diff options
| -rw-r--r-- | hw/arm/virt.c | 2 | ||||
| -rw-r--r-- | hw/display/bcm2835_fb.c | 2 | ||||
| -rw-r--r-- | target/arm/cpu.h | 17 | ||||
| -rw-r--r-- | target/arm/cpu64.c | 42 | ||||
| -rw-r--r-- | target/arm/helper-sve.h | 389 | ||||
| -rw-r--r-- | target/arm/helper.c | 337 | ||||
| -rw-r--r-- | target/arm/helper.h | 2 | ||||
| -rw-r--r-- | target/arm/internals.h | 44 | ||||
| -rw-r--r-- | target/arm/kvm.c | 2 | ||||
| -rw-r--r-- | target/arm/kvm_arm.h | 4 | ||||
| -rw-r--r-- | target/arm/op_helper.c | 24 | ||||
| -rw-r--r-- | target/arm/sve_helper.c | 1969 | ||||
| -rw-r--r-- | target/arm/translate-a64.c | 8 | ||||
| -rw-r--r-- | target/arm/translate-sve.c | 690 | ||||
| -rw-r--r-- | target/arm/translate.c | 198 | ||||
| -rw-r--r-- | target/arm/translate.h | 1 |
16 files changed, 2623 insertions, 1108 deletions
diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 0b57f87abc..a472566074 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -1926,6 +1926,8 @@ static void virt_machine_2_10_options(MachineClass *mc) { virt_machine_2_11_options(mc); SET_MACHINE_COMPAT(mc, VIRT_COMPAT_2_10); + /* before 2.11 we never faulted accesses to bad addresses */ + mc->ignore_memory_transaction_failures = true; } DEFINE_VIRT_MACHINE(2, 10) diff --git a/hw/display/bcm2835_fb.c b/hw/display/bcm2835_fb.c index d534d00a65..599863e4e1 100644 --- a/hw/display/bcm2835_fb.c +++ b/hw/display/bcm2835_fb.c @@ -190,7 +190,7 @@ static void fb_update_display(void *opaque) } if (s->invalidate) { - hwaddr base = s->config.base + xoff + yoff * src_width; + hwaddr base = s->config.base + xoff + (hwaddr)yoff * src_width; framebuffer_update_memory_section(&s->fbsection, s->dma_mr, base, s->config.yres, src_width); diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 65c0fa0a65..3a2aff1192 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -56,6 +56,7 @@ #define EXCP_SEMIHOST 16 /* semihosting call */ #define EXCP_NOCP 17 /* v7M NOCP UsageFault */ #define EXCP_INVSTATE 18 /* v7M INVSTATE UsageFault */ +#define EXCP_STKOF 19 /* v8M STKOF UsageFault */ /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 @@ -910,12 +911,20 @@ int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, int aarch64_cpu_gdb_read_register(CPUState *cpu, uint8_t *buf, int reg); int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq); +void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el); +#else +static inline void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) { } +static inline void aarch64_sve_change_el(CPUARMState *env, int o, int n) { } #endif target_ulong do_arm_semihosting(CPUARMState *env); void aarch64_sync_32_to_64(CPUARMState *env); void aarch64_sync_64_to_32(CPUARMState *env); +int fp_exception_el(CPUARMState *env, int cur_el); +int sve_exception_el(CPUARMState *env, int cur_el); +uint32_t sve_zcr_len_for_el(CPUARMState *env, int el); + static inline bool is_a64(CPUARMState *env) { return env->aarch64; @@ -1336,8 +1345,10 @@ FIELD(V7M_CCR, UNALIGN_TRP, 3, 1) FIELD(V7M_CCR, DIV_0_TRP, 4, 1) FIELD(V7M_CCR, BFHFNMIGN, 8, 1) FIELD(V7M_CCR, STKALIGN, 9, 1) +FIELD(V7M_CCR, STKOFHFNMIGN, 10, 1) FIELD(V7M_CCR, DC, 16, 1) FIELD(V7M_CCR, IC, 17, 1) +FIELD(V7M_CCR, BP, 18, 1) /* V7M SCR bits */ FIELD(V7M_SCR, SLEEPONEXIT, 1, 1) @@ -1378,6 +1389,7 @@ FIELD(V7M_CFSR, UNDEFINSTR, 16 + 0, 1) FIELD(V7M_CFSR, INVSTATE, 16 + 1, 1) FIELD(V7M_CFSR, INVPC, 16 + 2, 1) FIELD(V7M_CFSR, NOCP, 16 + 3, 1) +FIELD(V7M_CFSR, STKOF, 16 + 4, 1) FIELD(V7M_CFSR, UNALIGNED, 16 + 8, 1) FIELD(V7M_CFSR, DIVBYZERO, 16 + 9, 1) @@ -2842,6 +2854,9 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) /* For M profile only, Handler (ie not Thread) mode */ #define ARM_TBFLAG_HANDLER_SHIFT 21 #define ARM_TBFLAG_HANDLER_MASK (1 << ARM_TBFLAG_HANDLER_SHIFT) +/* For M profile only, whether we should generate stack-limit checks */ +#define ARM_TBFLAG_STACKCHECK_SHIFT 22 +#define ARM_TBFLAG_STACKCHECK_MASK (1 << ARM_TBFLAG_STACKCHECK_SHIFT) /* Bit usage when in AArch64 state */ #define ARM_TBFLAG_TBI0_SHIFT 0 /* TBI0 for EL0/1 or TBI for EL2/3 */ @@ -2884,6 +2899,8 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) (((F) & ARM_TBFLAG_BE_DATA_MASK) >> ARM_TBFLAG_BE_DATA_SHIFT) #define ARM_TBFLAG_HANDLER(F) \ (((F) & ARM_TBFLAG_HANDLER_MASK) >> ARM_TBFLAG_HANDLER_SHIFT) +#define ARM_TBFLAG_STACKCHECK(F) \ + (((F) & ARM_TBFLAG_STACKCHECK_MASK) >> ARM_TBFLAG_STACKCHECK_SHIFT) #define ARM_TBFLAG_TBI0(F) \ (((F) & ARM_TBFLAG_TBI0_MASK) >> ARM_TBFLAG_TBI0_SHIFT) #define ARM_TBFLAG_TBI1(F) \ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 800bff780e..db71504cb5 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -410,45 +410,3 @@ static void aarch64_cpu_register_types(void) } type_init(aarch64_cpu_register_types) - -/* The manual says that when SVE is enabled and VQ is widened the - * implementation is allowed to zero the previously inaccessible - * portion of the registers. The corollary to that is that when - * SVE is enabled and VQ is narrowed we are also allowed to zero - * the now inaccessible portion of the registers. - * - * The intent of this is that no predicate bit beyond VQ is ever set. - * Which means that some operations on predicate registers themselves - * may operate on full uint64_t or even unrolled across the maximum - * uint64_t[4]. Performing 4 bits of host arithmetic unconditionally - * may well be cheaper than conditionals to restrict the operation - * to the relevant portion of a uint16_t[16]. - * - * TODO: Need to call this for changes to the real system registers - * and EL state changes. - */ -void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) -{ - int i, j; - uint64_t pmask; - - assert(vq >= 1 && vq <= ARM_MAX_VQ); - assert(vq <= arm_env_get_cpu(env)->sve_max_vq); - - /* Zap the high bits of the zregs. */ - for (i = 0; i < 32; i++) { - memset(&env->vfp.zregs[i].d[2 * vq], 0, 16 * (ARM_MAX_VQ - vq)); - } - - /* Zap the high bits of the pregs and ffr. */ - pmask = 0; - if (vq & 3) { - pmask = ~(-1ULL << (16 * (vq & 3))); - } - for (j = vq / 4; j < ARM_MAX_VQ / 4; j++) { - for (i = 0; i < 17; ++i) { - env->vfp.pregs[i].p[j] &= pmask; - } - pmask = 0; - } -} diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 023952a9a4..9e79182ab4 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -1128,20 +1128,35 @@ DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) - -DEF_HELPER_FLAGS_4(sve_ld1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) - -DEF_HELPER_FLAGS_4(sve_ld1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1150,13 +1165,21 @@ DEF_HELPER_FLAGS_4(sve_ld1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ld1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1166,17 +1189,28 @@ DEF_HELPER_FLAGS_4(sve_ldff1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldff1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1186,218 +1220,357 @@ DEF_HELPER_FLAGS_4(sve_ldnf1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_ldnf1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1hs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1hd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hs_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hs_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) -DEF_HELPER_FLAGS_4(sve_st1sd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhsu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhsu_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhsu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldss_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldssu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbss_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhsu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhsu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhsu_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldssu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbss_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbdu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldddu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsdu_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbds_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhds_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsds_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbdu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhdu_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_lddd_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldddu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_lddd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbds_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbdu_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhdu_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhdu_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsdu_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldddu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_lddd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_lddd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbds_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldhds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldhds_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldsds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldsds_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhsu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhsu_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhsu_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffssu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbss_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbsu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhsu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhsu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhsu_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffssu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbss_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbdu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsdu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffddu_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsdu_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbds_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhds_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsds_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsds_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbdu_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhdu_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsdu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffdd_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffddu_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffdd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbds_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsds_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbdu_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhdu_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhdu_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsdu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsdu_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffddu_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffdd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbds_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffhds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffhds_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_ldffsds_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_ldffsds_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sths_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stss_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stss_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbs_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sths_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sths_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sths_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stss_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stss_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbd_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sthd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_le_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zsu, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_be_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_le_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbd_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sthd_be_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_le_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stsd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zss, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stdd_le_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_be_zss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbd_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_sthd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_sthd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sthd_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stsd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) -DEF_HELPER_FLAGS_6(sve_stdd_zd, TCG_CALL_NO_WG, +DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) diff --git a/target/arm/helper.c b/target/arm/helper.c index 64b1564594..c83f7c1109 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4400,78 +4400,105 @@ static const ARMCPRegInfo debug_lpae_cp_reginfo[] = { REGINFO_SENTINEL }; -/* Return the exception level to which SVE-disabled exceptions should - * be taken, or 0 if SVE is enabled. +/* Return the exception level to which exceptions should be taken + * via SVEAccessTrap. If an exception should be routed through + * AArch64.AdvSIMDFPAccessTrap, return 0; fp_exception_el should + * take care of raising that exception. + * C.f. the ARM pseudocode function CheckSVEEnabled. */ -static int sve_exception_el(CPUARMState *env) +int sve_exception_el(CPUARMState *env, int el) { #ifndef CONFIG_USER_ONLY - unsigned current_el = arm_current_el(env); + if (el <= 1) { + bool disabled = false; - /* The CPACR.ZEN controls traps to EL1: - * 0, 2 : trap EL0 and EL1 accesses - * 1 : trap only EL0 accesses - * 3 : trap no accesses - */ - switch (extract32(env->cp15.cpacr_el1, 16, 2)) { - default: - if (current_el <= 1) { - /* Trap to PL1, which might be EL1 or EL3 */ - if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) { - return 3; - } - return 1; + /* The CPACR.ZEN controls traps to EL1: + * 0, 2 : trap EL0 and EL1 accesses + * 1 : trap only EL0 accesses + * 3 : trap no accesses + */ + if (!extract32(env->cp15.cpacr_el1, 16, 1)) { + disabled = true; + } else if (!extract32(env->cp15.cpacr_el1, 17, 1)) { + disabled = el == 0; } - break; - case 1: - if (current_el == 0) { - return 1; + if (disabled) { + /* route_to_el2 */ + return (arm_feature(env, ARM_FEATURE_EL2) + && !arm_is_secure(env) + && (env->cp15.hcr_el2 & HCR_TGE) ? 2 : 1); } - break; - case 3: - break; - } - /* Similarly for CPACR.FPEN, after having checked ZEN. */ - switch (extract32(env->cp15.cpacr_el1, 20, 2)) { - default: - if (current_el <= 1) { - if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) { - return 3; - } - return 1; + /* Check CPACR.FPEN. */ + if (!extract32(env->cp15.cpacr_el1, 20, 1)) { + disabled = true; + } else if (!extract32(env->cp15.cpacr_el1, 21, 1)) { + disabled = el == 0; } - break; - case 1: - if (current_el == 0) { - return 1; + if (disabled) { + return 0; } - break; - case 3: - break; } - /* CPTR_EL2. Check both TZ and TFP. */ - if (current_el <= 2 - && (env->cp15.cptr_el[2] & (CPTR_TFP | CPTR_TZ)) - && !arm_is_secure_below_el3(env)) { - return 2; + /* CPTR_EL2. Since TZ and TFP are positive, + * they will be zero when EL2 is not present. + */ + if (el <= 2 && !arm_is_secure_below_el3(env)) { + if (env->cp15.cptr_el[2] & CPTR_TZ) { + return 2; + } + if (env->cp15.cptr_el[2] & CPTR_TFP) { + return 0; + } } - /* CPTR_EL3. Check both EZ and TFP. */ - if (!(env->cp15.cptr_el[3] & CPTR_EZ) - || (env->cp15.cptr_el[3] & CPTR_TFP)) { + /* CPTR_EL3. Since EZ is negative we must check for EL3. */ + if (arm_feature(env, ARM_FEATURE_EL3) + && !(env->cp15.cptr_el[3] & CPTR_EZ)) { return 3; } #endif return 0; } +/* + * Given that SVE is enabled, return the vector length for EL. + */ +uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) +{ + ARMCPU *cpu = arm_env_get_cpu(env); + uint32_t zcr_len = cpu->sve_max_vq - 1; + + if (el <= 1) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[1]); + } + if (el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[2]); + } + if (el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { + zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]); + } + return zcr_len; +} + static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { + int cur_el = arm_current_el(env); + int old_len = sve_zcr_len_for_el(env, cur_el); + int new_len; + /* Bits other than [3:0] are RAZ/WI. */ raw_write(env, ri, value & 0xf); + + /* + * Because we arrived here, we know both FP and SVE are enabled; + * otherwise we would have trapped access to the ZCR_ELn register. + */ + new_len = sve_zcr_len_for_el(env, cur_el); + if (new_len < old_len) { + aarch64_sve_narrow_vq(env, new_len + 1); + } } static const ARMCPRegInfo zcr_el1_reginfo = { @@ -5018,9 +5045,10 @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ID_AA64PFR4_EL1_RESERVED", .state = ARM_CP_STATE_AA64, + { .name = "ID_AA64ZFR0_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, + /* At present, only SVEver == 0 is defined anyway. */ .resetvalue = 0 }, { .name = "ID_AA64PFR5_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 5, @@ -6554,18 +6582,6 @@ pend_fault: return false; } -/* Return true if we're using the process stack pointer (not the MSP) */ -static bool v7m_using_psp(CPUARMState *env) -{ - /* Handler mode always uses the main stack; for thread mode - * the CONTROL.SPSEL bit determines the answer. - * Note that in v7M it is not possible to be in Handler mode with - * CONTROL.SPSEL non-zero, but in v8M it is, so we must check both. - */ - return !arm_v7m_is_handler_mode(env) && - env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK; -} - /* Write to v7M CONTROL.SPSEL bit for the specified security bank. * This may change the current stack pointer between Main and Process * stack pointers if it is done for the CONTROL register for the current @@ -6722,6 +6738,10 @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) "BLXNS with misaligned SP is UNPREDICTABLE\n"); } + if (sp < v7m_sp_limit(env)) { + raise_exception(env, EXCP_STKOF, 0, 1); + } + saved_psr = env->v7m.exception; if (env->v7m.control[M_REG_S] & R_V7M_CONTROL_SFPA_MASK) { saved_psr |= XPSR_SFPA; @@ -6851,6 +6871,8 @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, uint32_t frameptr; ARMMMUIdx mmu_idx; bool stacked_ok; + uint32_t limit; + bool want_psp; if (dotailchain) { bool mode = lr & R_V7M_EXCRET_MODE_MASK; @@ -6860,12 +6882,34 @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, M_REG_S, priv); frame_sp_p = get_v7m_sp_ptr(env, M_REG_S, mode, lr & R_V7M_EXCRET_SPSEL_MASK); + want_psp = mode && (lr & R_V7M_EXCRET_SPSEL_MASK); + if (want_psp) { + limit = env->v7m.psplim[M_REG_S]; + } else { + limit = env->v7m.msplim[M_REG_S]; + } } else { mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); frame_sp_p = &env->regs[13]; + limit = v7m_sp_limit(env); } frameptr = *frame_sp_p - 0x28; + if (frameptr < limit) { + /* + * Stack limit failure: set SP to the limit value, and generate + * STKOF UsageFault. Stack pushes below the limit must not be + * performed. It is IMPDEF whether pushes above the limit are + * performed; we choose not to. + */ + qemu_log_mask(CPU_LOG_INT, + "...STKOF during callee-saves register stacking\n"); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_STKOF_MASK; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, + env->v7m.secure); + *frame_sp_p = limit; + return true; + } /* Write as much of the stack frame as we can. A write failure may * cause us to pend a derived exception. @@ -6889,10 +6933,7 @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, v7m_stack_write(cpu, frameptr + 0x24, env->regs[11], mmu_idx, ignore_faults); - /* Update SP regardless of whether any of the stack accesses failed. - * When we implement v8M stack limit checking then this attempt to - * update SP might also fail and result in a derived exception. - */ + /* Update SP regardless of whether any of the stack accesses failed. */ *frame_sp_p = frameptr; return !stacked_ok; @@ -6938,7 +6979,7 @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, * not already saved. */ if (lr & R_V7M_EXCRET_DCRS_MASK && - !(dotailchain && (lr & R_V7M_EXCRET_ES_MASK))) { + !(dotailchain && !(lr & R_V7M_EXCRET_ES_MASK))) { push_failed = v7m_push_callee_stack(cpu, lr, dotailchain, ignore_stackfaults); } @@ -7040,6 +7081,26 @@ static bool v7m_push_stack(ARMCPU *cpu) frameptr -= 0x20; + if (arm_feature(env, ARM_FEATURE_V8)) { + uint32_t limit = v7m_sp_limit(env); + + if (frameptr < limit) { + /* + * Stack limit failure: set SP to the limit value, and generate + * STKOF UsageFault. Stack pushes below the limit must not be + * performed. It is IMPDEF whether pushes above the limit are + * performed; we choose not to. + */ + qemu_log_mask(CPU_LOG_INT, + "...STKOF during stacking\n"); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_STKOF_MASK; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, + env->v7m.secure); + env->regs[13] = limit; + return true; + } + } + /* Write as much of the stack frame as we can. If we fail a stack * write this will result in a derived exception being pended * (which may be taken in preference to the one we started with @@ -7055,10 +7116,7 @@ static bool v7m_push_stack(ARMCPU *cpu) v7m_stack_write(cpu, frameptr + 24, env->regs[15], mmu_idx, false) && v7m_stack_write(cpu, frameptr + 28, xpsr, mmu_idx, false); - /* Update SP regardless of whether any of the stack accesses failed. - * When we implement v8M stack limit checking then this attempt to - * update SP might also fail and result in a derived exception. - */ + /* Update SP regardless of whether any of the stack accesses failed. */ env->regs[13] = frameptr; return !stacked_ok; @@ -7304,7 +7362,6 @@ static void do_v7m_exception_exit(ARMCPU *cpu) pop_ok = pop_ok && v7m_stack_read(cpu, &env->regs[4], frameptr + 0x8, mmu_idx) && - v7m_stack_read(cpu, &env->regs[4], frameptr + 0x8, mmu_idx) && v7m_stack_read(cpu, &env->regs[5], frameptr + 0xc, mmu_idx) && v7m_stack_read(cpu, &env->regs[6], frameptr + 0x10, mmu_idx) && v7m_stack_read(cpu, &env->regs[7], frameptr + 0x14, mmu_idx) && @@ -7512,6 +7569,7 @@ static void arm_log_exception(int idx) [EXCP_SEMIHOST] = "Semihosting call", [EXCP_NOCP] = "v7M NOCP UsageFault", [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", + [EXCP_STKOF] = "v8M STKOF UsageFault", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { @@ -7667,6 +7725,10 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVSTATE_MASK; break; + case EXCP_STKOF: + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_STKOF_MASK; + break; case EXCP_SWI: /* The PC already points to the next instruction. */ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); @@ -8310,8 +8372,11 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) unsigned int new_el = env->exception.target_el; target_ulong addr = env->cp15.vbar_el[new_el]; unsigned int new_mode = aarch64_pstate_mode(new_el, true); + unsigned int cur_el = arm_current_el(env); - if (arm_current_el(env) < new_el) { + aarch64_sve_change_el(env, cur_el, new_el); + + if (cur_el < new_el) { /* Entry vector offset depends on whether the implemented EL * immediately lower than the target level is using AArch32 or AArch64 */ @@ -10929,11 +10994,23 @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) * currently in handler mode or not, using the NS CONTROL.SPSEL. */ bool spsel = env->v7m.control[M_REG_NS] & R_V7M_CONTROL_SPSEL_MASK; + bool is_psp = !arm_v7m_is_handler_mode(env) && spsel; + uint32_t limit; if (!env->v7m.secure) { return; } - if (!arm_v7m_is_handler_mode(env) && spsel) { + + limit = is_psp ? env->v7m.psplim[false] : env->v7m.msplim[false]; + + if (val < limit) { + CPUState *cs = CPU(arm_env_get_cpu(env)); + + cpu_restore_state(cs, GETPC(), true); + raise_exception(env, EXCP_STKOF, 0, 1); + } + + if (is_psp) { env->v7m.other_ss_psp = val; } else { env->v7m.other_ss_msp = val; @@ -12516,11 +12593,10 @@ uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) /* Return the exception level to which FP-disabled exceptions should * be taken, or 0 if FP is enabled. */ -static inline int fp_exception_el(CPUARMState *env) +int fp_exception_el(CPUARMState *env, int cur_el) { #ifndef CONFIG_USER_ONLY int fpen; - int cur_el = arm_current_el(env); /* CPACR and the CPTR registers don't exist before v6, so FP is * always accessible @@ -12583,7 +12659,8 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); - int fp_el = fp_exception_el(env); + int current_el = arm_current_el(env); + int fp_el = fp_exception_el(env, current_el); uint32_t flags; if (is_a64(env)) { @@ -12594,7 +12671,7 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags |= (arm_regime_tbi1(env, mmu_idx) << ARM_TBFLAG_TBI1_SHIFT); if (arm_feature(env, ARM_FEATURE_SVE)) { - int sve_el = sve_exception_el(env); + int sve_el = sve_exception_el(env, current_el); uint32_t zcr_len; /* If SVE is disabled, but FP is enabled, @@ -12603,19 +12680,7 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (sve_el != 0 && fp_el == 0) { zcr_len = 0; } else { - int current_el = arm_current_el(env); - ARMCPU *cpu = arm_env_get_cpu(env); - - zcr_len = cpu->sve_max_vq - 1; - if (current_el <= 1) { - zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[1]); - } - if (current_el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { - zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[2]); - } - if (current_el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { - zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]); - } + zcr_len = sve_zcr_len_for_el(env, current_el); } flags |= sve_el << ARM_TBFLAG_SVEEXC_EL_SHIFT; flags |= zcr_len << ARM_TBFLAG_ZCR_LEN_SHIFT; @@ -12668,6 +12733,98 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags |= ARM_TBFLAG_HANDLER_MASK; } + /* v8M always applies stack limit checks unless CCR.STKOFHFNMIGN is + * suppressing them because the requested execution priority is less than 0. + */ + if (arm_feature(env, ARM_FEATURE_V8) && + arm_feature(env, ARM_FEATURE_M) && + !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) && + (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) { + flags |= ARM_TBFLAG_STACKCHECK_MASK; + } + *pflags = flags; *cs_base = 0; } + +#ifdef TARGET_AARCH64 +/* + * The manual says that when SVE is enabled and VQ is widened the + * implementation is allowed to zero the previously inaccessible + * portion of the registers. The corollary to that is that when + * SVE is enabled and VQ is narrowed we are also allowed to zero + * the now inaccessible portion of the registers. + * + * The intent of this is that no predicate bit beyond VQ is ever set. + * Which means that some operations on predicate registers themselves + * may operate on full uint64_t or even unrolled across the maximum + * uint64_t[4]. Performing 4 bits of host arithmetic unconditionally + * may well be cheaper than conditionals to restrict the operation + * to the relevant portion of a uint16_t[16]. + */ +void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) +{ + int i, j; + uint64_t pmask; + + assert(vq >= 1 && vq <= ARM_MAX_VQ); + assert(vq <= arm_env_get_cpu(env)->sve_max_vq); + + /* Zap the high bits of the zregs. */ + for (i = 0; i < 32; i++) { + memset(&env->vfp.zregs[i].d[2 * vq], 0, 16 * (ARM_MAX_VQ - vq)); + } + + /* Zap the high bits of the pregs and ffr. */ + pmask = 0; + if (vq & 3) { + pmask = ~(-1ULL << (16 * (vq & 3))); + } + for (j = vq / 4; j < ARM_MAX_VQ / 4; j++) { + for (i = 0; i < 17; ++i) { + env->vfp.pregs[i].p[j] &= pmask; + } + pmask = 0; + } +} + +/* + * Notice a change in SVE vector size when changing EL. + */ +void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el) +{ + int old_len, new_len; + + /* Nothing to do if no SVE. */ + if (!arm_feature(env, ARM_FEATURE_SVE)) { + return; + } + + /* Nothing to do if FP is disabled in either EL. */ + if (fp_exception_el(env, old_el) || fp_exception_el(env, new_el)) { + return; + } + + /* + * DDI0584A.d sec 3.2: "If SVE instructions are disabled or trapped + * at ELx, or not available because the EL is in AArch32 state, then + * for all purposes other than a direct read, the ZCR_ELx.LEN field + * has an effective value of 0". + * + * Consider EL2 (aa64, vq=4) -> EL0 (aa32) -> EL1 (aa64, vq=0). + * If we ignore aa32 state, we would fail to see the vq4->vq0 transition + * from EL2->EL1. Thus we go ahead and narrow when entering aa32 so that + * we already have the correct register contents when encountering the + * vq0->vq0 transition between EL0->EL1. + */ + old_len = (arm_el_is_aa64(env, old_el) && !sve_exception_el(env, old_el) + ? sve_zcr_len_for_el(env, old_el) : 0); + new_len = (arm_el_is_aa64(env, new_el) && !sve_exception_el(env, new_el) + ? sve_zcr_len_for_el(env, new_el) : 0); + + /* When changing vector length, clear inaccessible state. */ + if (new_len < old_len) { + aarch64_sve_narrow_vq(env, new_len + 1); + } +} +#endif diff --git a/target/arm/helper.h b/target/arm/helper.h index 59e8c3bd1b..8c9590091b 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -69,6 +69,8 @@ DEF_HELPER_2(v7m_blxns, void, env, i32) DEF_HELPER_3(v7m_tt, i32, env, i32, i32) +DEF_HELPER_2(v8m_stackcheck, void, env, i32) + DEF_HELPER_4(access_check_cp_reg, void, env, ptr, i32, i32) DEF_HELPER_3(set_cp_reg, void, env, ptr, i32) DEF_HELPER_2(get_cp_reg, i32, env, ptr) diff --git a/target/arm/internals.h b/target/arm/internals.h index dc9357766c..a4fc709bcc 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -94,6 +94,15 @@ FIELD(V7M_EXCRET, RES1, 7, 25) /* including the must-be-1 prefix */ #define M_FAKE_FSR_NSC_EXEC 0xf /* NS executing in S&NSC memory */ #define M_FAKE_FSR_SFAULT 0xe /* SecureFault INVTRAN, INVEP or AUVIOL */ +/** + * raise_exception: Raise the specified exception. + * Raise a guest exception with the specified value, syndrome register + * and target exception level. This should be called from helper functions, + * and never returns because we will longjump back up to the CPU main loop. + */ +void QEMU_NORETURN raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el); + /* * For AArch64, map a given EL to an index in the banked_spsr array. * Note that this mapping and the AArch32 mapping defined in bank_number() @@ -796,4 +805,39 @@ static inline uint32_t arm_debug_exception_fsr(CPUARMState *env) } } +/* Note make_memop_idx reserves 4 bits for mmu_idx, and MO_BSWAP is bit 3. + * Thus a TCGMemOpIdx, without any MO_ALIGN bits, fits in 8 bits. + */ +#define MEMOPIDX_SHIFT 8 + +/** + * v7m_using_psp: Return true if using process stack pointer + * Return true if the CPU is currently using the process stack + * pointer, or false if it is using the main stack pointer. + */ +static inline bool v7m_using_psp(CPUARMState *env) +{ + /* Handler mode always uses the main stack; for thread mode + * the CONTROL.SPSEL bit determines the answer. + * Note that in v7M it is not possible to be in Handler mode with + * CONTROL.SPSEL non-zero, but in v8M it is, so we must check both. + */ + return !arm_v7m_is_handler_mode(env) && + env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK; +} + +/** + * v7m_sp_limit: Return SP limit for current CPU state + * Return the SP limit value for the current CPU security state + * and stack pointer. + */ +static inline uint32_t v7m_sp_limit(CPUARMState *env) +{ + if (v7m_using_psp(env)) { + return env->v7m.psplim[env->v7m.secure]; + } else { + return env->v7m.msplim[env->v7m.secure]; + } +} + #endif diff --git a/target/arm/kvm.c b/target/arm/kvm.c index 65f867d569..54ef5f711b 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -310,7 +310,7 @@ static int compare_u64(const void *a, const void *b) return 0; } -/* Initialize the CPUState's cpreg list according to the kernel's +/* Initialize the ARMCPU cpreg list according to the kernel's * definition of what CPU registers it knows about (and throw away * the previous TCG-created cpreg list). */ diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index 863f205822..5948e8b560 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -50,9 +50,9 @@ void kvm_arm_register_device(MemoryRegion *mr, uint64_t devid, uint64_t group, /** * kvm_arm_init_cpreg_list: - * @cs: CPUState + * @cpu: ARMCPU * - * Initialize the CPUState's cpreg list according to the kernel's + * Initialize the ARMCPU cpreg list according to the kernel's * definition of what CPU registers it knows about (and throw away * the previous TCG-created cpreg list). * diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index 952b8d122b..fb15a13e6c 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -28,8 +28,8 @@ #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) -static void raise_exception(CPUARMState *env, uint32_t excp, - uint32_t syndrome, uint32_t target_el) +void raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) { CPUState *cs = CPU(arm_env_get_cpu(env)); @@ -238,6 +238,25 @@ void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, #endif /* !defined(CONFIG_USER_ONLY) */ +void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue) +{ + /* + * Perform the v8M stack limit check for SP updates from translated code, + * raising an exception if the limit is breached. + */ + if (newvalue < v7m_sp_limit(env)) { + CPUState *cs = CPU(arm_env_get_cpu(env)); + + /* + * Stack limit exceptions are a rare case, so rather than syncing + * PC/condbits before the call, we use cpu_restore_state() to + * get them right before raising the exception. + */ + cpu_restore_state(cs, GETPC(), true); + raise_exception(env, EXCP_STKOF, 0, 1); + } +} + uint32_t HELPER(add_setq)(CPUARMState *env, uint32_t a, uint32_t b) { uint32_t res = a + b; @@ -1082,6 +1101,7 @@ void HELPER(exception_return)(CPUARMState *env) "AArch64 EL%d PC 0x%" PRIx64 "\n", cur_el, new_el, env->pc); } + aarch64_sve_change_el(env, cur_el, new_el); qemu_mutex_lock_iothread(); arm_call_el_change_hook(arm_env_get_cpu(env)); diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index 0f98097253..8cbc6516ab 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -19,6 +19,7 @@ #include "qemu/osdep.h" #include "cpu.h" +#include "internals.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" @@ -1688,6 +1689,47 @@ static void swap_memmove(void *vd, void *vs, size_t n) } } +/* Similarly for memset of 0. */ +static void swap_memzero(void *vd, size_t n) +{ + uintptr_t d = (uintptr_t)vd; + uintptr_t o = (d | n) & 7; + size_t i; + + /* Usually, the first bit of a predicate is set, so N is 0. */ + if (likely(n == 0)) { + return; + } + +#ifndef HOST_WORDS_BIGENDIAN + o = 0; +#endif + switch (o) { + case 0: + memset(vd, 0, n); + break; + + case 4: + for (i = 0; i < n; i += 4) { + *(uint32_t *)H1_4(d + i) = 0; + } + break; + + case 2: + case 6: + for (i = 0; i < n; i += 2) { + *(uint16_t *)H1_2(d + i) = 0; + } + break; + + default: + for (i = 0; i < n; i++) { + *(uint8_t *)H1(d + i) = 0; + } + break; + } +} + void HELPER(sve_ext)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t opr_sz = simd_oprsz(desc); @@ -3927,161 +3969,471 @@ void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) /* * Load contiguous data, protected by a governing predicate. */ -#define DO_LD1(NAME, FN, TYPEE, TYPEM, H) \ -static void do_##NAME(CPUARMState *env, void *vd, void *vg, \ - target_ulong addr, intptr_t oprsz, \ - uintptr_t ra) \ -{ \ - intptr_t i = 0; \ - do { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - m = FN(env, addr, ra); \ - } \ - *(TYPEE *)(vd + H(i)) = m; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += sizeof(TYPEM); \ - } while (i & 15); \ - } while (i < oprsz); \ -} \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - do_##NAME(env, &env->vfp.zregs[simd_data(desc)], vg, \ - addr, simd_oprsz(desc), GETPC()); \ + +/* + * Load elements into @vd, controlled by @vg, from @host + @mem_ofs. + * Memory is valid through @host + @mem_max. The register element + * indicies are inferred from @mem_ofs, as modified by the types for + * which the helper is built. Return the @mem_ofs of the first element + * not loaded (which is @mem_max if they are all loaded). + * + * For softmmu, we have fully validated the guest page. For user-only, + * we cannot fully validate without taking the mmap lock, but since we + * know the access is within one host page, if any access is valid they + * all must be valid. However, when @vg is all false, it may be that + * no access is valid. + */ +typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host, + intptr_t mem_ofs, intptr_t mem_max); + +/* + * Load one element into @vd + @reg_off from (@env, @vaddr, @ra). + * The controlling predicate is known to be true. + */ +typedef void sve_ld1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong vaddr, TCGMemOpIdx oi, uintptr_t ra); +typedef sve_ld1_tlb_fn sve_st1_tlb_fn; + +/* + * Generate the above primitives. + */ + +#define DO_LD_HOST(NAME, H, TYPEE, TYPEM, HOST) \ +static intptr_t sve_##NAME##_host(void *vd, void *vg, void *host, \ + intptr_t mem_off, const intptr_t mem_max) \ +{ \ + intptr_t reg_off = mem_off * (sizeof(TYPEE) / sizeof(TYPEM)); \ + uint64_t *pg = vg; \ + while (mem_off + sizeof(TYPEM) <= mem_max) { \ + TYPEM val = 0; \ + if (likely((pg[reg_off >> 6] >> (reg_off & 63)) & 1)) { \ + val = HOST(host + mem_off); \ + } \ + *(TYPEE *)(vd + H(reg_off)) = val; \ + mem_off += sizeof(TYPEM), reg_off += sizeof(TYPEE); \ + } \ + return mem_off; \ +} + +#ifdef CONFIG_SOFTMMU +#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ +{ \ + TYPEM val = TLB(env, addr, oi, ra); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ } +#else +#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ +{ \ + TYPEM val = HOST(g2h(addr)); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ +} +#endif -#define DO_LD2(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m1 = 0, m2 = 0; \ - if (pg & 1) { \ - m1 = FN(env, addr, ra); \ - m2 = FN(env, addr + sizeof(TYPEM), ra); \ - } \ - *(TYPEE *)(d1 + H(i)) = m1; \ - *(TYPEE *)(d2 + H(i)) = m2; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 2 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +#define DO_LD_PRIM_1(NAME, H, TE, TM) \ + DO_LD_HOST(NAME, H, TE, TM, ldub_p) \ + DO_LD_TLB(NAME, H, TE, TM, ldub_p, 0, helper_ret_ldub_mmu) + +DO_LD_PRIM_1(ld1bb, H1, uint8_t, uint8_t) +DO_LD_PRIM_1(ld1bhu, H1_2, uint16_t, uint8_t) +DO_LD_PRIM_1(ld1bhs, H1_2, uint16_t, int8_t) +DO_LD_PRIM_1(ld1bsu, H1_4, uint32_t, uint8_t) +DO_LD_PRIM_1(ld1bss, H1_4, uint32_t, int8_t) +DO_LD_PRIM_1(ld1bdu, , uint64_t, uint8_t) +DO_LD_PRIM_1(ld1bds, , uint64_t, int8_t) + +#define DO_LD_PRIM_2(NAME, end, MOEND, H, TE, TM, PH, PT) \ + DO_LD_HOST(NAME##_##end, H, TE, TM, PH##_##end##_p) \ + DO_LD_TLB(NAME##_##end, H, TE, TM, PH##_##end##_p, \ + MOEND, helper_##end##_##PT##_mmu) + +DO_LD_PRIM_2(ld1hh, le, MO_LE, H1_2, uint16_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hsu, le, MO_LE, H1_4, uint32_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hss, le, MO_LE, H1_4, uint32_t, int16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hdu, le, MO_LE, , uint64_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hds, le, MO_LE, , uint64_t, int16_t, lduw, lduw) + +DO_LD_PRIM_2(ld1ss, le, MO_LE, H1_4, uint32_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sdu, le, MO_LE, , uint64_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sds, le, MO_LE, , uint64_t, int32_t, ldl, ldul) + +DO_LD_PRIM_2(ld1dd, le, MO_LE, , uint64_t, uint64_t, ldq, ldq) + +DO_LD_PRIM_2(ld1hh, be, MO_BE, H1_2, uint16_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hsu, be, MO_BE, H1_4, uint32_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hss, be, MO_BE, H1_4, uint32_t, int16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hdu, be, MO_BE, , uint64_t, uint16_t, lduw, lduw) +DO_LD_PRIM_2(ld1hds, be, MO_BE, , uint64_t, int16_t, lduw, lduw) + +DO_LD_PRIM_2(ld1ss, be, MO_BE, H1_4, uint32_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sdu, be, MO_BE, , uint64_t, uint32_t, ldl, ldul) +DO_LD_PRIM_2(ld1sds, be, MO_BE, , uint64_t, int32_t, ldl, ldul) + +DO_LD_PRIM_2(ld1dd, be, MO_BE, , uint64_t, uint64_t, ldq, ldq) + +#undef DO_LD_TLB +#undef DO_LD_HOST +#undef DO_LD_PRIM_1 +#undef DO_LD_PRIM_2 + +/* + * Skip through a sequence of inactive elements in the guarding predicate @vg, + * beginning at @reg_off bounded by @reg_max. Return the offset of the active + * element >= @reg_off, or @reg_max if there were no active elements at all. + */ +static intptr_t find_next_active(uint64_t *vg, intptr_t reg_off, + intptr_t reg_max, int esz) +{ + uint64_t pg_mask = pred_esz_masks[esz]; + uint64_t pg = (vg[reg_off >> 6] & pg_mask) >> (reg_off & 63); + + /* In normal usage, the first element is active. */ + if (likely(pg & 1)) { + return reg_off; + } + + if (pg == 0) { + reg_off &= -64; + do { + reg_off += 64; + if (unlikely(reg_off >= reg_max)) { + /* The entire predicate was false. */ + return reg_max; + } + pg = vg[reg_off >> 6] & pg_mask; + } while (pg == 0); + } + reg_off += ctz64(pg); + + /* We should never see an out of range predicate bit set. */ + tcg_debug_assert(reg_off < reg_max); + return reg_off; } -#define DO_LD3(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m1 = 0, m2 = 0, m3 = 0; \ - if (pg & 1) { \ - m1 = FN(env, addr, ra); \ - m2 = FN(env, addr + sizeof(TYPEM), ra); \ - m3 = FN(env, addr + 2 * sizeof(TYPEM), ra); \ - } \ - *(TYPEE *)(d1 + H(i)) = m1; \ - *(TYPEE *)(d2 + H(i)) = m2; \ - *(TYPEE *)(d3 + H(i)) = m3; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 3 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +/* + * Return the maximum offset <= @mem_max which is still within the page + * referenced by @base + @mem_off. + */ +static intptr_t max_for_page(target_ulong base, intptr_t mem_off, + intptr_t mem_max) +{ + target_ulong addr = base + mem_off; + intptr_t split = -(intptr_t)(addr | TARGET_PAGE_MASK); + return MIN(split, mem_max - mem_off) + mem_off; } -#define DO_LD4(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - void *d4 = &env->vfp.zregs[(rd + 3) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m1 = 0, m2 = 0, m3 = 0, m4 = 0; \ - if (pg & 1) { \ - m1 = FN(env, addr, ra); \ - m2 = FN(env, addr + sizeof(TYPEM), ra); \ - m3 = FN(env, addr + 2 * sizeof(TYPEM), ra); \ - m4 = FN(env, addr + 3 * sizeof(TYPEM), ra); \ - } \ - *(TYPEE *)(d1 + H(i)) = m1; \ - *(TYPEE *)(d2 + H(i)) = m2; \ - *(TYPEE *)(d3 + H(i)) = m3; \ - *(TYPEE *)(d4 + H(i)) = m4; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 4 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +static inline void set_helper_retaddr(uintptr_t ra) +{ +#ifdef CONFIG_USER_ONLY + helper_retaddr = ra; +#endif } -DO_LD1(sve_ld1bhu_r, cpu_ldub_data_ra, uint16_t, uint8_t, H1_2) -DO_LD1(sve_ld1bhs_r, cpu_ldsb_data_ra, uint16_t, int8_t, H1_2) -DO_LD1(sve_ld1bsu_r, cpu_ldub_data_ra, uint32_t, uint8_t, H1_4) -DO_LD1(sve_ld1bss_r, cpu_ldsb_data_ra, uint32_t, int8_t, H1_4) -DO_LD1(sve_ld1bdu_r, cpu_ldub_data_ra, uint64_t, uint8_t, ) -DO_LD1(sve_ld1bds_r, cpu_ldsb_data_ra, uint64_t, int8_t, ) +/* + * The result of tlb_vaddr_to_host for user-only is just g2h(x), + * which is always non-null. Elide the useless test. + */ +static inline bool test_host_page(void *host) +{ +#ifdef CONFIG_USER_ONLY + return true; +#else + return likely(host != NULL); +#endif +} -DO_LD1(sve_ld1hsu_r, cpu_lduw_data_ra, uint32_t, uint16_t, H1_4) -DO_LD1(sve_ld1hss_r, cpu_ldsw_data_ra, uint32_t, int16_t, H1_4) -DO_LD1(sve_ld1hdu_r, cpu_lduw_data_ra, uint64_t, uint16_t, ) -DO_LD1(sve_ld1hds_r, cpu_ldsw_data_ra, uint64_t, int16_t, ) +/* + * Common helper for all contiguous one-register predicated loads. + */ +static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr, + uint32_t desc, const uintptr_t retaddr, + const int esz, const int msz, + sve_ld1_host_fn *host_fn, + sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + void *vd = &env->vfp.zregs[rd]; + const int diffsz = esz - msz; + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t mem_max = reg_max >> diffsz; + ARMVectorReg scratch; + void *host; + intptr_t split, reg_off, mem_off; + + /* Find the first active element. */ + reg_off = find_next_active(vg, 0, reg_max, esz); + if (unlikely(reg_off == reg_max)) { + /* The entire predicate was false; no load occurs. */ + memset(vd, 0, reg_max); + return; + } + mem_off = reg_off >> diffsz; + set_helper_retaddr(retaddr); + + /* + * If the (remaining) load is entirely within a single page, then: + * For softmmu, and the tlb hits, then no faults will occur; + * For user-only, either the first load will fault or none will. + * We can thus perform the load directly to the destination and + * Vd will be unmodified on any exception path. + */ + split = max_for_page(addr, mem_off, mem_max); + if (likely(split == mem_max)) { + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + if (test_host_page(host)) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max); + tcg_debug_assert(mem_off == mem_max); + set_helper_retaddr(0); + /* After having taken any fault, zero leading inactive elements. */ + swap_memzero(vd, reg_off); + return; + } + } -DO_LD1(sve_ld1sdu_r, cpu_ldl_data_ra, uint64_t, uint32_t, ) -DO_LD1(sve_ld1sds_r, cpu_ldl_data_ra, uint64_t, int32_t, ) + /* + * Perform the predicated read into a temporary, thus ensuring + * if the load of the last element faults, Vd is not modified. + */ +#ifdef CONFIG_USER_ONLY + swap_memzero(&scratch, reg_off); + host_fn(&scratch, vg, g2h(addr), mem_off, mem_max); +#else + memset(&scratch, 0, reg_max); + goto start; + while (1) { + reg_off = find_next_active(vg, reg_off, reg_max, esz); + if (reg_off >= reg_max) { + break; + } + mem_off = reg_off >> diffsz; + split = max_for_page(addr, mem_off, mem_max); + + start: + if (split - mem_off >= (1 << msz)) { + /* At least one whole element on this page. */ + host = tlb_vaddr_to_host(env, addr + mem_off, + MMU_DATA_LOAD, mmu_idx); + if (host) { + mem_off = host_fn(&scratch, vg, host - mem_off, + mem_off, split); + reg_off = mem_off << diffsz; + continue; + } + } -DO_LD1(sve_ld1bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LD2(sve_ld2bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LD3(sve_ld3bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LD4(sve_ld4bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) + /* + * Perform one normal read. This may fault, longjmping out to the + * main loop in order to raise an exception. It may succeed, and + * as a side-effect load the TLB entry for the next round. Finally, + * in the extremely unlikely case we're performing this operation + * on I/O memory, it may succeed but not bring in the TLB entry. + * But even then we have still made forward progress. + */ + tlb_fn(env, &scratch, reg_off, addr + mem_off, oi, retaddr); + reg_off += 1 << esz; + } +#endif -DO_LD1(sve_ld1hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LD2(sve_ld2hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LD3(sve_ld3hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LD4(sve_ld4hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) + set_helper_retaddr(0); + memcpy(vd, &scratch, reg_max); +} -DO_LD1(sve_ld1ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LD2(sve_ld2ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LD3(sve_ld3ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LD4(sve_ld4ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) +#define DO_LD1_1(NAME, ESZ) \ +void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, 0, \ + sve_##NAME##_host, sve_##NAME##_tlb); \ +} + +#define DO_LD1_2(NAME, ESZ, MSZ) \ +void HELPER(sve_##NAME##_le_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ +} \ +void HELPER(sve_##NAME##_be_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ +} + +DO_LD1_1(ld1bb, 0) +DO_LD1_1(ld1bhu, 1) +DO_LD1_1(ld1bhs, 1) +DO_LD1_1(ld1bsu, 2) +DO_LD1_1(ld1bss, 2) +DO_LD1_1(ld1bdu, 3) +DO_LD1_1(ld1bds, 3) -DO_LD1(sve_ld1dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) -DO_LD2(sve_ld2dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) -DO_LD3(sve_ld3dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) -DO_LD4(sve_ld4dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) +DO_LD1_2(ld1hh, 1, 1) +DO_LD1_2(ld1hsu, 2, 1) +DO_LD1_2(ld1hss, 2, 1) +DO_LD1_2(ld1hdu, 3, 1) +DO_LD1_2(ld1hds, 3, 1) -#undef DO_LD1 -#undef DO_LD2 -#undef DO_LD3 -#undef DO_LD4 +DO_LD1_2(ld1ss, 2, 2) +DO_LD1_2(ld1sdu, 3, 2) +DO_LD1_2(ld1sds, 3, 2) + +DO_LD1_2(ld1dd, 3, 3) + +#undef DO_LD1_1 +#undef DO_LD1_2 /* - * Load contiguous data, first-fault and no-fault. + * Common helpers for all contiguous 2,3,4-register predicated loads. */ +static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, int size, uintptr_t ra, + sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + ARMVectorReg scratch[2] = { }; -#ifdef CONFIG_USER_ONLY + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, &scratch[0], i, addr, oi, ra); + tlb_fn(env, &scratch[1], i, addr + size, oi, ra); + } + i += size, pg >>= size; + addr += 2 * size; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz); + memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz); +} + +static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, int size, uintptr_t ra, + sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + ARMVectorReg scratch[3] = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, &scratch[0], i, addr, oi, ra); + tlb_fn(env, &scratch[1], i, addr + size, oi, ra); + tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra); + } + i += size, pg >>= size; + addr += 3 * size; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz); + memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz); + memcpy(&env->vfp.zregs[(rd + 2) & 31], &scratch[2], oprsz); +} + +static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, int size, uintptr_t ra, + sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + ARMVectorReg scratch[4] = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, &scratch[0], i, addr, oi, ra); + tlb_fn(env, &scratch[1], i, addr + size, oi, ra); + tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra); + tlb_fn(env, &scratch[3], i, addr + 3 * size, oi, ra); + } + i += size, pg >>= size; + addr += 4 * size; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz); + memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz); + memcpy(&env->vfp.zregs[(rd + 2) & 31], &scratch[2], oprsz); + memcpy(&env->vfp.zregs[(rd + 3) & 31], &scratch[3], oprsz); +} + +#define DO_LDN_1(N) \ +void __attribute__((flatten)) HELPER(sve_ld##N##bb_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_ld##N##_r(env, vg, addr, desc, 1, GETPC(), sve_ld1bb_tlb); \ +} + +#define DO_LDN_2(N, SUFF, SIZE) \ +void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_le_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \ + sve_ld1##SUFF##_le_tlb); \ +} \ +void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_be_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \ + sve_ld1##SUFF##_be_tlb); \ +} + +DO_LDN_1(2) +DO_LDN_1(3) +DO_LDN_1(4) + +DO_LDN_2(2, hh, 2) +DO_LDN_2(3, hh, 2) +DO_LDN_2(4, hh, 2) + +DO_LDN_2(2, ss, 4) +DO_LDN_2(3, ss, 4) +DO_LDN_2(4, ss, 4) + +DO_LDN_2(2, dd, 8) +DO_LDN_2(3, dd, 8) +DO_LDN_2(4, dd, 8) + +#undef DO_LDN_1 +#undef DO_LDN_2 + +/* + * Load contiguous data, first-fault and no-fault. + * + * For user-only, one could argue that we should hold the mmap_lock during + * the operation so that there is no race between page_check_range and the + * load operation. However, unmapping pages out from under a running thread + * is extraordinarily unlikely. This theoretical race condition also affects + * linux-user/ in its get_user/put_user macros. + * + * TODO: Construct some helpers, written in assembly, that interact with + * handle_cpu_signal to produce memory ops which can properly report errors + * without racing. + */ /* Fault on byte I. All bits in FFR from I are cleared. The vector * result from I is CONSTRAINED UNPREDICTABLE; we choose the MERGE @@ -4100,573 +4452,932 @@ static void record_fault(CPUARMState *env, uintptr_t i, uintptr_t oprsz) } } -/* Hold the mmap lock during the operation so that there is no race - * between page_check_range and the load operation. We expect the - * usual case to have no faults at all, so we check the whole range - * first and if successful defer to the normal load operation. - * - * TODO: Change mmap_lock to a rwlock so that multiple readers - * can run simultaneously. This will probably help other uses - * within QEMU as well. +/* + * Common helper for all contiguous first-fault loads. */ -#define DO_LDFF1(PART, FN, TYPEE, TYPEM, H) \ -static void do_sve_ldff1##PART(CPUARMState *env, void *vd, void *vg, \ - target_ulong addr, intptr_t oprsz, \ - bool first, uintptr_t ra) \ -{ \ - intptr_t i = 0; \ - do { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - if (!first && \ - unlikely(page_check_range(addr, sizeof(TYPEM), \ - PAGE_READ))) { \ - record_fault(env, i, oprsz); \ - return; \ - } \ - m = FN(env, addr, ra); \ - first = false; \ - } \ - *(TYPEE *)(vd + H(i)) = m; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += sizeof(TYPEM); \ - } while (i & 15); \ - } while (i < oprsz); \ -} \ -void HELPER(sve_ldff1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t oprsz = simd_oprsz(desc); \ - unsigned rd = simd_data(desc); \ - void *vd = &env->vfp.zregs[rd]; \ - mmap_lock(); \ - if (likely(page_check_range(addr, oprsz, PAGE_READ) == 0)) { \ - do_sve_ld1##PART(env, vd, vg, addr, oprsz, GETPC()); \ - } else { \ - do_sve_ldff1##PART(env, vd, vg, addr, oprsz, true, GETPC()); \ - } \ - mmap_unlock(); \ -} +static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr, + uint32_t desc, const uintptr_t retaddr, + const int esz, const int msz, + sve_ld1_host_fn *host_fn, + sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + void *vd = &env->vfp.zregs[rd]; + const int diffsz = esz - msz; + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t mem_max = reg_max >> diffsz; + intptr_t split, reg_off, mem_off; + void *host; + + /* Skip to the first active element. */ + reg_off = find_next_active(vg, 0, reg_max, esz); + if (unlikely(reg_off == reg_max)) { + /* The entire predicate was false; no load occurs. */ + memset(vd, 0, reg_max); + return; + } + mem_off = reg_off >> diffsz; + set_helper_retaddr(retaddr); + + /* + * If the (remaining) load is entirely within a single page, then: + * For softmmu, and the tlb hits, then no faults will occur; + * For user-only, either the first load will fault or none will. + * We can thus perform the load directly to the destination and + * Vd will be unmodified on any exception path. + */ + split = max_for_page(addr, mem_off, mem_max); + if (likely(split == mem_max)) { + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + if (test_host_page(host)) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max); + tcg_debug_assert(mem_off == mem_max); + set_helper_retaddr(0); + /* After any fault, zero any leading inactive elements. */ + swap_memzero(vd, reg_off); + return; + } + } -/* No-fault loads are like first-fault loads without the - * first faulting special case. - */ -#define DO_LDNF1(PART) \ -void HELPER(sve_ldnf1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t oprsz = simd_oprsz(desc); \ - unsigned rd = simd_data(desc); \ - void *vd = &env->vfp.zregs[rd]; \ - mmap_lock(); \ - if (likely(page_check_range(addr, oprsz, PAGE_READ) == 0)) { \ - do_sve_ld1##PART(env, vd, vg, addr, oprsz, GETPC()); \ - } else { \ - do_sve_ldff1##PART(env, vd, vg, addr, oprsz, false, GETPC()); \ - } \ - mmap_unlock(); \ -} +#ifdef CONFIG_USER_ONLY + /* + * The page(s) containing this first element at ADDR+MEM_OFF must + * be valid. Considering that this first element may be misaligned + * and cross a page boundary itself, take the rest of the page from + * the last byte of the element. + */ + split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max); + mem_off = host_fn(vd, vg, g2h(addr), mem_off, split); + /* After any fault, zero any leading inactive elements. */ + swap_memzero(vd, reg_off); + reg_off = mem_off << diffsz; #else + /* + * Perform one normal read, which will fault or not. + * But it is likely to bring the page into the tlb. + */ + tlb_fn(env, vd, reg_off, addr + mem_off, oi, retaddr); + + /* After any fault, zero any leading predicated false elts. */ + swap_memzero(vd, reg_off); + mem_off += 1 << msz; + reg_off += 1 << esz; + + /* Try again to read the balance of the page. */ + split = max_for_page(addr, mem_off - 1, mem_max); + if (split >= (1 << msz)) { + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + if (host) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, split); + reg_off = mem_off << diffsz; + } + } +#endif -/* TODO: System mode is not yet supported. - * This would probably use tlb_vaddr_to_host. - */ -#define DO_LDFF1(PART, FN, TYPEE, TYPEM, H) \ -void HELPER(sve_ldff1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - g_assert_not_reached(); \ + set_helper_retaddr(0); + record_fault(env, reg_off, reg_max); } -#define DO_LDNF1(PART) \ -void HELPER(sve_ldnf1##PART)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - g_assert_not_reached(); \ -} +/* + * Common helper for all contiguous no-fault loads. + */ +static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr, + uint32_t desc, const int esz, const int msz, + sve_ld1_host_fn *host_fn) +{ + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + void *vd = &env->vfp.zregs[rd]; + const int diffsz = esz - msz; + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t mem_max = reg_max >> diffsz; + const int mmu_idx = cpu_mmu_index(env, false); + intptr_t split, reg_off, mem_off; + void *host; +#ifdef CONFIG_USER_ONLY + host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx); + if (likely(page_check_range(addr, mem_max, PAGE_READ) == 0)) { + /* The entire operation is valid and will not fault. */ + host_fn(vd, vg, host, 0, mem_max); + return; + } #endif -DO_LDFF1(bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) -DO_LDFF1(bhu_r, cpu_ldub_data_ra, uint16_t, uint8_t, H1_2) -DO_LDFF1(bhs_r, cpu_ldsb_data_ra, uint16_t, int8_t, H1_2) -DO_LDFF1(bsu_r, cpu_ldub_data_ra, uint32_t, uint8_t, H1_4) -DO_LDFF1(bss_r, cpu_ldsb_data_ra, uint32_t, int8_t, H1_4) -DO_LDFF1(bdu_r, cpu_ldub_data_ra, uint64_t, uint8_t, ) -DO_LDFF1(bds_r, cpu_ldsb_data_ra, uint64_t, int8_t, ) + /* There will be no fault, so we may modify in advance. */ + memset(vd, 0, reg_max); -DO_LDFF1(hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) -DO_LDFF1(hsu_r, cpu_lduw_data_ra, uint32_t, uint16_t, H1_4) -DO_LDFF1(hss_r, cpu_ldsw_data_ra, uint32_t, int8_t, H1_4) -DO_LDFF1(hdu_r, cpu_lduw_data_ra, uint64_t, uint16_t, ) -DO_LDFF1(hds_r, cpu_ldsw_data_ra, uint64_t, int16_t, ) + /* Skip to the first active element. */ + reg_off = find_next_active(vg, 0, reg_max, esz); + if (unlikely(reg_off == reg_max)) { + /* The entire predicate was false; no load occurs. */ + return; + } + mem_off = reg_off >> diffsz; -DO_LDFF1(ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) -DO_LDFF1(sdu_r, cpu_ldl_data_ra, uint64_t, uint32_t, ) -DO_LDFF1(sds_r, cpu_ldl_data_ra, uint64_t, int32_t, ) +#ifdef CONFIG_USER_ONLY + if (page_check_range(addr + mem_off, 1 << msz, PAGE_READ) == 0) { + /* At least one load is valid; take the rest of the page. */ + split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max); + mem_off = host_fn(vd, vg, host, mem_off, split); + reg_off = mem_off << diffsz; + } +#else + /* + * If the address is not in the TLB, we have no way to bring the + * entry into the TLB without also risking a fault. Note that + * the corollary is that we never load from an address not in RAM. + * + * This last is out of spec, in a weird corner case. + * Per the MemNF/MemSingleNF pseudocode, a NF load from Device memory + * must not actually hit the bus -- it returns UNKNOWN data instead. + * But if you map non-RAM with Normal memory attributes and do a NF + * load then it should access the bus. (Nobody ought actually do this + * in the real world, obviously.) + * + * Then there are the annoying special cases with watchpoints... + * + * TODO: Add a form of tlb_fill that does not raise an exception, + * with a form of tlb_vaddr_to_host and a set of loads to match. + * The non_fault_vaddr_to_host would handle everything, usually, + * and the loads would handle the iomem path for watchpoints. + */ + host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx); + split = max_for_page(addr, mem_off, mem_max); + if (host && split >= (1 << msz)) { + mem_off = host_fn(vd, vg, host - mem_off, mem_off, split); + reg_off = mem_off << diffsz; + } +#endif -DO_LDFF1(dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) + record_fault(env, reg_off, reg_max); +} -#undef DO_LDFF1 +#define DO_LDFF1_LDNF1_1(PART, ESZ) \ +void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, 0, \ + sve_ld1##PART##_host, sve_ld1##PART##_tlb); \ +} \ +void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, 0, sve_ld1##PART##_host); \ +} -DO_LDNF1(bb_r) -DO_LDNF1(bhu_r) -DO_LDNF1(bhs_r) -DO_LDNF1(bsu_r) -DO_LDNF1(bss_r) -DO_LDNF1(bdu_r) -DO_LDNF1(bds_r) +#define DO_LDFF1_LDNF1_2(PART, ESZ, MSZ) \ +void HELPER(sve_ldff1##PART##_le_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ +} \ +void HELPER(sve_ldnf1##PART##_le_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_le_host); \ +} \ +void HELPER(sve_ldff1##PART##_be_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \ + sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ +} \ +void HELPER(sve_ldnf1##PART##_be_r)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_be_host); \ +} + +DO_LDFF1_LDNF1_1(bb, 0) +DO_LDFF1_LDNF1_1(bhu, 1) +DO_LDFF1_LDNF1_1(bhs, 1) +DO_LDFF1_LDNF1_1(bsu, 2) +DO_LDFF1_LDNF1_1(bss, 2) +DO_LDFF1_LDNF1_1(bdu, 3) +DO_LDFF1_LDNF1_1(bds, 3) -DO_LDNF1(hh_r) -DO_LDNF1(hsu_r) -DO_LDNF1(hss_r) -DO_LDNF1(hdu_r) -DO_LDNF1(hds_r) +DO_LDFF1_LDNF1_2(hh, 1, 1) +DO_LDFF1_LDNF1_2(hsu, 2, 1) +DO_LDFF1_LDNF1_2(hss, 2, 1) +DO_LDFF1_LDNF1_2(hdu, 3, 1) +DO_LDFF1_LDNF1_2(hds, 3, 1) -DO_LDNF1(ss_r) -DO_LDNF1(sdu_r) -DO_LDNF1(sds_r) +DO_LDFF1_LDNF1_2(ss, 2, 2) +DO_LDFF1_LDNF1_2(sdu, 3, 2) +DO_LDFF1_LDNF1_2(sds, 3, 2) -DO_LDNF1(dd_r) +DO_LDFF1_LDNF1_2(dd, 3, 3) -#undef DO_LDNF1 +#undef DO_LDFF1_LDNF1_1 +#undef DO_LDFF1_LDNF1_2 /* * Store contiguous data, protected by a governing predicate. */ -#define DO_ST1(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *vd = &env->vfp.zregs[rd]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m = *(TYPEE *)(vd + H(i)); \ - FN(env, addr, m, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += sizeof(TYPEM); \ - } while (i & 15); \ - } \ -} -#define DO_ST1_D(NAME, FN, TYPEM) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc) / 8; \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - uint64_t *d = &env->vfp.zregs[rd].d[0]; \ - uint8_t *pg = vg; \ - for (i = 0; i < oprsz; i += 1) { \ - if (pg[H1(i)] & 1) { \ - FN(env, addr, d[i], ra); \ - } \ - addr += sizeof(TYPEM); \ - } \ +#ifdef CONFIG_SOFTMMU +#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ +{ \ + TLB(env, addr, *(TYPEM *)(vd + H(reg_off)), oi, ra); \ } - -#define DO_ST2(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ - TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ - FN(env, addr, m1, ra); \ - FN(env, addr + sizeof(TYPEM), m2, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 2 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ +#else +#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \ +static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \ +{ \ + HOST(g2h(addr), *(TYPEM *)(vd + H(reg_off))); \ } +#endif -#define DO_ST3(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ - TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ - TYPEM m3 = *(TYPEE *)(d3 + H(i)); \ - FN(env, addr, m1, ra); \ - FN(env, addr + sizeof(TYPEM), m2, ra); \ - FN(env, addr + 2 * sizeof(TYPEM), m3, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 3 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ -} +DO_ST_TLB(st1bb, H1, uint8_t, stb_p, 0, helper_ret_stb_mmu) +DO_ST_TLB(st1bh, H1_2, uint16_t, stb_p, 0, helper_ret_stb_mmu) +DO_ST_TLB(st1bs, H1_4, uint32_t, stb_p, 0, helper_ret_stb_mmu) +DO_ST_TLB(st1bd, , uint64_t, stb_p, 0, helper_ret_stb_mmu) -#define DO_ST4(NAME, FN, TYPEE, TYPEM, H) \ -void HELPER(NAME)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - intptr_t ra = GETPC(); \ - unsigned rd = simd_data(desc); \ - void *d1 = &env->vfp.zregs[rd]; \ - void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ - void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ - void *d4 = &env->vfp.zregs[(rd + 3) & 31]; \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (pg & 1) { \ - TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ - TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ - TYPEM m3 = *(TYPEE *)(d3 + H(i)); \ - TYPEM m4 = *(TYPEE *)(d4 + H(i)); \ - FN(env, addr, m1, ra); \ - FN(env, addr + sizeof(TYPEM), m2, ra); \ - FN(env, addr + 2 * sizeof(TYPEM), m3, ra); \ - FN(env, addr + 3 * sizeof(TYPEM), m4, ra); \ - } \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - addr += 4 * sizeof(TYPEM); \ - } while (i & 15); \ - } \ -} +DO_ST_TLB(st1hh_le, H1_2, uint16_t, stw_le_p, MO_LE, helper_le_stw_mmu) +DO_ST_TLB(st1hs_le, H1_4, uint32_t, stw_le_p, MO_LE, helper_le_stw_mmu) +DO_ST_TLB(st1hd_le, , uint64_t, stw_le_p, MO_LE, helper_le_stw_mmu) -DO_ST1(sve_st1bh_r, cpu_stb_data_ra, uint16_t, uint8_t, H1_2) -DO_ST1(sve_st1bs_r, cpu_stb_data_ra, uint32_t, uint8_t, H1_4) -DO_ST1_D(sve_st1bd_r, cpu_stb_data_ra, uint8_t) +DO_ST_TLB(st1ss_le, H1_4, uint32_t, stl_le_p, MO_LE, helper_le_stl_mmu) +DO_ST_TLB(st1sd_le, , uint64_t, stl_le_p, MO_LE, helper_le_stl_mmu) -DO_ST1(sve_st1hs_r, cpu_stw_data_ra, uint32_t, uint16_t, H1_4) -DO_ST1_D(sve_st1hd_r, cpu_stw_data_ra, uint16_t) +DO_ST_TLB(st1dd_le, , uint64_t, stq_le_p, MO_LE, helper_le_stq_mmu) -DO_ST1_D(sve_st1sd_r, cpu_stl_data_ra, uint32_t) +DO_ST_TLB(st1hh_be, H1_2, uint16_t, stw_be_p, MO_BE, helper_be_stw_mmu) +DO_ST_TLB(st1hs_be, H1_4, uint32_t, stw_be_p, MO_BE, helper_be_stw_mmu) +DO_ST_TLB(st1hd_be, , uint64_t, stw_be_p, MO_BE, helper_be_stw_mmu) -DO_ST1(sve_st1bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) -DO_ST2(sve_st2bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) -DO_ST3(sve_st3bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) -DO_ST4(sve_st4bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) +DO_ST_TLB(st1ss_be, H1_4, uint32_t, stl_be_p, MO_BE, helper_be_stl_mmu) +DO_ST_TLB(st1sd_be, , uint64_t, stl_be_p, MO_BE, helper_be_stl_mmu) -DO_ST1(sve_st1hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) -DO_ST2(sve_st2hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) -DO_ST3(sve_st3hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) -DO_ST4(sve_st4hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) +DO_ST_TLB(st1dd_be, , uint64_t, stq_be_p, MO_BE, helper_be_stq_mmu) -DO_ST1(sve_st1ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) -DO_ST2(sve_st2ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) -DO_ST3(sve_st3ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) -DO_ST4(sve_st4ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) +#undef DO_ST_TLB -DO_ST1_D(sve_st1dd_r, cpu_stq_data_ra, uint64_t) +/* + * Common helpers for all contiguous 1,2,3,4-register predicated stores. + */ +static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + void *vd = &env->vfp.zregs[rd]; -void HELPER(sve_st2dd_r)(CPUARMState *env, void *vg, - target_ulong addr, uint32_t desc) + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, vd, i, addr, oi, ra); + } + i += esize, pg >>= esize; + addr += msize; + } while (i & 15); + } + set_helper_retaddr(0); +} + +static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) { - intptr_t i, oprsz = simd_oprsz(desc) / 8; - intptr_t ra = GETPC(); - unsigned rd = simd_data(desc); - uint64_t *d1 = &env->vfp.zregs[rd].d[0]; - uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; - uint8_t *pg = vg; + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + void *d1 = &env->vfp.zregs[rd]; + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; - for (i = 0; i < oprsz; i += 1) { - if (pg[H1(i)] & 1) { - cpu_stq_data_ra(env, addr, d1[i], ra); - cpu_stq_data_ra(env, addr + 8, d2[i], ra); - } - addr += 2 * 8; + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, d1, i, addr, oi, ra); + tlb_fn(env, d2, i, addr + msize, oi, ra); + } + i += esize, pg >>= esize; + addr += 2 * msize; + } while (i & 15); } + set_helper_retaddr(0); } -void HELPER(sve_st3dd_r)(CPUARMState *env, void *vg, - target_ulong addr, uint32_t desc) +static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) { - intptr_t i, oprsz = simd_oprsz(desc) / 8; - intptr_t ra = GETPC(); - unsigned rd = simd_data(desc); - uint64_t *d1 = &env->vfp.zregs[rd].d[0]; - uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; - uint64_t *d3 = &env->vfp.zregs[(rd + 2) & 31].d[0]; - uint8_t *pg = vg; + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + void *d1 = &env->vfp.zregs[rd]; + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; - for (i = 0; i < oprsz; i += 1) { - if (pg[H1(i)] & 1) { - cpu_stq_data_ra(env, addr, d1[i], ra); - cpu_stq_data_ra(env, addr + 8, d2[i], ra); - cpu_stq_data_ra(env, addr + 16, d3[i], ra); - } - addr += 3 * 8; + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, d1, i, addr, oi, ra); + tlb_fn(env, d2, i, addr + msize, oi, ra); + tlb_fn(env, d3, i, addr + 2 * msize, oi, ra); + } + i += esize, pg >>= esize; + addr += 3 * msize; + } while (i & 15); } + set_helper_retaddr(0); } -void HELPER(sve_st4dd_r)(CPUARMState *env, void *vg, - target_ulong addr, uint32_t desc) +static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr, + uint32_t desc, const uintptr_t ra, + const int esize, const int msize, + sve_st1_tlb_fn *tlb_fn) { - intptr_t i, oprsz = simd_oprsz(desc) / 8; - intptr_t ra = GETPC(); - unsigned rd = simd_data(desc); - uint64_t *d1 = &env->vfp.zregs[rd].d[0]; - uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; - uint64_t *d3 = &env->vfp.zregs[(rd + 2) & 31].d[0]; - uint64_t *d4 = &env->vfp.zregs[(rd + 3) & 31].d[0]; - uint8_t *pg = vg; + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5); + intptr_t i, oprsz = simd_oprsz(desc); + void *d1 = &env->vfp.zregs[rd]; + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; + void *d4 = &env->vfp.zregs[(rd + 3) & 31]; - for (i = 0; i < oprsz; i += 1) { - if (pg[H1(i)] & 1) { - cpu_stq_data_ra(env, addr, d1[i], ra); - cpu_stq_data_ra(env, addr + 8, d2[i], ra); - cpu_stq_data_ra(env, addr + 16, d3[i], ra); - cpu_stq_data_ra(env, addr + 24, d4[i], ra); - } - addr += 4 * 8; + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + tlb_fn(env, d1, i, addr, oi, ra); + tlb_fn(env, d2, i, addr + msize, oi, ra); + tlb_fn(env, d3, i, addr + 2 * msize, oi, ra); + tlb_fn(env, d4, i, addr + 3 * msize, oi, ra); + } + i += esize, pg >>= esize; + addr += 4 * msize; + } while (i & 15); } + set_helper_retaddr(0); } -/* Loads with a vector index. */ +#define DO_STN_1(N, NAME, ESIZE) \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, 1, \ + sve_st1##NAME##_tlb); \ +} -#define DO_LD1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - target_ulong off = *(TYPEI *)(vm + H1_4(i)); \ - m = FN(env, base + (off << scale), ra); \ - } \ - *(uint32_t *)(vd + H1_4(i)) = m; \ - i += 4, pg >>= 4; \ - } while (i & 15); \ - } \ +#define DO_STN_2(N, NAME, ESIZE, MSIZE) \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_le_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE, \ + sve_st1##NAME##_le_tlb); \ +} \ +void __attribute__((flatten)) HELPER(sve_st##N##NAME##_be_r) \ + (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \ +{ \ + sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE, \ + sve_st1##NAME##_be_tlb); \ +} + +DO_STN_1(1, bb, 1) +DO_STN_1(1, bh, 2) +DO_STN_1(1, bs, 4) +DO_STN_1(1, bd, 8) +DO_STN_1(2, bb, 1) +DO_STN_1(3, bb, 1) +DO_STN_1(4, bb, 1) + +DO_STN_2(1, hh, 2, 2) +DO_STN_2(1, hs, 4, 2) +DO_STN_2(1, hd, 8, 2) +DO_STN_2(2, hh, 2, 2) +DO_STN_2(3, hh, 2, 2) +DO_STN_2(4, hh, 2, 2) + +DO_STN_2(1, ss, 4, 4) +DO_STN_2(1, sd, 8, 4) +DO_STN_2(2, ss, 4, 4) +DO_STN_2(3, ss, 4, 4) +DO_STN_2(4, ss, 4, 4) + +DO_STN_2(1, dd, 8, 8) +DO_STN_2(2, dd, 8, 8) +DO_STN_2(3, dd, 8, 8) +DO_STN_2(4, dd, 8, 8) + +#undef DO_STN_1 +#undef DO_STN_2 + +/* + * Loads with a vector index. + */ + +/* + * Load the element at @reg + @reg_ofs, sign or zero-extend as needed. + */ +typedef target_ulong zreg_off_fn(void *reg, intptr_t reg_ofs); + +static target_ulong off_zsu_s(void *reg, intptr_t reg_ofs) +{ + return *(uint32_t *)(reg + H1_4(reg_ofs)); } -#define DO_LD1_ZPZ_D(NAME, TYPEI, TYPEM, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc) / 8; \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \ - for (i = 0; i < oprsz; i++) { \ - TYPEM mm = 0; \ - if (pg[H1(i)] & 1) { \ - target_ulong off = (TYPEI)m[i]; \ - mm = FN(env, base + (off << scale), ra); \ - } \ - d[i] = mm; \ - } \ +static target_ulong off_zss_s(void *reg, intptr_t reg_ofs) +{ + return *(int32_t *)(reg + H1_4(reg_ofs)); } -DO_LD1_ZPZ_S(sve_ldbsu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhsu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_S(sve_ldssu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_S(sve_ldbss_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhss_zsu, uint32_t, int16_t, cpu_lduw_data_ra) - -DO_LD1_ZPZ_S(sve_ldbsu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhsu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_S(sve_ldssu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_S(sve_ldbss_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_S(sve_ldhss_zss, int32_t, int16_t, cpu_lduw_data_ra) - -DO_LD1_ZPZ_D(sve_ldbdu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhdu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsdu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_D(sve_ldddu_zsu, uint32_t, uint64_t, cpu_ldq_data_ra) -DO_LD1_ZPZ_D(sve_ldbds_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhds_zsu, uint32_t, int16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsds_zsu, uint32_t, int32_t, cpu_ldl_data_ra) - -DO_LD1_ZPZ_D(sve_ldbdu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhdu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsdu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_D(sve_ldddu_zss, int32_t, uint64_t, cpu_ldq_data_ra) -DO_LD1_ZPZ_D(sve_ldbds_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhds_zss, int32_t, int16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsds_zss, int32_t, int32_t, cpu_ldl_data_ra) - -DO_LD1_ZPZ_D(sve_ldbdu_zd, uint64_t, uint8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhdu_zd, uint64_t, uint16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsdu_zd, uint64_t, uint32_t, cpu_ldl_data_ra) -DO_LD1_ZPZ_D(sve_ldddu_zd, uint64_t, uint64_t, cpu_ldq_data_ra) -DO_LD1_ZPZ_D(sve_ldbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) -DO_LD1_ZPZ_D(sve_ldhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) -DO_LD1_ZPZ_D(sve_ldsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) +static target_ulong off_zsu_d(void *reg, intptr_t reg_ofs) +{ + return (uint32_t)*(uint64_t *)(reg + reg_ofs); +} -/* First fault loads with a vector index. */ +static target_ulong off_zss_d(void *reg, intptr_t reg_ofs) +{ + return (int32_t)*(uint64_t *)(reg + reg_ofs); +} -#ifdef CONFIG_USER_ONLY +static target_ulong off_zd_d(void *reg, intptr_t reg_ofs) +{ + return *(uint64_t *)(reg + reg_ofs); +} -#define DO_LDFF1_ZPZ(NAME, TYPEE, TYPEI, TYPEM, FN, H) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - intptr_t i, oprsz = simd_oprsz(desc); \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - bool first = true; \ - mmap_lock(); \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - TYPEM m = 0; \ - if (pg & 1) { \ - target_ulong off = *(TYPEI *)(vm + H(i)); \ - target_ulong addr = base + (off << scale); \ - if (!first && \ - page_check_range(addr, sizeof(TYPEM), PAGE_READ)) { \ - record_fault(env, i, oprsz); \ - goto exit; \ - } \ - m = FN(env, addr, ra); \ - first = false; \ - } \ - *(TYPEE *)(vd + H(i)) = m; \ - i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ - } while (i & 15); \ - } \ - exit: \ - mmap_unlock(); \ +static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); + intptr_t i, oprsz = simd_oprsz(desc); + ARMVectorReg scratch = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i); + tlb_fn(env, &scratch, i, base + (off << scale), oi, ra); + } + i += 4, pg >>= 4; + } while (i & 15); + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(vd, &scratch, oprsz); } +static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); + intptr_t i, oprsz = simd_oprsz(desc) / 8; + ARMVectorReg scratch = { }; + + set_helper_retaddr(ra); + for (i = 0; i < oprsz; i++) { + uint8_t pg = *(uint8_t *)(vg + H1(i)); + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i * 8); + tlb_fn(env, &scratch, i * 8, base + (off << scale), oi, ra); + } + } + set_helper_retaddr(0); + + /* Wait until all exceptions have been raised to write back. */ + memcpy(vd, &scratch, oprsz * 8); +} + +#define DO_LD1_ZPZ_S(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_ld##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_ld1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_ld1##MEM##_tlb); \ +} + +#define DO_LD1_ZPZ_D(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_ld##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_ld1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_ld1##MEM##_tlb); \ +} + +DO_LD1_ZPZ_S(bsu, zsu) +DO_LD1_ZPZ_S(bsu, zss) +DO_LD1_ZPZ_D(bdu, zsu) +DO_LD1_ZPZ_D(bdu, zss) +DO_LD1_ZPZ_D(bdu, zd) + +DO_LD1_ZPZ_S(bss, zsu) +DO_LD1_ZPZ_S(bss, zss) +DO_LD1_ZPZ_D(bds, zsu) +DO_LD1_ZPZ_D(bds, zss) +DO_LD1_ZPZ_D(bds, zd) + +DO_LD1_ZPZ_S(hsu_le, zsu) +DO_LD1_ZPZ_S(hsu_le, zss) +DO_LD1_ZPZ_D(hdu_le, zsu) +DO_LD1_ZPZ_D(hdu_le, zss) +DO_LD1_ZPZ_D(hdu_le, zd) + +DO_LD1_ZPZ_S(hsu_be, zsu) +DO_LD1_ZPZ_S(hsu_be, zss) +DO_LD1_ZPZ_D(hdu_be, zsu) +DO_LD1_ZPZ_D(hdu_be, zss) +DO_LD1_ZPZ_D(hdu_be, zd) + +DO_LD1_ZPZ_S(hss_le, zsu) +DO_LD1_ZPZ_S(hss_le, zss) +DO_LD1_ZPZ_D(hds_le, zsu) +DO_LD1_ZPZ_D(hds_le, zss) +DO_LD1_ZPZ_D(hds_le, zd) + +DO_LD1_ZPZ_S(hss_be, zsu) +DO_LD1_ZPZ_S(hss_be, zss) +DO_LD1_ZPZ_D(hds_be, zsu) +DO_LD1_ZPZ_D(hds_be, zss) +DO_LD1_ZPZ_D(hds_be, zd) + +DO_LD1_ZPZ_S(ss_le, zsu) +DO_LD1_ZPZ_S(ss_le, zss) +DO_LD1_ZPZ_D(sdu_le, zsu) +DO_LD1_ZPZ_D(sdu_le, zss) +DO_LD1_ZPZ_D(sdu_le, zd) + +DO_LD1_ZPZ_S(ss_be, zsu) +DO_LD1_ZPZ_S(ss_be, zss) +DO_LD1_ZPZ_D(sdu_be, zsu) +DO_LD1_ZPZ_D(sdu_be, zss) +DO_LD1_ZPZ_D(sdu_be, zd) + +DO_LD1_ZPZ_D(sds_le, zsu) +DO_LD1_ZPZ_D(sds_le, zss) +DO_LD1_ZPZ_D(sds_le, zd) + +DO_LD1_ZPZ_D(sds_be, zsu) +DO_LD1_ZPZ_D(sds_be, zss) +DO_LD1_ZPZ_D(sds_be, zd) + +DO_LD1_ZPZ_D(dd_le, zsu) +DO_LD1_ZPZ_D(dd_le, zss) +DO_LD1_ZPZ_D(dd_le, zd) + +DO_LD1_ZPZ_D(dd_be, zsu) +DO_LD1_ZPZ_D(dd_be, zss) +DO_LD1_ZPZ_D(dd_be, zd) + +#undef DO_LD1_ZPZ_S +#undef DO_LD1_ZPZ_D + +/* First fault loads with a vector index. */ + +/* Load one element into VD+REG_OFF from (ENV,VADDR) without faulting. + * The controlling predicate is known to be true. Return true if the + * load was successful. + */ +typedef bool sve_ld1_nf_fn(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong vaddr, int mmu_idx); + +#ifdef CONFIG_SOFTMMU +#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \ +static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx) \ +{ \ + target_ulong next_page = -(addr | TARGET_PAGE_MASK); \ + if (likely(next_page - addr >= sizeof(TYPEM))) { \ + void *host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx); \ + if (likely(host)) { \ + TYPEM val = HOST(host); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ + return true; \ + } \ + } \ + return false; \ +} #else +#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \ +static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \ + target_ulong addr, int mmu_idx) \ +{ \ + if (likely(page_check_range(addr, sizeof(TYPEM), PAGE_READ))) { \ + TYPEM val = HOST(g2h(addr)); \ + *(TYPEE *)(vd + H(reg_off)) = val; \ + return true; \ + } \ + return false; \ +} +#endif -#define DO_LDFF1_ZPZ(NAME, TYPEE, TYPEI, TYPEM, FN, H) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ -{ \ - g_assert_not_reached(); \ +DO_LD_NF(bsu, H1_4, uint32_t, uint8_t, ldub_p) +DO_LD_NF(bss, H1_4, uint32_t, int8_t, ldsb_p) +DO_LD_NF(bdu, , uint64_t, uint8_t, ldub_p) +DO_LD_NF(bds, , uint64_t, int8_t, ldsb_p) + +DO_LD_NF(hsu_le, H1_4, uint32_t, uint16_t, lduw_le_p) +DO_LD_NF(hss_le, H1_4, uint32_t, int16_t, ldsw_le_p) +DO_LD_NF(hsu_be, H1_4, uint32_t, uint16_t, lduw_be_p) +DO_LD_NF(hss_be, H1_4, uint32_t, int16_t, ldsw_be_p) +DO_LD_NF(hdu_le, , uint64_t, uint16_t, lduw_le_p) +DO_LD_NF(hds_le, , uint64_t, int16_t, ldsw_le_p) +DO_LD_NF(hdu_be, , uint64_t, uint16_t, lduw_be_p) +DO_LD_NF(hds_be, , uint64_t, int16_t, ldsw_be_p) + +DO_LD_NF(ss_le, H1_4, uint32_t, uint32_t, ldl_le_p) +DO_LD_NF(ss_be, H1_4, uint32_t, uint32_t, ldl_be_p) +DO_LD_NF(sdu_le, , uint64_t, uint32_t, ldl_le_p) +DO_LD_NF(sds_le, , uint64_t, int32_t, ldl_le_p) +DO_LD_NF(sdu_be, , uint64_t, uint32_t, ldl_be_p) +DO_LD_NF(sds_be, , uint64_t, int32_t, ldl_be_p) + +DO_LD_NF(dd_le, , uint64_t, uint64_t, ldq_le_p) +DO_LD_NF(dd_be, , uint64_t, uint64_t, ldq_be_p) + +/* + * Common helper for all gather first-faulting loads. + */ +static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn, + sve_ld1_nf_fn *nonfault_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); + intptr_t reg_off, reg_max = simd_oprsz(desc); + target_ulong addr; + + /* Skip to the first true predicate. */ + reg_off = find_next_active(vg, 0, reg_max, MO_32); + if (likely(reg_off < reg_max)) { + /* Perform one normal read, which will fault or not. */ + set_helper_retaddr(ra); + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + tlb_fn(env, vd, reg_off, addr, oi, ra); + + /* The rest of the reads will be non-faulting. */ + set_helper_retaddr(0); + } + + /* After any fault, zero the leading predicated false elements. */ + swap_memzero(vd, reg_off); + + while (likely((reg_off += 4) < reg_max)) { + uint64_t pg = *(uint64_t *)(vg + (reg_off >> 6) * 8); + if (likely((pg >> (reg_off & 63)) & 1)) { + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + if (!nonfault_fn(env, vd, reg_off, addr, mmu_idx)) { + record_fault(env, reg_off, reg_max); + break; + } + } else { + *(uint32_t *)(vd + H1_4(reg_off)) = 0; + } + } } -#endif +static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn, + sve_ld1_nf_fn *nonfault_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int mmu_idx = get_mmuidx(oi); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); + intptr_t reg_off, reg_max = simd_oprsz(desc); + target_ulong addr; + + /* Skip to the first true predicate. */ + reg_off = find_next_active(vg, 0, reg_max, MO_64); + if (likely(reg_off < reg_max)) { + /* Perform one normal read, which will fault or not. */ + set_helper_retaddr(ra); + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + tlb_fn(env, vd, reg_off, addr, oi, ra); + + /* The rest of the reads will be non-faulting. */ + set_helper_retaddr(0); + } -#define DO_LDFF1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ - DO_LDFF1_ZPZ(NAME, uint32_t, TYPEI, TYPEM, FN, H1_4) -#define DO_LDFF1_ZPZ_D(NAME, TYPEI, TYPEM, FN) \ - DO_LDFF1_ZPZ(NAME, uint64_t, TYPEI, TYPEM, FN, ) - -DO_LDFF1_ZPZ_S(sve_ldffbsu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhsu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffssu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffbss_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhss_zsu, uint32_t, int16_t, cpu_lduw_data_ra) - -DO_LDFF1_ZPZ_S(sve_ldffbsu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhsu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffssu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffbss_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_S(sve_ldffhss_zss, int32_t, int16_t, cpu_lduw_data_ra) - -DO_LDFF1_ZPZ_D(sve_ldffbdu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhdu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsdu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffddu_zsu, uint32_t, uint64_t, cpu_ldq_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffbds_zsu, uint32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhds_zsu, uint32_t, int16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsds_zsu, uint32_t, int32_t, cpu_ldl_data_ra) - -DO_LDFF1_ZPZ_D(sve_ldffbdu_zss, int32_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhdu_zss, int32_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsdu_zss, int32_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffddu_zss, int32_t, uint64_t, cpu_ldq_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffbds_zss, int32_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhds_zss, int32_t, int16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsds_zss, int32_t, int32_t, cpu_ldl_data_ra) - -DO_LDFF1_ZPZ_D(sve_ldffbdu_zd, uint64_t, uint8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhdu_zd, uint64_t, uint16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsdu_zd, uint64_t, uint32_t, cpu_ldl_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffddu_zd, uint64_t, uint64_t, cpu_ldq_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) -DO_LDFF1_ZPZ_D(sve_ldffsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) + /* After any fault, zero the leading predicated false elements. */ + swap_memzero(vd, reg_off); -/* Stores with a vector index. */ + while (likely((reg_off += 8) < reg_max)) { + uint8_t pg = *(uint8_t *)(vg + H1(reg_off >> 3)); + if (likely(pg & 1)) { + addr = off_fn(vm, reg_off); + addr = base + (addr << scale); + if (!nonfault_fn(env, vd, reg_off, addr, mmu_idx)) { + record_fault(env, reg_off, reg_max); + break; + } + } else { + *(uint64_t *)(vd + reg_off) = 0; + } + } +} -#define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ +#define DO_LDFF1_ZPZ_S(MEM, OFS) \ +void HELPER(sve_ldff##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ { \ - intptr_t i, oprsz = simd_oprsz(desc); \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - for (i = 0; i < oprsz; ) { \ - uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ - do { \ - if (likely(pg & 1)) { \ - target_ulong off = *(TYPEI *)(vm + H1_4(i)); \ - uint32_t d = *(uint32_t *)(vd + H1_4(i)); \ - FN(env, base + (off << scale), d, ra); \ - } \ - i += sizeof(uint32_t), pg >>= sizeof(uint32_t); \ - } while (i & 15); \ - } \ + sve_ldff1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_ld1##MEM##_tlb, sve_ld##MEM##_nf); \ } -#define DO_ST1_ZPZ_D(NAME, TYPEI, FN) \ -void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ - target_ulong base, uint32_t desc) \ +#define DO_LDFF1_ZPZ_D(MEM, OFS) \ +void HELPER(sve_ldff##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ { \ - intptr_t i, oprsz = simd_oprsz(desc) / 8; \ - unsigned scale = simd_data(desc); \ - uintptr_t ra = GETPC(); \ - uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \ - for (i = 0; i < oprsz; i++) { \ - if (likely(pg[H1(i)] & 1)) { \ - target_ulong off = (target_ulong)(TYPEI)m[i] << scale; \ - FN(env, base + off, d[i], ra); \ - } \ - } \ -} + sve_ldff1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_ld1##MEM##_tlb, sve_ld##MEM##_nf); \ +} + +DO_LDFF1_ZPZ_S(bsu, zsu) +DO_LDFF1_ZPZ_S(bsu, zss) +DO_LDFF1_ZPZ_D(bdu, zsu) +DO_LDFF1_ZPZ_D(bdu, zss) +DO_LDFF1_ZPZ_D(bdu, zd) + +DO_LDFF1_ZPZ_S(bss, zsu) +DO_LDFF1_ZPZ_S(bss, zss) +DO_LDFF1_ZPZ_D(bds, zsu) +DO_LDFF1_ZPZ_D(bds, zss) +DO_LDFF1_ZPZ_D(bds, zd) + +DO_LDFF1_ZPZ_S(hsu_le, zsu) +DO_LDFF1_ZPZ_S(hsu_le, zss) +DO_LDFF1_ZPZ_D(hdu_le, zsu) +DO_LDFF1_ZPZ_D(hdu_le, zss) +DO_LDFF1_ZPZ_D(hdu_le, zd) + +DO_LDFF1_ZPZ_S(hsu_be, zsu) +DO_LDFF1_ZPZ_S(hsu_be, zss) +DO_LDFF1_ZPZ_D(hdu_be, zsu) +DO_LDFF1_ZPZ_D(hdu_be, zss) +DO_LDFF1_ZPZ_D(hdu_be, zd) + +DO_LDFF1_ZPZ_S(hss_le, zsu) +DO_LDFF1_ZPZ_S(hss_le, zss) +DO_LDFF1_ZPZ_D(hds_le, zsu) +DO_LDFF1_ZPZ_D(hds_le, zss) +DO_LDFF1_ZPZ_D(hds_le, zd) + +DO_LDFF1_ZPZ_S(hss_be, zsu) +DO_LDFF1_ZPZ_S(hss_be, zss) +DO_LDFF1_ZPZ_D(hds_be, zsu) +DO_LDFF1_ZPZ_D(hds_be, zss) +DO_LDFF1_ZPZ_D(hds_be, zd) + +DO_LDFF1_ZPZ_S(ss_le, zsu) +DO_LDFF1_ZPZ_S(ss_le, zss) +DO_LDFF1_ZPZ_D(sdu_le, zsu) +DO_LDFF1_ZPZ_D(sdu_le, zss) +DO_LDFF1_ZPZ_D(sdu_le, zd) + +DO_LDFF1_ZPZ_S(ss_be, zsu) +DO_LDFF1_ZPZ_S(ss_be, zss) +DO_LDFF1_ZPZ_D(sdu_be, zsu) +DO_LDFF1_ZPZ_D(sdu_be, zss) +DO_LDFF1_ZPZ_D(sdu_be, zd) + +DO_LDFF1_ZPZ_D(sds_le, zsu) +DO_LDFF1_ZPZ_D(sds_le, zss) +DO_LDFF1_ZPZ_D(sds_le, zd) + +DO_LDFF1_ZPZ_D(sds_be, zsu) +DO_LDFF1_ZPZ_D(sds_be, zss) +DO_LDFF1_ZPZ_D(sds_be, zd) + +DO_LDFF1_ZPZ_D(dd_le, zsu) +DO_LDFF1_ZPZ_D(dd_le, zss) +DO_LDFF1_ZPZ_D(dd_le, zd) + +DO_LDFF1_ZPZ_D(dd_be, zsu) +DO_LDFF1_ZPZ_D(dd_be, zss) +DO_LDFF1_ZPZ_D(dd_be, zd) -DO_ST1_ZPZ_S(sve_stbs_zsu, uint32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_S(sve_sths_zsu, uint32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_S(sve_stss_zsu, uint32_t, cpu_stl_data_ra) +/* Stores with a vector index. */ -DO_ST1_ZPZ_S(sve_stbs_zss, int32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_S(sve_sths_zss, int32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_S(sve_stss_zss, int32_t, cpu_stl_data_ra) +static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); + intptr_t i, oprsz = simd_oprsz(desc); -DO_ST1_ZPZ_D(sve_stbd_zsu, uint32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zsu, uint32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zsu, uint32_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zsu, uint32_t, cpu_stq_data_ra) + set_helper_retaddr(ra); + for (i = 0; i < oprsz; ) { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i); + tlb_fn(env, vd, i, base + (off << scale), oi, ra); + } + i += 4, pg >>= 4; + } while (i & 15); + } + set_helper_retaddr(0); +} -DO_ST1_ZPZ_D(sve_stbd_zss, int32_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zss, int32_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zss, int32_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zss, int32_t, cpu_stq_data_ra) +static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm, + target_ulong base, uint32_t desc, uintptr_t ra, + zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn) +{ + const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT); + const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2); + intptr_t i, oprsz = simd_oprsz(desc) / 8; -DO_ST1_ZPZ_D(sve_stbd_zd, uint64_t, cpu_stb_data_ra) -DO_ST1_ZPZ_D(sve_sthd_zd, uint64_t, cpu_stw_data_ra) -DO_ST1_ZPZ_D(sve_stsd_zd, uint64_t, cpu_stl_data_ra) -DO_ST1_ZPZ_D(sve_stdd_zd, uint64_t, cpu_stq_data_ra) + set_helper_retaddr(ra); + for (i = 0; i < oprsz; i++) { + uint8_t pg = *(uint8_t *)(vg + H1(i)); + if (likely(pg & 1)) { + target_ulong off = off_fn(vm, i * 8); + tlb_fn(env, vd, i * 8, base + (off << scale), oi, ra); + } + } + set_helper_retaddr(0); +} + +#define DO_ST1_ZPZ_S(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_st1_zs(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_s, sve_st1##MEM##_tlb); \ +} + +#define DO_ST1_ZPZ_D(MEM, OFS) \ +void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \ + (CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + sve_st1_zd(env, vd, vg, vm, base, desc, GETPC(), \ + off_##OFS##_d, sve_st1##MEM##_tlb); \ +} + +DO_ST1_ZPZ_S(bs, zsu) +DO_ST1_ZPZ_S(hs_le, zsu) +DO_ST1_ZPZ_S(hs_be, zsu) +DO_ST1_ZPZ_S(ss_le, zsu) +DO_ST1_ZPZ_S(ss_be, zsu) + +DO_ST1_ZPZ_S(bs, zss) +DO_ST1_ZPZ_S(hs_le, zss) +DO_ST1_ZPZ_S(hs_be, zss) +DO_ST1_ZPZ_S(ss_le, zss) +DO_ST1_ZPZ_S(ss_be, zss) + +DO_ST1_ZPZ_D(bd, zsu) +DO_ST1_ZPZ_D(hd_le, zsu) +DO_ST1_ZPZ_D(hd_be, zsu) +DO_ST1_ZPZ_D(sd_le, zsu) +DO_ST1_ZPZ_D(sd_be, zsu) +DO_ST1_ZPZ_D(dd_le, zsu) +DO_ST1_ZPZ_D(dd_be, zsu) + +DO_ST1_ZPZ_D(bd, zss) +DO_ST1_ZPZ_D(hd_le, zss) +DO_ST1_ZPZ_D(hd_be, zss) +DO_ST1_ZPZ_D(sd_le, zss) +DO_ST1_ZPZ_D(sd_be, zss) +DO_ST1_ZPZ_D(dd_le, zss) +DO_ST1_ZPZ_D(dd_be, zss) + +DO_ST1_ZPZ_D(bd, zd) +DO_ST1_ZPZ_D(hd_le, zd) +DO_ST1_ZPZ_D(hd_be, zd) +DO_ST1_ZPZ_D(sd_le, zd) +DO_ST1_ZPZ_D(sd_be, zd) +DO_ST1_ZPZ_D(dd_le, zd) +DO_ST1_ZPZ_D(dd_be, zd) + +#undef DO_ST1_ZPZ_S +#undef DO_ST1_ZPZ_D diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 8ca3876707..8a24278d79 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -166,11 +166,15 @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f, cpu_fprintf(f, "\n"); return; } + if (fp_exception_el(env, el) != 0) { + cpu_fprintf(f, " FPU disabled\n"); + return; + } cpu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (arm_feature(env, ARM_FEATURE_SVE)) { - int j, zcr_len = env->vfp.zcr_el[1] & 0xf; /* fix for system mode */ + if (arm_feature(env, ARM_FEATURE_SVE) && sve_exception_el(env, el) == 0) { + int j, zcr_len = sve_zcr_len_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { bool eol; diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 667879564f..fe7aebdc19 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -4600,62 +4600,97 @@ static const uint8_t dtype_esz[16] = { 3, 2, 1, 3 }; +static TCGMemOpIdx sve_memopidx(DisasContext *s, int dtype) +{ + return make_memop_idx(s->be_data | dtype_mop[dtype], get_mem_index(s)); +} + static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, - gen_helper_gvec_mem *fn) + int dtype, gen_helper_gvec_mem *fn) { unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; - TCGv_i32 desc; + TCGv_i32 t_desc; + int desc; /* For e.g. LD4, there are not enough arguments to pass all 4 * registers as pointers, so encode the regno into the data field. * For consistency, do this even for LD1. */ - desc = tcg_const_i32(simd_desc(vsz, vsz, zt)); + desc = sve_memopidx(s, dtype); + desc |= zt << MEMOPIDX_SHIFT; + desc = simd_desc(vsz, vsz, desc); + t_desc = tcg_const_i32(desc); t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); - fn(cpu_env, t_pg, addr, desc); + fn(cpu_env, t_pg, addr, t_desc); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(desc); + tcg_temp_free_i32(t_desc); } static void do_ld_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int dtype, int nreg) { - static gen_helper_gvec_mem * const fns[16][4] = { - { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, - gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, - { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1sds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hh_r, gen_helper_sve_ld2hh_r, - gen_helper_sve_ld3hh_r, gen_helper_sve_ld4hh_r }, - { gen_helper_sve_ld1hsu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hdu_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1hds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hss_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1ss_r, gen_helper_sve_ld2ss_r, - gen_helper_sve_ld3ss_r, gen_helper_sve_ld4ss_r }, - { gen_helper_sve_ld1sdu_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1dd_r, gen_helper_sve_ld2dd_r, - gen_helper_sve_ld3dd_r, gen_helper_sve_ld4dd_r }, + static gen_helper_gvec_mem * const fns[2][16][4] = { + /* Little-endian */ + { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_le_r, gen_helper_sve_ld2hh_le_r, + gen_helper_sve_ld3hh_le_r, gen_helper_sve_ld4hh_le_r }, + { gen_helper_sve_ld1hsu_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_le_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld2ss_le_r, + gen_helper_sve_ld3ss_le_r, gen_helper_sve_ld4ss_le_r }, + { gen_helper_sve_ld1sdu_le_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r, + gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } }, + + /* Big-endian */ + { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_be_r, gen_helper_sve_ld2hh_be_r, + gen_helper_sve_ld3hh_be_r, gen_helper_sve_ld4hh_be_r }, + { gen_helper_sve_ld1hsu_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_be_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld2ss_be_r, + gen_helper_sve_ld3ss_be_r, gen_helper_sve_ld4ss_be_r }, + { gen_helper_sve_ld1sdu_be_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r, + gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } }; - gen_helper_gvec_mem *fn = fns[dtype][nreg]; + gen_helper_gvec_mem *fn = fns[s->be_data == MO_BE][dtype][nreg]; /* While there are holes in the table, they are not * accessible via the instruction encoding. */ assert(fn != NULL); - do_mem_zpa(s, zt, pg, addr, fn); + do_mem_zpa(s, zt, pg, addr, dtype, fn); } static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) @@ -4689,59 +4724,104 @@ static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) { - static gen_helper_gvec_mem * const fns[16] = { - gen_helper_sve_ldff1bb_r, - gen_helper_sve_ldff1bhu_r, - gen_helper_sve_ldff1bsu_r, - gen_helper_sve_ldff1bdu_r, - - gen_helper_sve_ldff1sds_r, - gen_helper_sve_ldff1hh_r, - gen_helper_sve_ldff1hsu_r, - gen_helper_sve_ldff1hdu_r, - - gen_helper_sve_ldff1hds_r, - gen_helper_sve_ldff1hss_r, - gen_helper_sve_ldff1ss_r, - gen_helper_sve_ldff1sdu_r, - - gen_helper_sve_ldff1bds_r, - gen_helper_sve_ldff1bss_r, - gen_helper_sve_ldff1bhs_r, - gen_helper_sve_ldff1dd_r, + static gen_helper_gvec_mem * const fns[2][16] = { + /* Little-endian */ + { gen_helper_sve_ldff1bb_r, + gen_helper_sve_ldff1bhu_r, + gen_helper_sve_ldff1bsu_r, + gen_helper_sve_ldff1bdu_r, + + gen_helper_sve_ldff1sds_le_r, + gen_helper_sve_ldff1hh_le_r, + gen_helper_sve_ldff1hsu_le_r, + gen_helper_sve_ldff1hdu_le_r, + + gen_helper_sve_ldff1hds_le_r, + gen_helper_sve_ldff1hss_le_r, + gen_helper_sve_ldff1ss_le_r, + gen_helper_sve_ldff1sdu_le_r, + + gen_helper_sve_ldff1bds_r, + gen_helper_sve_ldff1bss_r, + gen_helper_sve_ldff1bhs_r, + gen_helper_sve_ldff1dd_le_r }, + + /* Big-endian */ + { gen_helper_sve_ldff1bb_r, + gen_helper_sve_ldff1bhu_r, + gen_helper_sve_ldff1bsu_r, + gen_helper_sve_ldff1bdu_r, + + gen_helper_sve_ldff1sds_be_r, + gen_helper_sve_ldff1hh_be_r, + gen_helper_sve_ldff1hsu_be_r, + gen_helper_sve_ldff1hdu_be_r, + + gen_helper_sve_ldff1hds_be_r, + gen_helper_sve_ldff1hss_be_r, + gen_helper_sve_ldff1ss_be_r, + gen_helper_sve_ldff1sdu_be_r, + + gen_helper_sve_ldff1bds_r, + gen_helper_sve_ldff1bss_r, + gen_helper_sve_ldff1bhs_r, + gen_helper_sve_ldff1dd_be_r }, }; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); - do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]); + do_mem_zpa(s, a->rd, a->pg, addr, a->dtype, + fns[s->be_data == MO_BE][a->dtype]); } return true; } static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) { - static gen_helper_gvec_mem * const fns[16] = { - gen_helper_sve_ldnf1bb_r, - gen_helper_sve_ldnf1bhu_r, - gen_helper_sve_ldnf1bsu_r, - gen_helper_sve_ldnf1bdu_r, - - gen_helper_sve_ldnf1sds_r, - gen_helper_sve_ldnf1hh_r, - gen_helper_sve_ldnf1hsu_r, - gen_helper_sve_ldnf1hdu_r, - - gen_helper_sve_ldnf1hds_r, - gen_helper_sve_ldnf1hss_r, - gen_helper_sve_ldnf1ss_r, - gen_helper_sve_ldnf1sdu_r, - - gen_helper_sve_ldnf1bds_r, - gen_helper_sve_ldnf1bss_r, - gen_helper_sve_ldnf1bhs_r, - gen_helper_sve_ldnf1dd_r, + static gen_helper_gvec_mem * const fns[2][16] = { + /* Little-endian */ + { gen_helper_sve_ldnf1bb_r, + gen_helper_sve_ldnf1bhu_r, + gen_helper_sve_ldnf1bsu_r, + gen_helper_sve_ldnf1bdu_r, + + gen_helper_sve_ldnf1sds_le_r, + gen_helper_sve_ldnf1hh_le_r, + gen_helper_sve_ldnf1hsu_le_r, + gen_helper_sve_ldnf1hdu_le_r, + + gen_helper_sve_ldnf1hds_le_r, + gen_helper_sve_ldnf1hss_le_r, + gen_helper_sve_ldnf1ss_le_r, + gen_helper_sve_ldnf1sdu_le_r, + + gen_helper_sve_ldnf1bds_r, + gen_helper_sve_ldnf1bss_r, + gen_helper_sve_ldnf1bhs_r, + gen_helper_sve_ldnf1dd_le_r }, + + /* Big-endian */ + { gen_helper_sve_ldnf1bb_r, + gen_helper_sve_ldnf1bhu_r, + gen_helper_sve_ldnf1bsu_r, + gen_helper_sve_ldnf1bdu_r, + + gen_helper_sve_ldnf1sds_be_r, + gen_helper_sve_ldnf1hh_be_r, + gen_helper_sve_ldnf1hsu_be_r, + gen_helper_sve_ldnf1hdu_be_r, + + gen_helper_sve_ldnf1hds_be_r, + gen_helper_sve_ldnf1hss_be_r, + gen_helper_sve_ldnf1ss_be_r, + gen_helper_sve_ldnf1sdu_be_r, + + gen_helper_sve_ldnf1bds_r, + gen_helper_sve_ldnf1bss_r, + gen_helper_sve_ldnf1bhs_r, + gen_helper_sve_ldnf1dd_be_r }, }; if (sve_access_check(s)) { @@ -4751,30 +4831,57 @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), off); - do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]); + do_mem_zpa(s, a->rd, a->pg, addr, a->dtype, + fns[s->be_data == MO_BE][a->dtype]); } return true; } static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) { - static gen_helper_gvec_mem * const fns[4] = { - gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_r, - gen_helper_sve_ld1ss_r, gen_helper_sve_ld1dd_r, + static gen_helper_gvec_mem * const fns[2][4] = { + { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_le_r, + gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld1dd_le_r }, + { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_be_r, + gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld1dd_be_r }, }; unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; - TCGv_i32 desc; + TCGv_i32 t_desc; + int desc, poff; /* Load the first quadword using the normal predicated load helpers. */ - desc = tcg_const_i32(simd_desc(16, 16, zt)); + desc = sve_memopidx(s, msz_dtype(msz)); + desc |= zt << MEMOPIDX_SHIFT; + desc = simd_desc(16, 16, desc); + t_desc = tcg_const_i32(desc); + + poff = pred_full_reg_offset(s, pg); + if (vsz > 16) { + /* + * Zero-extend the first 16 bits of the predicate into a temporary. + * This avoids triggering an assert making sure we don't have bits + * set within a predicate beyond VQ, but we have lowered VQ to 1 + * for this load operation. + */ + TCGv_i64 tmp = tcg_temp_new_i64(); +#ifdef HOST_WORDS_BIGENDIAN + poff += 6; +#endif + tcg_gen_ld16u_i64(tmp, cpu_env, poff); + + poff = offsetof(CPUARMState, vfp.preg_tmp); + tcg_gen_st_i64(tmp, cpu_env, poff); + tcg_temp_free_i64(tmp); + } + t_pg = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_pg, cpu_env, poff); - tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); - fns[msz](cpu_env, t_pg, addr, desc); + fns[s->be_data == MO_BE][msz](cpu_env, t_pg, addr, t_desc); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(desc); + tcg_temp_free_i32(t_desc); /* Replicate that first quadword. */ if (vsz > 16) { @@ -4860,35 +4967,73 @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { - static gen_helper_gvec_mem * const fn_single[4][4] = { - { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, - gen_helper_sve_st1bs_r, gen_helper_sve_st1bd_r }, - { NULL, gen_helper_sve_st1hh_r, - gen_helper_sve_st1hs_r, gen_helper_sve_st1hd_r }, - { NULL, NULL, - gen_helper_sve_st1ss_r, gen_helper_sve_st1sd_r }, - { NULL, NULL, NULL, gen_helper_sve_st1dd_r }, + static gen_helper_gvec_mem * const fn_single[2][4][4] = { + { { gen_helper_sve_st1bb_r, + gen_helper_sve_st1bh_r, + gen_helper_sve_st1bs_r, + gen_helper_sve_st1bd_r }, + { NULL, + gen_helper_sve_st1hh_le_r, + gen_helper_sve_st1hs_le_r, + gen_helper_sve_st1hd_le_r }, + { NULL, NULL, + gen_helper_sve_st1ss_le_r, + gen_helper_sve_st1sd_le_r }, + { NULL, NULL, NULL, + gen_helper_sve_st1dd_le_r } }, + { { gen_helper_sve_st1bb_r, + gen_helper_sve_st1bh_r, + gen_helper_sve_st1bs_r, + gen_helper_sve_st1bd_r }, + { NULL, + gen_helper_sve_st1hh_be_r, + gen_helper_sve_st1hs_be_r, + gen_helper_sve_st1hd_be_r }, + { NULL, NULL, + gen_helper_sve_st1ss_be_r, + gen_helper_sve_st1sd_be_r }, + { NULL, NULL, NULL, + gen_helper_sve_st1dd_be_r } }, }; - static gen_helper_gvec_mem * const fn_multiple[3][4] = { - { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_r, - gen_helper_sve_st2ss_r, gen_helper_sve_st2dd_r }, - { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_r, - gen_helper_sve_st3ss_r, gen_helper_sve_st3dd_r }, - { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_r, - gen_helper_sve_st4ss_r, gen_helper_sve_st4dd_r }, + static gen_helper_gvec_mem * const fn_multiple[2][3][4] = { + { { gen_helper_sve_st2bb_r, + gen_helper_sve_st2hh_le_r, + gen_helper_sve_st2ss_le_r, + gen_helper_sve_st2dd_le_r }, + { gen_helper_sve_st3bb_r, + gen_helper_sve_st3hh_le_r, + gen_helper_sve_st3ss_le_r, + gen_helper_sve_st3dd_le_r }, + { gen_helper_sve_st4bb_r, + gen_helper_sve_st4hh_le_r, + gen_helper_sve_st4ss_le_r, + gen_helper_sve_st4dd_le_r } }, + { { gen_helper_sve_st2bb_r, + gen_helper_sve_st2hh_be_r, + gen_helper_sve_st2ss_be_r, + gen_helper_sve_st2dd_be_r }, + { gen_helper_sve_st3bb_r, + gen_helper_sve_st3hh_be_r, + gen_helper_sve_st3ss_be_r, + gen_helper_sve_st3dd_be_r }, + { gen_helper_sve_st4bb_r, + gen_helper_sve_st4hh_be_r, + gen_helper_sve_st4ss_be_r, + gen_helper_sve_st4dd_be_r } }, }; gen_helper_gvec_mem *fn; + int be = s->be_data == MO_BE; if (nreg == 0) { /* ST1 */ - fn = fn_single[msz][esz]; + fn = fn_single[be][msz][esz]; } else { /* ST2, ST3, ST4 -- msz == esz, enforced by encoding */ assert(msz == esz); - fn = fn_multiple[nreg - 1][msz]; + fn = fn_multiple[be][nreg - 1][msz]; } assert(fn != NULL); - do_mem_zpa(s, zt, pg, addr, fn); + do_mem_zpa(s, zt, pg, addr, msz_dtype(msz), fn); } static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a, uint32_t insn) @@ -4926,111 +5071,203 @@ static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a, uint32_t insn) *** SVE gather loads / scatter stores */ -static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, int scale, - TCGv_i64 scalar, gen_helper_gvec_mem_scatter *fn) +static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, + int scale, TCGv_i64 scalar, int msz, + gen_helper_gvec_mem_scatter *fn) { unsigned vsz = vec_full_reg_size(s); - TCGv_i32 desc = tcg_const_i32(simd_desc(vsz, vsz, scale)); TCGv_ptr t_zm = tcg_temp_new_ptr(); TCGv_ptr t_pg = tcg_temp_new_ptr(); TCGv_ptr t_zt = tcg_temp_new_ptr(); + TCGv_i32 t_desc; + int desc; + + desc = sve_memopidx(s, msz_dtype(msz)); + desc |= scale << MEMOPIDX_SHIFT; + desc = simd_desc(vsz, vsz, desc); + t_desc = tcg_const_i32(desc); tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); tcg_gen_addi_ptr(t_zm, cpu_env, vec_full_reg_offset(s, zm)); tcg_gen_addi_ptr(t_zt, cpu_env, vec_full_reg_offset(s, zt)); - fn(cpu_env, t_zt, t_pg, t_zm, scalar, desc); + fn(cpu_env, t_zt, t_pg, t_zm, scalar, t_desc); tcg_temp_free_ptr(t_zt); tcg_temp_free_ptr(t_zm); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(desc); + tcg_temp_free_i32(t_desc); } -/* Indexed by [ff][xs][u][msz]. */ -static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][3] = { - { { { gen_helper_sve_ldbss_zsu, - gen_helper_sve_ldhss_zsu, - NULL, }, - { gen_helper_sve_ldbsu_zsu, - gen_helper_sve_ldhsu_zsu, - gen_helper_sve_ldssu_zsu, } }, - { { gen_helper_sve_ldbss_zss, - gen_helper_sve_ldhss_zss, - NULL, }, - { gen_helper_sve_ldbsu_zss, - gen_helper_sve_ldhsu_zss, - gen_helper_sve_ldssu_zss, } } }, - - { { { gen_helper_sve_ldffbss_zsu, - gen_helper_sve_ldffhss_zsu, - NULL, }, - { gen_helper_sve_ldffbsu_zsu, - gen_helper_sve_ldffhsu_zsu, - gen_helper_sve_ldffssu_zsu, } }, - { { gen_helper_sve_ldffbss_zss, - gen_helper_sve_ldffhss_zss, - NULL, }, - { gen_helper_sve_ldffbsu_zss, - gen_helper_sve_ldffhsu_zss, - gen_helper_sve_ldffssu_zss, } } } +/* Indexed by [be][ff][xs][u][msz]. */ +static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][2][3] = { + /* Little-endian */ + { { { { gen_helper_sve_ldbss_zsu, + gen_helper_sve_ldhss_le_zsu, + NULL, }, + { gen_helper_sve_ldbsu_zsu, + gen_helper_sve_ldhsu_le_zsu, + gen_helper_sve_ldss_le_zsu, } }, + { { gen_helper_sve_ldbss_zss, + gen_helper_sve_ldhss_le_zss, + NULL, }, + { gen_helper_sve_ldbsu_zss, + gen_helper_sve_ldhsu_le_zss, + gen_helper_sve_ldss_le_zss, } } }, + + /* First-fault */ + { { { gen_helper_sve_ldffbss_zsu, + gen_helper_sve_ldffhss_le_zsu, + NULL, }, + { gen_helper_sve_ldffbsu_zsu, + gen_helper_sve_ldffhsu_le_zsu, + gen_helper_sve_ldffss_le_zsu, } }, + { { gen_helper_sve_ldffbss_zss, + gen_helper_sve_ldffhss_le_zss, + NULL, }, + { gen_helper_sve_ldffbsu_zss, + gen_helper_sve_ldffhsu_le_zss, + gen_helper_sve_ldffss_le_zss, } } } }, + + /* Big-endian */ + { { { { gen_helper_sve_ldbss_zsu, + gen_helper_sve_ldhss_be_zsu, + NULL, }, + { gen_helper_sve_ldbsu_zsu, + gen_helper_sve_ldhsu_be_zsu, + gen_helper_sve_ldss_be_zsu, } }, + { { gen_helper_sve_ldbss_zss, + gen_helper_sve_ldhss_be_zss, + NULL, }, + { gen_helper_sve_ldbsu_zss, + gen_helper_sve_ldhsu_be_zss, + gen_helper_sve_ldss_be_zss, } } }, + + /* First-fault */ + { { { gen_helper_sve_ldffbss_zsu, + gen_helper_sve_ldffhss_be_zsu, + NULL, }, + { gen_helper_sve_ldffbsu_zsu, + gen_helper_sve_ldffhsu_be_zsu, + gen_helper_sve_ldffss_be_zsu, } }, + { { gen_helper_sve_ldffbss_zss, + gen_helper_sve_ldffhss_be_zss, + NULL, }, + { gen_helper_sve_ldffbsu_zss, + gen_helper_sve_ldffhsu_be_zss, + gen_helper_sve_ldffss_be_zss, } } } }, }; /* Note that we overload xs=2 to indicate 64-bit offset. */ -static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][3][2][4] = { - { { { gen_helper_sve_ldbds_zsu, - gen_helper_sve_ldhds_zsu, - gen_helper_sve_ldsds_zsu, - NULL, }, - { gen_helper_sve_ldbdu_zsu, - gen_helper_sve_ldhdu_zsu, - gen_helper_sve_ldsdu_zsu, - gen_helper_sve_ldddu_zsu, } }, - { { gen_helper_sve_ldbds_zss, - gen_helper_sve_ldhds_zss, - gen_helper_sve_ldsds_zss, - NULL, }, - { gen_helper_sve_ldbdu_zss, - gen_helper_sve_ldhdu_zss, - gen_helper_sve_ldsdu_zss, - gen_helper_sve_ldddu_zss, } }, - { { gen_helper_sve_ldbds_zd, - gen_helper_sve_ldhds_zd, - gen_helper_sve_ldsds_zd, - NULL, }, - { gen_helper_sve_ldbdu_zd, - gen_helper_sve_ldhdu_zd, - gen_helper_sve_ldsdu_zd, - gen_helper_sve_ldddu_zd, } } }, - - { { { gen_helper_sve_ldffbds_zsu, - gen_helper_sve_ldffhds_zsu, - gen_helper_sve_ldffsds_zsu, - NULL, }, - { gen_helper_sve_ldffbdu_zsu, - gen_helper_sve_ldffhdu_zsu, - gen_helper_sve_ldffsdu_zsu, - gen_helper_sve_ldffddu_zsu, } }, - { { gen_helper_sve_ldffbds_zss, - gen_helper_sve_ldffhds_zss, - gen_helper_sve_ldffsds_zss, - NULL, }, - { gen_helper_sve_ldffbdu_zss, - gen_helper_sve_ldffhdu_zss, - gen_helper_sve_ldffsdu_zss, - gen_helper_sve_ldffddu_zss, } }, - { { gen_helper_sve_ldffbds_zd, - gen_helper_sve_ldffhds_zd, - gen_helper_sve_ldffsds_zd, - NULL, }, - { gen_helper_sve_ldffbdu_zd, - gen_helper_sve_ldffhdu_zd, - gen_helper_sve_ldffsdu_zd, - gen_helper_sve_ldffddu_zd, } } } +static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][2][3][2][4] = { + /* Little-endian */ + { { { { gen_helper_sve_ldbds_zsu, + gen_helper_sve_ldhds_le_zsu, + gen_helper_sve_ldsds_le_zsu, + NULL, }, + { gen_helper_sve_ldbdu_zsu, + gen_helper_sve_ldhdu_le_zsu, + gen_helper_sve_ldsdu_le_zsu, + gen_helper_sve_lddd_le_zsu, } }, + { { gen_helper_sve_ldbds_zss, + gen_helper_sve_ldhds_le_zss, + gen_helper_sve_ldsds_le_zss, + NULL, }, + { gen_helper_sve_ldbdu_zss, + gen_helper_sve_ldhdu_le_zss, + gen_helper_sve_ldsdu_le_zss, + gen_helper_sve_lddd_le_zss, } }, + { { gen_helper_sve_ldbds_zd, + gen_helper_sve_ldhds_le_zd, + gen_helper_sve_ldsds_le_zd, + NULL, }, + { gen_helper_sve_ldbdu_zd, + gen_helper_sve_ldhdu_le_zd, + gen_helper_sve_ldsdu_le_zd, + gen_helper_sve_lddd_le_zd, } } }, + + /* First-fault */ + { { { gen_helper_sve_ldffbds_zsu, + gen_helper_sve_ldffhds_le_zsu, + gen_helper_sve_ldffsds_le_zsu, + NULL, }, + { gen_helper_sve_ldffbdu_zsu, + gen_helper_sve_ldffhdu_le_zsu, + gen_helper_sve_ldffsdu_le_zsu, + gen_helper_sve_ldffdd_le_zsu, } }, + { { gen_helper_sve_ldffbds_zss, + gen_helper_sve_ldffhds_le_zss, + gen_helper_sve_ldffsds_le_zss, + NULL, }, + { gen_helper_sve_ldffbdu_zss, + gen_helper_sve_ldffhdu_le_zss, + gen_helper_sve_ldffsdu_le_zss, + gen_helper_sve_ldffdd_le_zss, } }, + { { gen_helper_sve_ldffbds_zd, + gen_helper_sve_ldffhds_le_zd, + gen_helper_sve_ldffsds_le_zd, + NULL, }, + { gen_helper_sve_ldffbdu_zd, + gen_helper_sve_ldffhdu_le_zd, + gen_helper_sve_ldffsdu_le_zd, + gen_helper_sve_ldffdd_le_zd, } } } }, + + /* Big-endian */ + { { { { gen_helper_sve_ldbds_zsu, + gen_helper_sve_ldhds_be_zsu, + gen_helper_sve_ldsds_be_zsu, + NULL, }, + { gen_helper_sve_ldbdu_zsu, + gen_helper_sve_ldhdu_be_zsu, + gen_helper_sve_ldsdu_be_zsu, + gen_helper_sve_lddd_be_zsu, } }, + { { gen_helper_sve_ldbds_zss, + gen_helper_sve_ldhds_be_zss, + gen_helper_sve_ldsds_be_zss, + NULL, }, + { gen_helper_sve_ldbdu_zss, + gen_helper_sve_ldhdu_be_zss, + gen_helper_sve_ldsdu_be_zss, + gen_helper_sve_lddd_be_zss, } }, + { { gen_helper_sve_ldbds_zd, + gen_helper_sve_ldhds_be_zd, + gen_helper_sve_ldsds_be_zd, + NULL, }, + { gen_helper_sve_ldbdu_zd, + gen_helper_sve_ldhdu_be_zd, + gen_helper_sve_ldsdu_be_zd, + gen_helper_sve_lddd_be_zd, } } }, + + /* First-fault */ + { { { gen_helper_sve_ldffbds_zsu, + gen_helper_sve_ldffhds_be_zsu, + gen_helper_sve_ldffsds_be_zsu, + NULL, }, + { gen_helper_sve_ldffbdu_zsu, + gen_helper_sve_ldffhdu_be_zsu, + gen_helper_sve_ldffsdu_be_zsu, + gen_helper_sve_ldffdd_be_zsu, } }, + { { gen_helper_sve_ldffbds_zss, + gen_helper_sve_ldffhds_be_zss, + gen_helper_sve_ldffsds_be_zss, + NULL, }, + { gen_helper_sve_ldffbdu_zss, + gen_helper_sve_ldffhdu_be_zss, + gen_helper_sve_ldffsdu_be_zss, + gen_helper_sve_ldffdd_be_zss, } }, + { { gen_helper_sve_ldffbds_zd, + gen_helper_sve_ldffhds_be_zd, + gen_helper_sve_ldffsds_be_zd, + NULL, }, + { gen_helper_sve_ldffbdu_zd, + gen_helper_sve_ldffhdu_be_zd, + gen_helper_sve_ldffsdu_be_zd, + gen_helper_sve_ldffdd_be_zd, } } } }, }; static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn = NULL; + int be = s->be_data == MO_BE; if (!sve_access_check(s)) { return true; @@ -5038,22 +5275,23 @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) switch (a->esz) { case MO_32: - fn = gather_load_fn32[a->ff][a->xs][a->u][a->msz]; + fn = gather_load_fn32[be][a->ff][a->xs][a->u][a->msz]; break; case MO_64: - fn = gather_load_fn64[a->ff][a->xs][a->u][a->msz]; + fn = gather_load_fn64[be][a->ff][a->xs][a->u][a->msz]; break; } assert(fn != NULL); do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz, - cpu_reg_sp(s, a->rn), fn); + cpu_reg_sp(s, a->rn), a->msz, fn); return true; } static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn = NULL; + int be = s->be_data == MO_BE; TCGv_i64 imm; if (a->esz < a->msz || (a->esz == a->msz && !a->u)) { @@ -5065,10 +5303,10 @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) switch (a->esz) { case MO_32: - fn = gather_load_fn32[a->ff][0][a->u][a->msz]; + fn = gather_load_fn32[be][a->ff][0][a->u][a->msz]; break; case MO_64: - fn = gather_load_fn64[a->ff][2][a->u][a->msz]; + fn = gather_load_fn64[be][a->ff][2][a->u][a->msz]; break; } assert(fn != NULL); @@ -5077,40 +5315,63 @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) * by loading the immediate into the scalar parameter. */ imm = tcg_const_i64(a->imm << a->msz); - do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn); + do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, a->msz, fn); tcg_temp_free_i64(imm); return true; } -/* Indexed by [xs][msz]. */ -static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][3] = { - { gen_helper_sve_stbs_zsu, - gen_helper_sve_sths_zsu, - gen_helper_sve_stss_zsu, }, - { gen_helper_sve_stbs_zss, - gen_helper_sve_sths_zss, - gen_helper_sve_stss_zss, }, +/* Indexed by [be][xs][msz]. */ +static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][3] = { + /* Little-endian */ + { { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_le_zsu, + gen_helper_sve_stss_le_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_le_zss, + gen_helper_sve_stss_le_zss, } }, + /* Big-endian */ + { { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_be_zsu, + gen_helper_sve_stss_be_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_be_zss, + gen_helper_sve_stss_be_zss, } }, }; /* Note that we overload xs=2 to indicate 64-bit offset. */ -static gen_helper_gvec_mem_scatter * const scatter_store_fn64[3][4] = { - { gen_helper_sve_stbd_zsu, - gen_helper_sve_sthd_zsu, - gen_helper_sve_stsd_zsu, - gen_helper_sve_stdd_zsu, }, - { gen_helper_sve_stbd_zss, - gen_helper_sve_sthd_zss, - gen_helper_sve_stsd_zss, - gen_helper_sve_stdd_zss, }, - { gen_helper_sve_stbd_zd, - gen_helper_sve_sthd_zd, - gen_helper_sve_stsd_zd, - gen_helper_sve_stdd_zd, }, +static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][3][4] = { + /* Little-endian */ + { { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_le_zsu, + gen_helper_sve_stsd_le_zsu, + gen_helper_sve_stdd_le_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_le_zss, + gen_helper_sve_stsd_le_zss, + gen_helper_sve_stdd_le_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_le_zd, + gen_helper_sve_stsd_le_zd, + gen_helper_sve_stdd_le_zd, } }, + /* Big-endian */ + { { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_be_zsu, + gen_helper_sve_stsd_be_zsu, + gen_helper_sve_stdd_be_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_be_zss, + gen_helper_sve_stsd_be_zss, + gen_helper_sve_stdd_be_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_be_zd, + gen_helper_sve_stsd_be_zd, + gen_helper_sve_stdd_be_zd, } }, }; static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn; + int be = s->be_data == MO_BE; if (a->esz < a->msz || (a->msz == 0 && a->scale)) { return false; @@ -5120,22 +5381,23 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) } switch (a->esz) { case MO_32: - fn = scatter_store_fn32[a->xs][a->msz]; + fn = scatter_store_fn32[be][a->xs][a->msz]; break; case MO_64: - fn = scatter_store_fn64[a->xs][a->msz]; + fn = scatter_store_fn64[be][a->xs][a->msz]; break; default: g_assert_not_reached(); } do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz, - cpu_reg_sp(s, a->rn), fn); + cpu_reg_sp(s, a->rn), a->msz, fn); return true; } static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) { gen_helper_gvec_mem_scatter *fn = NULL; + int be = s->be_data == MO_BE; TCGv_i64 imm; if (a->esz < a->msz) { @@ -5147,10 +5409,10 @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) switch (a->esz) { case MO_32: - fn = scatter_store_fn32[0][a->msz]; + fn = scatter_store_fn32[be][0][a->msz]; break; case MO_64: - fn = scatter_store_fn64[2][a->msz]; + fn = scatter_store_fn64[be][2][a->msz]; break; } assert(fn != NULL); @@ -5159,7 +5421,7 @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) * by loading the immediate into the scalar parameter. */ imm = tcg_const_i64(a->imm << a->msz); - do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn); + do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, a->msz, fn); tcg_temp_free_i64(imm); return true; } diff --git a/target/arm/translate.c b/target/arm/translate.c index c6a5d2ac44..1b4bacb522 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -239,6 +239,23 @@ static void store_reg(DisasContext *s, int reg, TCGv_i32 var) tcg_temp_free_i32(var); } +/* + * Variant of store_reg which applies v8M stack-limit checks before updating + * SP. If the check fails this will result in an exception being taken. + * We disable the stack checks for CONFIG_USER_ONLY because we have + * no idea what the stack limits should be in that case. + * If stack checking is not being done this just acts like store_reg(). + */ +static void store_sp_checked(DisasContext *s, TCGv_i32 var) +{ +#ifndef CONFIG_USER_ONLY + if (s->v8m_stackcheck) { + gen_helper_v8m_stackcheck(cpu_env, var); + } +#endif + store_reg(s, 13, var); +} + /* Value extensions. */ #define gen_uxtb(var) tcg_gen_ext8u_i32(var, var) #define gen_uxth(var) tcg_gen_ext16u_i32(var, var) @@ -4212,6 +4229,18 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) if (insn & (1 << 24)) /* pre-decrement */ tcg_gen_addi_i32(addr, addr, -((insn & 0xff) << 2)); + if (s->v8m_stackcheck && rn == 13 && w) { + /* + * Here 'addr' is the lowest address we will store to, + * and is either the old SP (if post-increment) or + * the new SP (if pre-decrement). For post-increment + * where the old value is below the limit and the new + * value is above, it is UNKNOWN whether the limit check + * triggers; we choose to trigger. + */ + gen_helper_v8m_stackcheck(cpu_env, addr); + } + if (dp) offset = 8; else @@ -10261,6 +10290,8 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) * 0b1111_1001_x11x_xxxx_xxxx_xxxx_xxxx_xxxx * - load/store dual (pre-indexed) */ + bool wback = extract32(insn, 21, 1); + if (rn == 15) { if (insn & (1 << 21)) { /* UNPREDICTABLE */ @@ -10272,8 +10303,29 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) addr = load_reg(s, rn); } offset = (insn & 0xff) * 4; - if ((insn & (1 << 23)) == 0) + if ((insn & (1 << 23)) == 0) { offset = -offset; + } + + if (s->v8m_stackcheck && rn == 13 && wback) { + /* + * Here 'addr' is the current SP; if offset is +ve we're + * moving SP up, else down. It is UNKNOWN whether the limit + * check triggers when SP starts below the limit and ends + * up above it; check whichever of the current and final + * SP is lower, so QEMU will trigger in that situation. + */ + if ((int32_t)offset < 0) { + TCGv_i32 newsp = tcg_temp_new_i32(); + + tcg_gen_addi_i32(newsp, addr, offset); + gen_helper_v8m_stackcheck(cpu_env, newsp); + tcg_temp_free_i32(newsp); + } else { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + } + if (insn & (1 << 24)) { tcg_gen_addi_i32(addr, addr, offset); offset = 0; @@ -10297,7 +10349,7 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) gen_aa32_st32(s, tmp, addr, get_mem_index(s)); tcg_temp_free_i32(tmp); } - if (insn & (1 << 21)) { + if (wback) { /* Base writeback. */ tcg_gen_addi_i32(addr, addr, offset - 4); store_reg(s, rn, addr); @@ -10484,6 +10536,7 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } else { int i, loaded_base = 0; TCGv_i32 loaded_var; + bool wback = extract32(insn, 21, 1); /* Load/store multiple. */ addr = load_reg(s, rn); offset = 0; @@ -10491,10 +10544,26 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (insn & (1 << i)) offset += 4; } + if (insn & (1 << 24)) { tcg_gen_addi_i32(addr, addr, -offset); } + if (s->v8m_stackcheck && rn == 13 && wback) { + /* + * If the writeback is incrementing SP rather than + * decrementing it, and the initial SP is below the + * stack limit but the final written-back SP would + * be above, then then we must not perform any memory + * accesses, but it is IMPDEF whether we generate + * an exception. We choose to do so in this case. + * At this point 'addr' is the lowest address, so + * either the original SP (if incrementing) or our + * final SP (if decrementing), so that's what we check. + */ + gen_helper_v8m_stackcheck(cpu_env, addr); + } + loaded_var = NULL; for (i = 0; i < 16; i++) { if ((insn & (1 << i)) == 0) @@ -10522,7 +10591,7 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (loaded_base) { store_reg(s, rn, loaded_var); } - if (insn & (1 << 21)) { + if (wback) { /* Base register writeback. */ if (insn & (1 << 24)) { tcg_gen_addi_i32(addr, addr, -offset); @@ -10583,7 +10652,13 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (gen_thumb2_data_op(s, op, conds, 0, tmp, tmp2)) goto illegal_op; tcg_temp_free_i32(tmp2); - if (rd != 15) { + if (rd == 13 && + ((op == 2 && rn == 15) || + (op == 8 && rn == 13) || + (op == 13 && rn == 13))) { + /* MOV SP, ... or ADD SP, SP, ... or SUB SP, SP, ... */ + store_sp_checked(s, tmp); + } else if (rd != 15) { store_reg(s, rd, tmp); } else { tcg_temp_free_i32(tmp); @@ -10600,6 +10675,10 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp2 = load_reg(s, rm); if ((insn & 0x70) != 0) goto illegal_op; + /* + * 0b1111_1010_0xxx_xxxx_1111_xxxx_0000_xxxx: + * - MOV, MOVS (register-shifted register), flagsetting + */ op = (insn >> 21) & 3; logic_cc = (insn & (1 << 20)) != 0; gen_arm_shift_reg(tmp, op, tmp2, logic_cc); @@ -11267,8 +11346,15 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) gen_jmp(s, s->pc + offset); } } else { - /* Data processing immediate. */ + /* + * 0b1111_0xxx_xxxx_0xxx_xxxx_xxxx + * - Data-processing (modified immediate, plain binary immediate) + */ if (insn & (1 << 25)) { + /* + * 0b1111_0x1x_xxxx_0xxx_xxxx_xxxx + * - Data-processing (plain binary immediate) + */ if (insn & (1 << 24)) { if (insn & (1 << 20)) goto illegal_op; @@ -11364,6 +11450,7 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, imm); } + store_reg(s, rd, tmp); } else { /* Add/sub 12-bit immediate. */ if (rn == 15) { @@ -11374,17 +11461,27 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) offset += imm; tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, offset); + store_reg(s, rd, tmp); } else { tmp = load_reg(s, rn); if (insn & (1 << 23)) tcg_gen_subi_i32(tmp, tmp, imm); else tcg_gen_addi_i32(tmp, tmp, imm); + if (rn == 13 && rd == 13) { + /* ADD SP, SP, imm or SUB SP, SP, imm */ + store_sp_checked(s, tmp); + } else { + store_reg(s, rd, tmp); + } } } - store_reg(s, rd, tmp); } } else { + /* + * 0b1111_0x0x_xxxx_0xxx_xxxx_xxxx + * - Data-processing (modified immediate) + */ int shifter_out = 0; /* modified 12-bit immediate. */ shift = ((insn & 0x04000000) >> 23) | ((insn & 0x7000) >> 12); @@ -11426,7 +11523,11 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) goto illegal_op; tcg_temp_free_i32(tmp2); rd = (insn >> 8) & 0xf; - if (rd != 15) { + if (rd == 13 && rn == 13 + && (op == 8 || op == 13)) { + /* ADD(S) SP, SP, imm or SUB(S) SP, SP, imm */ + store_sp_checked(s, tmp); + } else if (rd != 15) { store_reg(s, rd, tmp); } else { tcg_temp_free_i32(tmp); @@ -11535,7 +11636,6 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) imm = -imm; /* Fall through. */ case 0xf: /* Pre-increment. */ - tcg_gen_addi_i32(addr, addr, imm); writeback = 1; break; default: @@ -11547,6 +11647,28 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) issinfo = writeback ? ISSInvalid : rs; + if (s->v8m_stackcheck && rn == 13 && writeback) { + /* + * Stackcheck. Here we know 'addr' is the current SP; + * if imm is +ve we're moving SP up, else down. It is + * UNKNOWN whether the limit check triggers when SP starts + * below the limit and ends up above it; we chose to do so. + */ + if ((int32_t)imm < 0) { + TCGv_i32 newsp = tcg_temp_new_i32(); + + tcg_gen_addi_i32(newsp, addr, imm); + gen_helper_v8m_stackcheck(cpu_env, newsp); + tcg_temp_free_i32(newsp); + } else { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + } + + if (writeback && !postinc) { + tcg_gen_addi_i32(addr, addr, imm); + } + if (insn & (1 << 20)) { /* Load. */ tmp = tcg_temp_new_i32(); @@ -11629,7 +11751,11 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) rd = insn & 7; op = (insn >> 11) & 3; if (op == 3) { - /* add/subtract */ + /* + * 0b0001_1xxx_xxxx_xxxx + * - Add, subtract (three low registers) + * - Add, subtract (two low registers and immediate) + */ rn = (insn >> 3) & 7; tmp = load_reg(s, rn); if (insn & (1 << 10)) { @@ -11666,7 +11792,10 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) } break; case 2: case 3: - /* arithmetic large immediate */ + /* + * 0b001x_xxxx_xxxx_xxxx + * - Add, subtract, compare, move (one low register and immediate) + */ op = (insn >> 11) & 3; rd = (insn >> 8) & 0x7; if (op == 0) { /* mov */ @@ -11732,7 +11861,12 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) tmp2 = load_reg(s, rm); tcg_gen_add_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); - store_reg(s, rd, tmp); + if (rd == 13) { + /* ADD SP, SP, reg */ + store_sp_checked(s, tmp); + } else { + store_reg(s, rd, tmp); + } break; case 1: /* cmp */ tmp = load_reg(s, rd); @@ -11743,7 +11877,12 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; case 2: /* mov/cpy */ tmp = load_reg(s, rm); - store_reg(s, rd, tmp); + if (rd == 13) { + /* MOV SP, reg */ + store_sp_checked(s, tmp); + } else { + store_reg(s, rd, tmp); + } break; case 3: { @@ -11793,7 +11932,10 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; } - /* data processing register */ + /* + * 0b0100_00xx_xxxx_xxxx + * - Data-processing (two low registers) + */ rd = insn & 7; rm = (insn >> 3) & 7; op = (insn >> 6) & 0xf; @@ -12071,7 +12213,10 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; case 10: - /* add to high reg */ + /* + * 0b1010_xxxx_xxxx_xxxx + * - Add PC/SP (immediate) + */ rd = (insn >> 8) & 7; if (insn & (1 << 11)) { /* SP */ @@ -12091,13 +12236,17 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) op = (insn >> 8) & 0xf; switch (op) { case 0: - /* adjust stack pointer */ + /* + * 0b1011_0000_xxxx_xxxx + * - ADD (SP plus immediate) + * - SUB (SP minus immediate) + */ tmp = load_reg(s, 13); val = (insn & 0x7f) * 4; if (insn & (1 << 7)) val = -(int32_t)val; tcg_gen_addi_i32(tmp, tmp, val); - store_reg(s, 13, tmp); + store_sp_checked(s, tmp); break; case 2: /* sign/zero extend. */ @@ -12114,7 +12263,10 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) store_reg(s, rd, tmp); break; case 4: case 5: case 0xc: case 0xd: - /* push/pop */ + /* + * 0b1011_x10x_xxxx_xxxx + * - push/pop + */ addr = load_reg(s, 13); if (insn & (1 << 8)) offset = 4; @@ -12127,6 +12279,17 @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) if ((insn & (1 << 11)) == 0) { tcg_gen_addi_i32(addr, addr, -offset); } + + if (s->v8m_stackcheck) { + /* + * Here 'addr' is the lower of "old SP" and "new SP"; + * if this is a pop that starts below the limit and ends + * above it, it is UNKNOWN whether the limit check triggers; + * we choose to trigger. + */ + gen_helper_v8m_stackcheck(cpu_env, addr); + } + for (i = 0; i < 8; i++) { if (insn & (1 << i)) { if (insn & (1 << 11)) { @@ -12451,6 +12614,7 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->v7m_handler_mode = ARM_TBFLAG_HANDLER(dc->base.tb->flags); dc->v8m_secure = arm_feature(env, ARM_FEATURE_M_SECURITY) && regime_is_secure(env, dc->mmu_idx); + dc->v8m_stackcheck = ARM_TBFLAG_STACKCHECK(dc->base.tb->flags); dc->cp_regs = cpu->cp_regs; dc->features = env->features; diff --git a/target/arm/translate.h b/target/arm/translate.h index 45f04244be..c1b65f3efb 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -38,6 +38,7 @@ typedef struct DisasContext { int vec_stride; bool v7m_handler_mode; bool v8m_secure; /* true if v8M and we're in Secure mode */ + bool v8m_stackcheck; /* true if we need to perform v8M stack limit checks */ /* Immediate value in AArch32 SVC insn; must be set if is_jmp == DISAS_SWI * so that top level loop can generate correct syndrome information. */ |