_t regs[R_SPI_MAX]; +} MSSSpiState; + +#endif /* HW_MSS_SPI_H */ diff --git a/hw/ssi/mss-spi.c b/hw/ssi/mss-spi.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/ssi/mss-spi.c @@ -XXX,XX +XXX,XX @@ +/* + * Block model of SPI controller present in + * Microsemi's SmartFusion2 and SmartFusion SoCs. + * + * Copyright (C) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/ssi/mss-spi.h" +#include "qemu/log.h" + +#ifndef MSS_SPI_ERR_DEBUG +#define MSS_SPI_ERR_DEBUG 0 +#endif + +#define DB_PRINT_L(lvl, fmt, args...) do { \ + if (MSS_SPI_ERR_DEBUG >= lvl) { \ + qemu_log("%s: " fmt "\n", __func__, ## args); \ + } \ +} while (0); + +#define DB_PRINT(fmt, args...) DB_PRINT_L(1, fmt, ## args) + +#define FIFO_CAPACITY 32 + +#define R_SPI_CONTROL 0 +#define R_SPI_DFSIZE 1 +#define R_SPI_STATUS 2 +#define R_SPI_INTCLR 3 +#define R_SPI_RX 4 +#define R_SPI_TX 5 +#define R_SPI_CLKGEN 6 +#define R_SPI_SS 7 +#define R_SPI_MIS 8 +#define R_SPI_RIS 9 + +#define S_TXDONE (1 << 0) +#define S_RXRDY (1 << 1) +#define S_RXCHOVRF (1 << 2) +#define S_RXFIFOFUL (1 << 4) +#define S_RXFIFOFULNXT (1 << 5) +#define S_RXFIFOEMP (1 << 6) +#define S_RXFIFOEMPNXT (1 << 7) +#define S_TXFIFOFUL (1 << 8) +#define S_TXFIFOFULNXT (1 << 9) +#define S_TXFIFOEMP (1 << 10) +#define S_TXFIFOEMPNXT (1 << 11) +#define S_FRAMESTART (1 << 12) +#define S_SSEL (1 << 13) +#define S_ACTIVE (1 << 14) + +#define C_ENABLE (1 << 0) +#define C_MODE (1 << 1) +#define C_INTRXDATA (1 << 4) +#define C_INTTXDATA (1 << 5) +#define C_INTRXOVRFLO (1 << 6) +#define C_SPS (1 << 26) +#define C_BIGFIFO (1 << 29) +#define C_RESET (1 << 31) + +#define FRAMESZ_MASK 0x1F +#define FMCOUNT_MASK 0x00FFFF00 +#define FMCOUNT_SHIFT 8 + +static void txfifo_reset(MSSSpiState *s) +{ + fifo32_reset(&s->tx_fifo); + + s->regs[R_SPI_STATUS] &= ~S_TXFIFOFUL; + s->regs[R_SPI_STATUS] |= S_TXFIFOEMP; +} + +static void rxfifo_reset(MSSSpiState *s) +{ + fifo32_reset(&s->rx_fifo); + + s->regs[R_SPI_STATUS] &= ~S_RXFIFOFUL; + s->regs[R_SPI_STATUS] |= S_RXFIFOEMP; +} + +static void set_fifodepth(MSSSpiState *s) +{ + unsigned int size = s->regs[R_SPI_DFSIZE] & FRAMESZ_MASK; + + if (size <= 8) { + s->fifo_depth = 32; + } else if (size <= 16) { + s->fifo_depth = 16; + } else if (size <= 32) { + s->fifo_depth = 8; + } else { + s->fifo_depth = 4; + } +} + +static void update_mis(MSSSpiState *s) +{ + uint32_t reg = s->regs[R_SPI_CONTROL]; + uint32_t tmp; + + /* + * form the Control register interrupt enable bits + * same as RIS, MIS and Interrupt clear registers for simplicity + */ + tmp = ((reg & C_INTRXOVRFLO) >> 4) | ((reg & C_INTRXDATA) >> 3) | + ((reg & C_INTTXDATA) >> 5); + s->regs[R_SPI_MIS] |= tmp & s->regs[R_SPI_RIS]; +} + +static void spi_update_irq(MSSSpiState *s) +{ + int irq; + + update_mis(s); + irq = !!(s->regs[R_SPI_MIS]); + + qemu_set_irq(s->irq, irq); +} + +static void mss_spi_reset(DeviceState *d) +{ + MSSSpiState *s = MSS_SPI(d); + + memset(s->regs, 0, sizeof s->regs); + s->regs[R_SPI_CONTROL] = 0x80000102; + s->regs[R_SPI_DFSIZE] = 0x4; + s->regs[R_SPI_STATUS] = S_SSEL | S_TXFIFOEMP | S_RXFIFOEMP; + s->regs[R_SPI_CLKGEN] = 0x7; + s->regs[R_SPI_RIS] = 0x0; + + s->fifo_depth = 4; + s->frame_count = 1; + s->enabled = false; + + rxfifo_reset(s); + txfifo_reset(s); +} + +static uint64_t +spi_read(void *opaque, hwaddr addr, unsigned int size) +{ + MSSSpiState *s = opaque; + uint32_t ret = 0; + + addr >>= 2; + switch (addr) { + case R_SPI_RX: + s->regs[R_SPI_STATUS] &= ~S_RXFIFOFUL; + s->regs[R_SPI_STATUS] &= ~S_RXCHOVRF; + ret = fifo32_pop(&s->rx_fifo); + if (fifo32_is_empty(&s->rx_fifo)) { + s->regs[R_SPI_STATUS] |= S_RXFIFOEMP; + } + break; + + case R_SPI_MIS: + update_mis(s); + ret = s->regs[R_SPI_MIS]; + break; + + default: + if (addr < ARRAY_SIZE(s->regs)) { + ret = s->regs[addr]; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return ret; + } + break; + } + + DB_PRINT("addr=0x%" HWADDR_PRIx " = 0x%" PRIx32, addr * 4, ret); + spi_update_irq(s); + return ret; +} + +static void assert_cs(MSSSpiState *s) +{ + qemu_set_irq(s->cs_line, 0); +} + +static void deassert_cs(MSSSpiState *s) +{ + qemu_set_irq(s->cs_line, 1); +} + +static void spi_flush_txfifo(MSSSpiState *s) +{ + uint32_t tx; + uint32_t rx; + bool sps = !!(s->regs[R_SPI_CONTROL] & C_SPS); + + /* + * Chip Select(CS) is automatically controlled by this controller. + * If SPS bit is set in Control register then CS is asserted + * until all the frames set in frame count of Control register are + * transferred. If SPS is not set then CS pulses between frames. + * Note that Slave Select register specifies which of the CS line + * has to be controlled automatically by controller. Bits SS[7:1] are for + * masters in FPGA fabric since we model only Microcontroller subsystem + * of Smartfusion2 we control only one CS(SS[0]) line. + */ + while (!fifo32_is_empty(&s->tx_fifo) && s->frame_count) { + assert_cs(s); + + s->regs[R_SPI_STATUS] &= ~(S_TXDONE | S_RXRDY); + + tx = fifo32_pop(&s->tx_fifo); + DB_PRINT("data tx:0x%" PRIx32, tx); + rx = ssi_transfer(s->spi, tx); + DB_PRINT("data rx:0x%" PRIx32, rx); + + if (fifo32_num_used(&s->rx_fifo) == s->fifo_depth) { + s->regs[R_SPI_STATUS] |= S_RXCHOVRF; + s->regs[R_SPI_RIS] |= S_RXCHOVRF; + } else { + fifo32_push(&s->rx_fifo, rx); + s->regs[R_SPI_STATUS] &= ~S_RXFIFOEMP; + if (fifo32_num_used(&s->rx_fifo) == (s->fifo_depth - 1)) { + s->regs[R_SPI_STATUS] |= S_RXFIFOFULNXT; + } else if (fifo32_num_used(&s->rx_fifo) == s->fifo_depth) { + s->regs[R_SPI_STATUS] |= S_RXFIFOFUL; + } + } + s->frame_count--; + if (!sps) { + deassert_cs(s); + } + } + + if (!s->frame_count) { + s->frame_count = (s->regs[R_SPI_CONTROL] & FMCOUNT_MASK) >> + FMCOUNT_SHIFT; + deassert_cs(s); + s->regs[R_SPI_RIS] |= S_TXDONE | S_RXRDY; + s->regs[R_SPI_STATUS] |= S_TXDONE | S_RXRDY; + } +} + +static void spi_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) +{ + MSSSpiState *s = opaque; + uint32_t value = val64; + + DB_PRINT("addr=0x%" HWADDR_PRIx " =0x%" PRIx32, addr, value); + addr >>= 2; + + switch (addr) { + case R_SPI_TX: + /* adding to already full FIFO */ + if (fifo32_num_used(&s->tx_fifo) == s->fifo_depth) { + break; + } + s->regs[R_SPI_STATUS] &= ~S_TXFIFOEMP; + fifo32_push(&s->tx_fifo, value); + if (fifo32_num_used(&s->tx_fifo) == (s->fifo_depth - 1)) { + s->regs[R_SPI_STATUS] |= S_TXFIFOFULNXT; + } else if (fifo32_num_used(&s->tx_fifo) == s->fifo_depth) { + s->regs[R_SPI_STATUS] |= S_TXFIFOFUL; + } + if (s->enabled) { + spi_flush_txfifo(s); + } + break; + + case R_SPI_CONTROL: + s->regs[R_SPI_CONTROL] = value; + if (value & C_BIGFIFO) { + set_fifodepth(s); + } else { + s->fifo_depth = 4; + } + s->enabled = value & C_ENABLE; + s->frame_count = (value & FMCOUNT_MASK) >> FMCOUNT_SHIFT; + if (value & C_RESET) { + mss_spi_reset(DEVICE(s)); + } + break; + + case R_SPI_DFSIZE: + if (s->enabled) { + break; + } + s->regs[R_SPI_DFSIZE] = value; + break; + + case R_SPI_INTCLR: + s->regs[R_SPI_INTCLR] = value; + if (value & S_TXDONE) { + s->regs[R_SPI_RIS] &= ~S_TXDONE; + } + if (value & S_RXRDY) { + s->regs[R_SPI_RIS] &= ~S_RXRDY; + } + if (value & S_RXCHOVRF) { + s->regs[R_SPI_RIS] &= ~S_RXCHOVRF; + } + break; + + case R_SPI_MIS: + case R_SPI_STATUS: + case R_SPI_RIS: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Write to read only register 0x%" HWADDR_PRIx "\n", + __func__, addr * 4); + break; + + default: + if (addr < ARRAY_SIZE(s->regs)) { + s->regs[addr] = value; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + } + break; + } + + spi_update_irq(s); +} + +static const MemoryRegionOps spi_ops = { + .read = spi_read, + .write = spi_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 4 + } +}; + +static void mss_spi_realize(DeviceState *dev, Error **errp) +{ + MSSSpiState *s = MSS_SPI(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + + s->spi = ssi_create_bus(dev, "spi"); + + sysbus_init_irq(sbd, &s->irq); + ssi_auto_connect_slaves(dev, &s->cs_line, s->spi); + sysbus_init_irq(sbd, &s->cs_line); + + memory_region_init_io(&s->mmio, OBJECT(s), &spi_ops, s, + TYPE_MSS_SPI, R_SPI_MAX * 4); + sysbus_init_mmio(sbd, &s->mmio); + + fifo32_create(&s->tx_fifo, FIFO_CAPACITY); + fifo32_create(&s->rx_fifo, FIFO_CAPACITY); +} + +static const VMStateDescription vmstate_mss_spi = { + .name = TYPE_MSS_SPI, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_FIFO32(tx_fifo, MSSSpiState), + VMSTATE_FIFO32(rx_fifo, MSSSpiState), + VMSTATE_UINT32_ARRAY(regs, MSSSpiState, R_SPI_MAX), + VMSTATE_END_OF_LIST() + } +}; + +static void mss_spi_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = mss_spi_realize; + dc->reset = mss_spi_reset; + dc->vmsd = &vmstate_mss_spi; +} + +static const TypeInfo mss_spi_info = { + .name = TYPE_MSS_SPI, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MSSSpiState), + .class_init = mss_spi_class_init, +}; + +static void mss_spi_register_types(void) +{ + type_register_static(&mss_spi_info); +} + +type_init(mss_spi_register_types) -- 2.7.4 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Smartfusion2 SoC has hardened Microcontroller subsystem and flash based FPGA fabric. This patch adds support for Microcontroller subsystem in the SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170920201737.25723-5-f4bug@amsat.org [PMD: drop cpu_model to directly use cpu type, check m3clk non null] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 1 + include/hw/arm/msf2-soc.h | 67 +++++++++++ hw/arm/msf2-soc.c | 238 ++++++++++++++++++++++++++++++++++++++++ default-configs/arm-softmmu.mak | 1 + 4 files changed, 307 insertions(+) create mode 100644 include/hw/arm/msf2-soc.h create mode 100644 hw/arm/msf2-soc.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_FSL_IMX31) += fsl-imx31.o kzm.o obj-$(CONFIG_FSL_IMX6) += fsl-imx6.o sabrelite.o obj-$(CONFIG_ASPEED_SOC) += aspeed_soc.o aspeed.o obj-$(CONFIG_MPS2) += mps2.o +obj-$(CONFIG_MSF2) += msf2-soc.o diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ +/* + * Microsemi Smartfusion2 SoC + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_ARM_MSF2_SOC_H +#define HW_ARM_MSF2_SOC_H + +#include "hw/arm/armv7m.h" +#include "hw/timer/mss-timer.h" +#include "hw/misc/msf2-sysreg.h" +#include "hw/ssi/mss-spi.h" + +#define TYPE_MSF2_SOC "msf2-soc" +#define MSF2_SOC(obj) OBJECT_CHECK(MSF2State, (obj), TYPE_MSF2_SOC) + +#define MSF2_NUM_SPIS 2 +#define MSF2_NUM_UARTS 2 + +/* + * System timer consists of two programmable 32-bit + * decrementing counters that generate individual interrupts to + * the Cortex-M3 processor + */ +#define MSF2_NUM_TIMERS 2 + +typedef struct MSF2State { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + ARMv7MState armv7m; + + char *cpu_type; + char *part_name; + uint64_t envm_size; + uint64_t esram_size; + + uint32_t m3clk; + uint8_t apb0div; + uint8_t apb1div; + + MSF2SysregState sysreg; + MSSTimerState timer; + MSSSpiState spi[MSF2_NUM_SPIS]; +} MSF2State; + +#endif diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ +/* + * SmartFusion2 SoC emulation. + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "hw/arm/arm.h" +#include "exec/address-spaces.h" +#include "hw/char/serial.h" +#include "hw/boards.h" +#include "sysemu/block-backend.h" +#include "qemu/cutils.h" +#include "hw/arm/msf2-soc.h" +#include "hw/misc/unimp.h" + +#define MSF2_TIMER_BASE 0x40004000 +#define MSF2_SYSREG_BASE 0x40038000 + +#define ENVM_BASE_ADDRESS 0x60000000 + +#define SRAM_BASE_ADDRESS 0x20000000 + +#define MSF2_ENVM_MAX_SIZE (512 * K_BYTE) + +/* + * eSRAM max size is 80k without SECDED(Single error correction and + * dual error detection) feature and 64k with SECDED. + * We do not support SECDED now. + */ +#define MSF2_ESRAM_MAX_SIZE (80 * K_BYTE) + +static const uint32_t spi_addr[MSF2_NUM_SPIS] = { 0x40001000 , 0x40011000 }; +static const uint32_t uart_addr[MSF2_NUM_UARTS] = { 0x40000000 , 0x40010000 }; + +static const int spi_irq[MSF2_NUM_SPIS] = { 2, 3 }; +static const int uart_irq[MSF2_NUM_UARTS] = { 10, 11 }; +static const int timer_irq[MSF2_NUM_TIMERS] = { 14, 15 }; + +static void m2sxxx_soc_initfn(Object *obj) +{ + MSF2State *s = MSF2_SOC(obj); + int i; + + object_initialize(&s->armv7m, sizeof(s->armv7m), TYPE_ARMV7M); + qdev_set_parent_bus(DEVICE(&s->armv7m), sysbus_get_default()); + + object_initialize(&s->sysreg, sizeof(s->sysreg), TYPE_MSF2_SYSREG); + qdev_set_parent_bus(DEVICE(&s->sysreg), sysbus_get_default()); + + object_initialize(&s->timer, sizeof(s->timer), TYPE_MSS_TIMER); + qdev_set_parent_bus(DEVICE(&s->timer), sysbus_get_default()); + + for (i = 0; i < MSF2_NUM_SPIS; i++) { + object_initialize(&s->spi[i], sizeof(s->spi[i]), + TYPE_MSS_SPI); + qdev_set_parent_bus(DEVICE(&s->spi[i]), sysbus_get_default()); + } +} + +static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) +{ + MSF2State *s = MSF2_SOC(dev_soc); + DeviceState *dev, *armv7m; + SysBusDevice *busdev; + Error *err = NULL; + int i; + + MemoryRegion *system_memory = get_system_memory(); + MemoryRegion *nvm = g_new(MemoryRegion, 1); + MemoryRegion *nvm_alias = g_new(MemoryRegion, 1); + MemoryRegion *sram = g_new(MemoryRegion, 1); + + memory_region_init_rom(nvm, NULL, "MSF2.eNVM", s->envm_size, + &error_fatal); + /* + * On power-on, the eNVM region 0x60000000 is automatically + * remapped to the Cortex-M3 processor executable region + * start address (0x0). We do not support remapping other eNVM, + * eSRAM and DDR regions by guest(via Sysreg) currently. + */ + memory_region_init_alias(nvm_alias, NULL, "MSF2.eNVM", + nvm, 0, s->envm_size); + + memory_region_add_subregion(system_memory, ENVM_BASE_ADDRESS, nvm); + memory_region_add_subregion(system_memory, 0, nvm_alias); + + memory_region_init_ram(sram, NULL, "MSF2.eSRAM", s->esram_size, + &error_fatal); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + + armv7m = DEVICE(&s->armv7m); + qdev_prop_set_uint32(armv7m, "num-irq", 81); + qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); + object_property_set_link(OBJECT(&s->armv7m), OBJECT(get_system_memory()), + "memory", &error_abort); + object_property_set_bool(OBJECT(&s->armv7m), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + + if (!s->m3clk) { + error_setg(errp, "Invalid m3clk value"); + error_append_hint(errp, "m3clk can not be zero\n"); + return; + } + system_clock_scale = NANOSECONDS_PER_SECOND / s->m3clk; + + for (i = 0; i < MSF2_NUM_UARTS; i++) { + if (serial_hds[i]) { + serial_mm_init(get_system_memory(), uart_addr[i], 2, + qdev_get_gpio_in(armv7m, uart_irq[i]), + 115200, serial_hds[i], DEVICE_NATIVE_ENDIAN); + } + } + + dev = DEVICE(&s->timer); + /* APB0 clock is the timer input clock */ + qdev_prop_set_uint32(dev, "clock-frequency", s->m3clk / s->apb0div); + object_property_set_bool(OBJECT(&s->timer), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, MSF2_TIMER_BASE); + sysbus_connect_irq(busdev, 0, + qdev_get_gpio_in(armv7m, timer_irq[0])); + sysbus_connect_irq(busdev, 1, + qdev_get_gpio_in(armv7m, timer_irq[1])); + + dev = DEVICE(&s->sysreg); + qdev_prop_set_uint32(dev, "apb0divisor", s->apb0div); + qdev_prop_set_uint32(dev, "apb1divisor", s->apb1div); + object_property_set_bool(OBJECT(&s->sysreg), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, MSF2_SYSREG_BASE); + + for (i = 0; i < MSF2_NUM_SPIS; i++) { + gchar *bus_name; + + object_property_set_bool(OBJECT(&s->spi[i]), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, spi_addr[i]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0, + qdev_get_gpio_in(armv7m, spi_irq[i])); + + /* Alias controller SPI bus to the SoC itself */ + bus_name = g_strdup_printf("spi%d", i); + object_property_add_alias(OBJECT(s), bus_name, + OBJECT(&s->spi[i]), "spi", + &error_abort); + g_free(bus_name); + } + + /* Below devices are not modelled yet. */ + create_unimplemented_device("i2c_0", 0x40002000, 0x1000); + create_unimplemented_device("dma", 0x40003000, 0x1000); + create_unimplemented_device("watchdog", 0x40005000, 0x1000); + create_unimplemented_device("i2c_1", 0x40012000, 0x1000); + create_unimplemented_device("gpio", 0x40013000, 0x1000); + create_unimplemented_device("hs-dma", 0x40014000, 0x1000); + create_unimplemented_device("can", 0x40015000, 0x1000); + create_unimplemented_device("rtc", 0x40017000, 0x1000); + create_unimplemented_device("apb_config", 0x40020000, 0x10000); + create_unimplemented_device("emac", 0x40041000, 0x1000); + create_unimplemented_device("usb", 0x40043000, 0x1000); +} + +static Property m2sxxx_soc_properties[] = { + /* + * part name specifies the type of SmartFusion2 device variant(this + * property is for information purpose only. + */ + DEFINE_PROP_STRING("cpu-type", MSF2State, cpu_type), + DEFINE_PROP_STRING("part-name", MSF2State, part_name), + DEFINE_PROP_UINT64("eNVM-size", MSF2State, envm_size, MSF2_ENVM_MAX_SIZE), + DEFINE_PROP_UINT64("eSRAM-size", MSF2State, esram_size, + MSF2_ESRAM_MAX_SIZE), + /* Libero GUI shows 100Mhz as default for clocks */ + DEFINE_PROP_UINT32("m3clk", MSF2State, m3clk, 100 * 1000000), + /* default divisors in Libero GUI */ + DEFINE_PROP_UINT8("apb0div", MSF2State, apb0div, 2), + DEFINE_PROP_UINT8("apb1div", MSF2State, apb1div, 2), + DEFINE_PROP_END_OF_LIST(), +}; + +static void m2sxxx_soc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = m2sxxx_soc_realize; + dc->props = m2sxxx_soc_properties; +} + +static const TypeInfo m2sxxx_soc_info = { + .name = TYPE_MSF2_SOC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MSF2State), + .instance_init = m2sxxx_soc_initfn, + .class_init = m2sxxx_soc_class_init, +}; + +static void m2sxxx_soc_types(void) +{ + type_register_static(&m2sxxx_soc_info); +} + +type_init(m2sxxx_soc_types) diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_ACPI=y CONFIG_SMBIOS=y CONFIG_ASPEED_SOC=y CONFIG_GPIO_KEY=y +CONFIG_MSF2=y -- 2.7.4 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Emulated Emcraft's Smartfusion2 System On Module starter kit. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170920201737.25723-6-f4bug@amsat.org [PMD: drop cpu_model to directly use cpu type] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 2 +- hw/arm/msf2-som.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 106 insertions(+), 1 deletion(-) create mode 100644 hw/arm/msf2-som.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_FSL_IMX31) += fsl-imx31.o kzm.o obj-$(CONFIG_FSL_IMX6) += fsl-imx6.o sabrelite.o obj-$(CONFIG_ASPEED_SOC) += aspeed_soc.o aspeed.o obj-$(CONFIG_MPS2) += mps2.o -obj-$(CONFIG_MSF2) += msf2-soc.o +obj-$(CONFIG_MSF2) += msf2-soc.o msf2-som.o diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/msf2-som.c @@ -XXX,XX +XXX,XX @@ +/* + * SmartFusion2 SOM starter kit(from Emcraft) emulation. + * + * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "hw/boards.h" +#include "hw/arm/arm.h" +#include "exec/address-spaces.h" +#include "qemu/cutils.h" +#include "hw/arm/msf2-soc.h" +#include "cpu.h" + +#define DDR_BASE_ADDRESS 0xA0000000 +#define DDR_SIZE (64 * M_BYTE) + +#define M2S010_ENVM_SIZE (256 * K_BYTE) +#define M2S010_ESRAM_SIZE (64 * K_BYTE) + +static void emcraft_sf2_s2s010_init(MachineState *machine) +{ + DeviceState *dev; + DeviceState *spi_flash; + MSF2State *soc; + MachineClass *mc = MACHINE_GET_CLASS(machine); + DriveInfo *dinfo = drive_get_next(IF_MTD); + qemu_irq cs_line; + SSIBus *spi_bus; + MemoryRegion *sysmem = get_system_memory(); + MemoryRegion *ddr = g_new(MemoryRegion, 1); + + if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { + error_report("This board can only be used with CPU %s", + mc->default_cpu_type); + } + + memory_region_init_ram(ddr, NULL, "ddr-ram", DDR_SIZE, + &error_fatal); + memory_region_add_subregion(sysmem, DDR_BASE_ADDRESS, ddr); + + dev = qdev_create(NULL, TYPE_MSF2_SOC); + qdev_prop_set_string(dev, "part-name", "M2S010"); + qdev_prop_set_string(dev, "cpu-type", mc->default_cpu_type); + + qdev_prop_set_uint64(dev, "eNVM-size", M2S010_ENVM_SIZE); + qdev_prop_set_uint64(dev, "eSRAM-size", M2S010_ESRAM_SIZE); + + /* + * CPU clock and peripheral clocks(APB0, APB1)are configurable + * in Libero. CPU clock is divided by APB0 and APB1 divisors for + * peripherals. Emcraft's SoM kit comes with these settings by default. + */ + qdev_prop_set_uint32(dev, "m3clk", 142 * 1000000); + qdev_prop_set_uint32(dev, "apb0div", 2); + qdev_prop_set_uint32(dev, "apb1div", 2); + + object_property_set_bool(OBJECT(dev), true, "realized", &error_fatal); + + soc = MSF2_SOC(dev); + + /* Attach SPI flash to SPI0 controller */ + spi_bus = (SSIBus *)qdev_get_child_bus(dev, "spi0"); + spi_flash = ssi_create_slave_no_init(spi_bus, "s25sl12801"); + qdev_prop_set_uint8(spi_flash, "spansion-cr2nv", 1); + if (dinfo) { + qdev_prop_set_drive(spi_flash, "drive", blk_by_legacy_dinfo(dinfo), + &error_fatal); + } + qdev_init_nofail(spi_flash); + cs_line = qdev_get_gpio_in_named(spi_flash, SSI_GPIO_CS, 0); + sysbus_connect_irq(SYS_BUS_DEVICE(&soc->spi[0]), 1, cs_line); + + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + soc->envm_size); +} + +static void emcraft_sf2_machine_init(MachineClass *mc) +{ + mc->desc = "SmartFusion2 SOM kit from Emcraft (M2S010)"; + mc->init = emcraft_sf2_s2s010_init; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m3"); +} + +DEFINE_MACHINE("emcraft-sf2", emcraft_sf2_machine_init) -- 2.7.4 As promised, another pullreq... This one's mostly RTH's patches. thanks -- PMM The following changes since commit 784c2e4f232adf5ef47a84a262ec72a07d068d6a: Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging (2018-10-19 15:30:40 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20181019 for you to fetch changes up to 88c9add25e7120e8622796c81ad3f3fb7f8d40e7: target/arm: Only flush tlb if ASID changes (2018-10-19 17:38:48 +0100) ---------------------------------------------------------------- target-arm queue: * ssi-sd: Make devices picking up backends unavailable with -device * Add support for VCPU event states * Move towards making ID registers the source of truth for whether a guest CPU implements a feature, rather than having parallel ID registers and feature bit flags * Implement various HCR hypervisor trap/config bits * Get IL bit correct for v7 syndrome values * Report correct syndrome for FP/SIMD traps to Hyp mode * hw/arm/boot: Increase compliance with kernel arm64 boot protocol * Refactor A32 Neon to use generic vector infrastructure * Fix a bug in A32 VLD2 "(multiple 2-element structures)" insn * net: cadence_gem: Report features correctly in ID register * Avoid some unnecessary TLB flushes on TTBR register writes ---------------------------------------------------------------- Dongjiu Geng (1): target/arm: Add support for VCPU event states Edgar E. Iglesias (2): net: cadence_gem: Announce availability of priority queues net: cadence_gem: Announce 64bit addressing support Markus Armbruster (1): ssi-sd: Make devices picking up backends unavailable with -device Peter Maydell (10): target/arm: Improve debug logging of AArch32 exception return target/arm: Make switch_mode() file-local target/arm: Implement HCR.FB target/arm: Implement HCR.DC target/arm: ISR_EL1 bits track virtual interrupts if IMO/FMO set target/arm: Implement HCR.VI and VF target/arm: Implement HCR.PTW target/arm: New utility function to extract EC from syndrome target/arm: Get IL bit correct for v7 syndrome values target/arm: Report correct syndrome for FP/SIMD traps to Hyp mode Richard Henderson (30): target/arm: Move some system registers into a substructure target/arm: V8M should not imply V7VE target/arm: Convert v8 extensions from feature bits to isar tests target/arm: Convert division from feature bits to isar0 tests target/arm: Convert jazelle from feature bit to isar1 test target/arm: Convert t32ee from feature bit to isar3 test target/arm: Convert sve from feature bit to aa64pfr0 test target/arm: Convert v8.2-fp16 from feature bit to aa64pfr0 test target/arm: Hoist address increment for vector memory ops target/arm: Don't call tcg_clear_temp_count target/arm: Use tcg_gen_gvec_dup_i64 for LD[1-4]R target/arm: Promote consecutive memory ops for aa64 target/arm: Mark some arrays const target/arm: Use gvec for NEON VDUP target/arm: Use gvec for NEON VMOV, VMVN, VBIC & VORR (immediate) target/arm: Use gvec for NEON_3R_LOGIC insns target/arm: Use gvec for NEON_3R_VADD_VSUB insns target/arm: Use gvec for NEON_2RM_VMN, NEON_2RM_VNEG target/arm: Use gvec for NEON_3R_VMUL target/arm: Use gvec for VSHR, VSHL target/arm: Use gvec for VSRA target/arm: Use gvec for VSRI, VSLI target/arm: Use gvec for NEON_3R_VML target/arm: Use gvec for NEON_3R_VTST_VCEQ, NEON_3R_VCGT, NEON_3R_VCGE target/arm: Use gvec for NEON VLD all lanes target/arm: Reorg NEON VLD/VST all elements target/arm: Promote consecutive memory ops for aa32 target/arm: Reorg NEON VLD/VST single element to one lane target/arm: Remove writefn from TTBR0_EL3 target/arm: Only flush tlb if ASID changes Stewart Hildebrand (1): hw/arm/boot: Increase compliance with kernel arm64 boot protocol target/arm/cpu.h | 227 ++++++- target/arm/internals.h | 45 +- target/arm/kvm_arm.h | 24 + target/arm/translate.h | 21 + hw/arm/boot.c | 18 + hw/intc/armv7m_nvic.c | 12 +- hw/net/cadence_gem.c | 9 +- hw/sd/ssi-sd.c | 2 + linux-user/aarch64/signal.c | 4 +- linux-user/elfload.c | 60 +- linux-user/syscall.c | 10 +- target/arm/cpu.c | 242 ++++---- target/arm/cpu64.c | 148 +++-- target/arm/helper.c | 397 ++++++++---- target/arm/kvm.c | 60 ++ target/arm/kvm32.c | 13 + target/arm/kvm64.c | 15 +- target/arm/machine.c | 28 +- target/arm/op_helper.c | 2 +- target/arm/translate-a64.c | 715 ++++----------------- target/arm/translate.c | 1451 ++++++++++++++++++++++++++++--------------- 21 files changed, 2021 insertions(+), 1482 deletions(-) From: Markus Armbruster <armbru@redhat.com> Device models aren't supposed to go on fishing expeditions for backends. They should expose suitable properties for the user to set. For onboard devices, board code sets them. Device ssi-sd picks up its block backend in its init() method with drive_get_next() instead. This mistake is already marked FIXME since commit af9e40a. Unset user_creatable to remove the mistake from our external interface. Since the SSI bus doesn't support hotplug, only -device can be affected. Only certain ARM machines have ssi-sd and provide an SSI bus for it; this patch breaks -device ssi-sd for these machines. No actual use of -device ssi-sd is known. Signed-off-by: Markus Armbruster <armbru@redhat.com> Acked-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Thomas Huth <thuth@redhat.com> Message-id: 20181009060835.4608-1-armbru@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/ssi-sd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/sd/ssi-sd.c b/hw/sd/ssi-sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/ssi-sd.c +++ b/hw/sd/ssi-sd.c @@ -XXX,XX +XXX,XX @@ static void ssi_sd_class_init(ObjectClass *klass, void *data) k->cs_polarity = SSI_CS_LOW; dc->vmsd = &vmstate_ssi_sd; dc->reset = ssi_sd_reset; + /* Reason: init() method uses drive_get_next() */ + dc->user_creatable = false; } static const TypeInfo ssi_sd_info = { -- 2.19.1 From: Dongjiu Geng <gengdongjiu@huawei.com> This patch extends the qemu-kvm state sync logic with support for KVM_GET/SET_VCPU_EVENTS, giving access to yet missing SError exception. And also it can support the exception state migration. The SError exception states include SError pending state and ESR value, the kvm_put/get_vcpu_events() will be called when set or get system registers. When do migration, if source machine has SError pending, QEMU will do this migration regardless whether the target machine supports to specify guest ESR value, because if target machine does not support that, it can also inject the SError with zero ESR value. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1538067351-23931-3-git-send-email-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 7 ++++++ target/arm/kvm_arm.h | 24 ++++++++++++++++++ target/arm/kvm.c | 60 ++++++++++++++++++++++++++++++++++++++++++++ target/arm/kvm32.c | 13 ++++++++++ target/arm/kvm64.c | 13 ++++++++++ target/arm/machine.c | 22 ++++++++++++++++ 6 files changed, 139 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { */ } exception; + /* Information associated with an SError */ + struct { + uint8_t pending; + uint8_t has_esr; + uint64_t esr; + } serror; + /* Thumb-2 EE state. */ uint32_t teecr; uint32_t teehbr; diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ bool write_kvmstate_to_list(ARMCPU *cpu); */ void kvm_arm_reset_vcpu(ARMCPU *cpu); +/** + * kvm_arm_init_serror_injection: + * @cs: CPUState + * + * Check whether KVM can set guest SError syndrome. + */ +void kvm_arm_init_serror_injection(CPUState *cs); + +/** + * kvm_get_vcpu_events: + * @cpu: ARMCPU + * + * Get VCPU related state from kvm. + */ +int kvm_get_vcpu_events(ARMCPU *cpu); + +/** + * kvm_put_vcpu_events: + * @cpu: ARMCPU + * + * Put VCPU related state to kvm. + */ +int kvm_put_vcpu_events(ARMCPU *cpu); + #ifdef CONFIG_KVM /** * kvm_arm_create_scratch_host_vcpu: diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = { }; static bool cap_has_mp_state; +static bool cap_has_inject_serror_esr; static ARMHostCPUFeatures arm_host_cpu_features; @@ -XXX,XX +XXX,XX @@ int kvm_arm_vcpu_init(CPUState *cs) return kvm_vcpu_ioctl(cs, KVM_ARM_VCPU_INIT, &init); } +void kvm_arm_init_serror_injection(CPUState *cs) +{ + cap_has_inject_serror_esr = kvm_check_extension(cs->kvm_state, + KVM_CAP_ARM_INJECT_SERROR_ESR); +} + bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, int *fdarray, struct kvm_vcpu_init *init) @@ -XXX,XX +XXX,XX @@ int kvm_arm_sync_mpstate_to_qemu(ARMCPU *cpu) return 0; } +int kvm_put_vcpu_events(ARMCPU *cpu) +{ + CPUARMState *env = &cpu->env; + struct kvm_vcpu_events events; + int ret; + + if (!kvm_has_vcpu_events()) { + return 0; + } + + memset(&events, 0, sizeof(events)); + events.exception.serror_pending = env->serror.pending; + + /* Inject SError to guest with specified syndrome if host kernel + * supports it, otherwise inject SError without syndrome. + */ + if (cap_has_inject_serror_esr) { + events.exception.serror_has_esr = env->serror.has_esr; + events.exception.serror_esr = env->serror.esr; + } + + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_VCPU_EVENTS, &events); + if (ret) { + error_report("failed to put vcpu events"); + } + + return ret; +} + +int kvm_get_vcpu_events(ARMCPU *cpu) +{ + CPUARMState *env = &cpu->env; + struct kvm_vcpu_events events; + int ret; + + if (!kvm_has_vcpu_events()) { + return 0; + } + + memset(&events, 0, sizeof(events)); + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_VCPU_EVENTS, &events); + if (ret) { + error_report("failed to get vcpu events"); + return ret; + } + + env->serror.pending = events.exception.serror_pending; + env->serror.has_esr = events.exception.serror_has_esr; + env->serror.esr = events.exception.serror_esr; + + return 0; +} + void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run) { } diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) } cpu->mp_affinity = mpidr & ARM32_AFFINITY_MASK; + /* Check whether userspace can specify guest syndrome value */ + kvm_arm_init_serror_injection(cs); + return kvm_arm_init_cpreg_list(cpu); } @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + ret = kvm_put_vcpu_events(cpu); + if (ret) { + return ret; + } + /* Note that we do not call write_cpustate_to_list() * here, so we are only writing the tuple list back to * KVM. This is safe because nothing can change the @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) } vfp_set_fpscr(env, fpscr); + ret = kvm_get_vcpu_events(cpu); + if (ret) { + return ret; + } + if (!write_kvmstate_to_list(cpu)) { return EINVAL; } diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) kvm_arm_init_debug(cs); + /* Check whether user space can specify guest syndrome value */ + kvm_arm_init_serror_injection(cs); + return kvm_arm_init_cpreg_list(cpu); } @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + ret = kvm_put_vcpu_events(cpu); + if (ret) { + return ret; + } + if (!write_list_to_kvmstate(cpu, level)) { return EINVAL; } @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) } vfp_set_fpcr(env, fpr); + ret = kvm_get_vcpu_events(cpu); + if (ret) { + return ret; + } + if (!write_kvmstate_to_list(cpu)) { return EINVAL; } diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_sve = { }; #endif /* AARCH64 */ +static bool serror_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + CPUARMState *env = &cpu->env; + + return env->serror.pending != 0; +} + +static const VMStateDescription vmstate_serror = { + .name = "cpu/serror", + .version_id = 1, + .minimum_version_id = 1, + .needed = serror_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT8(env.serror.pending, ARMCPU), + VMSTATE_UINT8(env.serror.has_esr, ARMCPU), + VMSTATE_UINT64(env.serror.esr, ARMCPU), + VMSTATE_END_OF_LIST() + } +}; + static bool m_needed(void *opaque) { ARMCPU *cpu = opaque; @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = { #ifdef TARGET_AARCH64 &vmstate_sve, #endif + &vmstate_serror, NULL } }; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Create struct ARMISARegisters, to be accessed during translation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 32 ++++---- hw/intc/armv7m_nvic.c | 12 +-- target/arm/cpu.c | 178 +++++++++++++++++++++--------------------- target/arm/cpu64.c | 70 ++++++++--------- target/arm/helper.c | 28 +++---- 5 files changed, 162 insertions(+), 158 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { * ARMv7AR ARM Architecture Reference Manual. A reset_ prefix * is used for reset values of non-constant registers; no reset_ * prefix means a constant register. + * Some of these registers are split out into a substructure that + * is shared with the translators to control the ISA. */ + struct ARMISARegisters { + uint32_t id_isar0; + uint32_t id_isar1; + uint32_t id_isar2; + uint32_t id_isar3; + uint32_t id_isar4; + uint32_t id_isar5; + uint32_t id_isar6; + uint32_t mvfr0; + uint32_t mvfr1; + uint32_t mvfr2; + uint64_t id_aa64isar0; + uint64_t id_aa64isar1; + uint64_t id_aa64pfr0; + uint64_t id_aa64pfr1; + } isar; uint32_t midr; uint32_t revidr; uint32_t reset_fpsid; - uint32_t mvfr0; - uint32_t mvfr1; - uint32_t mvfr2; uint32_t ctr; uint32_t reset_sctlr; uint32_t id_pfr0; @@ -XXX,XX +XXX,XX @@ struct ARMCPU { uint32_t id_mmfr2; uint32_t id_mmfr3; uint32_t id_mmfr4; - uint32_t id_isar0; - uint32_t id_isar1; - uint32_t id_isar2; - uint32_t id_isar3; - uint32_t id_isar4; - uint32_t id_isar5; - uint32_t id_isar6; - uint64_t id_aa64pfr0; - uint64_t id_aa64pfr1; uint64_t id_aa64dfr0; uint64_t id_aa64dfr1; uint64_t id_aa64afr0; uint64_t id_aa64afr1; - uint64_t id_aa64isar0; - uint64_t id_aa64isar1; uint64_t id_aa64mmfr0; uint64_t id_aa64mmfr1; uint32_t dbgdidr; diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) case 0xd5c: /* MMFR3. */ return cpu->id_mmfr3; case 0xd60: /* ISAR0. */ - return cpu->id_isar0; + return cpu->isar.id_isar0; case 0xd64: /* ISAR1. */ - return cpu->id_isar1; + return cpu->isar.id_isar1; case 0xd68: /* ISAR2. */ - return cpu->id_isar2; + return cpu->isar.id_isar2; case 0xd6c: /* ISAR3. */ - return cpu->id_isar3; + return cpu->isar.id_isar3; case 0xd70: /* ISAR4. */ - return cpu->id_isar4; + return cpu->isar.id_isar4; case 0xd74: /* ISAR5. */ - return cpu->id_isar5; + return cpu->isar.id_isar5; case 0xd78: /* CLIDR */ return cpu->clidr; case 0xd7c: /* CTR */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) g_hash_table_foreach(cpu->cp_regs, cp_reg_check_reset, cpu); env->vfp.xregs[ARM_VFP_FPSID] = cpu->reset_fpsid; - env->vfp.xregs[ARM_VFP_MVFR0] = cpu->mvfr0; - env->vfp.xregs[ARM_VFP_MVFR1] = cpu->mvfr1; - env->vfp.xregs[ARM_VFP_MVFR2] = cpu->mvfr2; + env->vfp.xregs[ARM_VFP_MVFR0] = cpu->isar.mvfr0; + env->vfp.xregs[ARM_VFP_MVFR1] = cpu->isar.mvfr1; + env->vfp.xregs[ARM_VFP_MVFR2] = cpu->isar.mvfr2; cpu->power_state = cpu->start_powered_off ? PSCI_OFF : PSCI_ON; s->halted = cpu->start_powered_off; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * registers as well. These are id_pfr1[7:4] and id_aa64pfr0[15:12]. */ cpu->id_pfr1 &= ~0xf0; - cpu->id_aa64pfr0 &= ~0xf000; + cpu->isar.id_aa64pfr0 &= ~0xf000; } if (!cpu->has_el2) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * registers if we don't have EL2. These are id_pfr1[15:12] and * id_aa64pfr0_el1[11:8]. */ - cpu->id_aa64pfr0 &= ~0xf00; + cpu->isar.id_aa64pfr0 &= ~0xf00; cpu->id_pfr1 &= ~0xf000; } @@ -XXX,XX +XXX,XX @@ static void arm1136_r2_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); cpu->midr = 0x4107b362; cpu->reset_fpsid = 0x410120b4; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; @@ -XXX,XX +XXX,XX @@ static void arm1136_r2_initfn(Object *obj) cpu->id_mmfr0 = 0x01130003; cpu->id_mmfr1 = 0x10030302; cpu->id_mmfr2 = 0x01222110; - cpu->id_isar0 = 0x00140011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11231111; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x141; + cpu->isar.id_isar0 = 0x00140011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11231111; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x141; cpu->reset_auxcr = 7; } @@ -XXX,XX +XXX,XX @@ static void arm1136_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); cpu->midr = 0x4117b363; cpu->reset_fpsid = 0x410120b4; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; @@ -XXX,XX +XXX,XX @@ static void arm1136_initfn(Object *obj) cpu->id_mmfr0 = 0x01130003; cpu->id_mmfr1 = 0x10030302; cpu->id_mmfr2 = 0x01222110; - cpu->id_isar0 = 0x00140011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11231111; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x141; + cpu->isar.id_isar0 = 0x00140011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11231111; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x141; cpu->reset_auxcr = 7; } @@ -XXX,XX +XXX,XX @@ static void arm1176_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fb767; cpu->reset_fpsid = 0x410120b5; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; @@ -XXX,XX +XXX,XX @@ static void arm1176_initfn(Object *obj) cpu->id_mmfr0 = 0x01130003; cpu->id_mmfr1 = 0x10030302; cpu->id_mmfr2 = 0x01222100; - cpu->id_isar0 = 0x0140011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11231121; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x01141; + cpu->isar.id_isar0 = 0x0140011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11231121; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x01141; cpu->reset_auxcr = 7; } @@ -XXX,XX +XXX,XX @@ static void arm11mpcore_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); cpu->midr = 0x410fb022; cpu->reset_fpsid = 0x410120b4; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1d192992; /* 32K icache 32K dcache */ cpu->id_pfr0 = 0x111; cpu->id_pfr1 = 0x1; @@ -XXX,XX +XXX,XX @@ static void arm11mpcore_initfn(Object *obj) cpu->id_mmfr0 = 0x01100103; cpu->id_mmfr1 = 0x10020302; cpu->id_mmfr2 = 0x01222000; - cpu->id_isar0 = 0x00100011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11221011; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x141; + cpu->isar.id_isar0 = 0x00100011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11221011; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x141; cpu->reset_auxcr = 1; } @@ -XXX,XX +XXX,XX @@ static void cortex_m3_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x00000000; cpu->id_mmfr3 = 0x00000000; - cpu->id_isar0 = 0x01141110; - cpu->id_isar1 = 0x02111000; - cpu->id_isar2 = 0x21112231; - cpu->id_isar3 = 0x01111110; - cpu->id_isar4 = 0x01310102; - cpu->id_isar5 = 0x00000000; - cpu->id_isar6 = 0x00000000; + cpu->isar.id_isar0 = 0x01141110; + cpu->isar.id_isar1 = 0x02111000; + cpu->isar.id_isar2 = 0x21112231; + cpu->isar.id_isar3 = 0x01111110; + cpu->isar.id_isar4 = 0x01310102; + cpu->isar.id_isar5 = 0x00000000; + cpu->isar.id_isar6 = 0x00000000; } static void cortex_m4_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void cortex_m4_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x00000000; cpu->id_mmfr3 = 0x00000000; - cpu->id_isar0 = 0x01141110; - cpu->id_isar1 = 0x02111000; - cpu->id_isar2 = 0x21112231; - cpu->id_isar3 = 0x01111110; - cpu->id_isar4 = 0x01310102; - cpu->id_isar5 = 0x00000000; - cpu->id_isar6 = 0x00000000; + cpu->isar.id_isar0 = 0x01141110; + cpu->isar.id_isar1 = 0x02111000; + cpu->isar.id_isar2 = 0x21112231; + cpu->isar.id_isar3 = 0x01111110; + cpu->isar.id_isar4 = 0x01310102; + cpu->isar.id_isar5 = 0x00000000; + cpu->isar.id_isar6 = 0x00000000; } static void cortex_m33_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void cortex_m33_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x01000000; cpu->id_mmfr3 = 0x00000000; - cpu->id_isar0 = 0x01101110; - cpu->id_isar1 = 0x02212000; - cpu->id_isar2 = 0x20232232; - cpu->id_isar3 = 0x01111131; - cpu->id_isar4 = 0x01310132; - cpu->id_isar5 = 0x00000000; - cpu->id_isar6 = 0x00000000; + cpu->isar.id_isar0 = 0x01101110; + cpu->isar.id_isar1 = 0x02212000; + cpu->isar.id_isar2 = 0x20232232; + cpu->isar.id_isar3 = 0x01111131; + cpu->isar.id_isar4 = 0x01310132; + cpu->isar.id_isar5 = 0x00000000; + cpu->isar.id_isar6 = 0x00000000; cpu->clidr = 0x00000000; cpu->ctr = 0x8000c000; } @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x01200000; cpu->id_mmfr3 = 0x0211; - cpu->id_isar0 = 0x02101111; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232141; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x0010142; - cpu->id_isar5 = 0x0; - cpu->id_isar6 = 0x0; + cpu->isar.id_isar0 = 0x02101111; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232141; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x0010142; + cpu->isar.id_isar5 = 0x0; + cpu->isar.id_isar6 = 0x0; cpu->mp_is_up = true; cpu->pmsav7_dregion = 16; define_arm_cp_regs(cpu, cortexr5_cp_reginfo); @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fc080; cpu->reset_fpsid = 0x410330c0; - cpu->mvfr0 = 0x11110222; - cpu->mvfr1 = 0x00011111; + cpu->isar.mvfr0 = 0x11110222; + cpu->isar.mvfr1 = 0x00011111; cpu->ctr = 0x82048004; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x1031; @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) cpu->id_mmfr1 = 0x20000000; cpu->id_mmfr2 = 0x01202000; cpu->id_mmfr3 = 0x11; - cpu->id_isar0 = 0x00101111; - cpu->id_isar1 = 0x12112111; - cpu->id_isar2 = 0x21232031; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x00111142; + cpu->isar.id_isar0 = 0x00101111; + cpu->isar.id_isar1 = 0x12112111; + cpu->isar.id_isar2 = 0x21232031; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x00111142; cpu->dbgdidr = 0x15141000; cpu->clidr = (1 << 27) | (2 << 24) | 3; cpu->ccsidr[0] = 0xe007e01a; /* 16k L1 dcache. */ @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CBAR); cpu->midr = 0x410fc090; cpu->reset_fpsid = 0x41033090; - cpu->mvfr0 = 0x11110222; - cpu->mvfr1 = 0x01111111; + cpu->isar.mvfr0 = 0x11110222; + cpu->isar.mvfr1 = 0x01111111; cpu->ctr = 0x80038003; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x1031; @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) cpu->id_mmfr1 = 0x20000000; cpu->id_mmfr2 = 0x01230000; cpu->id_mmfr3 = 0x00002111; - cpu->id_isar0 = 0x00101111; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232041; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x00111142; + cpu->isar.id_isar0 = 0x00101111; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232041; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x00111142; cpu->dbgdidr = 0x35141000; cpu->clidr = (1 << 27) | (1 << 24) | 3; cpu->ccsidr[0] = 0xe00fe019; /* 16k L1 dcache. */ @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A7; cpu->midr = 0x410fc075; cpu->reset_fpsid = 0x41023075; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x11111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x11111111; cpu->ctr = 0x84448003; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x00001131; @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but * table 4-41 gives 0x02101110, which includes the arm div insns. */ - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232041; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x10011142; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232041; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x10011142; cpu->dbgdidr = 0x3515f005; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */ @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A15; cpu->midr = 0x412fc0f1; cpu->reset_fpsid = 0x410430f0; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x11111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x11111111; cpu->ctr = 0x8444c004; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x00001131; @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) cpu->id_mmfr1 = 0x20000000; cpu->id_mmfr2 = 0x01240000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232041; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x10011142; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232041; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x10011142; cpu->dbgdidr = 0x3515f021; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->midr = 0x411fd070; cpu->revidr = 0x00000000; cpu->reset_fpsid = 0x41034070; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x12111111; - cpu->mvfr2 = 0x00000043; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; cpu->ctr = 0x8444c004; cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->id_mmfr1 = 0x40000000; cpu->id_mmfr2 = 0x01260000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232042; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x00011142; - cpu->id_isar5 = 0x00011121; - cpu->id_isar6 = 0; - cpu->id_aa64pfr0 = 0x00002222; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_isar6 = 0; + cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; cpu->pmceid0 = 0x00000000; cpu->pmceid1 = 0x00000000; - cpu->id_aa64isar0 = 0x00011120; + cpu->isar.id_aa64isar0 = 0x00011120; cpu->id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->midr = 0x410fd034; cpu->revidr = 0x00000000; cpu->reset_fpsid = 0x41034070; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x12111111; - cpu->mvfr2 = 0x00000043; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; cpu->ctr = 0x84448004; /* L1Ip = VIPT */ cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->id_mmfr1 = 0x40000000; cpu->id_mmfr2 = 0x01260000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232042; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x00011142; - cpu->id_isar5 = 0x00011121; - cpu->id_isar6 = 0; - cpu->id_aa64pfr0 = 0x00002222; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_isar6 = 0; + cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; - cpu->id_aa64isar0 = 0x00011120; + cpu->isar.id_aa64isar0 = 0x00011120; cpu->id_aa64mmfr0 = 0x00001122; /* 40 bit physical addr */ cpu->dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->midr = 0x410fd083; cpu->revidr = 0x00000000; cpu->reset_fpsid = 0x41034080; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x12111111; - cpu->mvfr2 = 0x00000043; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; cpu->ctr = 0x8444c004; cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->id_mmfr1 = 0x40000000; cpu->id_mmfr2 = 0x01260000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232042; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x00011142; - cpu->id_isar5 = 0x00011121; - cpu->id_aa64pfr0 = 0x00002222; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; cpu->pmceid0 = 0x00000000; cpu->pmceid1 = 0x00000000; - cpu->id_aa64isar0 = 0x00011120; + cpu->isar.id_aa64isar0 = 0x00011120; cpu->id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t id_pfr1_read(CPUARMState *env, const ARMCPRegInfo *ri) static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri) { ARMCPU *cpu = arm_env_get_cpu(env); - uint64_t pfr0 = cpu->id_aa64pfr0; + uint64_t pfr0 = cpu->isar.id_aa64pfr0; if (env->gicv3state) { pfr0 |= 1 << 24; @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_ISAR0", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar0 }, + .resetvalue = cpu->isar.id_isar0 }, { .name = "ID_ISAR1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar1 }, + .resetvalue = cpu->isar.id_isar1 }, { .name = "ID_ISAR2", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar2 }, + .resetvalue = cpu->isar.id_isar2 }, { .name = "ID_ISAR3", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar3 }, + .resetvalue = cpu->isar.id_isar3 }, { .name = "ID_ISAR4", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar4 }, + .resetvalue = cpu->isar.id_isar4 }, { .name = "ID_ISAR5", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 5, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar5 }, + .resetvalue = cpu->isar.id_isar5 }, { .name = "ID_MMFR4", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 6, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_ISAR6", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 7, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar6 }, + .resetvalue = cpu->isar.id_isar6 }, REGINFO_SENTINEL }; define_arm_cp_regs(cpu, v6_idregs); @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_AA64PFR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_aa64pfr1}, + .resetvalue = cpu->isar.id_aa64pfr1}, { .name = "ID_AA64PFR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_AA64ISAR0_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_aa64isar0 }, + .resetvalue = cpu->isar.id_aa64isar0 }, { .name = "ID_AA64ISAR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_aa64isar1 }, + .resetvalue = cpu->isar.id_aa64isar1 }, { .name = "ID_AA64ISAR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "MVFR0_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->mvfr0 }, + .resetvalue = cpu->isar.mvfr0 }, { .name = "MVFR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->mvfr1 }, + .resetvalue = cpu->isar.mvfr1 }, { .name = "MVFR2_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->mvfr2 }, + .resetvalue = cpu->isar.mvfr2 }, { .name = "MVFR3_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Instantiating mps2-an505 (cortex-m33) will fail make check when V7VE asserts that ID_ISAR0.Divide includes ARM division. It is also wrong to include ARM_FEATURE_LPAE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) /* Some features automatically imply others: */ if (arm_feature(env, ARM_FEATURE_V8)) { - set_feature(env, ARM_FEATURE_V7VE); + if (arm_feature(env, ARM_FEATURE_M)) { + set_feature(env, ARM_FEATURE_V7); + } else { + set_feature(env, ARM_FEATURE_V7VE); + } } if (arm_feature(env, ARM_FEATURE_V7VE)) { /* v7 Virtualization Extensions. In real hardware this implies -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Most of the v8 extensions are self-contained within the ISAR registers and are not implied by other feature bits, which makes them the easiest to convert. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 131 +++++++++++++++++++++++++++++++++---- target/arm/translate.h | 7 ++ linux-user/elfload.c | 46 ++++++++----- target/arm/cpu.c | 27 +++++--- target/arm/cpu64.c | 57 +++++++++------- target/arm/translate-a64.c | 101 ++++++++++++++-------------- target/arm/translate.c | 36 +++++----- 7 files changed, 273 insertions(+), 132 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef enum ARMPSCIState { PSCI_ON_PENDING = 2 } ARMPSCIState; +typedef struct ARMISARegisters ARMISARegisters; + /** * ARMCPU: * @env: #CPUARMState @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_LPAE, /* has Large Physical Address Extension */ ARM_FEATURE_V8, ARM_FEATURE_AARCH64, /* supports 64 bit mode */ - ARM_FEATURE_V8_AES, /* implements AES part of v8 Crypto Extensions */ ARM_FEATURE_CBAR, /* has cp15 CBAR */ ARM_FEATURE_CRC, /* ARMv8 CRC instructions */ ARM_FEATURE_CBAR_RO, /* has cp15 CBAR and it is read-only */ ARM_FEATURE_EL2, /* has EL2 Virtualization support */ ARM_FEATURE_EL3, /* has EL3 Secure monitor support */ - ARM_FEATURE_V8_SHA1, /* implements SHA1 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SHA256, /* implements SHA256 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_PMULL, /* implements PMULL part of v8 Crypto Extensions */ ARM_FEATURE_THUMB_DSP, /* DSP insns supported in the Thumb encodings */ ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ ARM_FEATURE_JAZELLE, /* has (trivial) Jazelle implementation */ ARM_FEATURE_SVE, /* has Scalable Vector Extension */ - ARM_FEATURE_V8_SHA512, /* implements SHA512 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SHA3, /* implements SHA3 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SM3, /* implements SM3 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SM4, /* implements SM4 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_ATOMICS, /* ARMv8.1-Atomics feature */ - ARM_FEATURE_V8_RDM, /* implements v8.1 simd round multiply */ - ARM_FEATURE_V8_DOTPROD, /* implements v8.2 simd dot product */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ - ARM_FEATURE_V8_FCMA, /* has complex number part of v8.3 extensions. */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ }; @@ -XXX,XX +XXX,XX @@ static inline uint64_t *aa64_vfp_qreg(CPUARMState *env, unsigned regno) /* Shared between translate-sve.c and sve_helper.c. */ extern const uint64_t pred_esz_masks[4]; +/* + * 32-bit feature tests via id registers. + */ +static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; +} + +static inline bool isar_feature_aa32_pmull(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) > 1; +} + +static inline bool isar_feature_aa32_sha1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA1) != 0; +} + +static inline bool isar_feature_aa32_sha2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA2) != 0; +} + +static inline bool isar_feature_aa32_crc32(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, CRC32) != 0; +} + +static inline bool isar_feature_aa32_rdm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, RDM) != 0; +} + +static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; +} + +static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; +} + +/* + * 64-bit feature tests via id registers. + */ +static inline bool isar_feature_aa64_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) != 0; +} + +static inline bool isar_feature_aa64_pmull(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) > 1; +} + +static inline bool isar_feature_aa64_sha1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA1) != 0; +} + +static inline bool isar_feature_aa64_sha256(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) != 0; +} + +static inline bool isar_feature_aa64_sha512(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) > 1; +} + +static inline bool isar_feature_aa64_crc32(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, CRC32) != 0; +} + +static inline bool isar_feature_aa64_atomics(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, ATOMIC) != 0; +} + +static inline bool isar_feature_aa64_rdm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RDM) != 0; +} + +static inline bool isar_feature_aa64_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sm3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM3) != 0; +} + +static inline bool isar_feature_aa64_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; +} + +static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; +} + +/* + * Forward to the above feature tests given an ARMCPU pointer. + */ +#define cpu_isar_feature(name, cpu) \ + ({ ARMCPU *cpu_ = (cpu); isar_feature_##name(&cpu_->isar); }) + #endif diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ /* internal defines */ typedef struct DisasContext { DisasContextBase base; + const ARMISARegisters *isar; target_ulong pc; target_ulong page_start; @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) return ret; } +/* + * Forward to the isar_feature_* tests given a DisasContext pointer. + */ +#define dc_isar_feature(name, ctx) \ + ({ DisasContext *ctx_ = (ctx); isar_feature_##name(ctx_->isar); }) + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) /* probe for the extra features */ #define GET_FEATURE(feat, hwcap) \ do { if (arm_feature(&cpu->env, feat)) { hwcaps |= hwcap; } } while (0) + +#define GET_FEATURE_ID(feat, hwcap) \ + do { if (cpu_isar_feature(feat, cpu)) { hwcaps |= hwcap; } } while (0) + /* EDSP is in v5TE and above, but all our v5 CPUs are v5TE */ GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); GET_FEATURE(ARM_FEATURE_VFP, ARM_HWCAP_ARM_VFP); @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) ARMCPU *cpu = ARM_CPU(thread_cpu); uint32_t hwcaps = 0; - GET_FEATURE(ARM_FEATURE_V8_AES, ARM_HWCAP2_ARM_AES); - GET_FEATURE(ARM_FEATURE_V8_PMULL, ARM_HWCAP2_ARM_PMULL); - GET_FEATURE(ARM_FEATURE_V8_SHA1, ARM_HWCAP2_ARM_SHA1); - GET_FEATURE(ARM_FEATURE_V8_SHA256, ARM_HWCAP2_ARM_SHA2); - GET_FEATURE(ARM_FEATURE_CRC, ARM_HWCAP2_ARM_CRC32); + GET_FEATURE_ID(aa32_aes, ARM_HWCAP2_ARM_AES); + GET_FEATURE_ID(aa32_pmull, ARM_HWCAP2_ARM_PMULL); + GET_FEATURE_ID(aa32_sha1, ARM_HWCAP2_ARM_SHA1); + GET_FEATURE_ID(aa32_sha2, ARM_HWCAP2_ARM_SHA2); + GET_FEATURE_ID(aa32_crc32, ARM_HWCAP2_ARM_CRC32); return hwcaps; } #undef GET_FEATURE +#undef GET_FEATURE_ID #else /* 64 bit ARM definitions */ @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) /* probe for the extra features */ #define GET_FEATURE(feat, hwcap) \ do { if (arm_feature(&cpu->env, feat)) { hwcaps |= hwcap; } } while (0) - GET_FEATURE(ARM_FEATURE_V8_AES, ARM_HWCAP_A64_AES); - GET_FEATURE(ARM_FEATURE_V8_PMULL, ARM_HWCAP_A64_PMULL); - GET_FEATURE(ARM_FEATURE_V8_SHA1, ARM_HWCAP_A64_SHA1); - GET_FEATURE(ARM_FEATURE_V8_SHA256, ARM_HWCAP_A64_SHA2); - GET_FEATURE(ARM_FEATURE_CRC, ARM_HWCAP_A64_CRC32); - GET_FEATURE(ARM_FEATURE_V8_SHA3, ARM_HWCAP_A64_SHA3); - GET_FEATURE(ARM_FEATURE_V8_SM3, ARM_HWCAP_A64_SM3); - GET_FEATURE(ARM_FEATURE_V8_SM4, ARM_HWCAP_A64_SM4); - GET_FEATURE(ARM_FEATURE_V8_SHA512, ARM_HWCAP_A64_SHA512); +#define GET_FEATURE_ID(feat, hwcap) \ + do { if (cpu_isar_feature(feat, cpu)) { hwcaps |= hwcap; } } while (0) + + GET_FEATURE_ID(aa64_aes, ARM_HWCAP_A64_AES); + GET_FEATURE_ID(aa64_pmull, ARM_HWCAP_A64_PMULL); + GET_FEATURE_ID(aa64_sha1, ARM_HWCAP_A64_SHA1); + GET_FEATURE_ID(aa64_sha256, ARM_HWCAP_A64_SHA2); + GET_FEATURE_ID(aa64_sha512, ARM_HWCAP_A64_SHA512); + GET_FEATURE_ID(aa64_crc32, ARM_HWCAP_A64_CRC32); + GET_FEATURE_ID(aa64_sha3, ARM_HWCAP_A64_SHA3); + GET_FEATURE_ID(aa64_sm3, ARM_HWCAP_A64_SM3); + GET_FEATURE_ID(aa64_sm4, ARM_HWCAP_A64_SM4); GET_FEATURE(ARM_FEATURE_V8_FP16, ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); - GET_FEATURE(ARM_FEATURE_V8_ATOMICS, ARM_HWCAP_A64_ATOMICS); - GET_FEATURE(ARM_FEATURE_V8_RDM, ARM_HWCAP_A64_ASIMDRDM); - GET_FEATURE(ARM_FEATURE_V8_DOTPROD, ARM_HWCAP_A64_ASIMDDP); - GET_FEATURE(ARM_FEATURE_V8_FCMA, ARM_HWCAP_A64_FCMA); + GET_FEATURE_ID(aa64_atomics, ARM_HWCAP_A64_ATOMICS); + GET_FEATURE_ID(aa64_rdm, ARM_HWCAP_A64_ASIMDRDM); + GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); + GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); GET_FEATURE(ARM_FEATURE_SVE, ARM_HWCAP_A64_SVE); + #undef GET_FEATURE +#undef GET_FEATURE_ID return hwcaps; } diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) cortex_a15_initfn(obj); #ifdef CONFIG_USER_ONLY /* We don't set these in system emulation mode for the moment, - * since we don't correctly set the ID registers to advertise them, + * since we don't correctly set (all of) the ID registers to + * advertise them. */ set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); - set_feature(&cpu->env, ARM_FEATURE_V8_RDM); - set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); - set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); + { + uint32_t t; + + t = cpu->isar.id_isar5; + t = FIELD_DP32(t, ID_ISAR5, AES, 2); + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = t; + + t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, DP, 1); + cpu->isar.id_isar6 = t; + } #endif } } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); set_feature(&cpu->env, ARM_FEATURE_PMU); @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); set_feature(&cpu->env, ARM_FEATURE_PMU); @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); set_feature(&cpu->env, ARM_FEATURE_PMU); @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); } else { + uint64_t t; + uint32_t u; aarch64_a57_initfn(obj); + + t = cpu->isar.id_aa64isar0; + t = FIELD_DP64(t, ID_AA64ISAR0, AES, 2); /* AES + PMULL */ + t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SHA2, 2); /* SHA512 */ + t = FIELD_DP64(t, ID_AA64ISAR0, CRC32, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, ATOMIC, 2); + t = FIELD_DP64(t, ID_AA64ISAR0, RDM, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SHA3, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SM3, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SM4, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); + cpu->isar.id_aa64isar0 = t; + + t = cpu->isar.id_aa64isar1; + t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); + cpu->isar.id_aa64isar1 = t; + + /* Replicate the same data to the 32-bit id registers. */ + u = cpu->isar.id_isar5; + u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */ + u = FIELD_DP32(u, ID_ISAR5, SHA1, 1); + u = FIELD_DP32(u, ID_ISAR5, SHA2, 1); + u = FIELD_DP32(u, ID_ISAR5, CRC32, 1); + u = FIELD_DP32(u, ID_ISAR5, RDM, 1); + u = FIELD_DP32(u, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = u; + + u = cpu->isar.id_isar6; + u = FIELD_DP32(u, ID_ISAR6, DP, 1); + cpu->isar.id_isar6 = u; + #ifdef CONFIG_USER_ONLY /* We don't set these in system emulation mode for the moment, * since we don't correctly set the ID registers to advertise them, @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) * whereas the architecture requires them to be present in both if * present in either. */ - set_feature(&cpu->env, ARM_FEATURE_V8_SHA512); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA3); - set_feature(&cpu->env, ARM_FEATURE_V8_SM3); - set_feature(&cpu->env, ARM_FEATURE_V8_SM4); - set_feature(&cpu->env, ARM_FEATURE_V8_ATOMICS); - set_feature(&cpu->env, ARM_FEATURE_V8_RDM); - set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); set_feature(&cpu->env, ARM_FEATURE_V8_FP16); - set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); set_feature(&cpu->env, ARM_FEATURE_SVE); /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } if (rt2 == 31 && ((rt | rs) & 1) == 0 - && arm_dc_feature(s, ARM_FEATURE_V8_ATOMICS)) { + && dc_isar_feature(aa64_atomics, s)) { /* CASP / CASPL */ gen_compare_and_swap_pair(s, rs, rt, rn, size | 2); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } if (rt2 == 31 && ((rt | rs) & 1) == 0 - && arm_dc_feature(s, ARM_FEATURE_V8_ATOMICS)) { + && dc_isar_feature(aa64_atomics, s)) { /* CASPA / CASPAL */ gen_compare_and_swap_pair(s, rs, rt, rn, size | 2); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) case 0xb: /* CASL */ case 0xe: /* CASA */ case 0xf: /* CASAL */ - if (rt2 == 31 && arm_dc_feature(s, ARM_FEATURE_V8_ATOMICS)) { + if (rt2 == 31 && dc_isar_feature(aa64_atomics, s)) { gen_compare_and_swap(s, rs, rt, rn, size); return; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, int rs = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int o3_opc = extract32(insn, 12, 4); - int feature = ARM_FEATURE_V8_ATOMICS; TCGv_i64 tcg_rn, tcg_rs; AtomicThreeOpFn *fn; - if (is_vector) { + if (is_vector || !dc_isar_feature(aa64_atomics, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { - unallocated_encoding(s); - return; - } if (rn == 31) { gen_check_sp_alignment(s); @@ -XXX,XX +XXX,XX @@ static void handle_crc32(DisasContext *s, TCGv_i64 tcg_acc, tcg_val; TCGv_i32 tcg_bytes; - if (!arm_dc_feature(s, ARM_FEATURE_CRC) + if (!dc_isar_feature(aa64_crc32, s) || (sf == 1 && sz != 3) || (sf == 0 && sz == 3)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_extra(DisasContext *s, bool u = extract32(insn, 29, 1); TCGv_i32 ele1, ele2, ele3; TCGv_i64 res; - int feature; + bool feature; switch (u * 16 + opcode) { case 0x10: /* SQRDMLAH (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_extra(DisasContext *s, unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_RDM; + feature = dc_isar_feature(aa64_rdm, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) return; } if (size == 3) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_PMULL)) { + if (!dc_isar_feature(aa64_pmull, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) int size = extract32(insn, 22, 2); bool u = extract32(insn, 29, 1); bool is_q = extract32(insn, 30, 1); - int feature, rot; + bool feature; + int rot; switch (u * 16 + opcode) { case 0x10: /* SQRDMLAH (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_RDM; + feature = dc_isar_feature(aa64_rdm, s); break; case 0x02: /* SDOT (vector) */ case 0x12: /* UDOT (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_DOTPROD; + feature = dc_isar_feature(aa64_dp, s); break; case 0x18: /* FCMLA, #0 */ case 0x19: /* FCMLA, #90 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_FCMA; + feature = dc_isar_feature(aa64_fcma, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; case 0x1d: /* SQRDMLAH */ case 0x1f: /* SQRDMLSH */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_RDM)) { + if (!dc_isar_feature(aa64_rdm, s)) { unallocated_encoding(s); return; } break; case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ - if (size != MO_32 || !arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + if (size != MO_32 || !dc_isar_feature(aa64_dp, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ case 0x17: /* FCMLA #270 */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA)) { + if (!dc_isar_feature(aa64_fcma, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) TCGv_i32 tcg_decrypt; CryptoThreeOpIntFn *genfn; - if (!arm_dc_feature(s, ARM_FEATURE_V8_AES) - || size != 0) { + if (!dc_isar_feature(aa64_aes, s) || size != 0) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) int rd = extract32(insn, 0, 5); CryptoThreeOpFn *genfn; TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; - int feature = ARM_FEATURE_V8_SHA256; + bool feature; if (size != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) case 2: /* SHA1M */ case 3: /* SHA1SU0 */ genfn = NULL; - feature = ARM_FEATURE_V8_SHA1; + feature = dc_isar_feature(aa64_sha1, s); break; case 4: /* SHA256H */ genfn = gen_helper_crypto_sha256h; + feature = dc_isar_feature(aa64_sha256, s); break; case 5: /* SHA256H2 */ genfn = gen_helper_crypto_sha256h2; + feature = dc_isar_feature(aa64_sha256, s); break; case 6: /* SHA256SU1 */ genfn = gen_helper_crypto_sha256su1; + feature = dc_isar_feature(aa64_sha256, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); CryptoTwoOpFn *genfn; - int feature; + bool feature; TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; if (size != 0) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SHA1H */ - feature = ARM_FEATURE_V8_SHA1; + feature = dc_isar_feature(aa64_sha1, s); genfn = gen_helper_crypto_sha1h; break; case 1: /* SHA1SU1 */ - feature = ARM_FEATURE_V8_SHA1; + feature = dc_isar_feature(aa64_sha1, s); genfn = gen_helper_crypto_sha1su1; break; case 2: /* SHA256SU0 */ - feature = ARM_FEATURE_V8_SHA256; + feature = dc_isar_feature(aa64_sha256, s); genfn = gen_helper_crypto_sha256su0; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int feature; + bool feature; CryptoThreeOpFn *genfn; if (o == 0) { switch (opcode) { case 0: /* SHA512H */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512h; break; case 1: /* SHA512H2 */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512h2; break; case 2: /* SHA512SU1 */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512su1; break; case 3: /* RAX1 */ - feature = ARM_FEATURE_V8_SHA3; + feature = dc_isar_feature(aa64_sha3, s); genfn = NULL; break; } } else { switch (opcode) { case 0: /* SM3PARTW1 */ - feature = ARM_FEATURE_V8_SM3; + feature = dc_isar_feature(aa64_sm3, s); genfn = gen_helper_crypto_sm3partw1; break; case 1: /* SM3PARTW2 */ - feature = ARM_FEATURE_V8_SM3; + feature = dc_isar_feature(aa64_sm3, s); genfn = gen_helper_crypto_sm3partw2; break; case 2: /* SM4EKEY */ - feature = ARM_FEATURE_V8_SM4; + feature = dc_isar_feature(aa64_sm4, s); genfn = gen_helper_crypto_sm4ekey; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) } } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; - int feature; + bool feature; CryptoTwoOpFn *genfn; switch (opcode) { case 0: /* SHA512SU0 */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512su0; break; case 1: /* SM4E */ - feature = ARM_FEATURE_V8_SM4; + feature = dc_isar_feature(aa64_sm4, s); genfn = gen_helper_crypto_sm4e; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_four_reg(DisasContext *s, uint32_t insn) int ra = extract32(insn, 10, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int feature; + bool feature; switch (op0) { case 0: /* EOR3 */ case 1: /* BCAX */ - feature = ARM_FEATURE_V8_SHA3; + feature = dc_isar_feature(aa64_sha3, s); break; case 2: /* SM3SS1 */ - feature = ARM_FEATURE_V8_SM3; + feature = dc_isar_feature(aa64_sm3, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; int pass; - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA3)) { + if (!dc_isar_feature(aa64_sha3, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; TCGv_i32 tcg_imm2, tcg_opcode; - if (!arm_dc_feature(s, ARM_FEATURE_V8_SM3)) { + if (!dc_isar_feature(aa64_sm3, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, ARMCPU *arm_cpu = arm_env_get_cpu(env); int bound; + dc->isar = &arm_cpu->isar; dc->pc = dc->base.pc_first; dc->condjmp = 0; diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static const uint8_t neon_2rm_sizes[] = { static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, int q, int rd, int rn, int rm) { - if (arm_dc_feature(s, ARM_FEATURE_V8_RDM)) { + if (dc_isar_feature(aa32_rdm, s)) { int opr_sz = (1 + q) * 8; tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), vfp_reg_offset(1, rn), @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } if (!u) { /* SHA-1 */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA1)) { + if (!dc_isar_feature(aa32_sha1, s)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp4); tcg_temp_free_i32(tmp4); } else { /* SHA-256 */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA256) || size == 3) { + if (!dc_isar_feature(aa32_sha2, s) || size == 3) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (op == 14 && size == 2) { TCGv_i64 tcg_rn, tcg_rm, tcg_rd; - if (!arm_dc_feature(s, ARM_FEATURE_V8_PMULL)) { + if (!dc_isar_feature(aa32_pmull, s)) { return 1; } tcg_rn = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { NeonGenThreeOpEnvFn *fn; - if (!arm_dc_feature(s, ARM_FEATURE_V8_RDM)) { + if (!dc_isar_feature(aa32_rdm, s)) { return 1; } if (u && ((rd | rn) & 1)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } case NEON_2RM_AESE: case NEON_2RM_AESMC: - if (!arm_dc_feature(s, ARM_FEATURE_V8_AES) - || ((rm | rd) & 1)) { + if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp3); break; case NEON_2RM_SHA1H: - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA1) - || ((rm | rd) & 1)) { + if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } /* bit 6 (q): set -> SHA256SU0, cleared -> SHA1SU1 */ if (q) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA256)) { + if (!dc_isar_feature(aa32_sha2, s)) { return 1; } - } else if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA1)) { + } else if (!dc_isar_feature(aa32_sha1, s)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) /* VCMLA -- 1111 110R R.1S .... .... 1000 ...0 .... */ int size = extract32(insn, 20, 1); data = extract32(insn, 23, 2); /* rot */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) + if (!dc_isar_feature(aa32_vcma, s) || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ int size = extract32(insn, 20, 1); data = extract32(insn, 24, 1); /* rot */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) + if (!dc_isar_feature(aa32_vcma, s) || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) } else if ((insn & 0xfeb00f00) == 0xfc200d00) { /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ bool u = extract32(insn, 4, 1); - if (!arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + if (!dc_isar_feature(aa32_dp, s)) { return 1; } fn_gvec = u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) int size = extract32(insn, 23, 1); int index; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA)) { + if (!dc_isar_feature(aa32_vcma, s)) { return 1; } if (size == 0) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) } else if ((insn & 0xffb00f00) == 0xfe200d00) { /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ int u = extract32(insn, 4, 1); - if (!arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + if (!dc_isar_feature(aa32_dp, s)) { return 1; } fn_gvec = u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * op1 == 3 is UNPREDICTABLE but handle as UNDEFINED. * Bits 8, 10 and 11 should be zero. */ - if (!arm_dc_feature(s, ARM_FEATURE_CRC) || op1 == 0x3 || - (c & 0xd) != 0) { + if (!dc_isar_feature(aa32_crc32, s) || op1 == 0x3 || (c & 0xd) != 0) { goto illegal_op; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) case 0x28: case 0x29: case 0x2a: - if (!arm_dc_feature(s, ARM_FEATURE_CRC)) { + if (!dc_isar_feature(aa32_crc32, s)) { goto illegal_op; } break; @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) CPUARMState *env = cs->env_ptr; ARMCPU *cpu = arm_env_get_cpu(env); + dc->isar = &cpu->isar; dc->pc = dc->base.pc_first; dc->condjmp = 0; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Both arm and thumb2 division are controlled by the same ISAR field, which takes care of the arm implies thumb case. Having M imply thumb2 division was wrong for cortex-m0, which is v6m and does not have thumb2 at all, much less thumb2 division. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 12 ++++++++++-- linux-user/elfload.c | 4 ++-- target/arm/cpu.c | 10 +--------- target/arm/translate.c | 4 ++-- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_VFP3, ARM_FEATURE_VFP_FP16, ARM_FEATURE_NEON, - ARM_FEATURE_THUMB_DIV, /* divide supported in Thumb encoding */ ARM_FEATURE_M, /* Microcontroller profile. */ ARM_FEATURE_OMAPCP, /* OMAP specific CP15 ops handling. */ ARM_FEATURE_THUMB2EE, @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_V5, ARM_FEATURE_STRONGARM, ARM_FEATURE_VAPA, /* cp15 VA to PA lookups */ - ARM_FEATURE_ARM_DIV, /* divide supported in ARM encoding */ ARM_FEATURE_VFP4, /* VFPv4 (implies that NEON is v2) */ ARM_FEATURE_GENERIC_TIMER, ARM_FEATURE_MVFR, /* Media and VFP Feature Registers 0 and 1 */ @@ -XXX,XX +XXX,XX @@ extern const uint64_t pred_esz_masks[4]; /* * 32-bit feature tests via id registers. */ +static inline bool isar_feature_thumb_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; +} + +static inline bool isar_feature_arm_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; +} + static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPv3); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); GET_FEATURE(ARM_FEATURE_VFP4, ARM_HWCAP_ARM_VFPv4); - GET_FEATURE(ARM_FEATURE_ARM_DIV, ARM_HWCAP_ARM_IDIVA); - GET_FEATURE(ARM_FEATURE_THUMB_DIV, ARM_HWCAP_ARM_IDIVT); + GET_FEATURE_ID(arm_div, ARM_HWCAP_ARM_IDIVA); + GET_FEATURE_ID(thumb_div, ARM_HWCAP_ARM_IDIVT); /* All QEMU's VFPv3 CPUs have 32 registers, see VFP_DREG in translate.c. * Note that the ARM_HWCAP_ARM_VFPv3D16 bit is always the inverse of * ARM_HWCAP_ARM_VFPD32 (and so always clear for QEMU); it is unrelated diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * Presence of EL2 itself is ARM_FEATURE_EL2, and of the * Security Extensions is ARM_FEATURE_EL3. */ - set_feature(env, ARM_FEATURE_ARM_DIV); + assert(cpu_isar_feature(arm_div, cpu)); set_feature(env, ARM_FEATURE_LPAE); set_feature(env, ARM_FEATURE_V7); } @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (arm_feature(env, ARM_FEATURE_V5)) { set_feature(env, ARM_FEATURE_V4T); } - if (arm_feature(env, ARM_FEATURE_M)) { - set_feature(env, ARM_FEATURE_THUMB_DIV); - } - if (arm_feature(env, ARM_FEATURE_ARM_DIV)) { - set_feature(env, ARM_FEATURE_THUMB_DIV); - } if (arm_feature(env, ARM_FEATURE_VFP4)) { set_feature(env, ARM_FEATURE_VFP3); set_feature(env, ARM_FEATURE_VFP_FP16); @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) ARMCPU *cpu = ARM_CPU(obj); set_feature(&cpu->env, ARM_FEATURE_V7); - set_feature(&cpu->env, ARM_FEATURE_THUMB_DIV); - set_feature(&cpu->env, ARM_FEATURE_ARM_DIV); set_feature(&cpu->env, ARM_FEATURE_V7MP); set_feature(&cpu->env, ARM_FEATURE_PMSA); cpu->midr = 0x411fc153; /* r1p3 */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) case 1: case 3: /* SDIV, UDIV */ - if (!arm_dc_feature(s, ARM_FEATURE_ARM_DIV)) { + if (!dc_isar_feature(arm_div, s)) { goto illegal_op; } if (((insn >> 5) & 7) || (rd != 15)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp2 = load_reg(s, rm); if ((op & 0x50) == 0x10) { /* sdiv, udiv */ - if (!arm_dc_feature(s, ARM_FEATURE_THUMB_DIV)) { + if (!dc_isar_feature(thumb_div, s)) { goto illegal_op; } if (op & 0x20) -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Having V6 alone imply jazelle was wrong for cortex-m0. Change to an assertion for V6 & !M. This was harmless, because the only place we tested ARM_FEATURE_JAZELLE was for 'bxj' in disas_arm(), which is unreachable for M-profile cores. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 +++++- target/arm/cpu.c | 17 ++++++++++++++--- target/arm/translate.c | 2 +- 3 files changed, 20 insertions(+), 5 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ - ARM_FEATURE_JAZELLE, /* has (trivial) Jazelle implementation */ ARM_FEATURE_SVE, /* has Scalable Vector Extension */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_arm_div(const ARMISARegisters *id) return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; } +static inline bool isar_feature_jazelle(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; +} + static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (arm_feature(env, ARM_FEATURE_V6)) { set_feature(env, ARM_FEATURE_V5); - set_feature(env, ARM_FEATURE_JAZELLE); if (!arm_feature(env, ARM_FEATURE_M)) { + assert(cpu_isar_feature(jazelle, cpu)); set_feature(env, ARM_FEATURE_AUXCR); } } @@ -XXX,XX +XXX,XX @@ static void arm926_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN); - set_feature(&cpu->env, ARM_FEATURE_JAZELLE); cpu->midr = 0x41069265; cpu->reset_fpsid = 0x41011090; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00090078; + + /* + * ARMv5 does not have the ID_ISAR registers, but we can still + * set the field to indicate Jazelle support within QEMU. + */ + cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1); } static void arm946_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_AUXCR); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN); - set_feature(&cpu->env, ARM_FEATURE_JAZELLE); cpu->midr = 0x4106a262; cpu->reset_fpsid = 0x410110a0; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00090078; cpu->reset_auxcr = 1; + + /* + * ARMv5 does not have the ID_ISAR registers, but we can still + * set the field to indicate Jazelle support within QEMU. + */ + cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1); + { /* The 1026 had an IFAR at c6,c0,0,1 rather than the ARMv6 c6,c0,0,2 */ ARMCPRegInfo ifar = { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ #define ENABLE_ARCH_5 arm_dc_feature(s, ARM_FEATURE_V5) /* currently all emulated v5 cores are also v5TE, so don't bother */ #define ENABLE_ARCH_5TE arm_dc_feature(s, ARM_FEATURE_V5) -#define ENABLE_ARCH_5J arm_dc_feature(s, ARM_FEATURE_JAZELLE) +#define ENABLE_ARCH_5J dc_isar_feature(jazelle, s) #define ENABLE_ARCH_6 arm_dc_feature(s, ARM_FEATURE_V6) #define ENABLE_ARCH_6K arm_dc_feature(s, ARM_FEATURE_V6K) #define ENABLE_ARCH_6T2 arm_dc_feature(s, ARM_FEATURE_THUMB2) -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 +++++- linux-user/elfload.c | 2 +- target/arm/cpu.c | 4 ---- target/arm/helper.c | 2 +- target/arm/machine.c | 3 +-- 5 files changed, 8 insertions(+), 9 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_NEON, ARM_FEATURE_M, /* Microcontroller profile. */ ARM_FEATURE_OMAPCP, /* OMAP specific CP15 ops handling. */ - ARM_FEATURE_THUMB2EE, ARM_FEATURE_V7MP, /* v7 Multiprocessing Extensions */ ARM_FEATURE_V7VE, /* v7 Virtualization Extensions (non-EL2 parts) */ ARM_FEATURE_V4T, @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_jazelle(const ARMISARegisters *id) return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; } +static inline bool isar_feature_t32ee(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar3, ID_ISAR3, T32EE) != 0; +} + static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); GET_FEATURE(ARM_FEATURE_VFP, ARM_HWCAP_ARM_VFP); GET_FEATURE(ARM_FEATURE_IWMMXT, ARM_HWCAP_ARM_IWMMXT); - GET_FEATURE(ARM_FEATURE_THUMB2EE, ARM_HWCAP_ARM_THUMBEE); + GET_FEATURE_ID(t32ee, ARM_HWCAP_ARM_THUMBEE); GET_FEATURE(ARM_FEATURE_NEON, ARM_HWCAP_ARM_NEON); GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPv3); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V7); set_feature(&cpu->env, ARM_FEATURE_VFP3); 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; @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_VFP3); 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 @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V7VE); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V7VE); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, vmsa_pmsa_cp_reginfo); define_arm_cp_regs(cpu, vmsa_cp_reginfo); } - if (arm_feature(env, ARM_FEATURE_THUMB2EE)) { + if (cpu_isar_feature(t32ee, cpu)) { define_arm_cp_regs(cpu, t2ee_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_GENERIC_TIMER)) { diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_m = { static bool thumb2ee_needed(void *opaque) { ARMCPU *cpu = opaque; - CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_THUMB2EE); + return cpu_isar_feature(t32ee, cpu); } static const VMStateDescription vmstate_thumb2ee = { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 16 +++++++++++++++- linux-user/aarch64/signal.c | 4 ++-- linux-user/elfload.c | 2 +- linux-user/syscall.c | 10 ++++++---- target/arm/cpu64.c | 5 ++++- target/arm/helper.c | 9 ++++++--- target/arm/machine.c | 3 +-- target/arm/translate-a64.c | 4 ++-- 8 files changed, 37 insertions(+), 16 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR1, FRINTTS, 32, 4) FIELD(ID_AA64ISAR1, SB, 36, 4) FIELD(ID_AA64ISAR1, SPECRES, 40, 4) +FIELD(ID_AA64PFR0, EL0, 0, 4) +FIELD(ID_AA64PFR0, EL1, 4, 4) +FIELD(ID_AA64PFR0, EL2, 8, 4) +FIELD(ID_AA64PFR0, EL3, 12, 4) +FIELD(ID_AA64PFR0, FP, 16, 4) +FIELD(ID_AA64PFR0, ADVSIMD, 20, 4) +FIELD(ID_AA64PFR0, GIC, 24, 4) +FIELD(ID_AA64PFR0, RAS, 28, 4) +FIELD(ID_AA64PFR0, SVE, 32, 4) + QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK); /* If adding a feature bit which corresponds to a Linux ELF @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ - ARM_FEATURE_SVE, /* has Scalable Vector Extension */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ }; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; +} + /* * Forward to the above feature tests given an ARMCPU pointer. */ diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; case TARGET_SVE_MAGIC: - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, arm_env_get_cpu(env))) { vq = (env->vfp.zcr_el[1] & 0xf) + 1; sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); if (!sve && size == sve_size) { @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, &layout); /* SVE state needs saving only if it exists. */ - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, arm_env_get_cpu(env))) { vq = (env->vfp.zcr_el[1] & 0xf) + 1; sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); sve_ofs = alloc_sigframe_space(sve_size, &layout); diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_rdm, ARM_HWCAP_A64_ASIMDRDM); GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); - GET_FEATURE(ARM_FEATURE_SVE, ARM_HWCAP_A64_SVE); + GET_FEATURE_ID(aa64_sve, ARM_HWCAP_A64_SVE); #undef GET_FEATURE #undef GET_FEATURE_ID diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, * even though the current architectural maximum is VQ=16. */ ret = -TARGET_EINVAL; - if (arm_feature(cpu_env, ARM_FEATURE_SVE) + if (cpu_isar_feature(aa64_sve, arm_env_get_cpu(cpu_env)) && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { CPUARMState *env = cpu_env; ARMCPU *cpu = arm_env_get_cpu(env); @@ -XXX,XX +XXX,XX @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, return ret; case TARGET_PR_SVE_GET_VL: ret = -TARGET_EINVAL; - if (arm_feature(cpu_env, ARM_FEATURE_SVE)) { - CPUARMState *env = cpu_env; - ret = ((env->vfp.zcr_el[1] & 0xf) + 1) * 16; + { + ARMCPU *cpu = arm_env_get_cpu(cpu_env); + if (cpu_isar_feature(aa64_sve, cpu)) { + ret = ((cpu->env.vfp.zcr_el[1] & 0xf) + 1) * 16; + } } return ret; #endif /* AARCH64 */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); cpu->isar.id_aa64isar1 = t; + t = cpu->isar.id_aa64pfr0; + t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); + cpu->isar.id_aa64pfr0 = t; + /* Replicate the same data to the 32-bit id registers. */ u = cpu->isar.id_isar5; u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */ @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) * present in either. */ set_feature(&cpu->env, ARM_FEATURE_V8_FP16); - set_feature(&cpu->env, ARM_FEATURE_SVE); /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, &sctlr); } - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, cpu)) { define_one_arm_cp_reg(cpu, &zcr_el1_reginfo); if (arm_feature(env, ARM_FEATURE_EL2)) { define_one_arm_cp_reg(cpu, &zcr_el2_reginfo); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, uint32_t flags; if (is_a64(env)) { + ARMCPU *cpu = arm_env_get_cpu(env); + *pc = env->pc; flags = ARM_TBFLAG_AARCH64_STATE_MASK; /* Get control bits for tagged addresses */ flags |= (arm_regime_tbi0(env, mmu_idx) << ARM_TBFLAG_TBI0_SHIFT); flags |= (arm_regime_tbi1(env, mmu_idx) << ARM_TBFLAG_TBI1_SHIFT); - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, cpu)) { int sve_el = sve_exception_el(env, current_el); uint32_t zcr_len; @@ -XXX,XX +XXX,XX @@ void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el, bool el0_a64) { + ARMCPU *cpu = arm_env_get_cpu(env); int old_len, new_len; bool old_a64, new_a64; /* Nothing to do if no SVE. */ - if (!arm_feature(env, ARM_FEATURE_SVE)) { + if (!cpu_isar_feature(aa64_sve, cpu)) { return; } diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_iwmmxt = { static bool sve_needed(void *opaque) { ARMCPU *cpu = opaque; - CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_SVE); + return cpu_isar_feature(aa64_sve, cpu); } /* The first two words of each Zreg is stored in VFP state. */ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f, cpu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (arm_feature(env, ARM_FEATURE_SVE) && sve_exception_el(env, el) == 0) { + if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { int j, zcr_len = sve_zcr_len_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) unallocated_encoding(s); break; case 0x2: - if (!arm_dc_feature(s, ARM_FEATURE_SVE) || !disas_sve(s, insn)) { + if (!dc_isar_feature(aa64_sve, s) || !disas_sve(s, insn)) { unallocated_encoding(s); } break; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 17 +++++++++++++++- linux-user/elfload.c | 6 +----- target/arm/cpu64.c | 16 ++++++++------- target/arm/helper.c | 2 +- target/arm/translate-a64.c | 40 +++++++++++++++++++------------------- target/arm/translate.c | 6 +++--- 6 files changed, 50 insertions(+), 37 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ - ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ }; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; } +static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) +{ + /* + * This is a placeholder for use by VCMA until the rest of + * the ARMv8.2-FP16 extension is implemented for aa32 mode. + * At which point we can properly set and check MVFR1.FPHP. + */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; +} + /* * 64-bit feature tests via id registers. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically wrt FP16. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; +} + static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) hwcaps |= ARM_HWCAP_A64_ASIMD; /* probe for the extra features */ -#define GET_FEATURE(feat, hwcap) \ - do { if (arm_feature(&cpu->env, feat)) { hwcaps |= hwcap; } } while (0) #define GET_FEATURE_ID(feat, hwcap) \ do { if (cpu_isar_feature(feat, cpu)) { hwcaps |= hwcap; } } while (0) @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_sha3, ARM_HWCAP_A64_SHA3); GET_FEATURE_ID(aa64_sm3, ARM_HWCAP_A64_SM3); GET_FEATURE_ID(aa64_sm4, ARM_HWCAP_A64_SM4); - GET_FEATURE(ARM_FEATURE_V8_FP16, - ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); + GET_FEATURE_ID(aa64_fp16, ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); GET_FEATURE_ID(aa64_atomics, ARM_HWCAP_A64_ATOMICS); GET_FEATURE_ID(aa64_rdm, ARM_HWCAP_A64_ASIMDRDM); GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); GET_FEATURE_ID(aa64_sve, ARM_HWCAP_A64_SVE); -#undef GET_FEATURE #undef GET_FEATURE_ID return hwcaps; diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); + t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); + t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); cpu->isar.id_aa64pfr0 = t; /* Replicate the same data to the 32-bit id registers. */ @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_ISAR6, DP, 1); cpu->isar.id_isar6 = u; -#ifdef CONFIG_USER_ONLY - /* We don't set these in system emulation mode for the moment, - * since we don't correctly set the ID registers to advertise them, - * and in some cases they're only available in AArch64 and not AArch32, - * whereas the architecture requires them to be present in both if - * present in either. + /* + * FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet, + * so do not set MVFR1.FPHP. Strictly speaking this is not legal, + * but it is also not legal to enable SVE without support for FP16, + * and enabling SVE in system mode is more useful in the short term. */ - set_feature(&cpu->env, ARM_FEATURE_V8_FP16); + +#ifdef CONFIG_USER_ONLY /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) uint32_t changed; /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ - if (!arm_feature(env, ARM_FEATURE_V8_FP16)) { + if (!cpu_isar_feature(aa64_fp16, arm_env_get_cpu(env))) { val &= ~FPCR_FZ16; } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_fp_compare(DisasContext *s, uint32_t insn) break; case 3: size = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) break; case 3: size = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) break; case 3: sz = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) handle_fp_1src_double(s, opcode, rd, rn); break; case 3: - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_2src(DisasContext *s, uint32_t insn) handle_fp_2src_double(s, opcode, rd, rn, rm); break; case 3: - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra); break; case 3: - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_imm(DisasContext *s, uint32_t insn) break; case 3: sz = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_fixed_conv(DisasContext *s, uint32_t insn) case 1: /* float64 */ break; case 3: /* float16 */ - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) break; case 0x6: /* 16-bit float, 32-bit int */ case 0xe: /* 16-bit float, 64-bit int */ - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) case 1: /* float64 */ break; case 3: /* float16 */ - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) */ is_min = extract32(size, 1, 1); is_fp = true; - if (!is_u && arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!is_u && dc_isar_feature(aa64_fp16, s)) { size = 1; } else if (!is_u || !is_q || extract32(size, 0, 1)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) if (o2 != 0 || ((cmode == 0xf) && is_neg && !is_q)) { /* Check for FMOV (vector, immediate) - half-precision */ - if (!(arm_dc_feature(s, ARM_FEATURE_V8_FP16) && o2 && cmode == 0xf)) { + if (!(dc_isar_feature(aa64_fp16, s) && o2 && cmode == 0xf)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0x2f: /* FMINP */ /* FP op, size[0] is 32 or 64 bit*/ if (!u) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } else { @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_intfp_conv(DisasContext *s, bool is_scalar, size = MO_32; } else if (immh & 2) { size = MO_16; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, size = MO_32; } else if (immh & 0x2) { size = MO_16; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, return; } - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) TCGv_ptr fpst; bool pairwise = false; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) case 0x1c: /* FCADD, #90 */ case 0x1e: /* FCADD, #270 */ if (size == 0 - || (size == 1 && !arm_dc_feature(s, ARM_FEATURE_V8_FP16)) + || (size == 1 && !dc_isar_feature(aa64_fp16, s)) || (size == 3 && !is_q)) { unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) bool need_fpst = true; int rmode; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } break; } - if (is_fp16 && !arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (is_fp16 && !dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) int size = extract32(insn, 20, 1); data = extract32(insn, 23, 2); /* rot */ if (!dc_isar_feature(aa32_vcma, s) - || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { + || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { return 1; } fn_gvec_ptr = size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) int size = extract32(insn, 20, 1); data = extract32(insn, 24, 1); /* rot */ if (!dc_isar_feature(aa32_vcma, s) - || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { + || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { return 1; } fn_gvec_ptr = size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) return 1; } if (size == 0) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { return 1; } /* For fp16, rm is just Vm, and index is M. */ -- 2.19.1 For AArch32, exception return happens through certain kinds of CPSR write. We don't currently have any CPU_LOG_INT logging of these events (unlike AArch64, where we log in the ERET instruction). Add some suitable logging. This will log exception returns like this: Exception return from AArch32 hyp to usr PC 0x80100374 paralleling the existing logging in the exception_return helper for AArch64 exception returns: Exception return from AArch64 EL2 to AArch64 EL0 PC 0x8003045c Exception return from AArch64 EL2 to AArch32 EL0 PC 0x8003045c (Note that an AArch32 exception return can only be AArch32->AArch32, never to AArch64.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-2-peter.maydell@linaro.org --- target/arm/internals.h | 18 ++++++++++++++++++ target/arm/helper.c | 10 ++++++++++ target/arm/translate.c | 7 +------ 3 files changed, 29 insertions(+), 6 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t v7m_sp_limit(CPUARMState *env) } } +/** + * aarch32_mode_name(): Return name of the AArch32 CPU mode + * @psr: Program Status Register indicating CPU mode + * + * Returns, for debug logging purposes, a printable representation + * of the AArch32 CPU mode ("svc", "usr", etc) as indicated by + * the low bits of the specified PSR. + */ +static inline const char *aarch32_mode_name(uint32_t psr) +{ + static const char cpu_mode_names[16][4] = { + "usr", "fiq", "irq", "svc", "???", "???", "mon", "abt", + "???", "???", "hyp", "und", "???", "???", "???", "sys" + }; + + return cpu_mode_names[psr & 0xf]; +} + #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask, mask |= CPSR_IL; val |= CPSR_IL; } + qemu_log_mask(LOG_GUEST_ERROR, + "Illegal AArch32 mode switch attempt from %s to %s\n", + aarch32_mode_name(env->uncached_cpsr), + aarch32_mode_name(val)); } else { + qemu_log_mask(CPU_LOG_INT, "%s %s to %s PC 0x%" PRIx32 "\n", + write_type == CPSRWriteExceptionReturn ? + "Exception return from AArch32" : + "AArch32 mode switch from", + aarch32_mode_name(env->uncached_cpsr), + aarch32_mode_name(val), env->regs[15]); switch_mode(env, val & CPSR_M); } } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb) translator_loop(ops, &dc.base, cpu, tb); } -static const char *cpu_mode_names[16] = { - "usr", "fiq", "irq", "svc", "???", "???", "mon", "abt", - "???", "???", "hyp", "und", "???", "???", "???", "sys" -}; - void arm_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, int flags) { @@ -XXX,XX +XXX,XX @@ void arm_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, psr & CPSR_V ? 'V' : '-', psr & CPSR_T ? 'T' : 'A', ns_status, - cpu_mode_names[psr & 0xf], (psr & 0x10) ? 32 : 26); + aarch32_mode_name(psr), (psr & 0x10) ? 32 : 26); } if (flags & CPU_DUMP_FPU) { -- 2.19.1 The switch_mode() function is defined in target/arm/helper.c and used only in that file and nowhere else, so we can make it file-local rather than global. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-3-peter.maydell@linaro.org --- target/arm/internals.h | 1 - target/arm/helper.c | 6 ++++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline int bank_number(int mode) g_assert_not_reached(); } -void switch_mode(CPUARMState *, int); void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu); void arm_translate_init(void); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, V8M_SAttributes *sattrs); #endif +static void switch_mode(CPUARMState *env, int mode); + static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg) { int nregs; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) return 0; } -void switch_mode(CPUARMState *env, int mode) +static void switch_mode(CPUARMState *env, int mode) { ARMCPU *cpu = arm_env_get_cpu(env); @@ -XXX,XX +XXX,XX @@ void aarch64_sync_64_to_32(CPUARMState *env) #else -void switch_mode(CPUARMState *env, int mode) +static void switch_mode(CPUARMState *env, int mode) { int old_mode; int i; -- 2.19.1 The HCR.FB virtualization configuration register bit requests that TLB maintenance, branch predictor invalidate-all and icache invalidate-all operations performed in NS EL1 should be upgraded from "local CPU only to "broadcast within Inner Shareable domain". For QEMU we NOP the branch predictor and icache operations, so we only need to upgrade the TLB invalidates: AArch32 TLBIALL, TLBIMVA, TLBIASID, DTLBIALL, DTLBIMVA, DTLBIASID, ITLBIALL, ITLBIMVA, ITLBIASID, TLBIMVAA, TLBIMVAL, TLBIMVAAL AArch64 TLBI VMALLE1, TLBI VAE1, TLBI ASIDE1, TLBI VAAE1, TLBI VALE1, TLBI VAALE1 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-4-peter.maydell@linaro.org --- target/arm/helper.c | 191 +++++++++++++++++++++++++++----------------- 1 file changed, 116 insertions(+), 75 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, raw_write(env, ri, value); } -static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate all (TLBIALL) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush(CPU(cpu)); -} - -static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); -} - -static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by ASID (TLBIASID) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush(CPU(cpu)); -} - -static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); -} - /* IS variants of TLB operations must affect all cores */ static void tlbiall_is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) @@ -XXX,XX +XXX,XX @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); } +/* + * Non-IS variants of TLB operations are upgraded to + * IS versions if we are at NS EL1 and HCR_EL2.FB is set to + * force broadcast of these operations. + */ +static bool tlb_force_broadcast(CPUARMState *env) +{ + return (env->cp15.hcr_el2 & HCR_FB) && + arm_current_el(env) == 1 && arm_is_secure_below_el3(env); +} + +static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate all (TLBIALL) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbiall_is_write(env, NULL, value); + return; + } + + tlb_flush(CPU(cpu)); +} + +static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbimva_is_write(env, NULL, value); + return; + } + + tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); +} + +static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate by ASID (TLBIASID) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbiasid_is_write(env, NULL, value); + return; + } + + tlb_flush(CPU(cpu)); +} + +static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbimvaa_is_write(env, NULL, value); + return; + } + + tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); +} + static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static CPAccessResult aa64_cacheop_access(CPUARMState *env, * Page D4-1736 (DDI0487A.b) */ -static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = ENV_GET_CPU(env); - - if (arm_is_secure_below_el3(env)) { - tlb_flush_by_mmuidx(cs, - ARMMMUIdxBit_S1SE1 | - ARMMMUIdxBit_S1SE0); - } else { - tlb_flush_by_mmuidx(cs, - ARMMMUIdxBit_S12NSE1 | - ARMMMUIdxBit_S12NSE0); - } -} - static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = ENV_GET_CPU(env); + + if (tlb_force_broadcast(env)) { + tlbi_aa64_vmalle1_write(env, NULL, value); + return; + } + + if (arm_is_secure_below_el3(env)) { + tlb_flush_by_mmuidx(cs, + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); + } else { + tlb_flush_by_mmuidx(cs, + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); + } +} + static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E3); } -static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by VA, EL1&0 (AArch64 version). - * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1, - * since we don't support flush-for-specific-ASID-only or - * flush-last-level-only. - */ - ARMCPU *cpu = arm_env_get_cpu(env); - CPUState *cs = CPU(cpu); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - - if (arm_is_secure_below_el3(env)) { - tlb_flush_page_by_mmuidx(cs, pageaddr, - ARMMMUIdxBit_S1SE1 | - ARMMMUIdxBit_S1SE0); - } else { - tlb_flush_page_by_mmuidx(cs, pageaddr, - ARMMMUIdxBit_S12NSE1 | - ARMMMUIdxBit_S12NSE0); - } -} - static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate by VA, EL1&0 (AArch64 version). + * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + ARMCPU *cpu = arm_env_get_cpu(env); + CPUState *cs = CPU(cpu); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + + if (tlb_force_broadcast(env)) { + tlbi_aa64_vae1is_write(env, NULL, value); + return; + } + + if (arm_is_secure_below_el3(env)) { + tlb_flush_page_by_mmuidx(cs, pageaddr, + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); + } else { + tlb_flush_page_by_mmuidx(cs, pageaddr, + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); + } +} + static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { -- 2.19.1 The HCR.DC virtualization configuration register bit has the following effects: * SCTLR.M behaves as if it is 0 for all purposes except direct reads of the bit * HCR.VM behaves as if it is 1 for all purposes except direct reads of the bit * the memory type produced by the first stage of the EL1&EL0 translation regime is Normal Non-Shareable, Inner Write-Back Read-Allocate Write-Allocate, Outer Write-Back Read-Allocate Write-Allocate. Implement this behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-5-peter.maydell@linaro.org --- target/arm/helper.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, * * The Non-secure TTBCR.EAE bit is set to 1 * * The implementation includes EL2, and the value of HCR.VM is 1 * + * (Note that HCR.DC makes HCR.VM behave as if it is 1.) + * * ATS1Hx always uses the 64bit format (not supported yet). */ format64 = arm_s1_regime_using_lpae_format(env, mmu_idx); if (arm_feature(env, ARM_FEATURE_EL2)) { if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - format64 |= env->cp15.hcr_el2 & HCR_VM; + format64 |= env->cp15.hcr_el2 & (HCR_VM | HCR_DC); } else { format64 |= arm_current_el(env) == 2; } @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_disabled(CPUARMState *env, } if (mmu_idx == ARMMMUIdx_S2NS) { - return (env->cp15.hcr_el2 & HCR_VM) == 0; + /* HCR.DC means HCR.VM behaves as 1 */ + return (env->cp15.hcr_el2 & (HCR_DC | HCR_VM)) == 0; } if (env->cp15.hcr_el2 & HCR_TGE) { @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_disabled(CPUARMState *env, } } + if ((env->cp15.hcr_el2 & HCR_DC) && + (mmu_idx == ARMMMUIdx_S1NSE0 || mmu_idx == ARMMMUIdx_S1NSE1)) { + /* HCR.DC means SCTLR_EL1.M behaves as 0 */ + return true; + } + return (regime_sctlr(env, mmu_idx) & SCTLR_M) == 0; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, /* Combine the S1 and S2 cache attributes, if needed */ if (!ret && cacheattrs != NULL) { + if (env->cp15.hcr_el2 & HCR_DC) { + /* + * HCR.DC forces the first stage attributes to + * Normal Non-Shareable, + * Inner Write-Back Read-Allocate Write-Allocate, + * Outer Write-Back Read-Allocate Write-Allocate. + */ + cacheattrs->attrs = 0xff; + cacheattrs->shareability = 0; + } *cacheattrs = combine_cacheattrs(*cacheattrs, cacheattrs2); } -- 2.19.1 The A/I/F bits in ISR_EL1 should track the virtual interrupt status, not the physical interrupt status, if the associated HCR_EL2.AMO/IMO/FMO bit is set. Implement this, rather than always showing the physical interrupt status. We don't currently implement anything to do with external aborts, so this applies only to the I and F bits (though it ought to be possible for the outer guest to present a virtual external abort to the inner guest, even if QEMU doesn't emulate physical external aborts, so there is missing functionality in this area). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-6-peter.maydell@linaro.org --- target/arm/helper.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t isr_read(CPUARMState *env, const ARMCPRegInfo *ri) CPUState *cs = ENV_GET_CPU(env); uint64_t ret = 0; - if (cs->interrupt_request & CPU_INTERRUPT_HARD) { - ret |= CPSR_I; + if (arm_hcr_el2_imo(env)) { + if (cs->interrupt_request & CPU_INTERRUPT_VIRQ) { + ret |= CPSR_I; + } + } else { + if (cs->interrupt_request & CPU_INTERRUPT_HARD) { + ret |= CPSR_I; + } } - if (cs->interrupt_request & CPU_INTERRUPT_FIQ) { - ret |= CPSR_F; + + if (arm_hcr_el2_fmo(env)) { + if (cs->interrupt_request & CPU_INTERRUPT_VFIQ) { + ret |= CPSR_F; + } + } else { + if (cs->interrupt_request & CPU_INTERRUPT_FIQ) { + ret |= CPSR_F; + } } + /* External aborts are not possible in QEMU so A bit is always clear */ return ret; } -- 2.19.1 The HCR_EL2 VI and VF bits are supposed to track whether there is a pending virtual IRQ or virtual FIQ. For QEMU we store the pending VIRQ/VFIQ status in cs->interrupt_request, so this means: * if the register is read we must get these bit values from cs->interrupt_request * if the register is written then we must write the bit values back into cs->interrupt_request Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-7-peter.maydell@linaro.org --- target/arm/helper.c | 47 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 43 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_no_el2_v8_cp_reginfo[] = { static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { ARMCPU *cpu = arm_env_get_cpu(env); + CPUState *cs = ENV_GET_CPU(env); uint64_t valid_mask = HCR_MASK; if (arm_feature(env, ARM_FEATURE_EL3)) { @@ -XXX,XX +XXX,XX @@ static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) /* Clear RES0 bits. */ value &= valid_mask; + /* + * VI and VF are kept in cs->interrupt_request. Modifying that + * requires that we have the iothread lock, which is done by + * marking the reginfo structs as ARM_CP_IO. + * Note that if a write to HCR pends a VIRQ or VFIQ it is never + * possible for it to be taken immediately, because VIRQ and + * VFIQ are masked unless running at EL0 or EL1, and HCR + * can only be written at EL2. + */ + g_assert(qemu_mutex_iothread_locked()); + if (value & HCR_VI) { + cs->interrupt_request |= CPU_INTERRUPT_VIRQ; + } else { + cs->interrupt_request &= ~CPU_INTERRUPT_VIRQ; + } + if (value & HCR_VF) { + cs->interrupt_request |= CPU_INTERRUPT_VFIQ; + } else { + cs->interrupt_request &= ~CPU_INTERRUPT_VFIQ; + } + value &= ~(HCR_VI | HCR_VF); + /* These bits change the MMU setup: * HCR_VM enables stage 2 translation * HCR_PTW forbids certain page-table setups @@ -XXX,XX +XXX,XX @@ static void hcr_writelow(CPUARMState *env, const ARMCPRegInfo *ri, hcr_write(env, NULL, value); } +static uint64_t hcr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* The VI and VF bits live in cs->interrupt_request */ + uint64_t ret = env->cp15.hcr_el2 & ~(HCR_VI | HCR_VF); + CPUState *cs = ENV_GET_CPU(env); + + if (cs->interrupt_request & CPU_INTERRUPT_VIRQ) { + ret |= HCR_VI; + } + if (cs->interrupt_request & CPU_INTERRUPT_VFIQ) { + ret |= HCR_VF; + } + return ret; +} + static const ARMCPRegInfo el2_cp_reginfo[] = { { .name = "HCR_EL2", .state = ARM_CP_STATE_AA64, + .type = ARM_CP_IO, .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2), - .writefn = hcr_write }, + .writefn = hcr_write, .readfn = hcr_read }, { .name = "HCR", .state = ARM_CP_STATE_AA32, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .cp = 15, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2), - .writefn = hcr_writelow }, + .writefn = hcr_writelow, .readfn = hcr_read }, { .name = "ELR_EL2", .state = ARM_CP_STATE_AA64, .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 0, .opc2 = 1, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = { static const ARMCPRegInfo el2_v8_cp_reginfo[] = { { .name = "HCR2", .state = ARM_CP_STATE_AA32, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .cp = 15, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 4, .access = PL2_RW, .fieldoffset = offsetofhigh32(CPUARMState, cp15.hcr_el2), -- 2.19.1 If the HCR_EL2 PTW virtualizaiton configuration register bit is set, then this means that a stage 2 Permission fault must be generated if a stage 1 translation table access is made to an address that is mapped as Device memory in stage 2. Implement this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-8-peter.maydell@linaro.org --- target/arm/helper.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, hwaddr s2pa; int s2prot; int ret; + ARMCacheAttrs cacheattrs = {}; + ARMCacheAttrs *pcacheattrs = NULL; + + if (env->cp15.hcr_el2 & HCR_PTW) { + /* + * PTW means we must fault if this S1 walk touches S2 Device + * memory; otherwise we don't care about the attributes and can + * save the S2 translation the effort of computing them. + */ + pcacheattrs = &cacheattrs; + } ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_S2NS, &s2pa, - &txattrs, &s2prot, &s2size, fi, NULL); + &txattrs, &s2prot, &s2size, fi, pcacheattrs); if (ret) { assert(fi->type != ARMFault_None); fi->s2addr = addr; @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, fi->s1ptw = true; return ~0; } + if (pcacheattrs && (pcacheattrs->attrs & 0xf0) == 0) { + /* Access was to Device memory: generate Permission fault */ + fi->type = ARMFault_Permission; + fi->s2addr = addr; + fi->stage2 = true; + fi->s1ptw = true; + return ~0; + } addr = s2pa; } return addr; -- 2.19.1 Create and use a utility function to extract the EC field from a syndrome, rather than open-coding the shift. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-9-peter.maydell@linaro.org --- target/arm/internals.h | 5 +++++ target/arm/helper.c | 4 ++-- target/arm/kvm64.c | 2 +- target/arm/op_helper.c | 2 +- 4 files changed, 9 insertions(+), 4 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { #define ARM_EL_IL (1 << ARM_EL_IL_SHIFT) #define ARM_EL_ISV (1 << ARM_EL_ISV_SHIFT) +static inline uint32_t syn_get_ec(uint32_t syn) +{ + return syn >> ARM_EL_EC_SHIFT; +} + /* Utility functions for constructing various kinds of syndrome value. * Note that in general we follow the AArch64 syndrome values; in a * few cases the value in HSR for exceptions taken to AArch32 Hyp diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32(CPUState *cs) uint32_t moe; /* If this is a debug exception we must update the DBGDSCR.MOE bits */ - switch (env->exception.syndrome >> ARM_EL_EC_SHIFT) { + switch (syn_get_ec(env->exception.syndrome)) { case EC_BREAKPOINT: case EC_BREAKPOINT_SAME_EL: moe = 1; @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_interrupt(CPUState *cs) if (qemu_loglevel_mask(CPU_LOG_INT) && !excp_is_internal(cs->exception_index)) { qemu_log_mask(CPU_LOG_INT, "...with ESR 0x%x/0x%" PRIx32 "\n", - env->exception.syndrome >> ARM_EL_EC_SHIFT, + syn_get_ec(env->exception.syndrome), env->exception.syndrome); } diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit) { - int hsr_ec = debug_exit->hsr >> ARM_EL_EC_SHIFT; + int hsr_ec = syn_get_ec(debug_exit->hsr); ARMCPU *cpu = ARM_CPU(cs); CPUClass *cc = CPU_GET_CLASS(cs); CPUARMState *env = &cpu->env; diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void raise_exception(CPUARMState *env, uint32_t excp, * (see DDI0478C.a D1.10.4) */ target_el = 2; - if (syndrome >> ARM_EL_EC_SHIFT == EC_ADVSIMDFPACCESSTRAP) { + if (syn_get_ec(syndrome) == EC_ADVSIMDFPACCESSTRAP) { syndrome = syn_uncategorized(); } } -- 2.19.1 For the v7 version of the Arm architecture, the IL bit in syndrome register values where the field is not valid was defined to be UNK/SBZP. In v8 this is RES1, which is what QEMU currently implements. Handle the desired v7 behaviour by squashing the IL bit for the affected cases: * EC == EC_UNCATEGORIZED * prefetch aborts * data aborts where ISV is 0 (The fourth case listed in the v8 Arm ARM DDI 0487C.a in section G7.2.70, "illegal state exception", can't happen on a v7 CPU.) This deals with a corner case noted in a comment. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-10-peter.maydell@linaro.org --- target/arm/internals.h | 7 ++----- target/arm/helper.c | 13 +++++++++++++ 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_get_ec(uint32_t syn) /* Utility functions for constructing various kinds of syndrome value. * Note that in general we follow the AArch64 syndrome values; in a * few cases the value in HSR for exceptions taken to AArch32 Hyp - * mode differs slightly, so if we ever implemented Hyp mode then the - * syndrome value would need some massaging on exception entry. - * (One example of this is that AArch64 defaults to IL bit set for - * exceptions which don't specifically indicate information about the - * trapping instruction, whereas AArch32 defaults to IL bit clear.) + * mode differs slightly, and we fix this up when populating HSR in + * arm_cpu_do_interrupt_aarch32_hyp(). */ static inline uint32_t syn_uncategorized(void) { diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs) } if (cs->exception_index != EXCP_IRQ && cs->exception_index != EXCP_FIQ) { + if (!arm_feature(env, ARM_FEATURE_V8)) { + /* + * QEMU syndrome values are v8-style. v7 has the IL bit + * UNK/SBZP for "field not valid" cases, where v8 uses RES1. + * If this is a v7 CPU, squash the IL bit in those cases. + */ + if (cs->exception_index == EXCP_PREFETCH_ABORT || + (cs->exception_index == EXCP_DATA_ABORT && + !(env->exception.syndrome & ARM_EL_ISV)) || + syn_get_ec(env->exception.syndrome) == EC_UNCATEGORIZED) { + env->exception.syndrome &= ~ARM_EL_IL; + } + } env->cp15.esr_el[2] = env->exception.syndrome; } -- 2.19.1 For traps of FP/SIMD instructions to AArch32 Hyp mode, the syndrome provided in HSR has more information than is reported to AArch64. Specifically, there are extra fields TA and coproc which indicate whether the trapped instruction was FP or SIMD. Add this extra information to the syndromes we construct, and mask it out when taking the exception to AArch64. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-11-peter.maydell@linaro.org --- target/arm/internals.h | 14 +++++++++++++- target/arm/helper.c | 9 +++++++++ target/arm/translate.c | 8 ++++---- 3 files changed, 26 insertions(+), 5 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_get_ec(uint32_t syn) * few cases the value in HSR for exceptions taken to AArch32 Hyp * mode differs slightly, and we fix this up when populating HSR in * arm_cpu_do_interrupt_aarch32_hyp(). + * The exception is FP/SIMD access traps -- these report extra information + * when taking an exception to AArch32. For those we include the extra coproc + * and TA fields, and mask them out when taking the exception to AArch64. */ static inline uint32_t syn_uncategorized(void) { @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm, static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit) { + /* AArch32 FP trap or any AArch64 FP/SIMD trap: TA == 0 coproc == 0xa */ return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20); + | (cv << 24) | (cond << 20) | 0xa; +} + +static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit) +{ + /* AArch32 SIMD trap: TA == 1 coproc == 0 */ + return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) + | (is_16bit ? 0 : ARM_EL_IL) + | (cv << 24) | (cond << 20) | (1 << 5); } static inline uint32_t syn_sve_access_trap(void) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) case EXCP_HVC: case EXCP_HYP_TRAP: case EXCP_SMC: + if (syn_get_ec(env->exception.syndrome) == EC_ADVSIMDFPACCESSTRAP) { + /* + * QEMU internal FP/SIMD syndromes from AArch32 include the + * TA and coproc fields which are only exposed if the exception + * is taken to AArch32 Hyp mode. Mask them out to get a valid + * AArch64 format syndrome. + */ + env->exception.syndrome &= ~MAKE_64BIT_MASK(0, 20); + } env->cp15.esr_el[new_el] = env->exception.syndrome; break; case EXCP_IRQ: diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) */ if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) */ if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } if (!s->vfp_enabled) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } if (!s->vfp_enabled) { -- 2.19.1 From: Stewart Hildebrand <Stewart.Hildebrand@dornerworks.com> "The Image must be placed text_offset bytes from a 2MB aligned base address anywhere in usable system RAM and called there." For the virt board, we write our startup bootloader at the very bottom of RAM, so that bit can't be used for the image. To avoid overlap in case the image requests to be loaded at an offset smaller than our bootloader, we increment the load offset to the next 2MB. This fixes a boot failure for Xen AArch64. Signed-off-by: Stewart Hildebrand <stewart.hildebrand@dornerworks.com> Tested-by: Andre Przywara <andre.przywara@arm.com> Message-id: b8a89518794b4436af0c151ed10de4fa@dornerworks.com [PMM: Rephrased a comment a bit] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ #include "qemu/config-file.h" #include "qemu/option.h" #include "exec/address-spaces.h" +#include "qemu/units.h" /* Kernel boot protocol is specified in the kernel docs * Documentation/arm/Booting and Documentation/arm64/booting.txt @@ -XXX,XX +XXX,XX @@ #define ARM64_TEXT_OFFSET_OFFSET 8 #define ARM64_MAGIC_OFFSET 56 +#define BOOTLOADER_MAX_SIZE (4 * KiB) + AddressSpace *arm_boot_address_space(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static void write_bootloader(const char *name, hwaddr addr, code[i] = tswap32(insn); } + assert((len * sizeof(uint32_t)) < BOOTLOADER_MAX_SIZE); + rom_add_blob_fixed_as(name, code, len * sizeof(uint32_t), addr, as); g_free(code); @@ -XXX,XX +XXX,XX @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, memcpy(&hdrvals, buffer + ARM64_TEXT_OFFSET_OFFSET, sizeof(hdrvals)); if (hdrvals[1] != 0) { kernel_load_offset = le64_to_cpu(hdrvals[0]); + + /* + * We write our startup "bootloader" at the very bottom of RAM, + * so that bit can't be used for the image. Luckily the Image + * format specification is that the image requests only an offset + * from a 2MB boundary, not an absolute load address. So if the + * image requests an offset that might mean it overlaps with the + * bootloader, we can just load it starting at 2MB+offset rather + * than 0MB + offset. + */ + if (kernel_load_offset < BOOTLOADER_MAX_SIZE) { + kernel_load_offset += 2 * MiB; + } } } -- 2.19.1 From: Richard Henderson <rth@twiddle.net> This can reduce the number of opcodes required for certain complex forms of load-multiple (e.g. ld4.16b). Signed-off-by: Richard Henderson <rth@twiddle.net> Message-id: 20181011205206.3552-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) bool is_store = !extract32(insn, 22, 1); bool is_postidx = extract32(insn, 23, 1); bool is_q = extract32(insn, 30, 1); - TCGv_i64 tcg_addr, tcg_rn; + TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; int ebytes = 1 << size; int elements = (is_q ? 128 : 64) / (8 << size); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) tcg_rn = cpu_reg_sp(s, rn); tcg_addr = tcg_temp_new_i64(); tcg_gen_mov_i64(tcg_addr, tcg_rn); + tcg_ebytes = tcg_const_i64(ebytes); for (r = 0; r < rpt; r++) { int e; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) clear_vec_high(s, is_q, tt); } } - tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes); + tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); tt = (tt + 1) % 32; } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); } } + tcg_temp_free_i64(tcg_ebytes); tcg_temp_free_i64(tcg_addr); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) bool replicate = false; int index = is_q << 3 | S << 2 | size; int ebytes, xs; - TCGv_i64 tcg_addr, tcg_rn; + TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; switch (scale) { case 3: @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) tcg_rn = cpu_reg_sp(s, rn); tcg_addr = tcg_temp_new_i64(); tcg_gen_mov_i64(tcg_addr, tcg_rn); + tcg_ebytes = tcg_const_i64(ebytes); for (xs = 0; xs < selem; xs++) { if (replicate) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) do_vec_st(s, rt, index, tcg_addr, scale); } } - tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes); + tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); rt = (rt + 1) % 32; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); } } + tcg_temp_free_i64(tcg_ebytes); tcg_temp_free_i64(tcg_addr); } -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> This is done generically in translator_loop. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181011205206.3552-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 1 - target/arm/translate.c | 1 - 2 files changed, 2 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, static void aarch64_tr_tb_start(DisasContextBase *db, CPUState *cpu) { - tcg_clear_temp_count(); } static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_tb_start(DisasContextBase *dcbase, CPUState *cpu) tcg_gen_movi_i32(tmp, 0); store_cpu_field(tmp, condexec_bits); } - tcg_clear_temp_count(); } static void arm_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 28 +++------------------------- 1 file changed, 3 insertions(+), 25 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) for (xs = 0; xs < selem; xs++) { if (replicate) { /* Load and replicate to all elements */ - uint64_t mulconst; TCGv_i64 tcg_tmp = tcg_temp_new_i64(); tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), s->be_data + scale); - switch (scale) { - case 0: - mulconst = 0x0101010101010101ULL; - break; - case 1: - mulconst = 0x0001000100010001ULL; - break; - case 2: - mulconst = 0x0000000100000001ULL; - break; - case 3: - mulconst = 0; - break; - default: - g_assert_not_reached(); - } - if (mulconst) { - tcg_gen_muli_i64(tcg_tmp, tcg_tmp, mulconst); - } - write_vec_element(s, tcg_tmp, rt, 0, MO_64); - if (is_q) { - write_vec_element(s, tcg_tmp, rt, 1, MO_64); - } + tcg_gen_gvec_dup_i64(scale, vec_full_reg_offset(s, rt), + (is_q + 1) * 8, vec_full_reg_size(s), + tcg_tmp); tcg_temp_free_i64(tcg_tmp); - clear_vec_high(s, is_q, rt); } else { /* Load/store one element per register */ if (is_load) { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> For a sequence of loads or stores from a single register, little-endian operations can be promoted to an 8-byte op. This can reduce the number of operations by a factor of 8. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 66 +++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 26 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src, /* Store from vector register to memory */ static void do_vec_st(DisasContext *s, int srcidx, int element, - TCGv_i64 tcg_addr, int size) + TCGv_i64 tcg_addr, int size, TCGMemOp endian) { - TCGMemOp memop = s->be_data + size; TCGv_i64 tcg_tmp = tcg_temp_new_i64(); read_vec_element(s, tcg_tmp, srcidx, element, size); - tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop); + tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), endian | size); tcg_temp_free_i64(tcg_tmp); } /* Load from memory to vector register */ static void do_vec_ld(DisasContext *s, int destidx, int element, - TCGv_i64 tcg_addr, int size) + TCGv_i64 tcg_addr, int size, TCGMemOp endian) { - TCGMemOp memop = s->be_data + size; TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop); + tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), endian | size); write_vec_element(s, tcg_tmp, destidx, element, size); tcg_temp_free_i64(tcg_tmp); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) bool is_postidx = extract32(insn, 23, 1); bool is_q = extract32(insn, 30, 1); TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; + TCGMemOp endian = s->be_data; - int ebytes = 1 << size; - int elements = (is_q ? 128 : 64) / (8 << size); + int ebytes; /* bytes per element */ + int elements; /* elements per vector */ int rpt; /* num iterations */ int selem; /* structure elements */ int r; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } + /* For our purposes, bytes are always little-endian. */ + if (size == 0) { + endian = MO_LE; + } + + /* Consecutive little-endian elements from a single register + * can be promoted to a larger little-endian operation. + */ + if (selem == 1 && endian == MO_LE) { + size = 3; + } + ebytes = 1 << size; + elements = (is_q ? 16 : 8) / ebytes; + tcg_rn = cpu_reg_sp(s, rn); tcg_addr = tcg_temp_new_i64(); tcg_gen_mov_i64(tcg_addr, tcg_rn); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) for (r = 0; r < rpt; r++) { int e; for (e = 0; e < elements; e++) { - int tt = (rt + r) % 32; int xs; for (xs = 0; xs < selem; xs++) { + int tt = (rt + r + xs) % 32; if (is_store) { - do_vec_st(s, tt, e, tcg_addr, size); + do_vec_st(s, tt, e, tcg_addr, size, endian); } else { - do_vec_ld(s, tt, e, tcg_addr, size); - - /* For non-quad operations, setting a slice of the low - * 64 bits of the register clears the high 64 bits (in - * the ARM ARM pseudocode this is implicit in the fact - * that 'rval' is a 64 bit wide variable). - * For quad operations, we might still need to zero the - * high bits of SVE. We optimize by noticing that we only - * need to do this the first time we touch a register. - */ - if (e == 0 && (r == 0 || xs == selem - 1)) { - clear_vec_high(s, is_q, tt); - } + do_vec_ld(s, tt, e, tcg_addr, size, endian); } tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); - tt = (tt + 1) % 32; } } } + if (!is_store) { + /* For non-quad operations, setting a slice of the low + * 64 bits of the register clears the high 64 bits (in + * the ARM ARM pseudocode this is implicit in the fact + * that 'rval' is a 64 bit wide variable). + * For quad operations, we might still need to zero the + * high bits of SVE. + */ + for (r = 0; r < rpt * selem; r++) { + int tt = (rt + r) % 32; + clear_vec_high(s, is_q, tt); + } + } + if (is_postidx) { int rm = extract32(insn, 16, 5); if (rm == 31) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } else { /* Load/store one element per register */ if (is_load) { - do_vec_ld(s, rt, index, tcg_addr, scale); + do_vec_ld(s, rt, index, tcg_addr, scale, s->be_data); } else { - do_vec_st(s, rt, index, tcg_addr, scale); + do_vec_st(s, rt, index, tcg_addr, scale, s->be_data); } } tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181011205206.3552-6-richard.henderson@linaro.org [PMM: drop change to now-deleted cpu_mode_names array] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i64 cpu_F0d, cpu_F1d; #include "exec/gen-icount.h" -static const char *regnames[] = +static const char * const regnames[] = { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" }; @@ -XXX,XX +XXX,XX @@ static struct { int nregs; int interleave; int spacing; -} neon_ls_element_type[11] = { +} const neon_ls_element_type[11] = { {4, 4, 1}, {4, 4, 2}, {4, 1, 1}, -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Also introduces neon_element_offset to find the env offset of a specific element within a neon register. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 63 ++++++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 27 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ neon_reg_offset (int reg, int n) return vfp_reg_offset(0, sreg); } +/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, + * where 0 is the least significant end of the register. + */ +static inline long +neon_element_offset(int reg, int element, TCGMemOp size) +{ + int element_size = 1 << size; + int ofs = element * element_size; +#ifdef HOST_WORDS_BIGENDIAN + /* Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + */ + if (element_size < 8) { + ofs ^= 8 - element_size; + } +#endif + return neon_reg_offset(reg, 0) + ofs; +} + static TCGv_i32 neon_load_reg(int reg, int pass) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tmp = load_reg(s, rd); if (insn & (1 << 23)) { /* VDUP */ - if (size == 0) { - gen_neon_dup_u8(tmp, 0); - } else if (size == 1) { - gen_neon_dup_low16(tmp); - } - for (n = 0; n <= pass * 2; n++) { - tmp2 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp2, tmp); - neon_store_reg(rn, n, tmp2); - } - neon_store_reg(rn, n, tmp); + int vec_size = pass ? 16 : 8; + tcg_gen_gvec_dup_i32(size, neon_reg_offset(rn, 0), + vec_size, vec_size, tmp); + tcg_temp_free_i32(tmp); } else { /* VMOV */ switch (size) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp); } else if ((insn & 0x380) == 0) { /* VDUP */ + int element; + TCGMemOp size; + if ((insn & (7 << 16)) == 0 || (q && (rd & 1))) { return 1; } - if (insn & (1 << 19)) { - tmp = neon_load_reg(rm, 1); - } else { - tmp = neon_load_reg(rm, 0); - } if (insn & (1 << 16)) { - gen_neon_dup_u8(tmp, ((insn >> 17) & 3) * 8); + size = MO_8; + element = (insn >> 17) & 7; } else if (insn & (1 << 17)) { - if ((insn >> 18) & 1) - gen_neon_dup_high16(tmp); - else - gen_neon_dup_low16(tmp); + size = MO_16; + element = (insn >> 18) & 3; + } else { + size = MO_32; + element = (insn >> 19) & 1; } - for (pass = 0; pass < (q ? 4 : 2); pass++) { - tmp2 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp2, tmp); - neon_store_reg(rd, pass, tmp2); - } - tcg_temp_free_i32(tmp); + tcg_gen_gvec_dup_mem(size, neon_reg_offset(rd, 0), + neon_element_offset(rm, element, size), + q ? 16 : 8, q ? 16 : 8); } else { return 1; } -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 67 ++++++++++++++++++++++++------------------ 1 file changed, 39 insertions(+), 28 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } } else { /* (insn & 0x00380080) == 0 */ - int invert; + int invert, reg_ofs, vec_size; + if (q && (rd & 1)) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; case 14: imm |= (imm << 8) | (imm << 16) | (imm << 24); - if (invert) + if (invert) { imm = ~imm; + } break; case 15: if (invert) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); break; } - if (invert) + if (invert) { imm = ~imm; + } - for (pass = 0; pass < (q ? 4 : 2); pass++) { - if (op & 1 && op < 12) { - tmp = neon_load_reg(rd, pass); - if (invert) { - /* The immediate value has already been inverted, so - BIC becomes AND. */ - tcg_gen_andi_i32(tmp, tmp, imm); - } else { - tcg_gen_ori_i32(tmp, tmp, imm); - } + reg_ofs = neon_reg_offset(rd, 0); + vec_size = q ? 16 : 8; + + if (op & 1 && op < 12) { + if (invert) { + /* The immediate value has already been inverted, + * so BIC becomes AND. + */ + tcg_gen_gvec_andi(MO_32, reg_ofs, reg_ofs, imm, + vec_size, vec_size); } else { - /* VMOV, VMVN. */ - tmp = tcg_temp_new_i32(); - if (op == 14 && invert) { - int n; - uint32_t val; - val = 0; - for (n = 0; n < 4; n++) { - if (imm & (1 << (n + (pass & 1) * 4))) - val |= 0xff << (n * 8); - } - tcg_gen_movi_i32(tmp, val); - } else { - tcg_gen_movi_i32(tmp, imm); - } + tcg_gen_gvec_ori(MO_32, reg_ofs, reg_ofs, imm, + vec_size, vec_size); + } + } else { + /* VMOV, VMVN. */ + if (op == 14 && invert) { + TCGv_i64 t64 = tcg_temp_new_i64(); + + for (pass = 0; pass <= q; ++pass) { + uint64_t val = 0; + int n; + + for (n = 0; n < 8; n++) { + if (imm & (1 << (n + pass * 8))) { + val |= 0xffull << (n * 8); + } + } + tcg_gen_movi_i64(t64, val); + neon_store_reg64(t64, rd + pass); + } + tcg_temp_free_i64(t64); + } else { + tcg_gen_gvec_dup32i(reg_ofs, vec_size, vec_size, imm); } - neon_store_reg(rd, pass, tmp); } } } else { /* (insn & 0x00800010 == 0x00800000) */ -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move expanders for VBSL, VBIT, and VBIF from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 6 ++ target/arm/translate-a64.c | 61 -------------- target/arm/translate.c | 162 +++++++++++++++++++++++++++---------- 3 files changed, 124 insertions(+), 105 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) return ret; } + +/* Vector operations shared between ARM and AArch64. */ +extern const GVecGen3 bsl_op; +extern const GVecGen3 bit_op; +extern const GVecGen3 bif_op; + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) } } -static void gen_bsl_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) -{ - tcg_gen_xor_i64(rn, rn, rm); - tcg_gen_and_i64(rn, rn, rd); - tcg_gen_xor_i64(rd, rm, rn); -} - -static void gen_bit_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) -{ - tcg_gen_xor_i64(rn, rn, rd); - tcg_gen_and_i64(rn, rn, rm); - tcg_gen_xor_i64(rd, rd, rn); -} - -static void gen_bif_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) -{ - tcg_gen_xor_i64(rn, rn, rd); - tcg_gen_andc_i64(rn, rn, rm); - tcg_gen_xor_i64(rd, rd, rn); -} - -static void gen_bsl_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) -{ - tcg_gen_xor_vec(vece, rn, rn, rm); - tcg_gen_and_vec(vece, rn, rn, rd); - tcg_gen_xor_vec(vece, rd, rm, rn); -} - -static void gen_bit_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) -{ - tcg_gen_xor_vec(vece, rn, rn, rd); - tcg_gen_and_vec(vece, rn, rn, rm); - tcg_gen_xor_vec(vece, rd, rd, rn); -} - -static void gen_bif_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) -{ - tcg_gen_xor_vec(vece, rn, rn, rd); - tcg_gen_andc_vec(vece, rn, rn, rm); - tcg_gen_xor_vec(vece, rd, rd, rn); -} - /* Logic op (opcode == 3) subgroup of C3.6.16. */ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) { - static const GVecGen3 bsl_op = { - .fni8 = gen_bsl_i64, - .fniv = gen_bsl_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true - }; - static const GVecGen3 bit_op = { - .fni8 = gen_bit_i64, - .fniv = gen_bit_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true - }; - static const GVecGen3 bif_op = { - .fni8 = gen_bif_i64, - .fniv = gen_bif_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true - }; - int rd = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); int rm = extract32(insn, 16, 5); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) return 0; } -/* Bitwise select. dest = c ? t : f. Clobbers T and F. */ -static void gen_neon_bsl(TCGv_i32 dest, TCGv_i32 t, TCGv_i32 f, TCGv_i32 c) -{ - tcg_gen_and_i32(t, t, c); - tcg_gen_andc_i32(f, f, c); - tcg_gen_or_i32(dest, t, f); -} - static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src) { switch (size) { @@ -XXX,XX +XXX,XX @@ static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, return 1; } +/* + * Expanders for VBitOps_VBIF, VBIT, VBSL. + */ +static void gen_bsl_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_xor_i64(rn, rn, rm); + tcg_gen_and_i64(rn, rn, rd); + tcg_gen_xor_i64(rd, rm, rn); +} + +static void gen_bit_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_xor_i64(rn, rn, rd); + tcg_gen_and_i64(rn, rn, rm); + tcg_gen_xor_i64(rd, rd, rn); +} + +static void gen_bif_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_xor_i64(rn, rn, rd); + tcg_gen_andc_i64(rn, rn, rm); + tcg_gen_xor_i64(rd, rd, rn); +} + +static void gen_bsl_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) +{ + tcg_gen_xor_vec(vece, rn, rn, rm); + tcg_gen_and_vec(vece, rn, rn, rd); + tcg_gen_xor_vec(vece, rd, rm, rn); +} + +static void gen_bit_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) +{ + tcg_gen_xor_vec(vece, rn, rn, rd); + tcg_gen_and_vec(vece, rn, rn, rm); + tcg_gen_xor_vec(vece, rd, rd, rn); +} + +static void gen_bif_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) +{ + tcg_gen_xor_vec(vece, rn, rn, rd); + tcg_gen_andc_vec(vece, rn, rn, rm); + tcg_gen_xor_vec(vece, rd, rd, rn); +} + +const GVecGen3 bsl_op = { + .fni8 = gen_bsl_i64, + .fniv = gen_bsl_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true +}; + +const GVecGen3 bit_op = { + .fni8 = gen_bit_i64, + .fniv = gen_bit_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true +}; + +const GVecGen3 bif_op = { + .fni8 = gen_bif_i64, + .fniv = gen_bif_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true +}; + + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { int op; int q; - int rd, rn, rm; + int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs; int size; int shift; int pass; int count; int pairwise; int u; + int vec_size; uint32_t imm, mask; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; TCGv_ptr ptr1, ptr2, ptr3; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) VFP_DREG_N(rn, insn); VFP_DREG_M(rm, insn); size = (insn >> 20) & 3; + vec_size = q ? 16 : 8; + rd_ofs = neon_reg_offset(rd, 0); + rn_ofs = neon_reg_offset(rn, 0); + rm_ofs = neon_reg_offset(rm, 0); + if ((insn & (1 << 23)) == 0) { /* Three register same length. */ op = ((insn >> 7) & 0x1e) | ((insn >> 4) & 1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) q, rd, rn, rm); } return 1; + + case NEON_3R_LOGIC: /* Logic ops. */ + switch ((u << 2) | size) { + case 0: /* VAND */ + tcg_gen_gvec_and(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 1: /* VBIC */ + tcg_gen_gvec_andc(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 2: + if (rn == rm) { + /* VMOV */ + tcg_gen_gvec_mov(0, rd_ofs, rn_ofs, vec_size, vec_size); + } else { + /* VORR */ + tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + break; + case 3: /* VORN */ + tcg_gen_gvec_orc(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 4: /* VEOR */ + tcg_gen_gvec_xor(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 5: /* VBSL */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &bsl_op); + break; + case 6: /* VBIT */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &bit_op); + break; + case 7: /* VBIF */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &bif_op); + break; + } + return 0; } - if (size == 3 && op != NEON_3R_LOGIC) { + if (size == 3) { /* 64-bit element instructions. */ for (pass = 0; pass < (q ? 2 : 1); pass++) { neon_load_reg64(cpu_V0, rn + pass); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VRHADD: GEN_NEON_INTEGER_OP(rhadd); break; - case NEON_3R_LOGIC: /* Logic ops. */ - switch ((u << 2) | size) { - case 0: /* VAND */ - tcg_gen_and_i32(tmp, tmp, tmp2); - break; - case 1: /* BIC */ - tcg_gen_andc_i32(tmp, tmp, tmp2); - break; - case 2: /* VORR */ - tcg_gen_or_i32(tmp, tmp, tmp2); - break; - case 3: /* VORN */ - tcg_gen_orc_i32(tmp, tmp, tmp2); - break; - case 4: /* VEOR */ - tcg_gen_xor_i32(tmp, tmp, tmp2); - break; - case 5: /* VBSL */ - tmp3 = neon_load_reg(rd, pass); - gen_neon_bsl(tmp, tmp, tmp2, tmp3); - tcg_temp_free_i32(tmp3); - break; - case 6: /* VBIT */ - tmp3 = neon_load_reg(rd, pass); - gen_neon_bsl(tmp, tmp, tmp3, tmp2); - tcg_temp_free_i32(tmp3); - break; - case 7: /* VBIF */ - tmp3 = neon_load_reg(rd, pass); - gen_neon_bsl(tmp, tmp3, tmp, tmp2); - tcg_temp_free_i32(tmp3); - break; - } - break; case NEON_3R_VHSUB: GEN_NEON_INTEGER_OP(hsub); break; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 29 ++++++++++------------------- 1 file changed, 10 insertions(+), 19 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } return 0; + + case NEON_3R_VADD_VSUB: + if (u) { + tcg_gen_gvec_sub(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + tcg_gen_gvec_add(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; } if (size == 3) { /* 64-bit element instructions. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) cpu_V1, cpu_V0); } break; - case NEON_3R_VADD_VSUB: - if (u) { - tcg_gen_sub_i64(CPU_V001); - } else { - tcg_gen_add_i64(CPU_V001); - } - break; default: abort(); } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); break; - case NEON_3R_VADD_VSUB: - if (!u) { /* VADD */ - gen_neon_add(size, tmp, tmp2); - } else { /* VSUB */ - switch (size) { - case 0: gen_helper_neon_sub_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_sub_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_sub_i32(tmp, tmp, tmp2); break; - default: abort(); - } - } - break; case NEON_3R_VTST_VCEQ: if (!u) { /* VTST */ switch (size) { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(ptr1); tcg_temp_free_ptr(ptr2); break; + + case NEON_2RM_VMVN: + tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size); + break; + case NEON_2RM_VNEG: + tcg_gen_gvec_neg(size, rd_ofs, rm_ofs, vec_size, vec_size); + break; + default: elementwise: for (pass = 0; pass < (q ? 4 : 2); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_2RM_VCNT: gen_helper_neon_cnt_u8(tmp, tmp); break; - case NEON_2RM_VMVN: - tcg_gen_not_i32(tmp, tmp); - break; case NEON_2RM_VQABS: switch (size) { case 0: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: abort(); } break; - case NEON_2RM_VNEG: - tmp2 = tcg_const_i32(0); - gen_neon_rsb(size, tmp, tmp2); - tcg_temp_free_i32(tmp2); - break; case NEON_2RM_VCGT0_F: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) vec_size, vec_size); } return 0; + + case NEON_3R_VMUL: /* VMUL */ + if (u) { + /* Polynomial case allows only P8 and is handled below. */ + if (size != 0) { + return 1; + } + } else { + tcg_gen_gvec_mul(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + return 0; + } + break; } if (size == 3) { /* 64-bit element instructions. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } break; - case NEON_3R_VMUL: - if (u && (size != 0)) { - /* UNDEF on invalid size for polynomial subcase */ - return 1; - } - break; case NEON_3R_VFM_VQRDMLSH: if (!arm_dc_feature(s, ARM_FEATURE_VFP4)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; case NEON_3R_VMUL: - if (u) { /* polynomial */ - gen_helper_neon_mul_p8(tmp, tmp, tmp2); - } else { /* Integer */ - switch (size) { - case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_mul_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_mul_i32(tmp, tmp, tmp2); break; - default: abort(); - } - } + /* VMUL.P8; other cases already eliminated. */ + gen_helper_neon_mul_p8(tmp, tmp, tmp2); break; case NEON_3R_VPMAX: GEN_NEON_INTEGER_OP(pmax); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-13-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 70 +++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 22 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - /* To avoid excessive duplication of ops we implement shift - by immediate using the variable shift operations. */ if (op < 8) { /* Shift by immediate: VSHR, VSRA, VRSHR, VRSRA, VSRI, VSHL, VQSHL, VQSHLU. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } /* Right shifts are encoded as N - shift, where N is the element size in bits. */ - if (op <= 4) + if (op <= 4) { shift = shift - (1 << (size + 3)); + } + + switch (op) { + case 0: /* VSHR */ + /* Right shift comes here negative. */ + shift = -shift; + /* Shifts larger than the element size are architecturally + * valid. Unsigned results in all zeros; signed results + * in all sign bits. + */ + if (!u) { + tcg_gen_gvec_sari(size, rd_ofs, rm_ofs, + MIN(shift, (8 << size) - 1), + vec_size, vec_size); + } else if (shift >= 8 << size) { + tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0); + } else { + tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + + case 5: /* VSHL, VSLI */ + if (!u) { /* VSHL */ + /* Shifts larger than the element size are + * architecturally valid and results in zero. + */ + if (shift >= 8 << size) { + tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0); + } else { + tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + } + break; + } + if (size == 3) { count = q + 1; } else { count = q ? 4: 2; } - switch (size) { - case 0: - imm = (uint8_t) shift; - imm |= imm << 8; - imm |= imm << 16; - break; - case 1: - imm = (uint16_t) shift; - imm |= imm << 16; - break; - case 2: - case 3: - imm = shift; - break; - default: - abort(); - } + + /* To avoid excessive duplication of ops we implement shift + * by immediate using the variable shift operations. + */ + imm = dup_const(size, shift); for (pass = 0; pass < count; pass++) { if (size == 3) { neon_load_reg64(cpu_V0, rm + pass); tcg_gen_movi_i64(cpu_V1, imm); switch (op) { - case 0: /* VSHR */ case 1: /* VSRA */ if (u) gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) cpu_V0, cpu_V1); } break; + default: + g_assert_not_reached(); } if (op == 1 || op == 3) { /* Accumulate. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, imm); switch (op) { - case 0: /* VSHR */ case 1: /* VSRA */ GEN_NEON_INTEGER_OP(shl); break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 7: /* VQSHL */ GEN_NEON_INTEGER_OP_ENV(qshl); break; + default: + g_assert_not_reached(); } tcg_temp_free_i32(tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move ssra_op and usra_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-14-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 106 ---------------------------- target/arm/translate.c | 139 ++++++++++++++++++++++++++++++++++--- 3 files changed, 130 insertions(+), 117 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) extern const GVecGen3 bsl_op; extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; +extern const GVecGen2i ssra_op[4]; +extern const GVecGen2i usra_op[4]; /* * Forward to the isar_feature_* tests given a DisasContext pointer. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } } -static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_sar8i_i64(a, a, shift); - tcg_gen_vec_add8_i64(d, d, a); -} - -static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_sar16i_i64(a, a, shift); - tcg_gen_vec_add16_i64(d, d, a); -} - -static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_sari_i32(a, a, shift); - tcg_gen_add_i32(d, d, a); -} - -static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_sari_i64(a, a, shift); - tcg_gen_add_i64(d, d, a); -} - -static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - tcg_gen_sari_vec(vece, a, a, sh); - tcg_gen_add_vec(vece, d, d, a); -} - -static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_shr8i_i64(a, a, shift); - tcg_gen_vec_add8_i64(d, d, a); -} - -static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_shr16i_i64(a, a, shift); - tcg_gen_vec_add16_i64(d, d, a); -} - -static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_shri_i32(a, a, shift); - tcg_gen_add_i32(d, d, a); -} - -static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_shri_i64(a, a, shift); - tcg_gen_add_i64(d, d, a); -} - -static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - tcg_gen_shri_vec(vece, a, a, sh); - tcg_gen_add_vec(vece, d, d, a); -} - static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { uint64_t mask = dup_const(MO_8, 0xff >> shift); @@ -XXX,XX +XXX,XX @@ static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, int immh, int immb, int opcode, int rn, int rd) { - static const GVecGen2i ssra_op[4] = { - { .fni8 = gen_ssra8_i64, - .fniv = gen_ssra_vec, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_8 }, - { .fni8 = gen_ssra16_i64, - .fniv = gen_ssra_vec, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_16 }, - { .fni4 = gen_ssra32_i32, - .fniv = gen_ssra_vec, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_32 }, - { .fni8 = gen_ssra64_i64, - .fniv = gen_ssra_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_64 }, - }; - static const GVecGen2i usra_op[4] = { - { .fni8 = gen_usra8_i64, - .fniv = gen_usra_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_8, }, - { .fni8 = gen_usra16_i64, - .fniv = gen_usra_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_16, }, - { .fni4 = gen_usra32_i32, - .fniv = gen_usra_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_32, }, - { .fni8 = gen_usra64_i64, - .fniv = gen_usra_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_64, }, - }; static const GVecGen2i sri_op[4] = { { .fni8 = gen_shr8_ins_i64, .fniv = gen_shr_ins_vec, diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ const GVecGen3 bif_op = { .load_dest = true }; +static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_sar8i_i64(a, a, shift); + tcg_gen_vec_add8_i64(d, d, a); +} + +static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_sar16i_i64(a, a, shift); + tcg_gen_vec_add16_i64(d, d, a); +} + +static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_sari_i32(a, a, shift); + tcg_gen_add_i32(d, d, a); +} + +static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_sari_i64(a, a, shift); + tcg_gen_add_i64(d, d, a); +} + +static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + tcg_gen_sari_vec(vece, a, a, sh); + tcg_gen_add_vec(vece, d, d, a); +} + +const GVecGen2i ssra_op[4] = { + { .fni8 = gen_ssra8_i64, + .fniv = gen_ssra_vec, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_8 }, + { .fni8 = gen_ssra16_i64, + .fniv = gen_ssra_vec, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_16 }, + { .fni4 = gen_ssra32_i32, + .fniv = gen_ssra_vec, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_32 }, + { .fni8 = gen_ssra64_i64, + .fniv = gen_ssra_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_64 }, +}; + +static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_shr8i_i64(a, a, shift); + tcg_gen_vec_add8_i64(d, d, a); +} + +static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_shr16i_i64(a, a, shift); + tcg_gen_vec_add16_i64(d, d, a); +} + +static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_shri_i32(a, a, shift); + tcg_gen_add_i32(d, d, a); +} + +static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_shri_i64(a, a, shift); + tcg_gen_add_i64(d, d, a); +} + +static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + tcg_gen_shri_vec(vece, a, a, sh); + tcg_gen_add_vec(vece, d, d, a); +} + +const GVecGen2i usra_op[4] = { + { .fni8 = gen_usra8_i64, + .fniv = gen_usra_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_8, }, + { .fni8 = gen_usra16_i64, + .fniv = gen_usra_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_16, }, + { .fni4 = gen_usra32_i32, + .fniv = gen_usra_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_32, }, + { .fni8 = gen_usra64_i64, + .fniv = gen_usra_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_64, }, +}; /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case 1: /* VSRA */ + /* Right shift comes here negative. */ + shift = -shift; + /* Shifts larger than the element size are architecturally + * valid. Unsigned results in all zeros; signed results + * in all sign bits. + */ + if (!u) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, + MIN(shift, (8 << size) - 1), + &ssra_op[size]); + } else if (shift >= 8 << size) { + /* rd += 0 */ + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, + shift, &usra_op[size]); + } + return 0; + case 5: /* VSHL, VSLI */ if (!u) { /* VSHL */ /* Shifts larger than the element size are @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_load_reg64(cpu_V0, rm + pass); tcg_gen_movi_i64(cpu_V1, imm); switch (op) { - case 1: /* VSRA */ - if (u) - gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1); - else - gen_helper_neon_shl_s64(cpu_V0, cpu_V0, cpu_V1); - break; case 2: /* VRSHR */ case 3: /* VRSRA */ if (u) @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: g_assert_not_reached(); } - if (op == 1 || op == 3) { + if (op == 3) { /* Accumulate. */ neon_load_reg64(cpu_V1, rd + pass); tcg_gen_add_i64(cpu_V0, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, imm); switch (op) { - case 1: /* VSRA */ - GEN_NEON_INTEGER_OP(shl); - break; case 2: /* VRSHR */ case 3: /* VRSRA */ GEN_NEON_INTEGER_OP(rshl); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } tcg_temp_free_i32(tmp2); - if (op == 1 || op == 3) { + if (op == 3) { /* Accumulate. */ tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move shi_op and sli_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-15-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 152 +---------------------- target/arm/translate.c | 244 ++++++++++++++++++++++++++----------- 3 files changed, 179 insertions(+), 219 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; +extern const GVecGen2i sri_op[4]; +extern const GVecGen2i sli_op[4]; /* * Forward to the isar_feature_* tests given a DisasContext pointer. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } } -static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_8, 0xff >> shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_16, 0xffff >> shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_shri_i32(a, a, shift); - tcg_gen_deposit_i32(d, d, a, 0, 32 - shift); -} - -static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_shri_i64(a, a, shift); - tcg_gen_deposit_i64(d, d, a, 0, 64 - shift); -} - -static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - uint64_t mask = (2ull << ((8 << vece) - 1)) - 1; - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); - - tcg_gen_dupi_vec(vece, m, mask ^ (mask >> sh)); - tcg_gen_shri_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); - - tcg_temp_free_vec(t); - tcg_temp_free_vec(m); -} - /* SSHR[RA]/USHR[RA] - Vector shift right (optional rounding/accumulate) */ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, int immh, int immb, int opcode, int rn, int rd) { - static const GVecGen2i sri_op[4] = { - { .fni8 = gen_shr8_ins_i64, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_8 }, - { .fni8 = gen_shr16_ins_i64, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_16 }, - { .fni4 = gen_shr32_ins_i32, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_32 }, - { .fni8 = gen_shr64_ins_i64, - .fniv = gen_shr_ins_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_64 }, - }; - int size = 32 - clz32(immh) - 1; int immhb = immh << 3 | immb; int shift = 2 * (8 << size) - immhb; @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, clear_vec_high(s, is_q, rd); } -static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_8, 0xff << shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shli_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_16, 0xffff << shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shli_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_deposit_i32(d, d, a, shift, 32 - shift); -} - -static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_deposit_i64(d, d, a, shift, 64 - shift); -} - -static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - uint64_t mask = (1ull << sh) - 1; - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); - - tcg_gen_dupi_vec(vece, m, mask); - tcg_gen_shli_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); - - tcg_temp_free_vec(t); - tcg_temp_free_vec(m); -} - /* SHL/SLI - Vector shift left */ static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert, int immh, int immb, int opcode, int rn, int rd) { - static const GVecGen2i shi_op[4] = { - { .fni8 = gen_shl8_ins_i64, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_8 }, - { .fni8 = gen_shl16_ins_i64, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_shl32_ins_i32, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_shl64_ins_i64, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_64 }, - }; int size = 32 - clz32(immh) - 1; int immhb = immh << 3 | immb; int shift = immhb - (8 << size); @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert, } if (insert) { - gen_gvec_op2i(s, is_q, rd, rn, shift, &shi_op[size]); + gen_gvec_op2i(s, is_q, rd, rn, shift, &sli_op[size]); } else { gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shli, size); } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ const GVecGen2i usra_op[4] = { .vece = MO_64, }, }; +static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_8, 0xff >> shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_16, 0xffff >> shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_shri_i32(a, a, shift); + tcg_gen_deposit_i32(d, d, a, 0, 32 - shift); +} + +static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_shri_i64(a, a, shift); + tcg_gen_deposit_i64(d, d, a, 0, 64 - shift); +} + +static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + if (sh == 0) { + tcg_gen_mov_vec(d, a); + } else { + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); + + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh)); + tcg_gen_shri_vec(vece, t, a, sh); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(m); + } +} + +const GVecGen2i sri_op[4] = { + { .fni8 = gen_shr8_ins_i64, + .fniv = gen_shr_ins_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_8 }, + { .fni8 = gen_shr16_ins_i64, + .fniv = gen_shr_ins_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_16 }, + { .fni4 = gen_shr32_ins_i32, + .fniv = gen_shr_ins_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_32 }, + { .fni8 = gen_shr64_ins_i64, + .fniv = gen_shr_ins_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_64 }, +}; + +static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_8, 0xff << shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shli_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_16, 0xffff << shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shli_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_deposit_i32(d, d, a, shift, 32 - shift); +} + +static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_deposit_i64(d, d, a, shift, 64 - shift); +} + +static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + if (sh == 0) { + tcg_gen_mov_vec(d, a); + } else { + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); + + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh)); + tcg_gen_shli_vec(vece, t, a, sh); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(m); + } +} + +const GVecGen2i sli_op[4] = { + { .fni8 = gen_shl8_ins_i64, + .fniv = gen_shl_ins_vec, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_8 }, + { .fni8 = gen_shl16_ins_i64, + .fniv = gen_shl_ins_vec, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_16 }, + { .fni4 = gen_shl32_ins_i32, + .fniv = gen_shl_ins_vec, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_32 }, + { .fni8 = gen_shl64_ins_i64, + .fniv = gen_shl_ins_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int pairwise; int u; int vec_size; - uint32_t imm, mask; + uint32_t imm; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; TCGv_ptr ptr1, ptr2, ptr3; TCGv_i64 tmp64; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case 4: /* VSRI */ + if (!u) { + return 1; + } + /* Right shift comes here negative. */ + shift = -shift; + /* Shift out of range leaves destination unchanged. */ + if (shift < 8 << size) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, + shift, &sri_op[size]); + } + return 0; + case 5: /* VSHL, VSLI */ - if (!u) { /* VSHL */ + if (u) { /* VSLI */ + /* Shift out of range leaves destination unchanged. */ + if (shift < 8 << size) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, + vec_size, shift, &sli_op[size]); + } + } else { /* VSHL */ /* Shifts larger than the element size are * architecturally valid and results in zero. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, vec_size, vec_size); } - return 0; } - break; + return 0; } if (size == 3) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) else gen_helper_neon_rshl_s64(cpu_V0, cpu_V0, cpu_V1); break; - case 4: /* VSRI */ - case 5: /* VSHL, VSLI */ - gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1); - break; case 6: /* VQSHLU */ gen_helper_neon_qshlu_s64(cpu_V0, cpu_env, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* Accumulate. */ neon_load_reg64(cpu_V1, rd + pass); tcg_gen_add_i64(cpu_V0, cpu_V0, cpu_V1); - } else if (op == 4 || (op == 5 && u)) { - /* Insert */ - neon_load_reg64(cpu_V1, rd + pass); - uint64_t mask; - if (shift < -63 || shift > 63) { - mask = 0; - } else { - if (op == 4) { - mask = 0xffffffffffffffffull >> -shift; - } else { - mask = 0xffffffffffffffffull << shift; - } - } - tcg_gen_andi_i64(cpu_V1, cpu_V1, ~mask); - tcg_gen_or_i64(cpu_V0, cpu_V0, cpu_V1); } neon_store_reg64(cpu_V0, rd + pass); } else { /* size < 3 */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 3: /* VRSRA */ GEN_NEON_INTEGER_OP(rshl); break; - case 4: /* VSRI */ - case 5: /* VSHL, VSLI */ - switch (size) { - case 0: gen_helper_neon_shl_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_shl_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_shl_u32(tmp, tmp, tmp2); break; - default: abort(); - } - break; case 6: /* VQSHLU */ switch (size) { case 0: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); tcg_temp_free_i32(tmp2); - } else if (op == 4 || (op == 5 && u)) { - /* Insert */ - switch (size) { - case 0: - if (op == 4) - mask = 0xff >> -shift; - else - mask = (uint8_t)(0xff << shift); - mask |= mask << 8; - mask |= mask << 16; - break; - case 1: - if (op == 4) - mask = 0xffff >> -shift; - else - mask = (uint16_t)(0xffff << shift); - mask |= mask << 16; - break; - case 2: - if (shift < -31 || shift > 31) { - mask = 0; - } else { - if (op == 4) - mask = 0xffffffffu >> -shift; - else - mask = 0xffffffffu << shift; - } - break; - default: - abort(); - } - tmp2 = neon_load_reg(rd, pass); - tcg_gen_andi_i32(tmp, tmp, mask); - tcg_gen_andi_i32(tmp2, tmp2, ~mask); - tcg_gen_or_i32(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); } neon_store_reg(rd, pass, tmp); } -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move mla_op and mls_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-16-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 106 ----------------------------- target/arm/translate.c | 134 ++++++++++++++++++++++++++++++++----- 3 files changed, 120 insertions(+), 122 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) extern const GVecGen3 bsl_op; extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; +extern const GVecGen3 mla_op[4]; +extern const GVecGen3 mls_op[4]; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) } } -static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u8(a, a, b); - gen_helper_neon_add_u8(d, d, a); -} - -static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u16(a, a, b); - gen_helper_neon_add_u16(d, d, a); -} - -static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_mul_i32(a, a, b); - tcg_gen_add_i32(d, d, a); -} - -static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_mul_i64(a, a, b); - tcg_gen_add_i64(d, d, a); -} - -static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_mul_vec(vece, a, a, b); - tcg_gen_add_vec(vece, d, d, a); -} - -static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u8(a, a, b); - gen_helper_neon_sub_u8(d, d, a); -} - -static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u16(a, a, b); - gen_helper_neon_sub_u16(d, d, a); -} - -static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_mul_i32(a, a, b); - tcg_gen_sub_i32(d, d, a); -} - -static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_mul_i64(a, a, b); - tcg_gen_sub_i64(d, d, a); -} - -static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_mul_vec(vece, a, a, b); - tcg_gen_sub_vec(vece, d, d, a); -} - /* Integer op subgroup of C3.6.16. */ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; - static const GVecGen3 mla_op[4] = { - { .fni4 = gen_mla8_i32, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_8 }, - { .fni4 = gen_mla16_i32, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_mla32_i32, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_mla64_i64, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_64 }, - }; - static const GVecGen3 mls_op[4] = { - { .fni4 = gen_mls8_i32, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_8 }, - { .fni4 = gen_mls16_i32, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_mls32_i32, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_mls64_i64, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_64 }, - }; int is_q = extract32(insn, 30, 1); int u = extract32(insn, 29, 1); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_neon_narrow_op(int op, int u, int size, #define NEON_3R_VABA 15 #define NEON_3R_VADD_VSUB 16 #define NEON_3R_VTST_VCEQ 17 -#define NEON_3R_VML 18 /* VMLA, VMLAL, VMLS, VMLSL */ +#define NEON_3R_VML 18 /* VMLA, VMLS */ #define NEON_3R_VMUL 19 #define NEON_3R_VPMAX 20 #define NEON_3R_VPMIN 21 @@ -XXX,XX +XXX,XX @@ const GVecGen2i sli_op[4] = { .vece = MO_64 }, }; +static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u8(a, a, b); + gen_helper_neon_add_u8(d, d, a); +} + +static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u8(a, a, b); + gen_helper_neon_sub_u8(d, d, a); +} + +static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u16(a, a, b); + gen_helper_neon_add_u16(d, d, a); +} + +static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u16(a, a, b); + gen_helper_neon_sub_u16(d, d, a); +} + +static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_mul_i32(a, a, b); + tcg_gen_add_i32(d, d, a); +} + +static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_mul_i32(a, a, b); + tcg_gen_sub_i32(d, d, a); +} + +static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_mul_i64(a, a, b); + tcg_gen_add_i64(d, d, a); +} + +static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_mul_i64(a, a, b); + tcg_gen_sub_i64(d, d, a); +} + +static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_mul_vec(vece, a, a, b); + tcg_gen_add_vec(vece, d, d, a); +} + +static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_mul_vec(vece, a, a, b); + tcg_gen_sub_vec(vece, d, d, a); +} + +/* Note that while NEON does not support VMLA and VMLS as 64-bit ops, + * these tables are shared with AArch64 which does support them. + */ +const GVecGen3 mla_op[4] = { + { .fni4 = gen_mla8_i32, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_8 }, + { .fni4 = gen_mla16_i32, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_mla32_i32, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_mla64_i64, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .vece = MO_64 }, +}; + +const GVecGen3 mls_op[4] = { + { .fni4 = gen_mls8_i32, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_8 }, + { .fni4 = gen_mls16_i32, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_mls32_i32, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_mls64_i64, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 0; } break; + + case NEON_3R_VML: /* VMLA, VMLS */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, + u ? &mls_op[size] : &mla_op[size]); + return 0; } + if (size == 3) { /* 64-bit element instructions. */ for (pass = 0; pass < (q ? 2 : 1); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } } break; - case NEON_3R_VML: /* VMLA, VMLAL, VMLS,VMLSL */ - switch (size) { - case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_mul_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_mul_i32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - tmp2 = neon_load_reg(rd, pass); - if (u) { /* VMLS */ - gen_neon_rsb(size, tmp, tmp2); - } else { /* VMLA */ - gen_neon_add(size, tmp, tmp2); - } - break; case NEON_3R_VMUL: /* VMUL.P8; other cases already eliminated. */ gen_helper_neon_mul_p8(tmp, tmp, tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move cmtst_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-17-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 38 ------------------ target/arm/translate.c | 81 +++++++++++++++++++++++++++----------- 3 files changed, 60 insertions(+), 61 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; +extern const GVecGen3 cmtst_op[4]; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; extern const GVecGen2i sli_op[4]; +void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); /* * Forward to the isar_feature_* tests given a DisasContext pointer. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* CMTST : test is "if (X & Y != 0)". */ -static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_and_i32(d, a, b); - tcg_gen_setcondi_i32(TCG_COND_NE, d, d, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_and_i64(d, a, b); - tcg_gen_setcondi_i64(TCG_COND_NE, d, d, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_and_vec(vece, d, a, b); - tcg_gen_dupi_vec(vece, a, 0); - tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); -} - static void handle_3same_64(DisasContext *s, int opcode, bool u, TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 tcg_rm) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) /* Integer op subgroup of C3.6.16. */ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) { - static const GVecGen3 cmtst_op[4] = { - { .fni4 = gen_helper_neon_tst_u8, - .fniv = gen_cmtst_vec, - .vece = MO_8 }, - { .fni4 = gen_helper_neon_tst_u16, - .fniv = gen_cmtst_vec, - .vece = MO_16 }, - { .fni4 = gen_cmtst_i32, - .fniv = gen_cmtst_vec, - .vece = MO_32 }, - { .fni8 = gen_cmtst_i64, - .fniv = gen_cmtst_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, - }; - int is_q = extract32(insn, 30, 1); int u = extract32(insn, 29, 1); int size = extract32(insn, 22, 2); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ const GVecGen3 mls_op[4] = { .vece = MO_64 }, }; +/* CMTST : test is "if (X & Y != 0)". */ +static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_and_i32(d, a, b); + tcg_gen_setcondi_i32(TCG_COND_NE, d, d, 0); + tcg_gen_neg_i32(d, d); +} + +void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_and_i64(d, a, b); + tcg_gen_setcondi_i64(TCG_COND_NE, d, d, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_and_vec(vece, d, a, b); + tcg_gen_dupi_vec(vece, a, 0); + tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); +} + +const GVecGen3 cmtst_op[4] = { + { .fni4 = gen_helper_neon_tst_u8, + .fniv = gen_cmtst_vec, + .vece = MO_8 }, + { .fni4 = gen_helper_neon_tst_u16, + .fniv = gen_cmtst_vec, + .vece = MO_16 }, + { .fni4 = gen_cmtst_i32, + .fniv = gen_cmtst_vec, + .vece = MO_32 }, + { .fni8 = gen_cmtst_i64, + .fniv = gen_cmtst_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, u ? &mls_op[size] : &mla_op[size]); return 0; + + case NEON_3R_VTST_VCEQ: + if (u) { /* VCEQ */ + tcg_gen_gvec_cmp(TCG_COND_EQ, size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { /* VTST */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &cmtst_op[size]); + } + return 0; + + case NEON_3R_VCGT: + tcg_gen_gvec_cmp(u ? TCG_COND_GTU : TCG_COND_GT, size, + rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); + return 0; + + case NEON_3R_VCGE: + tcg_gen_gvec_cmp(u ? TCG_COND_GEU : TCG_COND_GE, size, + rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); + return 0; } if (size == 3) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQSUB: GEN_NEON_INTEGER_OP_ENV(qsub); break; - case NEON_3R_VCGT: - GEN_NEON_INTEGER_OP(cgt); - break; - case NEON_3R_VCGE: - GEN_NEON_INTEGER_OP(cge); - break; case NEON_3R_VSHL: GEN_NEON_INTEGER_OP(shl); break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); break; - case NEON_3R_VTST_VCEQ: - if (!u) { /* VTST */ - switch (size) { - case 0: gen_helper_neon_tst_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_tst_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_tst_u32(tmp, tmp, tmp2); break; - default: abort(); - } - } else { /* VCEQ */ - switch (size) { - case 0: gen_helper_neon_ceq_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_ceq_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_ceq_u32(tmp, tmp, tmp2); break; - default: abort(); - } - } - break; case NEON_3R_VMUL: /* VMUL.P8; other cases already eliminated. */ gen_helper_neon_mul_p8(tmp, tmp, tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-18-richard.henderson@linaro.org [PMM: added parens in ?: expression] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 81 ++++++++++++++---------------------------- 1 file changed, 26 insertions(+), 55 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_vfp_msr(TCGv_i32 tmp) tcg_temp_free_i32(tmp); } -static void gen_neon_dup_u8(TCGv_i32 var, int shift) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - if (shift) - tcg_gen_shri_i32(var, var, shift); - tcg_gen_ext8u_i32(var, var); - tcg_gen_shli_i32(tmp, var, 8); - tcg_gen_or_i32(var, var, tmp); - tcg_gen_shli_i32(tmp, var, 16); - tcg_gen_or_i32(var, var, tmp); - tcg_temp_free_i32(tmp); -} - static void gen_neon_dup_low16(TCGv_i32 var) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) tcg_temp_free_i32(tmp); } -static TCGv_i32 gen_load_and_replicate(DisasContext *s, TCGv_i32 addr, int size) -{ - /* Load a single Neon element and replicate into a 32 bit TCG reg */ - TCGv_i32 tmp = tcg_temp_new_i32(); - switch (size) { - case 0: - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - gen_neon_dup_u8(tmp, 0); - break; - case 1: - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - gen_neon_dup_low16(tmp); - break; - case 2: - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - break; - default: /* Avoid compiler warnings. */ - abort(); - } - return tmp; -} - static int handle_vsel(uint32_t insn, uint32_t rd, uint32_t rn, uint32_t rm, uint32_t dp) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int load; int shift; int n; + int vec_size; TCGv_i32 addr; TCGv_i32 tmp; TCGv_i32 tmp2; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) } addr = tcg_temp_new_i32(); load_reg_var(s, addr, rn); - if (nregs == 1) { - /* VLD1 to all lanes: bit 5 indicates how many Dregs to write */ - tmp = gen_load_and_replicate(s, addr, size); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 0)); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 1)); - if (insn & (1 << 5)) { - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd + 1, 0)); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd + 1, 1)); - } - tcg_temp_free_i32(tmp); - } else { - /* VLD2/3/4 to all lanes: bit 5 indicates register stride */ - stride = (insn & (1 << 5)) ? 2 : 1; - for (reg = 0; reg < nregs; reg++) { - tmp = gen_load_and_replicate(s, addr, size); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 0)); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 1)); - tcg_temp_free_i32(tmp); - tcg_gen_addi_i32(addr, addr, 1 << size); - rd += stride; + + /* VLD1 to all lanes: bit 5 indicates how many Dregs to write. + * VLD2/3/4 to all lanes: bit 5 indicates register stride. + */ + stride = (insn & (1 << 5)) ? 2 : 1; + vec_size = nregs == 1 ? stride * 8 : 8; + + tmp = tcg_temp_new_i32(); + for (reg = 0; reg < nregs; reg++) { + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); + if ((rd & 1) && vec_size == 16) { + /* We cannot write 16 bytes at once because the + * destination is unaligned. + */ + tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), + 8, 8, tmp); + tcg_gen_gvec_mov(0, neon_reg_offset(rd + 1, 0), + neon_reg_offset(rd, 0), 8, 8); + } else { + tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), + vec_size, vec_size, tmp); } + tcg_gen_addi_i32(addr, addr, 1 << size); + rd += stride; } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(addr); stride = (1 << size) * nregs; } else { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Instead of shifts and masks, use direct loads and stores from the neon register file. Mirror the iteration structure of the ARM pseudocode more closely. Correct the parameters of the VLD2 A2 insn. Note that this includes a bugfix for handling of the insn "VLD2 (multiple 2-element structures)" -- we were using an incorrect stride value. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-19-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 170 ++++++++++++++++++----------------------- 1 file changed, 74 insertions(+), 96 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 neon_load_reg(int reg, int pass) return tmp; } +static void neon_load_element64(TCGv_i64 var, int reg, int ele, TCGMemOp mop) +{ + long offset = neon_element_offset(reg, ele, mop & MO_SIZE); + + switch (mop) { + case MO_UB: + tcg_gen_ld8u_i64(var, cpu_env, offset); + break; + case MO_UW: + tcg_gen_ld16u_i64(var, cpu_env, offset); + break; + case MO_UL: + tcg_gen_ld32u_i64(var, cpu_env, offset); + break; + case MO_Q: + tcg_gen_ld_i64(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static void neon_store_reg(int reg, int pass, TCGv_i32 var) { tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass)); tcg_temp_free_i32(var); } +static void neon_store_element64(int reg, int ele, TCGMemOp size, TCGv_i64 var) +{ + long offset = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_8: + tcg_gen_st8_i64(var, cpu_env, offset); + break; + case MO_16: + tcg_gen_st16_i64(var, cpu_env, offset); + break; + case MO_32: + tcg_gen_st32_i64(var, cpu_env, offset); + break; + case MO_64: + tcg_gen_st_i64(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static inline void neon_load_reg64(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); @@ -XXX,XX +XXX,XX @@ static struct { int interleave; int spacing; } const neon_ls_element_type[11] = { - {4, 4, 1}, - {4, 4, 2}, + {1, 4, 1}, + {1, 4, 2}, {4, 1, 1}, - {4, 2, 1}, - {3, 3, 1}, - {3, 3, 2}, + {2, 2, 2}, + {1, 3, 1}, + {1, 3, 2}, {3, 1, 1}, {1, 1, 1}, - {2, 2, 1}, - {2, 2, 2}, + {1, 2, 1}, + {1, 2, 2}, {2, 1, 1} }; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int shift; int n; int vec_size; + int mmu_idx; + TCGMemOp endian; TCGv_i32 addr; TCGv_i32 tmp; TCGv_i32 tmp2; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) rn = (insn >> 16) & 0xf; rm = insn & 0xf; load = (insn & (1 << 21)) != 0; + endian = s->be_data; + mmu_idx = get_mem_index(s); if ((insn & (1 << 23)) == 0) { /* Load store all elements. */ op = (insn >> 8) & 0xf; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) nregs = neon_ls_element_type[op].nregs; interleave = neon_ls_element_type[op].interleave; spacing = neon_ls_element_type[op].spacing; - if (size == 3 && (interleave | spacing) != 1) + if (size == 3 && (interleave | spacing) != 1) { return 1; + } + tmp64 = tcg_temp_new_i64(); addr = tcg_temp_new_i32(); + tmp2 = tcg_const_i32(1 << size); load_reg_var(s, addr, rn); - stride = (1 << size) * interleave; for (reg = 0; reg < nregs; reg++) { - if (interleave > 2 || (interleave == 2 && nregs == 2)) { - load_reg_var(s, addr, rn); - tcg_gen_addi_i32(addr, addr, (1 << size) * reg); - } else if (interleave == 2 && nregs == 4 && reg == 2) { - load_reg_var(s, addr, rn); - tcg_gen_addi_i32(addr, addr, 1 << size); - } - if (size == 3) { - tmp64 = tcg_temp_new_i64(); - if (load) { - gen_aa32_ld64(s, tmp64, addr, get_mem_index(s)); - neon_store_reg64(tmp64, rd); - } else { - neon_load_reg64(tmp64, rd); - gen_aa32_st64(s, tmp64, addr, get_mem_index(s)); - } - tcg_temp_free_i64(tmp64); - tcg_gen_addi_i32(addr, addr, stride); - } else { - for (pass = 0; pass < 2; pass++) { - if (size == 2) { - if (load) { - tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg(rd, pass, tmp); - } else { - tmp = neon_load_reg(rd, pass); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp); - } - tcg_gen_addi_i32(addr, addr, stride); - } else if (size == 1) { - if (load) { - tmp = tcg_temp_new_i32(); - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - tcg_gen_addi_i32(addr, addr, stride); - tmp2 = tcg_temp_new_i32(); - gen_aa32_ld16u(s, tmp2, addr, get_mem_index(s)); - tcg_gen_addi_i32(addr, addr, stride); - tcg_gen_shli_i32(tmp2, tmp2, 16); - tcg_gen_or_i32(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); - neon_store_reg(rd, pass, tmp); - } else { - tmp = neon_load_reg(rd, pass); - tmp2 = tcg_temp_new_i32(); - tcg_gen_shri_i32(tmp2, tmp, 16); - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp); - tcg_gen_addi_i32(addr, addr, stride); - gen_aa32_st16(s, tmp2, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp2); - tcg_gen_addi_i32(addr, addr, stride); - } - } else /* size == 0 */ { - if (load) { - tmp2 = NULL; - for (n = 0; n < 4; n++) { - tmp = tcg_temp_new_i32(); - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - tcg_gen_addi_i32(addr, addr, stride); - if (n == 0) { - tmp2 = tmp; - } else { - tcg_gen_shli_i32(tmp, tmp, n * 8); - tcg_gen_or_i32(tmp2, tmp2, tmp); - tcg_temp_free_i32(tmp); - } - } - neon_store_reg(rd, pass, tmp2); - } else { - tmp2 = neon_load_reg(rd, pass); - for (n = 0; n < 4; n++) { - tmp = tcg_temp_new_i32(); - if (n == 0) { - tcg_gen_mov_i32(tmp, tmp2); - } else { - tcg_gen_shri_i32(tmp, tmp2, n * 8); - } - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp); - tcg_gen_addi_i32(addr, addr, stride); - } - tcg_temp_free_i32(tmp2); - } + for (n = 0; n < 8 >> size; n++) { + int xs; + for (xs = 0; xs < interleave; xs++) { + int tt = rd + reg + spacing * xs; + + if (load) { + gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); + neon_store_element64(tt, n, size, tmp64); + } else { + neon_load_element64(tmp64, tt, n, size); + gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); } + tcg_gen_add_i32(addr, addr, tmp2); } } - rd += spacing; } tcg_temp_free_i32(addr); - stride = nregs * 8; + tcg_temp_free_i32(tmp2); + tcg_temp_free_i64(tmp64); + stride = nregs * interleave * 8; } else { size = (insn >> 10) & 3; if (size == 3) { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> For a sequence of loads or stores from a single register, little-endian operations can be promoted to an 8-byte op. This can reduce the number of operations by a factor of 8. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-20-richard.henderson@linaro.org Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) if (size == 3 && (interleave | spacing) != 1) { return 1; } + /* For our purposes, bytes are always little-endian. */ + if (size == 0) { + endian = MO_LE; + } + /* Consecutive little-endian elements from a single register + * can be promoted to a larger little-endian operation. + */ + if (interleave == 1 && endian == MO_LE) { + size = 3; + } tmp64 = tcg_temp_new_i64(); addr = tcg_temp_new_i32(); tmp2 = tcg_const_i32(1 << size); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Instead of shifts and masks, use direct loads and stores from the neon register file. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-21-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 92 +++++++++++++++++++++++------------------- 1 file changed, 50 insertions(+), 42 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 neon_load_reg(int reg, int pass) return tmp; } +static void neon_load_element(TCGv_i32 var, int reg, int ele, TCGMemOp mop) +{ + long offset = neon_element_offset(reg, ele, mop & MO_SIZE); + + switch (mop) { + case MO_UB: + tcg_gen_ld8u_i32(var, cpu_env, offset); + break; + case MO_UW: + tcg_gen_ld16u_i32(var, cpu_env, offset); + break; + case MO_UL: + tcg_gen_ld_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static void neon_load_element64(TCGv_i64 var, int reg, int ele, TCGMemOp mop) { long offset = neon_element_offset(reg, ele, mop & MO_SIZE); @@ -XXX,XX +XXX,XX @@ static void neon_store_reg(int reg, int pass, TCGv_i32 var) tcg_temp_free_i32(var); } +static void neon_store_element(int reg, int ele, TCGMemOp size, TCGv_i32 var) +{ + long offset = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_8: + tcg_gen_st8_i32(var, cpu_env, offset); + break; + case MO_16: + tcg_gen_st16_i32(var, cpu_env, offset); + break; + case MO_32: + tcg_gen_st_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static void neon_store_element64(int reg, int ele, TCGMemOp size, TCGv_i64 var) { long offset = neon_element_offset(reg, ele, size); @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int stride; int size; int reg; - int pass; int load; - int shift; int n; int vec_size; int mmu_idx; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) } else { /* Single element. */ int idx = (insn >> 4) & 0xf; - pass = (insn >> 7) & 1; + int reg_idx; switch (size) { case 0: - shift = ((insn >> 5) & 3) * 8; + reg_idx = (insn >> 5) & 7; stride = 1; break; case 1: - shift = ((insn >> 6) & 1) * 16; + reg_idx = (insn >> 6) & 3; stride = (insn & (1 << 5)) ? 2 : 1; break; case 2: - shift = 0; + reg_idx = (insn >> 7) & 1; stride = (insn & (1 << 6)) ? 2 : 1; break; default: @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) */ return 1; } + tmp = tcg_temp_new_i32(); addr = tcg_temp_new_i32(); load_reg_var(s, addr, rn); for (reg = 0; reg < nregs; reg++) { if (load) { - tmp = tcg_temp_new_i32(); - switch (size) { - case 0: - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - break; - case 1: - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - break; - case 2: - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - break; - default: /* Avoid compiler warnings. */ - abort(); - } - if (size != 2) { - tmp2 = neon_load_reg(rd, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, - shift, size ? 16 : 8); - tcg_temp_free_i32(tmp2); - } - neon_store_reg(rd, pass, tmp); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); + neon_store_element(rd, reg_idx, size, tmp); } else { /* Store */ - tmp = neon_load_reg(rd, pass); - if (shift) - tcg_gen_shri_i32(tmp, tmp, shift); - switch (size) { - case 0: - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); - break; - case 1: - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); - break; - case 2: - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); - break; - } - tcg_temp_free_i32(tmp); + neon_load_element(tmp, rd, reg_idx, size); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); } rd += stride; tcg_gen_addi_i32(addr, addr, 1 << size); } tcg_temp_free_i32(addr); + tcg_temp_free_i32(tmp); stride = nregs * (1 << size); } } -- 2.19.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Announce the availability of the various priority queues. This fixes an issue where guest kernels would miss to configure secondary queues due to inproper feature bits. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20181017213932.19973-2-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) int i; CadenceGEMState *s = CADENCE_GEM(d); const uint8_t *a; + uint32_t queues_mask = 0; DB_PRINT("\n"); @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[GEM_DESCONF] = 0x02500111; s->regs[GEM_DESCONF2] = 0x2ab13fff; s->regs[GEM_DESCONF5] = 0x002f2045; - s->regs[GEM_DESCONF6] = 0x00000200; + s->regs[GEM_DESCONF6] = 0x0; + + if (s->num_priority_queues > 1) { + queues_mask = MAKE_64BIT_MASK(1, s->num_priority_queues - 1); + s->regs[GEM_DESCONF6] |= queues_mask; + } /* Set MAC address */ a = &s->conf.macaddr.a[0]; -- 2.19.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Announce 64bit addressing support. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20181017213932.19973-3-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ #define GEM_DESCONF4 (0x0000028C/4) #define GEM_DESCONF5 (0x00000290/4) #define GEM_DESCONF6 (0x00000294/4) +#define GEM_DESCONF6_64B_MASK (1U << 23) #define GEM_DESCONF7 (0x00000298/4) #define GEM_INT_Q1_STATUS (0x00000400 / 4) @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[GEM_DESCONF] = 0x02500111; s->regs[GEM_DESCONF2] = 0x2ab13fff; s->regs[GEM_DESCONF5] = 0x002f2045; - s->regs[GEM_DESCONF6] = 0x0; + s->regs[GEM_DESCONF6] = GEM_DESCONF6_64B_MASK; if (s->num_priority_queues > 1) { queues_mask = MAKE_64BIT_MASK(1, s->num_priority_queues - 1); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> The EL3 version of this register does not include an ASID, and so the tlb_flush performed by vmsa_ttbr_write is not needed. Reviewed-by: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181019015617.22583-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.mvbar) }, { .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, + .access = PL3_RW, .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, -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Since QEMU does not implement ASIDs, changes to the ASID must flush the tlb. However, if the ASID does not change there is no reason to flush. In testing a boot of the Ubuntu installer to the first menu, this reduces the number of flushes by 30%, or nearly 600k instances. Reviewed-by: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181019015617.22583-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void vmsa_tcr_el1_write(CPUARMState *env, const ARMCPRegInfo *ri, static void vmsa_ttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - /* 64 bit accesses to the TTBRs can change the ASID and so we - * must flush the TLB. - */ - if (cpreg_field_is_64bit(ri)) { + /* If the ASID changes (with a 64-bit write), we must flush the TLB. */ + if (cpreg_field_is_64bit(ri) && + extract64(raw_read(env, ri) ^ value, 48, 16) != 0) { ARMCPU *cpu = arm_env_get_cpu(env); - tlb_flush(CPU(cpu)); } raw_write(env, ri, value); -- 2.19.1