diff --git a/fpu/softfloat.c b/fpu/softfloat.c index e0ea599769..fc0b179df4 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -2372,6 +2372,17 @@ float32 float32_muladd(float32 a, float32 b, float32 c, int flags STATUS_PARAM) } } /* Zero plus something non-zero : just return the something */ + if (flags & float_muladd_halve_result) { + if (cExp == 0) { + normalizeFloat32Subnormal(cSig, &cExp, &cSig); + } + /* Subtract one to halve, and one again because roundAndPackFloat32 + * wants one less than the true exponent. + */ + cExp -= 2; + cSig = (cSig | 0x00800000) << 7; + return roundAndPackFloat32(cSign ^ signflip, cExp, cSig STATUS_VAR); + } return packFloat32(cSign ^ signflip, cExp, cSig); } @@ -2408,6 +2419,9 @@ float32 float32_muladd(float32 a, float32 b, float32 c, int flags STATUS_PARAM) /* Throw out the special case of c being an exact zero now */ shift64RightJamming(pSig64, 32, &pSig64); pSig = pSig64; + if (flags & float_muladd_halve_result) { + pExp--; + } return roundAndPackFloat32(zSign, pExp - 1, pSig STATUS_VAR); } @@ -2472,6 +2486,10 @@ float32 float32_muladd(float32 a, float32 b, float32 c, int flags STATUS_PARAM) zSig64 <<= shiftcount; zExp -= shiftcount; } + if (flags & float_muladd_halve_result) { + zExp--; + } + shift64RightJamming(zSig64, 32, &zSig64); return roundAndPackFloat32(zSign, zExp, zSig64 STATUS_VAR); } @@ -4088,6 +4106,17 @@ float64 float64_muladd(float64 a, float64 b, float64 c, int flags STATUS_PARAM) } } /* Zero plus something non-zero : just return the something */ + if (flags & float_muladd_halve_result) { + if (cExp == 0) { + normalizeFloat64Subnormal(cSig, &cExp, &cSig); + } + /* Subtract one to halve, and one again because roundAndPackFloat64 + * wants one less than the true exponent. + */ + cExp -= 2; + cSig = (cSig | 0x0010000000000000ULL) << 10; + return roundAndPackFloat64(cSign ^ signflip, cExp, cSig STATUS_VAR); + } return packFloat64(cSign ^ signflip, cExp, cSig); } @@ -4123,6 +4152,9 @@ float64 float64_muladd(float64 a, float64 b, float64 c, int flags STATUS_PARAM) if (!cSig) { /* Throw out the special case of c being an exact zero now */ shift128RightJamming(pSig0, pSig1, 64, &pSig0, &pSig1); + if (flags & float_muladd_halve_result) { + pExp--; + } return roundAndPackFloat64(zSign, pExp - 1, pSig1 STATUS_VAR); } @@ -4159,6 +4191,9 @@ float64 float64_muladd(float64 a, float64 b, float64 c, int flags STATUS_PARAM) zExp--; } shift128RightJamming(zSig0, zSig1, 64, &zSig0, &zSig1); + if (flags & float_muladd_halve_result) { + zExp--; + } return roundAndPackFloat64(zSign, zExp, zSig1 STATUS_VAR); } else { /* Subtraction */ @@ -4209,6 +4244,9 @@ float64 float64_muladd(float64 a, float64 b, float64 c, int flags STATUS_PARAM) zExp -= (shiftcount + 64); } } + if (flags & float_muladd_halve_result) { + zExp--; + } return roundAndPackFloat64(zSign, zExp, zSig0 STATUS_VAR); } } diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index 66bc0dccc9..45a99c819d 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -224,27 +224,24 @@ static const VMStateDescription vmstate_pxa2xx_cm = { } }; -static int pxa2xx_clkcfg_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t pxa2xx_clkcfg_read(CPUARMState *env, const ARMCPRegInfo *ri) { PXA2xxState *s = (PXA2xxState *)ri->opaque; - *value = s->clkcfg; - return 0; + return s->clkcfg; } -static int pxa2xx_clkcfg_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pxa2xx_clkcfg_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { PXA2xxState *s = (PXA2xxState *)ri->opaque; s->clkcfg = value & 0xf; if (value & 2) { printf("%s: CPU frequency change attempt\n", __func__); } - return 0; } -static int pxa2xx_pwrmode_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pxa2xx_pwrmode_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { PXA2xxState *s = (PXA2xxState *)ri->opaque; static const char *pwrmode[8] = { @@ -310,36 +307,29 @@ static int pxa2xx_pwrmode_write(CPUARMState *env, const ARMCPRegInfo *ri, printf("%s: machine entered %s mode\n", __func__, pwrmode[value & 7]); } - - return 0; } -static int pxa2xx_cppmnc_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t pxa2xx_cppmnc_read(CPUARMState *env, const ARMCPRegInfo *ri) { PXA2xxState *s = (PXA2xxState *)ri->opaque; - *value = s->pmnc; - return 0; + return s->pmnc; } -static int pxa2xx_cppmnc_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pxa2xx_cppmnc_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { PXA2xxState *s = (PXA2xxState *)ri->opaque; s->pmnc = value; - return 0; } -static int pxa2xx_cpccnt_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t pxa2xx_cpccnt_read(CPUARMState *env, const ARMCPRegInfo *ri) { PXA2xxState *s = (PXA2xxState *)ri->opaque; if (s->pmnc & 1) { - *value = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); } else { - *value = 0; + return 0; } - return 0; } static const ARMCPRegInfo pxa_cp_reginfo[] = { diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index 46d337cf84..345fa4a491 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -217,20 +217,17 @@ static const int pxa2xx_cp_reg_map[0x10] = { [0xa] = ICPR2, }; -static int pxa2xx_pic_cp_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t pxa2xx_pic_cp_read(CPUARMState *env, const ARMCPRegInfo *ri) { int offset = pxa2xx_cp_reg_map[ri->crn]; - *value = pxa2xx_pic_mem_read(ri->opaque, offset, 4); - return 0; + return pxa2xx_pic_mem_read(ri->opaque, offset, 4); } -static int pxa2xx_pic_cp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pxa2xx_pic_cp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { int offset = pxa2xx_cp_reg_map[ri->crn]; pxa2xx_pic_mem_write(ri->opaque, offset, value, 4); - return 0; } #define REGINFO_FOR_PIC_CP(NAME, CRN) \ diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c index 93eaa6b2fa..955b8d4945 100644 --- a/hw/intc/arm_gic.c +++ b/hw/intc/arm_gic.c @@ -189,7 +189,7 @@ uint32_t gic_acknowledge_irq(GICState *s, int cpu) } s->last_active[irq][cpu] = s->running_irq[cpu]; - if (s->revision == REV_11MPCORE) { + if (s->revision == REV_11MPCORE || s->revision == REV_NVIC) { /* Clear pending flags for both level and edge triggered interrupts. * Level triggered IRQs will be reasserted once they become inactive. */ diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index 806ae13780..4b4df88527 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -249,11 +249,14 @@ void float_raise( int8 flags STATUS_PARAM); | Using these differs from negating an input or output before calling | the muladd function in that this means that a NaN doesn't have its | sign bit inverted before it is propagated. +| We also support halving the result before rounding, as a special +| case to support the ARM fused-sqrt-step instruction FRSQRTS. *----------------------------------------------------------------------------*/ enum { float_muladd_negate_c = 1, float_muladd_negate_product = 2, float_muladd_negate_result = 4, + float_muladd_halve_result = 8, }; /*---------------------------------------------------------------------------- diff --git a/linux-user/main.c b/linux-user/main.c index cabc9e1a0e..919297736c 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -953,7 +953,8 @@ static int do_strex_a64(CPUARMState *env) goto finish; } } - val = env->xregs[rt]; + /* handle the zero register */ + val = rt == 31 ? 0 : env->xregs[rt]; switch (size) { case 0: segv = put_user_u8(val, addr); @@ -972,7 +973,8 @@ static int do_strex_a64(CPUARMState *env) goto error; } if (is_pair) { - val = env->xregs[rt2]; + /* handle the zero register */ + val = rt2 == 31 ? 0 : env->xregs[rt2]; if (size == 2) { segv = put_user_u32(val, addr + 4); } else { diff --git a/target-arm/cpu.c b/target-arm/cpu.c index 45ad7f0260..6e7ce8905e 100644 --- a/target-arm/cpu.c +++ b/target-arm/cpu.c @@ -128,7 +128,7 @@ static void arm_cpu_reset(CPUState *s) } } - if (env->cp15.c1_sys & (1 << 13)) { + if (env->cp15.c1_sys & SCTLR_V) { env->regs[15] = 0xFFFF0000; } @@ -681,14 +681,12 @@ static void cortex_a9_initfn(Object *obj) } #ifndef CONFIG_USER_ONLY -static int a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) { /* Linux wants the number of processors from here. * Might as well set the interrupt-controller bit too. */ - *value = ((smp_cpus - 1) << 24) | (1 << 23); - return 0; + return ((smp_cpus - 1) << 24) | (1 << 23); } #endif diff --git a/target-arm/cpu.h b/target-arm/cpu.h index 383c58221e..3c8a2dba2f 100644 --- a/target-arm/cpu.h +++ b/target-arm/cpu.h @@ -217,11 +217,6 @@ typedef struct CPUARMState { uint32_t c15_power_control; /* power control */ } cp15; - /* System registers (AArch64) */ - struct { - uint64_t tpidr_el0; - } sr; - struct { uint32_t other_sp; uint32_t vecbase; @@ -337,6 +332,58 @@ int cpu_arm_handle_mmu_fault (CPUARMState *env, target_ulong address, int rw, int mmu_idx); #define cpu_handle_mmu_fault cpu_arm_handle_mmu_fault +/* SCTLR bit meanings. Several bits have been reused in newer + * versions of the architecture; in that case we define constants + * for both old and new bit meanings. Code which tests against those + * bits should probably check or otherwise arrange that the CPU + * is the architectural version it expects. + */ +#define SCTLR_M (1U << 0) +#define SCTLR_A (1U << 1) +#define SCTLR_C (1U << 2) +#define SCTLR_W (1U << 3) /* up to v6; RAO in v7 */ +#define SCTLR_SA (1U << 3) +#define SCTLR_P (1U << 4) /* up to v5; RAO in v6 and v7 */ +#define SCTLR_SA0 (1U << 4) /* v8 onward, AArch64 only */ +#define SCTLR_D (1U << 5) /* up to v5; RAO in v6 */ +#define SCTLR_CP15BEN (1U << 5) /* v7 onward */ +#define SCTLR_L (1U << 6) /* up to v5; RAO in v6 and v7; RAZ in v8 */ +#define SCTLR_B (1U << 7) /* up to v6; RAZ in v7 */ +#define SCTLR_ITD (1U << 7) /* v8 onward */ +#define SCTLR_S (1U << 8) /* up to v6; RAZ in v7 */ +#define SCTLR_SED (1U << 8) /* v8 onward */ +#define SCTLR_R (1U << 9) /* up to v6; RAZ in v7 */ +#define SCTLR_UMA (1U << 9) /* v8 onward, AArch64 only */ +#define SCTLR_F (1U << 10) /* up to v6 */ +#define SCTLR_SW (1U << 10) /* v7 onward */ +#define SCTLR_Z (1U << 11) +#define SCTLR_I (1U << 12) +#define SCTLR_V (1U << 13) +#define SCTLR_RR (1U << 14) /* up to v7 */ +#define SCTLR_DZE (1U << 14) /* v8 onward, AArch64 only */ +#define SCTLR_L4 (1U << 15) /* up to v6; RAZ in v7 */ +#define SCTLR_UCT (1U << 15) /* v8 onward, AArch64 only */ +#define SCTLR_DT (1U << 16) /* up to ??, RAO in v6 and v7 */ +#define SCTLR_nTWI (1U << 16) /* v8 onward */ +#define SCTLR_HA (1U << 17) +#define SCTLR_IT (1U << 18) /* up to ??, RAO in v6 and v7 */ +#define SCTLR_nTWE (1U << 18) /* v8 onward */ +#define SCTLR_WXN (1U << 19) +#define SCTLR_ST (1U << 20) /* up to ??, RAZ in v6 */ +#define SCTLR_UWXN (1U << 20) /* v7 onward */ +#define SCTLR_FI (1U << 21) +#define SCTLR_U (1U << 22) +#define SCTLR_XP (1U << 23) /* up to v6; v7 onward RAO */ +#define SCTLR_VE (1U << 24) /* up to v7 */ +#define SCTLR_E0E (1U << 24) /* v8 onward, AArch64 only */ +#define SCTLR_EE (1U << 25) +#define SCTLR_L2 (1U << 26) /* up to v6, RAZ in v7 */ +#define SCTLR_UCI (1U << 26) /* v8 onward, AArch64 only */ +#define SCTLR_NMFI (1U << 27) +#define SCTLR_TRE (1U << 28) +#define SCTLR_AFE (1U << 29) +#define SCTLR_TE (1U << 30) + #define CPSR_M (0x1fU) #define CPSR_T (1U << 5) #define CPSR_F (1U << 6) @@ -764,14 +811,30 @@ static inline int arm_current_pl(CPUARMState *env) typedef struct ARMCPRegInfo ARMCPRegInfo; -/* Access functions for coprocessor registers. These should return - * 0 on success, or one of the EXCP_* constants if access should cause - * an exception (in which case *value is not written). +typedef enum CPAccessResult { + /* Access is permitted */ + CP_ACCESS_OK = 0, + /* Access fails due to a configurable trap or enable which would + * result in a categorized exception syndrome giving information about + * the failing instruction (ie syndrome category 0x3, 0x4, 0x5, 0x6, + * 0xc or 0x18). + */ + CP_ACCESS_TRAP = 1, + /* Access fails and results in an exception syndrome 0x0 ("uncategorized"). + * Note that this is not a catch-all case -- the set of cases which may + * result in this failure is specifically defined by the architecture. + */ + CP_ACCESS_TRAP_UNCATEGORIZED = 2, +} CPAccessResult; + +/* Access functions for coprocessor registers. These cannot fail and + * may not raise exceptions. */ -typedef int CPReadFn(CPUARMState *env, const ARMCPRegInfo *opaque, - uint64_t *value); -typedef int CPWriteFn(CPUARMState *env, const ARMCPRegInfo *opaque, - uint64_t value); +typedef uint64_t CPReadFn(CPUARMState *env, const ARMCPRegInfo *opaque); +typedef void CPWriteFn(CPUARMState *env, const ARMCPRegInfo *opaque, + uint64_t value); +/* Access permission check functions for coprocessor registers. */ +typedef CPAccessResult CPAccessFn(CPUARMState *env, const ARMCPRegInfo *opaque); /* Hook function for register reset */ typedef void CPResetFn(CPUARMState *env, const ARMCPRegInfo *opaque); @@ -825,6 +888,12 @@ struct ARMCPRegInfo { * 2. both readfn and writefn are specified */ ptrdiff_t fieldoffset; /* offsetof(CPUARMState, field) */ + /* Function for making any access checks for this register in addition to + * those specified by the 'access' permissions bits. If NULL, no extra + * checks required. The access check is performed at runtime, not at + * translate time. + */ + CPAccessFn *accessfn; /* Function for handling reads of this register. If NULL, then reads * will be done by loading from the offset into CPUARMState specified * by fieldoffset. @@ -838,14 +907,14 @@ struct ARMCPRegInfo { /* Function for doing a "raw" read; used when we need to copy * coprocessor state to the kernel for KVM or out for * migration. This only needs to be provided if there is also a - * readfn and it makes an access permission check. + * readfn and it has side effects (for instance clear-on-read bits). */ CPReadFn *raw_readfn; /* Function for doing a "raw" write; used when we need to copy KVM * kernel coprocessor state into userspace, or for inbound * migration. This only needs to be provided if there is also a - * writefn and it makes an access permission check or masks out - * "unwritable" bits or has write-one-to-clear or similar behaviour. + * writefn and it masks out "unwritable" bits or has write-one-to-clear + * or similar behaviour. */ CPWriteFn *raw_writefn; /* Function for resetting the register. If NULL, then reset will be done @@ -880,10 +949,10 @@ static inline void define_one_arm_cp_reg(ARMCPU *cpu, const ARMCPRegInfo *regs) const ARMCPRegInfo *get_arm_cp_reginfo(GHashTable *cpregs, uint32_t encoded_cp); /* CPWriteFn that can be used to implement writes-ignored behaviour */ -int arm_cp_write_ignore(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); +void arm_cp_write_ignore(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); /* CPReadFn that can be used for read-as-zero behaviour */ -int arm_cp_read_zero(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t *value); +uint64_t arm_cp_read_zero(CPUARMState *env, const ARMCPRegInfo *ri); /* CPResetFn that does nothing, for use if no reset is required even * if fieldoffset is non zero. diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c index 6ca958afb1..c2ce33ee88 100644 --- a/target-arm/helper-a64.c +++ b/target-arm/helper-a64.c @@ -123,6 +123,32 @@ uint64_t HELPER(vfp_cmped_a64)(float64 x, float64 y, void *fp_status) return float_rel_to_flags(float64_compare(x, y, fp_status)); } +float32 HELPER(vfp_mulxs)(float32 a, float32 b, void *fpstp) +{ + float_status *fpst = fpstp; + + if ((float32_is_zero(a) && float32_is_infinity(b)) || + (float32_is_infinity(a) && float32_is_zero(b))) { + /* 2.0 with the sign bit set to sign(A) XOR sign(B) */ + return make_float32((1U << 30) | + ((float32_val(a) ^ float32_val(b)) & (1U << 31))); + } + return float32_mul(a, b, fpst); +} + +float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + + if ((float64_is_zero(a) && float64_is_infinity(b)) || + (float64_is_infinity(a) && float64_is_zero(b))) { + /* 2.0 with the sign bit set to sign(A) XOR sign(B) */ + return make_float64((1ULL << 62) | + ((float64_val(a) ^ float64_val(b)) & (1ULL << 63))); + } + return float64_mul(a, b, fpst); +} + uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, uint32_t rn, uint32_t numregs) { @@ -153,3 +179,82 @@ uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, } return result; } + +/* 64bit/double versions of the neon float compare functions */ +uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + return -float64_eq_quiet(a, b, fpst); +} + +uint64_t HELPER(neon_cge_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + return -float64_le(b, a, fpst); +} + +uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + return -float64_lt(b, a, fpst); +} + +/* Reciprocal step and sqrt step. Note that unlike the A32/T32 + * versions, these do a fully fused multiply-add or + * multiply-add-and-halve. + */ +#define float32_two make_float32(0x40000000) +#define float32_three make_float32(0x40400000) +#define float32_one_point_five make_float32(0x3fc00000) + +#define float64_two make_float64(0x4000000000000000ULL) +#define float64_three make_float64(0x4008000000000000ULL) +#define float64_one_point_five make_float64(0x3FF8000000000000ULL) + +float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float32_chs(a); + if ((float32_is_infinity(a) && float32_is_zero(b)) || + (float32_is_infinity(b) && float32_is_zero(a))) { + return float32_two; + } + return float32_muladd(a, b, float32_two, 0, fpst); +} + +float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float64_chs(a); + if ((float64_is_infinity(a) && float64_is_zero(b)) || + (float64_is_infinity(b) && float64_is_zero(a))) { + return float64_two; + } + return float64_muladd(a, b, float64_two, 0, fpst); +} + +float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float32_chs(a); + if ((float32_is_infinity(a) && float32_is_zero(b)) || + (float32_is_infinity(b) && float32_is_zero(a))) { + return float32_one_point_five; + } + return float32_muladd(a, b, float32_three, float_muladd_halve_result, fpst); +} + +float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float64_chs(a); + if ((float64_is_infinity(a) && float64_is_zero(b)) || + (float64_is_infinity(b) && float64_is_zero(a))) { + return float64_one_point_five; + } + return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst); +} diff --git a/target-arm/helper-a64.h b/target-arm/helper-a64.h index 99832ee55e..ab9933cab0 100644 --- a/target-arm/helper-a64.h +++ b/target-arm/helper-a64.h @@ -27,3 +27,12 @@ DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr) DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32) +DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr) +DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr) +DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) +DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) +DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) +DEF_HELPER_FLAGS_3(recpsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr) +DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) +DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr) +DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) diff --git a/target-arm/helper.c b/target-arm/helper.c index 5ae08c9ad1..1b111b6e85 100644 --- a/target-arm/helper.c +++ b/target-arm/helper.c @@ -107,65 +107,56 @@ static int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg) } } -static int raw_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t raw_read(CPUARMState *env, const ARMCPRegInfo *ri) { if (ri->type & ARM_CP_64BIT) { - *value = CPREG_FIELD64(env, ri); + return CPREG_FIELD64(env, ri); } else { - *value = CPREG_FIELD32(env, ri); + return CPREG_FIELD32(env, ri); } - return 0; } -static int raw_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void raw_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { if (ri->type & ARM_CP_64BIT) { CPREG_FIELD64(env, ri) = value; } else { CPREG_FIELD32(env, ri) = value; } - return 0; } -static bool read_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *v) +static uint64_t read_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri) { - /* Raw read of a coprocessor register (as needed for migration, etc) - * return true on success, false if the read is impossible for some reason. - */ + /* Raw read of a coprocessor register (as needed for migration, etc). */ if (ri->type & ARM_CP_CONST) { - *v = ri->resetvalue; + return ri->resetvalue; } else if (ri->raw_readfn) { - return (ri->raw_readfn(env, ri, v) == 0); + return ri->raw_readfn(env, ri); } else if (ri->readfn) { - return (ri->readfn(env, ri, v) == 0); + return ri->readfn(env, ri); } else { - raw_read(env, ri, v); + return raw_read(env, ri); } - return true; } -static bool write_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri, - int64_t v) +static void write_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t v) { /* Raw write of a coprocessor register (as needed for migration, etc). - * Return true on success, false if the write is impossible for some reason. * Note that constant registers are treated as write-ignored; the * caller should check for success by whether a readback gives the * value written. */ if (ri->type & ARM_CP_CONST) { - return true; + return; } else if (ri->raw_writefn) { - return (ri->raw_writefn(env, ri, v) == 0); + ri->raw_writefn(env, ri, v); } else if (ri->writefn) { - return (ri->writefn(env, ri, v) == 0); + ri->writefn(env, ri, v); } else { raw_write(env, ri, v); } - return true; } bool write_cpustate_to_list(ARMCPU *cpu) @@ -177,7 +168,7 @@ bool write_cpustate_to_list(ARMCPU *cpu) for (i = 0; i < cpu->cpreg_array_len; i++) { uint32_t regidx = kvm_to_cpreg_id(cpu->cpreg_indexes[i]); const ARMCPRegInfo *ri; - uint64_t v; + ri = get_arm_cp_reginfo(cpu->cp_regs, regidx); if (!ri) { ok = false; @@ -186,11 +177,7 @@ bool write_cpustate_to_list(ARMCPU *cpu) if (ri->type & ARM_CP_NO_MIGRATE) { continue; } - if (!read_raw_cp_reg(&cpu->env, ri, &v)) { - ok = false; - continue; - } - cpu->cpreg_values[i] = v; + cpu->cpreg_values[i] = read_raw_cp_reg(&cpu->env, ri); } return ok; } @@ -203,7 +190,6 @@ bool write_list_to_cpustate(ARMCPU *cpu) for (i = 0; i < cpu->cpreg_array_len; i++) { uint32_t regidx = kvm_to_cpreg_id(cpu->cpreg_indexes[i]); uint64_t v = cpu->cpreg_values[i]; - uint64_t readback; const ARMCPRegInfo *ri; ri = get_arm_cp_reginfo(cpu->cp_regs, regidx); @@ -218,9 +204,8 @@ bool write_list_to_cpustate(ARMCPU *cpu) * (to catch read-only registers and partially read-only * registers where the incoming migration value doesn't match) */ - if (!write_raw_cp_reg(&cpu->env, ri, v) || - !read_raw_cp_reg(&cpu->env, ri, &readback) || - readback != v) { + write_raw_cp_reg(&cpu->env, ri, v); + if (read_raw_cp_reg(&cpu->env, ri) != v) { ok = false; } } @@ -309,14 +294,13 @@ void init_cpreg_list(ARMCPU *cpu) g_list_free(keys); } -static int dacr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void dacr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { env->cp15.c3 = value; tlb_flush(env, 1); /* Flush TLB as domain not tracked in TLB */ - return 0; } -static int fcse_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void fcse_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { if (env->cp15.c13_fcse != value) { /* Unlike real hardware the qemu TLB uses virtual addresses, @@ -325,10 +309,10 @@ static int fcse_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) tlb_flush(env, 1); env->cp15.c13_fcse = value; } - return 0; } -static int contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) + +static void contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { if (env->cp15.c13_context != value && !arm_feature(env, ARM_FEATURE_MPU)) { /* For VMSA (when not using the LPAE long descriptor page table @@ -338,39 +322,34 @@ static int contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush(env, 1); } env->cp15.c13_context = value; - return 0; } -static int tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Invalidate all (TLBIALL) */ tlb_flush(env, 1); - return 0; } -static int tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ tlb_flush_page(env, value & TARGET_PAGE_MASK); - return 0; } -static int tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Invalidate by ASID (TLBIASID) */ tlb_flush(env, value == 0); - return 0; } -static int tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ tlb_flush_page(env, value & TARGET_PAGE_MASK); - return 0; } static const ARMCPRegInfo cp_reginfo[] = { @@ -450,14 +429,14 @@ static const ARMCPRegInfo not_v7_cp_reginfo[] = { REGINFO_SENTINEL }; -static int cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { if (env->cp15.c1_coproc != value) { env->cp15.c1_coproc = value; /* ??? Is this safe when called from within a TB? */ tb_flush(env); } - return 0; } static const ARMCPRegInfo v6_cp_reginfo[] = { @@ -485,118 +464,88 @@ static const ARMCPRegInfo v6_cp_reginfo[] = { REGINFO_SENTINEL }; - -static int pmreg_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri) { - /* Generic performance monitor register read function for where - * user access may be allowed by PMUSERENR. + /* Perfomance monitor registers user accessibility is controlled + * by PMUSERENR. */ if (arm_current_pl(env) == 0 && !env->cp15.c9_pmuserenr) { - return EXCP_UDEF; + return CP_ACCESS_TRAP; } - *value = CPREG_FIELD32(env, ri); - return 0; + return CP_ACCESS_OK; } -static int pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { - if (arm_current_pl(env) == 0 && !env->cp15.c9_pmuserenr) { - return EXCP_UDEF; - } /* only the DP, X, D and E bits are writable */ env->cp15.c9_pmcr &= ~0x39; env->cp15.c9_pmcr |= (value & 0x39); - return 0; } -static int pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri, +static void pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - if (arm_current_pl(env) == 0 && !env->cp15.c9_pmuserenr) { - return EXCP_UDEF; - } value &= (1 << 31); env->cp15.c9_pmcnten |= value; - return 0; } -static int pmcntenclr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmcntenclr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { - if (arm_current_pl(env) == 0 && !env->cp15.c9_pmuserenr) { - return EXCP_UDEF; - } value &= (1 << 31); env->cp15.c9_pmcnten &= ~value; - return 0; } -static int pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { - if (arm_current_pl(env) == 0 && !env->cp15.c9_pmuserenr) { - return EXCP_UDEF; - } env->cp15.c9_pmovsr &= ~value; - return 0; } -static int pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { - if (arm_current_pl(env) == 0 && !env->cp15.c9_pmuserenr) { - return EXCP_UDEF; - } env->cp15.c9_pmxevtyper = value & 0xff; - return 0; } -static int pmuserenr_write(CPUARMState *env, const ARMCPRegInfo *ri, +static void pmuserenr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { env->cp15.c9_pmuserenr = value & 1; - return 0; } -static int pmintenset_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmintenset_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* We have no event counters so only the C bit can be changed */ value &= (1 << 31); env->cp15.c9_pminten |= value; - return 0; } -static int pmintenclr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmintenclr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { value &= (1 << 31); env->cp15.c9_pminten &= ~value; - return 0; } -static int vbar_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void vbar_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c12_vbar = value & ~0x1Ful; - return 0; } -static int ccsidr_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t ccsidr_read(CPUARMState *env, const ARMCPRegInfo *ri) { ARMCPU *cpu = arm_env_get_cpu(env); - *value = cpu->ccsidr[env->cp15.c0_cssel]; - return 0; + return cpu->ccsidr[env->cp15.c0_cssel]; } -static int csselr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void csselr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c0_cssel = value & 0xf; - return 0; } static const ARMCPRegInfo v7_cp_reginfo[] = { @@ -624,37 +573,41 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { { .name = "PMCNTENSET", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 1, .access = PL0_RW, .resetvalue = 0, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcnten), - .readfn = pmreg_read, .writefn = pmcntenset_write, - .raw_readfn = raw_read, .raw_writefn = raw_write }, + .writefn = pmcntenset_write, + .accessfn = pmreg_access, + .raw_writefn = raw_write }, { .name = "PMCNTENCLR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 2, .access = PL0_RW, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcnten), - .readfn = pmreg_read, .writefn = pmcntenclr_write, + .accessfn = pmreg_access, + .writefn = pmcntenclr_write, .type = ARM_CP_NO_MIGRATE }, { .name = "PMOVSR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 3, .access = PL0_RW, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), - .readfn = pmreg_read, .writefn = pmovsr_write, - .raw_readfn = raw_read, .raw_writefn = raw_write }, - /* Unimplemented so WI. Strictly speaking write accesses in PL0 should - * respect PMUSERENR. - */ + .accessfn = pmreg_access, + .writefn = pmovsr_write, + .raw_writefn = raw_write }, + /* Unimplemented so WI. */ { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4, - .access = PL0_W, .type = ARM_CP_NOP }, + .access = PL0_W, .accessfn = pmreg_access, .type = ARM_CP_NOP }, /* Since we don't implement any events, writing to PMSELR is UNPREDICTABLE. - * We choose to RAZ/WI. XXX should respect PMUSERENR. + * We choose to RAZ/WI. */ { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5, - .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* Unimplemented, RAZ/WI. XXX PMUSERENR */ + .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = pmreg_access }, + /* Unimplemented, RAZ/WI. */ { .name = "PMCCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 0, - .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = pmreg_access }, { .name = "PMXEVTYPER", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 1, .access = PL0_RW, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmxevtyper), - .readfn = pmreg_read, .writefn = pmxevtyper_write, - .raw_readfn = raw_read, .raw_writefn = raw_write }, - /* Unimplemented, RAZ/WI. XXX PMUSERENR */ + .accessfn = pmreg_access, .writefn = pmxevtyper_write, + .raw_writefn = raw_write }, + /* Unimplemented, RAZ/WI. */ { .name = "PMXEVCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 2, - .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = pmreg_access }, { .name = "PMUSERENR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 0, .access = PL0_R | PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmuserenr), @@ -689,34 +642,19 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { REGINFO_SENTINEL }; -static int teecr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void teecr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { value &= 1; env->teecr = value; - return 0; } -static int teehbr_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) -{ - /* This is a helper function because the user access rights - * depend on the value of the TEECR. - */ - if (arm_current_pl(env) == 0 && (env->teecr & 1)) { - return EXCP_UDEF; - } - *value = env->teehbr; - return 0; -} - -static int teehbr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static CPAccessResult teehbr_access(CPUARMState *env, const ARMCPRegInfo *ri) { if (arm_current_pl(env) == 0 && (env->teecr & 1)) { - return EXCP_UDEF; + return CP_ACCESS_TRAP; } - env->teehbr = value; - return 0; + return CP_ACCESS_OK; } static const ARMCPRegInfo t2ee_cp_reginfo[] = { @@ -726,8 +664,7 @@ static const ARMCPRegInfo t2ee_cp_reginfo[] = { .writefn = teecr_write }, { .name = "TEEHBR", .cp = 14, .crn = 1, .crm = 0, .opc1 = 6, .opc2 = 0, .access = PL0_RW, .fieldoffset = offsetof(CPUARMState, teehbr), - .resetvalue = 0, .raw_readfn = raw_read, .raw_writefn = raw_write, - .readfn = teehbr_read, .writefn = teehbr_write }, + .accessfn = teehbr_access, .resetvalue = 0 }, REGINFO_SENTINEL }; @@ -757,6 +694,59 @@ static const ARMCPRegInfo v6k_cp_reginfo[] = { #ifndef CONFIG_USER_ONLY +static CPAccessResult gt_cntfrq_access(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* CNTFRQ: not visible from PL0 if both PL0PCTEN and PL0VCTEN are zero */ + if (arm_current_pl(env) == 0 && !extract32(env->cp15.c14_cntkctl, 0, 2)) { + return CP_ACCESS_TRAP; + } + return CP_ACCESS_OK; +} + +static CPAccessResult gt_counter_access(CPUARMState *env, int timeridx) +{ + /* CNT[PV]CT: not visible from PL0 if ELO[PV]CTEN is zero */ + if (arm_current_pl(env) == 0 && + !extract32(env->cp15.c14_cntkctl, timeridx, 1)) { + return CP_ACCESS_TRAP; + } + return CP_ACCESS_OK; +} + +static CPAccessResult gt_timer_access(CPUARMState *env, int timeridx) +{ + /* CNT[PV]_CVAL, CNT[PV]_CTL, CNT[PV]_TVAL: not visible from PL0 if + * EL0[PV]TEN is zero. + */ + if (arm_current_pl(env) == 0 && + !extract32(env->cp15.c14_cntkctl, 9 - timeridx, 1)) { + return CP_ACCESS_TRAP; + } + return CP_ACCESS_OK; +} + +static CPAccessResult gt_pct_access(CPUARMState *env, + const ARMCPRegInfo *ri) +{ + return gt_counter_access(env, GTIMER_PHYS); +} + +static CPAccessResult gt_vct_access(CPUARMState *env, + const ARMCPRegInfo *ri) +{ + return gt_counter_access(env, GTIMER_VIRT); +} + +static CPAccessResult gt_ptimer_access(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return gt_timer_access(env, GTIMER_PHYS); +} + +static CPAccessResult gt_vtimer_access(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return gt_timer_access(env, GTIMER_VIRT); +} + static uint64_t gt_get_countervalue(CPUARMState *env) { return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / GTIMER_SCALE; @@ -802,17 +792,6 @@ static void gt_recalc_timer(ARMCPU *cpu, int timeridx) } } -static int gt_cntfrq_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) -{ - /* Not visible from PL0 if both PL0PCTEN and PL0VCTEN are zero */ - if (arm_current_pl(env) == 0 && !extract32(env->cp15.c14_cntkctl, 0, 2)) { - return EXCP_UDEF; - } - *value = env->cp15.c14_cntfrq; - return 0; -} - static void gt_cnt_reset(CPUARMState *env, const ARMCPRegInfo *ri) { ARMCPU *cpu = arm_env_get_cpu(env); @@ -821,81 +800,40 @@ static void gt_cnt_reset(CPUARMState *env, const ARMCPRegInfo *ri) timer_del(cpu->gt_timer[timeridx]); } -static int gt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t gt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri) { - int timeridx = ri->opc1 & 1; - - if (arm_current_pl(env) == 0 && - !extract32(env->cp15.c14_cntkctl, timeridx, 1)) { - return EXCP_UDEF; - } - *value = gt_get_countervalue(env); - return 0; + return gt_get_countervalue(env); } -static int gt_cval_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) -{ - int timeridx = ri->opc1 & 1; - - if (arm_current_pl(env) == 0 && - !extract32(env->cp15.c14_cntkctl, 9 - timeridx, 1)) { - return EXCP_UDEF; - } - *value = env->cp15.c14_timer[timeridx].cval; - return 0; -} - -static int gt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void gt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { int timeridx = ri->opc1 & 1; env->cp15.c14_timer[timeridx].cval = value; gt_recalc_timer(arm_env_get_cpu(env), timeridx); - return 0; } -static int gt_tval_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) + +static uint64_t gt_tval_read(CPUARMState *env, const ARMCPRegInfo *ri) { int timeridx = ri->crm & 1; - if (arm_current_pl(env) == 0 && - !extract32(env->cp15.c14_cntkctl, 9 - timeridx, 1)) { - return EXCP_UDEF; - } - *value = (uint32_t)(env->cp15.c14_timer[timeridx].cval - - gt_get_countervalue(env)); - return 0; + return (uint32_t)(env->cp15.c14_timer[timeridx].cval - + gt_get_countervalue(env)); } -static int gt_tval_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void gt_tval_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { int timeridx = ri->crm & 1; env->cp15.c14_timer[timeridx].cval = gt_get_countervalue(env) + + sextract64(value, 0, 32); gt_recalc_timer(arm_env_get_cpu(env), timeridx); - return 0; } -static int gt_ctl_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) -{ - int timeridx = ri->crm & 1; - - if (arm_current_pl(env) == 0 && - !extract32(env->cp15.c14_cntkctl, 9 - timeridx, 1)) { - return EXCP_UDEF; - } - *value = env->cp15.c14_timer[timeridx].ctl; - return 0; -} - -static int gt_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void gt_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { ARMCPU *cpu = arm_env_get_cpu(env); int timeridx = ri->crm & 1; @@ -912,7 +850,6 @@ static int gt_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri, qemu_set_irq(cpu->gt_timer_outputs[timeridx], (oldval & 4) && (value & 2)); } - return 0; } void arm_gt_ptimer_cb(void *opaque) @@ -938,7 +875,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { .access = PL1_RW | PL0_R, .fieldoffset = offsetof(CPUARMState, cp15.c14_cntfrq), .resetvalue = (1000 * 1000 * 1000) / GTIMER_SCALE, - .readfn = gt_cntfrq_read, .raw_readfn = raw_read, + .accessfn = gt_cntfrq_access, }, /* overall control: mostly access permissions */ { .name = "CNTKCTL", .cp = 15, .crn = 14, .crm = 1, .opc1 = 0, .opc2 = 0, @@ -951,32 +888,36 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { .type = ARM_CP_IO, .access = PL1_RW | PL0_R, .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].ctl), .resetvalue = 0, - .readfn = gt_ctl_read, .writefn = gt_ctl_write, - .raw_readfn = raw_read, .raw_writefn = raw_write, + .accessfn = gt_ptimer_access, + .writefn = gt_ctl_write, .raw_writefn = raw_write, }, { .name = "CNTV_CTL", .cp = 15, .crn = 14, .crm = 3, .opc1 = 0, .opc2 = 1, .type = ARM_CP_IO, .access = PL1_RW | PL0_R, .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].ctl), .resetvalue = 0, - .readfn = gt_ctl_read, .writefn = gt_ctl_write, - .raw_readfn = raw_read, .raw_writefn = raw_write, + .accessfn = gt_vtimer_access, + .writefn = gt_ctl_write, .raw_writefn = raw_write, }, /* TimerValue views: a 32 bit downcounting view of the underlying state */ { .name = "CNTP_TVAL", .cp = 15, .crn = 14, .crm = 2, .opc1 = 0, .opc2 = 0, .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, .access = PL1_RW | PL0_R, + .accessfn = gt_ptimer_access, .readfn = gt_tval_read, .writefn = gt_tval_write, }, { .name = "CNTV_TVAL", .cp = 15, .crn = 14, .crm = 3, .opc1 = 0, .opc2 = 0, .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, .access = PL1_RW | PL0_R, + .accessfn = gt_vtimer_access, .readfn = gt_tval_read, .writefn = gt_tval_write, }, /* The counter itself */ { .name = "CNTPCT", .cp = 15, .crm = 14, .opc1 = 0, .access = PL0_R, .type = ARM_CP_64BIT | ARM_CP_NO_MIGRATE | ARM_CP_IO, + .accessfn = gt_pct_access, .readfn = gt_cnt_read, .resetfn = gt_cnt_reset, }, { .name = "CNTVCT", .cp = 15, .crm = 14, .opc1 = 1, .access = PL0_R, .type = ARM_CP_64BIT | ARM_CP_NO_MIGRATE | ARM_CP_IO, + .accessfn = gt_vct_access, .readfn = gt_cnt_read, .resetfn = gt_cnt_reset, }, /* Comparison value, indicating when the timer goes off */ @@ -985,16 +926,16 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { .type = ARM_CP_64BIT | ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].cval), .resetvalue = 0, - .readfn = gt_cval_read, .writefn = gt_cval_write, - .raw_readfn = raw_read, .raw_writefn = raw_write, + .accessfn = gt_ptimer_access, + .writefn = gt_cval_write, .raw_writefn = raw_write, }, { .name = "CNTV_CVAL", .cp = 15, .crm = 14, .opc1 = 3, .access = PL1_RW | PL0_R, .type = ARM_CP_64BIT | ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].cval), .resetvalue = 0, - .readfn = gt_cval_read, .writefn = gt_cval_write, - .raw_readfn = raw_read, .raw_writefn = raw_write, + .accessfn = gt_vtimer_access, + .writefn = gt_cval_write, .raw_writefn = raw_write, }, REGINFO_SENTINEL }; @@ -1010,7 +951,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { #endif -static int par_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void par_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { if (arm_feature(env, ARM_FEATURE_LPAE)) { env->cp15.c7_par = value; @@ -1019,7 +960,6 @@ static int par_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) } else { env->cp15.c7_par = value & 0xfffff1ff; } - return 0; } #ifndef CONFIG_USER_ONLY @@ -1035,7 +975,20 @@ static inline bool extended_addresses_enabled(CPUARMState *env) && (env->cp15.c2_control & (1U << 31)); } -static int ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri) +{ + if (ri->opc2 & 4) { + /* Other states are only available with TrustZone; in + * a non-TZ implementation these registers don't exist + * at all, which is an Uncategorized trap. This underdecoding + * is safe because the reginfo is NO_MIGRATE. + */ + return CP_ACCESS_TRAP_UNCATEGORIZED; + } + return CP_ACCESS_OK; +} + +static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { hwaddr phys_addr; target_ulong page_size; @@ -1043,10 +996,6 @@ static int ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) int ret, is_user = ri->opc2 & 2; int access_type = ri->opc2 & 1; - if (ri->opc2 & 4) { - /* Other states are only available with TrustZone */ - return EXCP_UDEF; - } ret = get_phys_addr(env, value, access_type, is_user, &phys_addr, &prot, &page_size); if (extended_addresses_enabled(env)) { @@ -1088,7 +1037,6 @@ static int ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) } env->cp15.c7_par_hi = 0; } - return 0; } #endif @@ -1099,7 +1047,8 @@ static const ARMCPRegInfo vapa_cp_reginfo[] = { .writefn = par_write }, #ifndef CONFIG_USER_ONLY { .name = "ATS", .cp = 15, .crn = 7, .crm = 8, .opc1 = 0, .opc2 = CP_ANY, - .access = PL1_W, .writefn = ats_write, .type = ARM_CP_NO_MIGRATE }, + .access = PL1_W, .accessfn = ats_access, + .writefn = ats_write, .type = ARM_CP_NO_MIGRATE }, #endif REGINFO_SENTINEL }; @@ -1134,52 +1083,26 @@ static uint32_t extended_mpu_ap_bits(uint32_t val) return ret; } -static int pmsav5_data_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmsav5_data_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c5_data = extended_mpu_ap_bits(value); - return 0; } -static int pmsav5_data_ap_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t pmsav5_data_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = simple_mpu_ap_bits(env->cp15.c5_data); - return 0; + return simple_mpu_ap_bits(env->cp15.c5_data); } -static int pmsav5_insn_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmsav5_insn_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c5_insn = extended_mpu_ap_bits(value); - return 0; } -static int pmsav5_insn_ap_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t pmsav5_insn_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = simple_mpu_ap_bits(env->cp15.c5_insn); - return 0; -} - -static int arm946_prbs_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) -{ - if (ri->crm >= 8) { - return EXCP_UDEF; - } - *value = env->cp15.c6_region[ri->crm]; - return 0; -} - -static int arm946_prbs_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - if (ri->crm >= 8) { - return EXCP_UDEF; - } - env->cp15.c6_region[ri->crm] = value; - return 0; + return simple_mpu_ap_bits(env->cp15.c5_insn); } static const ARMCPRegInfo pmsav5_cp_reginfo[] = { @@ -1204,14 +1127,35 @@ static const ARMCPRegInfo pmsav5_cp_reginfo[] = { .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c2_insn), .resetvalue = 0, }, /* Protection region base and size registers */ - { .name = "946_PRBS", .cp = 15, .crn = 6, .crm = CP_ANY, .opc1 = 0, - .opc2 = CP_ANY, .access = PL1_RW, - .readfn = arm946_prbs_read, .writefn = arm946_prbs_write, }, + { .name = "946_PRBS0", .cp = 15, .crn = 6, .crm = 0, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[0]) }, + { .name = "946_PRBS1", .cp = 15, .crn = 6, .crm = 1, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[1]) }, + { .name = "946_PRBS2", .cp = 15, .crn = 6, .crm = 2, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[2]) }, + { .name = "946_PRBS3", .cp = 15, .crn = 6, .crm = 3, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[3]) }, + { .name = "946_PRBS4", .cp = 15, .crn = 6, .crm = 4, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[4]) }, + { .name = "946_PRBS5", .cp = 15, .crn = 6, .crm = 5, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[5]) }, + { .name = "946_PRBS6", .cp = 15, .crn = 6, .crm = 6, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[6]) }, + { .name = "946_PRBS7", .cp = 15, .crn = 6, .crm = 7, .opc1 = 0, + .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.c6_region[7]) }, REGINFO_SENTINEL }; -static int vmsa_ttbcr_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void vmsa_ttbcr_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { int maskshift = extract32(value, 0, 3); @@ -1228,11 +1172,10 @@ static int vmsa_ttbcr_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.c2_control = value; env->cp15.c2_mask = ~(((uint32_t)0xffffffffu) >> maskshift); env->cp15.c2_base_mask = ~((uint32_t)0x3fffu >> maskshift); - return 0; } -static int vmsa_ttbcr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void vmsa_ttbcr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { if (arm_feature(env, ARM_FEATURE_LPAE)) { /* With LPAE the TTBCR could result in a change of ASID @@ -1240,7 +1183,7 @@ static int vmsa_ttbcr_write(CPUARMState *env, const ARMCPRegInfo *ri, */ tlb_flush(env, 1); } - return vmsa_ttbcr_raw_write(env, ri, value); + vmsa_ttbcr_raw_write(env, ri, value); } static void vmsa_ttbcr_reset(CPUARMState *env, const ARMCPRegInfo *ri) @@ -1273,40 +1216,36 @@ static const ARMCPRegInfo vmsa_cp_reginfo[] = { REGINFO_SENTINEL }; -static int omap_ticonfig_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void omap_ticonfig_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c15_ticonfig = value & 0xe7; /* The OS_TYPE bit in this register changes the reported CPUID! */ env->cp15.c0_cpuid = (value & (1 << 5)) ? ARM_CPUID_TI915T : ARM_CPUID_TI925T; - return 0; } -static int omap_threadid_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void omap_threadid_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c15_threadid = value & 0xffff; - return 0; } -static int omap_wfi_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void omap_wfi_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Wait-for-interrupt (deprecated) */ cpu_interrupt(CPU(arm_env_get_cpu(env)), CPU_INTERRUPT_HALT); - return 0; } -static int omap_cachemaint_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void omap_cachemaint_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* On OMAP there are registers indicating the max/min index of dcache lines * containing a dirty line; cache flush operations have to reset these. */ env->cp15.c15_i_max = 0x000; env->cp15.c15_i_min = 0xff0; - return 0; } static const ARMCPRegInfo omap_cp_reginfo[] = { @@ -1348,8 +1287,8 @@ static const ARMCPRegInfo omap_cp_reginfo[] = { REGINFO_SENTINEL }; -static int xscale_cpar_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void xscale_cpar_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { value &= 0x3fff; if (env->cp15.c15_cpar != value) { @@ -1357,7 +1296,6 @@ static int xscale_cpar_write(CPUARMState *env, const ARMCPRegInfo *ri, tb_flush(env); env->cp15.c15_cpar = value; } - return 0; } static const ARMCPRegInfo xscale_cp_reginfo[] = { @@ -1437,8 +1375,7 @@ static const ARMCPRegInfo strongarm_cp_reginfo[] = { REGINFO_SENTINEL }; -static int mpidr_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t mpidr_read(CPUARMState *env, const ARMCPRegInfo *ri) { CPUState *cs = CPU(arm_env_get_cpu(env)); uint32_t mpidr = cs->cpu_index; @@ -1453,8 +1390,7 @@ static int mpidr_read(CPUARMState *env, const ARMCPRegInfo *ri, * not currently model any of those cores. */ } - *value = mpidr; - return 0; + return mpidr; } static const ARMCPRegInfo mpidr_cp_reginfo[] = { @@ -1463,17 +1399,16 @@ static const ARMCPRegInfo mpidr_cp_reginfo[] = { REGINFO_SENTINEL }; -static int par64_read(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t *value) +static uint64_t par64_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = ((uint64_t)env->cp15.c7_par_hi << 32) | env->cp15.c7_par; - return 0; + return ((uint64_t)env->cp15.c7_par_hi << 32) | env->cp15.c7_par; } -static int par64_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void par64_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c7_par_hi = value >> 32; env->cp15.c7_par = value; - return 0; } static void par64_reset(CPUARMState *env, const ARMCPRegInfo *ri) @@ -1482,27 +1417,24 @@ static void par64_reset(CPUARMState *env, const ARMCPRegInfo *ri) env->cp15.c7_par = 0; } -static int ttbr064_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t ttbr064_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = ((uint64_t)env->cp15.c2_base0_hi << 32) | env->cp15.c2_base0; - return 0; + return ((uint64_t)env->cp15.c2_base0_hi << 32) | env->cp15.c2_base0; } -static int ttbr064_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void ttbr064_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c2_base0_hi = value >> 32; env->cp15.c2_base0 = value; - return 0; } -static int ttbr064_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void ttbr064_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Writes to the 64 bit format TTBRs may change the ASID */ tlb_flush(env, 1); - return ttbr064_raw_write(env, ri, value); + ttbr064_raw_write(env, ri, value); } static void ttbr064_reset(CPUARMState *env, const ARMCPRegInfo *ri) @@ -1511,19 +1443,16 @@ static void ttbr064_reset(CPUARMState *env, const ARMCPRegInfo *ri) env->cp15.c2_base0 = 0; } -static int ttbr164_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t ttbr164_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = ((uint64_t)env->cp15.c2_base1_hi << 32) | env->cp15.c2_base1; - return 0; + return ((uint64_t)env->cp15.c2_base1_hi << 32) | env->cp15.c2_base1; } -static int ttbr164_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void ttbr164_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c2_base1_hi = value >> 32; env->cp15.c2_base1 = value; - return 0; } static void ttbr164_reset(CPUARMState *env, const ARMCPRegInfo *ri) @@ -1560,32 +1489,26 @@ static const ARMCPRegInfo lpae_cp_reginfo[] = { REGINFO_SENTINEL }; -static int aa64_fpcr_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t aa64_fpcr_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = vfp_get_fpcr(env); - return 0; + return vfp_get_fpcr(env); } -static int aa64_fpcr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void aa64_fpcr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { vfp_set_fpcr(env, value); - return 0; } -static int aa64_fpsr_read(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t *value) +static uint64_t aa64_fpsr_read(CPUARMState *env, const ARMCPRegInfo *ri) { - *value = vfp_get_fpsr(env); - return 0; + return vfp_get_fpsr(env); } -static int aa64_fpsr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void aa64_fpsr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { vfp_set_fpsr(env, value); - return 0; } static const ARMCPRegInfo v8_cp_reginfo[] = { @@ -1618,13 +1541,13 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { REGINFO_SENTINEL }; -static int sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { env->cp15.c1_sys = value; /* ??? Lots of these bits are not implemented. */ /* This may enable/disable the MMU, so do a TLB flush. */ tlb_flush(env, 1); - return 0; } void register_cp_regs_for_features(ARMCPU *cpu) @@ -1707,8 +1630,8 @@ void register_cp_regs_for_features(ARMCPU *cpu) .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, .access = PL0_RW, .resetvalue = cpu->midr & 0xff000000, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr), - .readfn = pmreg_read, .writefn = pmcr_write, - .raw_readfn = raw_read, .raw_writefn = raw_write, + .accessfn = pmreg_access, .writefn = pmcr_write, + .raw_writefn = raw_write, }; ARMCPRegInfo clidr = { .name = "CLIDR", .cp = 15, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 1, @@ -2202,17 +2125,15 @@ const ARMCPRegInfo *get_arm_cp_reginfo(GHashTable *cpregs, uint32_t encoded_cp) return g_hash_table_lookup(cpregs, &encoded_cp); } -int arm_cp_write_ignore(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void arm_cp_write_ignore(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { /* Helper coprocessor write function for write-ignore registers */ - return 0; } -int arm_cp_read_zero(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t *value) +uint64_t arm_cp_read_zero(CPUARMState *env, const ARMCPRegInfo *ri) { /* Helper coprocessor write function for read-as-zero registers */ - *value = 0; return 0; } @@ -2718,7 +2639,7 @@ void arm_cpu_do_interrupt(CPUState *cs) return; /* Never happens. Keep compiler happy. */ } /* High vectors. */ - if (env->cp15.c1_sys & (1 << 13)) { + if (env->cp15.c1_sys & SCTLR_V) { /* when enabled, base address cannot be remapped. */ addr += 0xffff0000; } else { @@ -2741,7 +2662,7 @@ void arm_cpu_do_interrupt(CPUState *cs) /* this is a lie, as the was no c1_sys on V4T/V5, but who cares * and we should just guard the thumb mode on V4 */ if (arm_feature(env, ARM_FEATURE_V4T)) { - env->thumb = (env->cp15.c1_sys & (1 << 30)) != 0; + env->thumb = (env->cp15.c1_sys & SCTLR_TE) != 0; } env->regs[14] = env->regs[15] + offset; env->regs[15] = addr; @@ -2767,12 +2688,15 @@ static inline int check_ap(CPUARMState *env, int ap, int domain_prot, switch (ap) { case 0: + if (arm_feature(env, ARM_FEATURE_V7)) { + return 0; + } if (access_type == 1) return 0; - switch ((env->cp15.c1_sys >> 8) & 3) { - case 1: + switch (env->cp15.c1_sys & (SCTLR_S | SCTLR_R)) { + case SCTLR_S: return is_user ? 0 : PAGE_READ; - case 2: + case SCTLR_R: return PAGE_READ; default: return 0; @@ -3003,7 +2927,7 @@ static int get_phys_addr_v6(CPUARMState *env, uint32_t address, int access_type, goto do_fault; /* The simplified model uses AP[0] as an access control bit. */ - if ((env->cp15.c1_sys & (1 << 29)) && (ap & 1) == 0) { + if ((env->cp15.c1_sys & SCTLR_AFE) && (ap & 1) == 0) { /* Access flag fault. */ code = (code == 15) ? 6 : 3; goto do_fault; @@ -3295,7 +3219,7 @@ static inline int get_phys_addr(CPUARMState *env, uint32_t address, if (address < 0x02000000) address += env->cp15.c13_fcse; - if ((env->cp15.c1_sys & 1) == 0) { + if ((env->cp15.c1_sys & SCTLR_M) == 0) { /* MMU/MPU disabled. */ *phys_ptr = address; *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; @@ -3308,7 +3232,7 @@ static inline int get_phys_addr(CPUARMState *env, uint32_t address, } else if (extended_addresses_enabled(env)) { return get_phys_addr_lpae(env, address, access_type, is_user, phys_ptr, prot, page_size); - } else if (env->cp15.c1_sys & (1 << 23)) { + } else if (env->cp15.c1_sys & SCTLR_XP) { return get_phys_addr_v6(env, address, access_type, is_user, phys_ptr, prot, page_size); } else { diff --git a/target-arm/helper.h b/target-arm/helper.h index 951e6ada07..19bd620532 100644 --- a/target-arm/helper.h +++ b/target-arm/helper.h @@ -57,6 +57,7 @@ DEF_HELPER_1(cpsr_read, i32, env) DEF_HELPER_3(v7m_msr, void, env, i32, i32) DEF_HELPER_2(v7m_mrs, i32, env, i32) +DEF_HELPER_2(access_check_cp_reg, void, env, ptr) DEF_HELPER_3(set_cp_reg, void, env, ptr, i32) DEF_HELPER_2(get_cp_reg, i32, env, ptr) DEF_HELPER_3(set_cp_reg64, void, env, ptr, i64) @@ -382,6 +383,8 @@ DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr) DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr) DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr) DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_acge_f64, i64, i64, i64, ptr) +DEF_HELPER_3(neon_acgt_f64, i64, i64, i64, ptr) /* iwmmxt_helper.c */ DEF_HELPER_2(iwmmxt_maddsq, i64, i64, i64) diff --git a/target-arm/kvm-consts.h b/target-arm/kvm-consts.h index 0e7f889cba..6009a33f10 100644 --- a/target-arm/kvm-consts.h +++ b/target-arm/kvm-consts.h @@ -50,15 +50,29 @@ MISMATCH_CHECK(PSCI_FN_CPU_OFF, KVM_PSCI_FN_CPU_OFF) MISMATCH_CHECK(PSCI_FN_CPU_ON, KVM_PSCI_FN_CPU_ON) MISMATCH_CHECK(PSCI_FN_MIGRATE, KVM_PSCI_FN_MIGRATE) +/* Note that KVM uses overlapping values for AArch32 and AArch64 + * target CPU numbers. AArch32 targets: + */ #define QEMU_KVM_ARM_TARGET_CORTEX_A15 0 +#define QEMU_KVM_ARM_TARGET_CORTEX_A7 1 + +/* AArch64 targets: */ +#define QEMU_KVM_ARM_TARGET_AEM_V8 0 +#define QEMU_KVM_ARM_TARGET_FOUNDATION_V8 1 +#define QEMU_KVM_ARM_TARGET_CORTEX_A57 2 /* There's no kernel define for this: sentinel value which * matches no KVM target value for either 64 or 32 bit */ #define QEMU_KVM_ARM_TARGET_NONE UINT_MAX -#ifndef TARGET_AARCH64 +#ifdef TARGET_AARCH64 +MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_AEM_V8, KVM_ARM_TARGET_AEM_V8) +MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_FOUNDATION_V8, KVM_ARM_TARGET_FOUNDATION_V8) +MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A57, KVM_ARM_TARGET_CORTEX_A57) +#else MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A15, KVM_ARM_TARGET_CORTEX_A15) +MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A7, KVM_ARM_TARGET_CORTEX_A7) #endif #define CP_REG_ARM64 0x6000000000000000ULL diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c index b4c86904f4..13752baf63 100644 --- a/target-arm/neon_helper.c +++ b/target-arm/neon_helper.c @@ -1823,6 +1823,22 @@ uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, void *fpstp) return -float32_lt(f1, f0, fpst); } +uint64_t HELPER(neon_acge_f64)(uint64_t a, uint64_t b, void *fpstp) +{ + float_status *fpst = fpstp; + float64 f0 = float64_abs(make_float64(a)); + float64 f1 = float64_abs(make_float64(b)); + return -float64_le(f1, f0, fpst); +} + +uint64_t HELPER(neon_acgt_f64)(uint64_t a, uint64_t b, void *fpstp) +{ + float_status *fpst = fpstp; + float64 f0 = float64_abs(make_float64(a)); + float64 f1 = float64_abs(make_float64(b)); + return -float64_lt(f1, f0, fpst); +} + #define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1)) void HELPER(neon_qunzip8)(CPUARMState *env, uint32_t rd, uint32_t rm) diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c index a918e5b27a..eb0fccd98f 100644 --- a/target-arm/op_helper.c +++ b/target-arm/op_helper.c @@ -273,44 +273,50 @@ void HELPER(set_user_reg)(CPUARMState *env, uint32_t regno, uint32_t val) } } +void HELPER(access_check_cp_reg)(CPUARMState *env, void *rip) +{ + const ARMCPRegInfo *ri = rip; + switch (ri->accessfn(env, ri)) { + case CP_ACCESS_OK: + return; + case CP_ACCESS_TRAP: + case CP_ACCESS_TRAP_UNCATEGORIZED: + /* These cases will eventually need to generate different + * syndrome information. + */ + break; + default: + g_assert_not_reached(); + } + raise_exception(env, EXCP_UDEF); +} + void HELPER(set_cp_reg)(CPUARMState *env, void *rip, uint32_t value) { const ARMCPRegInfo *ri = rip; - int excp = ri->writefn(env, ri, value); - if (excp) { - raise_exception(env, excp); - } + + ri->writefn(env, ri, value); } uint32_t HELPER(get_cp_reg)(CPUARMState *env, void *rip) { const ARMCPRegInfo *ri = rip; - uint64_t value; - int excp = ri->readfn(env, ri, &value); - if (excp) { - raise_exception(env, excp); - } - return value; + + return ri->readfn(env, ri); } void HELPER(set_cp_reg64)(CPUARMState *env, void *rip, uint64_t value) { const ARMCPRegInfo *ri = rip; - int excp = ri->writefn(env, ri, value); - if (excp) { - raise_exception(env, excp); - } + + ri->writefn(env, ri, value); } uint64_t HELPER(get_cp_reg64)(CPUARMState *env, void *rip) { const ARMCPRegInfo *ri = rip; - uint64_t value; - int excp = ri->readfn(env, ri, &value); - if (excp) { - raise_exception(env, excp); - } - return value; + + return ri->readfn(env, ri); } /* ??? Flag setting arithmetic is awkward because we need to do comparisons. diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c index d60223af8e..8752e7e16c 100644 --- a/target-arm/translate-a64.c +++ b/target-arm/translate-a64.c @@ -75,8 +75,12 @@ typedef struct AArch64DecodeTable { /* Function prototype for gen_ functions for calling Neon helpers */ typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); +typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); +typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); +typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); /* initialize TCG globals. */ void a64_translate_init(void) @@ -614,20 +618,26 @@ static void gen_adc_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1) */ /* - * Store from GPR register to memory + * Store from GPR register to memory. */ +static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source, + TCGv_i64 tcg_addr, int size, int memidx) +{ + g_assert(size <= 3); + tcg_gen_qemu_st_i64(source, tcg_addr, memidx, MO_TE + size); +} + static void do_gpr_st(DisasContext *s, TCGv_i64 source, TCGv_i64 tcg_addr, int size) { - g_assert(size <= 3); - tcg_gen_qemu_st_i64(source, tcg_addr, get_mem_index(s), MO_TE + size); + do_gpr_st_memidx(s, source, tcg_addr, size, get_mem_index(s)); } /* * Load from memory to GPR register */ -static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, - int size, bool is_signed, bool extend) +static void do_gpr_ld_memidx(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, + int size, bool is_signed, bool extend, int memidx) { TCGMemOp memop = MO_TE + size; @@ -637,7 +647,7 @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, memop += MO_SIGN; } - tcg_gen_qemu_ld_i64(dest, tcg_addr, get_mem_index(s), memop); + tcg_gen_qemu_ld_i64(dest, tcg_addr, memidx, memop); if (extend && is_signed) { g_assert(size < 3); @@ -645,6 +655,13 @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, } } +static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, + int size, bool is_signed, bool extend) +{ + do_gpr_ld_memidx(s, dest, tcg_addr, size, is_signed, extend, + get_mem_index(s)); +} + /* * Store from FP register to memory */ @@ -1175,7 +1192,12 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, crn, crm, op0, op1, op2)); if (!ri) { - /* Unknown register */ + /* Unknown register; this might be a guest error or a QEMU + * unimplemented feature. + */ + qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch64 " + "system register op0:%d op1:%d crn:%d crm:%d op2:%d\n", + isread ? "read" : "write", op0, op1, crn, crm, op2); unallocated_encoding(s); return; } @@ -1186,6 +1208,17 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, return; } + if (ri->accessfn) { + /* Emit code to perform further access permissions checks at + * runtime; this may result in an exception. + */ + TCGv_ptr tmpptr; + gen_a64_set_pc_im(s->pc - 4); + tmpptr = tcg_const_ptr(ri); + gen_helper_access_check_cp_reg(cpu_env, tmpptr); + tcg_temp_free_ptr(tmpptr); + } + /* Handle special cases first */ switch (ri->type & ~(ARM_CP_FLAG_MASK & ~ARM_CP_SPECIAL)) { case ARM_CP_NOP: @@ -1213,7 +1246,6 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, tcg_gen_movi_i64(tcg_rt, ri->resetvalue); } else if (ri->readfn) { TCGv_ptr tmpptr; - gen_a64_set_pc_im(s->pc - 4); tmpptr = tcg_const_ptr(ri); gen_helper_get_cp_reg64(tcg_rt, cpu_env, tmpptr); tcg_temp_free_ptr(tmpptr); @@ -1226,7 +1258,6 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, return; } else if (ri->writefn) { TCGv_ptr tmpptr; - gen_a64_set_pc_im(s->pc - 4); tmpptr = tcg_const_ptr(ri); gen_helper_set_cp_reg64(cpu_env, tmpptr, tcg_rt); tcg_temp_free_ptr(tmpptr); @@ -1471,12 +1502,68 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, } #else static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, - TCGv_i64 addr, int size, int is_pair) + TCGv_i64 inaddr, int size, int is_pair) { - qemu_log_mask(LOG_UNIMP, - "%s:%d: system mode store_exclusive unsupported " - "at pc=%016" PRIx64 "\n", - __FILE__, __LINE__, s->pc - 4); + /* if (env->exclusive_addr == addr && env->exclusive_val == [addr] + * && (!is_pair || env->exclusive_high == [addr + datasize])) { + * [addr] = {Rt}; + * if (is_pair) { + * [addr + datasize] = {Rt2}; + * } + * {Rd} = 0; + * } else { + * {Rd} = 1; + * } + * env->exclusive_addr = -1; + */ + int fail_label = gen_new_label(); + int done_label = gen_new_label(); + TCGv_i64 addr = tcg_temp_local_new_i64(); + TCGv_i64 tmp; + + /* Copy input into a local temp so it is not trashed when the + * basic block ends at the branch insn. + */ + tcg_gen_mov_i64(addr, inaddr); + tcg_gen_brcond_i64(TCG_COND_NE, addr, cpu_exclusive_addr, fail_label); + + tmp = tcg_temp_new_i64(); + tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), MO_TE + size); + tcg_gen_brcond_i64(TCG_COND_NE, tmp, cpu_exclusive_val, fail_label); + tcg_temp_free_i64(tmp); + + if (is_pair) { + TCGv_i64 addrhi = tcg_temp_new_i64(); + TCGv_i64 tmphi = tcg_temp_new_i64(); + + tcg_gen_addi_i64(addrhi, addr, 1 << size); + tcg_gen_qemu_ld_i64(tmphi, addrhi, get_mem_index(s), MO_TE + size); + tcg_gen_brcond_i64(TCG_COND_NE, tmphi, cpu_exclusive_high, fail_label); + + tcg_temp_free_i64(tmphi); + tcg_temp_free_i64(addrhi); + } + + /* We seem to still have the exclusive monitor, so do the store */ + tcg_gen_qemu_st_i64(cpu_reg(s, rt), addr, get_mem_index(s), MO_TE + size); + if (is_pair) { + TCGv_i64 addrhi = tcg_temp_new_i64(); + + tcg_gen_addi_i64(addrhi, addr, 1 << size); + tcg_gen_qemu_st_i64(cpu_reg(s, rt2), addrhi, + get_mem_index(s), MO_TE + size); + tcg_temp_free_i64(addrhi); + } + + tcg_temp_free_i64(addr); + + tcg_gen_movi_i64(cpu_reg(s, rd), 0); + tcg_gen_br(done_label); + gen_set_label(fail_label); + tcg_gen_movi_i64(cpu_reg(s, rd), 1); + gen_set_label(done_label); + tcg_gen_movi_i64(cpu_exclusive_addr, -1); + } #endif @@ -1750,6 +1837,7 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) * +----+-------+---+-----+-----+---+--------+-----+------+------+ * * idx = 01 -> post-indexed, 11 pre-indexed, 00 unscaled imm. (no writeback) + 10 -> unprivileged * V = 0 -> non-vector * size: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64bit * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32 @@ -1765,6 +1853,7 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) bool is_signed = false; bool is_store = false; bool is_extended = false; + bool is_unpriv = (idx == 2); bool is_vector = extract32(insn, 26, 1); bool post_index; bool writeback; @@ -1773,7 +1862,7 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) if (is_vector) { size |= (opc & 2) << 1; - if (size > 4) { + if (size > 4 || is_unpriv) { unallocated_encoding(s); return; } @@ -1781,6 +1870,10 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) } else { if (size == 3 && opc == 2) { /* PRFM - prefetch */ + if (is_unpriv) { + unallocated_encoding(s); + return; + } return; } if (opc == 3 && size > 1) { @@ -1794,6 +1887,7 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) switch (idx) { case 0: + case 2: post_index = false; writeback = false; break; @@ -1805,9 +1899,6 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) post_index = false; writeback = true; break; - case 2: - g_assert(false); - break; } if (rn == 31) { @@ -1827,10 +1918,13 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); + int memidx = is_unpriv ? 1 : get_mem_index(s); + if (is_store) { - do_gpr_st(s, tcg_rt, tcg_addr, size); + do_gpr_st_memidx(s, tcg_rt, tcg_addr, size, memidx); } else { - do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended); + do_gpr_ld_memidx(s, tcg_rt, tcg_addr, size, + is_signed, is_extended, memidx); } } @@ -2010,25 +2104,6 @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn) } } -/* Load/store register (immediate forms) */ -static void disas_ldst_reg_imm(DisasContext *s, uint32_t insn) -{ - switch (extract32(insn, 10, 2)) { - case 0: case 1: case 3: - /* Load/store register (unscaled immediate) */ - /* Load/store immediate pre/post-indexed */ - disas_ldst_reg_imm9(s, insn); - break; - case 2: - /* Load/store register unprivileged */ - unsupported_encoding(s, insn); - break; - default: - unallocated_encoding(s); - break; - } -} - /* Load/store register (all forms) */ static void disas_ldst_reg(DisasContext *s, uint32_t insn) { @@ -2037,7 +2112,11 @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) if (extract32(insn, 21, 1) == 1 && extract32(insn, 10, 2) == 2) { disas_ldst_reg_roffset(s, insn); } else { - disas_ldst_reg_imm(s, insn); + /* Load/store register (unscaled immediate) + * Load/store immediate pre/post-indexed + * Load/store register unprivileged + */ + disas_ldst_reg_imm9(s, insn); } break; case 1: @@ -5838,7 +5917,100 @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn) */ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) { - unsupported_encoding(s, insn); + bool is_u = extract32(insn, 29, 1); + int size = extract32(insn, 22, 2); + int opcode = extract32(insn, 12, 4); + int rm = extract32(insn, 16, 5); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + + if (is_u) { + unallocated_encoding(s); + return; + } + + switch (opcode) { + case 0x9: /* SQDMLAL, SQDMLAL2 */ + case 0xb: /* SQDMLSL, SQDMLSL2 */ + case 0xd: /* SQDMULL, SQDMULL2 */ + if (size == 0 || size == 3) { + unallocated_encoding(s); + return; + } + break; + default: + unallocated_encoding(s); + return; + } + + if (size == 2) { + TCGv_i64 tcg_op1 = tcg_temp_new_i64(); + TCGv_i64 tcg_op2 = tcg_temp_new_i64(); + TCGv_i64 tcg_res = tcg_temp_new_i64(); + + read_vec_element(s, tcg_op1, rn, 0, MO_32 | MO_SIGN); + read_vec_element(s, tcg_op2, rm, 0, MO_32 | MO_SIGN); + + tcg_gen_mul_i64(tcg_res, tcg_op1, tcg_op2); + gen_helper_neon_addl_saturate_s64(tcg_res, cpu_env, tcg_res, tcg_res); + + switch (opcode) { + case 0xd: /* SQDMULL, SQDMULL2 */ + break; + case 0xb: /* SQDMLSL, SQDMLSL2 */ + tcg_gen_neg_i64(tcg_res, tcg_res); + /* fall through */ + case 0x9: /* SQDMLAL, SQDMLAL2 */ + read_vec_element(s, tcg_op1, rd, 0, MO_64); + gen_helper_neon_addl_saturate_s64(tcg_res, cpu_env, + tcg_res, tcg_op1); + break; + default: + g_assert_not_reached(); + } + + write_fp_dreg(s, rd, tcg_res); + + tcg_temp_free_i64(tcg_op1); + tcg_temp_free_i64(tcg_op2); + tcg_temp_free_i64(tcg_res); + } else { + TCGv_i32 tcg_op1 = tcg_temp_new_i32(); + TCGv_i32 tcg_op2 = tcg_temp_new_i32(); + TCGv_i64 tcg_res = tcg_temp_new_i64(); + + read_vec_element_i32(s, tcg_op1, rn, 0, MO_16); + read_vec_element_i32(s, tcg_op2, rm, 0, MO_16); + + gen_helper_neon_mull_s16(tcg_res, tcg_op1, tcg_op2); + gen_helper_neon_addl_saturate_s32(tcg_res, cpu_env, tcg_res, tcg_res); + + switch (opcode) { + case 0xd: /* SQDMULL, SQDMULL2 */ + break; + case 0xb: /* SQDMLSL, SQDMLSL2 */ + gen_helper_neon_negl_u32(tcg_res, tcg_res); + /* fall through */ + case 0x9: /* SQDMLAL, SQDMLAL2 */ + { + TCGv_i64 tcg_op3 = tcg_temp_new_i64(); + read_vec_element(s, tcg_op3, rd, 0, MO_32); + gen_helper_neon_addl_saturate_s32(tcg_res, cpu_env, + tcg_res, tcg_op3); + tcg_temp_free_i64(tcg_op3); + break; + } + default: + g_assert_not_reached(); + } + + tcg_gen_ext32u_i64(tcg_res, tcg_res); + write_fp_dreg(s, rd, tcg_res); + + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + tcg_temp_free_i64(tcg_res); + } } static void handle_3same_64(DisasContext *s, int opcode, bool u, @@ -5950,15 +6122,33 @@ static void handle_3same_float(DisasContext *s, int size, int elements, read_vec_element(s, tcg_op2, rm, pass, MO_64); switch (fpopcode) { + case 0x39: /* FMLS */ + /* As usual for ARM, separate negation for fused multiply-add */ + gen_helper_vfp_negd(tcg_op1, tcg_op1); + /* fall through */ + case 0x19: /* FMLA */ + read_vec_element(s, tcg_res, rd, pass, MO_64); + gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, + tcg_res, fpst); + break; case 0x18: /* FMAXNM */ gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x1a: /* FADD */ gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x1b: /* FMULX */ + gen_helper_vfp_mulxd(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1c: /* FCMEQ */ + gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x1e: /* FMAX */ gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x1f: /* FRECPS */ + gen_helper_recpsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x38: /* FMINNM */ gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -5968,9 +6158,18 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x3e: /* FMIN */ gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x3f: /* FRSQRTS */ + gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x5b: /* FMUL */ gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x5c: /* FCMGE */ + gen_helper_neon_cge_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x5d: /* FACGE */ + gen_helper_neon_acge_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x5f: /* FDIV */ gen_helper_vfp_divd(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -5978,6 +6177,12 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_absd(tcg_res, tcg_res); break; + case 0x7c: /* FCMGT */ + gen_helper_neon_cgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x7d: /* FACGT */ + gen_helper_neon_acgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); + break; default: g_assert_not_reached(); } @@ -5997,12 +6202,30 @@ static void handle_3same_float(DisasContext *s, int size, int elements, read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); switch (fpopcode) { + case 0x39: /* FMLS */ + /* As usual for ARM, separate negation for fused multiply-add */ + gen_helper_vfp_negs(tcg_op1, tcg_op1); + /* fall through */ + case 0x19: /* FMLA */ + read_vec_element_i32(s, tcg_res, rd, pass, MO_32); + gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, + tcg_res, fpst); + break; case 0x1a: /* FADD */ gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x1b: /* FMULX */ + gen_helper_vfp_mulxs(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1c: /* FCMEQ */ + gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x1e: /* FMAX */ gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x1f: /* FRECPS */ + gen_helper_recpsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x18: /* FMAXNM */ gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -6015,9 +6238,18 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x3e: /* FMIN */ gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x3f: /* FRSQRTS */ + gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x5b: /* FMUL */ gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x5c: /* FCMGE */ + gen_helper_neon_cge_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x5d: /* FACGE */ + gen_helper_neon_acge_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x5f: /* FDIV */ gen_helper_vfp_divs(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -6025,6 +6257,12 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_abss(tcg_res, tcg_res); break; + case 0x7c: /* FCMGT */ + gen_helper_neon_cgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x7d: /* FACGT */ + gen_helper_neon_acgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); + break; default: g_assert_not_reached(); } @@ -6075,15 +6313,13 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) int fpopcode = opcode | (extract32(size, 1, 1) << 5) | (u << 6); switch (fpopcode) { case 0x1b: /* FMULX */ - case 0x1c: /* FCMEQ */ case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ - case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ - case 0x7c: /* FCMGT */ case 0x7d: /* FACGT */ - unsupported_encoding(s, insn); - return; + case 0x1c: /* FCMEQ */ + case 0x5c: /* FCMGE */ + case 0x7c: /* FCMGT */ case 0x7a: /* FABD */ break; default: @@ -6268,6 +6504,115 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, } } +static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, + bool is_scalar, bool is_u, bool is_q, + int size, int rn, int rd) +{ + bool is_double = (size == 3); + TCGv_ptr fpst = get_fpstatus_ptr(); + + if (is_double) { + TCGv_i64 tcg_op = tcg_temp_new_i64(); + TCGv_i64 tcg_zero = tcg_const_i64(0); + TCGv_i64 tcg_res = tcg_temp_new_i64(); + NeonGenTwoDoubleOPFn *genfn; + bool swap = false; + int pass; + + switch (opcode) { + case 0x2e: /* FCMLT (zero) */ + swap = true; + /* fallthrough */ + case 0x2c: /* FCMGT (zero) */ + genfn = gen_helper_neon_cgt_f64; + break; + case 0x2d: /* FCMEQ (zero) */ + genfn = gen_helper_neon_ceq_f64; + break; + case 0x6d: /* FCMLE (zero) */ + swap = true; + /* fall through */ + case 0x6c: /* FCMGE (zero) */ + genfn = gen_helper_neon_cge_f64; + break; + default: + g_assert_not_reached(); + } + + for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { + read_vec_element(s, tcg_op, rn, pass, MO_64); + if (swap) { + genfn(tcg_res, tcg_zero, tcg_op, fpst); + } else { + genfn(tcg_res, tcg_op, tcg_zero, fpst); + } + write_vec_element(s, tcg_res, rd, pass, MO_64); + } + if (is_scalar) { + clear_vec_high(s, rd); + } + + tcg_temp_free_i64(tcg_res); + tcg_temp_free_i64(tcg_zero); + tcg_temp_free_i64(tcg_op); + } else { + TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_zero = tcg_const_i32(0); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + NeonGenTwoSingleOPFn *genfn; + bool swap = false; + int pass, maxpasses; + + switch (opcode) { + case 0x2e: /* FCMLT (zero) */ + swap = true; + /* fall through */ + case 0x2c: /* FCMGT (zero) */ + genfn = gen_helper_neon_cgt_f32; + break; + case 0x2d: /* FCMEQ (zero) */ + genfn = gen_helper_neon_ceq_f32; + break; + case 0x6d: /* FCMLE (zero) */ + swap = true; + /* fall through */ + case 0x6c: /* FCMGE (zero) */ + genfn = gen_helper_neon_cge_f32; + break; + default: + g_assert_not_reached(); + } + + if (is_scalar) { + maxpasses = 1; + } else { + maxpasses = is_q ? 4 : 2; + } + + for (pass = 0; pass < maxpasses; pass++) { + read_vec_element_i32(s, tcg_op, rn, pass, MO_32); + if (swap) { + genfn(tcg_res, tcg_zero, tcg_op, fpst); + } else { + genfn(tcg_res, tcg_op, tcg_zero, fpst); + } + if (is_scalar) { + write_fp_sreg(s, rd, tcg_res); + } else { + write_vec_element_i32(s, tcg_res, rd, pass, MO_32); + } + } + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_zero); + tcg_temp_free_i32(tcg_op); + if (!is_q && !is_scalar) { + clear_vec_high(s, rd); + } + } + + tcg_temp_free_ptr(fpst); +} + /* C3.6.12 AdvSIMD scalar two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ @@ -6297,9 +6642,47 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; + case 0xc ... 0xf: + case 0x16 ... 0x1d: + case 0x1f: + /* Floating point: U, size[1] and opcode indicate operation; + * size[0] indicates single or double precision. + */ + opcode |= (extract32(size, 1, 1) << 5) | (u << 6); + size = extract32(size, 0, 1) ? 3 : 2; + switch (opcode) { + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ + handle_2misc_fcmp_zero(s, opcode, true, u, true, size, rn, rd); + return; + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x1d: /* SCVTF */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + case 0x3d: /* FRECPE */ + case 0x3f: /* FRECPX */ + case 0x56: /* FCVTXN, FCVTXN2 */ + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x5c: /* FCVTAU */ + case 0x5d: /* UCVTF */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ + case 0x7d: /* FRSQRTE */ + unsupported_encoding(s, insn); + return; + default: + unallocated_encoding(s); + return; + } + break; default: /* Other categories of encoding in this class: - * + floating point (single and double) * + SUQADD/USQADD/SQABS/SQNEG : size 8, 16, 32 or 64 * + SQXTN/SQXTN2/SQXTUN/SQXTUN2/UQXTN/UQXTN2: * narrowing saturate ops: size 64/32/16 -> 32/16/8 @@ -6322,17 +6705,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } } -/* C3.6.13 AdvSIMD scalar x indexed element - * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0 - * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ - * | 0 1 | U | 1 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd | - * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ - */ -static void disas_simd_scalar_indexed(DisasContext *s, uint32_t insn) -{ - unsupported_encoding(s, insn); -} - /* SSHR[RA]/USHR[RA] - Vector shift right (optional rounding/accumulate) */ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, int immh, int immb, int opcode, int rn, int rd) @@ -6514,6 +6886,24 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn) } } +/* Generate code to do a "long" addition or subtraction, ie one done in + * TCGv_i64 on vector lanes twice the width specified by size. + */ +static void gen_neon_addl(int size, bool is_sub, TCGv_i64 tcg_res, + TCGv_i64 tcg_op1, TCGv_i64 tcg_op2) +{ + static NeonGenTwo64OpFn * const fns[3][2] = { + { gen_helper_neon_addl_u16, gen_helper_neon_subl_u16 }, + { gen_helper_neon_addl_u32, gen_helper_neon_subl_u32 }, + { tcg_gen_add_i64, tcg_gen_sub_i64 }, + }; + NeonGenTwo64OpFn *genfn; + assert(size < 3); + + genfn = fns[size][is_sub]; + genfn(tcg_res, tcg_op1, tcg_op2); +} + static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, int opcode, int rd, int rn, int rm) { @@ -6569,6 +6959,12 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, } switch (opcode) { + case 0: /* SADDL, SADDL2, UADDL, UADDL2 */ + tcg_gen_add_i64(tcg_passres, tcg_op1, tcg_op2); + break; + case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */ + tcg_gen_sub_i64(tcg_passres, tcg_op1, tcg_op2); + break; case 5: /* SABAL, SABAL2, UABAL, UABAL2 */ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */ { @@ -6589,15 +6985,31 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, case 12: /* UMULL, UMULL2, SMULL, SMULL2 */ tcg_gen_mul_i64(tcg_passres, tcg_op1, tcg_op2); break; + case 9: /* SQDMLAL, SQDMLAL2 */ + case 11: /* SQDMLSL, SQDMLSL2 */ + case 13: /* SQDMULL, SQDMULL2 */ + tcg_gen_mul_i64(tcg_passres, tcg_op1, tcg_op2); + gen_helper_neon_addl_saturate_s64(tcg_passres, cpu_env, + tcg_passres, tcg_passres); + break; default: g_assert_not_reached(); } - if (accop > 0) { + if (opcode == 9 || opcode == 11) { + /* saturating accumulate ops */ + if (accop < 0) { + tcg_gen_neg_i64(tcg_passres, tcg_passres); + } + gen_helper_neon_addl_saturate_s64(tcg_res[pass], cpu_env, + tcg_res[pass], tcg_passres); + } else if (accop > 0) { tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_passres); - tcg_temp_free_i64(tcg_passres); } else if (accop < 0) { tcg_gen_sub_i64(tcg_res[pass], tcg_res[pass], tcg_passres); + } + + if (accop != 0) { tcg_temp_free_i64(tcg_passres); } @@ -6622,6 +7034,23 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, } switch (opcode) { + case 0: /* SADDL, SADDL2, UADDL, UADDL2 */ + case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */ + { + TCGv_i64 tcg_op2_64 = tcg_temp_new_i64(); + static NeonGenWidenFn * const widenfns[2][2] = { + { gen_helper_neon_widen_s8, gen_helper_neon_widen_u8 }, + { gen_helper_neon_widen_s16, gen_helper_neon_widen_u16 }, + }; + NeonGenWidenFn *widenfn = widenfns[size][is_u]; + + widenfn(tcg_op2_64, tcg_op2); + widenfn(tcg_passres, tcg_op1); + gen_neon_addl(size, (opcode == 2), tcg_passres, + tcg_passres, tcg_op2_64); + tcg_temp_free_i64(tcg_op2_64); + break; + } case 5: /* SABAL, SABAL2, UABAL, UABAL2 */ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */ if (size == 0) { @@ -6655,28 +7084,32 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, } } break; + case 9: /* SQDMLAL, SQDMLAL2 */ + case 11: /* SQDMLSL, SQDMLSL2 */ + case 13: /* SQDMULL, SQDMULL2 */ + assert(size == 1); + gen_helper_neon_mull_s16(tcg_passres, tcg_op1, tcg_op2); + gen_helper_neon_addl_saturate_s32(tcg_passres, cpu_env, + tcg_passres, tcg_passres); + break; default: g_assert_not_reached(); } tcg_temp_free_i32(tcg_op1); tcg_temp_free_i32(tcg_op2); - if (accop > 0) { - if (size == 0) { - gen_helper_neon_addl_u16(tcg_res[pass], tcg_res[pass], - tcg_passres); + if (accop != 0) { + if (opcode == 9 || opcode == 11) { + /* saturating accumulate ops */ + if (accop < 0) { + gen_helper_neon_negl_u32(tcg_passres, tcg_passres); + } + gen_helper_neon_addl_saturate_s32(tcg_res[pass], cpu_env, + tcg_res[pass], + tcg_passres); } else { - gen_helper_neon_addl_u32(tcg_res[pass], tcg_res[pass], - tcg_passres); - } - tcg_temp_free_i64(tcg_passres); - } else if (accop < 0) { - if (size == 0) { - gen_helper_neon_subl_u16(tcg_res[pass], tcg_res[pass], - tcg_passres); - } else { - gen_helper_neon_subl_u32(tcg_res[pass], tcg_res[pass], - tcg_passres); + gen_neon_addl(size, (accop < 0), tcg_res[pass], + tcg_res[pass], tcg_passres); } tcg_temp_free_i64(tcg_passres); } @@ -6689,6 +7122,95 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, tcg_temp_free_i64(tcg_res[1]); } +static void handle_3rd_wide(DisasContext *s, int is_q, int is_u, int size, + int opcode, int rd, int rn, int rm) +{ + TCGv_i64 tcg_res[2]; + int part = is_q ? 2 : 0; + int pass; + + for (pass = 0; pass < 2; pass++) { + TCGv_i64 tcg_op1 = tcg_temp_new_i64(); + TCGv_i32 tcg_op2 = tcg_temp_new_i32(); + TCGv_i64 tcg_op2_wide = tcg_temp_new_i64(); + static NeonGenWidenFn * const widenfns[3][2] = { + { gen_helper_neon_widen_s8, gen_helper_neon_widen_u8 }, + { gen_helper_neon_widen_s16, gen_helper_neon_widen_u16 }, + { tcg_gen_ext_i32_i64, tcg_gen_extu_i32_i64 }, + }; + NeonGenWidenFn *widenfn = widenfns[size][is_u]; + + read_vec_element(s, tcg_op1, rn, pass, MO_64); + read_vec_element_i32(s, tcg_op2, rm, part + pass, MO_32); + widenfn(tcg_op2_wide, tcg_op2); + tcg_temp_free_i32(tcg_op2); + tcg_res[pass] = tcg_temp_new_i64(); + gen_neon_addl(size, (opcode == 3), + tcg_res[pass], tcg_op1, tcg_op2_wide); + tcg_temp_free_i64(tcg_op1); + tcg_temp_free_i64(tcg_op2_wide); + } + + for (pass = 0; pass < 2; pass++) { + write_vec_element(s, tcg_res[pass], rd, pass, MO_64); + tcg_temp_free_i64(tcg_res[pass]); + } +} + +static void do_narrow_high_u32(TCGv_i32 res, TCGv_i64 in) +{ + tcg_gen_shri_i64(in, in, 32); + tcg_gen_trunc_i64_i32(res, in); +} + +static void do_narrow_round_high_u32(TCGv_i32 res, TCGv_i64 in) +{ + tcg_gen_addi_i64(in, in, 1U << 31); + do_narrow_high_u32(res, in); +} + +static void handle_3rd_narrowing(DisasContext *s, int is_q, int is_u, int size, + int opcode, int rd, int rn, int rm) +{ + TCGv_i32 tcg_res[2]; + int part = is_q ? 2 : 0; + int pass; + + for (pass = 0; pass < 2; pass++) { + TCGv_i64 tcg_op1 = tcg_temp_new_i64(); + TCGv_i64 tcg_op2 = tcg_temp_new_i64(); + TCGv_i64 tcg_wideres = tcg_temp_new_i64(); + static NeonGenNarrowFn * const narrowfns[3][2] = { + { gen_helper_neon_narrow_high_u8, + gen_helper_neon_narrow_round_high_u8 }, + { gen_helper_neon_narrow_high_u16, + gen_helper_neon_narrow_round_high_u16 }, + { do_narrow_high_u32, do_narrow_round_high_u32 }, + }; + NeonGenNarrowFn *gennarrow = narrowfns[size][is_u]; + + read_vec_element(s, tcg_op1, rn, pass, MO_64); + read_vec_element(s, tcg_op2, rm, pass, MO_64); + + gen_neon_addl(size, (opcode == 6), tcg_wideres, tcg_op1, tcg_op2); + + tcg_temp_free_i64(tcg_op1); + tcg_temp_free_i64(tcg_op2); + + tcg_res[pass] = tcg_temp_new_i32(); + gennarrow(tcg_res[pass], tcg_wideres); + tcg_temp_free_i64(tcg_wideres); + } + + for (pass = 0; pass < 2; pass++) { + write_vec_element_i32(s, tcg_res[pass], rd, pass + part, MO_32); + tcg_temp_free_i32(tcg_res[pass]); + } + if (!is_q) { + clear_vec_high(s, rd); + } +} + /* C3.6.15 AdvSIMD three different * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+--------+-----+------+------+ @@ -6719,31 +7241,43 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) case 1: /* SADDW, SADDW2, UADDW, UADDW2 */ case 3: /* SSUBW, SSUBW2, USUBW, USUBW2 */ /* 64 x 128 -> 128 */ - unsupported_encoding(s, insn); + if (size == 3) { + unallocated_encoding(s); + return; + } + handle_3rd_wide(s, is_q, is_u, size, opcode, rd, rn, rm); break; case 4: /* ADDHN, ADDHN2, RADDHN, RADDHN2 */ case 6: /* SUBHN, SUBHN2, RSUBHN, RSUBHN2 */ /* 128 x 128 -> 64 */ + if (size == 3) { + unallocated_encoding(s); + return; + } + handle_3rd_narrowing(s, is_q, is_u, size, opcode, rd, rn, rm); + break; + case 14: /* PMULL, PMULL2 */ + if (is_u || size == 1 || size == 2) { + unallocated_encoding(s); + return; + } unsupported_encoding(s, insn); break; - case 9: - case 11: - case 13: - case 14: - if (is_u) { + case 9: /* SQDMLAL, SQDMLAL2 */ + case 11: /* SQDMLSL, SQDMLSL2 */ + case 13: /* SQDMULL, SQDMULL2 */ + if (is_u || size == 0) { unallocated_encoding(s); return; } /* fall through */ - case 0: - case 2: - unsupported_encoding(s, insn); - break; - case 5: - case 7: - case 8: - case 10: - case 12: + case 0: /* SADDL, SADDL2, UADDL, UADDL2 */ + case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */ + case 5: /* SABAL, SABAL2, UABAL, UABAL2 */ + case 7: /* SABDL, SABDL2, UABDL, UABDL2 */ + case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */ + case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */ + case 12: /* SMULL, SMULL2, UMULL, UMULL2 */ /* 64 x 64 -> 128 */ if (size == 3) { unallocated_encoding(s); @@ -6856,39 +7390,22 @@ static void gen_min_u32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2) tcg_gen_movcond_i32(TCG_COND_LEU, res, op1, op2, op1, op2); } -/* Pairwise op subgroup of C3.6.16. */ -static void disas_simd_3same_pair(DisasContext *s, uint32_t insn) +/* Pairwise op subgroup of C3.6.16. + * + * This is called directly or via the handle_3same_float for float pairwise + * operations where the opcode and size are calculated differently. + */ +static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, + int size, int rn, int rm, int rd) { - int is_q = extract32(insn, 30, 1); - int u = extract32(insn, 29, 1); - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 11, 5); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); + TCGv_ptr fpst; int pass; - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 0x14: /* SMAXP, UMAXP */ - case 0x15: /* SMINP, UMINP */ - if (size == 3) { - unallocated_encoding(s); - return; - } - break; - case 0x17: - if (u) { - unallocated_encoding(s); - return; - } - break; - default: - g_assert_not_reached(); + /* Floating point operations need fpst */ + if (opcode >= 0x58) { + fpst = get_fpstatus_ptr(); + } else { + TCGV_UNUSED_PTR(fpst); } /* These operations work on the concatenated rm:rn, with each pair of @@ -6906,9 +7423,28 @@ static void disas_simd_3same_pair(DisasContext *s, uint32_t insn) read_vec_element(s, tcg_op2, passreg, 1, MO_64); tcg_res[pass] = tcg_temp_new_i64(); - /* The only 64 bit pairwise integer op is ADDP */ - assert(opcode == 0x17); - tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2); + switch (opcode) { + case 0x17: /* ADDP */ + tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2); + break; + case 0x58: /* FMAXNMP */ + gen_helper_vfp_maxnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x5a: /* FADDP */ + gen_helper_vfp_addd(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x5e: /* FMAXP */ + gen_helper_vfp_maxd(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x78: /* FMINNMP */ + gen_helper_vfp_minnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x7e: /* FMINP */ + gen_helper_vfp_mind(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + default: + g_assert_not_reached(); + } tcg_temp_free_i64(tcg_op1); tcg_temp_free_i64(tcg_op2); @@ -6925,7 +7461,7 @@ static void disas_simd_3same_pair(DisasContext *s, uint32_t insn) for (pass = 0; pass < maxpass; pass++) { TCGv_i32 tcg_op1 = tcg_temp_new_i32(); TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - NeonGenTwoOpFn *genfn; + NeonGenTwoOpFn *genfn = NULL; int passreg = pass < (maxpass / 2) ? rn : rm; int passelt = (is_q && (pass & 1)) ? 2 : 0; @@ -6964,11 +7500,30 @@ static void disas_simd_3same_pair(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } + /* The FP operations are all on single floats (32 bit) */ + case 0x58: /* FMAXNMP */ + gen_helper_vfp_maxnums(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x5a: /* FADDP */ + gen_helper_vfp_adds(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x5e: /* FMAXP */ + gen_helper_vfp_maxs(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x78: /* FMINNMP */ + gen_helper_vfp_minnums(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x7e: /* FMINP */ + gen_helper_vfp_mins(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; default: g_assert_not_reached(); } - genfn(tcg_res[pass], tcg_op1, tcg_op2); + /* FP ops called directly, otherwise call now */ + if (genfn) { + genfn(tcg_res[pass], tcg_op1, tcg_op2); + } tcg_temp_free_i32(tcg_op1); tcg_temp_free_i32(tcg_op2); @@ -6982,6 +7537,10 @@ static void disas_simd_3same_pair(DisasContext *s, uint32_t insn) clear_vec_high(s, rd); } } + + if (!TCGV_IS_UNUSED_PTR(fpst)) { + tcg_temp_free_ptr(fpst); + } } /* Floating point op subgroup of C3.6.16. */ @@ -7015,30 +7574,32 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x5e: /* FMAXP */ case 0x78: /* FMINNMP */ case 0x7e: /* FMINP */ - /* pairwise ops */ - unsupported_encoding(s, insn); + if (size && !is_q) { + unallocated_encoding(s); + return; + } + handle_simd_3same_pair(s, is_q, 0, fpopcode, size ? MO_64 : MO_32, + rn, rm, rd); return; case 0x1b: /* FMULX */ - case 0x1c: /* FCMEQ */ case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ - case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ - case 0x7c: /* FCMGT */ case 0x7d: /* FACGT */ case 0x19: /* FMLA */ case 0x39: /* FMLS */ - unsupported_encoding(s, insn); - return; case 0x18: /* FMAXNM */ case 0x1a: /* FADD */ + case 0x1c: /* FCMEQ */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ + case 0x5c: /* FCMGE */ case 0x5f: /* FDIV */ case 0x7a: /* FABD */ + case 0x7c: /* FCMGT */ handle_3same_float(s, size, elements, fpopcode, rd, rn, rm); return; default: @@ -7366,9 +7927,28 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) case 0x17: /* ADDP */ case 0x14: /* SMAXP, UMAXP */ case 0x15: /* SMINP, UMINP */ + { /* Pairwise operations */ - disas_simd_3same_pair(s, insn); + int is_q = extract32(insn, 30, 1); + int u = extract32(insn, 29, 1); + int size = extract32(insn, 22, 2); + int rm = extract32(insn, 16, 5); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + if (opcode == 0x17) { + if (u || (size == 3 && !is_q)) { + unallocated_encoding(s); + return; + } + } else { + if (size == 3) { + unallocated_encoding(s); + return; + } + } + handle_simd_3same_pair(s, is_q, u, opcode, size, rn, rm, rd); break; + } case 0x18 ... 0x31: /* floating point ops, sz[1] and U are part of opcode */ disas_simd_3same_float(s, insn); @@ -7618,6 +8198,17 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ + if (size == 3 && !is_q) { + unallocated_encoding(s); + return; + } + handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd); + return; case 0x16: /* FCVTN, FCVTN2 */ case 0x17: /* FCVTL, FCVTL2 */ case 0x18: /* FRINTN */ @@ -7626,9 +8217,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x1b: /* FCVTMS */ case 0x1c: /* FCVTAS */ case 0x1d: /* SCVTF */ - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ case 0x38: /* FRINTP */ case 0x39: /* FRINTZ */ case 0x3a: /* FCVTPS */ @@ -7642,8 +8230,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x5b: /* FCVTMU */ case 0x5c: /* FCVTAU */ case 0x5d: /* UCVTF */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ case 0x79: /* FRINTI */ case 0x7a: /* FCVTPU */ case 0x7b: /* FCVTZU */ @@ -7805,15 +8391,455 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } } -/* C3.6.18 AdvSIMD vector x indexed element +/* C3.6.13 AdvSIMD scalar x indexed element + * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0 + * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ + * | 0 1 | U | 1 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd | + * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ + * C3.6.18 AdvSIMD vector x indexed element * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+ * | 0 | Q | U | 0 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd | * +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+ */ -static void disas_simd_indexed_vector(DisasContext *s, uint32_t insn) +static void disas_simd_indexed(DisasContext *s, uint32_t insn) { - unsupported_encoding(s, insn); + /* This encoding has two kinds of instruction: + * normal, where we perform elt x idxelt => elt for each + * element in the vector + * long, where we perform elt x idxelt and generate a result of + * double the width of the input element + * The long ops have a 'part' specifier (ie come in INSN, INSN2 pairs). + */ + bool is_scalar = extract32(insn, 28, 1); + bool is_q = extract32(insn, 30, 1); + bool u = extract32(insn, 29, 1); + int size = extract32(insn, 22, 2); + int l = extract32(insn, 21, 1); + int m = extract32(insn, 20, 1); + /* Note that the Rm field here is only 4 bits, not 5 as it usually is */ + int rm = extract32(insn, 16, 4); + int opcode = extract32(insn, 12, 4); + int h = extract32(insn, 11, 1); + int rn = extract32(insn, 5, 5); + int rd = extract32(insn, 0, 5); + bool is_long = false; + bool is_fp = false; + int index; + TCGv_ptr fpst; + + switch (opcode) { + case 0x0: /* MLA */ + case 0x4: /* MLS */ + if (!u || is_scalar) { + unallocated_encoding(s); + return; + } + break; + case 0x2: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */ + case 0x6: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */ + case 0xa: /* SMULL, SMULL2, UMULL, UMULL2 */ + if (is_scalar) { + unallocated_encoding(s); + return; + } + is_long = true; + break; + case 0x3: /* SQDMLAL, SQDMLAL2 */ + case 0x7: /* SQDMLSL, SQDMLSL2 */ + case 0xb: /* SQDMULL, SQDMULL2 */ + is_long = true; + /* fall through */ + case 0xc: /* SQDMULH */ + case 0xd: /* SQRDMULH */ + if (u) { + unallocated_encoding(s); + return; + } + break; + case 0x8: /* MUL */ + if (u || is_scalar) { + unallocated_encoding(s); + return; + } + break; + case 0x1: /* FMLA */ + case 0x5: /* FMLS */ + if (u) { + unallocated_encoding(s); + return; + } + /* fall through */ + case 0x9: /* FMUL, FMULX */ + if (!extract32(size, 1, 1)) { + unallocated_encoding(s); + return; + } + is_fp = true; + break; + default: + unallocated_encoding(s); + return; + } + + if (is_fp) { + /* low bit of size indicates single/double */ + size = extract32(size, 0, 1) ? 3 : 2; + if (size == 2) { + index = h << 1 | l; + } else { + if (l || !is_q) { + unallocated_encoding(s); + return; + } + index = h; + } + rm |= (m << 4); + } else { + switch (size) { + case 1: + index = h << 2 | l << 1 | m; + break; + case 2: + index = h << 1 | l; + rm |= (m << 4); + break; + default: + unallocated_encoding(s); + return; + } + } + + if (is_fp) { + fpst = get_fpstatus_ptr(); + } else { + TCGV_UNUSED_PTR(fpst); + } + + if (size == 3) { + TCGv_i64 tcg_idx = tcg_temp_new_i64(); + int pass; + + assert(is_fp && is_q && !is_long); + + read_vec_element(s, tcg_idx, rm, index, MO_64); + + for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { + TCGv_i64 tcg_op = tcg_temp_new_i64(); + TCGv_i64 tcg_res = tcg_temp_new_i64(); + + read_vec_element(s, tcg_op, rn, pass, MO_64); + + switch (opcode) { + case 0x5: /* FMLS */ + /* As usual for ARM, separate negation for fused multiply-add */ + gen_helper_vfp_negd(tcg_op, tcg_op); + /* fall through */ + case 0x1: /* FMLA */ + read_vec_element(s, tcg_res, rd, pass, MO_64); + gen_helper_vfp_muladdd(tcg_res, tcg_op, tcg_idx, tcg_res, fpst); + break; + case 0x9: /* FMUL, FMULX */ + if (u) { + gen_helper_vfp_mulxd(tcg_res, tcg_op, tcg_idx, fpst); + } else { + gen_helper_vfp_muld(tcg_res, tcg_op, tcg_idx, fpst); + } + break; + default: + g_assert_not_reached(); + } + + write_vec_element(s, tcg_res, rd, pass, MO_64); + tcg_temp_free_i64(tcg_op); + tcg_temp_free_i64(tcg_res); + } + + if (is_scalar) { + clear_vec_high(s, rd); + } + + tcg_temp_free_i64(tcg_idx); + } else if (!is_long) { + /* 32 bit floating point, or 16 or 32 bit integer. + * For the 16 bit scalar case we use the usual Neon helpers and + * rely on the fact that 0 op 0 == 0 with no side effects. + */ + TCGv_i32 tcg_idx = tcg_temp_new_i32(); + int pass, maxpasses; + + if (is_scalar) { + maxpasses = 1; + } else { + maxpasses = is_q ? 4 : 2; + } + + read_vec_element_i32(s, tcg_idx, rm, index, size); + + if (size == 1 && !is_scalar) { + /* The simplest way to handle the 16x16 indexed ops is to duplicate + * the index into both halves of the 32 bit tcg_idx and then use + * the usual Neon helpers. + */ + tcg_gen_deposit_i32(tcg_idx, tcg_idx, tcg_idx, 16, 16); + } + + for (pass = 0; pass < maxpasses; pass++) { + TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32); + + switch (opcode) { + case 0x0: /* MLA */ + case 0x4: /* MLS */ + case 0x8: /* MUL */ + { + static NeonGenTwoOpFn * const fns[2][2] = { + { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 }, + { tcg_gen_add_i32, tcg_gen_sub_i32 }, + }; + NeonGenTwoOpFn *genfn; + bool is_sub = opcode == 0x4; + + if (size == 1) { + gen_helper_neon_mul_u16(tcg_res, tcg_op, tcg_idx); + } else { + tcg_gen_mul_i32(tcg_res, tcg_op, tcg_idx); + } + if (opcode == 0x8) { + break; + } + read_vec_element_i32(s, tcg_op, rd, pass, MO_32); + genfn = fns[size - 1][is_sub]; + genfn(tcg_res, tcg_op, tcg_res); + break; + } + case 0x5: /* FMLS */ + /* As usual for ARM, separate negation for fused multiply-add */ + gen_helper_vfp_negs(tcg_op, tcg_op); + /* fall through */ + case 0x1: /* FMLA */ + read_vec_element_i32(s, tcg_res, rd, pass, MO_32); + gen_helper_vfp_muladds(tcg_res, tcg_op, tcg_idx, tcg_res, fpst); + break; + case 0x9: /* FMUL, FMULX */ + if (u) { + gen_helper_vfp_mulxs(tcg_res, tcg_op, tcg_idx, fpst); + } else { + gen_helper_vfp_muls(tcg_res, tcg_op, tcg_idx, fpst); + } + break; + case 0xc: /* SQDMULH */ + if (size == 1) { + gen_helper_neon_qdmulh_s16(tcg_res, cpu_env, + tcg_op, tcg_idx); + } else { + gen_helper_neon_qdmulh_s32(tcg_res, cpu_env, + tcg_op, tcg_idx); + } + break; + case 0xd: /* SQRDMULH */ + if (size == 1) { + gen_helper_neon_qrdmulh_s16(tcg_res, cpu_env, + tcg_op, tcg_idx); + } else { + gen_helper_neon_qrdmulh_s32(tcg_res, cpu_env, + tcg_op, tcg_idx); + } + break; + default: + g_assert_not_reached(); + } + + if (is_scalar) { + write_fp_sreg(s, rd, tcg_res); + } else { + write_vec_element_i32(s, tcg_res, rd, pass, MO_32); + } + + tcg_temp_free_i32(tcg_op); + tcg_temp_free_i32(tcg_res); + } + + tcg_temp_free_i32(tcg_idx); + + if (!is_q) { + clear_vec_high(s, rd); + } + } else { + /* long ops: 16x16->32 or 32x32->64 */ + TCGv_i64 tcg_res[2]; + int pass; + bool satop = extract32(opcode, 0, 1); + TCGMemOp memop = MO_32; + + if (satop || !u) { + memop |= MO_SIGN; + } + + if (size == 2) { + TCGv_i64 tcg_idx = tcg_temp_new_i64(); + + read_vec_element(s, tcg_idx, rm, index, memop); + + for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { + TCGv_i64 tcg_op = tcg_temp_new_i64(); + TCGv_i64 tcg_passres; + int passelt; + + if (is_scalar) { + passelt = 0; + } else { + passelt = pass + (is_q * 2); + } + + read_vec_element(s, tcg_op, rn, passelt, memop); + + tcg_res[pass] = tcg_temp_new_i64(); + + if (opcode == 0xa || opcode == 0xb) { + /* Non-accumulating ops */ + tcg_passres = tcg_res[pass]; + } else { + tcg_passres = tcg_temp_new_i64(); + } + + tcg_gen_mul_i64(tcg_passres, tcg_op, tcg_idx); + tcg_temp_free_i64(tcg_op); + + if (satop) { + /* saturating, doubling */ + gen_helper_neon_addl_saturate_s64(tcg_passres, cpu_env, + tcg_passres, tcg_passres); + } + + if (opcode == 0xa || opcode == 0xb) { + continue; + } + + /* Accumulating op: handle accumulate step */ + read_vec_element(s, tcg_res[pass], rd, pass, MO_64); + + switch (opcode) { + case 0x2: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */ + tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_passres); + break; + case 0x6: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */ + tcg_gen_sub_i64(tcg_res[pass], tcg_res[pass], tcg_passres); + break; + case 0x7: /* SQDMLSL, SQDMLSL2 */ + tcg_gen_neg_i64(tcg_passres, tcg_passres); + /* fall through */ + case 0x3: /* SQDMLAL, SQDMLAL2 */ + gen_helper_neon_addl_saturate_s64(tcg_res[pass], cpu_env, + tcg_res[pass], + tcg_passres); + break; + default: + g_assert_not_reached(); + } + tcg_temp_free_i64(tcg_passres); + } + tcg_temp_free_i64(tcg_idx); + + if (is_scalar) { + clear_vec_high(s, rd); + } + } else { + TCGv_i32 tcg_idx = tcg_temp_new_i32(); + + assert(size == 1); + read_vec_element_i32(s, tcg_idx, rm, index, size); + + if (!is_scalar) { + /* The simplest way to handle the 16x16 indexed ops is to + * duplicate the index into both halves of the 32 bit tcg_idx + * and then use the usual Neon helpers. + */ + tcg_gen_deposit_i32(tcg_idx, tcg_idx, tcg_idx, 16, 16); + } + + for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { + TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i64 tcg_passres; + + if (is_scalar) { + read_vec_element_i32(s, tcg_op, rn, pass, size); + } else { + read_vec_element_i32(s, tcg_op, rn, + pass + (is_q * 2), MO_32); + } + + tcg_res[pass] = tcg_temp_new_i64(); + + if (opcode == 0xa || opcode == 0xb) { + /* Non-accumulating ops */ + tcg_passres = tcg_res[pass]; + } else { + tcg_passres = tcg_temp_new_i64(); + } + + if (memop & MO_SIGN) { + gen_helper_neon_mull_s16(tcg_passres, tcg_op, tcg_idx); + } else { + gen_helper_neon_mull_u16(tcg_passres, tcg_op, tcg_idx); + } + if (satop) { + gen_helper_neon_addl_saturate_s32(tcg_passres, cpu_env, + tcg_passres, tcg_passres); + } + tcg_temp_free_i32(tcg_op); + + if (opcode == 0xa || opcode == 0xb) { + continue; + } + + /* Accumulating op: handle accumulate step */ + read_vec_element(s, tcg_res[pass], rd, pass, MO_64); + + switch (opcode) { + case 0x2: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */ + gen_helper_neon_addl_u32(tcg_res[pass], tcg_res[pass], + tcg_passres); + break; + case 0x6: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */ + gen_helper_neon_subl_u32(tcg_res[pass], tcg_res[pass], + tcg_passres); + break; + case 0x7: /* SQDMLSL, SQDMLSL2 */ + gen_helper_neon_negl_u32(tcg_passres, tcg_passres); + /* fall through */ + case 0x3: /* SQDMLAL, SQDMLAL2 */ + gen_helper_neon_addl_saturate_s32(tcg_res[pass], cpu_env, + tcg_res[pass], + tcg_passres); + break; + default: + g_assert_not_reached(); + } + tcg_temp_free_i64(tcg_passres); + } + tcg_temp_free_i32(tcg_idx); + + if (is_scalar) { + tcg_gen_ext32u_i64(tcg_res[0], tcg_res[0]); + } + } + + if (is_scalar) { + tcg_res[1] = tcg_const_i64(0); + } + + for (pass = 0; pass < 2; pass++) { + write_vec_element(s, tcg_res[pass], rd, pass, MO_64); + tcg_temp_free_i64(tcg_res[pass]); + } + } + + if (!TCGV_IS_UNUSED_PTR(fpst)) { + tcg_temp_free_ptr(fpst); + } } /* C3.6.19 Crypto AES @@ -7861,7 +8887,7 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, { 0x0e300800, 0x9f3e0c00, disas_simd_across_lanes }, { 0x0e000400, 0x9fe08400, disas_simd_copy }, - { 0x0f000000, 0x9f000400, disas_simd_indexed_vector }, + { 0x0f000000, 0x9f000400, disas_simd_indexed }, /* vector indexed */ /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */ { 0x0f000400, 0x9ff80400, disas_simd_mod_imm }, { 0x0f000400, 0x9f800400, disas_simd_shift_imm }, @@ -7873,7 +8899,7 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, { 0x5e300800, 0xdf3e0c00, disas_simd_scalar_pairwise }, { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, - { 0x5f000000, 0xdf000400, disas_simd_scalar_indexed }, + { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, { 0x4e280800, 0xff3e0c00, disas_crypto_aes }, { 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha }, diff --git a/target-arm/translate.c b/target-arm/translate.c index 782aab8b58..6ccf0ba482 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -6837,6 +6837,17 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn) return 1; } + if (ri->accessfn) { + /* Emit code to perform further access permissions checks at + * runtime; this may result in an exception. + */ + TCGv_ptr tmpptr; + gen_set_pc_im(s, s->pc); + tmpptr = tcg_const_ptr(ri); + gen_helper_access_check_cp_reg(cpu_env, tmpptr); + tcg_temp_free_ptr(tmpptr); + } + /* Handle special cases first */ switch (ri->type & ~(ARM_CP_FLAG_MASK & ~ARM_CP_SPECIAL)) { case ARM_CP_NOP: @@ -6865,7 +6876,6 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn) tmp64 = tcg_const_i64(ri->resetvalue); } else if (ri->readfn) { TCGv_ptr tmpptr; - gen_set_pc_im(s, s->pc); tmp64 = tcg_temp_new_i64(); tmpptr = tcg_const_ptr(ri); gen_helper_get_cp_reg64(tmp64, cpu_env, tmpptr); @@ -6888,7 +6898,6 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn) tmp = tcg_const_i32(ri->resetvalue); } else if (ri->readfn) { TCGv_ptr tmpptr; - gen_set_pc_im(s, s->pc); tmp = tcg_temp_new_i32(); tmpptr = tcg_const_ptr(ri); gen_helper_get_cp_reg(tmp, cpu_env, tmpptr); @@ -6923,7 +6932,6 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmphi); if (ri->writefn) { TCGv_ptr tmpptr = tcg_const_ptr(ri); - gen_set_pc_im(s, s->pc); gen_helper_set_cp_reg64(cpu_env, tmpptr, tmp64); tcg_temp_free_ptr(tmpptr); } else { @@ -6934,7 +6942,6 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn) if (ri->writefn) { TCGv_i32 tmp; TCGv_ptr tmpptr; - gen_set_pc_im(s, s->pc); tmp = load_reg(s, rt); tmpptr = tcg_const_ptr(ri); gen_helper_set_cp_reg(cpu_env, tmpptr, tmp); @@ -6962,6 +6969,19 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn) return 0; } + /* Unknown register; this might be a guest error or a QEMU + * unimplemented feature. + */ + if (is64) { + qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch32 " + "64 bit system register cp:%d opc1: %d crm:%d\n", + isread ? "read" : "write", cpnum, opc1, crm); + } else { + qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch32 " + "system register cp:%d opc1:%d crn:%d crm:%d opc2:%d\n", + isread ? "read" : "write", cpnum, opc1, crn, crm, opc2); + } + return 1; }