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target-arm queue: * more preparatory work for v8M support * convert some omap devices away from old_mmio * remove out of date ARM ARM section references in comments * add the Smartfusion2 board ---------------------------------------------------------------- Peter Maydell (26):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for v8M nvic: Make SHCSR banked for v8M nvic: Support banked exceptions in acknowledge and complete target/arm: Remove out of date ARM ARM section references in A64 decoder hw/arm/palm.c: Don't use old_mmio for static_ops hw/gpio/omap_gpio.c: Don't use old_mmio hw/timer/omap_synctimer.c: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 First arm pullreq of the cycle; this is mostly my softfloat NaN handling series. (Lots more in my to-review queue, but I don't like pullreqs growing too close to a hundred patches at a time :-)) thanks -- PMM The following changes since commit 97f2796a3736ed37a1b85dc1c76a6c45b829dd17: Open 10.0 development tree (2024-12-10 17:41:17 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20241211 for you to fetch changes up to 1abe28d519239eea5cf9620bb13149423e5665f8: MAINTAINERS: Add correct email address for Vikram Garhwal (2024-12-11 15:31:09 +0000) ---------------------------------------------------------------- target-arm queue: * hw/net/lan9118: Extract PHY model, reuse with imx_fec, fix bugs * fpu: Make muladd NaN handling runtime-selected, not compile-time * fpu: Make default NaN pattern runtime-selected, not compile-time * fpu: Minor NaN-related cleanups * MAINTAINERS: email address updates ---------------------------------------------------------------- Bernhard Beschow (5): hw/net/lan9118: Extract lan9118_phy hw/net/lan9118_phy: Reuse in imx_fec and consolidate implementations hw/net/lan9118_phy: Fix off-by-one error in MII_ANLPAR register hw/net/lan9118_phy: Reuse MII constants hw/net/lan9118_phy: Add missing 100 mbps full duplex advertisement Leif Lindholm (1): MAINTAINERS: update email address for Leif Lindholm Peter Maydell (54): fpu: handle raising Invalid for infzero in pick_nan_muladd fpu: Check for default_nan_mode before calling pickNaNMulAdd softfloat: Allow runtime choice of inf * 0 + NaN result tests/fp: Explicitly set inf-zero-nan rule target/arm: Set FloatInfZeroNaNRule explicitly target/s390: Set FloatInfZeroNaNRule explicitly target/ppc: Set FloatInfZeroNaNRule explicitly target/mips: Set FloatInfZeroNaNRule explicitly target/sparc: Set FloatInfZeroNaNRule explicitly target/xtensa: Set FloatInfZeroNaNRule explicitly target/x86: Set FloatInfZeroNaNRule explicitly target/loongarch: Set FloatInfZeroNaNRule explicitly target/hppa: Set FloatInfZeroNaNRule explicitly softfloat: Pass have_snan to pickNaNMulAdd softfloat: Allow runtime choice of NaN propagation for muladd tests/fp: Explicitly set 3-NaN propagation rule target/arm: Set Float3NaNPropRule explicitly target/loongarch: Set Float3NaNPropRule explicitly target/ppc: Set Float3NaNPropRule explicitly target/s390x: Set Float3NaNPropRule explicitly target/sparc: Set Float3NaNPropRule explicitly target/mips: Set Float3NaNPropRule explicitly target/xtensa: Set Float3NaNPropRule explicitly target/i386: Set Float3NaNPropRule explicitly target/hppa: Set Float3NaNPropRule explicitly fpu: Remove use_first_nan field from float_status target/m68k: Don't pass NULL float_status to floatx80_default_nan() softfloat: Create floatx80 default NaN from parts64_default_nan target/loongarch: Use normal float_status in fclass_s and fclass_d helpers target/m68k: In frem helper, initialize local float_status from env->fp_status target/m68k: Init local float_status from env fp_status in gdb get/set reg target/sparc: Initialize local scratch float_status from env->fp_status target/ppc: Use env->fp_status in helper_compute_fprf functions fpu: Allow runtime choice of default NaN value tests/fp: Set default NaN pattern explicitly target/microblaze: Set default NaN pattern explicitly target/i386: Set default NaN pattern explicitly target/hppa: Set default NaN pattern explicitly target/alpha: Set default NaN pattern explicitly target/arm: Set default NaN pattern explicitly target/loongarch: Set default NaN pattern explicitly target/m68k: Set default NaN pattern explicitly target/mips: Set default NaN pattern explicitly target/openrisc: Set default NaN pattern explicitly target/ppc: Set default NaN pattern explicitly target/sh4: Set default NaN pattern explicitly target/rx: Set default NaN pattern explicitly target/s390x: Set default NaN pattern explicitly target/sparc: Set default NaN pattern explicitly target/xtensa: Set default NaN pattern explicitly target/hexagon: Set default NaN pattern explicitly target/riscv: Set default NaN pattern explicitly target/tricore: Set default NaN pattern explicitly fpu: Remove default handling for dnan_pattern Richard Henderson (11): target/arm: Copy entire float_status in is_ebf softfloat: Inline pickNaNMulAdd softfloat: Use goto for default nan case in pick_nan_muladd softfloat: Remove which from parts_pick_nan_muladd softfloat: Pad array size in pick_nan_muladd softfloat: Move propagateFloatx80NaN to softfloat.c softfloat: Use parts_pick_nan in propagateFloatx80NaN softfloat: Inline pickNaN softfloat: Share code between parts_pick_nan cases softfloat: Sink frac_cmp in parts_pick_nan until needed softfloat: Replace WHICH with RET in parts_pick_nan Vikram Garhwal (1): MAINTAINERS: Add correct email address for Vikram Garhwal MAINTAINERS | 4 +- include/fpu/softfloat-helpers.h | 38 +++- include/fpu/softfloat-types.h | 89 +++++++- include/hw/net/imx_fec.h | 9 +- include/hw/net/lan9118_phy.h | 37 ++++ include/hw/net/mii.h | 6 + target/mips/fpu_helper.h | 20 ++ target/sparc/helper.h | 4 +- fpu/softfloat.c | 19 ++ hw/net/imx_fec.c | 146 ++------------ hw/net/lan9118.c | 137 ++----------- hw/net/lan9118_phy.c | 222 ++++++++++++++++++++ linux-user/arm/nwfpe/fpa11.c | 5 + target/alpha/cpu.c | 2 + target/arm/cpu.c | 10 + target/arm/tcg/vec_helper.c | 20 +- target/hexagon/cpu.c | 2 + target/hppa/fpu_helper.c | 12 ++ target/i386/tcg/fpu_helper.c | 12 ++ target/loongarch/tcg/fpu_helper.c | 14 +- target/m68k/cpu.c | 14 +- target/m68k/fpu_helper.c | 6 +- target/m68k/helper.c | 6 +- target/microblaze/cpu.c | 2 + target/mips/msa.c | 10 + target/openrisc/cpu.c | 2 + target/ppc/cpu_init.c | 19 ++ target/ppc/fpu_helper.c | 3 +- target/riscv/cpu.c | 2 + target/rx/cpu.c | 2 + target/s390x/cpu.c | 5 + target/sh4/cpu.c | 2 + target/sparc/cpu.c | 6 + target/sparc/fop_helper.c | 8 +- target/sparc/translate.c | 4 +- target/tricore/helper.c | 2 + target/xtensa/cpu.c | 4 + target/xtensa/fpu_helper.c | 3 +- tests/fp/fp-bench.c | 7 + tests/fp/fp-test-log2.c | 1 + tests/fp/fp-test.c | 7 + fpu/softfloat-parts.c.inc | 152 +++++++++++--- fpu/softfloat-specialize.c.inc | 412 ++------------------------------------ .mailmap | 5 +- hw/net/Kconfig | 5 + hw/net/meson.build | 1 + hw/net/trace-events | 10 +- 47 files changed, 778 insertions(+), 730 deletions(-) create mode 100644 include/hw/net/lan9118_phy.h create mode 100644 hw/net/lan9118_phy.c From: Bernhard Beschow <shentey@gmail.com> A very similar implementation of the same device exists in imx_fec. Prepare for a common implementation by extracting a device model into its own files. Some migration state has been moved into the new device model which breaks migration compatibility for the following machines: * smdkc210 * realview-* * vexpress-* * kzm * mps2-* While breaking migration ABI, fix the size of the MII registers to be 16 bit, as defined by IEEE 802.3u. Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241102125724.532843-2-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/lan9118_phy.h | 37 ++++++++ hw/net/lan9118.c | 137 +++++----------------------- hw/net/lan9118_phy.c | 169 +++++++++++++++++++++++++++++++++++ hw/net/Kconfig | 4 + hw/net/meson.build | 1 + 5 files changed, 233 insertions(+), 115 deletions(-) create mode 100644 include/hw/net/lan9118_phy.h create mode 100644 hw/net/lan9118_phy.c diff --git a/include/hw/net/lan9118_phy.h b/include/hw/net/lan9118_phy.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/lan9118_phy.h @@ -XXX,XX +XXX,XX @@ +/* + * SMSC LAN9118 PHY emulation + * + * Copyright (c) 2009 CodeSourcery, LLC. + * Written by Paul Brook + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef HW_NET_LAN9118_PHY_H +#define HW_NET_LAN9118_PHY_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +#define TYPE_LAN9118_PHY "lan9118-phy" +OBJECT_DECLARE_SIMPLE_TYPE(Lan9118PhyState, LAN9118_PHY) + +typedef struct Lan9118PhyState { + SysBusDevice parent_obj; + + uint16_t status; + uint16_t control; + uint16_t advertise; + uint16_t ints; + uint16_t int_mask; + qemu_irq irq; + bool link_down; +} Lan9118PhyState; + +void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down); +void lan9118_phy_reset(Lan9118PhyState *s); +uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg); +void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val); + +#endif diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118.c +++ b/hw/net/lan9118.c @@ -XXX,XX +XXX,XX @@ #include "net/net.h" #include "net/eth.h" #include "hw/irq.h" +#include "hw/net/lan9118_phy.h" #include "hw/net/lan9118.h" #include "hw/ptimer.h" #include "hw/qdev-properties.h" @@ -XXX,XX +XXX,XX @@ do { printf("lan9118: " fmt , ## __VA_ARGS__); } while (0) #define MAC_CR_RXEN 0x00000004 #define MAC_CR_RESERVED 0x7f404213 -#define PHY_INT_ENERGYON 0x80 -#define PHY_INT_AUTONEG_COMPLETE 0x40 -#define PHY_INT_FAULT 0x20 -#define PHY_INT_DOWN 0x10 -#define PHY_INT_AUTONEG_LP 0x08 -#define PHY_INT_PARFAULT 0x04 -#define PHY_INT_AUTONEG_PAGE 0x02 - #define GPT_TIMER_EN 0x20000000 /* @@ -XXX,XX +XXX,XX @@ struct lan9118_state { uint32_t mac_mii_data; uint32_t mac_flow; - uint32_t phy_status; - uint32_t phy_control; - uint32_t phy_advertise; - uint32_t phy_int; - uint32_t phy_int_mask; + Lan9118PhyState mii; + IRQState mii_irq; int32_t eeprom_writable; uint8_t eeprom[128]; @@ -XXX,XX +XXX,XX @@ struct lan9118_state { static const VMStateDescription vmstate_lan9118 = { .name = "lan9118", - .version_id = 2, - .minimum_version_id = 1, + .version_id = 3, + .minimum_version_id = 3, .fields = (const VMStateField[]) { VMSTATE_PTIMER(timer, lan9118_state), VMSTATE_UINT32(irq_cfg, lan9118_state), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_lan9118 = { VMSTATE_UINT32(mac_mii_acc, lan9118_state), VMSTATE_UINT32(mac_mii_data, lan9118_state), VMSTATE_UINT32(mac_flow, lan9118_state), - VMSTATE_UINT32(phy_status, lan9118_state), - VMSTATE_UINT32(phy_control, lan9118_state), - VMSTATE_UINT32(phy_advertise, lan9118_state), - VMSTATE_UINT32(phy_int, lan9118_state), - VMSTATE_UINT32(phy_int_mask, lan9118_state), VMSTATE_INT32(eeprom_writable, lan9118_state), VMSTATE_UINT8_ARRAY(eeprom, lan9118_state, 128), VMSTATE_INT32(tx_fifo_size, lan9118_state), @@ -XXX,XX +XXX,XX @@ static void lan9118_reload_eeprom(lan9118_state *s) lan9118_mac_changed(s); } -static void phy_update_irq(lan9118_state *s) +static void lan9118_update_irq(void *opaque, int n, int level) { - if (s->phy_int & s->phy_int_mask) { + lan9118_state *s = opaque; + + if (level) { s->int_sts |= PHY_INT; } else { s->int_sts &= ~PHY_INT; @@ -XXX,XX +XXX,XX @@ static void phy_update_irq(lan9118_state *s) lan9118_update(s); } -static void phy_update_link(lan9118_state *s) -{ - /* Autonegotiation status mirrors link status. */ - if (qemu_get_queue(s->nic)->link_down) { - s->phy_status &= ~0x0024; - s->phy_int |= PHY_INT_DOWN; - } else { - s->phy_status |= 0x0024; - s->phy_int |= PHY_INT_ENERGYON; - s->phy_int |= PHY_INT_AUTONEG_COMPLETE; - } - phy_update_irq(s); -} - static void lan9118_set_link(NetClientState *nc) { - phy_update_link(qemu_get_nic_opaque(nc)); -} - -static void phy_reset(lan9118_state *s) -{ - s->phy_status = 0x7809; - s->phy_control = 0x3000; - s->phy_advertise = 0x01e1; - s->phy_int_mask = 0; - s->phy_int = 0; - phy_update_link(s); + lan9118_phy_update_link(&LAN9118(qemu_get_nic_opaque(nc))->mii, + nc->link_down); } static void lan9118_reset(DeviceState *d) @@ -XXX,XX +XXX,XX @@ static void lan9118_reset(DeviceState *d) s->read_word_n = 0; s->write_word_n = 0; - phy_reset(s); - s->eeprom_writable = 0; lan9118_reload_eeprom(s); } @@ -XXX,XX +XXX,XX @@ static void do_tx_packet(lan9118_state *s) uint32_t status; /* FIXME: Honor TX disable, and allow queueing of packets. */ - if (s->phy_control & 0x4000) { + if (s->mii.control & 0x4000) { /* This assumes the receive routine doesn't touch the VLANClient. */ qemu_receive_packet(qemu_get_queue(s->nic), s->txp->data, s->txp->len); } else { @@ -XXX,XX +XXX,XX @@ static void tx_fifo_push(lan9118_state *s, uint32_t val) } } -static uint32_t do_phy_read(lan9118_state *s, int reg) -{ - uint32_t val; - - switch (reg) { - case 0: /* Basic Control */ - return s->phy_control; - case 1: /* Basic Status */ - return s->phy_status; - case 2: /* ID1 */ - return 0x0007; - case 3: /* ID2 */ - return 0xc0d1; - case 4: /* Auto-neg advertisement */ - return s->phy_advertise; - case 5: /* Auto-neg Link Partner Ability */ - return 0x0f71; - case 6: /* Auto-neg Expansion */ - return 1; - /* TODO 17, 18, 27, 29, 30, 31 */ - case 29: /* Interrupt source. */ - val = s->phy_int; - s->phy_int = 0; - phy_update_irq(s); - return val; - case 30: /* Interrupt mask */ - return s->phy_int_mask; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "do_phy_read: PHY read reg %d\n", reg); - return 0; - } -} - -static void do_phy_write(lan9118_state *s, int reg, uint32_t val) -{ - switch (reg) { - case 0: /* Basic Control */ - if (val & 0x8000) { - phy_reset(s); - break; - } - s->phy_control = val & 0x7980; - /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->phy_status |= 0x0020; - } - break; - case 4: /* Auto-neg advertisement */ - s->phy_advertise = (val & 0x2d7f) | 0x80; - break; - /* TODO 17, 18, 27, 31 */ - case 30: /* Interrupt mask */ - s->phy_int_mask = val & 0xff; - phy_update_irq(s); - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "do_phy_write: PHY write reg %d = 0x%04x\n", reg, val); - } -} - static void do_mac_write(lan9118_state *s, int reg, uint32_t val) { switch (reg) { @@ -XXX,XX +XXX,XX @@ static void do_mac_write(lan9118_state *s, int reg, uint32_t val) if (val & 2) { DPRINTF("PHY write %d = 0x%04x\n", (val >> 6) & 0x1f, s->mac_mii_data); - do_phy_write(s, (val >> 6) & 0x1f, s->mac_mii_data); + lan9118_phy_write(&s->mii, (val >> 6) & 0x1f, s->mac_mii_data); } else { - s->mac_mii_data = do_phy_read(s, (val >> 6) & 0x1f); + s->mac_mii_data = lan9118_phy_read(&s->mii, (val >> 6) & 0x1f); DPRINTF("PHY read %d = 0x%04x\n", (val >> 6) & 0x1f, s->mac_mii_data); } @@ -XXX,XX +XXX,XX @@ static void lan9118_writel(void *opaque, hwaddr offset, break; case CSR_PMT_CTRL: if (val & 0x400) { - phy_reset(s); + lan9118_phy_reset(&s->mii); } s->pmt_ctrl &= ~0x34e; s->pmt_ctrl |= (val & 0x34e); @@ -XXX,XX +XXX,XX @@ static void lan9118_realize(DeviceState *dev, Error **errp) const MemoryRegionOps *mem_ops = s->mode_16bit ? &lan9118_16bit_mem_ops : &lan9118_mem_ops; + qemu_init_irq(&s->mii_irq, lan9118_update_irq, s, 0); + object_initialize_child(OBJECT(s), "mii", &s->mii, TYPE_LAN9118_PHY); + if (!sysbus_realize_and_unref(SYS_BUS_DEVICE(&s->mii), errp)) { + return; + } + qdev_connect_gpio_out(DEVICE(&s->mii), 0, &s->mii_irq); + memory_region_init_io(&s->mmio, OBJECT(dev), mem_ops, s, "lan9118-mmio", 0x100); sysbus_init_mmio(sbd, &s->mmio); diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ +/* + * SMSC LAN9118 PHY emulation + * + * Copyright (c) 2009 CodeSourcery, LLC. + * Written by Paul Brook + * + * This code is licensed under the GNU GPL v2 + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "hw/net/lan9118_phy.h" +#include "hw/irq.h" +#include "hw/resettable.h" +#include "migration/vmstate.h" +#include "qemu/log.h" + +#define PHY_INT_ENERGYON (1 << 7) +#define PHY_INT_AUTONEG_COMPLETE (1 << 6) +#define PHY_INT_FAULT (1 << 5) +#define PHY_INT_DOWN (1 << 4) +#define PHY_INT_AUTONEG_LP (1 << 3) +#define PHY_INT_PARFAULT (1 << 2) +#define PHY_INT_AUTONEG_PAGE (1 << 1) + +static void lan9118_phy_update_irq(Lan9118PhyState *s) +{ + qemu_set_irq(s->irq, !!(s->ints & s->int_mask)); +} + +uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) +{ + uint16_t val; + + switch (reg) { + case 0: /* Basic Control */ + return s->control; + case 1: /* Basic Status */ + return s->status; + case 2: /* ID1 */ + return 0x0007; + case 3: /* ID2 */ + return 0xc0d1; + case 4: /* Auto-neg advertisement */ + return s->advertise; + case 5: /* Auto-neg Link Partner Ability */ + return 0x0f71; + case 6: /* Auto-neg Expansion */ + return 1; + /* TODO 17, 18, 27, 29, 30, 31 */ + case 29: /* Interrupt source. */ + val = s->ints; + s->ints = 0; + lan9118_phy_update_irq(s); + return val; + case 30: /* Interrupt mask */ + return s->int_mask; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "lan9118_phy_read: PHY read reg %d\n", reg); + return 0; + } +} + +void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) +{ + switch (reg) { + case 0: /* Basic Control */ + if (val & 0x8000) { + lan9118_phy_reset(s); + break; + } + s->control = val & 0x7980; + /* Complete autonegotiation immediately. */ + if (val & 0x1000) { + s->status |= 0x0020; + } + break; + case 4: /* Auto-neg advertisement */ + s->advertise = (val & 0x2d7f) | 0x80; + break; + /* TODO 17, 18, 27, 31 */ + case 30: /* Interrupt mask */ + s->int_mask = val & 0xff; + lan9118_phy_update_irq(s); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "lan9118_phy_write: PHY write reg %d = 0x%04x\n", reg, val); + } +} + +void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) +{ + s->link_down = link_down; + + /* Autonegotiation status mirrors link status. */ + if (link_down) { + s->status &= ~0x0024; + s->ints |= PHY_INT_DOWN; + } else { + s->status |= 0x0024; + s->ints |= PHY_INT_ENERGYON; + s->ints |= PHY_INT_AUTONEG_COMPLETE; + } + lan9118_phy_update_irq(s); +} + +void lan9118_phy_reset(Lan9118PhyState *s) +{ + s->control = 0x3000; + s->status = 0x7809; + s->advertise = 0x01e1; + s->int_mask = 0; + s->ints = 0; + lan9118_phy_update_link(s, s->link_down); +} + +static void lan9118_phy_reset_hold(Object *obj, ResetType type) +{ + Lan9118PhyState *s = LAN9118_PHY(obj); + + lan9118_phy_reset(s); +} + +static void lan9118_phy_init(Object *obj) +{ + Lan9118PhyState *s = LAN9118_PHY(obj); + + qdev_init_gpio_out(DEVICE(s), &s->irq, 1); +} + +static const VMStateDescription vmstate_lan9118_phy = { + .name = "lan9118-phy", + .version_id = 1, + .minimum_version_id = 1, + .fields = (const VMStateField[]) { + VMSTATE_UINT16(control, Lan9118PhyState), + VMSTATE_UINT16(status, Lan9118PhyState), + VMSTATE_UINT16(advertise, Lan9118PhyState), + VMSTATE_UINT16(ints, Lan9118PhyState), + VMSTATE_UINT16(int_mask, Lan9118PhyState), + VMSTATE_BOOL(link_down, Lan9118PhyState), + VMSTATE_END_OF_LIST() + } +}; + +static void lan9118_phy_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + rc->phases.hold = lan9118_phy_reset_hold; + dc->vmsd = &vmstate_lan9118_phy; +} + +static const TypeInfo types[] = { + { + .name = TYPE_LAN9118_PHY, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(Lan9118PhyState), + .instance_init = lan9118_phy_init, + .class_init = lan9118_phy_class_init, + } +}; + +DEFINE_TYPES(types) diff --git a/hw/net/Kconfig b/hw/net/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Kconfig +++ b/hw/net/Kconfig @@ -XXX,XX +XXX,XX @@ config VMXNET3_PCI config SMC91C111 bool +config LAN9118_PHY + bool + config LAN9118 bool + select LAN9118_PHY select PTIMER config NE2000_ISA diff --git a/hw/net/meson.build b/hw/net/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/meson.build +++ b/hw/net/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_VMXNET3_PCI', if_true: files('vmxnet3.c')) system_ss.add(when: 'CONFIG_SMC91C111', if_true: files('smc91c111.c')) system_ss.add(when: 'CONFIG_LAN9118', if_true: files('lan9118.c')) +system_ss.add(when: 'CONFIG_LAN9118_PHY', if_true: files('lan9118_phy.c')) system_ss.add(when: 'CONFIG_NE2000_ISA', if_true: files('ne2000-isa.c')) system_ss.add(when: 'CONFIG_OPENCORES_ETH', if_true: files('opencores_eth.c')) system_ss.add(when: 'CONFIG_XGMAC', if_true: files('xgmac.c')) -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> imx_fec models the same PHY as lan9118_phy. The code is almost the same with imx_fec having more logging and tracing. Merge these improvements into lan9118_phy and reuse in imx_fec to fix the code duplication. Some migration state how resides in the new device model which breaks migration compatibility for the following machines: * imx25-pdk * sabrelite * mcimx7d-sabre * mcimx6ul-evk Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241102125724.532843-3-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/imx_fec.h | 9 ++- hw/net/imx_fec.c | 146 ++++----------------------------------- hw/net/lan9118_phy.c | 82 ++++++++++++++++------ hw/net/Kconfig | 1 + hw/net/trace-events | 10 +-- 5 files changed, 85 insertions(+), 163 deletions(-) diff --git a/include/hw/net/imx_fec.h b/include/hw/net/imx_fec.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/imx_fec.h +++ b/include/hw/net/imx_fec.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(IMXFECState, IMX_FEC) #define TYPE_IMX_ENET "imx.enet" #include "hw/sysbus.h" +#include "hw/net/lan9118_phy.h" +#include "hw/irq.h" #include "net/net.h" #define ENET_EIR 1 @@ -XXX,XX +XXX,XX @@ struct IMXFECState { uint32_t tx_descriptor[ENET_TX_RING_NUM]; uint32_t tx_ring_num; - uint32_t phy_status; - uint32_t phy_control; - uint32_t phy_advertise; - uint32_t phy_int; - uint32_t phy_int_mask; + Lan9118PhyState mii; + IRQState mii_irq; uint32_t phy_num; bool phy_connected; struct IMXFECState *phy_consumer; diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_eth_txdescs = { static const VMStateDescription vmstate_imx_eth = { .name = TYPE_IMX_FEC, - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (const VMStateField[]) { VMSTATE_UINT32_ARRAY(regs, IMXFECState, ENET_MAX), VMSTATE_UINT32(rx_descriptor, IMXFECState), VMSTATE_UINT32(tx_descriptor[0], IMXFECState), - VMSTATE_UINT32(phy_status, IMXFECState), - VMSTATE_UINT32(phy_control, IMXFECState), - VMSTATE_UINT32(phy_advertise, IMXFECState), - VMSTATE_UINT32(phy_int, IMXFECState), - VMSTATE_UINT32(phy_int_mask, IMXFECState), VMSTATE_END_OF_LIST() }, .subsections = (const VMStateDescription * const []) { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_eth = { }, }; -#define PHY_INT_ENERGYON (1 << 7) -#define PHY_INT_AUTONEG_COMPLETE (1 << 6) -#define PHY_INT_FAULT (1 << 5) -#define PHY_INT_DOWN (1 << 4) -#define PHY_INT_AUTONEG_LP (1 << 3) -#define PHY_INT_PARFAULT (1 << 2) -#define PHY_INT_AUTONEG_PAGE (1 << 1) - static void imx_eth_update(IMXFECState *s); /* @@ -XXX,XX +XXX,XX @@ static void imx_eth_update(IMXFECState *s); * For now we don't handle any GPIO/interrupt line, so the OS will * have to poll for the PHY status. */ -static void imx_phy_update_irq(IMXFECState *s) +static void imx_phy_update_irq(void *opaque, int n, int level) { - imx_eth_update(s); -} - -static void imx_phy_update_link(IMXFECState *s) -{ - /* Autonegotiation status mirrors link status. */ - if (qemu_get_queue(s->nic)->link_down) { - trace_imx_phy_update_link("down"); - s->phy_status &= ~0x0024; - s->phy_int |= PHY_INT_DOWN; - } else { - trace_imx_phy_update_link("up"); - s->phy_status |= 0x0024; - s->phy_int |= PHY_INT_ENERGYON; - s->phy_int |= PHY_INT_AUTONEG_COMPLETE; - } - imx_phy_update_irq(s); + imx_eth_update(opaque); } static void imx_eth_set_link(NetClientState *nc) { - imx_phy_update_link(IMX_FEC(qemu_get_nic_opaque(nc))); -} - -static void imx_phy_reset(IMXFECState *s) -{ - trace_imx_phy_reset(); - - s->phy_status = 0x7809; - s->phy_control = 0x3000; - s->phy_advertise = 0x01e1; - s->phy_int_mask = 0; - s->phy_int = 0; - imx_phy_update_link(s); + lan9118_phy_update_link(&IMX_FEC(qemu_get_nic_opaque(nc))->mii, + nc->link_down); } static uint32_t imx_phy_read(IMXFECState *s, int reg) { - uint32_t val; uint32_t phy = reg / 32; if (!s->phy_connected) { @@ -XXX,XX +XXX,XX @@ static uint32_t imx_phy_read(IMXFECState *s, int reg) reg %= 32; - switch (reg) { - case 0: /* Basic Control */ - val = s->phy_control; - break; - case 1: /* Basic Status */ - val = s->phy_status; - break; - case 2: /* ID1 */ - val = 0x0007; - break; - case 3: /* ID2 */ - val = 0xc0d1; - break; - case 4: /* Auto-neg advertisement */ - val = s->phy_advertise; - break; - case 5: /* Auto-neg Link Partner Ability */ - val = 0x0f71; - break; - case 6: /* Auto-neg Expansion */ - val = 1; - break; - case 29: /* Interrupt source. */ - val = s->phy_int; - s->phy_int = 0; - imx_phy_update_irq(s); - break; - case 30: /* Interrupt mask */ - val = s->phy_int_mask; - break; - case 17: - case 18: - case 27: - case 31: - qemu_log_mask(LOG_UNIMP, "[%s.phy]%s: reg %d not implemented\n", - TYPE_IMX_FEC, __func__, reg); - val = 0; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad address at offset %d\n", - TYPE_IMX_FEC, __func__, reg); - val = 0; - break; - } - - trace_imx_phy_read(val, phy, reg); - - return val; + return lan9118_phy_read(&s->mii, reg); } static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) @@ -XXX,XX +XXX,XX @@ static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) reg %= 32; - trace_imx_phy_write(val, phy, reg); - - switch (reg) { - case 0: /* Basic Control */ - if (val & 0x8000) { - imx_phy_reset(s); - } else { - s->phy_control = val & 0x7980; - /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->phy_status |= 0x0020; - } - } - break; - case 4: /* Auto-neg advertisement */ - s->phy_advertise = (val & 0x2d7f) | 0x80; - break; - case 30: /* Interrupt mask */ - s->phy_int_mask = val & 0xff; - imx_phy_update_irq(s); - break; - case 17: - case 18: - case 27: - case 31: - qemu_log_mask(LOG_UNIMP, "[%s.phy)%s: reg %d not implemented\n", - TYPE_IMX_FEC, __func__, reg); - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad address at offset %d\n", - TYPE_IMX_FEC, __func__, reg); - break; - } + lan9118_phy_write(&s->mii, reg, val); } static void imx_fec_read_bd(IMXFECBufDesc *bd, dma_addr_t addr) @@ -XXX,XX +XXX,XX @@ static void imx_eth_reset(DeviceState *d) s->rx_descriptor = 0; memset(s->tx_descriptor, 0, sizeof(s->tx_descriptor)); - - /* We also reset the PHY */ - imx_phy_reset(s); } static uint32_t imx_default_read(IMXFECState *s, uint32_t index) @@ -XXX,XX +XXX,XX @@ static void imx_eth_realize(DeviceState *dev, Error **errp) sysbus_init_irq(sbd, &s->irq[0]); sysbus_init_irq(sbd, &s->irq[1]); + qemu_init_irq(&s->mii_irq, imx_phy_update_irq, s, 0); + object_initialize_child(OBJECT(s), "mii", &s->mii, TYPE_LAN9118_PHY); + if (!sysbus_realize_and_unref(SYS_BUS_DEVICE(&s->mii), errp)) { + return; + } + qdev_connect_gpio_out(DEVICE(&s->mii), 0, &s->mii_irq); + qemu_macaddr_default_if_unset(&s->conf.macaddr); s->nic = qemu_new_nic(&imx_eth_net_info, &s->conf, diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ * Copyright (c) 2009 CodeSourcery, LLC. * Written by Paul Brook * + * Copyright (c) 2013 Jean-Christophe Dubois. <jcd@tribudubois.net> + * * This code is licensed under the GNU GPL v2 * * Contributions after 2012-01-13 are licensed under the terms of the @@ -XXX,XX +XXX,XX @@ #include "hw/resettable.h" #include "migration/vmstate.h" #include "qemu/log.h" +#include "trace.h" #define PHY_INT_ENERGYON (1 << 7) #define PHY_INT_AUTONEG_COMPLETE (1 << 6) @@ -XXX,XX +XXX,XX @@ uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) switch (reg) { case 0: /* Basic Control */ - return s->control; + val = s->control; + break; case 1: /* Basic Status */ - return s->status; + val = s->status; + break; case 2: /* ID1 */ - return 0x0007; + val = 0x0007; + break; case 3: /* ID2 */ - return 0xc0d1; + val = 0xc0d1; + break; case 4: /* Auto-neg advertisement */ - return s->advertise; + val = s->advertise; + break; case 5: /* Auto-neg Link Partner Ability */ - return 0x0f71; + val = 0x0f71; + break; case 6: /* Auto-neg Expansion */ - return 1; - /* TODO 17, 18, 27, 29, 30, 31 */ + val = 1; + break; case 29: /* Interrupt source. */ val = s->ints; s->ints = 0; lan9118_phy_update_irq(s); - return val; + break; case 30: /* Interrupt mask */ - return s->int_mask; + val = s->int_mask; + break; + case 17: + case 18: + case 27: + case 31: + qemu_log_mask(LOG_UNIMP, "%s: reg %d not implemented\n", + __func__, reg); + val = 0; + break; default: - qemu_log_mask(LOG_GUEST_ERROR, - "lan9118_phy_read: PHY read reg %d\n", reg); - return 0; + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad address at offset %d\n", + __func__, reg); + val = 0; + break; } + + trace_lan9118_phy_read(val, reg); + + return val; } void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) { + trace_lan9118_phy_write(val, reg); + switch (reg) { case 0: /* Basic Control */ if (val & 0x8000) { lan9118_phy_reset(s); - break; - } - s->control = val & 0x7980; - /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->status |= 0x0020; + } else { + s->control = val & 0x7980; + /* Complete autonegotiation immediately. */ + if (val & 0x1000) { + s->status |= 0x0020; + } } break; case 4: /* Auto-neg advertisement */ s->advertise = (val & 0x2d7f) | 0x80; break; - /* TODO 17, 18, 27, 31 */ case 30: /* Interrupt mask */ s->int_mask = val & 0xff; lan9118_phy_update_irq(s); break; + case 17: + case 18: + case 27: + case 31: + qemu_log_mask(LOG_UNIMP, "%s: reg %d not implemented\n", + __func__, reg); + break; default: - qemu_log_mask(LOG_GUEST_ERROR, - "lan9118_phy_write: PHY write reg %d = 0x%04x\n", reg, val); + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad address at offset %d\n", + __func__, reg); + break; } } @@ -XXX,XX +XXX,XX @@ void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) /* Autonegotiation status mirrors link status. */ if (link_down) { + trace_lan9118_phy_update_link("down"); s->status &= ~0x0024; s->ints |= PHY_INT_DOWN; } else { + trace_lan9118_phy_update_link("up"); s->status |= 0x0024; s->ints |= PHY_INT_ENERGYON; s->ints |= PHY_INT_AUTONEG_COMPLETE; @@ -XXX,XX +XXX,XX @@ void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) void lan9118_phy_reset(Lan9118PhyState *s) { + trace_lan9118_phy_reset(); + s->control = 0x3000; s->status = 0x7809; s->advertise = 0x01e1; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_lan9118_phy = { .version_id = 1, .minimum_version_id = 1, .fields = (const VMStateField[]) { - VMSTATE_UINT16(control, Lan9118PhyState), VMSTATE_UINT16(status, Lan9118PhyState), + VMSTATE_UINT16(control, Lan9118PhyState), VMSTATE_UINT16(advertise, Lan9118PhyState), VMSTATE_UINT16(ints, Lan9118PhyState), VMSTATE_UINT16(int_mask, Lan9118PhyState), diff --git a/hw/net/Kconfig b/hw/net/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Kconfig +++ b/hw/net/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_SUN8I_EMAC config IMX_FEC bool + select LAN9118_PHY config CADENCE bool diff --git a/hw/net/trace-events b/hw/net/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_sun8i_emac_set_link(bool active) "Set link: active=%u" allwinner_sun8i_emac_read(uint64_t offset, uint64_t val) "MMIO read: offset=0x%" PRIx64 " value=0x%" PRIx64 allwinner_sun8i_emac_write(uint64_t offset, uint64_t val) "MMIO write: offset=0x%" PRIx64 " value=0x%" PRIx64 +# lan9118_phy.c +lan9118_phy_read(uint16_t val, int reg) "[0x%02x] -> 0x%04" PRIx16 +lan9118_phy_write(uint16_t val, int reg) "[0x%02x] <- 0x%04" PRIx16 +lan9118_phy_update_link(const char *s) "%s" +lan9118_phy_reset(void) "" + # lance.c lance_mem_readw(uint64_t addr, uint32_t ret) "addr=0x%"PRIx64"val=0x%04x" lance_mem_writew(uint64_t addr, uint32_t val) "addr=0x%"PRIx64"val=0x%04x" @@ -XXX,XX +XXX,XX @@ i82596_set_multicast(uint16_t count) "Added %d multicast entries" i82596_channel_attention(void *s) "%p: Received CHANNEL ATTENTION" # imx_fec.c -imx_phy_read(uint32_t val, int phy, int reg) "0x%04"PRIx32" <= phy[%d].reg[%d]" imx_phy_read_num(int phy, int configured) "read request from unconfigured phy %d (configured %d)" -imx_phy_write(uint32_t val, int phy, int reg) "0x%04"PRIx32" => phy[%d].reg[%d]" imx_phy_write_num(int phy, int configured) "write request to unconfigured phy %d (configured %d)" -imx_phy_update_link(const char *s) "%s" -imx_phy_reset(void) "" imx_fec_read_bd(uint64_t addr, int flags, int len, int data) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x" imx_enet_read_bd(uint64_t addr, int flags, int len, int data, int options, int status) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x option 0x%04x status 0x%04x" imx_eth_tx_bd_busy(void) "tx_bd ran out of descriptors to transmit" -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> Turns 0x70 into 0xe0 (== 0x70 << 1) which adds the missing MII_ANLPAR_TX and fixes the MSB of selector field to be zero, as specified in the datasheet. Fixes: 2a424990170b "LAN9118 emulation" Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241102125724.532843-4-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/lan9118_phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) val = s->advertise; break; case 5: /* Auto-neg Link Partner Ability */ - val = 0x0f71; + val = 0x0fe1; break; case 6: /* Auto-neg Expansion */ val = 1; -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> Prefer named constants over magic values for better readability. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20241102125724.532843-5-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/mii.h | 6 +++++ hw/net/lan9118_phy.c | 63 ++++++++++++++++++++++++++++---------------- 2 files changed, 46 insertions(+), 23 deletions(-) diff --git a/include/hw/net/mii.h b/include/hw/net/mii.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/mii.h +++ b/include/hw/net/mii.h @@ -XXX,XX +XXX,XX @@ #define MII_BMSR_JABBER (1 << 1) /* Jabber detected */ #define MII_BMSR_EXTCAP (1 << 0) /* Ext-reg capability */ +#define MII_ANAR_RFAULT (1 << 13) /* Say we can detect faults */ #define MII_ANAR_PAUSE_ASYM (1 << 11) /* Try for asymmetric pause */ #define MII_ANAR_PAUSE (1 << 10) /* Try for pause */ #define MII_ANAR_TXFD (1 << 8) @@ -XXX,XX +XXX,XX @@ #define MII_ANAR_10FD (1 << 6) #define MII_ANAR_10 (1 << 5) #define MII_ANAR_CSMACD (1 << 0) +#define MII_ANAR_SELECT (0x001f) /* Selector bits */ #define MII_ANLPAR_ACK (1 << 14) #define MII_ANLPAR_PAUSEASY (1 << 11) /* can pause asymmetrically */ @@ -XXX,XX +XXX,XX @@ #define RTL8201CP_PHYID1 0x0000 #define RTL8201CP_PHYID2 0x8201 +/* SMSC LAN9118 */ +#define SMSCLAN9118_PHYID1 0x0007 +#define SMSCLAN9118_PHYID2 0xc0d1 + /* RealTek 8211E */ #define RTL8211E_PHYID1 0x001c #define RTL8211E_PHYID2 0xc915 diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "hw/net/lan9118_phy.h" +#include "hw/net/mii.h" #include "hw/irq.h" #include "hw/resettable.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) uint16_t val; switch (reg) { - case 0: /* Basic Control */ + case MII_BMCR: val = s->control; break; - case 1: /* Basic Status */ + case MII_BMSR: val = s->status; break; - case 2: /* ID1 */ - val = 0x0007; + case MII_PHYID1: + val = SMSCLAN9118_PHYID1; break; - case 3: /* ID2 */ - val = 0xc0d1; + case MII_PHYID2: + val = SMSCLAN9118_PHYID2; break; - case 4: /* Auto-neg advertisement */ + case MII_ANAR: val = s->advertise; break; - case 5: /* Auto-neg Link Partner Ability */ - val = 0x0fe1; + case MII_ANLPAR: + val = MII_ANLPAR_PAUSEASY | MII_ANLPAR_PAUSE | MII_ANLPAR_T4 | + MII_ANLPAR_TXFD | MII_ANLPAR_TX | MII_ANLPAR_10FD | + MII_ANLPAR_10 | MII_ANLPAR_CSMACD; break; - case 6: /* Auto-neg Expansion */ - val = 1; + case MII_ANER: + val = MII_ANER_NWAY; break; case 29: /* Interrupt source. */ val = s->ints; @@ -XXX,XX +XXX,XX @@ void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) trace_lan9118_phy_write(val, reg); switch (reg) { - case 0: /* Basic Control */ - if (val & 0x8000) { + case MII_BMCR: + if (val & MII_BMCR_RESET) { lan9118_phy_reset(s); } else { - s->control = val & 0x7980; + s->control = val & (MII_BMCR_LOOPBACK | MII_BMCR_SPEED100 | + MII_BMCR_AUTOEN | MII_BMCR_PDOWN | MII_BMCR_FD | + MII_BMCR_CTST); /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->status |= 0x0020; + if (val & MII_BMCR_AUTOEN) { + s->status |= MII_BMSR_AN_COMP; } } break; - case 4: /* Auto-neg advertisement */ - s->advertise = (val & 0x2d7f) | 0x80; + case MII_ANAR: + s->advertise = (val & (MII_ANAR_RFAULT | MII_ANAR_PAUSE_ASYM | + MII_ANAR_PAUSE | MII_ANAR_10FD | MII_ANAR_10 | + MII_ANAR_SELECT)) + | MII_ANAR_TX; break; case 30: /* Interrupt mask */ s->int_mask = val & 0xff; @@ -XXX,XX +XXX,XX @@ void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) /* Autonegotiation status mirrors link status. */ if (link_down) { trace_lan9118_phy_update_link("down"); - s->status &= ~0x0024; + s->status &= ~(MII_BMSR_AN_COMP | MII_BMSR_LINK_ST); s->ints |= PHY_INT_DOWN; } else { trace_lan9118_phy_update_link("up"); - s->status |= 0x0024; + s->status |= MII_BMSR_AN_COMP | MII_BMSR_LINK_ST; s->ints |= PHY_INT_ENERGYON; s->ints |= PHY_INT_AUTONEG_COMPLETE; } @@ -XXX,XX +XXX,XX @@ void lan9118_phy_reset(Lan9118PhyState *s) { trace_lan9118_phy_reset(); - s->control = 0x3000; - s->status = 0x7809; - s->advertise = 0x01e1; + s->control = MII_BMCR_AUTOEN | MII_BMCR_SPEED100; + s->status = MII_BMSR_100TX_FD + | MII_BMSR_100TX_HD + | MII_BMSR_10T_FD + | MII_BMSR_10T_HD + | MII_BMSR_AUTONEG + | MII_BMSR_EXTCAP; + s->advertise = MII_ANAR_TXFD + | MII_ANAR_TX + | MII_ANAR_10FD + | MII_ANAR_10 + | MII_ANAR_CSMACD; s->int_mask = 0; s->ints = 0; lan9118_phy_update_link(s, s->link_down); -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> The real device advertises this mode and the device model already advertises 100 mbps half duplex and 10 mbps full+half duplex. So advertise this mode to make the model more realistic. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20241102125724.532843-6-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/lan9118_phy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) break; case MII_ANAR: s->advertise = (val & (MII_ANAR_RFAULT | MII_ANAR_PAUSE_ASYM | - MII_ANAR_PAUSE | MII_ANAR_10FD | MII_ANAR_10 | - MII_ANAR_SELECT)) + MII_ANAR_PAUSE | MII_ANAR_TXFD | MII_ANAR_10FD | + MII_ANAR_10 | MII_ANAR_SELECT)) | MII_ANAR_TX; break; case 30: /* Interrupt mask */ -- 2.34.1 For IEEE fused multiply-add, the (0 * inf) + NaN case should raise Invalid for the multiplication of 0 by infinity. Currently we handle this in the per-architecture ifdef ladder in pickNaNMulAdd(). However, since this isn't really architecture specific we can hoist it up to the generic code. For the cases where the infzero test in pickNaNMulAdd was returning 2, we can delete the check entirely and allow the code to fall into the normal pick-a-NaN handling, because this will return 2 anyway (input 'c' being the only NaN in this case). For the cases where infzero was returning 3 to indicate "return the default NaN", we must retain that "return 3". For Arm, this looks like it might be a behaviour change because we used to set float_flag_invalid | float_flag_invalid_imz only if C is a quiet NaN. However, it is not, because Arm target code never looks at float_flag_invalid_imz, and for the (0 * inf) + SNaN case we already raised float_flag_invalid via the "abc_mask & float_cmask_snan" check in pick_nan_muladd. For any target architecture using the "default implementation" at the bottom of the ifdef, this is a behaviour change but will be fixing a bug (where we failed to raise the Invalid exception for (0 * inf + QNaN). The architectures using the default case are: * hppa * i386 * sh4 * tricore The x86, Tricore and SH4 CPU architecture manuals are clear that this should have raised Invalid; HPPA is a bit vaguer but still seems clear enough. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-2-peter.maydell@linaro.org --- fpu/softfloat-parts.c.inc | 13 +++++++------ fpu/softfloat-specialize.c.inc | 29 +---------------------------- 2 files changed, 8 insertions(+), 34 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, int ab_mask, int abc_mask) { int which; + bool infzero = (ab_mask == float_cmask_infzero); if (unlikely(abc_mask & float_cmask_snan)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); } - which = pickNaNMulAdd(a->cls, b->cls, c->cls, - ab_mask == float_cmask_infzero, s); + if (infzero) { + /* This is (0 * inf) + NaN or (inf * 0) + NaN */ + float_raise(float_flag_invalid | float_flag_invalid_imz, s); + } + + which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); if (s->default_nan_mode || which == 3) { - /* - * Note that this check is after pickNaNMulAdd so that function - * has an opportunity to set the Invalid flag for infzero. - */ parts_default_nan(a, s); return a; } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * the default NaN */ if (infzero && is_qnan(c_cls)) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); return 3; } @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * case sets InvalidOp and returns the default NaN */ if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); return 3; } /* Prefer sNaN over qNaN, in the a, b, c order. */ @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } + /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * to return an input NaN if we have one (ie c) rather than generating * a default NaN */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 1; } #elif defined(TARGET_RISCV) - /* For RISC-V, InvalidOp is set when multiplicands are Inf and zero */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - } return 3; /* default NaN */ #elif defined(TARGET_S390X) if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); return 3; } @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 2; } #elif defined(TARGET_SPARC) - /* For (inf,0,nan) return c. */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } /* Prefer SNaN over QNaN, order C, B, A. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * For Xtensa, the (inf,zero,nan) case sets InvalidOp and returns * an input NaN if we have one (ie c). */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } if (status->use_first_nan) { if (is_nan(a_cls)) { return 0; -- 2.34.1 If the target sets default_nan_mode then we're always going to return the default NaN, and pickNaNMulAdd() no longer has any side effects. For consistency with pickNaN(), check for default_nan_mode before calling pickNaNMulAdd(). When we convert pickNaNMulAdd() to allow runtime selection of the NaN propagation rule, this means we won't have to make the targets which use default_nan_mode also set a propagation rule. Since RiscV always uses default_nan_mode, this allows us to remove its ifdef case from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-3-peter.maydell@linaro.org --- fpu/softfloat-parts.c.inc | 8 ++++++-- fpu/softfloat-specialize.c.inc | 9 +++++++-- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, float_raise(float_flag_invalid | float_flag_invalid_imz, s); } - which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); + if (s->default_nan_mode) { + which = 3; + } else { + which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); + } - if (s->default_nan_mode || which == 3) { + if (which == 3) { parts_default_nan(a, s); return a; } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, float_status *status) { + /* + * We guarantee not to require the target to tell us how to + * pick a NaN if we're always returning the default NaN. + * But if we're not in default-NaN mode then the target must + * specify. + */ + assert(!status->default_nan_mode); #if defined(TARGET_ARM) /* For ARM, the (inf,zero,qnan) case sets InvalidOp and returns * the default NaN @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { return 1; } -#elif defined(TARGET_RISCV) - return 3; /* default NaN */ #elif defined(TARGET_S390X) if (infzero) { return 3; -- 2.34.1 IEEE 758 does not define a fixed rule for what NaN to return in the case of a fused multiply-add of inf * 0 + NaN. Different architectures thus do different things: * some return the default NaN * some return the input NaN * Arm returns the default NaN if the input NaN is quiet, and the input NaN if it is signalling We want to make this logic be runtime selected rather than hardcoded into the binary, because: * this will let us have multiple targets in one QEMU binary * the Arm FEAT_AFP architectural feature includes letting the guest select a NaN propagation rule at runtime In this commit we add an enum for the propagation rule, the field in float_status, and the corresponding getters and setters. We change pickNaNMulAdd to honour this, but because all targets still leave this field at its default 0 value, the fallback logic will pick the rule type with the old ifdef ladder. Note that four architectures both use the muladd softfloat functions and did not have a branch of the ifdef ladder to specify their behaviour (and so were ending up with the "default" case, probably wrongly): i386, HPPA, SH4 and Tricore. SH4 and Tricore both set default_nan_mode, and so will never get into pickNaNMulAdd(). For HPPA and i386 we retain the same behaviour as the old default-case, which is to not ever return the default NaN. This might not be correct but it is not a behaviour change. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-4-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 11 ++++ include/fpu/softfloat-types.h | 23 +++++++++ fpu/softfloat-specialize.c.inc | 91 ++++++++++++++++++++++----------- 3 files changed, 95 insertions(+), 30 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_float_2nan_prop_rule(Float2NaNPropRule rule, status->float_2nan_prop_rule = rule; } +static inline void set_float_infzeronan_rule(FloatInfZeroNaNRule rule, + float_status *status) +{ + status->float_infzeronan_rule = rule; +} + static inline void set_flush_to_zero(bool val, float_status *status) { status->flush_to_zero = val; @@ -XXX,XX +XXX,XX @@ static inline Float2NaNPropRule get_float_2nan_prop_rule(float_status *status) return status->float_2nan_prop_rule; } +static inline FloatInfZeroNaNRule get_float_infzeronan_rule(float_status *status) +{ + return status->float_infzeronan_rule; +} + static inline bool get_flush_to_zero(float_status *status) { return status->flush_to_zero; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef enum __attribute__((__packed__)) { float_2nan_prop_x87, } Float2NaNPropRule; +/* + * Rule for result of fused multiply-add 0 * Inf + NaN. + * This must be a NaN, but implementations differ on whether this + * is the input NaN or the default NaN. + * + * You don't need to set this if default_nan_mode is enabled. + * When not in default-NaN mode, it is an error for the target + * not to set the rule in float_status if it uses muladd, and we + * will assert if we need to handle an input NaN and no rule was + * selected. + */ +typedef enum __attribute__((__packed__)) { + /* No propagation rule specified */ + float_infzeronan_none = 0, + /* Result is never the default NaN (so always the input NaN) */ + float_infzeronan_dnan_never, + /* Result is always the default NaN */ + float_infzeronan_dnan_always, + /* Result is the default NaN if the input NaN is quiet */ + float_infzeronan_dnan_if_qnan, +} FloatInfZeroNaNRule; + /* * Floating Point Status. Individual architectures may maintain * several versions of float_status for different functions. The @@ -XXX,XX +XXX,XX @@ typedef struct float_status { FloatRoundMode float_rounding_mode; FloatX80RoundPrec floatx80_rounding_precision; Float2NaNPropRule float_2nan_prop_rule; + FloatInfZeroNaNRule float_infzeronan_rule; bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ bool flush_to_zero; diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, float_status *status) { + FloatInfZeroNaNRule rule = status->float_infzeronan_rule; + /* * We guarantee not to require the target to tell us how to * pick a NaN if we're always returning the default NaN. @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * specify. */ assert(!status->default_nan_mode); + + if (rule == float_infzeronan_none) { + /* + * Temporarily fall back to ifdef ladder + */ #if defined(TARGET_ARM) - /* For ARM, the (inf,zero,qnan) case sets InvalidOp and returns - * the default NaN - */ - if (infzero && is_qnan(c_cls)) { - return 3; + /* + * For ARM, the (inf,zero,qnan) case returns the default NaN, + * but (inf,zero,snan) returns the input NaN. + */ + rule = float_infzeronan_dnan_if_qnan; +#elif defined(TARGET_MIPS) + if (snan_bit_is_one(status)) { + /* + * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) + * case sets InvalidOp and returns the default NaN + */ + rule = float_infzeronan_dnan_always; + } else { + /* + * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c' + */ + rule = float_infzeronan_dnan_never; + } +#elif defined(TARGET_PPC) || defined(TARGET_SPARC) || \ + defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ + defined(TARGET_I386) || defined(TARGET_LOONGARCH) + /* + * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c' + */ + /* + * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer + * to return an input NaN if we have one (ie c) rather than generating + * a default NaN + */ + rule = float_infzeronan_dnan_never; +#elif defined(TARGET_S390X) + rule = float_infzeronan_dnan_always; +#endif } + if (infzero) { + /* + * Inf * 0 + NaN -- some implementations return the default NaN here, + * and some return the input NaN. + */ + switch (rule) { + case float_infzeronan_dnan_never: + return 2; + case float_infzeronan_dnan_always: + return 3; + case float_infzeronan_dnan_if_qnan: + return is_qnan(c_cls) ? 3 : 2; + default: + g_assert_not_reached(); + } + } + +#if defined(TARGET_ARM) + /* This looks different from the ARM ARM pseudocode, because the ARM ARM * puts the operands to a fused mac operation (a*b)+c in the order c,a,b. */ @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } #elif defined(TARGET_MIPS) if (snan_bit_is_one(status)) { - /* - * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) - * case sets InvalidOp and returns the default NaN - */ - if (infzero) { - return 3; - } /* Prefer sNaN over qNaN, in the a, b, c order. */ if (is_snan(a_cls)) { return 0; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 2; } } else { - /* - * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } } #elif defined(TARGET_LOONGARCH64) - /* - * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ - /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 1; } #elif defined(TARGET_PPC) - /* For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer - * to return an input NaN if we have one (ie c) rather than generating - * a default NaN - */ - /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB */ @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 1; } #elif defined(TARGET_S390X) - if (infzero) { - return 3; - } - if (is_snan(a_cls)) { return 0; } else if (is_snan(b_cls)) { -- 2.34.1 Explicitly set a rule in the softfloat tests for the inf-zero-nan muladd special case. In meson.build we put -DTARGET_ARM in fpcflags, and so we should select here the Arm rule of float_infzeronan_dnan_if_qnan. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241202131347.498124-5-peter.maydell@linaro.org --- tests/fp/fp-bench.c | 5 +++++ tests/fp/fp-test.c | 5 +++++ 2 files changed, 10 insertions(+) diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-bench.c +++ b/tests/fp/fp-bench.c @@ -XXX,XX +XXX,XX @@ static void run_bench(void) { bench_func_t f; + /* + * These implementation-defined choices for various things IEEE + * doesn't specify match those used by the Arm architecture. + */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status); + set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &soft_status); f = bench_funcs[operation][precision]; g_assert(f); diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -XXX,XX +XXX,XX @@ void run_test(void) { unsigned int i; + /* + * These implementation-defined choices for various things IEEE + * doesn't specify match those used by the Arm architecture. + */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); + set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &qsf); genCases_setLevel(test_level); verCases_maxErrorCount = n_max_errors; -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the Arm target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-6-peter.maydell@linaro.org --- target/arm/cpu.c | 3 +++ fpu/softfloat-specialize.c.inc | 8 +------- 2 files changed, 4 insertions(+), 7 deletions(-) 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 @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, * * tininess-before-rounding * * 2-input NaN propagation prefers SNaN over QNaN, and then * operand A over operand B (see FPProcessNaNs() pseudocode) + * * 0 * Inf + NaN returns the default NaN if the input NaN is quiet, + * and the input NaN if it is signalling */ static void arm_set_default_fp_behaviours(float_status *s) { set_float_detect_tininess(float_tininess_before_rounding, s); set_float_2nan_prop_rule(float_2nan_prop_s_ab, s); + set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, s); } static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_ARM) - /* - * For ARM, the (inf,zero,qnan) case returns the default NaN, - * but (inf,zero,snan) returns the input NaN. - */ - rule = float_infzeronan_dnan_if_qnan; -#elif defined(TARGET_MIPS) +#if defined(TARGET_MIPS) if (snan_bit_is_one(status)) { /* * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for s390, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-7-peter.maydell@linaro.org --- target/s390x/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset_hold(Object *obj, ResetType type) set_float_detect_tininess(float_tininess_before_rounding, &env->fpu_status); set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fpu_status); + set_float_infzeronan_rule(float_infzeronan_dnan_always, + &env->fpu_status); /* fall through */ case RESET_TYPE_S390_CPU_NORMAL: env->psw.mask &= ~PSW_MASK_RI; diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * a default NaN */ rule = float_infzeronan_dnan_never; -#elif defined(TARGET_S390X) - rule = float_infzeronan_dnan_always; #endif } -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the PPC target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-8-peter.maydell@linaro.org --- target/ppc/cpu_init.c | 7 +++++++ fpu/softfloat-specialize.c.inc | 7 +------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type) */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); set_float_2nan_prop_rule(float_2nan_prop_ab, &env->vec_status); + /* + * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer + * to return an input NaN if we have one (ie c) rather than generating + * a default NaN + */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->vec_status); for (i = 0; i < ARRAY_SIZE(env->spr_cb); i++) { ppc_spr_t *spr = &env->spr_cb[i]; diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, */ rule = float_infzeronan_dnan_never; } -#elif defined(TARGET_PPC) || defined(TARGET_SPARC) || \ +#elif defined(TARGET_SPARC) || \ defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' */ - /* - * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer - * to return an input NaN if we have one (ie c) rather than generating - * a default NaN - */ rule = float_infzeronan_dnan_never; #endif } -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the MIPS target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-9-peter.maydell@linaro.org --- target/mips/fpu_helper.h | 9 +++++++++ target/mips/msa.c | 4 ++++ fpu/softfloat-specialize.c.inc | 16 +--------------- 3 files changed, 14 insertions(+), 15 deletions(-) diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/fpu_helper.h +++ b/target/mips/fpu_helper.h @@ -XXX,XX +XXX,XX @@ static inline void restore_flush_mode(CPUMIPSState *env) static inline void restore_snan_bit_mode(CPUMIPSState *env) { bool nan2008 = env->active_fpu.fcr31 & (1 << FCR31_NAN2008); + FloatInfZeroNaNRule izn_rule; /* * With nan2008, SNaNs are silenced in the usual way. @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) */ set_snan_bit_is_one(!nan2008, &env->active_fpu.fp_status); set_default_nan_mode(!nan2008, &env->active_fpu.fp_status); + /* + * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) + * case sets InvalidOp and returns the default NaN. + * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c'. + */ + izn_rule = nan2008 ? float_infzeronan_dnan_never : float_infzeronan_dnan_always; + set_float_infzeronan_rule(izn_rule, &env->active_fpu.fp_status); } static inline void restore_fp_status(CPUMIPSState *env) diff --git a/target/mips/msa.c b/target/mips/msa.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/msa.c +++ b/target/mips/msa.c @@ -XXX,XX +XXX,XX @@ void msa_reset(CPUMIPSState *env) /* set proper signanling bit meaning ("1" means "quiet") */ set_snan_bit_is_one(0, &env->active_tc.msa_fp_status); + + /* Inf * 0 + NaN returns the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, + &env->active_tc.msa_fp_status); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_MIPS) - if (snan_bit_is_one(status)) { - /* - * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) - * case sets InvalidOp and returns the default NaN - */ - rule = float_infzeronan_dnan_always; - } else { - /* - * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ - rule = float_infzeronan_dnan_never; - } -#elif defined(TARGET_SPARC) || \ +#if defined(TARGET_SPARC) || \ defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the SPARC target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-10-peter.maydell@linaro.org --- target/sparc/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp) * the CPU state struct so it won't get zeroed on reset. */ set_float_2nan_prop_rule(float_2nan_prop_s_ba, &env->fp_status); + /* For inf * 0 + NaN, return the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); cpu_exec_realizefn(cs, &local_err); if (local_err != NULL) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_SPARC) || \ - defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ +#if defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the xtensa target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-11-peter.maydell@linaro.org --- target/xtensa/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_reset_hold(Object *obj, ResetType type) reset_mmu(env); cs->halted = env->runstall; #endif + /* For inf * 0 + NaN, return the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_no_signaling_nans(!dfpu, &env->fp_status); xtensa_use_first_nan(env, !dfpu); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ +#if defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the x86 target. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-12-peter.maydell@linaro.org --- target/i386/tcg/fpu_helper.c | 7 +++++++ fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void cpu_init_fp_statuses(CPUX86State *env) */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->mmx_status); set_float_2nan_prop_rule(float_2nan_prop_x87, &env->sse_status); + /* + * Only SSE has multiply-add instructions. In the SDM Section 14.5.2 + * "Fused-Multiply-ADD (FMA) Numeric Behavior" the NaN handling is + * specified -- for 0 * inf + NaN the input NaN is selected, and if + * there are multiple input NaNs they are selected in the order a, b, c. + */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->sse_status); } static inline uint8_t save_exception_flags(CPUX86State *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * Temporarily fall back to ifdef ladder */ #if defined(TARGET_HPPA) || \ - defined(TARGET_I386) || defined(TARGET_LOONGARCH) + defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the loongarch target. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-13-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 5 +++++ fpu/softfloat-specialize.c.inc | 7 +------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void restore_fp_status(CPULoongArchState *env) &env->fp_status); set_flush_to_zero(0, &env->fp_status); set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status); + /* + * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c' + */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); } int ieee_ex_to_loongarch(int xcpt) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_HPPA) || \ - defined(TARGET_LOONGARCH) - /* - * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ +#if defined(TARGET_HPPA) rule = float_infzeronan_dnan_never; #endif } -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the HPPA target, so we can remove the ifdef from pickNaNMulAdd(). As this is the last target to be converted to explicitly setting the rule, we can remove the fallback code in pickNaNMulAdd() entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-14-peter.maydell@linaro.org --- target/hppa/fpu_helper.c | 2 ++ fpu/softfloat-specialize.c.inc | 13 +------------ 2 files changed, 3 insertions(+), 12 deletions(-) diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/fpu_helper.c +++ b/target/hppa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(loaded_fr0)(CPUHPPAState *env) * HPPA does note implement a CPU reset method at all... */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status); + /* For inf * 0 + NaN, return the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); } void cpu_hppa_loaded_fr0(CPUHPPAState *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, float_status *status) { - FloatInfZeroNaNRule rule = status->float_infzeronan_rule; - /* * We guarantee not to require the target to tell us how to * pick a NaN if we're always returning the default NaN. @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, */ assert(!status->default_nan_mode); - if (rule == float_infzeronan_none) { - /* - * Temporarily fall back to ifdef ladder - */ -#if defined(TARGET_HPPA) - rule = float_infzeronan_dnan_never; -#endif - } - if (infzero) { /* * Inf * 0 + NaN -- some implementations return the default NaN here, * and some return the input NaN. */ - switch (rule) { + switch (status->float_infzeronan_rule) { case float_infzeronan_dnan_never: return 2; case float_infzeronan_dnan_always: -- 2.34.1 The new implementation of pickNaNMulAdd() will find it convenient to know whether at least one of the three arguments to the muladd was a signaling NaN. We already calculate that in the caller, so pass it in as a new bool have_snan. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-15-peter.maydell@linaro.org --- fpu/softfloat-parts.c.inc | 5 +++-- fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, { int which; bool infzero = (ab_mask == float_cmask_infzero); + bool have_snan = (abc_mask & float_cmask_snan); - if (unlikely(abc_mask & float_cmask_snan)) { + if (unlikely(have_snan)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); } @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, if (s->default_nan_mode) { which = 3; } else { - which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); + which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, have_snan, s); } if (which == 3) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, | Return values : 0 : a; 1 : b; 2 : c; 3 : default-NaN *----------------------------------------------------------------------------*/ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, - bool infzero, float_status *status) + bool infzero, bool have_snan, float_status *status) { /* * We guarantee not to require the target to tell us how to -- 2.34.1 IEEE 758 does not define a fixed rule for which NaN to pick as the result if both operands of a 3-operand fused multiply-add operation are NaNs. As a result different architectures have ended up with different rules for propagating NaNs. QEMU currently hardcodes the NaN propagation logic into the binary because pickNaNMulAdd() has an ifdef ladder for different targets. We want to make the propagation rule instead be selectable at runtime, because: * this will let us have multiple targets in one QEMU binary * the Arm FEAT_AFP architectural feature includes letting the guest select a NaN propagation rule at runtime In this commit we add an enum for the propagation rule, the field in float_status, and the corresponding getters and setters. We change pickNaNMulAdd to honour this, but because all targets still leave this field at its default 0 value, the fallback logic will pick the rule type with the old ifdef ladder. It's valid not to set a propagation rule if default_nan_mode is enabled, because in that case there's no need to pick a NaN; all the callers of pickNaNMulAdd() catch this case and skip calling it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-16-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 11 +++ include/fpu/softfloat-types.h | 55 +++++++++++ fpu/softfloat-specialize.c.inc | 167 ++++++++------------------------ 3 files changed, 107 insertions(+), 126 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_float_2nan_prop_rule(Float2NaNPropRule rule, status->float_2nan_prop_rule = rule; } +static inline void set_float_3nan_prop_rule(Float3NaNPropRule rule, + float_status *status) +{ + status->float_3nan_prop_rule = rule; +} + static inline void set_float_infzeronan_rule(FloatInfZeroNaNRule rule, float_status *status) { @@ -XXX,XX +XXX,XX @@ static inline Float2NaNPropRule get_float_2nan_prop_rule(float_status *status) return status->float_2nan_prop_rule; } +static inline Float3NaNPropRule get_float_3nan_prop_rule(float_status *status) +{ + return status->float_3nan_prop_rule; +} + static inline FloatInfZeroNaNRule get_float_infzeronan_rule(float_status *status) { return status->float_infzeronan_rule; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ this code that are retained. #ifndef SOFTFLOAT_TYPES_H #define SOFTFLOAT_TYPES_H +#include "hw/registerfields.h" + /* * Software IEC/IEEE floating-point types. */ @@ -XXX,XX +XXX,XX @@ typedef enum __attribute__((__packed__)) { float_2nan_prop_x87, } Float2NaNPropRule; +/* + * 3-input NaN propagation rule, for fused multiply-add. Individual + * architectures have different rules for which input NaN is + * propagated to the output when there is more than one NaN on the + * input. + * + * If default_nan_mode is enabled then it is valid not to set a NaN + * propagation rule, because the softfloat code guarantees not to try + * to pick a NaN to propagate in default NaN mode. When not in + * default-NaN mode, it is an error for the target not to set the rule + * in float_status if it uses a muladd, and we will assert if we need + * to handle an input NaN and no rule was selected. + * + * The naming scheme for Float3NaNPropRule values is: + * float_3nan_prop_s_abc: + * = "Prefer SNaN over QNaN, then operand A over B over C" + * float_3nan_prop_abc: + * = "Prefer A over B over C regardless of SNaN vs QNAN" + * + * For QEMU, the multiply-add operation is A * B + C. + */ + +/* + * We set the Float3NaNPropRule enum values up so we can select the + * right value in pickNaNMulAdd in a data driven way. + */ +FIELD(3NAN, 1ST, 0, 2) /* which operand is most preferred ? */ +FIELD(3NAN, 2ND, 2, 2) /* which operand is next most preferred ? */ +FIELD(3NAN, 3RD, 4, 2) /* which operand is least preferred ? */ +FIELD(3NAN, SNAN, 6, 1) /* do we prefer SNaN over QNaN ? */ + +#define PROPRULE(X, Y, Z) \ + ((X << R_3NAN_1ST_SHIFT) | (Y << R_3NAN_2ND_SHIFT) | (Z << R_3NAN_3RD_SHIFT)) + +typedef enum __attribute__((__packed__)) { + float_3nan_prop_none = 0, /* No propagation rule specified */ + float_3nan_prop_abc = PROPRULE(0, 1, 2), + float_3nan_prop_acb = PROPRULE(0, 2, 1), + float_3nan_prop_bac = PROPRULE(1, 0, 2), + float_3nan_prop_bca = PROPRULE(1, 2, 0), + float_3nan_prop_cab = PROPRULE(2, 0, 1), + float_3nan_prop_cba = PROPRULE(2, 1, 0), + float_3nan_prop_s_abc = float_3nan_prop_abc | R_3NAN_SNAN_MASK, + float_3nan_prop_s_acb = float_3nan_prop_acb | R_3NAN_SNAN_MASK, + float_3nan_prop_s_bac = float_3nan_prop_bac | R_3NAN_SNAN_MASK, + float_3nan_prop_s_bca = float_3nan_prop_bca | R_3NAN_SNAN_MASK, + float_3nan_prop_s_cab = float_3nan_prop_cab | R_3NAN_SNAN_MASK, + float_3nan_prop_s_cba = float_3nan_prop_cba | R_3NAN_SNAN_MASK, +} Float3NaNPropRule; + +#undef PROPRULE + /* * Rule for result of fused multiply-add 0 * Inf + NaN. * This must be a NaN, but implementations differ on whether this @@ -XXX,XX +XXX,XX @@ typedef struct float_status { FloatRoundMode float_rounding_mode; FloatX80RoundPrec floatx80_rounding_precision; Float2NaNPropRule float_2nan_prop_rule; + Float3NaNPropRule float_3nan_prop_rule; FloatInfZeroNaNRule float_infzeronan_rule; bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, bool have_snan, float_status *status) { + FloatClass cls[3] = { a_cls, b_cls, c_cls }; + Float3NaNPropRule rule = status->float_3nan_prop_rule; + int which; + /* * We guarantee not to require the target to tell us how to * pick a NaN if we're always returning the default NaN. @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } } + if (rule == float_3nan_prop_none) { #if defined(TARGET_ARM) - - /* This looks different from the ARM ARM pseudocode, because the ARM ARM - * puts the operands to a fused mac operation (a*b)+c in the order c,a,b. - */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } + /* + * This looks different from the ARM ARM pseudocode, because the ARM ARM + * puts the operands to a fused mac operation (a*b)+c in the order c,a,b + */ + rule = float_3nan_prop_s_cab; #elif defined(TARGET_MIPS) - if (snan_bit_is_one(status)) { - /* Prefer sNaN over qNaN, in the a, b, c order. */ - if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_snan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else if (is_qnan(b_cls)) { - return 1; + if (snan_bit_is_one(status)) { + rule = float_3nan_prop_s_abc; } else { - return 2; + rule = float_3nan_prop_s_cab; } - } else { - /* Prefer sNaN over qNaN, in the c, a, b order. */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } - } #elif defined(TARGET_LOONGARCH64) - /* Prefer sNaN over qNaN, in the c, a, b order. */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } + rule = float_3nan_prop_s_cab; #elif defined(TARGET_PPC) - /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; - * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB - */ - if (is_nan(a_cls)) { - return 0; - } else if (is_nan(c_cls)) { - return 2; - } else { - return 1; - } + /* + * If fRA is a NaN return it; otherwise if fRB is a NaN return it; + * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB + */ + rule = float_3nan_prop_acb; #elif defined(TARGET_S390X) - if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_snan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else if (is_qnan(b_cls)) { - return 1; - } else { - return 2; - } + rule = float_3nan_prop_s_abc; #elif defined(TARGET_SPARC) - /* Prefer SNaN over QNaN, order C, B, A. */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(b_cls)) { - return 1; - } else { - return 0; - } + rule = float_3nan_prop_s_cba; #elif defined(TARGET_XTENSA) - /* - * For Xtensa, the (inf,zero,nan) case sets InvalidOp and returns - * an input NaN if we have one (ie c). - */ - if (status->use_first_nan) { - if (is_nan(a_cls)) { - return 0; - } else if (is_nan(b_cls)) { - return 1; + if (status->use_first_nan) { + rule = float_3nan_prop_abc; } else { - return 2; + rule = float_3nan_prop_cba; } - } else { - if (is_nan(c_cls)) { - return 2; - } else if (is_nan(b_cls)) { - return 1; - } else { - return 0; - } - } #else - /* A default implementation: prefer a to b to c. - * This is unlikely to actually match any real implementation. - */ - if (is_nan(a_cls)) { - return 0; - } else if (is_nan(b_cls)) { - return 1; - } else { - return 2; - } + rule = float_3nan_prop_abc; #endif + } + + assert(rule != float_3nan_prop_none); + if (have_snan && (rule & R_3NAN_SNAN_MASK)) { + /* We have at least one SNaN input and should prefer it */ + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_snan(cls[which])); + } else { + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_nan(cls[which])); + } + return which; } /*---------------------------------------------------------------------------- -- 2.34.1 Explicitly set a rule in the softfloat tests for propagating NaNs in the muladd case. In meson.build we put -DTARGET_ARM in fpcflags, and so we should select here the Arm rule of float_3nan_prop_s_cab. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-17-peter.maydell@linaro.org --- tests/fp/fp-bench.c | 1 + tests/fp/fp-test.c | 1 + 2 files changed, 2 insertions(+) diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-bench.c +++ b/tests/fp/fp-bench.c @@ -XXX,XX +XXX,XX @@ static void run_bench(void) * doesn't specify match those used by the Arm architecture. */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, &soft_status); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &soft_status); f = bench_funcs[operation][precision]; diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -XXX,XX +XXX,XX @@ void run_test(void) * doesn't specify match those used by the Arm architecture. */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, &qsf); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &qsf); genCases_setLevel(test_level); -- 2.34.1 Set the Float3NaNPropRule explicitly for Arm, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-18-peter.maydell@linaro.org --- target/arm/cpu.c | 5 +++++ fpu/softfloat-specialize.c.inc | 8 +------- 2 files changed, 6 insertions(+), 7 deletions(-) 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 @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, * * tininess-before-rounding * * 2-input NaN propagation prefers SNaN over QNaN, and then * operand A over operand B (see FPProcessNaNs() pseudocode) + * * 3-input NaN propagation prefers SNaN over QNaN, and then + * operand C over A over B (see FPProcessNaNs3() pseudocode, + * but note that for QEMU muladd is a * b + c, whereas for + * the pseudocode function the arguments are in the order c, a, b. * * 0 * Inf + NaN returns the default NaN if the input NaN is quiet, * and the input NaN if it is signalling */ @@ -XXX,XX +XXX,XX @@ static void arm_set_default_fp_behaviours(float_status *s) { set_float_detect_tininess(float_tininess_before_rounding, s); set_float_2nan_prop_rule(float_2nan_prop_s_ab, s); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, s); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, s); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } if (rule == float_3nan_prop_none) { -#if defined(TARGET_ARM) - /* - * This looks different from the ARM ARM pseudocode, because the ARM ARM - * puts the operands to a fused mac operation (a*b)+c in the order c,a,b - */ - rule = float_3nan_prop_s_cab; -#elif defined(TARGET_MIPS) +#if defined(TARGET_MIPS) if (snan_bit_is_one(status)) { rule = float_3nan_prop_s_abc; } else { -- 2.34.1 Set the Float3NaNPropRule explicitly for loongarch, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-19-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 1 + fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void restore_fp_status(CPULoongArchState *env) * case sets InvalidOp and returns the input value 'c' */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, &env->fp_status); } int ieee_ex_to_loongarch(int xcpt) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_LOONGARCH64) - rule = float_3nan_prop_s_cab; #elif defined(TARGET_PPC) /* * If fRA is a NaN return it; otherwise if fRB is a NaN return it; -- 2.34.1 Set the Float3NaNPropRule explicitly for PPC, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-20-peter.maydell@linaro.org --- target/ppc/cpu_init.c | 8 ++++++++ fpu/softfloat-specialize.c.inc | 6 ------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type) */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); set_float_2nan_prop_rule(float_2nan_prop_ab, &env->vec_status); + /* + * NaN propagation for fused multiply-add: + * if fRA is a NaN return it; otherwise if fRB is a NaN return it; + * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB + * whereas QEMU labels the operands as (a * b) + c. + */ + set_float_3nan_prop_rule(float_3nan_prop_acb, &env->fp_status); + set_float_3nan_prop_rule(float_3nan_prop_acb, &env->vec_status); /* * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer * to return an input NaN if we have one (ie c) rather than generating diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_PPC) - /* - * If fRA is a NaN return it; otherwise if fRB is a NaN return it; - * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB - */ - rule = float_3nan_prop_acb; #elif defined(TARGET_S390X) rule = float_3nan_prop_s_abc; #elif defined(TARGET_SPARC) -- 2.34.1 Set the Float3NaNPropRule explicitly for s390x, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-21-peter.maydell@linaro.org --- target/s390x/cpu.c | 1 + fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset_hold(Object *obj, ResetType type) set_float_detect_tininess(float_tininess_before_rounding, &env->fpu_status); set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fpu_status); + set_float_3nan_prop_rule(float_3nan_prop_s_abc, &env->fpu_status); set_float_infzeronan_rule(float_infzeronan_dnan_always, &env->fpu_status); /* fall through */ diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_S390X) - rule = float_3nan_prop_s_abc; #elif defined(TARGET_SPARC) rule = float_3nan_prop_s_cba; #elif defined(TARGET_XTENSA) -- 2.34.1 Set the Float3NaNPropRule explicitly for SPARC, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-22-peter.maydell@linaro.org --- target/sparc/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp) * the CPU state struct so it won't get zeroed on reset. */ set_float_2nan_prop_rule(float_2nan_prop_s_ba, &env->fp_status); + /* For fused-multiply add, prefer SNaN over QNaN, then C->B->A */ + set_float_3nan_prop_rule(float_3nan_prop_s_cba, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_SPARC) - rule = float_3nan_prop_s_cba; #elif defined(TARGET_XTENSA) if (status->use_first_nan) { rule = float_3nan_prop_abc; -- 2.34.1 Set the Float3NaNPropRule explicitly for Arm, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-23-peter.maydell@linaro.org --- target/mips/fpu_helper.h | 4 ++++ target/mips/msa.c | 3 +++ fpu/softfloat-specialize.c.inc | 8 +------- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/fpu_helper.h +++ b/target/mips/fpu_helper.h @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) { bool nan2008 = env->active_fpu.fcr31 & (1 << FCR31_NAN2008); FloatInfZeroNaNRule izn_rule; + Float3NaNPropRule nan3_rule; /* * With nan2008, SNaNs are silenced in the usual way. @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) */ izn_rule = nan2008 ? float_infzeronan_dnan_never : float_infzeronan_dnan_always; set_float_infzeronan_rule(izn_rule, &env->active_fpu.fp_status); + nan3_rule = nan2008 ? float_3nan_prop_s_cab : float_3nan_prop_s_abc; + set_float_3nan_prop_rule(nan3_rule, &env->active_fpu.fp_status); + } static inline void restore_fp_status(CPUMIPSState *env) diff --git a/target/mips/msa.c b/target/mips/msa.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/msa.c +++ b/target/mips/msa.c @@ -XXX,XX +XXX,XX @@ void msa_reset(CPUMIPSState *env) set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->active_tc.msa_fp_status); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, + &env->active_tc.msa_fp_status); + /* clear float_status exception flags */ set_float_exception_flags(0, &env->active_tc.msa_fp_status); diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } if (rule == float_3nan_prop_none) { -#if defined(TARGET_MIPS) - if (snan_bit_is_one(status)) { - rule = float_3nan_prop_s_abc; - } else { - rule = float_3nan_prop_s_cab; - } -#elif defined(TARGET_XTENSA) +#if defined(TARGET_XTENSA) if (status->use_first_nan) { rule = float_3nan_prop_abc; } else { -- 2.34.1 Set the Float3NaNPropRule explicitly for xtensa, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-24-peter.maydell@linaro.org --- target/xtensa/fpu_helper.c | 2 ++ fpu/softfloat-specialize.c.inc | 8 -------- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/target/xtensa/fpu_helper.c b/target/xtensa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/fpu_helper.c +++ b/target/xtensa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void xtensa_use_first_nan(CPUXtensaState *env, bool use_first) set_use_first_nan(use_first, &env->fp_status); set_float_2nan_prop_rule(use_first ? float_2nan_prop_ab : float_2nan_prop_ba, &env->fp_status); + set_float_3nan_prop_rule(use_first ? float_3nan_prop_abc : float_3nan_prop_cba, + &env->fp_status); } void HELPER(wur_fpu2k_fcr)(CPUXtensaState *env, uint32_t v) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } if (rule == float_3nan_prop_none) { -#if defined(TARGET_XTENSA) - if (status->use_first_nan) { - rule = float_3nan_prop_abc; - } else { - rule = float_3nan_prop_cba; - } -#else rule = float_3nan_prop_abc; -#endif } assert(rule != float_3nan_prop_none); -- 2.34.1 Set the Float3NaNPropRule explicitly for i386. We had no i386-specific behaviour in the old ifdef ladder, so we were using the default "prefer a then b then c" fallback; this is actually the correct per-the-spec handling for i386. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-25-peter.maydell@linaro.org --- target/i386/tcg/fpu_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void cpu_init_fp_statuses(CPUX86State *env) * there are multiple input NaNs they are selected in the order a, b, c. */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->sse_status); + set_float_3nan_prop_rule(float_3nan_prop_abc, &env->sse_status); } static inline uint8_t save_exception_flags(CPUX86State *env) -- 2.34.1 Set the Float3NaNPropRule explicitly for HPPA, and remove the ifdef from pickNaNMulAdd(). HPPA is the only target that was using the default branch of the ifdef ladder (other targets either do not use muladd or set default_nan_mode), so we can remove the ifdef fallback entirely now (allowing the "rule not set" case to fall into the default of the switch statement and assert). We add a TODO note that the HPPA rule is probably wrong; this is not a behavioural change for this refactoring. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-26-peter.maydell@linaro.org --- target/hppa/fpu_helper.c | 8 ++++++++ fpu/softfloat-specialize.c.inc | 4 ---- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/fpu_helper.c +++ b/target/hppa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(loaded_fr0)(CPUHPPAState *env) * HPPA does note implement a CPU reset method at all... */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status); + /* + * TODO: The HPPA architecture reference only documents its NaN + * propagation rule for 2-operand operations. Testing on real hardware + * might be necessary to confirm whether this order for muladd is correct. + * Not preferring the SNaN is almost certainly incorrect as it diverges + * from the documented rules for 2-operand operations. + */ + set_float_3nan_prop_rule(float_3nan_prop_abc, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } } - if (rule == float_3nan_prop_none) { - rule = float_3nan_prop_abc; - } - assert(rule != float_3nan_prop_none); if (have_snan && (rule & R_3NAN_SNAN_MASK)) { /* We have at least one SNaN input and should prefer it */ -- 2.34.1 The use_first_nan field in float_status was an xtensa-specific way to select at runtime from two different NaN propagation rules. Now that xtensa is using the target-agnostic NaN propagation rule selection that we've just added, we can remove use_first_nan, because there is no longer any code that reads it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-27-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 5 ----- include/fpu/softfloat-types.h | 1 - target/xtensa/fpu_helper.c | 1 - 3 files changed, 7 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_snan_bit_is_one(bool val, float_status *status) status->snan_bit_is_one = val; } -static inline void set_use_first_nan(bool val, float_status *status) -{ - status->use_first_nan = val; -} - static inline void set_no_signaling_nans(bool val, float_status *status) { status->no_signaling_nans = val; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef struct float_status { * softfloat-specialize.inc.c) */ bool snan_bit_is_one; - bool use_first_nan; bool no_signaling_nans; /* should overflowed results subtract re_bias to its exponent? */ bool rebias_overflow; diff --git a/target/xtensa/fpu_helper.c b/target/xtensa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/fpu_helper.c +++ b/target/xtensa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ static const struct { void xtensa_use_first_nan(CPUXtensaState *env, bool use_first) { - set_use_first_nan(use_first, &env->fp_status); set_float_2nan_prop_rule(use_first ? float_2nan_prop_ab : float_2nan_prop_ba, &env->fp_status); set_float_3nan_prop_rule(use_first ? float_3nan_prop_abc : float_3nan_prop_cba, -- 2.34.1 Currently m68k_cpu_reset_hold() calls floatx80_default_nan(NULL) to get the NaN bit pattern to reset the FPU registers. This works because it happens that our implementation of floatx80_default_nan() doesn't actually look at the float_status pointer except for TARGET_MIPS. However, this isn't guaranteed, and to be able to remove the ifdef in floatx80_default_nan() we're going to need a real float_status here. Rearrange m68k_cpu_reset_hold() so that we initialize env->fp_status earlier, and thus can pass it to floatx80_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-28-peter.maydell@linaro.org --- target/m68k/cpu.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) CPUState *cs = CPU(obj); M68kCPUClass *mcc = M68K_CPU_GET_CLASS(obj); CPUM68KState *env = cpu_env(cs); - floatx80 nan = floatx80_default_nan(NULL); + floatx80 nan; int i; if (mcc->parent_phases.hold) { @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) #else cpu_m68k_set_sr(env, SR_S | SR_I); #endif - for (i = 0; i < 8; i++) { - env->fregs[i].d = nan; - } - cpu_m68k_set_fpcr(env, 0); /* * M68000 FAMILY PROGRAMMER'S REFERENCE MANUAL * 3.4 FLOATING-POINT INSTRUCTION DETAILS @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) * preceding paragraph for nonsignaling NaNs. */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); + + nan = floatx80_default_nan(&env->fp_status); + for (i = 0; i < 8; i++) { + env->fregs[i].d = nan; + } + cpu_m68k_set_fpcr(env, 0); env->fpsr = 0; /* TODO: We should set PC from the interrupt vector. */ -- 2.34.1 We create our 128-bit default NaN by calling parts64_default_nan() and then adjusting the result. We can do the same trick for creating the floatx80 default NaN, which lets us drop a target ifdef. floatx80 is used only by: i386 m68k arm nwfpe old floating-point emulation emulation support (which is essentially dead, especially the parts involving floatx80) PPC (only in the xsrqpxp instruction, which just rounds an input value by converting to floatx80 and back, so will never generate the default NaN) The floatx80 default NaN as currently implemented is: m68k: sign = 0, exp = 1...1, int = 1, frac = 1....1 i386: sign = 1, exp = 1...1, int = 1, frac = 10...0 These are the same as the parts64_default_nan for these architectures. This is technically a possible behaviour change for arm linux-user nwfpe emulation emulation, because the default NaN will now have the sign bit clear. But we were already generating a different floatx80 default NaN from the real kernel emulation we are supposedly following, which appears to use an all-bits-1 value: https://elixir.bootlin.com/linux/v6.12/source/arch/arm/nwfpe/softfloat-specialize#L267 This won't affect the only "real" use of the nwfpe emulation, which is ancient binaries that used it as part of the old floating point calling convention; that only uses loads and stores of 32 and 64 bit floats, not any of the floatx80 behaviour the original hardware had. We also get the nwfpe float64 default NaN value wrong: https://elixir.bootlin.com/linux/v6.12/source/arch/arm/nwfpe/softfloat-specialize#L166 so if we ever cared about this obscure corner the right fix would be to correct that so nwfpe used its own default-NaN setting rather than the Arm VFP one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-29-peter.maydell@linaro.org --- fpu/softfloat-specialize.c.inc | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts128_silence_nan(FloatParts128 *p, float_status *status) floatx80 floatx80_default_nan(float_status *status) { floatx80 r; + /* + * Extrapolate from the choices made by parts64_default_nan to fill + * in the floatx80 format. We assume that floatx80's explicit + * integer bit is always set (this is true for i386 and m68k, + * which are the only real users of this format). + */ + FloatParts64 p64; + parts64_default_nan(&p64, status); - /* None of the targets that have snan_bit_is_one use floatx80. */ - assert(!snan_bit_is_one(status)); -#if defined(TARGET_M68K) - r.low = UINT64_C(0xFFFFFFFFFFFFFFFF); - r.high = 0x7FFF; -#else - /* X86 */ - r.low = UINT64_C(0xC000000000000000); - r.high = 0xFFFF; -#endif + r.high = 0x7FFF | (p64.sign << 15); + r.low = (1ULL << DECOMPOSED_BINARY_POINT) | p64.frac; return r; } -- 2.34.1 In target/loongarch's helper_fclass_s() and helper_fclass_d() we pass a zero-initialized float_status struct to float32_is_quiet_nan() and float64_is_quiet_nan(), with the cryptic comment "for snan_bit_is_one". This pattern appears to have been copied from target/riscv, where it is used because the functions there do not have ready access to the CPU state struct. The comment presumably refers to the fact that the main reason the is_quiet_nan() functions want the float_state is because they want to know about the snan_bit_is_one config. In the loongarch helpers, though, we have the CPU state struct to hand. Use the usual env->fp_status here. This avoids our needing to track that we need to update the initializer of the local float_status structs when the core softfloat code adds new options for targets to configure their behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-30-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t helper_fclass_s(CPULoongArchState *env, uint64_t fj) } else if (float32_is_zero_or_denormal(f)) { return sign ? 1 << 4 : 1 << 8; } else if (float32_is_any_nan(f)) { - float_status s = { }; /* for snan_bit_is_one */ - return float32_is_quiet_nan(f, &s) ? 1 << 1 : 1 << 0; + return float32_is_quiet_nan(f, &env->fp_status) ? 1 << 1 : 1 << 0; } else { return sign ? 1 << 3 : 1 << 7; } @@ -XXX,XX +XXX,XX @@ uint64_t helper_fclass_d(CPULoongArchState *env, uint64_t fj) } else if (float64_is_zero_or_denormal(f)) { return sign ? 1 << 4 : 1 << 8; } else if (float64_is_any_nan(f)) { - float_status s = { }; /* for snan_bit_is_one */ - return float64_is_quiet_nan(f, &s) ? 1 << 1 : 1 << 0; + return float64_is_quiet_nan(f, &env->fp_status) ? 1 << 1 : 1 << 0; } else { return sign ? 1 << 3 : 1 << 7; } -- 2.34.1 In the frem helper, we have a local float_status because we want to execute the floatx80_div() with a custom rounding mode. Instead of zero-initializing the local float_status and then having to set it up with the m68k standard behaviour (including the NaN propagation rule and copying the rounding precision from env->fp_status), initialize it as a complete copy of env->fp_status. This will avoid our having to add new code in this function for every new config knob we add to fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-31-peter.maydell@linaro.org --- target/m68k/fpu_helper.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/fpu_helper.c +++ b/target/m68k/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(frem)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) fp_rem = floatx80_rem(val1->d, val0->d, &env->fp_status); if (!floatx80_is_any_nan(fp_rem)) { - float_status fp_status = { }; + /* Use local temporary fp_status to set different rounding mode */ + float_status fp_status = env->fp_status; uint32_t quotient; int sign; /* Calculate quotient directly using round to nearest mode */ - set_float_2nan_prop_rule(float_2nan_prop_ab, &fp_status); set_float_rounding_mode(float_round_nearest_even, &fp_status); - set_floatx80_rounding_precision( - get_floatx80_rounding_precision(&env->fp_status), &fp_status); fp_quot.d = floatx80_div(val1->d, val0->d, &fp_status); sign = extractFloatx80Sign(fp_quot.d); -- 2.34.1 In cf_fpu_gdb_get_reg() and cf_fpu_gdb_set_reg() we do the conversion from float64 to floatx80 using a scratch float_status, because we don't want the conversion to affect the CPU's floating point exception status. Currently we use a zero-initialized float_status. This will get steadily more awkward as we add config knobs to float_status that the target must initialize. Avoid having to add any of that configuration here by instead initializing our local float_status from the env->fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-32-peter.maydell@linaro.org --- target/m68k/helper.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/target/m68k/helper.c b/target/m68k/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/helper.c +++ b/target/m68k/helper.c @@ -XXX,XX +XXX,XX @@ static int cf_fpu_gdb_get_reg(CPUState *cs, GByteArray *mem_buf, int n) CPUM68KState *env = &cpu->env; if (n < 8) { - float_status s = {}; + /* Use scratch float_status so any exceptions don't change CPU state */ + float_status s = env->fp_status; return gdb_get_reg64(mem_buf, floatx80_to_float64(env->fregs[n].d, &s)); } switch (n) { @@ -XXX,XX +XXX,XX @@ static int cf_fpu_gdb_set_reg(CPUState *cs, uint8_t *mem_buf, int n) CPUM68KState *env = &cpu->env; if (n < 8) { - float_status s = {}; + /* Use scratch float_status so any exceptions don't change CPU state */ + float_status s = env->fp_status; env->fregs[n].d = float64_to_floatx80(ldq_be_p(mem_buf), &s); return 8; } -- 2.34.1 In the helper functions flcmps and flcmpd we use a scratch float_status so that we don't change the CPU state if the comparison raises any floating point exception flags. Instead of zero-initializing this scratch float_status, initialize it as a copy of env->fp_status. This avoids the need to explicitly initialize settings like the NaN propagation rule or others we might add to softfloat in future. To do this we need to pass the CPU env pointer in to the helper. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-33-peter.maydell@linaro.org --- target/sparc/helper.h | 4 ++-- target/sparc/fop_helper.c | 8 ++++---- target/sparc/translate.c | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/target/sparc/helper.h b/target/sparc/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/helper.h +++ b/target/sparc/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(fcmpd, TCG_CALL_NO_WG, i32, env, f64, f64) DEF_HELPER_FLAGS_3(fcmped, TCG_CALL_NO_WG, i32, env, f64, f64) DEF_HELPER_FLAGS_3(fcmpq, TCG_CALL_NO_WG, i32, env, i128, i128) DEF_HELPER_FLAGS_3(fcmpeq, TCG_CALL_NO_WG, i32, env, i128, i128) -DEF_HELPER_FLAGS_2(flcmps, TCG_CALL_NO_RWG_SE, i32, f32, f32) -DEF_HELPER_FLAGS_2(flcmpd, TCG_CALL_NO_RWG_SE, i32, f64, f64) +DEF_HELPER_FLAGS_3(flcmps, TCG_CALL_NO_RWG_SE, i32, env, f32, f32) +DEF_HELPER_FLAGS_3(flcmpd, TCG_CALL_NO_RWG_SE, i32, env, f64, f64) DEF_HELPER_2(raise_exception, noreturn, env, int) DEF_HELPER_FLAGS_3(faddd, TCG_CALL_NO_WG, f64, env, f64, f64) diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/fop_helper.c +++ b/target/sparc/fop_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t helper_fcmpeq(CPUSPARCState *env, Int128 src1, Int128 src2) return finish_fcmp(env, r, GETPC()); } -uint32_t helper_flcmps(float32 src1, float32 src2) +uint32_t helper_flcmps(CPUSPARCState *env, float32 src1, float32 src2) { /* * FLCMP never raises an exception nor modifies any FSR fields. * Perform the comparison with a dummy fp environment. */ - float_status discard = { }; + float_status discard = env->fp_status; FloatRelation r; set_float_2nan_prop_rule(float_2nan_prop_s_ba, &discard); @@ -XXX,XX +XXX,XX @@ uint32_t helper_flcmps(float32 src1, float32 src2) g_assert_not_reached(); } -uint32_t helper_flcmpd(float64 src1, float64 src2) +uint32_t helper_flcmpd(CPUSPARCState *env, float64 src1, float64 src2) { - float_status discard = { }; + float_status discard = env->fp_status; FloatRelation r; set_float_2nan_prop_rule(float_2nan_prop_s_ba, &discard); diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_FLCMPs(DisasContext *dc, arg_FLCMPs *a) src1 = gen_load_fpr_F(dc, a->rs1); src2 = gen_load_fpr_F(dc, a->rs2); - gen_helper_flcmps(cpu_fcc[a->cc], src1, src2); + gen_helper_flcmps(cpu_fcc[a->cc], tcg_env, src1, src2); return advance_pc(dc); } @@ -XXX,XX +XXX,XX @@ static bool trans_FLCMPd(DisasContext *dc, arg_FLCMPd *a) src1 = gen_load_fpr_D(dc, a->rs1); src2 = gen_load_fpr_D(dc, a->rs2); - gen_helper_flcmpd(cpu_fcc[a->cc], src1, src2); + gen_helper_flcmpd(cpu_fcc[a->cc], tcg_env, src1, src2); return advance_pc(dc); } -- 2.34.1 In the helper_compute_fprf functions, we pass a dummy float_status in to the is_signaling_nan() function. This is unnecessary, because we have convenient access to the CPU env pointer here and that is already set up with the correct values for the snan_bit_is_one and no_signaling_nans config settings. is_signaling_nan() doesn't ever update the fp_status with any exception flags, so there is no reason not to use env->fp_status here. Use env->fp_status instead of the dummy fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-34-peter.maydell@linaro.org --- target/ppc/fpu_helper.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void helper_compute_fprf_##tp(CPUPPCState *env, tp arg) \ } else if (tp##_is_infinity(arg)) { \ fprf = neg ? 0x09 << FPSCR_FPRF : 0x05 << FPSCR_FPRF; \ } else { \ - float_status dummy = { }; /* snan_bit_is_one = 0 */ \ - if (tp##_is_signaling_nan(arg, &dummy)) { \ + if (tp##_is_signaling_nan(arg, &env->fp_status)) { \ fprf = 0x00 << FPSCR_FPRF; \ } else { \ fprf = 0x11 << FPSCR_FPRF; \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Now that float_status has a bunch of fp parameters, it is easier to copy an existing structure than create one from scratch. Begin by copying the structure that corresponds to the FPSR and make only the adjustments required for BFloat16 semantics. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_helper.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp) * no effect on AArch32 instructions. */ bool ebf = is_a64(env) && env->vfp.fpcr & FPCR_EBF; - *statusp = (float_status){ - .tininess_before_rounding = float_tininess_before_rounding, - .float_rounding_mode = float_round_to_odd_inf, - .flush_to_zero = true, - .flush_inputs_to_zero = true, - .default_nan_mode = true, - }; + + *statusp = env->vfp.fp_status; + set_default_nan_mode(true, statusp); if (ebf) { - float_status *fpst = &env->vfp.fp_status; - set_flush_to_zero(get_flush_to_zero(fpst), statusp); - set_flush_inputs_to_zero(get_flush_inputs_to_zero(fpst), statusp); - set_float_rounding_mode(get_float_rounding_mode(fpst), statusp); - /* EBF=1 needs to do a step with round-to-odd semantics */ *oddstatusp = *statusp; set_float_rounding_mode(float_round_to_odd, oddstatusp); + } else { + set_flush_to_zero(true, statusp); + set_flush_inputs_to_zero(true, statusp); + set_float_rounding_mode(float_round_to_odd_inf, statusp); } - return ebf; } -- 2.34.1 Currently we hardcode the default NaN value in parts64_default_nan() using a compile-time ifdef ladder. This is awkward for two cases: * for single-QEMU-binary we can't hard-code target-specifics like this * for Arm FEAT_AFP the default NaN value depends on FPCR.AH (specifically the sign bit is different) Add a field to float_status to specify the default NaN value; fall back to the old ifdef behaviour if these are not set. The default NaN value is specified by setting a uint8_t to a pattern corresponding to the sign and upper fraction parts of the NaN; the lower bits of the fraction are set from bit 0 of the pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-35-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 11 +++++++ include/fpu/softfloat-types.h | 10 ++++++ fpu/softfloat-specialize.c.inc | 55 ++++++++++++++++++++------------- 3 files changed, 54 insertions(+), 22 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_float_infzeronan_rule(FloatInfZeroNaNRule rule, status->float_infzeronan_rule = rule; } +static inline void set_float_default_nan_pattern(uint8_t dnan_pattern, + float_status *status) +{ + status->default_nan_pattern = dnan_pattern; +} + static inline void set_flush_to_zero(bool val, float_status *status) { status->flush_to_zero = val; @@ -XXX,XX +XXX,XX @@ static inline FloatInfZeroNaNRule get_float_infzeronan_rule(float_status *status return status->float_infzeronan_rule; } +static inline uint8_t get_float_default_nan_pattern(float_status *status) +{ + return status->default_nan_pattern; +} + static inline bool get_flush_to_zero(float_status *status) { return status->flush_to_zero; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef struct float_status { /* should denormalised inputs go to zero and set the input_denormal flag? */ bool flush_inputs_to_zero; bool default_nan_mode; + /* + * The pattern to use for the default NaN. Here the high bit specifies + * the default NaN's sign bit, and bits 6..0 specify the high bits of the + * fractional part. The low bits of the fractional part are copies of bit 0. + * The exponent of the default NaN is (as for any NaN) always all 1s. + * Note that a value of 0 here is not a valid NaN. The target must set + * this to the correct non-zero value, or we will assert when trying to + * create a default NaN. + */ + uint8_t default_nan_pattern; /* * The flags below are not used on all specializations and may * constant fold away (see snan_bit_is_one()/no_signalling_nans() in diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) { bool sign = 0; uint64_t frac; + uint8_t dnan_pattern = status->default_nan_pattern; + if (dnan_pattern == 0) { #if defined(TARGET_SPARC) || defined(TARGET_M68K) - /* !snan_bit_is_one, set all bits */ - frac = (1ULL << DECOMPOSED_BINARY_POINT) - 1; -#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ + /* Sign bit clear, all frac bits set */ + dnan_pattern = 0b01111111; +#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ || defined(TARGET_MICROBLAZE) - /* !snan_bit_is_one, set sign and msb */ - frac = 1ULL << (DECOMPOSED_BINARY_POINT - 1); - sign = 1; + /* Sign bit set, most significant frac bit set */ + dnan_pattern = 0b11000000; #elif defined(TARGET_HPPA) - /* snan_bit_is_one, set msb-1. */ - frac = 1ULL << (DECOMPOSED_BINARY_POINT - 2); + /* Sign bit clear, msb-1 frac bit set */ + dnan_pattern = 0b00100000; #elif defined(TARGET_HEXAGON) - sign = 1; - frac = ~0ULL; + /* Sign bit set, all frac bits set. */ + dnan_pattern = 0b11111111; #else - /* - * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, - * S390, SH4, TriCore, and Xtensa. Our other supported targets - * do not have floating-point. - */ - if (snan_bit_is_one(status)) { - /* set all bits other than msb */ - frac = (1ULL << (DECOMPOSED_BINARY_POINT - 1)) - 1; - } else { - /* set msb */ - frac = 1ULL << (DECOMPOSED_BINARY_POINT - 1); - } + /* + * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, + * S390, SH4, TriCore, and Xtensa. Our other supported targets + * do not have floating-point. + */ + if (snan_bit_is_one(status)) { + /* sign bit clear, set all frac bits other than msb */ + dnan_pattern = 0b00111111; + } else { + /* sign bit clear, set frac msb */ + dnan_pattern = 0b01000000; + } #endif + } + assert(dnan_pattern != 0); + + sign = dnan_pattern >> 7; + /* + * Place default_nan_pattern [6:0] into bits [62:56], + * and replecate bit [0] down into [55:0] + */ + frac = deposit64(0, DECOMPOSED_BINARY_POINT - 7, 7, dnan_pattern); + frac = deposit64(frac, 0, DECOMPOSED_BINARY_POINT - 7, -(dnan_pattern & 1)); *p = (FloatParts64) { .cls = float_class_qnan, -- 2.34.1 Set the default NaN pattern explicitly for the tests/fp code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-36-peter.maydell@linaro.org --- tests/fp/fp-bench.c | 1 + tests/fp/fp-test-log2.c | 1 + tests/fp/fp-test.c | 1 + 3 files changed, 3 insertions(+) diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-bench.c +++ b/tests/fp/fp-bench.c @@ -XXX,XX +XXX,XX @@ static void run_bench(void) set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status); set_float_3nan_prop_rule(float_3nan_prop_s_cab, &soft_status); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &soft_status); + set_float_default_nan_pattern(0b01000000, &soft_status); f = bench_funcs[operation][precision]; g_assert(f); diff --git a/tests/fp/fp-test-log2.c b/tests/fp/fp-test-log2.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test-log2.c +++ b/tests/fp/fp-test-log2.c @@ -XXX,XX +XXX,XX @@ int main(int ac, char **av) int i; set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); + set_float_default_nan_pattern(0b01000000, &qsf); set_float_rounding_mode(float_round_nearest_even, &qsf); test.d = 0.0; diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -XXX,XX +XXX,XX @@ void run_test(void) */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); set_float_3nan_prop_rule(float_3nan_prop_s_cab, &qsf); + set_float_default_nan_pattern(0b01000000, &qsf); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &qsf); genCases_setLevel(test_level); -- 2.34.1 Set the default NaN pattern explicitly, and remove the ifdef from parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-37-peter.maydell@linaro.org --- target/microblaze/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -XXX,XX +XXX,XX @@ static void mb_cpu_reset_hold(Object *obj, ResetType type) * this architecture. */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status); + /* Default NaN: sign bit set, most significant frac bit set */ + set_float_default_nan_pattern(0b11000000, &env->fp_status); #if defined(CONFIG_USER_ONLY) /* start in user mode with interrupts enabled. */ diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) #if defined(TARGET_SPARC) || defined(TARGET_M68K) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; -#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ - || defined(TARGET_MICROBLAZE) +#elif defined(TARGET_I386) || defined(TARGET_X86_64) /* Sign bit set, most significant frac bit set */ dnan_pattern = 0b11000000; #elif defined(TARGET_HPPA) -- 2.34.1 Set the default NaN pattern explicitly, and remove the ifdef from parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-38-peter.maydell@linaro.org --- target/i386/tcg/fpu_helper.c | 4 ++++ fpu/softfloat-specialize.c.inc | 3 --- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void cpu_init_fp_statuses(CPUX86State *env) */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->sse_status); set_float_3nan_prop_rule(float_3nan_prop_abc, &env->sse_status); + /* Default NaN: sign bit set, most significant frac bit set */ + set_float_default_nan_pattern(0b11000000, &env->fp_status); + set_float_default_nan_pattern(0b11000000, &env->mmx_status); + set_float_default_nan_pattern(0b11000000, &env->sse_status); } static inline uint8_t save_exception_flags(CPUX86State *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) #if defined(TARGET_SPARC) || defined(TARGET_M68K) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; -#elif defined(TARGET_I386) || defined(TARGET_X86_64) - /* Sign bit set, most significant frac bit set */ - dnan_pattern = 0b11000000; #elif defined(TARGET_HPPA) /* Sign bit clear, msb-1 frac bit set */ dnan_pattern = 0b00100000; -- 2.34.1 Set the default NaN pattern explicitly, and remove the ifdef from parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-39-peter.maydell@linaro.org --- target/hppa/fpu_helper.c | 2 ++ fpu/softfloat-specialize.c.inc | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/fpu_helper.c +++ b/target/hppa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(loaded_fr0)(CPUHPPAState *env) set_float_3nan_prop_rule(float_3nan_prop_abc, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + /* Default NaN: sign bit clear, msb-1 frac bit set */ + set_float_default_nan_pattern(0b00100000, &env->fp_status); } void cpu_hppa_loaded_fr0(CPUHPPAState *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) #if defined(TARGET_SPARC) || defined(TARGET_M68K) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; -#elif defined(TARGET_HPPA) - /* Sign bit clear, msb-1 frac bit set */ - dnan_pattern = 0b00100000; #elif defined(TARGET_HEXAGON) /* Sign bit set, all frac bits set. */ dnan_pattern = 0b11111111; -- 2.34.1 Set the default NaN pattern explicitly for the alpha target. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-40-peter.maydell@linaro.org --- target/alpha/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/cpu.c +++ b/target/alpha/cpu.c @@ -XXX,XX +XXX,XX @@ static void alpha_cpu_initfn(Object *obj) * operand in Fa. That is float_2nan_prop_ba. */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status); + /* Default NaN: sign bit clear, msb frac bit set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); #if defined(CONFIG_USER_ONLY) env->flags = ENV_FLAG_PS_USER | ENV_FLAG_FEN; cpu_alpha_store_fpcr(env, (uint64_t)(FPCR_INVD | FPCR_DZED | FPCR_OVFD -- 2.34.1 Set the default NaN pattern explicitly for the arm target. This includes setting it for the old linux-user nwfpe emulation. For nwfpe, our default doesn't match the real kernel, but we avoid making a behaviour change in this commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-41-peter.maydell@linaro.org --- linux-user/arm/nwfpe/fpa11.c | 5 +++++ target/arm/cpu.c | 2 ++ 2 files changed, 7 insertions(+) diff --git a/linux-user/arm/nwfpe/fpa11.c b/linux-user/arm/nwfpe/fpa11.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/nwfpe/fpa11.c +++ b/linux-user/arm/nwfpe/fpa11.c @@ -XXX,XX +XXX,XX @@ void resetFPA11(void) * this late date. */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &fpa11->fp_status); + /* + * Use the same default NaN value as Arm VFP. This doesn't match + * the Linux kernel's nwfpe emulation, which uses an all-1s value. + */ + set_float_default_nan_pattern(0b01000000, &fpa11->fp_status); } void SetRoundingMode(const unsigned int opcode) 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 @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, * the pseudocode function the arguments are in the order c, a, b. * * 0 * Inf + NaN returns the default NaN if the input NaN is quiet, * and the input NaN if it is signalling + * * Default NaN has sign bit clear, msb frac bit set */ static void arm_set_default_fp_behaviours(float_status *s) { @@ -XXX,XX +XXX,XX @@ static void arm_set_default_fp_behaviours(float_status *s) set_float_2nan_prop_rule(float_2nan_prop_s_ab, s); set_float_3nan_prop_rule(float_3nan_prop_s_cab, s); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, s); + set_float_default_nan_pattern(0b01000000, s); } static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque) -- 2.34.1 Set the default NaN pattern explicitly for loongarch. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-42-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void restore_fp_status(CPULoongArchState *env) */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_float_3nan_prop_rule(float_3nan_prop_s_cab, &env->fp_status); + /* Default NaN: sign bit clear, msb frac bit set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); } int ieee_ex_to_loongarch(int xcpt) -- 2.34.1 Set the default NaN pattern explicitly for m68k. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-43-peter.maydell@linaro.org --- target/m68k/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) * preceding paragraph for nonsignaling NaNs. */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); + /* Default NaN: sign bit clear, all frac bits set */ + set_float_default_nan_pattern(0b01111111, &env->fp_status); nan = floatx80_default_nan(&env->fp_status); for (i = 0; i < 8; i++) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint8_t dnan_pattern = status->default_nan_pattern; if (dnan_pattern == 0) { -#if defined(TARGET_SPARC) || defined(TARGET_M68K) +#if defined(TARGET_SPARC) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; #elif defined(TARGET_HEXAGON) -- 2.34.1 Set the default NaN pattern explicitly for MIPS. Note that this is our only target which currently changes the default NaN at runtime (which it was previously doing indirectly when it changed the snan_bit_is_one setting). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-44-peter.maydell@linaro.org --- target/mips/fpu_helper.h | 7 +++++++ target/mips/msa.c | 3 +++ 2 files changed, 10 insertions(+) diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/fpu_helper.h +++ b/target/mips/fpu_helper.h @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) set_float_infzeronan_rule(izn_rule, &env->active_fpu.fp_status); nan3_rule = nan2008 ? float_3nan_prop_s_cab : float_3nan_prop_s_abc; set_float_3nan_prop_rule(nan3_rule, &env->active_fpu.fp_status); + /* + * With nan2008, the default NaN value has the sign bit clear and the + * frac msb set; with the older mode, the sign bit is clear, and all + * frac bits except the msb are set. + */ + set_float_default_nan_pattern(nan2008 ? 0b01000000 : 0b00111111, + &env->active_fpu.fp_status); } diff --git a/target/mips/msa.c b/target/mips/msa.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/msa.c +++ b/target/mips/msa.c @@ -XXX,XX +XXX,XX @@ void msa_reset(CPUMIPSState *env) /* Inf * 0 + NaN returns the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->active_tc.msa_fp_status); + /* Default NaN: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, + &env->active_tc.msa_fp_status); } -- 2.34.1 Set the default NaN pattern explicitly for openrisc. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-45-peter.maydell@linaro.org --- target/openrisc/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_reset_hold(Object *obj, ResetType type) */ set_float_2nan_prop_rule(float_2nan_prop_x87, &cpu->env.fp_status); + /* Default NaN: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &cpu->env.fp_status); #ifndef CONFIG_USER_ONLY cpu->env.picmr = 0x00000000; -- 2.34.1 Set the default NaN pattern explicitly for ppc. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-46-peter.maydell@linaro.org --- target/ppc/cpu_init.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type) set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->vec_status); + /* Default NaN: sign bit clear, set frac msb */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); + set_float_default_nan_pattern(0b01000000, &env->vec_status); + for (i = 0; i < ARRAY_SIZE(env->spr_cb); i++) { ppc_spr_t *spr = &env->spr_cb[i]; -- 2.34.1 Set the default NaN pattern explicitly for sh4. Note that sh4 is one of the only three targets (the others being HPPA and sometimes MIPS) that has snan_bit_is_one set. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-47-peter.maydell@linaro.org --- target/sh4/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static void superh_cpu_reset_hold(Object *obj, ResetType type) set_flush_to_zero(1, &env->fp_status); #endif set_default_nan_mode(1, &env->fp_status); + /* sign bit clear, set all frac bits other than msb */ + set_float_default_nan_pattern(0b00111111, &env->fp_status); } static void superh_cpu_disas_set_info(CPUState *cpu, disassemble_info *info) -- 2.34.1 Set the default NaN pattern explicitly for rx. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-48-peter.maydell@linaro.org --- target/rx/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ static void rx_cpu_reset_hold(Object *obj, ResetType type) * then prefer dest over source", which is float_2nan_prop_s_ab. */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status); + /* Default NaN value: sign bit clear, set frac msb */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); } static ObjectClass *rx_cpu_class_by_name(const char *cpu_model) -- 2.34.1 Set the default NaN pattern explicitly for s390x. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-49-peter.maydell@linaro.org --- target/s390x/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset_hold(Object *obj, ResetType type) set_float_3nan_prop_rule(float_3nan_prop_s_abc, &env->fpu_status); set_float_infzeronan_rule(float_infzeronan_dnan_always, &env->fpu_status); + /* Default NaN value: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &env->fpu_status); /* fall through */ case RESET_TYPE_S390_CPU_NORMAL: env->psw.mask &= ~PSW_MASK_RI; -- 2.34.1 Set the default NaN pattern explicitly for SPARC, and remove the ifdef from parts64_default_nan. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-50-peter.maydell@linaro.org --- target/sparc/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 5 +---- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp) set_float_3nan_prop_rule(float_3nan_prop_s_cba, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + /* Default NaN value: sign bit clear, all frac bits set */ + set_float_default_nan_pattern(0b01111111, &env->fp_status); cpu_exec_realizefn(cs, &local_err); if (local_err != NULL) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint8_t dnan_pattern = status->default_nan_pattern; if (dnan_pattern == 0) { -#if defined(TARGET_SPARC) - /* Sign bit clear, all frac bits set */ - dnan_pattern = 0b01111111; -#elif defined(TARGET_HEXAGON) +#if defined(TARGET_HEXAGON) /* Sign bit set, all frac bits set. */ dnan_pattern = 0b11111111; #else -- 2.34.1 Set the default NaN pattern explicitly for xtensa. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-51-peter.maydell@linaro.org --- target/xtensa/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_reset_hold(Object *obj, ResetType type) /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_no_signaling_nans(!dfpu, &env->fp_status); + /* Default NaN value: sign bit clear, set frac msb */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); xtensa_use_first_nan(env, !dfpu); } -- 2.34.1 Set the default NaN pattern explicitly for hexagon. Remove the ifdef from parts64_default_nan(); the only remaining unconverted targets all use the default case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-52-peter.maydell@linaro.org --- target/hexagon/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 5 ----- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_reset_hold(Object *obj, ResetType type) set_default_nan_mode(1, &env->fp_status); set_float_detect_tininess(float_tininess_before_rounding, &env->fp_status); + /* Default NaN value: sign bit set, all frac bits set */ + set_float_default_nan_pattern(0b11111111, &env->fp_status); } static void hexagon_cpu_disas_set_info(CPUState *s, disassemble_info *info) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint8_t dnan_pattern = status->default_nan_pattern; if (dnan_pattern == 0) { -#if defined(TARGET_HEXAGON) - /* Sign bit set, all frac bits set. */ - dnan_pattern = 0b11111111; -#else /* * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, * S390, SH4, TriCore, and Xtensa. Our other supported targets @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) /* sign bit clear, set frac msb */ dnan_pattern = 0b01000000; } -#endif } assert(dnan_pattern != 0); -- 2.34.1 Set the default NaN pattern explicitly for riscv. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-53-peter.maydell@linaro.org --- target/riscv/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj, ResetType type) cs->exception_index = RISCV_EXCP_NONE; env->load_res = -1; set_default_nan_mode(1, &env->fp_status); + /* Default NaN value: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); env->vill = true; #ifndef CONFIG_USER_ONLY -- 2.34.1 Set the default NaN pattern explicitly for tricore. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-54-peter.maydell@linaro.org --- target/tricore/helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/tricore/helper.c b/target/tricore/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/helper.c +++ b/target/tricore/helper.c @@ -XXX,XX +XXX,XX @@ void fpu_set_state(CPUTriCoreState *env) set_flush_to_zero(1, &env->fp_status); set_float_detect_tininess(float_tininess_before_rounding, &env->fp_status); set_default_nan_mode(1, &env->fp_status); + /* Default NaN pattern: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); } uint32_t psw_read(CPUTriCoreState *env) -- 2.34.1 Now that all our targets have bene converted to explicitly specify their pattern for the default NaN value we can remove the remaining fallback code in parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-55-peter.maydell@linaro.org --- fpu/softfloat-specialize.c.inc | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint64_t frac; uint8_t dnan_pattern = status->default_nan_pattern; - if (dnan_pattern == 0) { - /* - * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, - * S390, SH4, TriCore, and Xtensa. Our other supported targets - * do not have floating-point. - */ - if (snan_bit_is_one(status)) { - /* sign bit clear, set all frac bits other than msb */ - dnan_pattern = 0b00111111; - } else { - /* sign bit clear, set frac msb */ - dnan_pattern = 0b01000000; - } - } assert(dnan_pattern != 0); sign = dnan_pattern >> 7; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Inline pickNaNMulAdd into its only caller. This makes one assert redundant with the immediately preceding IF. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-3-richard.henderson@linaro.org [PMM: keep comment from old code in new location] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 41 +++++++++++++++++++++++++- fpu/softfloat-specialize.c.inc | 54 ---------------------------------- 2 files changed, 40 insertions(+), 55 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, } if (s->default_nan_mode) { + /* + * We guarantee not to require the target to tell us how to + * pick a NaN if we're always returning the default NaN. + * But if we're not in default-NaN mode then the target must + * specify. + */ which = 3; + } else if (infzero) { + /* + * Inf * 0 + NaN -- some implementations return the + * default NaN here, and some return the input NaN. + */ + switch (s->float_infzeronan_rule) { + case float_infzeronan_dnan_never: + which = 2; + break; + case float_infzeronan_dnan_always: + which = 3; + break; + case float_infzeronan_dnan_if_qnan: + which = is_qnan(c->cls) ? 3 : 2; + break; + default: + g_assert_not_reached(); + } } else { - which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, have_snan, s); + FloatClass cls[3] = { a->cls, b->cls, c->cls }; + Float3NaNPropRule rule = s->float_3nan_prop_rule; + + assert(rule != float_3nan_prop_none); + if (have_snan && (rule & R_3NAN_SNAN_MASK)) { + /* We have at least one SNaN input and should prefer it */ + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_snan(cls[which])); + } else { + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_nan(cls[which])); + } } if (which == 3) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, } } -/*---------------------------------------------------------------------------- -| Select which NaN to propagate for a three-input operation. -| For the moment we assume that no CPU needs the 'larger significand' -| information. -| Return values : 0 : a; 1 : b; 2 : c; 3 : default-NaN -*----------------------------------------------------------------------------*/ -static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, - bool infzero, bool have_snan, float_status *status) -{ - FloatClass cls[3] = { a_cls, b_cls, c_cls }; - Float3NaNPropRule rule = status->float_3nan_prop_rule; - int which; - - /* - * We guarantee not to require the target to tell us how to - * pick a NaN if we're always returning the default NaN. - * But if we're not in default-NaN mode then the target must - * specify. - */ - assert(!status->default_nan_mode); - - if (infzero) { - /* - * Inf * 0 + NaN -- some implementations return the default NaN here, - * and some return the input NaN. - */ - switch (status->float_infzeronan_rule) { - case float_infzeronan_dnan_never: - return 2; - case float_infzeronan_dnan_always: - return 3; - case float_infzeronan_dnan_if_qnan: - return is_qnan(c_cls) ? 3 : 2; - default: - g_assert_not_reached(); - } - } - - assert(rule != float_3nan_prop_none); - if (have_snan && (rule & R_3NAN_SNAN_MASK)) { - /* We have at least one SNaN input and should prefer it */ - do { - which = rule & R_3NAN_1ST_MASK; - rule >>= R_3NAN_1ST_LENGTH; - } while (!is_snan(cls[which])); - } else { - do { - which = rule & R_3NAN_1ST_MASK; - rule >>= R_3NAN_1ST_LENGTH; - } while (!is_nan(cls[which])); - } - return which; -} - /*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Remove "3" as a special case for which and simply branch to return the desired value. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, * But if we're not in default-NaN mode then the target must * specify. */ - which = 3; + goto default_nan; } else if (infzero) { /* * Inf * 0 + NaN -- some implementations return the @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, */ switch (s->float_infzeronan_rule) { case float_infzeronan_dnan_never: - which = 2; break; case float_infzeronan_dnan_always: - which = 3; - break; + goto default_nan; case float_infzeronan_dnan_if_qnan: - which = is_qnan(c->cls) ? 3 : 2; + if (is_qnan(c->cls)) { + goto default_nan; + } break; default: g_assert_not_reached(); } + which = 2; } else { FloatClass cls[3] = { a->cls, b->cls, c->cls }; Float3NaNPropRule rule = s->float_3nan_prop_rule; @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, } } - if (which == 3) { - parts_default_nan(a, s); - return a; - } - switch (which) { case 0: break; @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, parts_silence_nan(a, s); } return a; + + default_nan: + parts_default_nan(a, s); + return a; } /* -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Assign the pointer return value to 'a' directly, rather than going through an intermediary index. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 32 ++++++++++---------------------- 1 file changed, 10 insertions(+), 22 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, FloatPartsN *c, float_status *s, int ab_mask, int abc_mask) { - int which; bool infzero = (ab_mask == float_cmask_infzero); bool have_snan = (abc_mask & float_cmask_snan); + FloatPartsN *ret; if (unlikely(have_snan)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, default: g_assert_not_reached(); } - which = 2; + ret = c; } else { - FloatClass cls[3] = { a->cls, b->cls, c->cls }; + FloatPartsN *val[3] = { a, b, c }; Float3NaNPropRule rule = s->float_3nan_prop_rule; assert(rule != float_3nan_prop_none); if (have_snan && (rule & R_3NAN_SNAN_MASK)) { /* We have at least one SNaN input and should prefer it */ do { - which = rule & R_3NAN_1ST_MASK; + ret = val[rule & R_3NAN_1ST_MASK]; rule >>= R_3NAN_1ST_LENGTH; - } while (!is_snan(cls[which])); + } while (!is_snan(ret->cls)); } else { do { - which = rule & R_3NAN_1ST_MASK; + ret = val[rule & R_3NAN_1ST_MASK]; rule >>= R_3NAN_1ST_LENGTH; - } while (!is_nan(cls[which])); + } while (!is_nan(ret->cls)); } } - switch (which) { - case 0: - break; - case 1: - a = b; - break; - case 2: - a = c; - break; - default: - g_assert_not_reached(); + if (is_snan(ret->cls)) { + parts_silence_nan(ret, s); } - if (is_snan(a->cls)) { - parts_silence_nan(a, s); - } - return a; + return ret; default_nan: parts_default_nan(a, s); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> While all indices into val[] should be in [0-2], the mask applied is two bits. To help static analysis see there is no possibility of read beyond the end of the array, pad the array to 4 entries, with the final being (implicitly) NULL. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, } ret = c; } else { - FloatPartsN *val[3] = { a, b, c }; + FloatPartsN *val[R_3NAN_1ST_MASK + 1] = { a, b, c }; Float3NaNPropRule rule = s->float_3nan_prop_rule; assert(rule != float_3nan_prop_none); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This function is part of the public interface and is not "specialized" to any target in any way. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat.c | 52 ++++++++++++++++++++++++++++++++++ fpu/softfloat-specialize.c.inc | 52 ---------------------------------- 2 files changed, 52 insertions(+), 52 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, *zExpPtr = 1 - shiftCount; } +/*---------------------------------------------------------------------------- +| Takes two extended double-precision floating-point values `a' and `b', one +| of which is a NaN, and returns the appropriate NaN result. If either `a' or +| `b' is a signaling NaN, the invalid exception is raised. +*----------------------------------------------------------------------------*/ + +floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) +{ + bool aIsLargerSignificand; + FloatClass a_cls, b_cls; + + /* This is not complete, but is good enough for pickNaN. */ + a_cls = (!floatx80_is_any_nan(a) + ? float_class_normal + : floatx80_is_signaling_nan(a, status) + ? float_class_snan + : float_class_qnan); + b_cls = (!floatx80_is_any_nan(b) + ? float_class_normal + : floatx80_is_signaling_nan(b, status) + ? float_class_snan + : float_class_qnan); + + if (is_snan(a_cls) || is_snan(b_cls)) { + float_raise(float_flag_invalid, status); + } + + if (status->default_nan_mode) { + return floatx80_default_nan(status); + } + + if (a.low < b.low) { + aIsLargerSignificand = 0; + } else if (b.low < a.low) { + aIsLargerSignificand = 1; + } else { + aIsLargerSignificand = (a.high < b.high) ? 1 : 0; + } + + if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { + if (is_snan(b_cls)) { + return floatx80_silence_nan(b, status); + } + return b; + } else { + if (is_snan(a_cls)) { + return floatx80_silence_nan(a, status); + } + return a; + } +} + /*---------------------------------------------------------------------------- | Takes an abstract floating-point value having sign `zSign', exponent `zExp', | and extended significand formed by the concatenation of `zSig0' and `zSig1', diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ floatx80 floatx80_silence_nan(floatx80 a, float_status *status) return a; } -/*---------------------------------------------------------------------------- -| Takes two extended double-precision floating-point values `a' and `b', one -| of which is a NaN, and returns the appropriate NaN result. If either `a' or -| `b' is a signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) -{ - bool aIsLargerSignificand; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!floatx80_is_any_nan(a) - ? float_class_normal - : floatx80_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!floatx80_is_any_nan(b) - ? float_class_normal - : floatx80_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return floatx80_default_nan(status); - } - - if (a.low < b.low) { - aIsLargerSignificand = 0; - } else if (b.low < a.low) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (a.high < b.high) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return floatx80_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return floatx80_silence_nan(a, status); - } - return a; - } -} - /*---------------------------------------------------------------------------- | Returns 1 if the quadruple-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Unpacking and repacking the parts may be slightly more work than we did before, but we get to reuse more code. For a code path handling exceptional values, this is an improvement. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241203203949.483774-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat.c | 43 +++++-------------------------------------- 1 file changed, 5 insertions(+), 38 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) { - bool aIsLargerSignificand; - FloatClass a_cls, b_cls; + FloatParts128 pa, pb, *pr; - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!floatx80_is_any_nan(a) - ? float_class_normal - : floatx80_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!floatx80_is_any_nan(b) - ? float_class_normal - : floatx80_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { return floatx80_default_nan(status); } - if (a.low < b.low) { - aIsLargerSignificand = 0; - } else if (b.low < a.low) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (a.high < b.high) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return floatx80_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return floatx80_silence_nan(a, status); - } - return a; - } + pr = parts_pick_nan(&pa, &pb, status); + return floatx80_round_pack_canonical(pr, status); } /*---------------------------------------------------------------------------- -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Inline pickNaN into its only caller. This makes one assert redundant with the immediately preceding IF. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 82 +++++++++++++++++++++++++---- fpu/softfloat-specialize.c.inc | 96 ---------------------------------- 2 files changed, 73 insertions(+), 105 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static void partsN(return_nan)(FloatPartsN *a, float_status *s) static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, float_status *s) { + int cmp, which; + if (is_snan(a->cls) || is_snan(b->cls)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); } if (s->default_nan_mode) { parts_default_nan(a, s); - } else { - int cmp = frac_cmp(a, b); - if (cmp == 0) { - cmp = a->sign < b->sign; - } + return a; + } - if (pickNaN(a->cls, b->cls, cmp > 0, s)) { - a = b; - } + cmp = frac_cmp(a, b); + if (cmp == 0) { + cmp = a->sign < b->sign; + } + + switch (s->float_2nan_prop_rule) { + case float_2nan_prop_s_ab: if (is_snan(a->cls)) { - parts_silence_nan(a, s); + which = 0; + } else if (is_snan(b->cls)) { + which = 1; + } else if (is_qnan(a->cls)) { + which = 0; + } else { + which = 1; } + break; + case float_2nan_prop_s_ba: + if (is_snan(b->cls)) { + which = 1; + } else if (is_snan(a->cls)) { + which = 0; + } else if (is_qnan(b->cls)) { + which = 1; + } else { + which = 0; + } + break; + case float_2nan_prop_ab: + which = is_nan(a->cls) ? 0 : 1; + break; + case float_2nan_prop_ba: + which = is_nan(b->cls) ? 1 : 0; + break; + case float_2nan_prop_x87: + /* + * This implements x87 NaN propagation rules: + * SNaN + QNaN => return the QNaN + * two SNaNs => return the one with the larger significand, silenced + * two QNaNs => return the one with the larger significand + * SNaN and a non-NaN => return the SNaN, silenced + * QNaN and a non-NaN => return the QNaN + * + * If we get down to comparing significands and they are the same, + * return the NaN with the positive sign bit (if any). + */ + if (is_snan(a->cls)) { + if (is_snan(b->cls)) { + which = cmp > 0 ? 0 : 1; + } else { + which = is_qnan(b->cls) ? 1 : 0; + } + } else if (is_qnan(a->cls)) { + if (is_snan(b->cls) || !is_qnan(b->cls)) { + which = 0; + } else { + which = cmp > 0 ? 0 : 1; + } + } else { + which = 1; + } + break; + default: + g_assert_not_reached(); + } + + if (which) { + a = b; + } + if (is_snan(a->cls)) { + parts_silence_nan(a, s); } return a; } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ bool float32_is_signaling_nan(float32 a_, float_status *status) } } -/*---------------------------------------------------------------------------- -| Select which NaN to propagate for a two-input operation. -| IEEE754 doesn't specify all the details of this, so the -| algorithm is target-specific. -| The routine is passed various bits of information about the -| two NaNs and should return 0 to select NaN a and 1 for NaN b. -| Note that signalling NaNs are always squashed to quiet NaNs -| by the caller, by calling floatXX_silence_nan() before -| returning them. -| -| aIsLargerSignificand is only valid if both a and b are NaNs -| of some kind, and is true if a has the larger significand, -| or if both a and b have the same significand but a is -| positive but b is negative. It is only needed for the x87 -| tie-break rule. -*----------------------------------------------------------------------------*/ - -static int pickNaN(FloatClass a_cls, FloatClass b_cls, - bool aIsLargerSignificand, float_status *status) -{ - /* - * We guarantee not to require the target to tell us how to - * pick a NaN if we're always returning the default NaN. - * But if we're not in default-NaN mode then the target must - * specify via set_float_2nan_prop_rule(). - */ - assert(!status->default_nan_mode); - - switch (status->float_2nan_prop_rule) { - case float_2nan_prop_s_ab: - if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } - break; - case float_2nan_prop_s_ba: - if (is_snan(b_cls)) { - return 1; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_qnan(b_cls)) { - return 1; - } else { - return 0; - } - break; - case float_2nan_prop_ab: - if (is_nan(a_cls)) { - return 0; - } else { - return 1; - } - break; - case float_2nan_prop_ba: - if (is_nan(b_cls)) { - return 1; - } else { - return 0; - } - break; - case float_2nan_prop_x87: - /* - * This implements x87 NaN propagation rules: - * SNaN + QNaN => return the QNaN - * two SNaNs => return the one with the larger significand, silenced - * two QNaNs => return the one with the larger significand - * SNaN and a non-NaN => return the SNaN, silenced - * QNaN and a non-NaN => return the QNaN - * - * If we get down to comparing significands and they are the same, - * return the NaN with the positive sign bit (if any). - */ - if (is_snan(a_cls)) { - if (is_snan(b_cls)) { - return aIsLargerSignificand ? 0 : 1; - } - return is_qnan(b_cls) ? 1 : 0; - } else if (is_qnan(a_cls)) { - if (is_snan(b_cls) || !is_qnan(b_cls)) { - return 0; - } else { - return aIsLargerSignificand ? 0 : 1; - } - } else { - return 1; - } - default: - g_assert_not_reached(); - } -} - /*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Remember if there was an SNaN, and use that to simplify float_2nan_prop_s_{ab,ba} to only the snan component. Then, fall through to the corresponding float_2nan_prop_{ab,ba} case to handle any remaining nans, which must be quiet. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 32 ++++++++++++-------------------- 1 file changed, 12 insertions(+), 20 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static void partsN(return_nan)(FloatPartsN *a, float_status *s) static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, float_status *s) { + bool have_snan = false; int cmp, which; if (is_snan(a->cls) || is_snan(b->cls)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); + have_snan = true; } if (s->default_nan_mode) { @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, switch (s->float_2nan_prop_rule) { case float_2nan_prop_s_ab: - if (is_snan(a->cls)) { - which = 0; - } else if (is_snan(b->cls)) { - which = 1; - } else if (is_qnan(a->cls)) { - which = 0; - } else { - which = 1; + if (have_snan) { + which = is_snan(a->cls) ? 0 : 1; + break; } - break; - case float_2nan_prop_s_ba: - if (is_snan(b->cls)) { - which = 1; - } else if (is_snan(a->cls)) { - which = 0; - } else if (is_qnan(b->cls)) { - which = 1; - } else { - which = 0; - } - break; + /* fall through */ case float_2nan_prop_ab: which = is_nan(a->cls) ? 0 : 1; break; + case float_2nan_prop_s_ba: + if (have_snan) { + which = is_snan(b->cls) ? 1 : 0; + break; + } + /* fall through */ case float_2nan_prop_ba: which = is_nan(b->cls) ? 1 : 0; break; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Move the fractional comparison to the end of the float_2nan_prop_x87 case. This is not required for any other 2nan propagation rule. Reorganize the x87 case itself to break out of the switch when the fractional comparison is not required. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, return a; } - cmp = frac_cmp(a, b); - if (cmp == 0) { - cmp = a->sign < b->sign; - } - switch (s->float_2nan_prop_rule) { case float_2nan_prop_s_ab: if (have_snan) { @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, * return the NaN with the positive sign bit (if any). */ if (is_snan(a->cls)) { - if (is_snan(b->cls)) { - which = cmp > 0 ? 0 : 1; - } else { + if (!is_snan(b->cls)) { which = is_qnan(b->cls) ? 1 : 0; + break; } } else if (is_qnan(a->cls)) { if (is_snan(b->cls) || !is_qnan(b->cls)) { which = 0; - } else { - which = cmp > 0 ? 0 : 1; + break; } } else { which = 1; + break; } + cmp = frac_cmp(a, b); + if (cmp == 0) { + cmp = a->sign < b->sign; + } + which = cmp > 0 ? 0 : 1; break; default: g_assert_not_reached(); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Replace the "index" selecting between A and B with a result variable of the proper type. This improves clarity within the function. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, float_status *s) { bool have_snan = false; - int cmp, which; + FloatPartsN *ret; + int cmp; if (is_snan(a->cls) || is_snan(b->cls)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, switch (s->float_2nan_prop_rule) { case float_2nan_prop_s_ab: if (have_snan) { - which = is_snan(a->cls) ? 0 : 1; + ret = is_snan(a->cls) ? a : b; break; } /* fall through */ case float_2nan_prop_ab: - which = is_nan(a->cls) ? 0 : 1; + ret = is_nan(a->cls) ? a : b; break; case float_2nan_prop_s_ba: if (have_snan) { - which = is_snan(b->cls) ? 1 : 0; + ret = is_snan(b->cls) ? b : a; break; } /* fall through */ case float_2nan_prop_ba: - which = is_nan(b->cls) ? 1 : 0; + ret = is_nan(b->cls) ? b : a; break; case float_2nan_prop_x87: /* @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, */ if (is_snan(a->cls)) { if (!is_snan(b->cls)) { - which = is_qnan(b->cls) ? 1 : 0; + ret = is_qnan(b->cls) ? b : a; break; } } else if (is_qnan(a->cls)) { if (is_snan(b->cls) || !is_qnan(b->cls)) { - which = 0; + ret = a; break; } } else { - which = 1; + ret = b; break; } cmp = frac_cmp(a, b); if (cmp == 0) { cmp = a->sign < b->sign; } - which = cmp > 0 ? 0 : 1; + ret = cmp > 0 ? a : b; break; default: g_assert_not_reached(); } - if (which) { - a = b; + if (is_snan(ret->cls)) { + parts_silence_nan(ret, s); } - if (is_snan(a->cls)) { - parts_silence_nan(a, s); - } - return a; + return ret; } static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, -- 2.34.1 From: Leif Lindholm <quic_llindhol@quicinc.com> I'm migrating to Qualcomm's new open source email infrastructure, so update my email address, and update the mailmap to match. Signed-off-by: Leif Lindholm <leif.lindholm@oss.qualcomm.com> Reviewed-by: Leif Lindholm <quic_llindhol@quicinc.com> Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241205114047.1125842-1-leif.lindholm@oss.qualcomm.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 +- .mailmap | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/ssi/imx_spi.h SBSA-REF M: Radoslaw Biernacki <rad@semihalf.com> M: Peter Maydell <peter.maydell@linaro.org> -R: Leif Lindholm <quic_llindhol@quicinc.com> +R: Leif Lindholm <leif.lindholm@oss.qualcomm.com> R: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> L: qemu-arm@nongnu.org S: Maintained diff --git a/.mailmap b/.mailmap index XXXXXXX..XXXXXXX 100644 --- a/.mailmap +++ b/.mailmap @@ -XXX,XX +XXX,XX @@ Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com> Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn> James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> Juan Quintela <quintela@trasno.org> <quintela@redhat.com> -Leif Lindholm <quic_llindhol@quicinc.com> <leif.lindholm@linaro.org> -Leif Lindholm <quic_llindhol@quicinc.com> <leif@nuviainc.com> +Leif Lindholm <leif.lindholm@oss.qualcomm.com> <quic_llindhol@quicinc.com> +Leif Lindholm <leif.lindholm@oss.qualcomm.com> <leif.lindholm@linaro.org> +Leif Lindholm <leif.lindholm@oss.qualcomm.com> <leif@nuviainc.com> Luc Michel <luc@lmichel.fr> <luc.michel@git.antfield.fr> Luc Michel <luc@lmichel.fr> <luc.michel@greensocs.com> Luc Michel <luc@lmichel.fr> <lmichel@kalray.eu> -- 2.34.1 From: Vikram Garhwal <vikram.garhwal@bytedance.com> Previously, maintainer role was paused due to inactive email id. Commit id: c009d715721861984c4987bcc78b7ee183e86d75. Signed-off-by: Vikram Garhwal <vikram.garhwal@bytedance.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20241204184205.12952-1-vikram.garhwal@bytedance.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: tests/qtest/fuzz-sb16-test.c Xilinx CAN M: Francisco Iglesias <francisco.iglesias@amd.com> +M: Vikram Garhwal <vikram.garhwal@bytedance.com> S: Maintained F: hw/net/can/xlnx-* F: include/hw/net/xlnx-* @@ -XXX,XX +XXX,XX @@ F: include/hw/rx/ CAN bus subsystem and hardware M: Pavel Pisa <pisa@cmp.felk.cvut.cz> M: Francisco Iglesias <francisco.iglesias@amd.com> +M: Vikram Garhwal <vikram.garhwal@bytedance.com> S: Maintained W: https://canbus.pages.fel.cvut.cz/ F: net/can/* -- 2.34.1