target-arm queue: the big things in here are SVE in system emulation mode, and v8M stack limit checking; there are also a handful of smaller fixes. thanks -- PMM The following changes since commit 079911cb6e26898e16f5bb56ef4f9d33cf92d32d: Merge remote-tracking branch 'remotes/rth/tags/pull-fpu-20181005' into staging (2018-10-08 12:44:35 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20181008 for you to fetch changes up to 74e2e59b8d0a68be0956310fc349179c89fd7be0: hw/display/bcm2835_fb: Silence Coverity warning about multiply overflow (2018-10-08 14:55:05 +0100) ---------------------------------------------------------------- target-arm queue: * target/arm: fix error in a code comment * virt: Suppress external aborts on virt-2.10 and earlier * target/arm: Correct condition for v8M callee stack push * target/arm: Don't read r4 from v8M exception stackframe twice * target/arm: Support SVE in system emulation mode * target/arm: Implement v8M hardware stack limit checking * hw/display/bcm2835_fb: Silence Coverity warning about multiply overflow ---------------------------------------------------------------- Dongjiu Geng (1): target/arm: fix code comments error Peter Maydell (17): virt: Suppress external aborts on virt-2.10 and earlier target/arm: Correct condition for v8M callee stack push target/arm: Don't read r4 from v8M exception stackframe twice target/arm: Define new TBFLAG for v8M stack checking target/arm: Define new EXCP type for v8M stack overflows target/arm: Move v7m_using_psp() to internals.h target/arm: Add v8M stack checks on ADD/SUB/MOV of SP target/arm: Add some comments in Thumb decode target/arm: Add v8M stack checks on exception entry target/arm: Add v8M stack limit checks on NS function calls target/arm: Add v8M stack checks for LDRD/STRD (imm) target/arm: Add v8M stack checks for Thumb2 LDM/STM target/arm: Add v8M stack checks for T32 load/store single target/arm: Add v8M stack checks for Thumb push/pop target/arm: Add v8M stack checks for VLDM/VSTM target/arm: Add v8M stack checks for MSR to SP_NS hw/display/bcm2835_fb: Silence Coverity warning about multiply overflow Richard Henderson (15): target/arm: Define ID_AA64ZFR0_EL1 target/arm: Adjust sve_exception_el target/arm: Pass in current_el to fp and sve_exception_el target/arm: Handle SVE vector length changes in system mode target/arm: Adjust aarch64_cpu_dump_state for system mode SVE target/arm: Clear unused predicate bits for LD1RQ target/arm: Rewrite helper_sve_ld1*_r using pages target/arm: Rewrite helper_sve_ld[234]*_r target/arm: Rewrite helper_sve_st[1234]*_r target/arm: Split contiguous loads for endianness target/arm: Split contiguous stores for endianness target/arm: Rewrite vector gather loads target/arm: Rewrite vector gather stores target/arm: Rewrite vector gather first-fault loads target/arm: Pass TCGMemOpIdx to sve memory helpers target/arm/cpu.h | 17 + target/arm/helper-sve.h | 385 ++++++--- target/arm/helper.h | 2 + target/arm/internals.h | 44 + target/arm/kvm_arm.h | 4 +- target/arm/translate.h | 1 + hw/arm/virt.c | 2 + hw/display/bcm2835_fb.c | 2 +- target/arm/cpu64.c | 42 - target/arm/helper.c | 345 +++++--- target/arm/kvm.c | 2 +- target/arm/op_helper.c | 24 +- target/arm/sve_helper.c | 1961 ++++++++++++++++++++++++++++++-------------- target/arm/translate-a64.c | 8 +- target/arm/translate-sve.c | 670 ++++++++++----- target/arm/translate.c | 198 ++++- 16 files changed, 2611 insertions(+), 1096 deletions(-) From: Dongjiu Geng <gengdongjiu@huawei.com> The parameter of kvm_arm_init_cpreg_list() is ARMCPU instead of CPUState, so correct the note to make it match the code. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Message-id: 1538069046-5757-1-git-send-email-gengdongjiu@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 4 ++-- target/arm/kvm.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ void kvm_arm_register_device(MemoryRegion *mr, uint64_t devid, uint64_t group, /** * kvm_arm_init_cpreg_list: - * @cs: CPUState + * @cpu: ARMCPU * - * Initialize the CPUState's cpreg list according to the kernel's + * Initialize the ARMCPU cpreg list according to the kernel's * definition of what CPU registers it knows about (and throw away * the previous TCG-created cpreg list). * diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ static int compare_u64(const void *a, const void *b) return 0; } -/* Initialize the CPUState's cpreg list according to the kernel's +/* Initialize the ARMCPU cpreg list according to the kernel's * definition of what CPU registers it knows about (and throw away * the previous TCG-created cpreg list). */ -- 2.19.0 In commit c79c0a314c43b78 we enabled emulation of external aborts when the guest attempts to access a physical address with no mapped device. In commit 4672cbd7bed88dc6 we suppress this for most legacy boards to prevent breakage of previously working guests, but we didn't suppress it in the 'virt' board, with the rationale "we know that guests won't try to prod devices that we don't describe in the device tree or ACPI tables". This is mostly true, but we've had a report of a Linux guest image that this did break. The problem seems to be that the guest is (incorrectly) configured with a DEBUG_UART_PHYS value that tells it there is a uart at 0x10009000 (which is true for vexpress but not for virt), so in early bootup the kernel probes this bogus address. This is a misconfigured guest, so we don't need to worry about it too much, but we can arrange that guests that ran on QEMU v2.10 (before c79c0a314c43b78) will still run on the "virt-2.10" board model, by suppressing external aborts only for that version and earlier. This seems a reasonable compromise: "virt-2.10" is supposed to behave the same way that "virt" did in the 2.10 release, and making it do that provides a usable workaround for guests with bugs like this. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180925144127.31965-1-peter.maydell@linaro.org Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> --- hw/arm/virt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_machine_2_10_options(MachineClass *mc) { virt_machine_2_11_options(mc); SET_MACHINE_COMPAT(mc, VIRT_COMPAT_2_10); + /* before 2.11 we never faulted accesses to bad addresses */ + mc->ignore_memory_transaction_failures = true; } DEFINE_VIRT_MACHINE(2, 10) -- 2.19.0 In v7m_exception_taken() we were incorrectly using a "LR bit EXCRET.ES is 1" check when it should be 0 (compare the pseudocode ExceptionTaken() function). This meant we didn't stack the callee-saved registers when tailchaining from a NonSecure to a Secure exception. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002145940.30931-1-peter.maydell@linaro.org --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, * not already saved. */ if (lr & R_V7M_EXCRET_DCRS_MASK && - !(dotailchain && (lr & R_V7M_EXCRET_ES_MASK))) { + !(dotailchain && !(lr & R_V7M_EXCRET_ES_MASK))) { push_failed = v7m_push_callee_stack(cpu, lr, dotailchain, ignore_stackfaults); } -- 2.19.0 A cut-and-paste error meant we were reading r4 from the v8M callee-saves exception stack frame twice. This is harmless since it just meant we did two memory accesses to the same location, but it's unnecessary. Delete it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002150304.2287-1-peter.maydell@linaro.org --- target/arm/helper.c | 1 - 1 file changed, 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) } pop_ok = pop_ok && - v7m_stack_read(cpu, &env->regs[4], frameptr + 0x8, mmu_idx) && v7m_stack_read(cpu, &env->regs[4], frameptr + 0x8, mmu_idx) && v7m_stack_read(cpu, &env->regs[5], frameptr + 0xc, mmu_idx) && v7m_stack_read(cpu, &env->regs[6], frameptr + 0x10, mmu_idx) && -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> Given that the only field defined for this new register may only be 0, we don't actually need to change anything except the name. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ID_AA64PFR4_EL1_RESERVED", .state = ARM_CP_STATE_AA64, + { .name = "ID_AA64ZFR0_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, + /* At present, only SVEver == 0 is defined anyway. */ .resetvalue = 0 }, { .name = "ID_AA64PFR5_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 5, -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> Check for EL3 before testing CPTR_EL3.EZ. Return 0 when the exception should be routed via AdvSIMDFPAccessTrap. Mirror the structure of CheckSVEEnabled more closely. Fixes: 5be5e8eda78 Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 96 ++++++++++++++++++++++----------------------- 1 file changed, 46 insertions(+), 50 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_lpae_cp_reginfo[] = { REGINFO_SENTINEL }; -/* Return the exception level to which SVE-disabled exceptions should - * be taken, or 0 if SVE is enabled. +/* Return the exception level to which exceptions should be taken + * via SVEAccessTrap. If an exception should be routed through + * AArch64.AdvSIMDFPAccessTrap, return 0; fp_exception_el should + * take care of raising that exception. + * C.f. the ARM pseudocode function CheckSVEEnabled. */ static int sve_exception_el(CPUARMState *env) { #ifndef CONFIG_USER_ONLY unsigned current_el = arm_current_el(env); - /* The CPACR.ZEN controls traps to EL1: - * 0, 2 : trap EL0 and EL1 accesses - * 1 : trap only EL0 accesses - * 3 : trap no accesses + if (current_el <= 1) { + bool disabled = false; + + /* The CPACR.ZEN controls traps to EL1: + * 0, 2 : trap EL0 and EL1 accesses + * 1 : trap only EL0 accesses + * 3 : trap no accesses + */ + if (!extract32(env->cp15.cpacr_el1, 16, 1)) { + disabled = true; + } else if (!extract32(env->cp15.cpacr_el1, 17, 1)) { + disabled = current_el == 0; + } + if (disabled) { + /* route_to_el2 */ + return (arm_feature(env, ARM_FEATURE_EL2) + && !arm_is_secure(env) + && (env->cp15.hcr_el2 & HCR_TGE) ? 2 : 1); + } + + /* Check CPACR.FPEN. */ + if (!extract32(env->cp15.cpacr_el1, 20, 1)) { + disabled = true; + } else if (!extract32(env->cp15.cpacr_el1, 21, 1)) { + disabled = current_el == 0; + } + if (disabled) { + return 0; + } + } + + /* CPTR_EL2. Since TZ and TFP are positive, + * they will be zero when EL2 is not present. */ - switch (extract32(env->cp15.cpacr_el1, 16, 2)) { - default: - if (current_el <= 1) { - /* Trap to PL1, which might be EL1 or EL3 */ - if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) { - return 3; - } - return 1; + if (current_el <= 2 && !arm_is_secure_below_el3(env)) { + if (env->cp15.cptr_el[2] & CPTR_TZ) { + return 2; } - break; - case 1: - if (current_el == 0) { - return 1; + if (env->cp15.cptr_el[2] & CPTR_TFP) { + return 0; } - break; - case 3: - break; } - /* Similarly for CPACR.FPEN, after having checked ZEN. */ - switch (extract32(env->cp15.cpacr_el1, 20, 2)) { - default: - if (current_el <= 1) { - if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) { - return 3; - } - return 1; - } - break; - case 1: - if (current_el == 0) { - return 1; - } - break; - case 3: - break; - } - - /* CPTR_EL2. Check both TZ and TFP. */ - if (current_el <= 2 - && (env->cp15.cptr_el[2] & (CPTR_TFP | CPTR_TZ)) - && !arm_is_secure_below_el3(env)) { - return 2; - } - - /* CPTR_EL3. Check both EZ and TFP. */ - if (!(env->cp15.cptr_el[3] & CPTR_EZ) - || (env->cp15.cptr_el[3] & CPTR_TFP)) { + /* CPTR_EL3. Since EZ is negative we must check for EL3. */ + if (arm_feature(env, ARM_FEATURE_EL3) + && !(env->cp15.cptr_el[3] & CPTR_EZ)) { return 3; } #endif -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> We are going to want to determine whether sve is enabled for EL other than current. Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_lpae_cp_reginfo[] = { * take care of raising that exception. * C.f. the ARM pseudocode function CheckSVEEnabled. */ -static int sve_exception_el(CPUARMState *env) +static int sve_exception_el(CPUARMState *env, int el) { #ifndef CONFIG_USER_ONLY - unsigned current_el = arm_current_el(env); - - if (current_el <= 1) { + if (el <= 1) { bool disabled = false; /* The CPACR.ZEN controls traps to EL1: @@ -XXX,XX +XXX,XX @@ static int sve_exception_el(CPUARMState *env) if (!extract32(env->cp15.cpacr_el1, 16, 1)) { disabled = true; } else if (!extract32(env->cp15.cpacr_el1, 17, 1)) { - disabled = current_el == 0; + disabled = el == 0; } if (disabled) { /* route_to_el2 */ @@ -XXX,XX +XXX,XX @@ static int sve_exception_el(CPUARMState *env) if (!extract32(env->cp15.cpacr_el1, 20, 1)) { disabled = true; } else if (!extract32(env->cp15.cpacr_el1, 21, 1)) { - disabled = current_el == 0; + disabled = el == 0; } if (disabled) { return 0; @@ -XXX,XX +XXX,XX @@ static int sve_exception_el(CPUARMState *env) /* CPTR_EL2. Since TZ and TFP are positive, * they will be zero when EL2 is not present. */ - if (current_el <= 2 && !arm_is_secure_below_el3(env)) { + if (el <= 2 && !arm_is_secure_below_el3(env)) { if (env->cp15.cptr_el[2] & CPTR_TZ) { return 2; } @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) /* Return the exception level to which FP-disabled exceptions should * be taken, or 0 if FP is enabled. */ -static inline int fp_exception_el(CPUARMState *env) +static int fp_exception_el(CPUARMState *env, int cur_el) { #ifndef CONFIG_USER_ONLY int fpen; - int cur_el = arm_current_el(env); /* CPACR and the CPTR registers don't exist before v6, so FP is * always accessible @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); - int fp_el = fp_exception_el(env); + int current_el = arm_current_el(env); + int fp_el = fp_exception_el(env, current_el); uint32_t flags; if (is_a64(env)) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags |= (arm_regime_tbi1(env, mmu_idx) << ARM_TBFLAG_TBI1_SHIFT); if (arm_feature(env, ARM_FEATURE_SVE)) { - int sve_el = sve_exception_el(env); + int sve_el = sve_exception_el(env, current_el); uint32_t zcr_len; /* If SVE is disabled, but FP is enabled, @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (sve_el != 0 && fp_el == 0) { zcr_len = 0; } else { - int current_el = arm_current_el(env); ARMCPU *cpu = arm_env_get_cpu(env); zcr_len = cpu->sve_max_vq - 1; -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> SVE vector length can change when changing EL, or when writing to one of the ZCR_ELn registers. For correctness, our implementation requires that predicate bits that are inaccessible are never set. Which means noticing length changes and zeroing the appropriate register bits. Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 4 ++ target/arm/cpu64.c | 42 ------------- target/arm/helper.c | 133 +++++++++++++++++++++++++++++++++++++---- target/arm/op_helper.c | 1 + 4 files changed, 125 insertions(+), 55 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 arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, int aarch64_cpu_gdb_read_register(CPUState *cpu, uint8_t *buf, int reg); int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq); +void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el); +#else +static inline void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) { } +static inline void aarch64_sve_change_el(CPUARMState *env, int o, int n) { } #endif target_ulong do_arm_semihosting(CPUARMState *env); diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_register_types(void) } type_init(aarch64_cpu_register_types) - -/* The manual says that when SVE is enabled and VQ is widened the - * implementation is allowed to zero the previously inaccessible - * portion of the registers. The corollary to that is that when - * SVE is enabled and VQ is narrowed we are also allowed to zero - * the now inaccessible portion of the registers. - * - * The intent of this is that no predicate bit beyond VQ is ever set. - * Which means that some operations on predicate registers themselves - * may operate on full uint64_t or even unrolled across the maximum - * uint64_t[4]. Performing 4 bits of host arithmetic unconditionally - * may well be cheaper than conditionals to restrict the operation - * to the relevant portion of a uint16_t[16]. - * - * TODO: Need to call this for changes to the real system registers - * and EL state changes. - */ -void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) -{ - int i, j; - uint64_t pmask; - - assert(vq >= 1 && vq <= ARM_MAX_VQ); - assert(vq <= arm_env_get_cpu(env)->sve_max_vq); - - /* Zap the high bits of the zregs. */ - for (i = 0; i < 32; i++) { - memset(&env->vfp.zregs[i].d[2 * vq], 0, 16 * (ARM_MAX_VQ - vq)); - } - - /* Zap the high bits of the pregs and ffr. */ - pmask = 0; - if (vq & 3) { - pmask = ~(-1ULL << (16 * (vq & 3))); - } - for (j = vq / 4; j < ARM_MAX_VQ / 4; j++) { - for (i = 0; i < 17; ++i) { - env->vfp.pregs[i].p[j] &= pmask; - } - pmask = 0; - } -} 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 int sve_exception_el(CPUARMState *env, int el) return 0; } +/* + * Given that SVE is enabled, return the vector length for EL. + */ +static uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) +{ + ARMCPU *cpu = arm_env_get_cpu(env); + uint32_t zcr_len = cpu->sve_max_vq - 1; + + if (el <= 1) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[1]); + } + if (el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[2]); + } + if (el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]); + } + return zcr_len; +} + static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { + int cur_el = arm_current_el(env); + int old_len = sve_zcr_len_for_el(env, cur_el); + int new_len; + /* Bits other than [3:0] are RAZ/WI. */ raw_write(env, ri, value & 0xf); + + /* + * Because we arrived here, we know both FP and SVE are enabled; + * otherwise we would have trapped access to the ZCR_ELn register. + */ + new_len = sve_zcr_len_for_el(env, cur_el); + if (new_len < old_len) { + aarch64_sve_narrow_vq(env, new_len + 1); + } } static const ARMCPRegInfo zcr_el1_reginfo = { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) unsigned int new_el = env->exception.target_el; target_ulong addr = env->cp15.vbar_el[new_el]; unsigned int new_mode = aarch64_pstate_mode(new_el, true); + unsigned int cur_el = arm_current_el(env); - if (arm_current_el(env) < new_el) { + aarch64_sve_change_el(env, cur_el, new_el); + + if (cur_el < new_el) { /* Entry vector offset depends on whether the implemented EL * immediately lower than the target level is using AArch32 or AArch64 */ @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (sve_el != 0 && fp_el == 0) { zcr_len = 0; } else { - ARMCPU *cpu = arm_env_get_cpu(env); - - zcr_len = cpu->sve_max_vq - 1; - if (current_el <= 1) { - zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[1]); - } - if (current_el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { - zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[2]); - } - if (current_el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { - zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]); - } + zcr_len = sve_zcr_len_for_el(env, current_el); } flags |= sve_el << ARM_TBFLAG_SVEEXC_EL_SHIFT; flags |= zcr_len << ARM_TBFLAG_ZCR_LEN_SHIFT; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *pflags = flags; *cs_base = 0; } + +#ifdef TARGET_AARCH64 +/* + * The manual says that when SVE is enabled and VQ is widened the + * implementation is allowed to zero the previously inaccessible + * portion of the registers. The corollary to that is that when + * SVE is enabled and VQ is narrowed we are also allowed to zero + * the now inaccessible portion of the registers. + * + * The intent of this is that no predicate bit beyond VQ is ever set. + * Which means that some operations on predicate registers themselves + * may operate on full uint64_t or even unrolled across the maximum + * uint64_t[4]. Performing 4 bits of host arithmetic unconditionally + * may well be cheaper than conditionals to restrict the operation + * to the relevant portion of a uint16_t[16]. + */ +void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) +{ + int i, j; + uint64_t pmask; + + assert(vq >= 1 && vq <= ARM_MAX_VQ); + assert(vq <= arm_env_get_cpu(env)->sve_max_vq); + + /* Zap the high bits of the zregs. */ + for (i = 0; i < 32; i++) { + memset(&env->vfp.zregs[i].d[2 * vq], 0, 16 * (ARM_MAX_VQ - vq)); + } + + /* Zap the high bits of the pregs and ffr. */ + pmask = 0; + if (vq & 3) { + pmask = ~(-1ULL << (16 * (vq & 3))); + } + for (j = vq / 4; j < ARM_MAX_VQ / 4; j++) { + for (i = 0; i < 17; ++i) { + env->vfp.pregs[i].p[j] &= pmask; + } + pmask = 0; + } +} + +/* + * Notice a change in SVE vector size when changing EL. + */ +void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el) +{ + int old_len, new_len; + + /* Nothing to do if no SVE. */ + if (!arm_feature(env, ARM_FEATURE_SVE)) { + return; + } + + /* Nothing to do if FP is disabled in either EL. */ + if (fp_exception_el(env, old_el) || fp_exception_el(env, new_el)) { + return; + } + + /* + * DDI0584A.d sec 3.2: "If SVE instructions are disabled or trapped + * at ELx, or not available because the EL is in AArch32 state, then + * for all purposes other than a direct read, the ZCR_ELx.LEN field + * has an effective value of 0". + * + * Consider EL2 (aa64, vq=4) -> EL0 (aa32) -> EL1 (aa64, vq=0). + * If we ignore aa32 state, we would fail to see the vq4->vq0 transition + * from EL2->EL1. Thus we go ahead and narrow when entering aa32 so that + * we already have the correct register contents when encountering the + * vq0->vq0 transition between EL0->EL1. + */ + old_len = (arm_el_is_aa64(env, old_el) && !sve_exception_el(env, old_el) + ? sve_zcr_len_for_el(env, old_el) : 0); + new_len = (arm_el_is_aa64(env, new_el) && !sve_exception_el(env, new_el) + ? sve_zcr_len_for_el(env, new_el) : 0); + + /* When changing vector length, clear inaccessible state. */ + if (new_len < old_len) { + aarch64_sve_narrow_vq(env, new_len + 1); + } +} +#endif diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env) "AArch64 EL%d PC 0x%" PRIx64 "\n", cur_el, new_el, env->pc); } + aarch64_sve_change_el(env, cur_el, new_el); qemu_mutex_lock_iothread(); arm_call_el_change_hook(arm_env_get_cpu(env)); -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> Use the existing helpers to determine if (1) the fpu is enabled, (2) sve state is enabled, and (3) the current sve vector length. Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 4 ++++ target/arm/helper.c | 6 +++--- target/arm/translate-a64.c | 8 ++++++-- 3 files changed, 13 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 @@ target_ulong do_arm_semihosting(CPUARMState *env); void aarch64_sync_32_to_64(CPUARMState *env); void aarch64_sync_64_to_32(CPUARMState *env); +int fp_exception_el(CPUARMState *env, int cur_el); +int sve_exception_el(CPUARMState *env, int cur_el); +uint32_t sve_zcr_len_for_el(CPUARMState *env, int el); + static inline bool is_a64(CPUARMState *env) { return env->aarch64; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_lpae_cp_reginfo[] = { * take care of raising that exception. * C.f. the ARM pseudocode function CheckSVEEnabled. */ -static int sve_exception_el(CPUARMState *env, int el) +int sve_exception_el(CPUARMState *env, int el) { #ifndef CONFIG_USER_ONLY if (el <= 1) { @@ -XXX,XX +XXX,XX @@ static int sve_exception_el(CPUARMState *env, int el) /* * Given that SVE is enabled, return the vector length for EL. */ -static uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) +uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) { ARMCPU *cpu = arm_env_get_cpu(env); uint32_t zcr_len = cpu->sve_max_vq - 1; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) /* Return the exception level to which FP-disabled exceptions should * be taken, or 0 if FP is enabled. */ -static int fp_exception_el(CPUARMState *env, int cur_el) +int fp_exception_el(CPUARMState *env, int cur_el) { #ifndef CONFIG_USER_ONLY int fpen; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f, cpu_fprintf(f, "\n"); return; } + if (fp_exception_el(env, el) != 0) { + cpu_fprintf(f, " FPU disabled\n"); + return; + } cpu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (arm_feature(env, ARM_FEATURE_SVE)) { - int j, zcr_len = env->vfp.zcr_el[1] & 0xf; /* fix for system mode */ + if (arm_feature(env, ARM_FEATURE_SVE) && sve_exception_el(env, el) == 0) { + int j, zcr_len = sve_zcr_len_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { bool eol; -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> The 16-byte load only uses 16 predicate bits. But while reusing the other load infrastructure, we find other bits that are set and trigger an assert. To avoid this and retain the assert, zero-extend the predicate that we pass to the LD1 helper. Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; TCGv_i32 desc; + int poff; /* Load the first quadword using the normal predicated load helpers. */ desc = tcg_const_i32(simd_desc(16, 16, zt)); - t_pg = tcg_temp_new_ptr(); - tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); + poff = pred_full_reg_offset(s, pg); + if (vsz > 16) { + /* + * Zero-extend the first 16 bits of the predicate into a temporary. + * This avoids triggering an assert making sure we don't have bits + * set within a predicate beyond VQ, but we have lowered VQ to 1 + * for this load operation. + */ + TCGv_i64 tmp = tcg_temp_new_i64(); +#ifdef HOST_WORDS_BIGENDIAN + poff += 6; +#endif + tcg_gen_ld16u_i64(tmp, cpu_env, poff); + + poff = offsetof(CPUARMState, vfp.preg_tmp); + tcg_gen_st_i64(tmp, cpu_env, poff); + tcg_temp_free_i64(tmp); + } + + t_pg = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_pg, cpu_env, poff); + fns[msz](cpu_env, t_pg, addr, desc); tcg_temp_free_ptr(t_pg); -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> Uses tlb_vaddr_to_host for correct operation with softmmu. Optimize for accesses within a single page or pair of pages. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 731 +++++++++++++++++++++++++++++++--------- 1 file changed, 569 insertions(+), 162 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static void swap_memmove(void *vd, void *vs, size_t n) } } +/* Similarly for memset of 0. */ +static void swap_memzero(void *vd, size_t n) +{ + uintptr_t d = (uintptr_t)vd; + uintptr_t o = (d | n) & 7; + size_t i; + + /* Usually, the first bit of a predicate is set, so N is 0. */ + if (likely(n == 0)) { + return; + } + +#ifndef HOST_WORDS_BIGENDIAN + o = 0; +#endif + switch (o) { + case 0: + memset(vd, 0, n); + break; + + case 4: + for (i = 0; i < n; i += 4) { + *(uint32_t *)H1_4(d + i) = 0; + } + break; + + case 2: + case 6: + for (i = 0; i < n; i += 2) { + *(uint16_t *)H1_2(d + i) = 0; + } + break; + + default: + for (i = 0; i < n; i++) { + *(uint8_t *)H1(d + i) = 0; + } + break; + } +} + void HELPER(sve_ext)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t opr_sz = simd_oprsz(desc); @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) /* * Load contiguous data, protected by a governing predicate. */ -#define DO_LD1(NAME, FN, TYPEE, TYPEM, H) \ -static void do_##NAME(CPUARMState *env, void *vd, void *vg, \ - target_ulong addr, intptr_t oprsz, \ - uintptr_t ra) \ -{ \ - intptr_t i = 0; \ - do { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - m = FN(env, addr, ra); \ - } \ - *(TYPEE *)(vd + H(i)) = m; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += sizeof(TYPEM); \ - } while (i & 15); \ - } while (i < oprsz); \ -} \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - do_##NAME(env, &env->vfp.zregs[simd_data(desc)], vg, \ - addr, simd_oprsz(desc), GETPC()); \ + +/* + * Load elements into @vd, controlled by @vg, from @host + @mem_ofs. + * Memory is valid through @host + @mem_max. The register element + * indicies are inferred from @mem_ofs, as modified by the types for + * which the helper is built. Return the @mem_ofs of the first element + * not loaded (which is @mem_max if they are all loaded). + * + * For softmmu, we have fully validated the guest page. For user-only, + * we cannot fully validate without taking the mmap lock, but since we + * know the access is within one host page, if any access is valid they + * all must be valid. However, when @vg is all false, it may be that + * no access is valid. + */ +typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host, + intptr_t mem_ofs, intptr_t mem_max); + +/* + * Load one element into @vd + @reg_off from (@env, @vaddr, @ra). + * The controlling predicate is known to be true. + */ +typedef void sve_ld1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong vaddr, int mmu_idx, uintptr_t ra); + +/* + * Generate the above primitives. + */ + +#define DO_LD_HOST(NAME, H, TYPEE, TYPEM, HOST) \ +static intptr_t sve_##NAME##_host(void *vd, void *vg, void *host, \ + intptr_t mem_off, const intptr_t mem_max) \ +{ \ + intptr_t reg_off = mem_off * (sizeof(TYPEE) / sizeof(TYPEM)); \ + uint64_t *pg = vg; \ + while (mem_off + sizeof(TYPEM) <= mem_max) { \ + TYPEM val = 0; \ + if (likely((pg[reg_off >> 6] >> (reg_off & 63)) & 1)) { \ + val = HOST(host + mem_off); \ + } \ + *(TYPEE *)(vd + H(reg_off)) = val; \ + mem_off += sizeof(TYPEM), reg_off += sizeof(TYPEE); \ + } \ + return mem_off; \ } +#ifdef CONFIG_SOFTMMU +#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx, uintptr_t ra) \ +{ \ + TCGMemOpIdx oi = make_memop_idx(ctz32(sizeof(TYPEM)) | MOEND, mmu_idx); \ + TYPEM val = TLB(env, addr, oi, ra); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ +} +#else +#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx, uintptr_t ra) \ +{ \ + TYPEM val = HOST(g2h(addr)); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ +} +#endif + +#define DO_LD_PRIM_1(NAME, H, TE, TM) \ + DO_LD_HOST(NAME, H, TE, TM, ldub_p) \ + DO_LD_TLB(NAME, H, TE, TM, ldub_p, 0, helper_ret_ldub_mmu) + +DO_LD_PRIM_1(ld1bb, H1, uint8_t, uint8_t) +DO_LD_PRIM_1(ld1bhu, H1_2, uint16_t, uint8_t) +DO_LD_PRIM_1(ld1bhs, H1_2, uint16_t, int8_t) +DO_LD_PRIM_1(ld1bsu, H1_4, uint32_t, uint8_t) +DO_LD_PRIM_1(ld1bss, H1_4, uint32_t, int8_t) +DO_LD_PRIM_1(ld1bdu, , uint64_t, uint8_t) +DO_LD_PRIM_1(ld1bds, , uint64_t, int8_t) + +#define DO_LD_PRIM_2(NAME, end, MOEND, H, TE, TM, PH, PT) \ + DO_LD_HOST(NAME##_##end, H, TE, TM, PH##_##end##_p) \ + DO_LD_TLB(NAME##_##end, H, TE, TM, PH##_##end##_p, \ + MOEND, helper_##end##_##PT##_mmu) + +DO_LD_PRIM_2(ld1hh, le, MO_LE, H1_2, uint16_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hsu, le, MO_LE, H1_4, uint32_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hss, le, MO_LE, H1_4, uint32_t, int16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hdu, le, MO_LE, , uint64_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hds, le, MO_LE, , uint64_t, int16_t, lduw, lduw) + +DO_LD_PRIM_2(ld1ss, le, MO_LE, H1_4, uint32_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sdu, le, MO_LE, , uint64_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sds, le, MO_LE, , uint64_t, int32_t, ldl, ldul) + +DO_LD_PRIM_2(ld1dd, le, MO_LE, , uint64_t, uint64_t, ldq, ldq) + +DO_LD_PRIM_2(ld1hh, be, MO_BE, H1_2, uint16_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hsu, be, MO_BE, H1_4, uint32_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hss, be, MO_BE, H1_4, uint32_t, int16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hdu, be, MO_BE, , uint64_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hds, be, MO_BE, , uint64_t, int16_t, lduw, lduw) + +DO_LD_PRIM_2(ld1ss, be, MO_BE, H1_4, uint32_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sdu, be, MO_BE, , uint64_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sds, be, MO_BE, , uint64_t, int32_t, ldl, ldul) + +DO_LD_PRIM_2(ld1dd, be, MO_BE, , uint64_t, uint64_t, ldq, ldq) + +#undef DO_LD_TLB +#undef DO_LD_HOST +#undef DO_LD_PRIM_1 +#undef DO_LD_PRIM_2 + +/* + * Skip through a sequence of inactive elements in the guarding predicate @vg, + * beginning at @reg_off bounded by @reg_max. Return the offset of the active + * element >= @reg_off, or @reg_max if there were no active elements at all. + */ +static intptr_t find_next_active(uint64_t *vg, intptr_t reg_off, + intptr_t reg_max, int esz) +{ + uint64_t pg_mask = pred_esz_masks[esz]; + uint64_t pg = (vg[reg_off >> 6] & pg_mask) >> (reg_off & 63); + + /* In normal usage, the first element is active. */ + if (likely(pg & 1)) { + return reg_off; + } + + if (pg == 0) { + reg_off &= -64; + do { + reg_off += 64; + if (unlikely(reg_off >= reg_max)) { + /* The entire predicate was false. */ + return reg_max; + } + pg = vg[reg_off >> 6] & pg_mask; + } while (pg == 0); + } + reg_off += ctz64(pg); + + /* We should never see an out of range predicate bit set. */ + tcg_debug_assert(reg_off < reg_max); + return reg_off; +} + +/* + * Return the maximum offset <= @mem_max which is still within the page + * referenced by @base + @mem_off. + */ +static intptr_t max_for_page(target_ulong base, intptr_t mem_off, + intptr_t mem_max) +{ + target_ulong addr = base + mem_off; + intptr_t split = -(intptr_t)(addr | TARGET_PAGE_MASK); + return MIN(split, mem_max - mem_off) + mem_off; +} + +static inline void set_helper_retaddr(uintptr_t ra) +{ +#ifdef CONFIG_USER_ONLY + helper_retaddr = ra; +#endif +} + +/* + * The result of tlb_vaddr_to_host for user-only is just g2h(x), + * which is always non-null. Elide the useless test. + */ +static inline bool test_host_page(void *host) +{ +#ifdef CONFIG_USER_ONLY + return true; +#else + return likely(host != NULL); +#endif +} + +/* + * Common helper for all contiguous one-register predicated loads. + */ +static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr, + uint32_t desc, const uintptr_t retaddr, + const int esz, const int msz, + sve_ld1_host_fn *host_fn, + sve_ld1_tlb_fn *tlb_fn) +{ + void *vd = &env->vfp.zregs[simd_data(desc)]; + const int diffsz = esz - msz; + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t mem_max = reg_max >> diffsz; + const int mmu_idx = cpu_mmu_index(env, false); + ARMVectorReg scratch; + void *host; + intptr_t split, reg_off, mem_off; + + /* Find the first active element. */ + reg_off = find_next_active(vg, 0, reg_max, esz); + if (unlikely(reg_off == reg_max)) { + /* The entire predicate was false; no load occurs. */ + memset(vd, 0, reg_max); + return; + } + mem_off = reg_off >> diffsz; + set_helper_retaddr(retaddr); + + /* + * If the (remaining) load is entirely within a single page, then: + * For softmmu, and the tlb hits, then no faults will occur; + * For user-only, either the first load will fault or none will. + * We can thus perform the load directly to the destination and + * Vd will be unmodified on any exception path. + */ + split = max_for_page(addr, mem_off, mem_max); + if (likely(split == mem_max)) { + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + if (test_host_page(host)) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max); + tcg_debug_assert(mem_off == mem_max); + set_helper_retaddr(0); + /* After having taken any fault, zero leading inactive elements. */ + swap_memzero(vd, reg_off); + return; + } + } + + /* + * Perform the predicated read into a temporary, thus ensuring + * if the load of the last element faults, Vd is not modified. + */ +#ifdef CONFIG_USER_ONLY + swap_memzero(&scratch, reg_off); + host_fn(&scratch, vg, g2h(addr), mem_off, mem_max); +#else + memset(&scratch, 0, reg_max); + goto start; + while (1) { + reg_off = find_next_active(vg, reg_off, reg_max, esz); + if (reg_off >= reg_max) { + break; + } + mem_off = reg_off >> diffsz; + split = max_for_page(addr, mem_off, mem_max); + + start: + if (split - mem_off >= (1 << msz)) { + /* At least one whole element on this page. */ + host = tlb_vaddr_to_host(env, addr + mem_off, + MMU_DATA_LOAD, mmu_idx); + if (host) { + mem_off = host_fn(&scratch, vg, host - mem_off, + mem_off, split); + reg_off = mem_off << diffsz; + continue; + } + } + + /* + * Perform one normal read. This may fault, longjmping out to the + * main loop in order to raise an exception. It may succeed, and + * as a side-effect load the TLB entry for the next round. Finally, + * in the extremely unlikely case we're performing this operation + * on I/O memory, it may succeed but not bring in the TLB entry. + * But even then we have still made forward progress. + */ + tlb_fn(env, &scratch, reg_off, addr + mem_off, mmu_idx, retaddr); + reg_off += 1 << esz; + } +#endif + + set_helper_retaddr(0); + memcpy(vd, &scratch, reg_max); +} + +#define DO_LD1_1(NAME, ESZ) \ +void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, 0, \ + sve_##NAME##_host, sve_##NAME##_tlb); \ +} + +/* TODO: Propagate the endian check back to the translator. */ +#define DO_LD1_2(NAME, ESZ, MSZ) \ +void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + if (arm_cpu_data_is_big_endian(env)) { \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ + } else { \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ + } \ +} + +DO_LD1_1(ld1bb, 0) +DO_LD1_1(ld1bhu, 1) +DO_LD1_1(ld1bhs, 1) +DO_LD1_1(ld1bsu, 2) +DO_LD1_1(ld1bss, 2) +DO_LD1_1(ld1bdu, 3) +DO_LD1_1(ld1bds, 3) + +DO_LD1_2(ld1hh, 1, 1) +DO_LD1_2(ld1hsu, 2, 1) +DO_LD1_2(ld1hss, 2, 1) +DO_LD1_2(ld1hdu, 3, 1) +DO_LD1_2(ld1hds, 3, 1) + +DO_LD1_2(ld1ss, 2, 2) +DO_LD1_2(ld1sdu, 3, 2) +DO_LD1_2(ld1sds, 3, 2) + +DO_LD1_2(ld1dd, 3, 3) + +#undef DO_LD1_1 +#undef DO_LD1_2 + #define DO_LD2(NAME, FN, TYPEE, TYPEM, H) \ void HELPER(NAME)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(CPUARMState *env, void *vg, \ } \ } -DO_LD1(sve_ld1bhu_r, cpu_ldub_data_ra, uint16_t, uint8_t, H1_2) -DO_LD1(sve_ld1bhs_r, cpu_ldsb_data_ra, uint16_t, int8_t, H1_2) -DO_LD1(sve_ld1bsu_r, cpu_ldub_data_ra, uint32_t, uint8_t, H1_4) -DO_LD1(sve_ld1bss_r, cpu_ldsb_data_ra, uint32_t, int8_t, H1_4) -DO_LD1(sve_ld1bdu_r, cpu_ldub_data_ra, uint64_t, uint8_t, ) -DO_LD1(sve_ld1bds_r, cpu_ldsb_data_ra, uint64_t, int8_t, ) - -DO_LD1(sve_ld1hsu_r, cpu_lduw_data_ra, uint32_t, uint16_t, H1_4) -DO_LD1(sve_ld1hss_r, cpu_ldsw_data_ra, uint32_t, int16_t, H1_4) -DO_LD1(sve_ld1hdu_r, cpu_lduw_data_ra, uint64_t, uint16_t, ) -DO_LD1(sve_ld1hds_r, cpu_ldsw_data_ra, uint64_t, int16_t, ) - -DO_LD1(sve_ld1sdu_r, cpu_ldl_data_ra, uint64_t, uint32_t, ) -DO_LD1(sve_ld1sds_r, cpu_ldl_data_ra, uint64_t, int32_t, ) - -DO_LD1(sve_ld1bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) DO_LD2(sve_ld2bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) DO_LD3(sve_ld3bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) DO_LD4(sve_ld4bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LD1(sve_ld1hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) DO_LD2(sve_ld2hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) DO_LD3(sve_ld3hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) DO_LD4(sve_ld4hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LD1(sve_ld1ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) DO_LD2(sve_ld2ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) DO_LD3(sve_ld3ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) DO_LD4(sve_ld4ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LD1(sve_ld1dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) DO_LD2(sve_ld2dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) DO_LD3(sve_ld3dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) DO_LD4(sve_ld4dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) -#undef DO_LD1 #undef DO_LD2 #undef DO_LD3 #undef DO_LD4 /* * Load contiguous data, first-fault and no-fault. + * + * For user-only, one could argue that we should hold the mmap_lock during + * the operation so that there is no race between page_check_range and the + * load operation. However, unmapping pages out from under a running thread + * is extraordinarily unlikely. This theoretical race condition also affects + * linux-user/ in its get_user/put_user macros. + * + * TODO: Construct some helpers, written in assembly, that interact with + * handle_cpu_signal to produce memory ops which can properly report errors + * without racing. */ -#ifdef CONFIG_USER_ONLY - /* Fault on byte I. All bits in FFR from I are cleared. The vector * result from I is CONSTRAINED UNPREDICTABLE; we choose the MERGE * option, which leaves subsequent data unchanged. @@ -XXX,XX +XXX,XX @@ static void record_fault(CPUARMState *env, uintptr_t i, uintptr_t oprsz) } } -/* Hold the mmap lock during the operation so that there is no race - * between page_check_range and the load operation. We expect the - * usual case to have no faults at all, so we check the whole range - * first and if successful defer to the normal load operation. - * - * TODO: Change mmap_lock to a rwlock so that multiple readers - * can run simultaneously. This will probably help other uses - * within QEMU as well. +/* + * Common helper for all contiguous first-fault loads. */ -#define DO_LDFF1(PART, FN, TYPEE, TYPEM, H) \ -static void do_sve_ldff1##PART(CPUARMState *env, void *vd, void *vg, \ - target_ulong addr, intptr_t oprsz, \ - bool first, uintptr_t ra) \ -{ \ - intptr_t i = 0; \ - do { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - if (!first && \ - unlikely(page_check_range(addr, sizeof(TYPEM), \ - PAGE_READ))) { \ - record_fault(env, i, oprsz); \ - return; \ - } \ - m = FN(env, addr, ra); \ - first = false; \ - } \ - *(TYPEE *)(vd + H(i)) = m; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += sizeof(TYPEM); \ - } while (i & 15); \ - } while (i < oprsz); \ -} \ -void HELPER(sve_ldff1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t oprsz = simd_oprsz(desc); \ - unsigned rd = simd_data(desc); \ - void *vd = &env->vfp.zregs[rd]; \ - mmap_lock(); \ - if (likely(page_check_range(addr, oprsz, PAGE_READ) == 0)) { \ - do_sve_ld1##PART(env, vd, vg, addr, oprsz, GETPC()); \ - } else { \ - do_sve_ldff1##PART(env, vd, vg, addr, oprsz, true, GETPC()); \ - } \ - mmap_unlock(); \ -} +static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr, + uint32_t desc, const uintptr_t retaddr, + const int esz, const int msz, + sve_ld1_host_fn *host_fn, + sve_ld1_tlb_fn *tlb_fn) +{ + void *vd = &env->vfp.zregs[simd_data(desc)]; + const int diffsz = esz - msz; + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t mem_max = reg_max >> diffsz; + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t split, reg_off, mem_off; + void *host; -/* No-fault loads are like first-fault loads without the - * first faulting special case. - */ -#define DO_LDNF1(PART) \ -void HELPER(sve_ldnf1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t oprsz = simd_oprsz(desc); \ - unsigned rd = simd_data(desc); \ - void *vd = &env->vfp.zregs[rd]; \ - mmap_lock(); \ - if (likely(page_check_range(addr, oprsz, PAGE_READ) == 0)) { \ - do_sve_ld1##PART(env, vd, vg, addr, oprsz, GETPC()); \ - } else { \ - do_sve_ldff1##PART(env, vd, vg, addr, oprsz, false, GETPC()); \ - } \ - mmap_unlock(); \ -} + /* Skip to the first active element. */ + reg_off = find_next_active(vg, 0, reg_max, esz); + if (unlikely(reg_off == reg_max)) { + /* The entire predicate was false; no load occurs. */ + memset(vd, 0, reg_max); + return; + } + mem_off = reg_off >> diffsz; + set_helper_retaddr(retaddr); + /* + * If the (remaining) load is entirely within a single page, then: + * For softmmu, and the tlb hits, then no faults will occur; + * For user-only, either the first load will fault or none will. + * We can thus perform the load directly to the destination and + * Vd will be unmodified on any exception path. + */ + split = max_for_page(addr, mem_off, mem_max); + if (likely(split == mem_max)) { + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + if (test_host_page(host)) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max); + tcg_debug_assert(mem_off == mem_max); + set_helper_retaddr(0); + /* After any fault, zero any leading inactive elements. */ + swap_memzero(vd, reg_off); + return; + } + } + +#ifdef CONFIG_USER_ONLY + /* + * The page(s) containing this first element at ADDR+MEM_OFF must + * be valid. Considering that this first element may be misaligned + * and cross a page boundary itself, take the rest of the page from + * the last byte of the element. + */ + split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max); + mem_off = host_fn(vd, vg, g2h(addr), mem_off, split); + + /* After any fault, zero any leading inactive elements. */ + swap_memzero(vd, reg_off); + reg_off = mem_off << diffsz; #else + /* + * Perform one normal read, which will fault or not. + * But it is likely to bring the page into the tlb. + */ + tlb_fn(env, vd, reg_off, addr + mem_off, mmu_idx, retaddr); -/* TODO: System mode is not yet supported. - * This would probably use tlb_vaddr_to_host. - */ -#define DO_LDFF1(PART, FN, TYPEE, TYPEM, H) \ -void HELPER(sve_ldff1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - g_assert_not_reached(); \ -} - -#define DO_LDNF1(PART) \ -void HELPER(sve_ldnf1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - g_assert_not_reached(); \ -} + /* After any fault, zero any leading predicated false elts. */ + swap_memzero(vd, reg_off); + mem_off += 1 << msz; + reg_off += 1 << esz; + /* Try again to read the balance of the page. */ + split = max_for_page(addr, mem_off - 1, mem_max); + if (split >= (1 << msz)) { + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + if (host) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, split); + reg_off = mem_off << diffsz; + } + } #endif -DO_LDFF1(bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LDFF1(bhu_r, cpu_ldub_data_ra, uint16_t, uint8_t, H1_2) -DO_LDFF1(bhs_r, cpu_ldsb_data_ra, uint16_t, int8_t, H1_2) -DO_LDFF1(bsu_r, cpu_ldub_data_ra, uint32_t, uint8_t, H1_4) -DO_LDFF1(bss_r, cpu_ldsb_data_ra, uint32_t, int8_t, H1_4) -DO_LDFF1(bdu_r, cpu_ldub_data_ra, uint64_t, uint8_t, ) -DO_LDFF1(bds_r, cpu_ldsb_data_ra, uint64_t, int8_t, ) + set_helper_retaddr(0); + record_fault(env, reg_off, reg_max); +} -DO_LDFF1(hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LDFF1(hsu_r, cpu_lduw_data_ra, uint32_t, uint16_t, H1_4) -DO_LDFF1(hss_r, cpu_ldsw_data_ra, uint32_t, int8_t, H1_4) -DO_LDFF1(hdu_r, cpu_lduw_data_ra, uint64_t, uint16_t, ) -DO_LDFF1(hds_r, cpu_ldsw_data_ra, uint64_t, int16_t, ) +/* + * Common helper for all contiguous no-fault loads. + */ +static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr, + uint32_t desc, const int esz, const int msz, + sve_ld1_host_fn *host_fn) +{ + void *vd = &env->vfp.zregs[simd_data(desc)]; + const int diffsz = esz - msz; + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t mem_max = reg_max >> diffsz; + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t split, reg_off, mem_off; + void *host; -DO_LDFF1(ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LDFF1(sdu_r, cpu_ldl_data_ra, uint64_t, uint32_t, ) -DO_LDFF1(sds_r, cpu_ldl_data_ra, uint64_t, int32_t, ) +#ifdef CONFIG_USER_ONLY + host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx); + if (likely(page_check_range(addr, mem_max, PAGE_READ) == 0)) { + /* The entire operation is valid and will not fault. */ + host_fn(vd, vg, host, 0, mem_max); + return; + } +#endif -DO_LDFF1(dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) + /* There will be no fault, so we may modify in advance. */ + memset(vd, 0, reg_max); -#undef DO_LDFF1 + /* Skip to the first active element. */ + reg_off = find_next_active(vg, 0, reg_max, esz); + if (unlikely(reg_off == reg_max)) { + /* The entire predicate was false; no load occurs. */ + return; + } + mem_off = reg_off >> diffsz; -DO_LDNF1(bb_r) -DO_LDNF1(bhu_r) -DO_LDNF1(bhs_r) -DO_LDNF1(bsu_r) -DO_LDNF1(bss_r) -DO_LDNF1(bdu_r) -DO_LDNF1(bds_r) +#ifdef CONFIG_USER_ONLY + if (page_check_range(addr + mem_off, 1 << msz, PAGE_READ) == 0) { + /* At least one load is valid; take the rest of the page. */ + split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max); + mem_off = host_fn(vd, vg, host, mem_off, split); + reg_off = mem_off << diffsz; + } +#else + /* + * If the address is not in the TLB, we have no way to bring the + * entry into the TLB without also risking a fault. Note that + * the corollary is that we never load from an address not in RAM. + * + * This last is out of spec, in a weird corner case. + * Per the MemNF/MemSingleNF pseudocode, a NF load from Device memory + * must not actually hit the bus -- it returns UNKNOWN data instead. + * But if you map non-RAM with Normal memory attributes and do a NF + * load then it should access the bus. (Nobody ought actually do this + * in the real world, obviously.) + * + * Then there are the annoying special cases with watchpoints... + * + * TODO: Add a form of tlb_fill that does not raise an exception, + * with a form of tlb_vaddr_to_host and a set of loads to match. + * The non_fault_vaddr_to_host would handle everything, usually, + * and the loads would handle the iomem path for watchpoints. + */ + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + split = max_for_page(addr, mem_off, mem_max); + if (host && split >= (1 << msz)) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, split); + reg_off = mem_off << diffsz; + } +#endif -DO_LDNF1(hh_r) -DO_LDNF1(hsu_r) -DO_LDNF1(hss_r) -DO_LDNF1(hdu_r) -DO_LDNF1(hds_r) + record_fault(env, reg_off, reg_max); +} -DO_LDNF1(ss_r) -DO_LDNF1(sdu_r) -DO_LDNF1(sds_r) +#define DO_LDFF1_LDNF1_1(PART, ESZ) \ +void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, 0, \ + sve_ld1##PART##_host, sve_ld1##PART##_tlb); \ +} \ +void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, 0, sve_ld1##PART##_host); \ +} -DO_LDNF1(dd_r) +/* TODO: Propagate the endian check back to the translator. */ +#define DO_LDFF1_LDNF1_2(PART, ESZ, MSZ) \ +void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + if (arm_cpu_data_is_big_endian(env)) { \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ + } else { \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ + } \ +} \ +void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + if (arm_cpu_data_is_big_endian(env)) { \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, \ + sve_ld1##PART##_be_host); \ + } else { \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, \ + sve_ld1##PART##_le_host); \ + } \ +} -#undef DO_LDNF1 +DO_LDFF1_LDNF1_1(bb, 0) +DO_LDFF1_LDNF1_1(bhu, 1) +DO_LDFF1_LDNF1_1(bhs, 1) +DO_LDFF1_LDNF1_1(bsu, 2) +DO_LDFF1_LDNF1_1(bss, 2) +DO_LDFF1_LDNF1_1(bdu, 3) +DO_LDFF1_LDNF1_1(bds, 3) + +DO_LDFF1_LDNF1_2(hh, 1, 1) +DO_LDFF1_LDNF1_2(hsu, 2, 1) +DO_LDFF1_LDNF1_2(hss, 2, 1) +DO_LDFF1_LDNF1_2(hdu, 3, 1) +DO_LDFF1_LDNF1_2(hds, 3, 1) + +DO_LDFF1_LDNF1_2(ss, 2, 2) +DO_LDFF1_LDNF1_2(sdu, 3, 2) +DO_LDFF1_LDNF1_2(sds, 3, 2) + +DO_LDFF1_LDNF1_2(dd, 3, 3) + +#undef DO_LDFF1_LDNF1_1 +#undef DO_LDFF1_LDNF1_2 /* * Store contiguous data, protected by a governing predicate. -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> Use the same *_tlb primitives as we use for ld1. For linux-user, this hoists the set of helper_retaddr. For softmmu, hoists the computation of the current mmu_idx outside the loop, fixes the endianness problem, and moves the main loop out of a macro and into an inlined function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 210 ++++++++++++++++++++++------------------ 1 file changed, 117 insertions(+), 93 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LD1_2(ld1dd, 3, 3) #undef DO_LD1_1 #undef DO_LD1_2 -#define DO_LD2(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m1 = 0, m2 = 0; \ - if (pg & 1) { \ - m1 = FN(env, addr, ra); \ - m2 = FN(env, addr + sizeof(TYPEM), ra); \ - } \ - *(TYPEE *)(d1 + H(i)) = m1; \ - *(TYPEE *)(d2 + H(i)) = m2; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 2 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +/* + * Common helpers for all contiguous 2,3,4-register predicated loads. + */ +static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, int size, uintptr_t ra, + sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); + unsigned rd = simd_data(desc); + ARMVectorReg scratch[2] = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra); + tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra); + } + i += size, pg >>= size; + addr += 2 * size; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz); + memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz); } -#define DO_LD3(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m1 = 0, m2 = 0, m3 = 0; \ - if (pg & 1) { \ - m1 = FN(env, addr, ra); \ - m2 = FN(env, addr + sizeof(TYPEM), ra); \ - m3 = FN(env, addr + 2 * sizeof(TYPEM), ra); \ - } \ - *(TYPEE *)(d1 + H(i)) = m1; \ - *(TYPEE *)(d2 + H(i)) = m2; \ - *(TYPEE *)(d3 + H(i)) = m3; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 3 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, int size, uintptr_t ra, + sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); + unsigned rd = simd_data(desc); + ARMVectorReg scratch[3] = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra); + tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra); + tlb_fn(env, &scratch[2], i, addr + 2 * size, mmu_idx, ra); + } + i += size, pg >>= size; + addr += 3 * size; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz); + memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz); + memcpy(&env->vfp.zregs[(rd + 2) & 31], &scratch[2], oprsz); } -#define DO_LD4(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - void *d4 = &env->vfp.zregs[(rd + 3) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m1 = 0, m2 = 0, m3 = 0, m4 = 0; \ - if (pg & 1) { \ - m1 = FN(env, addr, ra); \ - m2 = FN(env, addr + sizeof(TYPEM), ra); \ - m3 = FN(env, addr + 2 * sizeof(TYPEM), ra); \ - m4 = FN(env, addr + 3 * sizeof(TYPEM), ra); \ - } \ - *(TYPEE *)(d1 + H(i)) = m1; \ - *(TYPEE *)(d2 + H(i)) = m2; \ - *(TYPEE *)(d3 + H(i)) = m3; \ - *(TYPEE *)(d4 + H(i)) = m4; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 4 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, int size, uintptr_t ra, + sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); + unsigned rd = simd_data(desc); + ARMVectorReg scratch[4] = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra); + tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra); + tlb_fn(env, &scratch[2], i, addr + 2 * size, mmu_idx, ra); + tlb_fn(env, &scratch[3], i, addr + 3 * size, mmu_idx, ra); + } + i += size, pg >>= size; + addr += 4 * size; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz); + memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz); + memcpy(&env->vfp.zregs[(rd + 2) & 31], &scratch[2], oprsz); + memcpy(&env->vfp.zregs[(rd + 3) & 31], &scratch[3], oprsz); } -DO_LD2(sve_ld2bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LD3(sve_ld3bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LD4(sve_ld4bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) +#define DO_LDN_1(N) \ +void __attribute__((flatten)) HELPER(sve_ld##N##bb_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_ld##N##_r(env, vg, addr, desc, 1, GETPC(), sve_ld1bb_tlb); \ +} -DO_LD2(sve_ld2hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LD3(sve_ld3hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LD4(sve_ld4hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) +#define DO_LDN_2(N, SUFF, SIZE) \ +void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \ + arm_cpu_data_is_big_endian(env) \ + ? sve_ld1##SUFF##_be_tlb : sve_ld1##SUFF##_le_tlb); \ +} -DO_LD2(sve_ld2ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LD3(sve_ld3ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LD4(sve_ld4ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) +DO_LDN_1(2) +DO_LDN_1(3) +DO_LDN_1(4) -DO_LD2(sve_ld2dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) -DO_LD3(sve_ld3dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) -DO_LD4(sve_ld4dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) +DO_LDN_2(2, hh, 2) +DO_LDN_2(3, hh, 2) +DO_LDN_2(4, hh, 2) -#undef DO_LD2 -#undef DO_LD3 -#undef DO_LD4 +DO_LDN_2(2, ss, 4) +DO_LDN_2(3, ss, 4) +DO_LDN_2(4, ss, 4) + +DO_LDN_2(2, dd, 8) +DO_LDN_2(3, dd, 8) +DO_LDN_2(4, dd, 8) + +#undef DO_LDN_1 +#undef DO_LDN_2 /* * Load contiguous data, first-fault and no-fault. -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> This fixes the endianness problem for softmmu, and moves the main loop out of a macro and into an inlined function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 351 ++++++++++++++++++++-------------------- 1 file changed, 172 insertions(+), 179 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host, */ typedef void sve_ld1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off, target_ulong vaddr, int mmu_idx, uintptr_t ra); +typedef sve_ld1_tlb_fn sve_st1_tlb_fn; /* * Generate the above primitives. @@ -XXX,XX +XXX,XX @@ DO_LDFF1_LDNF1_2(dd, 3, 3) /* * Store contiguous data, protected by a governing predicate. */ -#define DO_ST1(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *vd = &env->vfp.zregs[rd]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m = *(TYPEE *)(vd + H(i)); \ - FN(env, addr, m, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += sizeof(TYPEM); \ - } while (i & 15); \ - } \ + +#ifdef CONFIG_SOFTMMU +#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx, uintptr_t ra) \ +{ \ + TCGMemOpIdx oi = make_memop_idx(ctz32(sizeof(TYPEM)) | MOEND, mmu_idx); \ + TLB(env, addr, *(TYPEM *)(vd + H(reg_off)), oi, ra); \ } - -#define DO_ST1_D(NAME, FN, TYPEM) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc) / 8; \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - uint64_t *d = &env->vfp.zregs[rd].d[0]; \ - uint8_t *pg = vg; \ - for (i = 0; i < oprsz; i += 1) { \ - if (pg[H1(i)] & 1) { \ - FN(env, addr, d[i], ra); \ - } \ - addr += sizeof(TYPEM); \ - } \ +#else +#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx, uintptr_t ra) \ +{ \ + HOST(g2h(addr), *(TYPEM *)(vd + H(reg_off))); \ } +#endif -#define DO_ST2(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ - TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ - FN(env, addr, m1, ra); \ - FN(env, addr + sizeof(TYPEM), m2, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 2 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ -} +DO_ST_TLB(st1bb, H1, uint8_t, stb_p, 0, helper_ret_stb_mmu) +DO_ST_TLB(st1bh, H1_2, uint16_t, stb_p, 0, helper_ret_stb_mmu) +DO_ST_TLB(st1bs, H1_4, uint32_t, stb_p, 0, helper_ret_stb_mmu) +DO_ST_TLB(st1bd, , uint64_t, stb_p, 0, helper_ret_stb_mmu) -#define DO_ST3(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ - TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ - TYPEM m3 = *(TYPEE *)(d3 + H(i)); \ - FN(env, addr, m1, ra); \ - FN(env, addr + sizeof(TYPEM), m2, ra); \ - FN(env, addr + 2 * sizeof(TYPEM), m3, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 3 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ -} +DO_ST_TLB(st1hh_le, H1_2, uint16_t, stw_le_p, MO_LE, helper_le_stw_mmu) +DO_ST_TLB(st1hs_le, H1_4, uint32_t, stw_le_p, MO_LE, helper_le_stw_mmu) +DO_ST_TLB(st1hd_le, , uint64_t, stw_le_p, MO_LE, helper_le_stw_mmu) -#define DO_ST4(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - void *d4 = &env->vfp.zregs[(rd + 3) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ - TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ - TYPEM m3 = *(TYPEE *)(d3 + H(i)); \ - TYPEM m4 = *(TYPEE *)(d4 + H(i)); \ - FN(env, addr, m1, ra); \ - FN(env, addr + sizeof(TYPEM), m2, ra); \ - FN(env, addr + 2 * sizeof(TYPEM), m3, ra); \ - FN(env, addr + 3 * sizeof(TYPEM), m4, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 4 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ -} +DO_ST_TLB(st1ss_le, H1_4, uint32_t, stl_le_p, MO_LE, helper_le_stl_mmu) +DO_ST_TLB(st1sd_le, , uint64_t, stl_le_p, MO_LE, helper_le_stl_mmu) -DO_ST1(sve_st1bh_r, cpu_stb_data_ra, uint16_t, uint8_t, H1_2) -DO_ST1(sve_st1bs_r, cpu_stb_data_ra, uint32_t, uint8_t, H1_4) -DO_ST1_D(sve_st1bd_r, cpu_stb_data_ra, uint8_t) +DO_ST_TLB(st1dd_le, , uint64_t, stq_le_p, MO_LE, helper_le_stq_mmu) -DO_ST1(sve_st1hs_r, cpu_stw_data_ra, uint32_t, uint16_t, H1_4) -DO_ST1_D(sve_st1hd_r, cpu_stw_data_ra, uint16_t) +DO_ST_TLB(st1hh_be, H1_2, uint16_t, stw_be_p, MO_BE, helper_be_stw_mmu) +DO_ST_TLB(st1hs_be, H1_4, uint32_t, stw_be_p, MO_BE, helper_be_stw_mmu) +DO_ST_TLB(st1hd_be, , uint64_t, stw_be_p, MO_BE, helper_be_stw_mmu) -DO_ST1_D(sve_st1sd_r, cpu_stl_data_ra, uint32_t) +DO_ST_TLB(st1ss_be, H1_4, uint32_t, stl_be_p, MO_BE, helper_be_stl_mmu) +DO_ST_TLB(st1sd_be, , uint64_t, stl_be_p, MO_BE, helper_be_stl_mmu) -DO_ST1(sve_st1bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) -DO_ST2(sve_st2bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) -DO_ST3(sve_st3bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) -DO_ST4(sve_st4bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) +DO_ST_TLB(st1dd_be, , uint64_t, stq_be_p, MO_BE, helper_be_stq_mmu) -DO_ST1(sve_st1hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) -DO_ST2(sve_st2hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) -DO_ST3(sve_st3hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) -DO_ST4(sve_st4hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) +#undef DO_ST_TLB -DO_ST1(sve_st1ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) -DO_ST2(sve_st2ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) -DO_ST3(sve_st3ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) -DO_ST4(sve_st4ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) - -DO_ST1_D(sve_st1dd_r, cpu_stq_data_ra, uint64_t) - -void HELPER(sve_st2dd_r)(CPUARMState *env, void *vg, - target_ulong addr, uint32_t desc) +/* + * Common helpers for all contiguous 1,2,3,4-register predicated stores. + */ +static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) { - intptr_t i, oprsz = simd_oprsz(desc) / 8; - intptr_t ra = GETPC(); + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); unsigned rd = simd_data(desc); - uint64_t *d1 = &env->vfp.zregs[rd].d[0]; - uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; - uint8_t *pg = vg; + void *vd = &env->vfp.zregs[rd]; - for (i = 0; i < oprsz; i += 1) { - if (pg[H1(i)] & 1) { - cpu_stq_data_ra(env, addr, d1[i], ra); - cpu_stq_data_ra(env, addr + 8, d2[i], ra); - } - addr += 2 * 8; + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, vd, i, addr, mmu_idx, ra); + } + i += esize, pg >>= esize; + addr += msize; + } while (i & 15); } + set_helper_retaddr(0); } -void HELPER(sve_st3dd_r)(CPUARMState *env, void *vg, - target_ulong addr, uint32_t desc) +static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) { - intptr_t i, oprsz = simd_oprsz(desc) / 8; - intptr_t ra = GETPC(); + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); unsigned rd = simd_data(desc); - uint64_t *d1 = &env->vfp.zregs[rd].d[0]; - uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; - uint64_t *d3 = &env->vfp.zregs[(rd + 2) & 31].d[0]; - uint8_t *pg = vg; + void *d1 = &env->vfp.zregs[rd]; + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; - for (i = 0; i < oprsz; i += 1) { - if (pg[H1(i)] & 1) { - cpu_stq_data_ra(env, addr, d1[i], ra); - cpu_stq_data_ra(env, addr + 8, d2[i], ra); - cpu_stq_data_ra(env, addr + 16, d3[i], ra); - } - addr += 3 * 8; + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, d1, i, addr, mmu_idx, ra); + tlb_fn(env, d2, i, addr + msize, mmu_idx, ra); + } + i += esize, pg >>= esize; + addr += 2 * msize; + } while (i & 15); } + set_helper_retaddr(0); } -void HELPER(sve_st4dd_r)(CPUARMState *env, void *vg, - target_ulong addr, uint32_t desc) +static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) { - intptr_t i, oprsz = simd_oprsz(desc) / 8; - intptr_t ra = GETPC(); + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); unsigned rd = simd_data(desc); - uint64_t *d1 = &env->vfp.zregs[rd].d[0]; - uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; - uint64_t *d3 = &env->vfp.zregs[(rd + 2) & 31].d[0]; - uint64_t *d4 = &env->vfp.zregs[(rd + 3) & 31].d[0]; - uint8_t *pg = vg; + void *d1 = &env->vfp.zregs[rd]; + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; - for (i = 0; i < oprsz; i += 1) { - if (pg[H1(i)] & 1) { - cpu_stq_data_ra(env, addr, d1[i], ra); - cpu_stq_data_ra(env, addr + 8, d2[i], ra); - cpu_stq_data_ra(env, addr + 16, d3[i], ra); - cpu_stq_data_ra(env, addr + 24, d4[i], ra); - } - addr += 4 * 8; + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, d1, i, addr, mmu_idx, ra); + tlb_fn(env, d2, i, addr + msize, mmu_idx, ra); + tlb_fn(env, d3, i, addr + 2 * msize, mmu_idx, ra); + } + i += esize, pg >>= esize; + addr += 3 * msize; + } while (i & 15); } + set_helper_retaddr(0); } +static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); + unsigned rd = simd_data(desc); + void *d1 = &env->vfp.zregs[rd]; + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; + void *d4 = &env->vfp.zregs[(rd + 3) & 31]; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, d1, i, addr, mmu_idx, ra); + tlb_fn(env, d2, i, addr + msize, mmu_idx, ra); + tlb_fn(env, d3, i, addr + 2 * msize, mmu_idx, ra); + tlb_fn(env, d4, i, addr + 3 * msize, mmu_idx, ra); + } + i += esize, pg >>= esize; + addr += 4 * msize; + } while (i & 15); + } + set_helper_retaddr(0); +} + +#define DO_STN_1(N, NAME, ESIZE) \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, 1, \ + sve_st1##NAME##_tlb); \ +} + +#define DO_STN_2(N, NAME, ESIZE, MSIZE) \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE, \ + arm_cpu_data_is_big_endian(env) \ + ? sve_st1##NAME##_be_tlb : sve_st1##NAME##_le_tlb); \ +} + +DO_STN_1(1, bb, 1) +DO_STN_1(1, bh, 2) +DO_STN_1(1, bs, 4) +DO_STN_1(1, bd, 8) +DO_STN_1(2, bb, 1) +DO_STN_1(3, bb, 1) +DO_STN_1(4, bb, 1) + +DO_STN_2(1, hh, 2, 2) +DO_STN_2(1, hs, 4, 2) +DO_STN_2(1, hd, 8, 2) +DO_STN_2(2, hh, 2, 2) +DO_STN_2(3, hh, 2, 2) +DO_STN_2(4, hh, 2, 2) + +DO_STN_2(1, ss, 4, 4) +DO_STN_2(1, sd, 8, 4) +DO_STN_2(2, ss, 4, 4) +DO_STN_2(3, ss, 4, 4) +DO_STN_2(4, ss, 4, 4) + +DO_STN_2(1, dd, 8, 8) +DO_STN_2(2, dd, 8, 8) +DO_STN_2(3, dd, 8, 8) +DO_STN_2(4, dd, 8, 8) + +#undef DO_STN_1 +#undef DO_STN_2 + /* Loads with a vector index. */ #define DO_LD1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> We can choose the endianness at translation time, rather than re-computing it at execution time. Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 117 +++++++++++++++------- target/arm/sve_helper.c | 70 ++++++------- target/arm/translate-sve.c | 196 +++++++++++++++++++++++++------------ 3 files changed, 252 insertions(+), 131 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ldff1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ldnf1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ sve_##NAME##_host, sve_##NAME##_tlb); \ } -/* TODO: Propagate the endian check back to the translator. */ #define DO_LD1_2(NAME, ESZ, MSZ) \ -void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - if (arm_cpu_data_is_big_endian(env)) { \ - sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ - sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ - } else { \ - sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ - sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ - } \ +void HELPER(sve_##NAME##_le_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ +} \ +void HELPER(sve_##NAME##_be_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ } DO_LD1_1(ld1bb, 0) @@ -XXX,XX +XXX,XX @@ void __attribute__((flatten)) HELPER(sve_ld##N##bb_r) \ } #define DO_LDN_2(N, SUFF, SIZE) \ -void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_r) \ +void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_le_r) \ (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ { \ sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \ - arm_cpu_data_is_big_endian(env) \ - ? sve_ld1##SUFF##_be_tlb : sve_ld1##SUFF##_le_tlb); \ + sve_ld1##SUFF##_le_tlb); \ +} \ +void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_be_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \ + sve_ld1##SUFF##_be_tlb); \ } DO_LDN_1(2) @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \ sve_ldnf1_r(env, vg, addr, desc, ESZ, 0, sve_ld1##PART##_host); \ } -/* TODO: Propagate the endian check back to the translator. */ #define DO_LDFF1_LDNF1_2(PART, ESZ, MSZ) \ -void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ +void HELPER(sve_ldff1##PART##_le_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ { \ - if (arm_cpu_data_is_big_endian(env)) { \ - sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ - sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ - } else { \ - sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ - sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ - } \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ } \ -void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ +void HELPER(sve_ldnf1##PART##_le_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ { \ - if (arm_cpu_data_is_big_endian(env)) { \ - sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, \ - sve_ld1##PART##_be_host); \ - } else { \ - sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, \ - sve_ld1##PART##_le_host); \ - } \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_le_host); \ +} \ +void HELPER(sve_ldff1##PART##_be_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ +} \ +void HELPER(sve_ldnf1##PART##_be_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_be_host); \ } DO_LDFF1_LDNF1_1(bb, 0) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, static void do_ld_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int dtype, int nreg) { - static gen_helper_gvec_mem * const fns[16][4] = { - { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, - gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, - { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + static gen_helper_gvec_mem * const fns[2][16][4] = { + /* Little-endian */ + { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1sds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hh_r, gen_helper_sve_ld2hh_r, - gen_helper_sve_ld3hh_r, gen_helper_sve_ld4hh_r }, - { gen_helper_sve_ld1hsu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hdu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1sds_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_le_r, gen_helper_sve_ld2hh_le_r, + gen_helper_sve_ld3hh_le_r, gen_helper_sve_ld4hh_le_r }, + { gen_helper_sve_ld1hsu_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_le_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hss_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1ss_r, gen_helper_sve_ld2ss_r, - gen_helper_sve_ld3ss_r, gen_helper_sve_ld4ss_r }, - { gen_helper_sve_ld1sdu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hds_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld2ss_le_r, + gen_helper_sve_ld3ss_le_r, gen_helper_sve_ld4ss_le_r }, + { gen_helper_sve_ld1sdu_le_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1dd_r, gen_helper_sve_ld2dd_r, - gen_helper_sve_ld3dd_r, gen_helper_sve_ld4dd_r }, + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r, + gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } }, + + /* Big-endian */ + { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_be_r, gen_helper_sve_ld2hh_be_r, + gen_helper_sve_ld3hh_be_r, gen_helper_sve_ld4hh_be_r }, + { gen_helper_sve_ld1hsu_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_be_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld2ss_be_r, + gen_helper_sve_ld3ss_be_r, gen_helper_sve_ld4ss_be_r }, + { gen_helper_sve_ld1sdu_be_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r, + gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } }; - gen_helper_gvec_mem *fn = fns[dtype][nreg]; + gen_helper_gvec_mem *fn = fns[s->be_data == MO_BE][dtype][nreg]; /* While there are holes in the table, they are not * accessible via the instruction encoding. @@ -XXX,XX +XXX,XX @@ static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) { - static gen_helper_gvec_mem * const fns[16] = { - gen_helper_sve_ldff1bb_r, - gen_helper_sve_ldff1bhu_r, - gen_helper_sve_ldff1bsu_r, - gen_helper_sve_ldff1bdu_r, + static gen_helper_gvec_mem * const fns[2][16] = { + /* Little-endian */ + { gen_helper_sve_ldff1bb_r, + gen_helper_sve_ldff1bhu_r, + gen_helper_sve_ldff1bsu_r, + gen_helper_sve_ldff1bdu_r, - gen_helper_sve_ldff1sds_r, - gen_helper_sve_ldff1hh_r, - gen_helper_sve_ldff1hsu_r, - gen_helper_sve_ldff1hdu_r, + gen_helper_sve_ldff1sds_le_r, + gen_helper_sve_ldff1hh_le_r, + gen_helper_sve_ldff1hsu_le_r, + gen_helper_sve_ldff1hdu_le_r, - gen_helper_sve_ldff1hds_r, - gen_helper_sve_ldff1hss_r, - gen_helper_sve_ldff1ss_r, - gen_helper_sve_ldff1sdu_r, + gen_helper_sve_ldff1hds_le_r, + gen_helper_sve_ldff1hss_le_r, + gen_helper_sve_ldff1ss_le_r, + gen_helper_sve_ldff1sdu_le_r, - gen_helper_sve_ldff1bds_r, - gen_helper_sve_ldff1bss_r, - gen_helper_sve_ldff1bhs_r, - gen_helper_sve_ldff1dd_r, + gen_helper_sve_ldff1bds_r, + gen_helper_sve_ldff1bss_r, + gen_helper_sve_ldff1bhs_r, + gen_helper_sve_ldff1dd_le_r }, + + /* Big-endian */ + { gen_helper_sve_ldff1bb_r, + gen_helper_sve_ldff1bhu_r, + gen_helper_sve_ldff1bsu_r, + gen_helper_sve_ldff1bdu_r, + + gen_helper_sve_ldff1sds_be_r, + gen_helper_sve_ldff1hh_be_r, + gen_helper_sve_ldff1hsu_be_r, + gen_helper_sve_ldff1hdu_be_r, + + gen_helper_sve_ldff1hds_be_r, + gen_helper_sve_ldff1hss_be_r, + gen_helper_sve_ldff1ss_be_r, + gen_helper_sve_ldff1sdu_be_r, + + gen_helper_sve_ldff1bds_r, + gen_helper_sve_ldff1bss_r, + gen_helper_sve_ldff1bhs_r, + gen_helper_sve_ldff1dd_be_r }, }; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); - do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]); + do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]); } return true; } static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) { - static gen_helper_gvec_mem * const fns[16] = { - gen_helper_sve_ldnf1bb_r, - gen_helper_sve_ldnf1bhu_r, - gen_helper_sve_ldnf1bsu_r, - gen_helper_sve_ldnf1bdu_r, + static gen_helper_gvec_mem * const fns[2][16] = { + /* Little-endian */ + { gen_helper_sve_ldnf1bb_r, + gen_helper_sve_ldnf1bhu_r, + gen_helper_sve_ldnf1bsu_r, + gen_helper_sve_ldnf1bdu_r, - gen_helper_sve_ldnf1sds_r, - gen_helper_sve_ldnf1hh_r, - gen_helper_sve_ldnf1hsu_r, - gen_helper_sve_ldnf1hdu_r, + gen_helper_sve_ldnf1sds_le_r, + gen_helper_sve_ldnf1hh_le_r, + gen_helper_sve_ldnf1hsu_le_r, + gen_helper_sve_ldnf1hdu_le_r, - gen_helper_sve_ldnf1hds_r, - gen_helper_sve_ldnf1hss_r, - gen_helper_sve_ldnf1ss_r, - gen_helper_sve_ldnf1sdu_r, + gen_helper_sve_ldnf1hds_le_r, + gen_helper_sve_ldnf1hss_le_r, + gen_helper_sve_ldnf1ss_le_r, + gen_helper_sve_ldnf1sdu_le_r, - gen_helper_sve_ldnf1bds_r, - gen_helper_sve_ldnf1bss_r, - gen_helper_sve_ldnf1bhs_r, - gen_helper_sve_ldnf1dd_r, + gen_helper_sve_ldnf1bds_r, + gen_helper_sve_ldnf1bss_r, + gen_helper_sve_ldnf1bhs_r, + gen_helper_sve_ldnf1dd_le_r }, + + /* Big-endian */ + { gen_helper_sve_ldnf1bb_r, + gen_helper_sve_ldnf1bhu_r, + gen_helper_sve_ldnf1bsu_r, + gen_helper_sve_ldnf1bdu_r, + + gen_helper_sve_ldnf1sds_be_r, + gen_helper_sve_ldnf1hh_be_r, + gen_helper_sve_ldnf1hsu_be_r, + gen_helper_sve_ldnf1hdu_be_r, + + gen_helper_sve_ldnf1hds_be_r, + gen_helper_sve_ldnf1hss_be_r, + gen_helper_sve_ldnf1ss_be_r, + gen_helper_sve_ldnf1sdu_be_r, + + gen_helper_sve_ldnf1bds_r, + gen_helper_sve_ldnf1bss_r, + gen_helper_sve_ldnf1bhs_r, + gen_helper_sve_ldnf1dd_be_r }, }; if (sve_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), off); - do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]); + do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]); } return true; } static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) { - static gen_helper_gvec_mem * const fns[4] = { - gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_r, - gen_helper_sve_ld1ss_r, gen_helper_sve_ld1dd_r, + static gen_helper_gvec_mem * const fns[2][4] = { + { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_le_r, + gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld1dd_le_r }, + { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_be_r, + gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld1dd_be_r }, }; unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; @@ -XXX,XX +XXX,XX @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_pg, cpu_env, poff); - fns[msz](cpu_env, t_pg, addr, desc); + fns[s->be_data == MO_BE][msz](cpu_env, t_pg, addr, desc); tcg_temp_free_ptr(t_pg); tcg_temp_free_i32(desc); -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> We can choose the endianness at translation time, rather than re-computing it at execution time. Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 48 +++++++++++++++++-------- target/arm/sve_helper.c | 11 ++++-- target/arm/translate-sve.c | 72 +++++++++++++++++++++++++++++--------- 3 files changed, 96 insertions(+), 35 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1hs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1hd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hs_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hs_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1sd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r) \ } #define DO_STN_2(N, NAME, ESIZE, MSIZE) \ -void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r) \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_le_r) \ (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ { \ sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE, \ - arm_cpu_data_is_big_endian(env) \ - ? sve_st1##NAME##_be_tlb : sve_st1##NAME##_le_tlb); \ + sve_st1##NAME##_le_tlb); \ +} \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_be_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE, \ + sve_st1##NAME##_be_tlb); \ } DO_STN_1(1, bb, 1) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { - static gen_helper_gvec_mem * const fn_single[4][4] = { - { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, - gen_helper_sve_st1bs_r, gen_helper_sve_st1bd_r }, - { NULL, gen_helper_sve_st1hh_r, - gen_helper_sve_st1hs_r, gen_helper_sve_st1hd_r }, - { NULL, NULL, - gen_helper_sve_st1ss_r, gen_helper_sve_st1sd_r }, - { NULL, NULL, NULL, gen_helper_sve_st1dd_r }, + static gen_helper_gvec_mem * const fn_single[2][4][4] = { + { { gen_helper_sve_st1bb_r, + gen_helper_sve_st1bh_r, + gen_helper_sve_st1bs_r, + gen_helper_sve_st1bd_r }, + { NULL, + gen_helper_sve_st1hh_le_r, + gen_helper_sve_st1hs_le_r, + gen_helper_sve_st1hd_le_r }, + { NULL, NULL, + gen_helper_sve_st1ss_le_r, + gen_helper_sve_st1sd_le_r }, + { NULL, NULL, NULL, + gen_helper_sve_st1dd_le_r } }, + { { gen_helper_sve_st1bb_r, + gen_helper_sve_st1bh_r, + gen_helper_sve_st1bs_r, + gen_helper_sve_st1bd_r }, + { NULL, + gen_helper_sve_st1hh_be_r, + gen_helper_sve_st1hs_be_r, + gen_helper_sve_st1hd_be_r }, + { NULL, NULL, + gen_helper_sve_st1ss_be_r, + gen_helper_sve_st1sd_be_r }, + { NULL, NULL, NULL, + gen_helper_sve_st1dd_be_r } }, }; - static gen_helper_gvec_mem * const fn_multiple[3][4] = { - { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_r, - gen_helper_sve_st2ss_r, gen_helper_sve_st2dd_r }, - { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_r, - gen_helper_sve_st3ss_r, gen_helper_sve_st3dd_r }, - { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_r, - gen_helper_sve_st4ss_r, gen_helper_sve_st4dd_r }, + static gen_helper_gvec_mem * const fn_multiple[2][3][4] = { + { { gen_helper_sve_st2bb_r, + gen_helper_sve_st2hh_le_r, + gen_helper_sve_st2ss_le_r, + gen_helper_sve_st2dd_le_r }, + { gen_helper_sve_st3bb_r, + gen_helper_sve_st3hh_le_r, + gen_helper_sve_st3ss_le_r, + gen_helper_sve_st3dd_le_r }, + { gen_helper_sve_st4bb_r, + gen_helper_sve_st4hh_le_r, + gen_helper_sve_st4ss_le_r, + gen_helper_sve_st4dd_le_r } }, + { { gen_helper_sve_st2bb_r, + gen_helper_sve_st2hh_be_r, + gen_helper_sve_st2ss_be_r, + gen_helper_sve_st2dd_be_r }, + { gen_helper_sve_st3bb_r, + gen_helper_sve_st3hh_be_r, + gen_helper_sve_st3ss_be_r, + gen_helper_sve_st3dd_be_r }, + { gen_helper_sve_st4bb_r, + gen_helper_sve_st4hh_be_r, + gen_helper_sve_st4ss_be_r, + gen_helper_sve_st4dd_be_r } }, }; gen_helper_gvec_mem *fn; + int be = s->be_data == MO_BE; if (nreg == 0) { /* ST1 */ - fn = fn_single[msz][esz]; + fn = fn_single[be][msz][esz]; } else { /* ST2, ST3, ST4 -- msz == esz, enforced by encoding */ assert(msz == esz); - fn = fn_multiple[nreg - 1][msz]; + fn = fn_multiple[be][nreg - 1][msz]; } assert(fn != NULL); do_mem_zpa(s, zt, pg, addr, fn); -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> This fixes the endianness problem for softmmu, and moves the main loop out of a macro and into an inlined function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 84 +++++++++---- target/arm/sve_helper.c | 225 ++++++++++++++++++++++++---------- target/arm/translate-sve.c | 244 +++++++++++++++++++++++++------------ 3 files changed, 386 insertions(+), 167 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhsu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhsu_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldssu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhsu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbss_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhsu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhsu_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldssu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhsu_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbss_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbdu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldddu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsdu_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbds_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbdu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldddu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsdu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbds_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbdu_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldddu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsdu_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbds_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_STN_2(4, dd, 8, 8) #undef DO_STN_1 #undef DO_STN_2 -/* Loads with a vector index. */ +/* + * Loads with a vector index. + */ -#define DO_LD1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - target_ulong off = *(TYPEI *)(vm + H1_4(i)); \ - m = FN(env, base + (off << scale), ra); \ - } \ - *(uint32_t *)(vd + H1_4(i)) = m; \ - i += 4, pg >>= 4; \ - } while (i & 15); \ - } \ +/* + * Load the element at @reg + @reg_ofs, sign or zero-extend as needed. + */ +typedef target_ulong zreg_off_fn(void *reg, intptr_t reg_ofs); + +static target_ulong off_zsu_s(void *reg, intptr_t reg_ofs) +{ + return *(uint32_t *)(reg + H1_4(reg_ofs)); } -#define DO_LD1_ZPZ_D(NAME, TYPEI, TYPEM, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc) / 8; \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \ - for (i = 0; i < oprsz; i++) { \ - TYPEM mm = 0; \ - if (pg[H1(i)] & 1) { \ - target_ulong off = (TYPEI)m[i]; \ - mm = FN(env, base + (off << scale), ra); \ - } \ - d[i] = mm; \ - } \ +static target_ulong off_zss_s(void *reg, intptr_t reg_ofs) +{ + return *(int32_t *)(reg + H1_4(reg_ofs)); } -DO_LD1_ZPZ_S(sve_ldbsu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhsu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_S(sve_ldssu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_S(sve_ldbss_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhss_zsu, uint32_t, int16_t, cpu_lduw_data_ra) +static target_ulong off_zsu_d(void *reg, intptr_t reg_ofs) +{ + return (uint32_t)*(uint64_t *)(reg + reg_ofs); +} -DO_LD1_ZPZ_S(sve_ldbsu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhsu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_S(sve_ldssu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_S(sve_ldbss_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhss_zss, int32_t, int16_t, cpu_lduw_data_ra) +static target_ulong off_zss_d(void *reg, intptr_t reg_ofs) +{ + return (int32_t)*(uint64_t *)(reg + reg_ofs); +} -DO_LD1_ZPZ_D(sve_ldbdu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhdu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsdu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_D(sve_ldddu_zsu, uint32_t, uint64_t, cpu_ldq_data_ra) -DO_LD1_ZPZ_D(sve_ldbds_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhds_zsu, uint32_t, int16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsds_zsu, uint32_t, int32_t, cpu_ldl_data_ra) +static target_ulong off_zd_d(void *reg, intptr_t reg_ofs) +{ + return *(uint64_t *)(reg + reg_ofs); +} -DO_LD1_ZPZ_D(sve_ldbdu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhdu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsdu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_D(sve_ldddu_zss, int32_t, uint64_t, cpu_ldq_data_ra) -DO_LD1_ZPZ_D(sve_ldbds_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhds_zss, int32_t, int16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsds_zss, int32_t, int32_t, cpu_ldl_data_ra) +static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); + unsigned scale = simd_data(desc); + ARMVectorReg scratch = { }; -DO_LD1_ZPZ_D(sve_ldbdu_zd, uint64_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhdu_zd, uint64_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsdu_zd, uint64_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_D(sve_ldddu_zd, uint64_t, uint64_t, cpu_ldq_data_ra) -DO_LD1_ZPZ_D(sve_ldbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i); + tlb_fn(env, &scratch, i, base + (off << scale), mmu_idx, ra); + } + i += 4, pg >>= 4; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(vd, &scratch, oprsz); +} + +static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc) / 8; + unsigned scale = simd_data(desc); + ARMVectorReg scratch = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; i++) { + uint8_t pg = *(uint8_t *)(vg + H1(i)); + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i * 8); + tlb_fn(env, &scratch, i * 8, base + (off << scale), mmu_idx, ra); + } + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(vd, &scratch, oprsz * 8); +} + +#define DO_LD1_ZPZ_S(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_ld##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_ld1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_ld1##MEM##_tlb); \ +} + +#define DO_LD1_ZPZ_D(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_ld##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_ld1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_ld1##MEM##_tlb); \ +} + +DO_LD1_ZPZ_S(bsu, zsu) +DO_LD1_ZPZ_S(bsu, zss) +DO_LD1_ZPZ_D(bdu, zsu) +DO_LD1_ZPZ_D(bdu, zss) +DO_LD1_ZPZ_D(bdu, zd) + +DO_LD1_ZPZ_S(bss, zsu) +DO_LD1_ZPZ_S(bss, zss) +DO_LD1_ZPZ_D(bds, zsu) +DO_LD1_ZPZ_D(bds, zss) +DO_LD1_ZPZ_D(bds, zd) + +DO_LD1_ZPZ_S(hsu_le, zsu) +DO_LD1_ZPZ_S(hsu_le, zss) +DO_LD1_ZPZ_D(hdu_le, zsu) +DO_LD1_ZPZ_D(hdu_le, zss) +DO_LD1_ZPZ_D(hdu_le, zd) + +DO_LD1_ZPZ_S(hsu_be, zsu) +DO_LD1_ZPZ_S(hsu_be, zss) +DO_LD1_ZPZ_D(hdu_be, zsu) +DO_LD1_ZPZ_D(hdu_be, zss) +DO_LD1_ZPZ_D(hdu_be, zd) + +DO_LD1_ZPZ_S(hss_le, zsu) +DO_LD1_ZPZ_S(hss_le, zss) +DO_LD1_ZPZ_D(hds_le, zsu) +DO_LD1_ZPZ_D(hds_le, zss) +DO_LD1_ZPZ_D(hds_le, zd) + +DO_LD1_ZPZ_S(hss_be, zsu) +DO_LD1_ZPZ_S(hss_be, zss) +DO_LD1_ZPZ_D(hds_be, zsu) +DO_LD1_ZPZ_D(hds_be, zss) +DO_LD1_ZPZ_D(hds_be, zd) + +DO_LD1_ZPZ_S(ss_le, zsu) +DO_LD1_ZPZ_S(ss_le, zss) +DO_LD1_ZPZ_D(sdu_le, zsu) +DO_LD1_ZPZ_D(sdu_le, zss) +DO_LD1_ZPZ_D(sdu_le, zd) + +DO_LD1_ZPZ_S(ss_be, zsu) +DO_LD1_ZPZ_S(ss_be, zss) +DO_LD1_ZPZ_D(sdu_be, zsu) +DO_LD1_ZPZ_D(sdu_be, zss) +DO_LD1_ZPZ_D(sdu_be, zd) + +DO_LD1_ZPZ_D(sds_le, zsu) +DO_LD1_ZPZ_D(sds_le, zss) +DO_LD1_ZPZ_D(sds_le, zd) + +DO_LD1_ZPZ_D(sds_be, zsu) +DO_LD1_ZPZ_D(sds_be, zss) +DO_LD1_ZPZ_D(sds_be, zd) + +DO_LD1_ZPZ_D(dd_le, zsu) +DO_LD1_ZPZ_D(dd_le, zss) +DO_LD1_ZPZ_D(dd_le, zd) + +DO_LD1_ZPZ_D(dd_be, zsu) +DO_LD1_ZPZ_D(dd_be, zss) +DO_LD1_ZPZ_D(dd_be, zd) + +#undef DO_LD1_ZPZ_S +#undef DO_LD1_ZPZ_D /* First fault loads with a vector index. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, int scale, tcg_temp_free_i32(desc); } -/* Indexed by [ff][xs][u][msz]. */ -static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][3] = { - { { { gen_helper_sve_ldbss_zsu, - gen_helper_sve_ldhss_zsu, - NULL, }, - { gen_helper_sve_ldbsu_zsu, - gen_helper_sve_ldhsu_zsu, - gen_helper_sve_ldssu_zsu, } }, - { { gen_helper_sve_ldbss_zss, - gen_helper_sve_ldhss_zss, - NULL, }, - { gen_helper_sve_ldbsu_zss, - gen_helper_sve_ldhsu_zss, - gen_helper_sve_ldssu_zss, } } }, +/* Indexed by [be][ff][xs][u][msz]. */ +static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][2][3] = { + /* Little-endian */ + { { { { gen_helper_sve_ldbss_zsu, + gen_helper_sve_ldhss_le_zsu, + NULL, }, + { gen_helper_sve_ldbsu_zsu, + gen_helper_sve_ldhsu_le_zsu, + gen_helper_sve_ldss_le_zsu, } }, + { { gen_helper_sve_ldbss_zss, + gen_helper_sve_ldhss_le_zss, + NULL, }, + { gen_helper_sve_ldbsu_zss, + gen_helper_sve_ldhsu_le_zss, + gen_helper_sve_ldss_le_zss, } } }, - { { { gen_helper_sve_ldffbss_zsu, - gen_helper_sve_ldffhss_zsu, - NULL, }, - { gen_helper_sve_ldffbsu_zsu, - gen_helper_sve_ldffhsu_zsu, - gen_helper_sve_ldffssu_zsu, } }, - { { gen_helper_sve_ldffbss_zss, - gen_helper_sve_ldffhss_zss, - NULL, }, - { gen_helper_sve_ldffbsu_zss, - gen_helper_sve_ldffhsu_zss, - gen_helper_sve_ldffssu_zss, } } } + /* First-fault */ + { { { gen_helper_sve_ldffbss_zsu, + gen_helper_sve_ldffhss_zsu, + NULL, }, + { gen_helper_sve_ldffbsu_zsu, + gen_helper_sve_ldffhsu_zsu, + gen_helper_sve_ldffssu_zsu, } }, + { { gen_helper_sve_ldffbss_zss, + gen_helper_sve_ldffhss_zss, + NULL, }, + { gen_helper_sve_ldffbsu_zss, + gen_helper_sve_ldffhsu_zss, + gen_helper_sve_ldffssu_zss, } } } }, + + /* Big-endian */ + { { { { gen_helper_sve_ldbss_zsu, + gen_helper_sve_ldhss_be_zsu, + NULL, }, + { gen_helper_sve_ldbsu_zsu, + gen_helper_sve_ldhsu_be_zsu, + gen_helper_sve_ldss_be_zsu, } }, + { { gen_helper_sve_ldbss_zss, + gen_helper_sve_ldhss_be_zss, + NULL, }, + { gen_helper_sve_ldbsu_zss, + gen_helper_sve_ldhsu_be_zss, + gen_helper_sve_ldss_be_zss, } } }, + + /* First-fault */ + { { { gen_helper_sve_ldffbss_zsu, + gen_helper_sve_ldffhss_zsu, + NULL, }, + { gen_helper_sve_ldffbsu_zsu, + gen_helper_sve_ldffhsu_zsu, + gen_helper_sve_ldffssu_zsu, } }, + { { gen_helper_sve_ldffbss_zss, + gen_helper_sve_ldffhss_zss, + NULL, }, + { gen_helper_sve_ldffbsu_zss, + gen_helper_sve_ldffhsu_zss, + gen_helper_sve_ldffssu_zss, } } } }, }; /* Note that we overload xs=2 to indicate 64-bit offset. */ -static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][3][2][4] = { - { { { gen_helper_sve_ldbds_zsu, - gen_helper_sve_ldhds_zsu, - gen_helper_sve_ldsds_zsu, - NULL, }, - { gen_helper_sve_ldbdu_zsu, - gen_helper_sve_ldhdu_zsu, - gen_helper_sve_ldsdu_zsu, - gen_helper_sve_ldddu_zsu, } }, - { { gen_helper_sve_ldbds_zss, - gen_helper_sve_ldhds_zss, - gen_helper_sve_ldsds_zss, - NULL, }, - { gen_helper_sve_ldbdu_zss, - gen_helper_sve_ldhdu_zss, - gen_helper_sve_ldsdu_zss, - gen_helper_sve_ldddu_zss, } }, - { { gen_helper_sve_ldbds_zd, - gen_helper_sve_ldhds_zd, - gen_helper_sve_ldsds_zd, - NULL, }, - { gen_helper_sve_ldbdu_zd, - gen_helper_sve_ldhdu_zd, - gen_helper_sve_ldsdu_zd, - gen_helper_sve_ldddu_zd, } } }, +static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][2][3][2][4] = { + /* Little-endian */ + { { { { gen_helper_sve_ldbds_zsu, + gen_helper_sve_ldhds_le_zsu, + gen_helper_sve_ldsds_le_zsu, + NULL, }, + { gen_helper_sve_ldbdu_zsu, + gen_helper_sve_ldhdu_le_zsu, + gen_helper_sve_ldsdu_le_zsu, + gen_helper_sve_lddd_le_zsu, } }, + { { gen_helper_sve_ldbds_zss, + gen_helper_sve_ldhds_le_zss, + gen_helper_sve_ldsds_le_zss, + NULL, }, + { gen_helper_sve_ldbdu_zss, + gen_helper_sve_ldhdu_le_zss, + gen_helper_sve_ldsdu_le_zss, + gen_helper_sve_lddd_le_zss, } }, + { { gen_helper_sve_ldbds_zd, + gen_helper_sve_ldhds_le_zd, + gen_helper_sve_ldsds_le_zd, + NULL, }, + { gen_helper_sve_ldbdu_zd, + gen_helper_sve_ldhdu_le_zd, + gen_helper_sve_ldsdu_le_zd, + gen_helper_sve_lddd_le_zd, } } }, - { { { gen_helper_sve_ldffbds_zsu, - gen_helper_sve_ldffhds_zsu, - gen_helper_sve_ldffsds_zsu, - NULL, }, - { gen_helper_sve_ldffbdu_zsu, - gen_helper_sve_ldffhdu_zsu, - gen_helper_sve_ldffsdu_zsu, - gen_helper_sve_ldffddu_zsu, } }, - { { gen_helper_sve_ldffbds_zss, - gen_helper_sve_ldffhds_zss, - gen_helper_sve_ldffsds_zss, - NULL, }, - { gen_helper_sve_ldffbdu_zss, - gen_helper_sve_ldffhdu_zss, - gen_helper_sve_ldffsdu_zss, - gen_helper_sve_ldffddu_zss, } }, - { { gen_helper_sve_ldffbds_zd, - gen_helper_sve_ldffhds_zd, - gen_helper_sve_ldffsds_zd, - NULL, }, - { gen_helper_sve_ldffbdu_zd, - gen_helper_sve_ldffhdu_zd, - gen_helper_sve_ldffsdu_zd, - gen_helper_sve_ldffddu_zd, } } } + /* First-fault */ + { { { gen_helper_sve_ldffbds_zsu, + gen_helper_sve_ldffhds_zsu, + gen_helper_sve_ldffsds_zsu, + NULL, }, + { gen_helper_sve_ldffbdu_zsu, + gen_helper_sve_ldffhdu_zsu, + gen_helper_sve_ldffsdu_zsu, + gen_helper_sve_ldffddu_zsu, } }, + { { gen_helper_sve_ldffbds_zss, + gen_helper_sve_ldffhds_zss, + gen_helper_sve_ldffsds_zss, + NULL, }, + { gen_helper_sve_ldffbdu_zss, + gen_helper_sve_ldffhdu_zss, + gen_helper_sve_ldffsdu_zss, + gen_helper_sve_ldffddu_zss, } }, + { { gen_helper_sve_ldffbds_zd, + gen_helper_sve_ldffhds_zd, + gen_helper_sve_ldffsds_zd, + NULL, }, + { gen_helper_sve_ldffbdu_zd, + gen_helper_sve_ldffhdu_zd, + gen_helper_sve_ldffsdu_zd, + gen_helper_sve_ldffddu_zd, } } } }, + + /* Big-endian */ + { { { { gen_helper_sve_ldbds_zsu, + gen_helper_sve_ldhds_be_zsu, + gen_helper_sve_ldsds_be_zsu, + NULL, }, + { gen_helper_sve_ldbdu_zsu, + gen_helper_sve_ldhdu_be_zsu, + gen_helper_sve_ldsdu_be_zsu, + gen_helper_sve_lddd_be_zsu, } }, + { { gen_helper_sve_ldbds_zss, + gen_helper_sve_ldhds_be_zss, + gen_helper_sve_ldsds_be_zss, + NULL, }, + { gen_helper_sve_ldbdu_zss, + gen_helper_sve_ldhdu_be_zss, + gen_helper_sve_ldsdu_be_zss, + gen_helper_sve_lddd_be_zss, } }, + { { gen_helper_sve_ldbds_zd, + gen_helper_sve_ldhds_be_zd, + gen_helper_sve_ldsds_be_zd, + NULL, }, + { gen_helper_sve_ldbdu_zd, + gen_helper_sve_ldhdu_be_zd, + gen_helper_sve_ldsdu_be_zd, + gen_helper_sve_lddd_be_zd, } } }, + + /* First-fault */ + { { { gen_helper_sve_ldffbds_zsu, + gen_helper_sve_ldffhds_zsu, + gen_helper_sve_ldffsds_zsu, + NULL, }, + { gen_helper_sve_ldffbdu_zsu, + gen_helper_sve_ldffhdu_zsu, + gen_helper_sve_ldffsdu_zsu, + gen_helper_sve_ldffddu_zsu, } }, + { { gen_helper_sve_ldffbds_zss, + gen_helper_sve_ldffhds_zss, + gen_helper_sve_ldffsds_zss, + NULL, }, + { gen_helper_sve_ldffbdu_zss, + gen_helper_sve_ldffhdu_zss, + gen_helper_sve_ldffsdu_zss, + gen_helper_sve_ldffddu_zss, } }, + { { gen_helper_sve_ldffbds_zd, + gen_helper_sve_ldffhds_zd, + gen_helper_sve_ldffsds_zd, + NULL, }, + { gen_helper_sve_ldffbdu_zd, + gen_helper_sve_ldffhdu_zd, + gen_helper_sve_ldffsdu_zd, + gen_helper_sve_ldffddu_zd, } } } }, }; static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn = NULL; + int be = s->be_data == MO_BE; if (!sve_access_check(s)) { return true; @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) switch (a->esz) { case MO_32: - fn = gather_load_fn32[a->ff][a->xs][a->u][a->msz]; + fn = gather_load_fn32[be][a->ff][a->xs][a->u][a->msz]; break; case MO_64: - fn = gather_load_fn64[a->ff][a->xs][a->u][a->msz]; + fn = gather_load_fn64[be][a->ff][a->xs][a->u][a->msz]; break; } assert(fn != NULL); @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn = NULL; + int be = s->be_data == MO_BE; TCGv_i64 imm; if (a->esz < a->msz || (a->esz == a->msz && !a->u)) { @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) switch (a->esz) { case MO_32: - fn = gather_load_fn32[a->ff][0][a->u][a->msz]; + fn = gather_load_fn32[be][a->ff][0][a->u][a->msz]; break; case MO_64: - fn = gather_load_fn64[a->ff][2][a->u][a->msz]; + fn = gather_load_fn64[be][a->ff][2][a->u][a->msz]; break; } assert(fn != NULL); -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> This fixes the endianness problem for softmmu, and moves the main loop out of a macro and into an inlined function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 52 ++++++++++---- target/arm/sve_helper.c | 139 ++++++++++++++++++++++++------------- target/arm/translate-sve.c | 74 +++++++++++++------- 3 files changed, 177 insertions(+), 88 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_ldffsds_zd, TCG_CALL_NO_WG, DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbs_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sths_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbd_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbd_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbd_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDFF1_ZPZ_D(sve_ldffsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) /* Stores with a vector index. */ -#define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (likely(pg & 1)) { \ - target_ulong off = *(TYPEI *)(vm + H1_4(i)); \ - uint32_t d = *(uint32_t *)(vd + H1_4(i)); \ - FN(env, base + (off << scale), d, ra); \ - } \ - i += sizeof(uint32_t), pg >>= sizeof(uint32_t); \ - } while (i & 15); \ - } \ +static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc); + unsigned scale = simd_data(desc); + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i); + tlb_fn(env, vd, i, base + (off << scale), mmu_idx, ra); + } + i += 4, pg >>= 4; + } while (i & 15); + } + set_helper_retaddr(0); } -#define DO_ST1_ZPZ_D(NAME, TYPEI, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc) / 8; \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \ - for (i = 0; i < oprsz; i++) { \ - if (likely(pg[H1(i)] & 1)) { \ - target_ulong off = (target_ulong)(TYPEI)m[i] << scale; \ - FN(env, base + off, d[i], ra); \ - } \ - } \ +static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t i, oprsz = simd_oprsz(desc) / 8; + unsigned scale = simd_data(desc); + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; i++) { + uint8_t pg = *(uint8_t *)(vg + H1(i)); + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i * 8); + tlb_fn(env, vd, i * 8, base + (off << scale), mmu_idx, ra); + } + } + set_helper_retaddr(0); } -DO_ST1_ZPZ_S(sve_stbs_zsu, uint32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_S(sve_sths_zsu, uint32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_S(sve_stss_zsu, uint32_t, cpu_stl_data_ra) +#define DO_ST1_ZPZ_S(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_st1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_st1##MEM##_tlb); \ +} -DO_ST1_ZPZ_S(sve_stbs_zss, int32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_S(sve_sths_zss, int32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_S(sve_stss_zss, int32_t, cpu_stl_data_ra) +#define DO_ST1_ZPZ_D(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_st1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_st1##MEM##_tlb); \ +} -DO_ST1_ZPZ_D(sve_stbd_zsu, uint32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zsu, uint32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zsu, uint32_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zsu, uint32_t, cpu_stq_data_ra) +DO_ST1_ZPZ_S(bs, zsu) +DO_ST1_ZPZ_S(hs_le, zsu) +DO_ST1_ZPZ_S(hs_be, zsu) +DO_ST1_ZPZ_S(ss_le, zsu) +DO_ST1_ZPZ_S(ss_be, zsu) -DO_ST1_ZPZ_D(sve_stbd_zss, int32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zss, int32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zss, int32_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zss, int32_t, cpu_stq_data_ra) +DO_ST1_ZPZ_S(bs, zss) +DO_ST1_ZPZ_S(hs_le, zss) +DO_ST1_ZPZ_S(hs_be, zss) +DO_ST1_ZPZ_S(ss_le, zss) +DO_ST1_ZPZ_S(ss_be, zss) -DO_ST1_ZPZ_D(sve_stbd_zd, uint64_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zd, uint64_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zd, uint64_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zd, uint64_t, cpu_stq_data_ra) +DO_ST1_ZPZ_D(bd, zsu) +DO_ST1_ZPZ_D(hd_le, zsu) +DO_ST1_ZPZ_D(hd_be, zsu) +DO_ST1_ZPZ_D(sd_le, zsu) +DO_ST1_ZPZ_D(sd_be, zsu) +DO_ST1_ZPZ_D(dd_le, zsu) +DO_ST1_ZPZ_D(dd_be, zsu) + +DO_ST1_ZPZ_D(bd, zss) +DO_ST1_ZPZ_D(hd_le, zss) +DO_ST1_ZPZ_D(hd_be, zss) +DO_ST1_ZPZ_D(sd_le, zss) +DO_ST1_ZPZ_D(sd_be, zss) +DO_ST1_ZPZ_D(dd_le, zss) +DO_ST1_ZPZ_D(dd_be, zss) + +DO_ST1_ZPZ_D(bd, zd) +DO_ST1_ZPZ_D(hd_le, zd) +DO_ST1_ZPZ_D(hd_be, zd) +DO_ST1_ZPZ_D(sd_le, zd) +DO_ST1_ZPZ_D(sd_be, zd) +DO_ST1_ZPZ_D(dd_le, zd) +DO_ST1_ZPZ_D(dd_be, zd) + +#undef DO_ST1_ZPZ_S +#undef DO_ST1_ZPZ_D diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) return true; } -/* Indexed by [xs][msz]. */ -static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][3] = { - { gen_helper_sve_stbs_zsu, - gen_helper_sve_sths_zsu, - gen_helper_sve_stss_zsu, }, - { gen_helper_sve_stbs_zss, - gen_helper_sve_sths_zss, - gen_helper_sve_stss_zss, }, +/* Indexed by [be][xs][msz]. */ +static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][3] = { + /* Little-endian */ + { { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_le_zsu, + gen_helper_sve_stss_le_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_le_zss, + gen_helper_sve_stss_le_zss, } }, + /* Big-endian */ + { { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_be_zsu, + gen_helper_sve_stss_be_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_be_zss, + gen_helper_sve_stss_be_zss, } }, }; /* Note that we overload xs=2 to indicate 64-bit offset. */ -static gen_helper_gvec_mem_scatter * const scatter_store_fn64[3][4] = { - { gen_helper_sve_stbd_zsu, - gen_helper_sve_sthd_zsu, - gen_helper_sve_stsd_zsu, - gen_helper_sve_stdd_zsu, }, - { gen_helper_sve_stbd_zss, - gen_helper_sve_sthd_zss, - gen_helper_sve_stsd_zss, - gen_helper_sve_stdd_zss, }, - { gen_helper_sve_stbd_zd, - gen_helper_sve_sthd_zd, - gen_helper_sve_stsd_zd, - gen_helper_sve_stdd_zd, }, +static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][3][4] = { + /* Little-endian */ + { { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_le_zsu, + gen_helper_sve_stsd_le_zsu, + gen_helper_sve_stdd_le_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_le_zss, + gen_helper_sve_stsd_le_zss, + gen_helper_sve_stdd_le_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_le_zd, + gen_helper_sve_stsd_le_zd, + gen_helper_sve_stdd_le_zd, } }, + /* Big-endian */ + { { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_be_zsu, + gen_helper_sve_stsd_be_zsu, + gen_helper_sve_stdd_be_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_be_zss, + gen_helper_sve_stsd_be_zss, + gen_helper_sve_stdd_be_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_be_zd, + gen_helper_sve_stsd_be_zd, + gen_helper_sve_stdd_be_zd, } }, }; static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn; + int be = s->be_data == MO_BE; if (a->esz < a->msz || (a->msz == 0 && a->scale)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) } switch (a->esz) { case MO_32: - fn = scatter_store_fn32[a->xs][a->msz]; + fn = scatter_store_fn32[be][a->xs][a->msz]; break; case MO_64: - fn = scatter_store_fn64[a->xs][a->msz]; + fn = scatter_store_fn64[be][a->xs][a->msz]; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn = NULL; + int be = s->be_data == MO_BE; TCGv_i64 imm; if (a->esz < a->msz) { @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) switch (a->esz) { case MO_32: - fn = scatter_store_fn32[0][a->msz]; + fn = scatter_store_fn32[be][0][a->msz]; break; case MO_64: - fn = scatter_store_fn64[2][a->msz]; + fn = scatter_store_fn64[be][2][a->msz]; break; } assert(fn != NULL); -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> This implements the feature for softmmu, and moves the main loop out of a macro and into a function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 84 ++++++++--- target/arm/sve_helper.c | 290 +++++++++++++++++++++++++++---------- target/arm/translate-sve.c | 84 +++++------ 3 files changed, 321 insertions(+), 137 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_ldsds_be_zd, TCG_CALL_NO_WG, DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhsu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhsu_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffssu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhsu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbss_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbsu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhsu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhsu_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffssu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhsu_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbss_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbdu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffddu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsdu_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbds_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbdu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffddu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsdu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbds_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbdu_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffddu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsdu_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbds_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LD1_ZPZ_D(dd_be, zd) /* First fault loads with a vector index. */ -#ifdef CONFIG_USER_ONLY +/* Load one element into VD+REG_OFF from (ENV,VADDR) without faulting. + * The controlling predicate is known to be true. Return true if the + * load was successful. + */ +typedef bool sve_ld1_nf_fn(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong vaddr, int mmu_idx); -#define DO_LDFF1_ZPZ(NAME, TYPEE, TYPEI, TYPEM, FN, H) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - bool first = true; \ - mmap_lock(); \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - target_ulong off = *(TYPEI *)(vm + H(i)); \ - target_ulong addr = base + (off << scale); \ - if (!first && \ - page_check_range(addr, sizeof(TYPEM), PAGE_READ)) { \ - record_fault(env, i, oprsz); \ - goto exit; \ - } \ - m = FN(env, addr, ra); \ - first = false; \ - } \ - *(TYPEE *)(vd + H(i)) = m; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - } while (i & 15); \ - } \ - exit: \ - mmap_unlock(); \ +#ifdef CONFIG_SOFTMMU +#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \ +static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx) \ +{ \ + target_ulong next_page = -(addr | TARGET_PAGE_MASK); \ + if (likely(next_page - addr >= sizeof(TYPEM))) { \ + void *host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx); \ + if (likely(host)) { \ + TYPEM val = HOST(host); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ + return true; \ + } \ + } \ + return false; \ } - #else - -#define DO_LDFF1_ZPZ(NAME, TYPEE, TYPEI, TYPEM, FN, H) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - g_assert_not_reached(); \ +#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \ +static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx) \ +{ \ + if (likely(page_check_range(addr, sizeof(TYPEM), PAGE_READ))) { \ + TYPEM val = HOST(g2h(addr)); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ + return true; \ + } \ + return false; \ } - #endif -#define DO_LDFF1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ - DO_LDFF1_ZPZ(NAME, uint32_t, TYPEI, TYPEM, FN, H1_4) -#define DO_LDFF1_ZPZ_D(NAME, TYPEI, TYPEM, FN) \ - DO_LDFF1_ZPZ(NAME, uint64_t, TYPEI, TYPEM, FN, ) +DO_LD_NF(bsu, H1_4, uint32_t, uint8_t, ldub_p) +DO_LD_NF(bss, H1_4, uint32_t, int8_t, ldsb_p) +DO_LD_NF(bdu, , uint64_t, uint8_t, ldub_p) +DO_LD_NF(bds, , uint64_t, int8_t, ldsb_p) -DO_LDFF1_ZPZ_S(sve_ldffbsu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhsu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffssu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffbss_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhss_zsu, uint32_t, int16_t, cpu_lduw_data_ra) +DO_LD_NF(hsu_le, H1_4, uint32_t, uint16_t, lduw_le_p) +DO_LD_NF(hss_le, H1_4, uint32_t, int16_t, ldsw_le_p) +DO_LD_NF(hsu_be, H1_4, uint32_t, uint16_t, lduw_be_p) +DO_LD_NF(hss_be, H1_4, uint32_t, int16_t, ldsw_be_p) +DO_LD_NF(hdu_le, , uint64_t, uint16_t, lduw_le_p) +DO_LD_NF(hds_le, , uint64_t, int16_t, ldsw_le_p) +DO_LD_NF(hdu_be, , uint64_t, uint16_t, lduw_be_p) +DO_LD_NF(hds_be, , uint64_t, int16_t, ldsw_be_p) -DO_LDFF1_ZPZ_S(sve_ldffbsu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhsu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffssu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffbss_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhss_zss, int32_t, int16_t, cpu_lduw_data_ra) +DO_LD_NF(ss_le, H1_4, uint32_t, uint32_t, ldl_le_p) +DO_LD_NF(ss_be, H1_4, uint32_t, uint32_t, ldl_be_p) +DO_LD_NF(sdu_le, , uint64_t, uint32_t, ldl_le_p) +DO_LD_NF(sds_le, , uint64_t, int32_t, ldl_le_p) +DO_LD_NF(sdu_be, , uint64_t, uint32_t, ldl_be_p) +DO_LD_NF(sds_be, , uint64_t, int32_t, ldl_be_p) -DO_LDFF1_ZPZ_D(sve_ldffbdu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhdu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsdu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffddu_zsu, uint32_t, uint64_t, cpu_ldq_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffbds_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhds_zsu, uint32_t, int16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsds_zsu, uint32_t, int32_t, cpu_ldl_data_ra) +DO_LD_NF(dd_le, , uint64_t, uint64_t, ldq_le_p) +DO_LD_NF(dd_be, , uint64_t, uint64_t, ldq_be_p) -DO_LDFF1_ZPZ_D(sve_ldffbdu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhdu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsdu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffddu_zss, int32_t, uint64_t, cpu_ldq_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffbds_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhds_zss, int32_t, int16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsds_zss, int32_t, int32_t, cpu_ldl_data_ra) +/* + * Common helper for all gather first-faulting loads. + */ +static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn, + sve_ld1_nf_fn *nonfault_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t reg_off, reg_max = simd_oprsz(desc); + unsigned scale = simd_data(desc); + target_ulong addr; -DO_LDFF1_ZPZ_D(sve_ldffbdu_zd, uint64_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhdu_zd, uint64_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsdu_zd, uint64_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffddu_zd, uint64_t, uint64_t, cpu_ldq_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) + /* Skip to the first true predicate. */ + reg_off = find_next_active(vg, 0, reg_max, MO_32); + if (likely(reg_off < reg_max)) { + /* Perform one normal read, which will fault or not. */ + set_helper_retaddr(ra); + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + tlb_fn(env, vd, reg_off, addr, mmu_idx, ra); + + /* The rest of the reads will be non-faulting. */ + set_helper_retaddr(0); + } + + /* After any fault, zero the leading predicated false elements. */ + swap_memzero(vd, reg_off); + + while (likely((reg_off += 4) < reg_max)) { + uint64_t pg = *(uint64_t *)(vg + (reg_off >> 6) * 8); + if (likely((pg >> (reg_off & 63)) & 1)) { + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + if (!nonfault_fn(env, vd, reg_off, addr, mmu_idx)) { + record_fault(env, reg_off, reg_max); + break; + } + } else { + *(uint32_t *)(vd + H1_4(reg_off)) = 0; + } + } +} + +static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn, + sve_ld1_nf_fn *nonfault_fn) +{ + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t reg_off, reg_max = simd_oprsz(desc); + unsigned scale = simd_data(desc); + target_ulong addr; + + /* Skip to the first true predicate. */ + reg_off = find_next_active(vg, 0, reg_max, MO_64); + if (likely(reg_off < reg_max)) { + /* Perform one normal read, which will fault or not. */ + set_helper_retaddr(ra); + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + tlb_fn(env, vd, reg_off, addr, mmu_idx, ra); + + /* The rest of the reads will be non-faulting. */ + set_helper_retaddr(0); + } + + /* After any fault, zero the leading predicated false elements. */ + swap_memzero(vd, reg_off); + + while (likely((reg_off += 8) < reg_max)) { + uint8_t pg = *(uint8_t *)(vg + H1(reg_off >> 3)); + if (likely(pg & 1)) { + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + if (!nonfault_fn(env, vd, reg_off, addr, mmu_idx)) { + record_fault(env, reg_off, reg_max); + break; + } + } else { + *(uint64_t *)(vd + reg_off) = 0; + } + } +} + +#define DO_LDFF1_ZPZ_S(MEM, OFS) \ +void HELPER(sve_ldff##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_ldff1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_ld1##MEM##_tlb, sve_ld##MEM##_nf); \ +} + +#define DO_LDFF1_ZPZ_D(MEM, OFS) \ +void HELPER(sve_ldff##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_ldff1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_ld1##MEM##_tlb, sve_ld##MEM##_nf); \ +} + +DO_LDFF1_ZPZ_S(bsu, zsu) +DO_LDFF1_ZPZ_S(bsu, zss) +DO_LDFF1_ZPZ_D(bdu, zsu) +DO_LDFF1_ZPZ_D(bdu, zss) +DO_LDFF1_ZPZ_D(bdu, zd) + +DO_LDFF1_ZPZ_S(bss, zsu) +DO_LDFF1_ZPZ_S(bss, zss) +DO_LDFF1_ZPZ_D(bds, zsu) +DO_LDFF1_ZPZ_D(bds, zss) +DO_LDFF1_ZPZ_D(bds, zd) + +DO_LDFF1_ZPZ_S(hsu_le, zsu) +DO_LDFF1_ZPZ_S(hsu_le, zss) +DO_LDFF1_ZPZ_D(hdu_le, zsu) +DO_LDFF1_ZPZ_D(hdu_le, zss) +DO_LDFF1_ZPZ_D(hdu_le, zd) + +DO_LDFF1_ZPZ_S(hsu_be, zsu) +DO_LDFF1_ZPZ_S(hsu_be, zss) +DO_LDFF1_ZPZ_D(hdu_be, zsu) +DO_LDFF1_ZPZ_D(hdu_be, zss) +DO_LDFF1_ZPZ_D(hdu_be, zd) + +DO_LDFF1_ZPZ_S(hss_le, zsu) +DO_LDFF1_ZPZ_S(hss_le, zss) +DO_LDFF1_ZPZ_D(hds_le, zsu) +DO_LDFF1_ZPZ_D(hds_le, zss) +DO_LDFF1_ZPZ_D(hds_le, zd) + +DO_LDFF1_ZPZ_S(hss_be, zsu) +DO_LDFF1_ZPZ_S(hss_be, zss) +DO_LDFF1_ZPZ_D(hds_be, zsu) +DO_LDFF1_ZPZ_D(hds_be, zss) +DO_LDFF1_ZPZ_D(hds_be, zd) + +DO_LDFF1_ZPZ_S(ss_le, zsu) +DO_LDFF1_ZPZ_S(ss_le, zss) +DO_LDFF1_ZPZ_D(sdu_le, zsu) +DO_LDFF1_ZPZ_D(sdu_le, zss) +DO_LDFF1_ZPZ_D(sdu_le, zd) + +DO_LDFF1_ZPZ_S(ss_be, zsu) +DO_LDFF1_ZPZ_S(ss_be, zss) +DO_LDFF1_ZPZ_D(sdu_be, zsu) +DO_LDFF1_ZPZ_D(sdu_be, zss) +DO_LDFF1_ZPZ_D(sdu_be, zd) + +DO_LDFF1_ZPZ_D(sds_le, zsu) +DO_LDFF1_ZPZ_D(sds_le, zss) +DO_LDFF1_ZPZ_D(sds_le, zd) + +DO_LDFF1_ZPZ_D(sds_be, zsu) +DO_LDFF1_ZPZ_D(sds_be, zss) +DO_LDFF1_ZPZ_D(sds_be, zd) + +DO_LDFF1_ZPZ_D(dd_le, zsu) +DO_LDFF1_ZPZ_D(dd_le, zss) +DO_LDFF1_ZPZ_D(dd_le, zd) + +DO_LDFF1_ZPZ_D(dd_be, zsu) +DO_LDFF1_ZPZ_D(dd_be, zss) +DO_LDFF1_ZPZ_D(dd_be, zd) /* Stores with a vector index. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][2][3] = { /* First-fault */ { { { gen_helper_sve_ldffbss_zsu, - gen_helper_sve_ldffhss_zsu, + gen_helper_sve_ldffhss_le_zsu, NULL, }, { gen_helper_sve_ldffbsu_zsu, - gen_helper_sve_ldffhsu_zsu, - gen_helper_sve_ldffssu_zsu, } }, + gen_helper_sve_ldffhsu_le_zsu, + gen_helper_sve_ldffss_le_zsu, } }, { { gen_helper_sve_ldffbss_zss, - gen_helper_sve_ldffhss_zss, + gen_helper_sve_ldffhss_le_zss, NULL, }, { gen_helper_sve_ldffbsu_zss, - gen_helper_sve_ldffhsu_zss, - gen_helper_sve_ldffssu_zss, } } } }, + gen_helper_sve_ldffhsu_le_zss, + gen_helper_sve_ldffss_le_zss, } } } }, /* Big-endian */ { { { { gen_helper_sve_ldbss_zsu, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][2][3] = { /* First-fault */ { { { gen_helper_sve_ldffbss_zsu, - gen_helper_sve_ldffhss_zsu, + gen_helper_sve_ldffhss_be_zsu, NULL, }, { gen_helper_sve_ldffbsu_zsu, - gen_helper_sve_ldffhsu_zsu, - gen_helper_sve_ldffssu_zsu, } }, + gen_helper_sve_ldffhsu_be_zsu, + gen_helper_sve_ldffss_be_zsu, } }, { { gen_helper_sve_ldffbss_zss, - gen_helper_sve_ldffhss_zss, + gen_helper_sve_ldffhss_be_zss, NULL, }, { gen_helper_sve_ldffbsu_zss, - gen_helper_sve_ldffhsu_zss, - gen_helper_sve_ldffssu_zss, } } } }, + gen_helper_sve_ldffhsu_be_zss, + gen_helper_sve_ldffss_be_zss, } } } }, }; /* Note that we overload xs=2 to indicate 64-bit offset. */ @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][2][3][2][4] = { /* First-fault */ { { { gen_helper_sve_ldffbds_zsu, - gen_helper_sve_ldffhds_zsu, - gen_helper_sve_ldffsds_zsu, + gen_helper_sve_ldffhds_le_zsu, + gen_helper_sve_ldffsds_le_zsu, NULL, }, { gen_helper_sve_ldffbdu_zsu, - gen_helper_sve_ldffhdu_zsu, - gen_helper_sve_ldffsdu_zsu, - gen_helper_sve_ldffddu_zsu, } }, + gen_helper_sve_ldffhdu_le_zsu, + gen_helper_sve_ldffsdu_le_zsu, + gen_helper_sve_ldffdd_le_zsu, } }, { { gen_helper_sve_ldffbds_zss, - gen_helper_sve_ldffhds_zss, - gen_helper_sve_ldffsds_zss, + gen_helper_sve_ldffhds_le_zss, + gen_helper_sve_ldffsds_le_zss, NULL, }, { gen_helper_sve_ldffbdu_zss, - gen_helper_sve_ldffhdu_zss, - gen_helper_sve_ldffsdu_zss, - gen_helper_sve_ldffddu_zss, } }, + gen_helper_sve_ldffhdu_le_zss, + gen_helper_sve_ldffsdu_le_zss, + gen_helper_sve_ldffdd_le_zss, } }, { { gen_helper_sve_ldffbds_zd, - gen_helper_sve_ldffhds_zd, - gen_helper_sve_ldffsds_zd, + gen_helper_sve_ldffhds_le_zd, + gen_helper_sve_ldffsds_le_zd, NULL, }, { gen_helper_sve_ldffbdu_zd, - gen_helper_sve_ldffhdu_zd, - gen_helper_sve_ldffsdu_zd, - gen_helper_sve_ldffddu_zd, } } } }, + gen_helper_sve_ldffhdu_le_zd, + gen_helper_sve_ldffsdu_le_zd, + gen_helper_sve_ldffdd_le_zd, } } } }, /* Big-endian */ { { { { gen_helper_sve_ldbds_zsu, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][2][3][2][4] = { /* First-fault */ { { { gen_helper_sve_ldffbds_zsu, - gen_helper_sve_ldffhds_zsu, - gen_helper_sve_ldffsds_zsu, + gen_helper_sve_ldffhds_be_zsu, + gen_helper_sve_ldffsds_be_zsu, NULL, }, { gen_helper_sve_ldffbdu_zsu, - gen_helper_sve_ldffhdu_zsu, - gen_helper_sve_ldffsdu_zsu, - gen_helper_sve_ldffddu_zsu, } }, + gen_helper_sve_ldffhdu_be_zsu, + gen_helper_sve_ldffsdu_be_zsu, + gen_helper_sve_ldffdd_be_zsu, } }, { { gen_helper_sve_ldffbds_zss, - gen_helper_sve_ldffhds_zss, - gen_helper_sve_ldffsds_zss, + gen_helper_sve_ldffhds_be_zss, + gen_helper_sve_ldffsds_be_zss, NULL, }, { gen_helper_sve_ldffbdu_zss, - gen_helper_sve_ldffhdu_zss, - gen_helper_sve_ldffsdu_zss, - gen_helper_sve_ldffddu_zss, } }, + gen_helper_sve_ldffhdu_be_zss, + gen_helper_sve_ldffsdu_be_zss, + gen_helper_sve_ldffdd_be_zss, } }, { { gen_helper_sve_ldffbds_zd, - gen_helper_sve_ldffhds_zd, - gen_helper_sve_ldffsds_zd, + gen_helper_sve_ldffhds_be_zd, + gen_helper_sve_ldffsds_be_zd, NULL, }, { gen_helper_sve_ldffbdu_zd, - gen_helper_sve_ldffhdu_zd, - gen_helper_sve_ldffsdu_zd, - gen_helper_sve_ldffddu_zd, } } } }, + gen_helper_sve_ldffhdu_be_zd, + gen_helper_sve_ldffsdu_be_zd, + gen_helper_sve_ldffdd_be_zd, } } } }, }; static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) -- 2.19.0 From: Richard Henderson <richard.henderson@linaro.org> There is quite a lot of code required to compute cpu_mem_index, or even put together the full TCGMemOpIdx. This can easily be done at translation time. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181005175350.30752-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 5 ++ target/arm/sve_helper.c | 138 +++++++++++++++++++------------------ target/arm/translate-sve.c | 67 +++++++++++------- 3 files changed, 121 insertions(+), 89 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_debug_exception_fsr(CPUARMState *env) } } +/* Note make_memop_idx reserves 4 bits for mmu_idx, and MO_BSWAP is bit 3. + * Thus a TCGMemOpIdx, without any MO_ALIGN bits, fits in 8 bits. + */ +#define MEMOPIDX_SHIFT 8 + #endif diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" +#include "internals.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" @@ -XXX,XX +XXX,XX @@ typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host, * The controlling predicate is known to be true. */ typedef void sve_ld1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off, - target_ulong vaddr, int mmu_idx, uintptr_t ra); + target_ulong vaddr, TCGMemOpIdx oi, uintptr_t ra); typedef sve_ld1_tlb_fn sve_st1_tlb_fn; /* @@ -XXX,XX +XXX,XX @@ static intptr_t sve_##NAME##_host(void *vd, void *vg, void *host, \ #ifdef CONFIG_SOFTMMU #define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \ static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ - target_ulong addr, int mmu_idx, uintptr_t ra) \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ { \ - TCGMemOpIdx oi = make_memop_idx(ctz32(sizeof(TYPEM)) | MOEND, mmu_idx); \ TYPEM val = TLB(env, addr, oi, ra); \ *(TYPEE *)(vd + H(reg_off)) = val; \ } #else #define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \ static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ - target_ulong addr, int mmu_idx, uintptr_t ra) \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ { \ TYPEM val = HOST(g2h(addr)); \ *(TYPEE *)(vd + H(reg_off)) = val; \ @@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr, sve_ld1_host_fn *host_fn, sve_ld1_tlb_fn *tlb_fn) { - void *vd = &env->vfp.zregs[simd_data(desc)]; + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + void *vd = &env->vfp.zregs[rd]; const int diffsz = esz - msz; const intptr_t reg_max = simd_oprsz(desc); const intptr_t mem_max = reg_max >> diffsz; - const int mmu_idx = cpu_mmu_index(env, false); ARMVectorReg scratch; void *host; intptr_t split, reg_off, mem_off; @@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr, * on I/O memory, it may succeed but not bring in the TLB entry. * But even then we have still made forward progress. */ - tlb_fn(env, &scratch, reg_off, addr + mem_off, mmu_idx, retaddr); + tlb_fn(env, &scratch, reg_off, addr + mem_off, oi, retaddr); reg_off += 1 << esz; } #endif @@ -XXX,XX +XXX,XX @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr, uint32_t desc, int size, uintptr_t ra, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); ARMVectorReg scratch[2] = { }; set_helper_retaddr(ra); @@ -XXX,XX +XXX,XX @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra); - tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra); + tlb_fn(env, &scratch[0], i, addr, oi, ra); + tlb_fn(env, &scratch[1], i, addr + size, oi, ra); } i += size, pg >>= size; addr += 2 * size; @@ -XXX,XX +XXX,XX @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr, uint32_t desc, int size, uintptr_t ra, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); ARMVectorReg scratch[3] = { }; set_helper_retaddr(ra); @@ -XXX,XX +XXX,XX @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra); - tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra); - tlb_fn(env, &scratch[2], i, addr + 2 * size, mmu_idx, ra); + tlb_fn(env, &scratch[0], i, addr, oi, ra); + tlb_fn(env, &scratch[1], i, addr + size, oi, ra); + tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra); } i += size, pg >>= size; addr += 3 * size; @@ -XXX,XX +XXX,XX @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr, uint32_t desc, int size, uintptr_t ra, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); ARMVectorReg scratch[4] = { }; set_helper_retaddr(ra); @@ -XXX,XX +XXX,XX @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra); - tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra); - tlb_fn(env, &scratch[2], i, addr + 2 * size, mmu_idx, ra); - tlb_fn(env, &scratch[3], i, addr + 3 * size, mmu_idx, ra); + tlb_fn(env, &scratch[0], i, addr, oi, ra); + tlb_fn(env, &scratch[1], i, addr + size, oi, ra); + tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra); + tlb_fn(env, &scratch[3], i, addr + 3 * size, oi, ra); } i += size, pg >>= size; addr += 4 * size; @@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr, sve_ld1_host_fn *host_fn, sve_ld1_tlb_fn *tlb_fn) { - void *vd = &env->vfp.zregs[simd_data(desc)]; + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + void *vd = &env->vfp.zregs[rd]; const int diffsz = esz - msz; const intptr_t reg_max = simd_oprsz(desc); const intptr_t mem_max = reg_max >> diffsz; - const int mmu_idx = cpu_mmu_index(env, false); intptr_t split, reg_off, mem_off; void *host; @@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr, * Perform one normal read, which will fault or not. * But it is likely to bring the page into the tlb. */ - tlb_fn(env, vd, reg_off, addr + mem_off, mmu_idx, retaddr); + tlb_fn(env, vd, reg_off, addr + mem_off, oi, retaddr); /* After any fault, zero any leading predicated false elts. */ swap_memzero(vd, reg_off); @@ -XXX,XX +XXX,XX @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr, uint32_t desc, const int esz, const int msz, sve_ld1_host_fn *host_fn) { - void *vd = &env->vfp.zregs[simd_data(desc)]; + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + void *vd = &env->vfp.zregs[rd]; const int diffsz = esz - msz; const intptr_t reg_max = simd_oprsz(desc); const intptr_t mem_max = reg_max >> diffsz; @@ -XXX,XX +XXX,XX @@ DO_LDFF1_LDNF1_2(dd, 3, 3) #ifdef CONFIG_SOFTMMU #define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \ static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ - target_ulong addr, int mmu_idx, uintptr_t ra) \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ { \ - TCGMemOpIdx oi = make_memop_idx(ctz32(sizeof(TYPEM)) | MOEND, mmu_idx); \ TLB(env, addr, *(TYPEM *)(vd + H(reg_off)), oi, ra); \ } #else #define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \ static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ - target_ulong addr, int mmu_idx, uintptr_t ra) \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ { \ HOST(g2h(addr), *(TYPEM *)(vd + H(reg_off))); \ } @@ -XXX,XX +XXX,XX @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr, const int esize, const int msize, sve_st1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); void *vd = &env->vfp.zregs[rd]; set_helper_retaddr(ra); @@ -XXX,XX +XXX,XX @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, vd, i, addr, mmu_idx, ra); + tlb_fn(env, vd, i, addr, oi, ra); } i += esize, pg >>= esize; addr += msize; @@ -XXX,XX +XXX,XX @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr, const int esize, const int msize, sve_st1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); void *d1 = &env->vfp.zregs[rd]; void *d2 = &env->vfp.zregs[(rd + 1) & 31]; @@ -XXX,XX +XXX,XX @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, d1, i, addr, mmu_idx, ra); - tlb_fn(env, d2, i, addr + msize, mmu_idx, ra); + tlb_fn(env, d1, i, addr, oi, ra); + tlb_fn(env, d2, i, addr + msize, oi, ra); } i += esize, pg >>= esize; addr += 2 * msize; @@ -XXX,XX +XXX,XX @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr, const int esize, const int msize, sve_st1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); void *d1 = &env->vfp.zregs[rd]; void *d2 = &env->vfp.zregs[(rd + 1) & 31]; void *d3 = &env->vfp.zregs[(rd + 2) & 31]; @@ -XXX,XX +XXX,XX @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, d1, i, addr, mmu_idx, ra); - tlb_fn(env, d2, i, addr + msize, mmu_idx, ra); - tlb_fn(env, d3, i, addr + 2 * msize, mmu_idx, ra); + tlb_fn(env, d1, i, addr, oi, ra); + tlb_fn(env, d2, i, addr + msize, oi, ra); + tlb_fn(env, d3, i, addr + 2 * msize, oi, ra); } i += esize, pg >>= esize; addr += 3 * msize; @@ -XXX,XX +XXX,XX @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr, const int esize, const int msize, sve_st1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); intptr_t i, oprsz = simd_oprsz(desc); - unsigned rd = simd_data(desc); void *d1 = &env->vfp.zregs[rd]; void *d2 = &env->vfp.zregs[(rd + 1) & 31]; void *d3 = &env->vfp.zregs[(rd + 2) & 31]; @@ -XXX,XX +XXX,XX @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr, uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); do { if (pg & 1) { - tlb_fn(env, d1, i, addr, mmu_idx, ra); - tlb_fn(env, d2, i, addr + msize, mmu_idx, ra); - tlb_fn(env, d3, i, addr + 2 * msize, mmu_idx, ra); - tlb_fn(env, d4, i, addr + 3 * msize, mmu_idx, ra); + tlb_fn(env, d1, i, addr, oi, ra); + tlb_fn(env, d2, i, addr + msize, oi, ra); + tlb_fn(env, d3, i, addr + 2 * msize, oi, ra); + tlb_fn(env, d4, i, addr + 3 * msize, oi, ra); } i += esize, pg >>= esize; addr += 4 * msize; @@ -XXX,XX +XXX,XX @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm, target_ulong base, uint32_t desc, uintptr_t ra, zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); intptr_t i, oprsz = simd_oprsz(desc); - unsigned scale = simd_data(desc); ARMVectorReg scratch = { }; set_helper_retaddr(ra); @@ -XXX,XX +XXX,XX @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm, do { if (likely(pg & 1)) { target_ulong off = off_fn(vm, i); - tlb_fn(env, &scratch, i, base + (off << scale), mmu_idx, ra); + tlb_fn(env, &scratch, i, base + (off << scale), oi, ra); } i += 4, pg >>= 4; } while (i & 15); @@ -XXX,XX +XXX,XX @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm, target_ulong base, uint32_t desc, uintptr_t ra, zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); intptr_t i, oprsz = simd_oprsz(desc) / 8; - unsigned scale = simd_data(desc); ARMVectorReg scratch = { }; set_helper_retaddr(ra); @@ -XXX,XX +XXX,XX @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm, uint8_t pg = *(uint8_t *)(vg + H1(i)); if (likely(pg & 1)) { target_ulong off = off_fn(vm, i * 8); - tlb_fn(env, &scratch, i * 8, base + (off << scale), mmu_idx, ra); + tlb_fn(env, &scratch, i * 8, base + (off << scale), oi, ra); } } set_helper_retaddr(0); @@ -XXX,XX +XXX,XX @@ typedef bool sve_ld1_nf_fn(CPUARMState *env, void *vd, intptr_t reg_off, #ifdef CONFIG_SOFTMMU #define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \ static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \ - target_ulong addr, int mmu_idx) \ + target_ulong addr, int mmu_idx) \ { \ target_ulong next_page = -(addr | TARGET_PAGE_MASK); \ if (likely(next_page - addr >= sizeof(TYPEM))) { \ @@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm, zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn, sve_ld1_nf_fn *nonfault_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); intptr_t reg_off, reg_max = simd_oprsz(desc); - unsigned scale = simd_data(desc); target_ulong addr; /* Skip to the first true predicate. */ @@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm, set_helper_retaddr(ra); addr = off_fn(vm, reg_off); addr = base + (addr << scale); - tlb_fn(env, vd, reg_off, addr, mmu_idx, ra); + tlb_fn(env, vd, reg_off, addr, oi, ra); /* The rest of the reads will be non-faulting. */ set_helper_retaddr(0); @@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm, zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn, sve_ld1_nf_fn *nonfault_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); intptr_t reg_off, reg_max = simd_oprsz(desc); - unsigned scale = simd_data(desc); target_ulong addr; /* Skip to the first true predicate. */ @@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm, set_helper_retaddr(ra); addr = off_fn(vm, reg_off); addr = base + (addr << scale); - tlb_fn(env, vd, reg_off, addr, mmu_idx, ra); + tlb_fn(env, vd, reg_off, addr, oi, ra); /* The rest of the reads will be non-faulting. */ set_helper_retaddr(0); @@ -XXX,XX +XXX,XX @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm, target_ulong base, uint32_t desc, uintptr_t ra, zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); intptr_t i, oprsz = simd_oprsz(desc); - unsigned scale = simd_data(desc); set_helper_retaddr(ra); for (i = 0; i < oprsz; ) { @@ -XXX,XX +XXX,XX @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm, do { if (likely(pg & 1)) { target_ulong off = off_fn(vm, i); - tlb_fn(env, vd, i, base + (off << scale), mmu_idx, ra); + tlb_fn(env, vd, i, base + (off << scale), oi, ra); } i += 4, pg >>= 4; } while (i & 15); @@ -XXX,XX +XXX,XX @@ static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm, target_ulong base, uint32_t desc, uintptr_t ra, zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) { - const int mmu_idx = cpu_mmu_index(env, false); + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); intptr_t i, oprsz = simd_oprsz(desc) / 8; - unsigned scale = simd_data(desc); set_helper_retaddr(ra); for (i = 0; i < oprsz; i++) { uint8_t pg = *(uint8_t *)(vg + H1(i)); if (likely(pg & 1)) { target_ulong off = off_fn(vm, i * 8); - tlb_fn(env, vd, i * 8, base + (off << scale), mmu_idx, ra); + tlb_fn(env, vd, i * 8, base + (off << scale), oi, ra); } } set_helper_retaddr(0); diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static const uint8_t dtype_esz[16] = { 3, 2, 1, 3 }; +static TCGMemOpIdx sve_memopidx(DisasContext *s, int dtype) +{ + return make_memop_idx(s->be_data | dtype_mop[dtype], get_mem_index(s)); +} + static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, - gen_helper_gvec_mem *fn) + int dtype, gen_helper_gvec_mem *fn) { unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; - TCGv_i32 desc; + TCGv_i32 t_desc; + int desc; /* For e.g. LD4, there are not enough arguments to pass all 4 * registers as pointers, so encode the regno into the data field. * For consistency, do this even for LD1. */ - desc = tcg_const_i32(simd_desc(vsz, vsz, zt)); + desc = sve_memopidx(s, dtype); + desc |= zt << MEMOPIDX_SHIFT; + desc = simd_desc(vsz, vsz, desc); + t_desc = tcg_const_i32(desc); t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); - fn(cpu_env, t_pg, addr, desc); + fn(cpu_env, t_pg, addr, t_desc); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(desc); + tcg_temp_free_i32(t_desc); } static void do_ld_zpa(DisasContext *s, int zt, int pg, @@ -XXX,XX +XXX,XX @@ static void do_ld_zpa(DisasContext *s, int zt, int pg, * accessible via the instruction encoding. */ assert(fn != NULL); - do_mem_zpa(s, zt, pg, addr, fn); + do_mem_zpa(s, zt, pg, addr, dtype, fn); } static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) @@ -XXX,XX +XXX,XX @@ static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); - do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]); + do_mem_zpa(s, a->rd, a->pg, addr, a->dtype, + fns[s->be_data == MO_BE][a->dtype]); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), off); - do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]); + do_mem_zpa(s, a->rd, a->pg, addr, a->dtype, + fns[s->be_data == MO_BE][a->dtype]); } return true; } @@ -XXX,XX +XXX,XX @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) }; unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; - TCGv_i32 desc; - int poff; + TCGv_i32 t_desc; + int desc, poff; /* Load the first quadword using the normal predicated load helpers. */ - desc = tcg_const_i32(simd_desc(16, 16, zt)); + desc = sve_memopidx(s, msz_dtype(msz)); + desc |= zt << MEMOPIDX_SHIFT; + desc = simd_desc(16, 16, desc); + t_desc = tcg_const_i32(desc); poff = pred_full_reg_offset(s, pg); if (vsz > 16) { @@ -XXX,XX +XXX,XX @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_pg, cpu_env, poff); - fns[s->be_data == MO_BE][msz](cpu_env, t_pg, addr, desc); + fns[s->be_data == MO_BE][msz](cpu_env, t_pg, addr, t_desc); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(desc); + tcg_temp_free_i32(t_desc); /* Replicate that first quadword. */ if (vsz > 16) { @@ -XXX,XX +XXX,XX @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, fn = fn_multiple[be][nreg - 1][msz]; } assert(fn != NULL); - do_mem_zpa(s, zt, pg, addr, fn); + do_mem_zpa(s, zt, pg, addr, msz_dtype(msz), fn); } static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a, uint32_t insn) @@ -XXX,XX +XXX,XX @@ static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a, uint32_t insn) *** SVE gather loads / scatter stores */ -static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, int scale, - TCGv_i64 scalar, gen_helper_gvec_mem_scatter *fn) +static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, + int scale, TCGv_i64 scalar, int msz, + gen_helper_gvec_mem_scatter *fn) { unsigned vsz = vec_full_reg_size(s); - TCGv_i32 desc = tcg_const_i32(simd_desc(vsz, vsz, scale)); TCGv_ptr t_zm = tcg_temp_new_ptr(); TCGv_ptr t_pg = tcg_temp_new_ptr(); TCGv_ptr t_zt = tcg_temp_new_ptr(); + TCGv_i32 t_desc; + int desc; + + desc = sve_memopidx(s, msz_dtype(msz)); + desc |= scale << MEMOPIDX_SHIFT; + desc = simd_desc(vsz, vsz, desc); + t_desc = tcg_const_i32(desc); tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); tcg_gen_addi_ptr(t_zm, cpu_env, vec_full_reg_offset(s, zm)); tcg_gen_addi_ptr(t_zt, cpu_env, vec_full_reg_offset(s, zt)); - fn(cpu_env, t_zt, t_pg, t_zm, scalar, desc); + fn(cpu_env, t_zt, t_pg, t_zm, scalar, t_desc); tcg_temp_free_ptr(t_zt); tcg_temp_free_ptr(t_zm); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(desc); + tcg_temp_free_i32(t_desc); } /* Indexed by [be][ff][xs][u][msz]. */ @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) assert(fn != NULL); do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz, - cpu_reg_sp(s, a->rn), fn); + cpu_reg_sp(s, a->rn), a->msz, fn); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) * by loading the immediate into the scalar parameter. */ imm = tcg_const_i64(a->imm << a->msz); - do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn); + do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, a->msz, fn); tcg_temp_free_i64(imm); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) g_assert_not_reached(); } do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz, - cpu_reg_sp(s, a->rn), fn); + cpu_reg_sp(s, a->rn), a->msz, fn); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) * by loading the immediate into the scalar parameter. */ imm = tcg_const_i64(a->imm << a->msz); - do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn); + do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, a->msz, fn); tcg_temp_free_i64(imm); return true; } -- 2.19.0 The Arm v8M architecture includes hardware stack limit checking. When certain instructions update the stack pointer, if the new value of SP is below the limit set in the associated limit register then an exception is taken. Add a TB flag that tracks whether the limit-checking code needs to be emitted. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181002163556.10279-2-peter.maydell@linaro.org --- target/arm/cpu.h | 7 +++++++ target/arm/translate.h | 1 + target/arm/helper.c | 10 ++++++++++ target/arm/translate.c | 1 + 4 files changed, 19 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(V7M_CCR, UNALIGN_TRP, 3, 1) FIELD(V7M_CCR, DIV_0_TRP, 4, 1) FIELD(V7M_CCR, BFHFNMIGN, 8, 1) FIELD(V7M_CCR, STKALIGN, 9, 1) +FIELD(V7M_CCR, STKOFHFNMIGN, 10, 1) FIELD(V7M_CCR, DC, 16, 1) FIELD(V7M_CCR, IC, 17, 1) +FIELD(V7M_CCR, BP, 18, 1) /* V7M SCR bits */ FIELD(V7M_SCR, SLEEPONEXIT, 1, 1) @@ -XXX,XX +XXX,XX @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) /* For M profile only, Handler (ie not Thread) mode */ #define ARM_TBFLAG_HANDLER_SHIFT 21 #define ARM_TBFLAG_HANDLER_MASK (1 << ARM_TBFLAG_HANDLER_SHIFT) +/* For M profile only, whether we should generate stack-limit checks */ +#define ARM_TBFLAG_STACKCHECK_SHIFT 22 +#define ARM_TBFLAG_STACKCHECK_MASK (1 << ARM_TBFLAG_STACKCHECK_SHIFT) /* Bit usage when in AArch64 state */ #define ARM_TBFLAG_TBI0_SHIFT 0 /* TBI0 for EL0/1 or TBI for EL2/3 */ @@ -XXX,XX +XXX,XX @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) (((F) & ARM_TBFLAG_BE_DATA_MASK) >> ARM_TBFLAG_BE_DATA_SHIFT) #define ARM_TBFLAG_HANDLER(F) \ (((F) & ARM_TBFLAG_HANDLER_MASK) >> ARM_TBFLAG_HANDLER_SHIFT) +#define ARM_TBFLAG_STACKCHECK(F) \ + (((F) & ARM_TBFLAG_STACKCHECK_MASK) >> ARM_TBFLAG_STACKCHECK_SHIFT) #define ARM_TBFLAG_TBI0(F) \ (((F) & ARM_TBFLAG_TBI0_MASK) >> ARM_TBFLAG_TBI0_SHIFT) #define ARM_TBFLAG_TBI1(F) \ diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { int vec_stride; bool v7m_handler_mode; bool v8m_secure; /* true if v8M and we're in Secure mode */ + bool v8m_stackcheck; /* true if we need to perform v8M stack limit checks */ /* Immediate value in AArch32 SVC insn; must be set if is_jmp == DISAS_SWI * so that top level loop can generate correct syndrome information. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags |= ARM_TBFLAG_HANDLER_MASK; } + /* v8M always applies stack limit checks unless CCR.STKOFHFNMIGN is + * suppressing them because the requested execution priority is less than 0. + */ + if (arm_feature(env, ARM_FEATURE_V8) && + arm_feature(env, ARM_FEATURE_M) && + !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) && + (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) { + flags |= ARM_TBFLAG_STACKCHECK_MASK; + } + *pflags = flags; *cs_base = 0; } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->v7m_handler_mode = ARM_TBFLAG_HANDLER(dc->base.tb->flags); dc->v8m_secure = arm_feature(env, ARM_FEATURE_M_SECURITY) && regime_is_secure(env, dc->mmu_idx); + dc->v8m_stackcheck = ARM_TBFLAG_STACKCHECK(dc->base.tb->flags); dc->cp_regs = cpu->cp_regs; dc->features = env->features; -- 2.19.0 Define EXCP_STKOF, and arrange for it to cause us to take a UsageFault with CFSR.STKOF set. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-3-peter.maydell@linaro.org --- target/arm/cpu.h | 2 ++ target/arm/helper.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ #define EXCP_SEMIHOST 16 /* semihosting call */ #define EXCP_NOCP 17 /* v7M NOCP UsageFault */ #define EXCP_INVSTATE 18 /* v7M INVSTATE UsageFault */ +#define EXCP_STKOF 19 /* v8M STKOF UsageFault */ /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 @@ -XXX,XX +XXX,XX @@ FIELD(V7M_CFSR, UNDEFINSTR, 16 + 0, 1) FIELD(V7M_CFSR, INVSTATE, 16 + 1, 1) FIELD(V7M_CFSR, INVPC, 16 + 2, 1) FIELD(V7M_CFSR, NOCP, 16 + 3, 1) +FIELD(V7M_CFSR, STKOF, 16 + 4, 1) FIELD(V7M_CFSR, UNALIGNED, 16 + 8, 1) FIELD(V7M_CFSR, DIVBYZERO, 16 + 9, 1) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_log_exception(int idx) [EXCP_SEMIHOST] = "Semihosting call", [EXCP_NOCP] = "v7M NOCP UsageFault", [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", + [EXCP_STKOF] = "v8M STKOF UsageFault", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) 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_STKOF: + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_STKOF_MASK; + break; case EXCP_SWI: /* The PC already points to the next instruction. */ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); -- 2.19.0 We're going to want v7m_using_psp() in op_helper.c in the next patch, so move it from helper.c to internals.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-4-peter.maydell@linaro.org --- target/arm/internals.h | 16 ++++++++++++++++ target/arm/helper.c | 12 ------------ 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_debug_exception_fsr(CPUARMState *env) */ #define MEMOPIDX_SHIFT 8 +/** + * v7m_using_psp: Return true if using process stack pointer + * Return true if the CPU is currently using the process stack + * pointer, or false if it is using the main stack pointer. + */ +static inline bool v7m_using_psp(CPUARMState *env) +{ + /* Handler mode always uses the main stack; for thread mode + * the CONTROL.SPSEL bit determines the answer. + * Note that in v7M it is not possible to be in Handler mode with + * CONTROL.SPSEL non-zero, but in v8M it is, so we must check both. + */ + return !arm_v7m_is_handler_mode(env) && + env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK; +} + #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ pend_fault: return false; } -/* Return true if we're using the process stack pointer (not the MSP) */ -static bool v7m_using_psp(CPUARMState *env) -{ - /* Handler mode always uses the main stack; for thread mode - * the CONTROL.SPSEL bit determines the answer. - * Note that in v7M it is not possible to be in Handler mode with - * CONTROL.SPSEL non-zero, but in v8M it is, so we must check both. - */ - return !arm_v7m_is_handler_mode(env) && - env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK; -} - /* Write to v7M CONTROL.SPSEL bit for the specified security bank. * This may change the current stack pointer between Main and Process * stack pointers if it is done for the CONTROL register for the current -- 2.19.0 Add code to insert calls to a helper function to do the stack limit checking when we handle these forms of instruction that write to SP: * ADD (SP plus immediate) * ADD (SP plus register) * SUB (SP minus immediate) * SUB (SP minus register) * MOV (register) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-5-peter.maydell@linaro.org --- target/arm/helper.h | 2 ++ target/arm/internals.h | 14 ++++++++ target/arm/op_helper.c | 19 ++++++++++ target/arm/translate.c | 80 +++++++++++++++++++++++++++++++++++++----- 4 files changed, 106 insertions(+), 9 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(v7m_blxns, void, env, i32) DEF_HELPER_3(v7m_tt, i32, env, i32, i32) +DEF_HELPER_2(v8m_stackcheck, void, env, i32) + DEF_HELPER_4(access_check_cp_reg, void, env, ptr, i32, i32) DEF_HELPER_3(set_cp_reg, void, env, ptr, i32) DEF_HELPER_2(get_cp_reg, i32, env, ptr) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline bool v7m_using_psp(CPUARMState *env) env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK; } +/** + * v7m_sp_limit: Return SP limit for current CPU state + * Return the SP limit value for the current CPU security state + * and stack pointer. + */ +static inline uint32_t v7m_sp_limit(CPUARMState *env) +{ + if (v7m_using_psp(env)) { + return env->v7m.psplim[env->v7m.secure]; + } else { + return env->v7m.msplim[env->v7m.secure]; + } +} + #endif diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, #endif /* !defined(CONFIG_USER_ONLY) */ +void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue) +{ + /* + * Perform the v8M stack limit check for SP updates from translated code, + * raising an exception if the limit is breached. + */ + if (newvalue < v7m_sp_limit(env)) { + CPUState *cs = CPU(arm_env_get_cpu(env)); + + /* + * Stack limit exceptions are a rare case, so rather than syncing + * PC/condbits before the call, we use cpu_restore_state() to + * get them right before raising the exception. + */ + cpu_restore_state(cs, GETPC(), true); + raise_exception(env, EXCP_STKOF, 0, 1); + } +} + uint32_t HELPER(add_setq)(CPUARMState *env, uint32_t a, uint32_t b) { uint32_t res = a + b; diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void store_reg(DisasContext *s, int reg, TCGv_i32 var) tcg_temp_free_i32(var); } +/* + * Variant of store_reg which applies v8M stack-limit checks before updating + * SP. If the check fails this will result in an exception being taken. + * We disable the stack checks for CONFIG_USER_ONLY because we have + * no idea what the stack limits should be in that case. + * If stack checking is not being done this just acts like store_reg(). + */ +static void store_sp_checked(DisasContext *s, TCGv_i32 var) +{ +#ifndef CONFIG_USER_ONLY + if (s->v8m_stackcheck) { + gen_helper_v8m_stackcheck(cpu_env, var); + } +#endif + store_reg(s, 13, var); +} + /* Value extensions. */ #define gen_uxtb(var) tcg_gen_ext8u_i32(var, var) #define gen_uxth(var) tcg_gen_ext16u_i32(var, var) @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (gen_thumb2_data_op(s, op, conds, 0, tmp, tmp2)) goto illegal_op; tcg_temp_free_i32(tmp2); - if (rd != 15) { + if (rd == 13 && + ((op == 2 && rn == 15) || + (op == 8 && rn == 13) || + (op == 13 && rn == 13))) { + /* MOV SP, ... or ADD SP, SP, ... or SUB SP, SP, ... */ + store_sp_checked(s, tmp); + } else if (rd != 15) { store_reg(s, rd, tmp); } else { tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) gen_jmp(s, s->pc + offset); } } else { - /* Data processing immediate. */ + /* + * 0b1111_0xxx_xxxx_0xxx_xxxx_xxxx + * - Data-processing (modified immediate, plain binary immediate) + */ if (insn & (1 << 25)) { + /* + * 0b1111_0x1x_xxxx_0xxx_xxxx_xxxx + * - Data-processing (plain binary immediate) + */ if (insn & (1 << 24)) { if (insn & (1 << 20)) goto illegal_op; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, imm); } + store_reg(s, rd, tmp); } else { /* Add/sub 12-bit immediate. */ if (rn == 15) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) offset += imm; tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, offset); + store_reg(s, rd, tmp); } else { tmp = load_reg(s, rn); if (insn & (1 << 23)) tcg_gen_subi_i32(tmp, tmp, imm); else tcg_gen_addi_i32(tmp, tmp, imm); + if (rn == 13 && rd == 13) { + /* ADD SP, SP, imm or SUB SP, SP, imm */ + store_sp_checked(s, tmp); + } else { + store_reg(s, rd, tmp); + } } } - store_reg(s, rd, tmp); } } else { + /* + * 0b1111_0x0x_xxxx_0xxx_xxxx_xxxx + * - Data-processing (modified immediate) + */ int shifter_out = 0; /* modified 12-bit immediate. */ shift = ((insn & 0x04000000) >> 23) | ((insn & 0x7000) >> 12); @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) goto illegal_op; tcg_temp_free_i32(tmp2); rd = (insn >> 8) & 0xf; - if (rd != 15) { + if (rd == 13 && rn == 13 + && (op == 8 || op == 13)) { + /* ADD(S) SP, SP, imm or SUB(S) SP, SP, imm */ + store_sp_checked(s, tmp); + } else if (rd != 15) { store_reg(s, rd, tmp); } else { tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) tmp2 = load_reg(s, rm); tcg_gen_add_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); - store_reg(s, rd, tmp); + if (rd == 13) { + /* ADD SP, SP, reg */ + store_sp_checked(s, tmp); + } else { + store_reg(s, rd, tmp); + } break; case 1: /* cmp */ tmp = load_reg(s, rd); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; case 2: /* mov/cpy */ tmp = load_reg(s, rm); - store_reg(s, rd, tmp); + if (rd == 13) { + /* MOV SP, reg */ + store_sp_checked(s, tmp); + } else { + store_reg(s, rd, tmp); + } break; case 3: { @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; case 10: - /* add to high reg */ + /* + * 0b1010_xxxx_xxxx_xxxx + * - Add PC/SP (immediate) + */ rd = (insn >> 8) & 7; if (insn & (1 << 11)) { /* SP */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) op = (insn >> 8) & 0xf; switch (op) { case 0: - /* adjust stack pointer */ + /* + * 0b1011_0000_xxxx_xxxx + * - ADD (SP plus immediate) + * - SUB (SP minus immediate) + */ tmp = load_reg(s, 13); val = (insn & 0x7f) * 4; if (insn & (1 << 7)) val = -(int32_t)val; tcg_gen_addi_i32(tmp, tmp, val); - store_reg(s, 13, tmp); + store_sp_checked(s, tmp); break; case 2: /* sign/zero extend. */ -- 2.19.0 Add some comments to the Thumb decoder indicating what bits of the instruction have been decoded at various points in the code. This is not an exhaustive set of comments; we're gradually adding comments as we work with particular bits of the code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-6-peter.maydell@linaro.org --- target/arm/translate.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp2 = load_reg(s, rm); if ((insn & 0x70) != 0) goto illegal_op; + /* + * 0b1111_1010_0xxx_xxxx_1111_xxxx_0000_xxxx: + * - MOV, MOVS (register-shifted register), flagsetting + */ op = (insn >> 21) & 3; logic_cc = (insn & (1 << 20)) != 0; gen_arm_shift_reg(tmp, op, tmp2, logic_cc); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) rd = insn & 7; op = (insn >> 11) & 3; if (op == 3) { - /* add/subtract */ + /* + * 0b0001_1xxx_xxxx_xxxx + * - Add, subtract (three low registers) + * - Add, subtract (two low registers and immediate) + */ rn = (insn >> 3) & 7; tmp = load_reg(s, rn); if (insn & (1 << 10)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) } break; case 2: case 3: - /* arithmetic large immediate */ + /* + * 0b001x_xxxx_xxxx_xxxx + * - Add, subtract, compare, move (one low register and immediate) + */ op = (insn >> 11) & 3; rd = (insn >> 8) & 0x7; if (op == 0) { /* mov */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; } - /* data processing register */ + /* + * 0b0100_00xx_xxxx_xxxx + * - Data-processing (two low registers) + */ rd = insn & 7; rm = (insn >> 3) & 7; op = (insn >> 6) & 0xf; -- 2.19.0 Add checks for breaches of the v8M stack limit when the stack pointer is decremented to push the exception frame for exception entry. Note that the exception-entry case is unique in that the stack pointer is updated to be the limit value if the limit is hit (per rule R_ZLZG). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-7-peter.maydell@linaro.org --- target/arm/helper.c | 54 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 8 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, uint32_t frameptr; ARMMMUIdx mmu_idx; bool stacked_ok; + uint32_t limit; + bool want_psp; if (dotailchain) { bool mode = lr & R_V7M_EXCRET_MODE_MASK; @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, M_REG_S, priv); frame_sp_p = get_v7m_sp_ptr(env, M_REG_S, mode, lr & R_V7M_EXCRET_SPSEL_MASK); + want_psp = mode && (lr & R_V7M_EXCRET_SPSEL_MASK); + if (want_psp) { + limit = env->v7m.psplim[M_REG_S]; + } else { + limit = env->v7m.msplim[M_REG_S]; + } } else { mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); frame_sp_p = &env->regs[13]; + limit = v7m_sp_limit(env); } frameptr = *frame_sp_p - 0x28; + if (frameptr < limit) { + /* + * Stack limit failure: set SP to the limit value, and generate + * STKOF UsageFault. Stack pushes below the limit must not be + * performed. It is IMPDEF whether pushes above the limit are + * performed; we choose not to. + */ + qemu_log_mask(CPU_LOG_INT, + "...STKOF during callee-saves register stacking\n"); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_STKOF_MASK; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, + env->v7m.secure); + *frame_sp_p = limit; + return true; + } /* Write as much of the stack frame as we can. A write failure may * cause us to pend a derived exception. @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, v7m_stack_write(cpu, frameptr + 0x24, env->regs[11], mmu_idx, ignore_faults); - /* Update SP regardless of whether any of the stack accesses failed. - * When we implement v8M stack limit checking then this attempt to - * update SP might also fail and result in a derived exception. - */ + /* Update SP regardless of whether any of the stack accesses failed. */ *frame_sp_p = frameptr; return !stacked_ok; @@ -XXX,XX +XXX,XX @@ static bool v7m_push_stack(ARMCPU *cpu) frameptr -= 0x20; + if (arm_feature(env, ARM_FEATURE_V8)) { + uint32_t limit = v7m_sp_limit(env); + + if (frameptr < limit) { + /* + * Stack limit failure: set SP to the limit value, and generate + * STKOF UsageFault. Stack pushes below the limit must not be + * performed. It is IMPDEF whether pushes above the limit are + * performed; we choose not to. + */ + qemu_log_mask(CPU_LOG_INT, + "...STKOF during stacking\n"); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_STKOF_MASK; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, + env->v7m.secure); + env->regs[13] = limit; + return true; + } + } + /* Write as much of the stack frame as we can. If we fail a stack * write this will result in a derived exception being pended * (which may be taken in preference to the one we started with @@ -XXX,XX +XXX,XX @@ static bool v7m_push_stack(ARMCPU *cpu) v7m_stack_write(cpu, frameptr + 24, env->regs[15], mmu_idx, false) && v7m_stack_write(cpu, frameptr + 28, xpsr, mmu_idx, false); - /* Update SP regardless of whether any of the stack accesses failed. - * When we implement v8M stack limit checking then this attempt to - * update SP might also fail and result in a derived exception. - */ + /* Update SP regardless of whether any of the stack accesses failed. */ env->regs[13] = frameptr; return !stacked_ok; -- 2.19.0 Check the v8M stack limits when pushing the frame for a non-secure function call via BLXNS. In order to be able to generate the exception we need to promote raise_exception() from being local to op_helper.c so we can call it from helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-8-peter.maydell@linaro.org --- target/arm/internals.h | 9 +++++++++ target/arm/helper.c | 4 ++++ target/arm/op_helper.c | 4 ++-- 3 files changed, 15 insertions(+), 2 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ FIELD(V7M_EXCRET, RES1, 7, 25) /* including the must-be-1 prefix */ #define M_FAKE_FSR_NSC_EXEC 0xf /* NS executing in S&NSC memory */ #define M_FAKE_FSR_SFAULT 0xe /* SecureFault INVTRAN, INVEP or AUVIOL */ +/** + * raise_exception: Raise the specified exception. + * Raise a guest exception with the specified value, syndrome register + * and target exception level. This should be called from helper functions, + * and never returns because we will longjump back up to the CPU main loop. + */ +void QEMU_NORETURN raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el); + /* * For AArch64, map a given EL to an index in the banked_spsr array. * Note that this mapping and the AArch32 mapping defined in bank_number() diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) "BLXNS with misaligned SP is UNPREDICTABLE\n"); } + if (sp < v7m_sp_limit(env)) { + raise_exception(env, EXCP_STKOF, 0, 1); + } + saved_psr = env->v7m.exception; if (env->v7m.control[M_REG_S] & R_V7M_CONTROL_SFPA_MASK) { saved_psr |= XPSR_SFPA; diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) -static void raise_exception(CPUARMState *env, uint32_t excp, - uint32_t syndrome, uint32_t target_el) +void raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) { CPUState *cs = CPU(arm_env_get_cpu(env)); -- 2.19.0 Add the v8M stack checks for: * LDRD (immediate) * STRD (immediate) Loads and stores are more complicated than ADD/SUB/MOV, because we must ensure that memory accesses below the stack limit are not performed, so we can't simply do the check when we actually update SP. For these instructions, if the stack limit check triggers we must not: * perform any memory access below the SP limit * update PC, SP or the load/store base register but it is IMPDEF whether we: * perform any accesses above or equal to the SP limit * update destination registers for loads For QEMU we choose to always check the limit before doing any other part of the load or store, so we won't update any registers or perform any memory accesses. It is UNKNOWN whether the limit check triggers for a load or store where the initial SP value is below the limit and one of the stores would be below the limit, but the writeback moves SP to above the limit. For QEMU we choose to trigger the check in this situation. Note that limit checks happen only for loads and stores which update SP via writeback; they do not happen for loads and stores which simply use SP as a base register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-9-peter.maydell@linaro.org --- target/arm/translate.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) * 0b1111_1001_x11x_xxxx_xxxx_xxxx_xxxx_xxxx * - load/store dual (pre-indexed) */ + bool wback = extract32(insn, 21, 1); + if (rn == 15) { if (insn & (1 << 21)) { /* UNPREDICTABLE */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) addr = load_reg(s, rn); } offset = (insn & 0xff) * 4; - if ((insn & (1 << 23)) == 0) + if ((insn & (1 << 23)) == 0) { offset = -offset; + } + + if (s->v8m_stackcheck && rn == 13 && wback) { + /* + * Here 'addr' is the current SP; if offset is +ve we're + * moving SP up, else down. It is UNKNOWN whether the limit + * check triggers when SP starts below the limit and ends + * up above it; check whichever of the current and final + * SP is lower, so QEMU will trigger in that situation. + */ + if ((int32_t)offset < 0) { + TCGv_i32 newsp = tcg_temp_new_i32(); + + tcg_gen_addi_i32(newsp, addr, offset); + gen_helper_v8m_stackcheck(cpu_env, newsp); + tcg_temp_free_i32(newsp); + } else { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + } + if (insn & (1 << 24)) { tcg_gen_addi_i32(addr, addr, offset); offset = 0; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) gen_aa32_st32(s, tmp, addr, get_mem_index(s)); tcg_temp_free_i32(tmp); } - if (insn & (1 << 21)) { + if (wback) { /* Base writeback. */ tcg_gen_addi_i32(addr, addr, offset - 4); store_reg(s, rn, addr); -- 2.19.0 Add the v8M stack checks for: * LDM (T2 encoding) * STM (T2 encoding) This includes the 32-bit encodings of the instructions listed in v8M ARM ARM rule R_YVWT as * LDM, LDMIA, LDMFD * LDMDB, LDMEA * POP (multiple registers) * PUSH (muliple registers) * STM, STMIA, STMEA * STMDB, STMFD We perform the stack limit before doing any other part of the load or store. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-10-peter.maydell@linaro.org --- target/arm/translate.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } else { int i, loaded_base = 0; TCGv_i32 loaded_var; + bool wback = extract32(insn, 21, 1); /* Load/store multiple. */ addr = load_reg(s, rn); offset = 0; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (insn & (1 << i)) offset += 4; } + if (insn & (1 << 24)) { tcg_gen_addi_i32(addr, addr, -offset); } + if (s->v8m_stackcheck && rn == 13 && wback) { + /* + * If the writeback is incrementing SP rather than + * decrementing it, and the initial SP is below the + * stack limit but the final written-back SP would + * be above, then then we must not perform any memory + * accesses, but it is IMPDEF whether we generate + * an exception. We choose to do so in this case. + * At this point 'addr' is the lowest address, so + * either the original SP (if incrementing) or our + * final SP (if decrementing), so that's what we check. + */ + gen_helper_v8m_stackcheck(cpu_env, addr); + } + loaded_var = NULL; for (i = 0; i < 16; i++) { if ((insn & (1 << i)) == 0) @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (loaded_base) { store_reg(s, rn, loaded_var); } - if (insn & (1 << 21)) { + if (wback) { /* Base register writeback. */ if (insn & (1 << 24)) { tcg_gen_addi_i32(addr, addr, -offset); -- 2.19.0 Add v8M stack checks for the instructions in the T32 "load/store single" encoding class: these are the "immediate pre-indexed" and "immediate, post-indexed" LDR and STR instructions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-11-peter.maydell@linaro.org --- target/arm/translate.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) imm = -imm; /* Fall through. */ case 0xf: /* Pre-increment. */ - tcg_gen_addi_i32(addr, addr, imm); writeback = 1; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) issinfo = writeback ? ISSInvalid : rs; + if (s->v8m_stackcheck && rn == 13 && writeback) { + /* + * Stackcheck. Here we know 'addr' is the current SP; + * if imm is +ve we're moving SP up, else down. It is + * UNKNOWN whether the limit check triggers when SP starts + * below the limit and ends up above it; we chose to do so. + */ + if ((int32_t)imm < 0) { + TCGv_i32 newsp = tcg_temp_new_i32(); + + tcg_gen_addi_i32(newsp, addr, imm); + gen_helper_v8m_stackcheck(cpu_env, newsp); + tcg_temp_free_i32(newsp); + } else { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + } + + if (writeback && !postinc) { + tcg_gen_addi_i32(addr, addr, imm); + } + if (insn & (1 << 20)) { /* Load. */ tmp = tcg_temp_new_i32(); -- 2.19.0 Add v8M stack checks for the 16-bit Thumb push/pop encodings: STMDB, STMFD, LDM, LDMIA, LDMFD. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-12-peter.maydell@linaro.org --- target/arm/translate.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) store_reg(s, rd, tmp); break; case 4: case 5: case 0xc: case 0xd: - /* push/pop */ + /* + * 0b1011_x10x_xxxx_xxxx + * - push/pop + */ addr = load_reg(s, 13); if (insn & (1 << 8)) offset = 4; @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) if ((insn & (1 << 11)) == 0) { tcg_gen_addi_i32(addr, addr, -offset); } + + if (s->v8m_stackcheck) { + /* + * Here 'addr' is the lower of "old SP" and "new SP"; + * if this is a pop that starts below the limit and ends + * above it, it is UNKNOWN whether the limit check triggers; + * we choose to trigger. + */ + gen_helper_v8m_stackcheck(cpu_env, addr); + } + for (i = 0; i < 8; i++) { if (insn & (1 << i)) { if (insn & (1 << 11)) { -- 2.19.0 Add the v8M stack checks for the VLDM/VSTM (aka VPUSH/VPOP) instructions. This code is currently unreachable because we haven't yet implemented M profile floating point support, but since the change is simple, we add it now because otherwise we're likely to forget to do it later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-13-peter.maydell@linaro.org --- target/arm/translate.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) if (insn & (1 << 24)) /* pre-decrement */ tcg_gen_addi_i32(addr, addr, -((insn & 0xff) << 2)); + if (s->v8m_stackcheck && rn == 13 && w) { + /* + * Here 'addr' is the lowest address we will store to, + * and is either the old SP (if post-increment) or + * the new SP (if pre-decrement). For post-increment + * where the old value is below the limit and the new + * value is above, it is UNKNOWN whether the limit check + * triggers; we choose to trigger. + */ + gen_helper_v8m_stackcheck(cpu_env, addr); + } + if (dp) offset = 8; else -- 2.19.0 Updating the NS stack pointer via MSR to SP_NS should include a check whether the new SP value is below the stack limit. No other kinds of update to the various stack pointer and limit registers via MSR should perform a check. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181002163556.10279-14-peter.maydell@linaro.org --- target/arm/helper.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) * currently in handler mode or not, using the NS CONTROL.SPSEL. */ bool spsel = env->v7m.control[M_REG_NS] & R_V7M_CONTROL_SPSEL_MASK; + bool is_psp = !arm_v7m_is_handler_mode(env) && spsel; + uint32_t limit; if (!env->v7m.secure) { return; } - if (!arm_v7m_is_handler_mode(env) && spsel) { + + limit = is_psp ? env->v7m.psplim[false] : env->v7m.msplim[false]; + + if (val < limit) { + CPUState *cs = CPU(arm_env_get_cpu(env)); + + cpu_restore_state(cs, GETPC(), true); + raise_exception(env, EXCP_STKOF, 0, 1); + } + + if (is_psp) { env->v7m.other_ss_psp = val; } else { env->v7m.other_ss_msp = val; -- 2.19.0 Coverity complains (CID 1395628) that the multiply in the calculation of the framebuffer base is performed as 32x32 but then used in a context that takes a 64-bit hwaddr. This can't actually ever overflow the 32-bit result, because of the constraints placed on the s->config values in bcm2835_fb_validate_config(). But we can placate Coverity anyway, by explicitly casting one of the inputs to a hwaddr, so the whole expression is calculated with 64-bit arithmetic. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20181005133012.26490-1-peter.maydell@linaro.org --- hw/display/bcm2835_fb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/display/bcm2835_fb.c b/hw/display/bcm2835_fb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/bcm2835_fb.c +++ b/hw/display/bcm2835_fb.c @@ -XXX,XX +XXX,XX @@ static void fb_update_display(void *opaque) } if (s->invalidate) { - hwaddr base = s->config.base + xoff + yoff * src_width; + hwaddr base = s->config.base + xoff + (hwaddr)yoff * src_width; framebuffer_update_memory_section(&s->fbsection, s->dma_mr, base, s->config.yres, src_width); -- 2.19.0 First arm pullreq of the 5.1 cycle; mostly bugfixes and some cleanup patches. The new clock modelling framework is the big thing here. -- PMM The following changes since commit 648db19685b7030aa558a4ddbd3a8e53d8c9a062: Merge remote-tracking branch 'remotes/armbru/tags/pull-misc-2020-04-29' into staging (2020-04-29 15:07:33 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200430 for you to fetch changes up to 1267437e593e85498f9105b3bdab796630d2e83f: hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes (2020-04-30 11:52:29 +0100) ---------------------------------------------------------------- target-arm queue: * xlnx-zdma: Fix endianness handling of descriptor loading * nrf51: Fix last GPIO CNF address * gicv3: Use gicr_typer in arm_gicv3_icc_reset * msf2: Add EMAC block to SmartFusion2 SoC * New clock modelling framework * hw/arm: versal: Setup the ADMA with 128bit bus-width * Cadence: gem: fix wraparound in 64bit descriptors * cadence_gem: clear RX control descriptor * target/arm: Vectorize integer comparison vs zero * hw/arm/virt: dt: add kaslr-seed property * hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes ---------------------------------------------------------------- Cameron Esfahani (1): nrf51: Fix last GPIO CNF address Damien Hedde (7): hw/core/clock-vmstate: define a vmstate entry for clock state qdev: add clock input&output support to devices. qdev-clock: introduce an init array to ease the device construction hw/misc/zynq_slcr: add clock generation for uarts hw/char/cadence_uart: add clock support hw/arm/xilinx_zynq: connect uart clocks to slcr qdev-monitor: print the device's clock with info qtree Edgar E. Iglesias (7): dma/xlnx-zdma: Fix descriptor loading (MEM) wrt endianness dma/xlnx-zdma: Fix descriptor loading (REG) wrt endianness hw/arm: versal: Setup the ADMA with 128bit bus-width device_tree: Allow name wildcards in qemu_fdt_node_path() device_tree: Constify compat in qemu_fdt_node_path() hw/arm: xlnx-zcu102: Move arm_boot_info into XlnxZCU102 hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes Jerome Forissier (2): hw/arm/virt: dt: move creation of /secure-chosen to create_fdt() hw/arm/virt: dt: add kaslr-seed property Keqian Zhu (2): bugfix: Use gicr_typer in arm_gicv3_icc_reset Typo: Correct the name of CPU hotplug memory region Peter Maydell (2): hw/core/clock: introduce clock object docs/clocks: add device's clock documentation Philippe Mathieu-Daudé (3): target/arm: Restrict the Address Translate write operation to TCG accel target/arm/cpu: Use ARRAY_SIZE() to iterate over ARMCPUInfo[] target/arm/cpu: Update coding style to make checkpatch.pl happy Ramon Fried (2): Cadence: gem: fix wraparound in 64bit descriptors net: cadence_gem: clear RX control descriptor Richard Henderson (1): target/arm: Vectorize integer comparison vs zero Subbaraya Sundeep (3): hw/net: Add Smartfusion2 emac block msf2: Add EMAC block to SmartFusion2 SoC tests/boot_linux_console: Add ethernet test to SmartFusion2 Thomas Huth (1): target/arm: Make cpu_register() available for other files hw/core/Makefile.objs | 2 + hw/net/Makefile.objs | 1 + tests/Makefile.include | 1 + include/hw/arm/msf2-soc.h | 2 + include/hw/char/cadence_uart.h | 1 + include/hw/clock.h | 225 +++++++++++++ include/hw/gpio/nrf51_gpio.h | 2 +- include/hw/net/msf2-emac.h | 53 +++ include/hw/qdev-clock.h | 159 +++++++++ include/hw/qdev-core.h | 12 + include/sysemu/device_tree.h | 5 +- target/arm/cpu-qom.h | 9 +- target/arm/helper.h | 27 +- target/arm/translate.h | 5 + device_tree.c | 4 +- hw/acpi/cpu.c | 2 +- hw/arm/msf2-soc.c | 26 +- hw/arm/virt.c | 20 +- hw/arm/xilinx_zynq.c | 57 +++- hw/arm/xlnx-versal.c | 2 + hw/arm/xlnx-zcu102.c | 39 ++- hw/char/cadence_uart.c | 73 +++- hw/core/clock-vmstate.c | 25 ++ hw/core/clock.c | 130 ++++++++ hw/core/qdev-clock.c | 185 +++++++++++ hw/core/qdev.c | 12 + hw/dma/xlnx-zdma.c | 25 +- hw/intc/arm_gicv3_kvm.c | 4 +- hw/misc/zynq_slcr.c | 172 +++++++++- hw/net/cadence_gem.c | 16 +- hw/net/msf2-emac.c | 589 +++++++++++++++++++++++++++++++++ qdev-monitor.c | 9 + target/arm/cpu.c | 25 +- target/arm/cpu64.c | 16 +- target/arm/helper.c | 17 + target/arm/neon_helper.c | 24 -- target/arm/translate-a64.c | 64 +--- target/arm/translate.c | 256 ++++++++++++-- target/arm/vec_helper.c | 25 ++ MAINTAINERS | 2 + docs/devel/clocks.rst | 391 ++++++++++++++++++++++ docs/devel/index.rst | 1 + hw/char/trace-events | 3 + hw/core/trace-events | 7 + tests/acceptance/boot_linux_console.py | 15 +- 45 files changed, 2538 insertions(+), 202 deletions(-) create mode 100644 include/hw/clock.h create mode 100644 include/hw/net/msf2-emac.h create mode 100644 include/hw/qdev-clock.h create mode 100644 hw/core/clock-vmstate.c create mode 100644 hw/core/clock.c create mode 100644 hw/core/qdev-clock.c create mode 100644 hw/net/msf2-emac.c create mode 100644 docs/devel/clocks.rst From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix descriptor loading from memory wrt host endianness. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200404122718.25111-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -XXX,XX +XXX,XX @@ static void zdma_put_regaddr64(XlnxZDMA *s, unsigned int basereg, uint64_t addr) s->regs[basereg + 1] = addr >> 32; } -static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, void *buf) +static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, + XlnxZDMADescr *descr) { /* ZDMA descriptors must be aligned to their own size. */ if (addr % sizeof(XlnxZDMADescr)) { qemu_log_mask(LOG_GUEST_ERROR, "zdma: unaligned descriptor at %" PRIx64, addr); - memset(buf, 0x0, sizeof(XlnxZDMADescr)); + memset(descr, 0x0, sizeof(XlnxZDMADescr)); s->error = true; return false; } - address_space_read(s->dma_as, addr, s->attr, buf, sizeof(XlnxZDMADescr)); + descr->addr = address_space_ldq_le(s->dma_as, addr, s->attr, NULL); + descr->size = address_space_ldl_le(s->dma_as, addr + 8, s->attr, NULL); + descr->attr = address_space_ldl_le(s->dma_as, addr + 12, s->attr, NULL); return true; } @@ -XXX,XX +XXX,XX @@ static void zdma_update_descr_addr(XlnxZDMA *s, bool type, } else { addr = zdma_get_regaddr64(s, basereg); addr += sizeof(s->dsc_dst); - address_space_read(s->dma_as, addr, s->attr, (void *) &next, 8); + next = address_space_ldq_le(s->dma_as, addr, s->attr, NULL); } zdma_put_regaddr64(s, basereg, next); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix descriptor loading from registers wrt host endianness. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20200404122718.25111-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -XXX,XX +XXX,XX @@ static void zdma_put_regaddr64(XlnxZDMA *s, unsigned int basereg, uint64_t addr) s->regs[basereg + 1] = addr >> 32; } +static void zdma_load_descriptor_reg(XlnxZDMA *s, unsigned int reg, + XlnxZDMADescr *descr) +{ + descr->addr = zdma_get_regaddr64(s, reg); + descr->size = s->regs[reg + 2]; + descr->attr = s->regs[reg + 3]; +} + static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, XlnxZDMADescr *descr) { @@ -XXX,XX +XXX,XX @@ static void zdma_load_src_descriptor(XlnxZDMA *s) unsigned int ptype = ARRAY_FIELD_EX32(s->regs, ZDMA_CH_CTRL0, POINT_TYPE); if (ptype == PT_REG) { - memcpy(&s->dsc_src, &s->regs[R_ZDMA_CH_SRC_DSCR_WORD0], - sizeof(s->dsc_src)); + zdma_load_descriptor_reg(s, R_ZDMA_CH_SRC_DSCR_WORD0, &s->dsc_src); return; } @@ -XXX,XX +XXX,XX @@ static void zdma_load_dst_descriptor(XlnxZDMA *s) bool dst_type; if (ptype == PT_REG) { - memcpy(&s->dsc_dst, &s->regs[R_ZDMA_CH_DST_DSCR_WORD0], - sizeof(s->dsc_dst)); + zdma_load_descriptor_reg(s, R_ZDMA_CH_DST_DSCR_WORD0, &s->dsc_dst); return; } -- 2.20.1 From: Cameron Esfahani <dirty@apple.com> NRF51_GPIO_REG_CNF_END doesn't actually refer to the start of the last valid CNF register: it's referring to the last byte of the last valid CNF register. This hasn't been a problem up to now, as current implementation in memory.c turns an unaligned 4-byte read from 0x77f to a single byte read and the qtest only looks at the least-significant byte of the register. But when running with patches which fix unaligned accesses in memory.c, the qtest breaks. Considering NRF51 doesn't support unaligned accesses, the simplest fix is to actually set NRF51_GPIO_REG_CNF_END to the start of the last valid CNF register: 0x77c. Now, qtests work with or without the unaligned access patches. Reviewed-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Signed-off-by: Cameron Esfahani <dirty@apple.com> Message-id: 51b427f06838622da783d38ba56e3630d6d85c60.1586925392.git.dirty@apple.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/gpio/nrf51_gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/gpio/nrf51_gpio.h b/include/hw/gpio/nrf51_gpio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/gpio/nrf51_gpio.h +++ b/include/hw/gpio/nrf51_gpio.h @@ -XXX,XX +XXX,XX @@ #define NRF51_GPIO_REG_DIRSET 0x518 #define NRF51_GPIO_REG_DIRCLR 0x51C #define NRF51_GPIO_REG_CNF_START 0x700 -#define NRF51_GPIO_REG_CNF_END 0x77F +#define NRF51_GPIO_REG_CNF_END 0x77C #define NRF51_GPIO_PULLDOWN 1 #define NRF51_GPIO_PULLUP 3 -- 2.20.1 From: Keqian Zhu <zhukeqian1@huawei.com> The KVM_VGIC_ATTR macro expect the second parameter as gicr_typer, of which high 32bit is constructed by mp_affinity. For most case, the high 32bit of mp_affinity is zero, so it will always access the ICC_CTLR_EL1 of CPU0. Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com> Message-id: 20200413091552.62748-2-zhukeqian1@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_get(GICv3State *s) static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) { - ARMCPU *cpu; GICv3State *s; GICv3CPUState *c; c = (GICv3CPUState *)env->gicv3state; s = c->gic; - cpu = ARM_CPU(c->cpu); c->icc_pmr_el1 = 0; c->icc_bpr[GICV3_G0] = GIC_MIN_BPR; @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) /* Initialize to actual HW supported configuration */ kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, - KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity), + KVM_VGIC_ATTR(ICC_CTLR_EL1, c->gicr_typer), &c->icc_ctlr_el1[GICV3_NS], false, &error_abort); c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS]; -- 2.20.1 From: Keqian Zhu <zhukeqian1@huawei.com> Replace "acpi-mem-hotplug" with "acpi-cpu-hotplug" Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com> Message-id: 20200413091552.62748-4-zhukeqian1@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/acpi/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -XXX,XX +XXX,XX @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, state->devs[i].arch_id = id_list->cpus[i].arch_id; } memory_region_init_io(&state->ctrl_reg, owner, &cpu_hotplug_ops, state, - "acpi-mem-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); + "acpi-cpu-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); memory_region_add_subregion(as, base_addr, &state->ctrl_reg); } -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Modelled Ethernet MAC of Smartfusion2 SoC. Micrel KSZ8051 PHY is present on Emcraft's SOM kit hence same PHY is emulated. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-2-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/Makefile.objs | 1 + include/hw/net/msf2-emac.h | 53 ++++ hw/net/msf2-emac.c | 589 +++++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + 4 files changed, 645 insertions(+) create mode 100644 include/hw/net/msf2-emac.h create mode 100644 hw/net/msf2-emac.c diff --git a/hw/net/Makefile.objs b/hw/net/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Makefile.objs +++ b/hw/net/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ROCKER) += rocker/rocker.o rocker/rocker_fp.o \ obj-$(call lnot,$(CONFIG_ROCKER)) += rocker/qmp-norocker.o common-obj-$(CONFIG_CAN_BUS) += can/ +common-obj-$(CONFIG_MSF2) += msf2-emac.o diff --git a/include/hw/net/msf2-emac.h b/include/hw/net/msf2-emac.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/msf2-emac.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Smartfusion2 Ethernet MAC. + * + * Copyright (c) 2020 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 "hw/sysbus.h" +#include "exec/memory.h" +#include "net/net.h" +#include "net/eth.h" + +#define TYPE_MSS_EMAC "msf2-emac" +#define MSS_EMAC(obj) \ + OBJECT_CHECK(MSF2EmacState, (obj), TYPE_MSS_EMAC) + +#define R_MAX (0x1a0 / 4) +#define PHY_MAX_REGS 32 + +typedef struct MSF2EmacState { + SysBusDevice parent; + + MemoryRegion mmio; + MemoryRegion *dma_mr; + AddressSpace dma_as; + + qemu_irq irq; + NICState *nic; + NICConf conf; + + uint8_t mac_addr[ETH_ALEN]; + uint32_t rx_desc; + uint16_t phy_regs[PHY_MAX_REGS]; + + uint32_t regs[R_MAX]; +} MSF2EmacState; diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/msf2-emac.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Smartfusion2 Ethernet MAC. + * + * Copyright (c) 2020 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. + * + * Refer to section Ethernet MAC in the document: + * UG0331: SmartFusion2 Microcontroller Subsystem User Guide + * Datasheet URL: + * https://www.microsemi.com/document-portal/cat_view/56661-internal-documents/ + * 56758-soc?lang=en&limit=20&limitstart=220 + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/log.h" +#include "qapi/error.h" +#include "exec/address-spaces.h" +#include "hw/registerfields.h" +#include "hw/net/msf2-emac.h" +#include "hw/net/mii.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" + +REG32(CFG1, 0x0) + FIELD(CFG1, RESET, 31, 1) + FIELD(CFG1, RX_EN, 2, 1) + FIELD(CFG1, TX_EN, 0, 1) + FIELD(CFG1, LB_EN, 8, 1) +REG32(CFG2, 0x4) +REG32(IFG, 0x8) +REG32(HALF_DUPLEX, 0xc) +REG32(MAX_FRAME_LENGTH, 0x10) +REG32(MII_CMD, 0x24) + FIELD(MII_CMD, READ, 0, 1) +REG32(MII_ADDR, 0x28) + FIELD(MII_ADDR, REGADDR, 0, 5) + FIELD(MII_ADDR, PHYADDR, 8, 5) +REG32(MII_CTL, 0x2c) +REG32(MII_STS, 0x30) +REG32(STA1, 0x40) +REG32(STA2, 0x44) +REG32(FIFO_CFG0, 0x48) +REG32(FIFO_CFG4, 0x58) + FIELD(FIFO_CFG4, BCAST, 9, 1) + FIELD(FIFO_CFG4, MCAST, 8, 1) +REG32(FIFO_CFG5, 0x5C) + FIELD(FIFO_CFG5, BCAST, 9, 1) + FIELD(FIFO_CFG5, MCAST, 8, 1) +REG32(DMA_TX_CTL, 0x180) + FIELD(DMA_TX_CTL, EN, 0, 1) +REG32(DMA_TX_DESC, 0x184) +REG32(DMA_TX_STATUS, 0x188) + FIELD(DMA_TX_STATUS, PKTCNT, 16, 8) + FIELD(DMA_TX_STATUS, UNDERRUN, 1, 1) + FIELD(DMA_TX_STATUS, PKT_SENT, 0, 1) +REG32(DMA_RX_CTL, 0x18c) + FIELD(DMA_RX_CTL, EN, 0, 1) +REG32(DMA_RX_DESC, 0x190) +REG32(DMA_RX_STATUS, 0x194) + FIELD(DMA_RX_STATUS, PKTCNT, 16, 8) + FIELD(DMA_RX_STATUS, OVERFLOW, 2, 1) + FIELD(DMA_RX_STATUS, PKT_RCVD, 0, 1) +REG32(DMA_IRQ_MASK, 0x198) +REG32(DMA_IRQ, 0x19c) + +#define EMPTY_MASK (1 << 31) +#define PKT_SIZE 0x7FF +#define PHYADDR 0x1 +#define MAX_PKT_SIZE 2048 + +typedef struct { + uint32_t pktaddr; + uint32_t pktsize; + uint32_t next; +} EmacDesc; + +static uint32_t emac_get_isr(MSF2EmacState *s) +{ + uint32_t ier = s->regs[R_DMA_IRQ_MASK]; + uint32_t tx = s->regs[R_DMA_TX_STATUS] & 0xF; + uint32_t rx = s->regs[R_DMA_RX_STATUS] & 0xF; + uint32_t isr = (rx << 4) | tx; + + s->regs[R_DMA_IRQ] = ier & isr; + return s->regs[R_DMA_IRQ]; +} + +static void emac_update_irq(MSF2EmacState *s) +{ + bool intr = emac_get_isr(s); + + qemu_set_irq(s->irq, intr); +} + +static void emac_load_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +{ + address_space_read(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); + /* Convert from LE into host endianness. */ + d->pktaddr = le32_to_cpu(d->pktaddr); + d->pktsize = le32_to_cpu(d->pktsize); + d->next = le32_to_cpu(d->next); +} + +static void emac_store_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +{ + /* Convert from host endianness into LE. */ + d->pktaddr = cpu_to_le32(d->pktaddr); + d->pktsize = cpu_to_le32(d->pktsize); + d->next = cpu_to_le32(d->next); + + address_space_write(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); +} + +static void msf2_dma_tx(MSF2EmacState *s) +{ + NetClientState *nc = qemu_get_queue(s->nic); + hwaddr desc = s->regs[R_DMA_TX_DESC]; + uint8_t buf[MAX_PKT_SIZE]; + EmacDesc d; + int size; + uint8_t pktcnt; + uint32_t status; + + if (!(s->regs[R_CFG1] & R_CFG1_TX_EN_MASK)) { + return; + } + + while (1) { + emac_load_desc(s, &d, desc); + if (d.pktsize & EMPTY_MASK) { + break; + } + size = d.pktsize & PKT_SIZE; + address_space_read(&s->dma_as, d.pktaddr, MEMTXATTRS_UNSPECIFIED, + buf, size); + /* + * This is very basic way to send packets. Ideally there should be + * a FIFO and packets should be sent out from FIFO only when + * R_CFG1 bit 0 is set. + */ + if (s->regs[R_CFG1] & R_CFG1_LB_EN_MASK) { + nc->info->receive(nc, buf, size); + } else { + qemu_send_packet(nc, buf, size); + } + d.pktsize |= EMPTY_MASK; + emac_store_desc(s, &d, desc); + /* update sent packets count */ + status = s->regs[R_DMA_TX_STATUS]; + pktcnt = FIELD_EX32(status, DMA_TX_STATUS, PKTCNT); + pktcnt++; + s->regs[R_DMA_TX_STATUS] = FIELD_DP32(status, DMA_TX_STATUS, + PKTCNT, pktcnt); + s->regs[R_DMA_TX_STATUS] |= R_DMA_TX_STATUS_PKT_SENT_MASK; + desc = d.next; + } + s->regs[R_DMA_TX_STATUS] |= R_DMA_TX_STATUS_UNDERRUN_MASK; + s->regs[R_DMA_TX_CTL] &= ~R_DMA_TX_CTL_EN_MASK; +} + +static void msf2_phy_update_link(MSF2EmacState *s) +{ + /* Autonegotiation status mirrors link status. */ + if (qemu_get_queue(s->nic)->link_down) { + s->phy_regs[MII_BMSR] &= ~(MII_BMSR_AN_COMP | + MII_BMSR_LINK_ST); + } else { + s->phy_regs[MII_BMSR] |= (MII_BMSR_AN_COMP | + MII_BMSR_LINK_ST); + } +} + +static void msf2_phy_reset(MSF2EmacState *s) +{ + memset(&s->phy_regs[0], 0, sizeof(s->phy_regs)); + s->phy_regs[MII_BMCR] = 0x1140; + s->phy_regs[MII_BMSR] = 0x7968; + s->phy_regs[MII_PHYID1] = 0x0022; + s->phy_regs[MII_PHYID2] = 0x1550; + s->phy_regs[MII_ANAR] = 0x01E1; + s->phy_regs[MII_ANLPAR] = 0xCDE1; + + msf2_phy_update_link(s); +} + +static void write_to_phy(MSF2EmacState *s) +{ + uint8_t reg_addr = s->regs[R_MII_ADDR] & R_MII_ADDR_REGADDR_MASK; + uint8_t phy_addr = (s->regs[R_MII_ADDR] >> R_MII_ADDR_PHYADDR_SHIFT) & + R_MII_ADDR_REGADDR_MASK; + uint16_t data = s->regs[R_MII_CTL] & 0xFFFF; + + if (phy_addr != PHYADDR) { + return; + } + + switch (reg_addr) { + case MII_BMCR: + if (data & MII_BMCR_RESET) { + /* Phy reset */ + msf2_phy_reset(s); + data &= ~MII_BMCR_RESET; + } + if (data & MII_BMCR_AUTOEN) { + /* Complete autonegotiation immediately */ + data &= ~MII_BMCR_AUTOEN; + s->phy_regs[MII_BMSR] |= MII_BMSR_AN_COMP; + } + break; + } + + s->phy_regs[reg_addr] = data; +} + +static uint16_t read_from_phy(MSF2EmacState *s) +{ + uint8_t reg_addr = s->regs[R_MII_ADDR] & R_MII_ADDR_REGADDR_MASK; + uint8_t phy_addr = (s->regs[R_MII_ADDR] >> R_MII_ADDR_PHYADDR_SHIFT) & + R_MII_ADDR_REGADDR_MASK; + + if (phy_addr == PHYADDR) { + return s->phy_regs[reg_addr]; + } else { + return 0xFFFF; + } +} + +static void msf2_emac_do_reset(MSF2EmacState *s) +{ + memset(&s->regs[0], 0, sizeof(s->regs)); + s->regs[R_CFG1] = 0x80000000; + s->regs[R_CFG2] = 0x00007000; + s->regs[R_IFG] = 0x40605060; + s->regs[R_HALF_DUPLEX] = 0x00A1F037; + s->regs[R_MAX_FRAME_LENGTH] = 0x00000600; + s->regs[R_FIFO_CFG5] = 0X3FFFF; + + msf2_phy_reset(s); +} + +static uint64_t emac_read(void *opaque, hwaddr addr, unsigned int size) +{ + MSF2EmacState *s = opaque; + uint32_t r = 0; + + addr >>= 2; + + switch (addr) { + case R_DMA_IRQ: + r = emac_get_isr(s); + break; + default: + if (addr >= ARRAY_SIZE(s->regs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return r; + } + r = s->regs[addr]; + break; + } + return r; +} + +static void emac_write(void *opaque, hwaddr addr, uint64_t val64, + unsigned int size) +{ + MSF2EmacState *s = opaque; + uint32_t value = val64; + uint32_t enreqbits; + uint8_t pktcnt; + + addr >>= 2; + switch (addr) { + case R_DMA_TX_CTL: + s->regs[addr] = value; + if (value & R_DMA_TX_CTL_EN_MASK) { + msf2_dma_tx(s); + } + break; + case R_DMA_RX_CTL: + s->regs[addr] = value; + if (value & R_DMA_RX_CTL_EN_MASK) { + s->rx_desc = s->regs[R_DMA_RX_DESC]; + qemu_flush_queued_packets(qemu_get_queue(s->nic)); + } + break; + case R_CFG1: + s->regs[addr] = value; + if (value & R_CFG1_RESET_MASK) { + msf2_emac_do_reset(s); + } + break; + case R_FIFO_CFG0: + /* + * For our implementation, turning on modules is instantaneous, + * so the states requested via the *ENREQ bits appear in the + * *ENRPLY bits immediately. Also the reset bits to reset PE-MCXMAC + * module are not emulated here since it deals with start of frames, + * inter-packet gap and control frames. + */ + enreqbits = extract32(value, 8, 5); + s->regs[addr] = deposit32(value, 16, 5, enreqbits); + break; + case R_DMA_TX_DESC: + if (value & 0x3) { + qemu_log_mask(LOG_GUEST_ERROR, "Tx Descriptor address should be" + " 32 bit aligned\n"); + } + /* Ignore [1:0] bits */ + s->regs[addr] = value & ~3; + break; + case R_DMA_RX_DESC: + if (value & 0x3) { + qemu_log_mask(LOG_GUEST_ERROR, "Rx Descriptor address should be" + " 32 bit aligned\n"); + } + /* Ignore [1:0] bits */ + s->regs[addr] = value & ~3; + break; + case R_DMA_TX_STATUS: + if (value & R_DMA_TX_STATUS_UNDERRUN_MASK) { + s->regs[addr] &= ~R_DMA_TX_STATUS_UNDERRUN_MASK; + } + if (value & R_DMA_TX_STATUS_PKT_SENT_MASK) { + pktcnt = FIELD_EX32(s->regs[addr], DMA_TX_STATUS, PKTCNT); + pktcnt--; + s->regs[addr] = FIELD_DP32(s->regs[addr], DMA_TX_STATUS, + PKTCNT, pktcnt); + if (pktcnt == 0) { + s->regs[addr] &= ~R_DMA_TX_STATUS_PKT_SENT_MASK; + } + } + break; + case R_DMA_RX_STATUS: + if (value & R_DMA_RX_STATUS_OVERFLOW_MASK) { + s->regs[addr] &= ~R_DMA_RX_STATUS_OVERFLOW_MASK; + } + if (value & R_DMA_RX_STATUS_PKT_RCVD_MASK) { + pktcnt = FIELD_EX32(s->regs[addr], DMA_RX_STATUS, PKTCNT); + pktcnt--; + s->regs[addr] = FIELD_DP32(s->regs[addr], DMA_RX_STATUS, + PKTCNT, pktcnt); + if (pktcnt == 0) { + s->regs[addr] &= ~R_DMA_RX_STATUS_PKT_RCVD_MASK; + } + } + break; + case R_DMA_IRQ: + break; + case R_MII_CMD: + if (value & R_MII_CMD_READ_MASK) { + s->regs[R_MII_STS] = read_from_phy(s); + } + break; + case R_MII_CTL: + s->regs[addr] = value; + write_to_phy(s); + break; + case R_STA1: + s->regs[addr] = value; + /* + * R_STA1 [31:24] : octet 1 of mac address + * R_STA1 [23:16] : octet 2 of mac address + * R_STA1 [15:8] : octet 3 of mac address + * R_STA1 [7:0] : octet 4 of mac address + */ + stl_be_p(s->mac_addr, value); + break; + case R_STA2: + s->regs[addr] = value; + /* + * R_STA2 [31:24] : octet 5 of mac address + * R_STA2 [23:16] : octet 6 of mac address + */ + stw_be_p(s->mac_addr + 4, value >> 16); + break; + default: + if (addr >= ARRAY_SIZE(s->regs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return; + } + s->regs[addr] = value; + break; + } + emac_update_irq(s); +} + +static const MemoryRegionOps emac_ops = { + .read = emac_read, + .write = emac_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4 + } +}; + +static bool emac_can_rx(NetClientState *nc) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + + return (s->regs[R_CFG1] & R_CFG1_RX_EN_MASK) && + (s->regs[R_DMA_RX_CTL] & R_DMA_RX_CTL_EN_MASK); +} + +static bool addr_filter_ok(MSF2EmacState *s, const uint8_t *buf) +{ + /* The broadcast MAC address: FF:FF:FF:FF:FF:FF */ + const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, + 0xFF, 0xFF }; + bool bcast_en = true; + bool mcast_en = true; + + if (s->regs[R_FIFO_CFG5] & R_FIFO_CFG5_BCAST_MASK) { + bcast_en = true; /* Broadcast dont care for drop circuitry */ + } else if (s->regs[R_FIFO_CFG4] & R_FIFO_CFG4_BCAST_MASK) { + bcast_en = false; + } + + if (s->regs[R_FIFO_CFG5] & R_FIFO_CFG5_MCAST_MASK) { + mcast_en = true; /* Multicast dont care for drop circuitry */ + } else if (s->regs[R_FIFO_CFG4] & R_FIFO_CFG4_MCAST_MASK) { + mcast_en = false; + } + + if (!memcmp(buf, broadcast_addr, sizeof(broadcast_addr))) { + return bcast_en; + } + + if (buf[0] & 1) { + return mcast_en; + } + + return !memcmp(buf, s->mac_addr, sizeof(s->mac_addr)); +} + +static ssize_t emac_rx(NetClientState *nc, const uint8_t *buf, size_t size) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + EmacDesc d; + uint8_t pktcnt; + uint32_t status; + + if (size > (s->regs[R_MAX_FRAME_LENGTH] & 0xFFFF)) { + return size; + } + if (!addr_filter_ok(s, buf)) { + return size; + } + + emac_load_desc(s, &d, s->rx_desc); + + if (d.pktsize & EMPTY_MASK) { + address_space_write(&s->dma_as, d.pktaddr, MEMTXATTRS_UNSPECIFIED, + buf, size & PKT_SIZE); + d.pktsize = size & PKT_SIZE; + emac_store_desc(s, &d, s->rx_desc); + /* update received packets count */ + status = s->regs[R_DMA_RX_STATUS]; + pktcnt = FIELD_EX32(status, DMA_RX_STATUS, PKTCNT); + pktcnt++; + s->regs[R_DMA_RX_STATUS] = FIELD_DP32(status, DMA_RX_STATUS, + PKTCNT, pktcnt); + s->regs[R_DMA_RX_STATUS] |= R_DMA_RX_STATUS_PKT_RCVD_MASK; + s->rx_desc = d.next; + } else { + s->regs[R_DMA_RX_CTL] &= ~R_DMA_RX_CTL_EN_MASK; + s->regs[R_DMA_RX_STATUS] |= R_DMA_RX_STATUS_OVERFLOW_MASK; + } + emac_update_irq(s); + return size; +} + +static void msf2_emac_reset(DeviceState *dev) +{ + MSF2EmacState *s = MSS_EMAC(dev); + + msf2_emac_do_reset(s); +} + +static void emac_set_link(NetClientState *nc) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + + msf2_phy_update_link(s); +} + +static NetClientInfo net_msf2_emac_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = emac_can_rx, + .receive = emac_rx, + .link_status_changed = emac_set_link, +}; + +static void msf2_emac_realize(DeviceState *dev, Error **errp) +{ + MSF2EmacState *s = MSS_EMAC(dev); + + if (!s->dma_mr) { + error_setg(errp, "MSS_EMAC 'ahb-bus' link not set"); + return; + } + + address_space_init(&s->dma_as, s->dma_mr, "emac-ahb"); + + qemu_macaddr_default_if_unset(&s->conf.macaddr); + s->nic = qemu_new_nic(&net_msf2_emac_info, &s->conf, + object_get_typename(OBJECT(dev)), dev->id, s); + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static void msf2_emac_init(Object *obj) +{ + MSF2EmacState *s = MSS_EMAC(obj); + + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); + + memory_region_init_io(&s->mmio, obj, &emac_ops, s, + "msf2-emac", R_MAX * 4); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); +} + +static Property msf2_emac_properties[] = { + DEFINE_PROP_LINK("ahb-bus", MSF2EmacState, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_NIC_PROPERTIES(MSF2EmacState, conf), + DEFINE_PROP_END_OF_LIST(), +}; + +static const VMStateDescription vmstate_msf2_emac = { + .name = TYPE_MSS_EMAC, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(mac_addr, MSF2EmacState, ETH_ALEN), + VMSTATE_UINT32(rx_desc, MSF2EmacState), + VMSTATE_UINT16_ARRAY(phy_regs, MSF2EmacState, PHY_MAX_REGS), + VMSTATE_UINT32_ARRAY(regs, MSF2EmacState, R_MAX), + VMSTATE_END_OF_LIST() + } +}; + +static void msf2_emac_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = msf2_emac_realize; + dc->reset = msf2_emac_reset; + dc->vmsd = &vmstate_msf2_emac; + device_class_set_props(dc, msf2_emac_properties); +} + +static const TypeInfo msf2_emac_info = { + .name = TYPE_MSS_EMAC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MSF2EmacState), + .instance_init = msf2_emac_init, + .class_init = msf2_emac_class_init, +}; + +static void msf2_emac_register_types(void) +{ + type_register_static(&msf2_emac_info); +} + +type_init(msf2_emac_register_types) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/arm/msf2-soc.h F: include/hw/misc/msf2-sysreg.h F: include/hw/timer/mss-timer.h F: include/hw/ssi/mss-spi.h +F: hw/net/msf2-emac.c +F: include/hw/net/msf2-emac.h Emcraft M2S-FG484 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> With SmartFusion2 Ethernet MAC model in place this patch adds the same to SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-3-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/msf2-soc.h | 2 ++ hw/arm/msf2-soc.c | 26 ++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/mss-timer.h" #include "hw/misc/msf2-sysreg.h" #include "hw/ssi/mss-spi.h" +#include "hw/net/msf2-emac.h" #define TYPE_MSF2_SOC "msf2-soc" #define MSF2_SOC(obj) OBJECT_CHECK(MSF2State, (obj), TYPE_MSF2_SOC) @@ -XXX,XX +XXX,XX @@ typedef struct MSF2State { MSF2SysregState sysreg; MSSTimerState timer; MSSSpiState spi[MSF2_NUM_SPIS]; + MSF2EmacState emac; } MSF2State; #endif diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ /* * SmartFusion2 SoC emulation. * - * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * Copyright (c) 2017-2020 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 @@ -XXX,XX +XXX,XX @@ #define MSF2_TIMER_BASE 0x40004000 #define MSF2_SYSREG_BASE 0x40038000 +#define MSF2_EMAC_BASE 0x40041000 #define ENVM_BASE_ADDRESS 0x60000000 #define SRAM_BASE_ADDRESS 0x20000000 +#define MSF2_EMAC_IRQ 12 + #define MSF2_ENVM_MAX_SIZE (512 * KiB) /* @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_initfn(Object *obj) sysbus_init_child_obj(obj, "spi[*]", &s->spi[i], sizeof(s->spi[i]), TYPE_MSS_SPI); } + + sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), + TYPE_MSS_EMAC); + if (nd_table[0].used) { + qemu_check_nic_model(&nd_table[0], TYPE_MSS_EMAC); + qdev_set_nic_properties(DEVICE(&s->emac), &nd_table[0]); + } } static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) g_free(bus_name); } + dev = DEVICE(&s->emac); + object_property_set_link(OBJECT(&s->emac), OBJECT(get_system_memory()), + "ahb-bus", &error_abort); + object_property_set_bool(OBJECT(&s->emac), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, MSF2_EMAC_BASE); + sysbus_connect_irq(busdev, 0, + qdev_get_gpio_in(armv7m, MSF2_EMAC_IRQ)); + /* Below devices are not modelled yet. */ create_unimplemented_device("i2c_0", 0x40002000, 0x1000); create_unimplemented_device("dma", 0x40003000, 0x1000); @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) 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); } -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> In addition to simple serial test this patch uses ping to test the ethernet block modelled in SmartFusion2 SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-4-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): """ uboot_url = ('https://raw.githubusercontent.com/' 'Subbaraya-Sundeep/qemu-test-binaries/' - 'fa030bd77a014a0b8e360d3b7011df89283a2f0b/u-boot') - uboot_hash = 'abba5d9c24cdd2d49cdc2a8aa92976cf20737eff' + 'fe371d32e50ca682391e1e70ab98c2942aeffb01/u-boot') + uboot_hash = 'cbb8cbab970f594bf6523b9855be209c08374ae2' uboot_path = self.fetch_asset(uboot_url, asset_hash=uboot_hash) spi_url = ('https://raw.githubusercontent.com/' 'Subbaraya-Sundeep/qemu-test-binaries/' - 'fa030bd77a014a0b8e360d3b7011df89283a2f0b/spi.bin') - spi_hash = '85f698329d38de63aea6e884a86fbde70890a78a' + 'fe371d32e50ca682391e1e70ab98c2942aeffb01/spi.bin') + spi_hash = '65523a1835949b6f4553be96dec1b6a38fb05501' spi_path = self.fetch_asset(spi_url, asset_hash=spi_hash) self.vm.set_console() @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): '-drive', 'file=' + spi_path + ',if=mtd,format=raw', '-no-reboot') self.vm.launch() - self.wait_for_console_pattern('init started: BusyBox') + self.wait_for_console_pattern('Enter \'help\' for a list') + + exec_command_and_wait_for_pattern(self, 'ifconfig eth0 10.0.2.15', + 'eth0: link becomes ready') + exec_command_and_wait_for_pattern(self, 'ping -c 3 10.0.2.2', + '3 packets transmitted, 3 packets received, 0% packet loss') def do_test_arm_raspi2(self, uart_id): """ -- 2.20.1 This object may be used to represent a clock inside a clock tree. A clock may be connected to another clock so that it receives update, through a callback, whenever the source/parent clock is updated. Although only the root clock of a clock tree controls the values (represented as periods) of all clocks in tree, each clock holds a local state containing the current value so that it can be fetched independently. It will allows us to fullfill migration requirements by migrating each clock independently of others. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-2-damien.hedde@greensocs.com [PMM: Use uint64_t rather than unsigned long long in trace events; the dtrace backend can't handle the latter] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 1 + include/hw/clock.h | 216 ++++++++++++++++++++++++++++++++++++++++++ hw/core/clock.c | 130 +++++++++++++++++++++++++ hw/core/trace-events | 7 ++ 4 files changed, 354 insertions(+) create mode 100644 include/hw/clock.h create mode 100644 hw/core/clock.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += hotplug.o common-obj-y += vmstate-if.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o +common-obj-y += clock.o common-obj-$(CONFIG_SOFTMMU) += reset.o common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o diff --git a/include/hw/clock.h b/include/hw/clock.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ +/* + * Hardware Clocks + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * 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 QEMU_HW_CLOCK_H +#define QEMU_HW_CLOCK_H + +#include "qom/object.h" +#include "qemu/queue.h" + +#define TYPE_CLOCK "clock" +#define CLOCK(obj) OBJECT_CHECK(Clock, (obj), TYPE_CLOCK) + +typedef void ClockCallback(void *opaque); + +/* + * clock store a value representing the clock's period in 2^-32ns unit. + * It can represent: + * + periods from 2^-32ns up to 4seconds + * + frequency from ~0.25Hz 2e10Ghz + * Resolution of frequency representation decreases with frequency: + * + at 100MHz, resolution is ~2mHz + * + at 1Ghz, resolution is ~0.2Hz + * + at 10Ghz, resolution is ~20Hz + */ +#define CLOCK_SECOND (1000000000llu << 32) + +/* + * macro helpers to convert to hertz / nanosecond + */ +#define CLOCK_PERIOD_FROM_NS(ns) ((ns) * (CLOCK_SECOND / 1000000000llu)) +#define CLOCK_PERIOD_TO_NS(per) ((per) / (CLOCK_SECOND / 1000000000llu)) +#define CLOCK_PERIOD_FROM_HZ(hz) (((hz) != 0) ? CLOCK_SECOND / (hz) : 0u) +#define CLOCK_PERIOD_TO_HZ(per) (((per) != 0) ? CLOCK_SECOND / (per) : 0u) + +/** + * Clock: + * @parent_obj: parent class + * @period: unsigned integer representing the period of the clock + * @canonical_path: clock path string cache (used for trace purpose) + * @callback: called when clock changes + * @callback_opaque: argument for @callback + * @source: source (or parent in clock tree) of the clock + * @children: list of clocks connected to this one (it is their source) + * @sibling: structure used to form a clock list + */ + +typedef struct Clock Clock; + +struct Clock { + /*< private >*/ + Object parent_obj; + + /* all fields are private and should not be modified directly */ + + /* fields */ + uint64_t period; + char *canonical_path; + ClockCallback *callback; + void *callback_opaque; + + /* Clocks are organized in a clock tree */ + Clock *source; + QLIST_HEAD(, Clock) children; + QLIST_ENTRY(Clock) sibling; +}; + +/** + * clock_setup_canonical_path: + * @clk: clock + * + * compute the canonical path of the clock (used by log messages) + */ +void clock_setup_canonical_path(Clock *clk); + +/** + * clock_set_callback: + * @clk: the clock to register the callback into + * @cb: the callback function + * @opaque: the argument to the callback + * + * Register a callback called on every clock update. + */ +void clock_set_callback(Clock *clk, ClockCallback *cb, void *opaque); + +/** + * clock_clear_callback: + * @clk: the clock to delete the callback from + * + * Unregister the callback registered with clock_set_callback. + */ +void clock_clear_callback(Clock *clk); + +/** + * clock_set_source: + * @clk: the clock. + * @src: the source clock + * + * Setup @src as the clock source of @clk. The current @src period + * value is also copied to @clk and its subtree but no callback is + * called. + * Further @src update will be propagated to @clk and its subtree. + */ +void clock_set_source(Clock *clk, Clock *src); + +/** + * clock_set: + * @clk: the clock to initialize. + * @value: the clock's value, 0 means unclocked + * + * Set the local cached period value of @clk to @value. + */ +void clock_set(Clock *clk, uint64_t value); + +static inline void clock_set_hz(Clock *clk, unsigned hz) +{ + clock_set(clk, CLOCK_PERIOD_FROM_HZ(hz)); +} + +static inline void clock_set_ns(Clock *clk, unsigned ns) +{ + clock_set(clk, CLOCK_PERIOD_FROM_NS(ns)); +} + +/** + * clock_propagate: + * @clk: the clock + * + * Propagate the clock period that has been previously configured using + * @clock_set(). This will update recursively all connected clocks. + * It is an error to call this function on a clock which has a source. + * Note: this function must not be called during device inititialization + * or migration. + */ +void clock_propagate(Clock *clk); + +/** + * clock_update: + * @clk: the clock to update. + * @value: the new clock's value, 0 means unclocked + * + * Update the @clk to the new @value. All connected clocks will be informed + * of this update. This is equivalent to call @clock_set() then + * @clock_propagate(). + */ +static inline void clock_update(Clock *clk, uint64_t value) +{ + clock_set(clk, value); + clock_propagate(clk); +} + +static inline void clock_update_hz(Clock *clk, unsigned hz) +{ + clock_update(clk, CLOCK_PERIOD_FROM_HZ(hz)); +} + +static inline void clock_update_ns(Clock *clk, unsigned ns) +{ + clock_update(clk, CLOCK_PERIOD_FROM_NS(ns)); +} + +/** + * clock_get: + * @clk: the clk to fetch the clock + * + * @return: the current period. + */ +static inline uint64_t clock_get(const Clock *clk) +{ + return clk->period; +} + +static inline unsigned clock_get_hz(Clock *clk) +{ + return CLOCK_PERIOD_TO_HZ(clock_get(clk)); +} + +static inline unsigned clock_get_ns(Clock *clk) +{ + return CLOCK_PERIOD_TO_NS(clock_get(clk)); +} + +/** + * clock_is_enabled: + * @clk: a clock + * + * @return: true if the clock is running. + */ +static inline bool clock_is_enabled(const Clock *clk) +{ + return clock_get(clk) != 0; +} + +static inline void clock_init(Clock *clk, uint64_t value) +{ + clock_set(clk, value); +} +static inline void clock_init_hz(Clock *clk, uint64_t value) +{ + clock_set_hz(clk, value); +} +static inline void clock_init_ns(Clock *clk, uint64_t value) +{ + clock_set_ns(clk, value); +} + +#endif /* QEMU_HW_CLOCK_H */ diff --git a/hw/core/clock.c b/hw/core/clock.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/clock.c @@ -XXX,XX +XXX,XX @@ +/* + * Hardware Clocks + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/clock.h" +#include "trace.h" + +#define CLOCK_PATH(_clk) (_clk->canonical_path) + +void clock_setup_canonical_path(Clock *clk) +{ + g_free(clk->canonical_path); + clk->canonical_path = object_get_canonical_path(OBJECT(clk)); +} + +void clock_set_callback(Clock *clk, ClockCallback *cb, void *opaque) +{ + clk->callback = cb; + clk->callback_opaque = opaque; +} + +void clock_clear_callback(Clock *clk) +{ + clock_set_callback(clk, NULL, NULL); +} + +void clock_set(Clock *clk, uint64_t period) +{ + trace_clock_set(CLOCK_PATH(clk), CLOCK_PERIOD_TO_NS(clk->period), + CLOCK_PERIOD_TO_NS(period)); + clk->period = period; +} + +static void clock_propagate_period(Clock *clk, bool call_callbacks) +{ + Clock *child; + + QLIST_FOREACH(child, &clk->children, sibling) { + if (child->period != clk->period) { + child->period = clk->period; + trace_clock_update(CLOCK_PATH(child), CLOCK_PATH(clk), + CLOCK_PERIOD_TO_NS(clk->period), + call_callbacks); + if (call_callbacks && child->callback) { + child->callback(child->callback_opaque); + } + clock_propagate_period(child, call_callbacks); + } + } +} + +void clock_propagate(Clock *clk) +{ + assert(clk->source == NULL); + trace_clock_propagate(CLOCK_PATH(clk)); + clock_propagate_period(clk, true); +} + +void clock_set_source(Clock *clk, Clock *src) +{ + /* changing clock source is not supported */ + assert(!clk->source); + + trace_clock_set_source(CLOCK_PATH(clk), CLOCK_PATH(src)); + + clk->period = src->period; + QLIST_INSERT_HEAD(&src->children, clk, sibling); + clk->source = src; + clock_propagate_period(clk, false); +} + +static void clock_disconnect(Clock *clk) +{ + if (clk->source == NULL) { + return; + } + + trace_clock_disconnect(CLOCK_PATH(clk)); + + clk->source = NULL; + QLIST_REMOVE(clk, sibling); +} + +static void clock_initfn(Object *obj) +{ + Clock *clk = CLOCK(obj); + + QLIST_INIT(&clk->children); +} + +static void clock_finalizefn(Object *obj) +{ + Clock *clk = CLOCK(obj); + Clock *child, *next; + + /* clear our list of children */ + QLIST_FOREACH_SAFE(child, &clk->children, sibling, next) { + clock_disconnect(child); + } + + /* remove us from source's children list */ + clock_disconnect(clk); + + g_free(clk->canonical_path); +} + +static const TypeInfo clock_info = { + .name = TYPE_CLOCK, + .parent = TYPE_OBJECT, + .instance_size = sizeof(Clock), + .instance_init = clock_initfn, + .instance_finalize = clock_finalizefn, +}; + +static void clock_register_types(void) +{ + type_register_static(&clock_info); +} + +type_init(clock_register_types) diff --git a/hw/core/trace-events b/hw/core/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/core/trace-events +++ b/hw/core/trace-events @@ -XXX,XX +XXX,XX @@ resettable_phase_exit_begin(void *obj, const char *objtype, unsigned count, int resettable_phase_exit_exec(void *obj, const char *objtype, int has_method) "obj=%p(%s) method=%d" resettable_phase_exit_end(void *obj, const char *objtype, unsigned count) "obj=%p(%s) count=%d" resettable_transitional_function(void *obj, const char *objtype) "obj=%p(%s)" + +# clock.c +clock_set_source(const char *clk, const char *src) "'%s', src='%s'" +clock_disconnect(const char *clk) "'%s'" +clock_set(const char *clk, uint64_t old, uint64_t new) "'%s', ns=%"PRIu64"->%"PRIu64 +clock_propagate(const char *clk) "'%s'" +clock_update(const char *clk, const char *src, uint64_t val, int cb) "'%s', src='%s', ns=%"PRIu64", cb=%d" -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-3-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 1 + include/hw/clock.h | 9 +++++++++ hw/core/clock-vmstate.c | 25 +++++++++++++++++++++++++ 3 files changed, 35 insertions(+) create mode 100644 hw/core/clock-vmstate.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SOFTMMU) += null-machine.o common-obj-$(CONFIG_SOFTMMU) += loader.o common-obj-$(CONFIG_SOFTMMU) += machine-hmp-cmds.o common-obj-$(CONFIG_SOFTMMU) += numa.o +common-obj-$(CONFIG_SOFTMMU) += clock-vmstate.o obj-$(CONFIG_SOFTMMU) += machine-qmp-cmds.o common-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o diff --git a/include/hw/clock.h b/include/hw/clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/clock.h +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ struct Clock { QLIST_ENTRY(Clock) sibling; }; +/* + * vmstate description entry to be added in device vmsd. + */ +extern const VMStateDescription vmstate_clock; +#define VMSTATE_CLOCK(field, state) \ + VMSTATE_CLOCK_V(field, state, 0) +#define VMSTATE_CLOCK_V(field, state, version) \ + VMSTATE_STRUCT_POINTER_V(field, state, version, vmstate_clock, Clock) + /** * clock_setup_canonical_path: * @clk: clock diff --git a/hw/core/clock-vmstate.c b/hw/core/clock-vmstate.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/clock-vmstate.c @@ -XXX,XX +XXX,XX @@ +/* + * Clock migration structure + * + * Copyright GreenSocs 2019-2020 + * + * Authors: + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "migration/vmstate.h" +#include "hw/clock.h" + +const VMStateDescription vmstate_clock = { + .name = "clock", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT64(period, Clock), + VMSTATE_END_OF_LIST() + } +}; -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add functions to easily handle clocks with devices. Clock inputs and outputs should be used to handle clock propagation between devices. The API is very similar the GPIO API. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-4-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 2 +- tests/Makefile.include | 1 + include/hw/qdev-clock.h | 104 +++++++++++++++++++++++++ include/hw/qdev-core.h | 12 +++ hw/core/qdev-clock.c | 168 ++++++++++++++++++++++++++++++++++++++++ hw/core/qdev.c | 12 +++ 6 files changed, 298 insertions(+), 1 deletion(-) create mode 100644 include/hw/qdev-clock.h create mode 100644 hw/core/qdev-clock.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += hotplug.o common-obj-y += vmstate-if.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o -common-obj-y += clock.o +common-obj-y += clock.o qdev-clock.o common-obj-$(CONFIG_SOFTMMU) += reset.o common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ tests/test-qdev-global-props$(EXESUF): tests/test-qdev-global-props.o \ hw/core/fw-path-provider.o \ hw/core/reset.o \ hw/core/vmstate-if.o \ + hw/core/clock.o hw/core/qdev-clock.o \ $(test-qapi-obj-y) tests/test-vmstate$(EXESUF): tests/test-vmstate.o \ migration/vmstate.o migration/vmstate-types.o migration/qemu-file.o \ diff --git a/include/hw/qdev-clock.h b/include/hw/qdev-clock.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/qdev-clock.h @@ -XXX,XX +XXX,XX @@ +/* + * Device's clock input and output + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * 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 QDEV_CLOCK_H +#define QDEV_CLOCK_H + +#include "hw/clock.h" + +/** + * qdev_init_clock_in: + * @dev: the device to add an input clock to + * @name: the name of the clock (can't be NULL). + * @callback: optional callback to be called on update or NULL. + * @opaque: argument for the callback + * @returns: a pointer to the newly added clock + * + * Add an input clock to device @dev as a clock named @name. + * This adds a child<> property. + * The callback will be called with @opaque as opaque parameter. + */ +Clock *qdev_init_clock_in(DeviceState *dev, const char *name, + ClockCallback *callback, void *opaque); + +/** + * qdev_init_clock_out: + * @dev: the device to add an output clock to + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the newly added clock + * + * Add an output clock to device @dev as a clock named @name. + * This adds a child<> property. + */ +Clock *qdev_init_clock_out(DeviceState *dev, const char *name); + +/** + * qdev_get_clock_in: + * @dev: the device which has the clock + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the clock + * + * Get the input clock @name from @dev or NULL if does not exist. + */ +Clock *qdev_get_clock_in(DeviceState *dev, const char *name); + +/** + * qdev_get_clock_out: + * @dev: the device which has the clock + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the clock + * + * Get the output clock @name from @dev or NULL if does not exist. + */ +Clock *qdev_get_clock_out(DeviceState *dev, const char *name); + +/** + * qdev_connect_clock_in: + * @dev: a device + * @name: the name of an input clock in @dev + * @source: the source clock (an output clock of another device for example) + * + * Set the source clock of input clock @name of device @dev to @source. + * @source period update will be propagated to @name clock. + */ +static inline void qdev_connect_clock_in(DeviceState *dev, const char *name, + Clock *source) +{ + clock_set_source(qdev_get_clock_in(dev, name), source); +} + +/** + * qdev_alias_clock: + * @dev: the device which has the clock + * @name: the name of the clock in @dev (can't be NULL) + * @alias_dev: the device to add the clock + * @alias_name: the name of the clock in @container + * @returns: a pointer to the clock + * + * Add a clock @alias_name in @alias_dev which is an alias of the clock @name + * in @dev. The direction _in_ or _out_ will the same as the original. + * An alias clock must not be modified or used by @alias_dev and should + * typically be only only for device composition purpose. + */ +Clock *qdev_alias_clock(DeviceState *dev, const char *name, + DeviceState *alias_dev, const char *alias_name); + +/** + * qdev_finalize_clocklist: + * @dev: the device being finalized + * + * Clear the clocklist from @dev. Only used internally in qdev. + */ +void qdev_finalize_clocklist(DeviceState *dev); + +#endif /* QDEV_CLOCK_H */ diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -XXX,XX +XXX,XX @@ struct NamedGPIOList { QLIST_ENTRY(NamedGPIOList) node; }; +typedef struct Clock Clock; +typedef struct NamedClockList NamedClockList; + +struct NamedClockList { + char *name; + Clock *clock; + bool output; + bool alias; + QLIST_ENTRY(NamedClockList) node; +}; + /** * DeviceState: * @realized: Indicates whether the device has been fully constructed. @@ -XXX,XX +XXX,XX @@ struct DeviceState { bool allow_unplug_during_migration; BusState *parent_bus; QLIST_HEAD(, NamedGPIOList) gpios; + QLIST_HEAD(, NamedClockList) clocks; QLIST_HEAD(, BusState) child_bus; int num_child_bus; int instance_id_alias; diff --git a/hw/core/qdev-clock.c b/hw/core/qdev-clock.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/qdev-clock.c @@ -XXX,XX +XXX,XX @@ +/* + * Device's clock input and output + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-core.h" +#include "qapi/error.h" + +/* + * qdev_init_clocklist: + * Add a new clock in a device + */ +static NamedClockList *qdev_init_clocklist(DeviceState *dev, const char *name, + bool output, Clock *clk) +{ + NamedClockList *ncl; + + /* + * Clock must be added before realize() so that we can compute the + * clock's canonical path during device_realize(). + */ + assert(!dev->realized); + + /* + * The ncl structure is freed by qdev_finalize_clocklist() which will + * be called during @dev's device_finalize(). + */ + ncl = g_new0(NamedClockList, 1); + ncl->name = g_strdup(name); + ncl->output = output; + ncl->alias = (clk != NULL); + + /* + * Trying to create a clock whose name clashes with some other + * clock or property is a bug in the caller and we will abort(). + */ + if (clk == NULL) { + clk = CLOCK(object_new(TYPE_CLOCK)); + object_property_add_child(OBJECT(dev), name, OBJECT(clk), &error_abort); + if (output) { + /* + * Remove object_new()'s initial reference. + * Note that for inputs, the reference created by object_new() + * will be deleted in qdev_finalize_clocklist(). + */ + object_unref(OBJECT(clk)); + } + } else { + object_property_add_link(OBJECT(dev), name, + object_get_typename(OBJECT(clk)), + (Object **) &ncl->clock, + NULL, OBJ_PROP_LINK_STRONG, &error_abort); + } + + ncl->clock = clk; + + QLIST_INSERT_HEAD(&dev->clocks, ncl, node); + return ncl; +} + +void qdev_finalize_clocklist(DeviceState *dev) +{ + /* called by @dev's device_finalize() */ + NamedClockList *ncl, *ncl_next; + + QLIST_FOREACH_SAFE(ncl, &dev->clocks, node, ncl_next) { + QLIST_REMOVE(ncl, node); + if (!ncl->output && !ncl->alias) { + /* + * We kept a reference on the input clock to ensure it lives up to + * this point so we can safely remove the callback. + * It avoids having a callback to a deleted object if ncl->clock + * is still referenced somewhere else (eg: by a clock output). + */ + clock_clear_callback(ncl->clock); + object_unref(OBJECT(ncl->clock)); + } + g_free(ncl->name); + g_free(ncl); + } +} + +Clock *qdev_init_clock_out(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_init_clocklist(dev, name, true, NULL); + + return ncl->clock; +} + +Clock *qdev_init_clock_in(DeviceState *dev, const char *name, + ClockCallback *callback, void *opaque) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_init_clocklist(dev, name, false, NULL); + + if (callback) { + clock_set_callback(ncl->clock, callback, opaque); + } + return ncl->clock; +} + +static NamedClockList *qdev_get_clocklist(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + QLIST_FOREACH(ncl, &dev->clocks, node) { + if (strcmp(name, ncl->name) == 0) { + return ncl; + } + } + + return NULL; +} + +Clock *qdev_get_clock_in(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_get_clocklist(dev, name); + assert(!ncl->output); + + return ncl->clock; +} + +Clock *qdev_get_clock_out(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_get_clocklist(dev, name); + assert(ncl->output); + + return ncl->clock; +} + +Clock *qdev_alias_clock(DeviceState *dev, const char *name, + DeviceState *alias_dev, const char *alias_name) +{ + NamedClockList *ncl; + + assert(name && alias_name); + + ncl = qdev_get_clocklist(dev, name); + + qdev_init_clocklist(alias_dev, alias_name, ncl->output, ncl->clock); + + return ncl->clock; +} diff --git a/hw/core/qdev.c b/hw/core/qdev.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "hw/boards.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "migration/vmstate.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void device_set_realized(Object *obj, bool value, Error **errp) DeviceClass *dc = DEVICE_GET_CLASS(dev); HotplugHandler *hotplug_ctrl; BusState *bus; + NamedClockList *ncl; Error *local_err = NULL; bool unattached_parent = false; static int unattached_count; @@ -XXX,XX +XXX,XX @@ static void device_set_realized(Object *obj, bool value, Error **errp) */ g_free(dev->canonical_path); dev->canonical_path = object_get_canonical_path(OBJECT(dev)); + QLIST_FOREACH(ncl, &dev->clocks, node) { + if (ncl->alias) { + continue; + } else { + clock_setup_canonical_path(ncl->clock); + } + } if (qdev_get_vmsd(dev)) { if (vmstate_register_with_alias_id(VMSTATE_IF(dev), @@ -XXX,XX +XXX,XX @@ static void device_initfn(Object *obj) dev->allow_unplug_during_migration = false; QLIST_INIT(&dev->gpios); + QLIST_INIT(&dev->clocks); } static void device_post_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void device_finalize(Object *obj) */ } + qdev_finalize_clocklist(dev); + /* Only send event if the device had been completely realized */ if (dev->pending_deleted_event) { g_assert(dev->canonical_path); -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Introduce a function and macro helpers to setup several clocks in a device from a static array description. An element of the array describes the clock (name and direction) as well as the related callback and an optional offset to store the created object pointer in the device state structure. The array must be terminated by a special element QDEV_CLOCK_END. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-5-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/qdev-clock.h | 55 +++++++++++++++++++++++++++++++++++++++++ hw/core/qdev-clock.c | 17 +++++++++++++ 2 files changed, 72 insertions(+) diff --git a/include/hw/qdev-clock.h b/include/hw/qdev-clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-clock.h +++ b/include/hw/qdev-clock.h @@ -XXX,XX +XXX,XX @@ Clock *qdev_alias_clock(DeviceState *dev, const char *name, */ void qdev_finalize_clocklist(DeviceState *dev); +/** + * ClockPortInitElem: + * @name: name of the clock (can't be NULL) + * @output: indicates whether the clock is input or output + * @callback: for inputs, optional callback to be called on clock's update + * with device as opaque + * @offset: optional offset to store the ClockIn or ClockOut pointer in device + * state structure (0 means unused) + */ +struct ClockPortInitElem { + const char *name; + bool is_output; + ClockCallback *callback; + size_t offset; +}; + +#define clock_offset_value(devstate, field) \ + (offsetof(devstate, field) + \ + type_check(Clock *, typeof_field(devstate, field))) + +#define QDEV_CLOCK(out_not_in, devstate, field, cb) { \ + .name = (stringify(field)), \ + .is_output = out_not_in, \ + .callback = cb, \ + .offset = clock_offset_value(devstate, field), \ +} + +/** + * QDEV_CLOCK_(IN|OUT): + * @devstate: structure type. @dev argument of qdev_init_clocks below must be + * a pointer to that same type. + * @field: a field in @_devstate (must be Clock*) + * @callback: (for input only) callback (or NULL) to be called with the device + * state as argument + * + * The name of the clock will be derived from @field + */ +#define QDEV_CLOCK_IN(devstate, field, callback) \ + QDEV_CLOCK(false, devstate, field, callback) + +#define QDEV_CLOCK_OUT(devstate, field) \ + QDEV_CLOCK(true, devstate, field, NULL) + +#define QDEV_CLOCK_END { .name = NULL } + +typedef struct ClockPortInitElem ClockPortInitArray[]; + +/** + * qdev_init_clocks: + * @dev: the device to add clocks to + * @clocks: a QDEV_CLOCK_END-terminated array which contains the + * clocks information. + */ +void qdev_init_clocks(DeviceState *dev, const ClockPortInitArray clocks); + #endif /* QDEV_CLOCK_H */ diff --git a/hw/core/qdev-clock.c b/hw/core/qdev-clock.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev-clock.c +++ b/hw/core/qdev-clock.c @@ -XXX,XX +XXX,XX @@ Clock *qdev_init_clock_in(DeviceState *dev, const char *name, return ncl->clock; } +void qdev_init_clocks(DeviceState *dev, const ClockPortInitArray clocks) +{ + const struct ClockPortInitElem *elem; + + for (elem = &clocks[0]; elem->name != NULL; elem++) { + Clock **clkp; + /* offset cannot be inside the DeviceState part */ + assert(elem->offset > sizeof(DeviceState)); + clkp = (Clock **)(((void *) dev) + elem->offset); + if (elem->is_output) { + *clkp = qdev_init_clock_out(dev, elem->name); + } else { + *clkp = qdev_init_clock_in(dev, elem->name, elem->callback, dev); + } + } +} + static NamedClockList *qdev_get_clocklist(DeviceState *dev, const char *name) { NamedClockList *ncl; -- 2.20.1 Add the documentation about the clock inputs and outputs in devices. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-6-damien.hedde@greensocs.com [PMM: Editing pass for minor grammar, style and Sphinx formatting fixes] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/devel/clocks.rst | 391 ++++++++++++++++++++++++++++++++++++++++++ docs/devel/index.rst | 1 + 2 files changed, 392 insertions(+) create mode 100644 docs/devel/clocks.rst diff --git a/docs/devel/clocks.rst b/docs/devel/clocks.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/clocks.rst @@ -XXX,XX +XXX,XX @@ +Modelling a clock tree in QEMU +============================== + +What are clocks? +---------------- + +Clocks are QOM objects developed for the purpose of modelling the +distribution of clocks in QEMU. + +They allow us to model the clock distribution of a platform and detect +configuration errors in the clock tree such as badly configured PLL, clock +source selection or disabled clock. + +The object is *Clock* and its QOM name is ``clock`` (in C code, the macro +``TYPE_CLOCK``). + +Clocks are typically used with devices where they are used to model inputs +and outputs. They are created in a similar way to GPIOs. Inputs and outputs +of different devices can be connected together. + +In these cases a Clock object is a child of a Device object, but this +is not a requirement. Clocks can be independent of devices. For +example it is possible to create a clock outside of any device to +model the main clock source of a machine. + +Here is an example of clocks:: + + +---------+ +----------------------+ +--------------+ + | Clock 1 | | Device B | | Device C | + | | | +-------+ +-------+ | | +-------+ | + | |>>-+-->>|Clock 2| |Clock 3|>>--->>|Clock 6| | + +---------+ | | | (in) | | (out) | | | | (in) | | + | | +-------+ +-------+ | | +-------+ | + | | +-------+ | +--------------+ + | | |Clock 4|>> + | | | (out) | | +--------------+ + | | +-------+ | | Device D | + | | +-------+ | | +-------+ | + | | |Clock 5|>>--->>|Clock 7| | + | | | (out) | | | | (in) | | + | | +-------+ | | +-------+ | + | +----------------------+ | | + | | +-------+ | + +----------------------------->>|Clock 8| | + | | (in) | | + | +-------+ | + +--------------+ + +Clocks are defined in the ``include/hw/clock.h`` header and device +related functions are defined in the ``include/hw/qdev-clock.h`` +header. + +The clock state +--------------- + +The state of a clock is its period; it is stored as an integer +representing it in units of 2 :sup:`-32` ns. The special value of 0 is used to +represent the clock being inactive or gated. The clocks do not model +the signal itself (pin toggling) or other properties such as the duty +cycle. + +All clocks contain this state: outputs as well as inputs. This allows +the current period of a clock to be fetched at any time. When a clock +is updated, the value is immediately propagated to all connected +clocks in the tree. + +To ease interaction with clocks, helpers with a unit suffix are defined for +every clock state setter or getter. The suffixes are: + +- ``_ns`` for handling periods in nanoseconds +- ``_hz`` for handling frequencies in hertz + +The 0 period value is converted to 0 in hertz and vice versa. 0 always means +that the clock is disabled. + +Adding a new clock +------------------ + +Adding clocks to a device must be done during the init method of the Device +instance. + +To add an input clock to a device, the function ``qdev_init_clock_in()`` +must be used. It takes the name, a callback and an opaque parameter +for the callback (this will be explained in a following section). +Output is simpler; only the name is required. Typically:: + + qdev_init_clock_in(DEVICE(dev), "clk_in", clk_in_callback, dev); + qdev_init_clock_out(DEVICE(dev), "clk_out"); + +Both functions return the created Clock pointer, which should be saved in the +device's state structure for further use. + +These objects will be automatically deleted by the QOM reference mechanism. + +Note that it is possible to create a static array describing clock inputs and +outputs. The function ``qdev_init_clocks()`` must be called with the array as +parameter to initialize the clocks: it has the same behaviour as calling the +``qdev_init_clock_in/out()`` for each clock in the array. To ease the array +construction, some macros are defined in ``include/hw/qdev-clock.h``. +As an example, the following creates 2 clocks to a device: one input and one +output. + +.. code-block:: c + + /* device structure containing pointers to the clock objects */ + typedef struct MyDeviceState { + DeviceState parent_obj; + Clock *clk_in; + Clock *clk_out; + } MyDeviceState; + + /* + * callback for the input clock (see "Callback on input clock + * change" section below for more information). + */ + static void clk_in_callback(void *opaque); + + /* + * static array describing clocks: + * + a clock input named "clk_in", whose pointer is stored in + * the clk_in field of a MyDeviceState structure with callback + * clk_in_callback. + * + a clock output named "clk_out" whose pointer is stored in + * the clk_out field of a MyDeviceState structure. + */ + static const ClockPortInitArray mydev_clocks = { + QDEV_CLOCK_IN(MyDeviceState, clk_in, clk_in_callback), + QDEV_CLOCK_OUT(MyDeviceState, clk_out), + QDEV_CLOCK_END + }; + + /* device initialization function */ + static void mydev_init(Object *obj) + { + /* cast to MyDeviceState */ + MyDeviceState *mydev = MYDEVICE(obj); + /* create and fill the pointer fields in the MyDeviceState */ + qdev_init_clocks(mydev, mydev_clocks); + [...] + } + +An alternative way to create a clock is to simply call +``object_new(TYPE_CLOCK)``. In that case the clock will neither be an +input nor an output of a device. After the whole QOM hierarchy of the +clock has been set ``clock_setup_canonical_path()`` should be called. + +At creation, the period of the clock is 0: the clock is disabled. You can +change it using ``clock_set_ns()`` or ``clock_set_hz()``. + +Note that if you are creating a clock with a fixed period which will never +change (for example the main clock source of a board), then you'll have +nothing else to do. This value will be propagated to other clocks when +connecting the clocks together and devices will fetch the right value during +the first reset. + +Retrieving clocks from a device +------------------------------- + +``qdev_get_clock_in()`` and ``dev_get_clock_out()`` are available to +get the clock inputs or outputs of a device. For example: + +.. code-block:: c + + Clock *clk = qdev_get_clock_in(DEVICE(mydev), "clk_in"); + +or: + +.. code-block:: c + + Clock *clk = qdev_get_clock_out(DEVICE(mydev), "clk_out"); + +Connecting two clocks together +------------------------------ + +To connect two clocks together, use the ``clock_set_source()`` function. +Given two clocks ``clk1``, and ``clk2``, ``clock_set_source(clk2, clk1);`` +configures ``clk2`` to follow the ``clk1`` period changes. Every time ``clk1`` +is updated, ``clk2`` will be updated too. + +When connecting clock between devices, prefer using the +``qdev_connect_clock_in()`` function to set the source of an input +device clock. For example, to connect the input clock ``clk2`` of +``devB`` to the output clock ``clk1`` of ``devA``, do: + +.. code-block:: c + + qdev_connect_clock_in(devB, "clk2", qdev_get_clock_out(devA, "clk1")) + +We used ``qdev_get_clock_out()`` above, but any clock can drive an +input clock, even another input clock. The following diagram shows +some examples of connections. Note also that a clock can drive several +other clocks. + +:: + + +------------+ +--------------------------------------------------+ + | Device A | | Device B | + | | | +---------------------+ | + | | | | Device C | | + | +-------+ | | +-------+ | +-------+ +-------+ | +-------+ | + | |Clock 1|>>-->>|Clock 2|>>+-->>|Clock 3| |Clock 5|>>>>|Clock 6|>> + | | (out) | | | | (in) | | | | (in) | | (out) | | | (out) | | + | +-------+ | | +-------+ | | +-------+ +-------+ | +-------+ | + +------------+ | | +---------------------+ | + | | | + | | +--------------+ | + | | | Device D | | + | | | +-------+ | | + | +-->>|Clock 4| | | + | | | (in) | | | + | | +-------+ | | + | +--------------+ | + +--------------------------------------------------+ + +In the above example, when *Clock 1* is updated by *Device A*, three +clocks get the new clock period value: *Clock 2*, *Clock 3* and *Clock 4*. + +It is not possible to disconnect a clock or to change the clock connection +after it is connected. + +Unconnected input clocks +------------------------ + +A newly created input clock is disabled (period of 0). This means the +clock will be considered as disabled until the period is updated. If +the clock remains unconnected it will always keep its initial value +of 0. If this is not the desired behaviour, ``clock_set()``, +``clock_set_ns()`` or ``clock_set_hz()`` should be called on the Clock +object during device instance init. For example: + +.. code-block:: c + + clk = qdev_init_clock_in(DEVICE(dev), "clk-in", clk_in_callback, + dev); + /* set initial value to 10ns / 100MHz */ + clock_set_ns(clk, 10); + +Fetching clock frequency/period +------------------------------- + +To get the current state of a clock, use the functions ``clock_get()``, +``clock_get_ns()`` or ``clock_get_hz()``. + +It is also possible to register a callback on clock frequency changes. +Here is an example: + +.. code-block:: c + + void clock_callback(void *opaque) { + MyDeviceState *s = (MyDeviceState *) opaque; + /* + * 'opaque' is the argument passed to qdev_init_clock_in(); + * usually this will be the device state pointer. + */ + + /* do something with the new period */ + fprintf(stdout, "device new period is %" PRIu64 "ns\n", + clock_get_ns(dev->my_clk_input)); + } + +Changing a clock period +----------------------- + +A device can change its outputs using the ``clock_update()``, +``clock_update_ns()`` or ``clock_update_hz()`` function. It will trigger +updates on every connected input. + +For example, let's say that we have an output clock *clkout* and we +have a pointer to it in the device state because we did the following +in init phase: + +.. code-block:: c + + dev->clkout = qdev_init_clock_out(DEVICE(dev), "clkout"); + +Then at any time (apart from the cases listed below), it is possible to +change the clock value by doing: + +.. code-block:: c + + clock_update_hz(dev->clkout, 1000 * 1000 * 1000); /* 1GHz */ + +Because updating a clock may trigger any side effects through +connected clocks and their callbacks, this operation must be done +while holding the qemu io lock. + +For the same reason, one can update clocks only when it is allowed to have +side effects on other objects. In consequence, it is forbidden: + +* during migration, +* and in the enter phase of reset. + +Note that calling ``clock_update[_ns|_hz]()`` is equivalent to calling +``clock_set[_ns|_hz]()`` (with the same arguments) then +``clock_propagate()`` on the clock. Thus, setting the clock value can +be separated from triggering the side-effects. This is often required +to factorize code to handle reset and migration in devices. + +Aliasing clocks +--------------- + +Sometimes, one needs to forward, or inherit, a clock from another +device. Typically, when doing device composition, a device might +expose a sub-device's clock without interfering with it. The function +``qdev_alias_clock()`` can be used to achieve this behaviour. Note +that it is possible to expose the clock under a different name. +``qdev_alias_clock()`` works for both input and output clocks. + +For example, if device B is a child of device A, +``device_a_instance_init()`` may do something like this: + +.. code-block:: c + + void device_a_instance_init(Object *obj) + { + AState *A = DEVICE_A(obj); + BState *B; + /* create object B as child of A */ + [...] + qdev_alias_clock(B, "clk", A, "b_clk"); + /* + * Now A has a clock "b_clk" which is an alias to + * the clock "clk" of its child B. + */ + } + +This function does not return any clock object. The new clock has the +same direction (input or output) as the original one. This function +only adds a link to the existing clock. In the above example, object B +remains the only object allowed to use the clock and device A must not +try to change the clock period or set a callback to the clock. This +diagram describes the example with an input clock:: + + +--------------------------+ + | Device A | + | +--------------+ | + | | Device B | | + | | +-------+ | | + >>"b_clk">>>| "clk" | | | + | (in) | | (in) | | | + | | +-------+ | | + | +--------------+ | + +--------------------------+ + +Migration +--------- + +Clock state is not migrated automatically. Every device must handle its +clock migration. Alias clocks must not be migrated. + +To ensure clock states are restored correctly during migration, there +are two solutions. + +Clock states can be migrated by adding an entry into the device +vmstate description. You should use the ``VMSTATE_CLOCK`` macro for this. +This is typically used to migrate an input clock state. For example: + +.. code-block:: c + + MyDeviceState { + DeviceState parent_obj; + [...] /* some fields */ + Clock *clk; + }; + + VMStateDescription my_device_vmstate = { + .name = "my_device", + .fields = (VMStateField[]) { + [...], /* other migrated fields */ + VMSTATE_CLOCK(clk, MyDeviceState), + VMSTATE_END_OF_LIST() + } + }; + +The second solution is to restore the clock state using information already +at our disposal. This can be used to restore output clock states using the +device state. The functions ``clock_set[_ns|_hz]()`` can be used during the +``post_load()`` migration callback. + +When adding clock support to an existing device, if you care about +migration compatibility you will need to be careful, as simply adding +a ``VMSTATE_CLOCK()`` line will break compatibility. Instead, you can +put the ``VMSTATE_CLOCK()`` line into a vmstate subsection with a +suitable ``needed`` function, and use ``clock_set()`` in a +``pre_load()`` function to set the default value that will be used if +the source virtual machine in the migration does not send the clock +state. + +Care should be taken not to use ``clock_update[_ns|_hz]()`` or +``clock_propagate()`` during the whole migration procedure because it +will trigger side effects to other devices in an unknown state. diff --git a/docs/devel/index.rst b/docs/devel/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -XXX,XX +XXX,XX @@ Contents: bitops reset s390-dasd-ipl + clocks -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add some clocks to zynq_slcr + the main input clock (ps_clk) + the reference clock outputs for each uart (uart0 & 1) This commit also transitional the slcr to multi-phase reset as it is required to initialize the clocks correctly. The clock frequencies are computed using the internal pll & uart configuration registers and the input ps_clk frequency. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Acked-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-7-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 172 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 168 insertions(+), 4 deletions(-) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "qemu/module.h" #include "hw/registerfields.h" +#include "hw/qdev-clock.h" #ifndef ZYNQ_SLCR_ERR_DEBUG #define ZYNQ_SLCR_ERR_DEBUG 0 @@ -XXX,XX +XXX,XX @@ REG32(LOCKSTA, 0x00c) REG32(ARM_PLL_CTRL, 0x100) REG32(DDR_PLL_CTRL, 0x104) REG32(IO_PLL_CTRL, 0x108) +/* fields for [ARM|DDR|IO]_PLL_CTRL registers */ + FIELD(xxx_PLL_CTRL, PLL_RESET, 0, 1) + FIELD(xxx_PLL_CTRL, PLL_PWRDWN, 1, 1) + FIELD(xxx_PLL_CTRL, PLL_BYPASS_QUAL, 3, 1) + FIELD(xxx_PLL_CTRL, PLL_BYPASS_FORCE, 4, 1) + FIELD(xxx_PLL_CTRL, PLL_FPDIV, 12, 7) REG32(PLL_STATUS, 0x10c) REG32(ARM_PLL_CFG, 0x110) REG32(DDR_PLL_CFG, 0x114) @@ -XXX,XX +XXX,XX @@ REG32(SMC_CLK_CTRL, 0x148) REG32(LQSPI_CLK_CTRL, 0x14c) REG32(SDIO_CLK_CTRL, 0x150) REG32(UART_CLK_CTRL, 0x154) + FIELD(UART_CLK_CTRL, CLKACT0, 0, 1) + FIELD(UART_CLK_CTRL, CLKACT1, 1, 1) + FIELD(UART_CLK_CTRL, SRCSEL, 4, 2) + FIELD(UART_CLK_CTRL, DIVISOR, 8, 6) REG32(SPI_CLK_CTRL, 0x158) REG32(CAN_CLK_CTRL, 0x15c) REG32(CAN_MIOCLK_CTRL, 0x160) @@ -XXX,XX +XXX,XX @@ typedef struct ZynqSLCRState { MemoryRegion iomem; uint32_t regs[ZYNQ_SLCR_NUM_REGS]; + + Clock *ps_clk; + Clock *uart0_ref_clk; + Clock *uart1_ref_clk; } ZynqSLCRState; -static void zynq_slcr_reset(DeviceState *d) +/* + * return the output frequency of ARM/DDR/IO pll + * using input frequency and PLL_CTRL register + */ +static uint64_t zynq_slcr_compute_pll(uint64_t input, uint32_t ctrl_reg) { - ZynqSLCRState *s = ZYNQ_SLCR(d); + uint32_t mult = ((ctrl_reg & R_xxx_PLL_CTRL_PLL_FPDIV_MASK) >> + R_xxx_PLL_CTRL_PLL_FPDIV_SHIFT); + + /* first, check if pll is bypassed */ + if (ctrl_reg & R_xxx_PLL_CTRL_PLL_BYPASS_FORCE_MASK) { + return input; + } + + /* is pll disabled ? */ + if (ctrl_reg & (R_xxx_PLL_CTRL_PLL_RESET_MASK | + R_xxx_PLL_CTRL_PLL_PWRDWN_MASK)) { + return 0; + } + + /* frequency multiplier -> period division */ + return input / mult; +} + +/* + * return the output period of a clock given: + * + the periods in an array corresponding to input mux selector + * + the register xxx_CLK_CTRL value + * + enable bit index in ctrl register + * + * This function makes the assumption that the ctrl_reg value is organized as + * follows: + * + bits[13:8] clock frequency divisor + * + bits[5:4] clock mux selector (index in array) + * + bits[index] clock enable + */ +static uint64_t zynq_slcr_compute_clock(const uint64_t periods[], + uint32_t ctrl_reg, + unsigned index) +{ + uint32_t srcsel = extract32(ctrl_reg, 4, 2); /* bits [5:4] */ + uint32_t divisor = extract32(ctrl_reg, 8, 6); /* bits [13:8] */ + + /* first, check if clock is disabled */ + if (((ctrl_reg >> index) & 1u) == 0) { + return 0; + } + + /* + * according to the Zynq technical ref. manual UG585 v1.12.2 in + * Clocks chapter, section 25.10.1 page 705: + * "The 6-bit divider provides a divide range of 1 to 63" + * We follow here what is implemented in linux kernel and consider + * the 0 value as a bypass (no division). + */ + /* frequency divisor -> period multiplication */ + return periods[srcsel] * (divisor ? divisor : 1u); +} + +/* + * macro helper around zynq_slcr_compute_clock to avoid repeating + * the register name. + */ +#define ZYNQ_COMPUTE_CLK(state, plls, reg, enable_field) \ + zynq_slcr_compute_clock((plls), (state)->regs[reg], \ + reg ## _ ## enable_field ## _SHIFT) + +/** + * Compute and set the ouputs clocks periods. + * But do not propagate them further. Connected clocks + * will not receive any updates (See zynq_slcr_compute_clocks()) + */ +static void zynq_slcr_compute_clocks(ZynqSLCRState *s) +{ + uint64_t ps_clk = clock_get(s->ps_clk); + + /* consider outputs clocks are disabled while in reset */ + if (device_is_in_reset(DEVICE(s))) { + ps_clk = 0; + } + + uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); + uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); + uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); + + uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; + + /* compute uartX reference clocks */ + clock_set(s->uart0_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); + clock_set(s->uart1_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); +} + +/** + * Propagate the outputs clocks. + * zynq_slcr_compute_clocks() should have been called before + * to configure them. + */ +static void zynq_slcr_propagate_clocks(ZynqSLCRState *s) +{ + clock_propagate(s->uart0_ref_clk); + clock_propagate(s->uart1_ref_clk); +} + +static void zynq_slcr_ps_clk_callback(void *opaque) +{ + ZynqSLCRState *s = (ZynqSLCRState *) opaque; + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} + +static void zynq_slcr_reset_init(Object *obj, ResetType type) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); int i; DB_PRINT("RESET\n"); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset(DeviceState *d) s->regs[R_DDRIOB + 12] = 0x00000021; } +static void zynq_slcr_reset_hold(Object *obj) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); + + /* will disable all output clocks */ + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} + +static void zynq_slcr_reset_exit(Object *obj) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); + + /* will compute output clocks according to ps_clk and registers */ + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} static bool zynq_slcr_check_offset(hwaddr offset, bool rnw) { @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_write(void *opaque, hwaddr offset, qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); } break; + case R_IO_PLL_CTRL: + case R_ARM_PLL_CTRL: + case R_DDR_PLL_CTRL: + case R_UART_CLK_CTRL: + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); + break; } } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps slcr_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; +static const ClockPortInitArray zynq_slcr_clocks = { + QDEV_CLOCK_IN(ZynqSLCRState, ps_clk, zynq_slcr_ps_clk_callback), + QDEV_CLOCK_OUT(ZynqSLCRState, uart0_ref_clk), + QDEV_CLOCK_OUT(ZynqSLCRState, uart1_ref_clk), + QDEV_CLOCK_END +}; + static void zynq_slcr_init(Object *obj) { ZynqSLCRState *s = ZYNQ_SLCR(obj); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_init(Object *obj) memory_region_init_io(&s->iomem, obj, &slcr_ops, s, "slcr", ZYNQ_SLCR_MMIO_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->iomem); + + qdev_init_clocks(DEVICE(obj), zynq_slcr_clocks); } static const VMStateDescription vmstate_zynq_slcr = { .name = "zynq_slcr", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(regs, ZynqSLCRState, ZYNQ_SLCR_NUM_REGS), + VMSTATE_CLOCK_V(ps_clk, ZynqSLCRState, 3), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_zynq_slcr = { static void zynq_slcr_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->vmsd = &vmstate_zynq_slcr; - dc->reset = zynq_slcr_reset; + rc->phases.enter = zynq_slcr_reset_init; + rc->phases.hold = zynq_slcr_reset_hold; + rc->phases.exit = zynq_slcr_reset_exit; } static const TypeInfo zynq_slcr_info = { -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Switch the cadence uart to multi-phase reset and add the reference clock input. The input clock frequency is added to the migration structure. The reference clock controls the baudrate generation. If it disabled, any input characters and events are ignored. If this clock remains unconnected, the uart behaves as before (it default to a 50MHz ref clock). Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-8-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/char/cadence_uart.h | 1 + hw/char/cadence_uart.c | 73 +++++++++++++++++++++++++++++----- hw/char/trace-events | 3 ++ 3 files changed, 67 insertions(+), 10 deletions(-) diff --git a/include/hw/char/cadence_uart.h b/include/hw/char/cadence_uart.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/cadence_uart.h +++ b/include/hw/char/cadence_uart.h @@ -XXX,XX +XXX,XX @@ typedef struct { CharBackend chr; qemu_irq irq; QEMUTimer *fifo_trigger_handle; + Clock *refclk; } CadenceUARTState; static inline DeviceState *cadence_uart_create(hwaddr addr, diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "hw/char/cadence_uart.h" #include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "trace.h" #ifdef CADENCE_UART_ERR_DEBUG #define DB_PRINT(...) do { \ @@ -XXX,XX +XXX,XX @@ #define LOCAL_LOOPBACK (0x2 << UART_MR_CHMODE_SH) #define REMOTE_LOOPBACK (0x3 << UART_MR_CHMODE_SH) -#define UART_INPUT_CLK 50000000 +#define UART_DEFAULT_REF_CLK (50 * 1000 * 1000) #define R_CR (0x00/4) #define R_MR (0x04/4) @@ -XXX,XX +XXX,XX @@ static void uart_send_breaks(CadenceUARTState *s) static void uart_parameters_setup(CadenceUARTState *s) { QEMUSerialSetParams ssp; - unsigned int baud_rate, packet_size; + unsigned int baud_rate, packet_size, input_clk; + input_clk = clock_get_hz(s->refclk); - baud_rate = (s->r[R_MR] & UART_MR_CLKS) ? - UART_INPUT_CLK / 8 : UART_INPUT_CLK; + baud_rate = (s->r[R_MR] & UART_MR_CLKS) ? input_clk / 8 : input_clk; + baud_rate /= (s->r[R_BRGR] * (s->r[R_BDIV] + 1)); + trace_cadence_uart_baudrate(baud_rate); + + ssp.speed = baud_rate; - ssp.speed = baud_rate / (s->r[R_BRGR] * (s->r[R_BDIV] + 1)); packet_size = 1; switch (s->r[R_MR] & UART_MR_PAR) { @@ -XXX,XX +XXX,XX @@ static void uart_parameters_setup(CadenceUARTState *s) } packet_size += ssp.data_bits + ssp.stop_bits; + if (ssp.speed == 0) { + /* + * Avoid division-by-zero below. + * TODO: find something better + */ + ssp.speed = 1; + } s->char_tx_time = (NANOSECONDS_PER_SECOND / ssp.speed) * packet_size; qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_PARAMS, &ssp); } @@ -XXX,XX +XXX,XX @@ static void uart_receive(void *opaque, const uint8_t *buf, int size) CadenceUARTState *s = opaque; uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { uart_write_rx_fifo(opaque, buf, size); } @@ -XXX,XX +XXX,XX @@ static void uart_event(void *opaque, QEMUChrEvent event) CadenceUARTState *s = opaque; uint8_t buf = '\0'; + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if (event == CHR_EVENT_BREAK) { uart_write_rx_fifo(opaque, &buf, 1); } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps uart_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static void cadence_uart_reset(DeviceState *dev) +static void cadence_uart_reset_init(Object *obj, ResetType type) { - CadenceUARTState *s = CADENCE_UART(dev); + CadenceUARTState *s = CADENCE_UART(obj); s->r[R_CR] = 0x00000128; s->r[R_IMR] = 0; @@ -XXX,XX +XXX,XX @@ static void cadence_uart_reset(DeviceState *dev) s->r[R_BRGR] = 0x0000028B; s->r[R_BDIV] = 0x0000000F; s->r[R_TTRIG] = 0x00000020; +} + +static void cadence_uart_reset_hold(Object *obj) +{ + CadenceUARTState *s = CADENCE_UART(obj); uart_rx_reset(s); uart_tx_reset(s); @@ -XXX,XX +XXX,XX @@ static void cadence_uart_realize(DeviceState *dev, Error **errp) uart_event, NULL, s, NULL, true); } +static void cadence_uart_refclk_update(void *opaque) +{ + CadenceUARTState *s = opaque; + + /* recompute uart's speed on clock change */ + uart_parameters_setup(s); +} + static void cadence_uart_init(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void cadence_uart_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq); + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", + cadence_uart_refclk_update, s); + /* initialize the frequency in case the clock remains unconnected */ + clock_set_hz(s->refclk, UART_DEFAULT_REF_CLK); + s->char_tx_time = (NANOSECONDS_PER_SECOND / 9600) * 10; } +static int cadence_uart_pre_load(void *opaque) +{ + CadenceUARTState *s = opaque; + + /* the frequency will be overriden if the refclk field is present */ + clock_set_hz(s->refclk, UART_DEFAULT_REF_CLK); + return 0; +} + static int cadence_uart_post_load(void *opaque, int version_id) { CadenceUARTState *s = opaque; @@ -XXX,XX +XXX,XX @@ static int cadence_uart_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_cadence_uart = { .name = "cadence_uart", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, + .pre_load = cadence_uart_pre_load, .post_load = cadence_uart_post_load, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(r, CadenceUARTState, CADENCE_UART_R_MAX), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_cadence_uart = { VMSTATE_UINT32(tx_count, CadenceUARTState), VMSTATE_UINT32(rx_wpos, CadenceUARTState), VMSTATE_TIMER_PTR(fifo_trigger_handle, CadenceUARTState), + VMSTATE_CLOCK_V(refclk, CadenceUARTState, 3), VMSTATE_END_OF_LIST() - } + }, }; static Property cadence_uart_properties[] = { @@ -XXX,XX +XXX,XX @@ static Property cadence_uart_properties[] = { static void cadence_uart_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->realize = cadence_uart_realize; dc->vmsd = &vmstate_cadence_uart; - dc->reset = cadence_uart_reset; + rc->phases.enter = cadence_uart_reset_init; + rc->phases.hold = cadence_uart_reset_hold; device_class_set_props(dc, cadence_uart_properties); } diff --git a/hw/char/trace-events b/hw/char/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -XXX,XX +XXX,XX @@ exynos_uart_wo_read(uint32_t channel, const char *name, uint32_t reg) "UART%d: T exynos_uart_rxsize(uint32_t channel, uint32_t size) "UART%d: Rx FIFO size: %d" exynos_uart_channel_error(uint32_t channel) "Wrong UART channel number: %d" exynos_uart_rx_timeout(uint32_t channel, uint32_t stat, uint32_t intsp) "UART%d: Rx timeout stat=0x%x intsp=0x%x" + +# hw/char/cadence_uart.c +cadence_uart_baudrate(unsigned baudrate) "baudrate %u" -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add the connection between the slcr's output clocks and the uarts inputs. Also add the main board clock 'ps_clk', which is hard-coded to 33.33MHz (the default frequency). This clock is used to feed the slcr's input clock. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-9-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 57 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 49 insertions(+), 8 deletions(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/cadence_uart.h" #include "hw/net/cadence_gem.h" #include "hw/cpu/a9mpcore.h" +#include "hw/qdev-clock.h" +#include "sysemu/reset.h" + +#define TYPE_ZYNQ_MACHINE MACHINE_TYPE_NAME("xilinx-zynq-a9") +#define ZYNQ_MACHINE(obj) \ + OBJECT_CHECK(ZynqMachineState, (obj), TYPE_ZYNQ_MACHINE) + +/* board base frequency: 33.333333 MHz */ +#define PS_CLK_FREQUENCY (100 * 1000 * 1000 / 3) #define NUM_SPI_FLASHES 4 #define NUM_QSPI_FLASHES 2 @@ -XXX,XX +XXX,XX @@ static const int dma_irqs[8] = { 0xe3401000 + ARMV7_IMM16(extract32((val), 16, 16)), /* movt r1 ... */ \ 0xe5801000 + (addr) +typedef struct ZynqMachineState { + MachineState parent; + Clock *ps_clk; +} ZynqMachineState; + static void zynq_write_board_setup(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, static void zynq_init(MachineState *machine) { + ZynqMachineState *zynq_machine = ZYNQ_MACHINE(machine); ARMCPU *cpu; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *ocm_ram = g_new(MemoryRegion, 1); - DeviceState *dev; + DeviceState *dev, *slcr; SysBusDevice *busdev; qemu_irq pic[64]; int n; @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) 1, 0x0066, 0x0022, 0x0000, 0x0000, 0x0555, 0x2aa, 0); - dev = qdev_create(NULL, "xilinx,zynq_slcr"); - qdev_init_nofail(dev); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xF8000000); + /* Create slcr, keep a pointer to connect clocks */ + slcr = qdev_create(NULL, "xilinx,zynq_slcr"); + qdev_init_nofail(slcr); + sysbus_mmio_map(SYS_BUS_DEVICE(slcr), 0, 0xF8000000); + + /* Create the main clock source, and feed slcr with it */ + zynq_machine->ps_clk = CLOCK(object_new(TYPE_CLOCK)); + object_property_add_child(OBJECT(zynq_machine), "ps_clk", + OBJECT(zynq_machine->ps_clk), &error_abort); + object_unref(OBJECT(zynq_machine->ps_clk)); + clock_set_hz(zynq_machine->ps_clk, PS_CLK_FREQUENCY); + qdev_connect_clock_in(slcr, "ps_clk", zynq_machine->ps_clk); dev = qdev_create(NULL, TYPE_A9MPCORE_PRIV); qdev_prop_set_uint32(dev, "num-cpu", 1); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_create_simple(TYPE_CHIPIDEA, 0xE0002000, pic[53 - IRQ_OFFSET]); sysbus_create_simple(TYPE_CHIPIDEA, 0xE0003000, pic[76 - IRQ_OFFSET]); - cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); - cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); + dev = cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); + qdev_connect_clock_in(dev, "refclk", + qdev_get_clock_out(slcr, "uart0_ref_clk")); + dev = cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); + qdev_connect_clock_in(dev, "refclk", + qdev_get_clock_out(slcr, "uart1_ref_clk")); sysbus_create_varargs("cadence_ttc", 0xF8001000, pic[42-IRQ_OFFSET], pic[43-IRQ_OFFSET], pic[44-IRQ_OFFSET], NULL); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) arm_load_kernel(ARM_CPU(first_cpu), machine, &zynq_binfo); } -static void zynq_machine_init(MachineClass *mc) +static void zynq_machine_class_init(ObjectClass *oc, void *data) { + MachineClass *mc = MACHINE_CLASS(oc); mc->desc = "Xilinx Zynq Platform Baseboard for Cortex-A9"; mc->init = zynq_init; mc->max_cpus = 1; @@ -XXX,XX +XXX,XX @@ static void zynq_machine_init(MachineClass *mc) mc->default_ram_id = "zynq.ext_ram"; } -DEFINE_MACHINE("xilinx-zynq-a9", zynq_machine_init) +static const TypeInfo zynq_machine_type = { + .name = TYPE_ZYNQ_MACHINE, + .parent = TYPE_MACHINE, + .class_init = zynq_machine_class_init, + .instance_size = sizeof(ZynqMachineState), +}; + +static void zynq_machine_register_types(void) +{ + type_register_static(&zynq_machine_type); +} + +type_init(zynq_machine_register_types) -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> This prints the clocks attached to a DeviceState when using "info qtree" monitor command. For every clock, it displays the direction, the name and if the clock is forwarded. For input clock, it displays also the frequency. This is based on the original work of Frederic Konrad. Here follows a sample of `info qtree` output on xilinx_zynq machine after linux boot with only one uart clocked: > bus: main-system-bus > type System > [...] > dev: cadence_uart, id "" > gpio-out "sysbus-irq" 1 > clock-in "refclk" freq_hz=0.000000e+00 > chardev = "" > mmio 00000000e0001000/0000000000001000 > dev: cadence_uart, id "" > gpio-out "sysbus-irq" 1 > clock-in "refclk" freq_hz=1.375661e+07 > chardev = "serial0" > mmio 00000000e0000000/0000000000001000 > [...] > dev: xilinx,zynq_slcr, id "" > clock-out "uart1_ref_clk" freq_hz=0.000000e+00 > clock-out "uart0_ref_clk" freq_hz=1.375661e+07 > clock-in "ps_clk" freq_hz=3.333333e+07 > mmio 00000000f8000000/0000000000001000 Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-10-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qdev-monitor.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/qdev-monitor.c b/qdev-monitor.c index XXXXXXX..XXXXXXX 100644 --- a/qdev-monitor.c +++ b/qdev-monitor.c @@ -XXX,XX +XXX,XX @@ #include "migration/misc.h" #include "migration/migration.h" #include "qemu/cutils.h" +#include "hw/clock.h" /* * Aliases were a bad idea from the start. Let's keep them @@ -XXX,XX +XXX,XX @@ static void qdev_print(Monitor *mon, DeviceState *dev, int indent) ObjectClass *class; BusState *child; NamedGPIOList *ngl; + NamedClockList *ncl; qdev_printf("dev: %s, id \"%s\"\n", object_get_typename(OBJECT(dev)), dev->id ? dev->id : ""); @@ -XXX,XX +XXX,XX @@ static void qdev_print(Monitor *mon, DeviceState *dev, int indent) ngl->num_out); } } + QLIST_FOREACH(ncl, &dev->clocks, node) { + qdev_printf("clock-%s%s \"%s\" freq_hz=%e\n", + ncl->output ? "out" : "in", + ncl->alias ? " (alias)" : "", + ncl->name, + CLOCK_PERIOD_TO_HZ(1.0 * clock_get(ncl->clock))); + } class = object_get_class(OBJECT(dev)); do { qdev_print_props(mon, dev, DEVICE_CLASS(class)->props_, indent); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Setup the ADMA with 128bit bus-width. This matters when FIXED BURST mode is used. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200417153800.27399-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic) dev = qdev_create(NULL, "xlnx.zdma"); s->lpd.iou.adma[i] = SYS_BUS_DEVICE(dev); + object_property_set_int(OBJECT(s->lpd.iou.adma[i]), 128, "bus-width", + &error_abort); object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); qdev_init_nofail(dev); -- 2.20.1 From: Ramon Fried <rfried.dev@gmail.com> Wraparound of TX descriptor cyclic buffer only updated the low 32 bits of the descriptor. Fix that by checking if we're working with 64bit descriptors. Signed-off-by: Ramon Fried <rfried.dev@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200417171736.441607-1-rfried.dev@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { tx_desc_set_last(desc); - packet_desc_addr = s->regs[GEM_TXQBASE]; + + if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + packet_desc_addr = s->regs[GEM_TBQPH]; + packet_desc_addr <<= 32; + } else { + packet_desc_addr = 0; + } + packet_desc_addr |= s->regs[GEM_TXQBASE]; } else { packet_desc_addr += 4 * gem_get_desc_len(s, false); } -- 2.20.1 From: Ramon Fried <rfried.dev@gmail.com> The RX ring descriptors control field is used for setting SOF and EOF (start of frame and end of frame). The SOF and EOF weren't cleared from the previous descriptors, causing inconsistencies in ring buffer. Fix that by clearing the control field of every descriptors we're processing. Signed-off-by: Ramon Fried <rfried.dev@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200418085145.489726-1-rfried.dev@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static inline void rx_desc_set_sof(uint32_t *desc) desc[1] |= DESC_1_RX_SOF; } +static inline void rx_desc_clear_control(uint32_t *desc) +{ + desc[1] = 0; +} + static inline void rx_desc_set_eof(uint32_t *desc) { desc[1] |= DESC_1_RX_EOF; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) rxbuf_ptr += MIN(bytes_to_copy, rxbufsize); bytes_to_copy -= MIN(bytes_to_copy, rxbufsize); + rx_desc_clear_control(s->rx_desc[q]); + /* Update the descriptor. */ if (first_desc) { rx_desc_set_sof(s->rx_desc[q]); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These instructions are often used in glibc's string routines. They were the final uses of the 32-bit at a time neon helpers. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200418162808.4680-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 27 ++-- target/arm/translate.h | 5 + target/arm/neon_helper.c | 24 ---- target/arm/translate-a64.c | 64 +++------- target/arm/translate.c | 256 +++++++++++++++++++++++++++++++------ target/arm/vec_helper.c | 25 ++++ 6 files changed, 278 insertions(+), 123 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_hsub_u16, i32, i32, i32) DEF_HELPER_2(neon_hsub_s32, s32, s32, s32) DEF_HELPER_2(neon_hsub_u32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u8, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s8, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u16, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s16, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s32, i32, i32, i32) -DEF_HELPER_2(neon_cge_u8, i32, i32, i32) -DEF_HELPER_2(neon_cge_s8, i32, i32, i32) -DEF_HELPER_2(neon_cge_u16, i32, i32, i32) -DEF_HELPER_2(neon_cge_s16, i32, i32, i32) -DEF_HELPER_2(neon_cge_u32, i32, i32, i32) -DEF_HELPER_2(neon_cge_s32, i32, i32, i32) - DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) DEF_HELPER_2(neon_pmin_u16, i32, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_mul_u16, i32, i32, i32) DEF_HELPER_2(neon_tst_u8, i32, i32, i32) DEF_HELPER_2(neon_tst_u16, i32, i32, i32) DEF_HELPER_2(neon_tst_u32, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u8, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u16, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u32, i32, i32, i32) DEF_HELPER_1(neon_clz_u8, i32, i32) DEF_HELPER_1(neon_clz_u16, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(frint32_d, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(frint64_d, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_3(gvec_ceq0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_clt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_clt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cle0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cgt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) uint64_t vfp_expand_imm(int size, uint8_t imm8); /* Vector operations shared between ARM and AArch64. */ +extern const GVecGen2 ceq0_op[4]; +extern const GVecGen2 clt0_op[4]; +extern const GVecGen2 cgt0_op[4]; +extern const GVecGen2 cle0_op[4]; +extern const GVecGen2 cge0_op[4]; extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_hsub_u32)(uint32_t src1, uint32_t src2) return dest; } -#define NEON_FN(dest, src1, src2) dest = (src1 > src2) ? ~0 : 0 -NEON_VOP(cgt_s8, neon_s8, 4) -NEON_VOP(cgt_u8, neon_u8, 4) -NEON_VOP(cgt_s16, neon_s16, 2) -NEON_VOP(cgt_u16, neon_u16, 2) -NEON_VOP(cgt_s32, neon_s32, 1) -NEON_VOP(cgt_u32, neon_u32, 1) -#undef NEON_FN - -#define NEON_FN(dest, src1, src2) dest = (src1 >= src2) ? ~0 : 0 -NEON_VOP(cge_s8, neon_s8, 4) -NEON_VOP(cge_u8, neon_u8, 4) -NEON_VOP(cge_s16, neon_s16, 2) -NEON_VOP(cge_u16, neon_u16, 2) -NEON_VOP(cge_s32, neon_s32, 1) -NEON_VOP(cge_u32, neon_u32, 1) -#undef NEON_FN - #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) @@ -XXX,XX +XXX,XX @@ NEON_VOP(tst_u16, neon_u16, 2) NEON_VOP(tst_u32, neon_u32, 1) #undef NEON_FN -#define NEON_FN(dest, src1, src2) dest = (src1 == src2) ? -1 : 0 -NEON_VOP(ceq_u8, neon_u8, 4) -NEON_VOP(ceq_u16, neon_u16, 2) -NEON_VOP(ceq_u32, neon_u32, 1) -#undef NEON_FN - /* Count Leading Sign/Zero Bits. */ static inline int do_clz8(uint8_t x) { diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm, is_q ? 16 : 8, vec_full_reg_size(s)); } +/* Expand a 2-operand AdvSIMD vector operation using an op descriptor. */ +static void gen_gvec_op2(DisasContext *s, bool is_q, int rd, + int rn, const GVecGen2 *gvec_op) +{ + tcg_gen_gvec_2(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), + is_q ? 16 : 8, vec_full_reg_size(s), gvec_op); +} + /* Expand a 2-operand + immediate AdvSIMD vector operation using * an op descriptor. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; + case 0x8: /* CMGT, CMGE */ + gen_gvec_op2(s, is_q, rd, rn, u ? &cge0_op[size] : &cgt0_op[size]); + return; + case 0x9: /* CMEQ, CMLE */ + gen_gvec_op2(s, is_q, rd, rn, u ? &cle0_op[size] : &ceq0_op[size]); + return; + case 0xa: /* CMLT */ + gen_gvec_op2(s, is_q, rd, rn, &clt0_op[size]); + return; case 0xb: if (u) { /* ABS, NEG */ gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_neg, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) for (pass = 0; pass < (is_q ? 4 : 2); pass++) { TCGv_i32 tcg_op = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); - TCGCond cond; read_vec_element_i32(s, tcg_op, rn, pass, MO_32); if (size == 2) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0xa: /* CMLT */ - /* 32 bit integer comparison against zero, result is - * test ? (2^32 - 1) : 0. We implement via setcond(test) - * and inverting. - */ - cond = TCG_COND_LT; - do_cmop: - tcg_gen_setcondi_i32(cond, tcg_res, tcg_op, 0); - tcg_gen_neg_i32(tcg_res, tcg_res); - break; - case 0x8: /* CMGT, CMGE */ - cond = u ? TCG_COND_GE : TCG_COND_GT; - goto do_cmop; - case 0x9: /* CMEQ, CMLE */ - cond = u ? TCG_COND_LE : TCG_COND_EQ; - goto do_cmop; case 0x4: /* CLS */ if (u) { tcg_gen_clzi_i32(tcg_res, tcg_op, 32); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) genfn(tcg_res, cpu_env, tcg_op); break; } - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - case 0xa: /* CMLT */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_cgt_s8, gen_helper_neon_cgt_s16 }, - { gen_helper_neon_cge_s8, gen_helper_neon_cge_s16 }, - { gen_helper_neon_ceq_u8, gen_helper_neon_ceq_u16 }, - }; - NeonGenTwoOpFn *genfn; - int comp; - bool reverse; - TCGv_i32 tcg_zero = tcg_const_i32(0); - - /* comp = index into [CMGT, CMGE, CMEQ, CMLE, CMLT] */ - comp = (opcode - 0x8) * 2 + u; - /* ...but LE, LT are implemented as reverse GE, GT */ - reverse = (comp > 2); - if (reverse) { - comp = 4 - comp; - } - genfn = fns[comp][size]; - if (reverse) { - genfn(tcg_res, tcg_zero, tcg_op); - } else { - genfn(tcg_res, tcg_op, tcg_zero); - } - tcg_temp_free_i32(tcg_zero); - break; - } case 0x4: /* CLS, CLZ */ if (u) { if (size == 0) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, return 1; } +static void gen_ceq0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_EQ, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_ceq0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_EQ, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_ceq0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_EQ, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +static const TCGOpcode vecop_list_cmp[] = { + INDEX_op_cmp_vec, 0 +}; + +const GVecGen2 ceq0_op[4] = { + { .fno = gen_helper_gvec_ceq0_b, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_ceq0_h, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_ceq0_i32, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_ceq0_i64, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cle0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_LE, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cle0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_LE, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cle0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_LE, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cle0_op[4] = { + { .fno = gen_helper_gvec_cle0_b, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cle0_h, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cle0_i32, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cle0_i64, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cge0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_GE, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cge0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_GE, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cge0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_GE, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cge0_op[4] = { + { .fno = gen_helper_gvec_cge0_b, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cge0_h, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cge0_i32, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cge0_i64, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_clt0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_LT, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_clt0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_LT, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_clt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_LT, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 clt0_op[4] = { + { .fno = gen_helper_gvec_clt0_b, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_clt0_h, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_clt0_i32, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_clt0_i64, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cgt0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_GT, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cgt0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_GT, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cgt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_GT, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cgt0_op[4] = { + { .fno = gen_helper_gvec_cgt0_b, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cgt0_h, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cgt0_i32, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cgt0_i64, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { tcg_gen_vec_sar8i_i64(a, a, shift); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_abs(size, rd_ofs, rm_ofs, vec_size, vec_size); break; + case NEON_2RM_VCEQ0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &ceq0_op[size]); + break; + case NEON_2RM_VCGT0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cgt0_op[size]); + break; + case NEON_2RM_VCLE0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cle0_op[size]); + break; + case NEON_2RM_VCGE0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cge0_op[size]); + break; + case NEON_2RM_VCLT0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &clt0_op[size]); + break; + default: elementwise: for (pass = 0; pass < (q ? 4 : 2); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: abort(); } break; - case NEON_2RM_VCGT0: case NEON_2RM_VCLE0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_cgt_s8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_cgt_s16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_cgt_s32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - if (op == NEON_2RM_VCLE0) { - tcg_gen_not_i32(tmp, tmp); - } - break; - case NEON_2RM_VCGE0: case NEON_2RM_VCLT0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_cge_s8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_cge_s16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_cge_s32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - if (op == NEON_2RM_VCLT0) { - tcg_gen_not_i32(tmp, tmp); - } - break; - case NEON_2RM_VCEQ0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_ceq_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_ceq_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_ceq_u32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - break; case NEON_2RM_VCGT0_F: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) } } #endif + +#define DO_CMP0(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + *(TYPE *)(vd + i) = -(nn OP 0); \ + } \ + clear_tail(vd, opr_sz, simd_maxsz(desc)); \ +} + +DO_CMP0(gvec_ceq0_b, int8_t, ==) +DO_CMP0(gvec_clt0_b, int8_t, <) +DO_CMP0(gvec_cle0_b, int8_t, <=) +DO_CMP0(gvec_cgt0_b, int8_t, >) +DO_CMP0(gvec_cge0_b, int8_t, >=) + +DO_CMP0(gvec_ceq0_h, int16_t, ==) +DO_CMP0(gvec_clt0_h, int16_t, <) +DO_CMP0(gvec_cle0_h, int16_t, <=) +DO_CMP0(gvec_cgt0_h, int16_t, >) +DO_CMP0(gvec_cge0_h, int16_t, >=) + +#undef DO_CMP0 -- 2.20.1 From: Jerome Forissier <jerome@forissier.org> The /secure-chosen node is currently used only by create_uart(), but this will change. Therefore move the creation of this node to create_fdt(). Signed-off-by: Jerome Forissier <jerome@forissier.org> Message-id: 20200420121807.8204-2-jerome@forissier.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); + if (vms->secure) { + qemu_fdt_add_subnode(fdt, "/secure-chosen"); + } + /* Clock node, for the benefit of the UART. The kernel device tree * binding documentation claims the PL011 node clock properties are * optional but in practice if you omit them the kernel refuses to @@ -XXX,XX +XXX,XX @@ static void create_uart(const VirtMachineState *vms, int uart, qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled"); qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay"); - qemu_fdt_add_subnode(vms->fdt, "/secure-chosen"); qemu_fdt_setprop_string(vms->fdt, "/secure-chosen", "stdout-path", nodename); } -- 2.20.1 From: Jerome Forissier <jerome@forissier.org> Generate random seeds to be used by the non-secure and/or secure OSes for ASLR. The seeds are 64-bit random values exported via the DT properties /chosen/kaslr-seed [1] and /secure-chosen/kaslr-seed, the latter being used by OP-TEE [2]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e5bc0c37c97e1 [2] https://github.com/OP-TEE/optee_os/commit/ef262691fe0e Signed-off-by: Jerome Forissier <jerome@forissier.org> Message-id: 20200420121807.8204-3-jerome@forissier.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ #include "hw/acpi/generic_event_device.h" #include "hw/virtio/virtio-iommu.h" #include "hw/char/pl011.h" +#include "qemu/guest-random.h" #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ @@ -XXX,XX +XXX,XX @@ static bool cpu_type_valid(const char *cpu) return false; } +static void create_kaslr_seed(VirtMachineState *vms, const char *node) +{ + Error *err = NULL; + uint64_t seed; + + if (qemu_guest_getrandom(&seed, sizeof(seed), &err)) { + error_free(err); + return; + } + qemu_fdt_setprop_u64(vms->fdt, node, "kaslr-seed", seed); +} + static void create_fdt(VirtMachineState *vms) { MachineState *ms = MACHINE(vms); @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); + create_kaslr_seed(vms, "/chosen"); if (vms->secure) { qemu_fdt_add_subnode(fdt, "/secure-chosen"); + create_kaslr_seed(vms, "/secure-chosen"); } /* Clock node, for the benefit of the UART. The kernel device tree -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Under KVM these registers are written by the hardware. Restrict the writefn handlers to TCG to avoid when building without TCG: LINK aarch64-softmmu/qemu-system-aarch64 target/arm/helper.o: In function `do_ats_write': target/arm/helper.c:3524: undefined reference to `raise_exception' Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-2-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 17 +++++++++++++++++ 1 file changed, 17 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 @@ static CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri, return CP_ACCESS_OK; } +#ifdef CONFIG_TCG static uint64_t do_ats_write(CPUARMState *env, uint64_t value, MMUAccessType access_type, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, } return par64; } +#endif /* CONFIG_TCG */ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; uint64_t par64; ARMMMUIdx mmu_idx; @@ -XXX,XX +XXX,XX @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) par64 = do_ats_write(env, value, access_type, mmu_idx); A32_BANKED_CURRENT_REG_SET(env, par, par64); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } static void ats1h_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; uint64_t par64; par64 = do_ats_write(env, value, access_type, ARMMMUIdx_E2); A32_BANKED_CURRENT_REG_SET(env, par, par64); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } static CPAccessResult at_s1e2_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static CPAccessResult at_s1e2_access(CPUARMState *env, const ARMCPRegInfo *ri, static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; ARMMMUIdx mmu_idx; int secure = arm_is_secure_below_el3(env); @@ -XXX,XX +XXX,XX @@ static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, } env->cp15.par_el[1] = do_ats_write(env, value, access_type, mmu_idx); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } #endif -- 2.20.1 From: Thomas Huth <thuth@redhat.com> Make cpu_register() (renamed to arm_cpu_register()) available from internals.h so we can register CPUs also from other files in the future. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-3-philmd@redhat.com Message-ID: <20190921150420.30743-2-thuth@redhat.com> [PMD: Only take cpu_register() from Thomas's patch] Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu-qom.h | 9 ++++++++- target/arm/cpu.c | 10 ++-------- target/arm/cpu64.c | 8 +------- 3 files changed, 11 insertions(+), 16 deletions(-) diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-qom.h +++ b/target/arm/cpu-qom.h @@ -XXX,XX +XXX,XX @@ struct arm_boot_info; #define TYPE_ARM_MAX_CPU "max-" TYPE_ARM_CPU -typedef struct ARMCPUInfo ARMCPUInfo; +typedef struct ARMCPUInfo { + const char *name; + void (*initfn)(Object *obj); + void (*class_init)(ObjectClass *oc, void *data); +} ARMCPUInfo; + +void arm_cpu_register(const ARMCPUInfo *info); +void aarch64_cpu_register(const ARMCPUInfo *info); /** * ARMCPUClass: diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) #endif /* !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) */ -struct ARMCPUInfo { - const char *name; - void (*initfn)(Object *obj); - void (*class_init)(ObjectClass *oc, void *data); -}; - static const ARMCPUInfo arm_cpus[] = { #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) { .name = "arm926", .initfn = arm926_initfn }, @@ -XXX,XX +XXX,XX @@ static void cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; } -static void cpu_register(const ARMCPUInfo *info) +void arm_cpu_register(const ARMCPUInfo *info) { TypeInfo type_info = { .parent = TYPE_ARM_CPU, @@ -XXX,XX +XXX,XX @@ static void arm_cpu_register_types(void) type_register_static(&idau_interface_type_info); while (info->name) { - cpu_register(info); + arm_cpu_register(info); info++; } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); } -struct ARMCPUInfo { - const char *name; - void (*initfn)(Object *obj); - void (*class_init)(ObjectClass *oc, void *data); -}; - static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, @@ -XXX,XX +XXX,XX @@ static void cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; } -static void aarch64_cpu_register(const ARMCPUInfo *info) +void aarch64_cpu_register(const ARMCPUInfo *info) { TypeInfo type_info = { .parent = TYPE_AARCH64_CPU, -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-4-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 8 +++----- target/arm/cpu64.c | 8 +++----- 2 files changed, 6 insertions(+), 10 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 @@ static const ARMCPUInfo arm_cpus[] = { { .name = "any", .initfn = arm_max_initfn }, #endif #endif - { .name = NULL } }; static Property arm_cpu_properties[] = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo idau_interface_type_info = { static void arm_cpu_register_types(void) { - const ARMCPUInfo *info = arm_cpus; + size_t i; type_register_static(&arm_cpu_type_info); type_register_static(&idau_interface_type_info); - while (info->name) { - arm_cpu_register(info); - info++; + for (i = 0; i < ARRAY_SIZE(arm_cpus); ++i) { + arm_cpu_register(&arm_cpus[i]); } #ifdef CONFIG_KVM diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, - { .name = NULL } }; static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp) @@ -XXX,XX +XXX,XX @@ static const TypeInfo aarch64_cpu_type_info = { static void aarch64_cpu_register_types(void) { - const ARMCPUInfo *info = aarch64_cpus; + size_t i; type_register_static(&aarch64_cpu_type_info); - while (info->name) { - aarch64_cpu_register(info); - info++; + for (i = 0; i < ARRAY_SIZE(aarch64_cpus); ++i) { + aarch64_cpu_register(&aarch64_cpus[i]); } } -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> We will move this code in the next commit. Clean it up first to avoid checkpatch.pl errors. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-5-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 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 @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) CPUARMState *env = &cpu->env; bool ret = false; - /* ARMv7-M interrupt masking works differently than -A or -R. + /* + * ARMv7-M interrupt masking works differently than -A or -R. * There is no FIQ/IRQ distinction. Instead of I and F bits * masking FIQ and IRQ interrupts, an exception is taken only * if it is higher priority than the current execution priority @@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj) static void arm1136_r2_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - /* What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an + /* + * What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an * older core than plain "arm1136". In particular this does not * have the v6K features. * These ID register values are correct for 1136 but may be wrong @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_cpus[] = { { .name = "arm926", .initfn = arm926_initfn }, { .name = "arm946", .initfn = arm946_initfn }, { .name = "arm1026", .initfn = arm1026_initfn }, - /* What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an + /* + * What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an * older core than plain "arm1136". In particular this does not * have the v6K features. */ -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Allow name wildcards in qemu_fdt_node_path(). This is useful to find all nodes with a given compatibility string. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 3 +++ device_tree.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); * NULL. If there is no error but no matching node was found, the * returned array contains a single element equal to NULL. If an error * was encountered when parsing the blob, the function returns NULL + * + * @name may be NULL to wildcard names and only match compatibility + * strings. */ char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, Error **errp); diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, offset = len; break; } - if (!strcmp(iter_name, name)) { + if (!name || !strcmp(iter_name, name)) { char *path; path = g_malloc(path_len); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Make compat in qemu_fdt_node_path() const char *. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-3-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 2 +- device_tree.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); * @name may be NULL to wildcard names and only match compatibility * strings. */ -char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, +char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat, Error **errp); /** diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ char **qemu_fdt_node_unit_path(void *fdt, const char *name, Error **errp) return path_array; } -char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, +char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat, Error **errp) { int offset, len, ret; -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Move arm_boot_info into XlnxZCU102. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-4-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ typedef struct XlnxZCU102 { bool secure; bool virt; + + struct arm_boot_info binfo; } XlnxZCU102; #define TYPE_ZCU102_MACHINE MACHINE_TYPE_NAME("xlnx-zcu102") #define ZCU102_MACHINE(obj) \ OBJECT_CHECK(XlnxZCU102, (obj), TYPE_ZCU102_MACHINE) -static struct arm_boot_info xlnx_zcu102_binfo; static bool zcu102_get_secure(Object *obj, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) /* TODO create and connect IDE devices for ide_drive_get() */ - xlnx_zcu102_binfo.ram_size = ram_size; - xlnx_zcu102_binfo.loader_start = 0; - arm_load_kernel(s->soc.boot_cpu_ptr, machine, &xlnx_zcu102_binfo); + s->binfo.ram_size = ram_size; + s->binfo.loader_start = 0; + arm_load_kernel(s->soc.boot_cpu_ptr, machine, &s->binfo); } static void xlnx_zcu102_machine_instance_init(Object *obj) -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Disable unsupported FDT firmware nodes if a user passes us a DTB with nodes enabled that the machine cannot support due to lack of EL3 or EL2 support. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-5-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qemu/log.h" #include "sysemu/qtest.h" +#include "sysemu/device_tree.h" typedef struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ static void zcu102_set_virt(Object *obj, bool value, Error **errp) s->virt = value; } +static void zcu102_modify_dtb(const struct arm_boot_info *binfo, void *fdt) +{ + XlnxZCU102 *s = container_of(binfo, XlnxZCU102, binfo); + bool method_is_hvc; + char **node_path; + const char *r; + int prop_len; + int i; + + /* If EL3 is enabled, we keep all firmware nodes active. */ + if (!s->secure) { + node_path = qemu_fdt_node_path(fdt, NULL, "xlnx,zynqmp-firmware", + &error_fatal); + + for (i = 0; node_path && node_path[i]; i++) { + r = qemu_fdt_getprop(fdt, node_path[i], "method", &prop_len, NULL); + method_is_hvc = r && !strcmp("hvc", r); + + /* Allow HVC based firmware if EL2 is enabled. */ + if (method_is_hvc && s->virt) { + continue; + } + qemu_fdt_setprop_string(fdt, node_path[i], "status", "disabled"); + } + g_strfreev(node_path); + } +} + static void xlnx_zcu102_init(MachineState *machine) { XlnxZCU102 *s = ZCU102_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) s->binfo.ram_size = ram_size; s->binfo.loader_start = 0; + s->binfo.modify_dtb = zcu102_modify_dtb; arm_load_kernel(s->soc.boot_cpu_ptr, machine, &s->binfo); } -- 2.20.1