[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-ppc] [PATCH 16/34] target/ppc: move FP and VMX registers into
From: |
David Gibson |
Subject: |
Re: [Qemu-ppc] [PATCH 16/34] target/ppc: move FP and VMX registers into aligned vsr register array |
Date: |
Wed, 19 Dec 2018 17:27:48 +1100 |
User-agent: |
Mutt/1.10.1 (2018-07-13) |
On Mon, Dec 17, 2018 at 10:38:53PM -0800, Richard Henderson wrote:
> From: Mark Cave-Ayland <address@hidden>
>
> The VSX register array is a block of 64 128-bit registers where the first 32
> registers consist of the existing 64-bit FP registers extended to 128-bit
> using new VSR registers, and the last 32 registers are the VMX 128-bit
> registers as show below:
>
> 64-bit 64-bit
> +--------------------+--------------------+
> | FP0 | | VSR0
> +--------------------+--------------------+
> | FP1 | | VSR1
> +--------------------+--------------------+
> | ... | ... | ...
> +--------------------+--------------------+
> | FP30 | | VSR30
> +--------------------+--------------------+
> | FP31 | | VSR31
> +--------------------+--------------------+
> | VMX0 | VSR32
> +-----------------------------------------+
> | VMX1 | VSR33
> +-----------------------------------------+
> | ... | ...
> +-----------------------------------------+
> | VMX30 | VSR62
> +-----------------------------------------+
> | VMX31 | VSR63
> +-----------------------------------------+
>
> In order to allow for future conversion of VSX instructions to use TCG vector
> operations, recreate the same layout using an aligned version of the existing
> vsr register array.
>
> Since the old fpr and avr register arrays are removed, the existing callers
> must also be updated to use the correct offset in the vsr register array. This
> also includes switching the relevant VMState fields over to using subarrays
> to make sure that migration is preserved.
>
> Signed-off-by: Mark Cave-Ayland <address@hidden>
Acked-by: David Gibson <address@hidden>
> Message-Id: <address@hidden>
> ---
> target/ppc/cpu.h | 9 ++--
> target/ppc/internal.h | 18 ++------
> linux-user/ppc/signal.c | 24 +++++-----
> target/ppc/arch_dump.c | 12 ++---
> target/ppc/gdbstub.c | 8 ++--
> target/ppc/machine.c | 72 +++++++++++++++++++++++++++--
> target/ppc/monitor.c | 4 +-
> target/ppc/translate.c | 14 +++---
> target/ppc/translate/dfp-impl.inc.c | 2 +-
> target/ppc/translate/vmx-impl.inc.c | 7 ++-
> target/ppc/translate/vsx-impl.inc.c | 4 +-
> target/ppc/translate_init.inc.c | 24 +++++-----
> 12 files changed, 126 insertions(+), 72 deletions(-)
>
> diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
> index 5445d4c3c1..c8f449081d 100644
> --- a/target/ppc/cpu.h
> +++ b/target/ppc/cpu.h
> @@ -1016,8 +1016,6 @@ struct CPUPPCState {
>
> /* Floating point execution context */
> float_status fp_status;
> - /* floating point registers */
> - float64 fpr[32];
> /* floating point status and control register */
> target_ulong fpscr;
>
> @@ -1067,11 +1065,10 @@ struct CPUPPCState {
> /* Special purpose registers */
> target_ulong spr[1024];
> ppc_spr_t spr_cb[1024];
> - /* Altivec registers */
> - ppc_avr_t avr[32];
> + /* Vector status and control register */
> uint32_t vscr;
> - /* VSX registers */
> - uint64_t vsr[32];
> + /* VSX registers (including FP and AVR) */
> + ppc_vsr_t vsr[64] QEMU_ALIGNED(16);
> /* SPE registers */
> uint64_t spe_acc;
> uint32_t spe_fscr;
> diff --git a/target/ppc/internal.h b/target/ppc/internal.h
> index b4b1f7b3db..b77d564a65 100644
> --- a/target/ppc/internal.h
> +++ b/target/ppc/internal.h
> @@ -218,24 +218,14 @@ EXTRACT_HELPER_SPLIT_3(DCMX_XV, 5, 16, 0, 1, 2, 5, 1,
> 6, 6);
>
> static inline void getVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
> {
> - if (n < 32) {
> - vsr->VsrD(0) = env->fpr[n];
> - vsr->VsrD(1) = env->vsr[n];
> - } else {
> - vsr->u64[0] = env->avr[n - 32].u64[0];
> - vsr->u64[1] = env->avr[n - 32].u64[1];
> - }
> + vsr->VsrD(0) = env->vsr[n].u64[0];
> + vsr->VsrD(1) = env->vsr[n].u64[1];
> }
>
> static inline void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
> {
> - if (n < 32) {
> - env->fpr[n] = vsr->VsrD(0);
> - env->vsr[n] = vsr->VsrD(1);
> - } else {
> - env->avr[n - 32].u64[0] = vsr->u64[0];
> - env->avr[n - 32].u64[1] = vsr->u64[1];
> - }
> + env->vsr[n].u64[0] = vsr->VsrD(0);
> + env->vsr[n].u64[1] = vsr->VsrD(1);
> }
>
> void helper_compute_fprf_float16(CPUPPCState *env, float16 arg);
> diff --git a/linux-user/ppc/signal.c b/linux-user/ppc/signal.c
> index 2ae120a2bc..a053dd5b84 100644
> --- a/linux-user/ppc/signal.c
> +++ b/linux-user/ppc/signal.c
> @@ -258,8 +258,8 @@ static void save_user_regs(CPUPPCState *env, struct
> target_mcontext *frame)
> /* Save Altivec registers if necessary. */
> if (env->insns_flags & PPC_ALTIVEC) {
> uint32_t *vrsave;
> - for (i = 0; i < ARRAY_SIZE(env->avr); i++) {
> - ppc_avr_t *avr = &env->avr[i];
> + for (i = 0; i < 32; i++) {
> + ppc_avr_t *avr = &env->vsr[32 + i];
> ppc_avr_t *vreg = (ppc_avr_t *)&frame->mc_vregs.altivec[i];
>
> __put_user(avr->u64[PPC_VEC_HI], &vreg->u64[0]);
> @@ -281,15 +281,15 @@ static void save_user_regs(CPUPPCState *env, struct
> target_mcontext *frame)
> /* Save VSX second halves */
> if (env->insns_flags2 & PPC2_VSX) {
> uint64_t *vsregs = (uint64_t *)&frame->mc_vregs.altivec[34];
> - for (i = 0; i < ARRAY_SIZE(env->vsr); i++) {
> - __put_user(env->vsr[i], &vsregs[i]);
> + for (i = 0; i < 32; i++) {
> + __put_user(env->vsr[i].u64[1], &vsregs[i]);
> }
> }
>
> /* Save floating point registers. */
> if (env->insns_flags & PPC_FLOAT) {
> - for (i = 0; i < ARRAY_SIZE(env->fpr); i++) {
> - __put_user(env->fpr[i], &frame->mc_fregs[i]);
> + for (i = 0; i < 32; i++) {
> + __put_user(env->vsr[i].u64[0], &frame->mc_fregs[i]);
> }
> __put_user((uint64_t) env->fpscr, &frame->mc_fregs[32]);
> }
> @@ -373,8 +373,8 @@ static void restore_user_regs(CPUPPCState *env,
> #else
> v_regs = (ppc_avr_t *)frame->mc_vregs.altivec;
> #endif
> - for (i = 0; i < ARRAY_SIZE(env->avr); i++) {
> - ppc_avr_t *avr = &env->avr[i];
> + for (i = 0; i < 32; i++) {
> + ppc_avr_t *avr = &env->vsr[32 + i];
> ppc_avr_t *vreg = &v_regs[i];
>
> __get_user(avr->u64[PPC_VEC_HI], &vreg->u64[0]);
> @@ -393,16 +393,16 @@ static void restore_user_regs(CPUPPCState *env,
> /* Restore VSX second halves */
> if (env->insns_flags2 & PPC2_VSX) {
> uint64_t *vsregs = (uint64_t *)&frame->mc_vregs.altivec[34];
> - for (i = 0; i < ARRAY_SIZE(env->vsr); i++) {
> - __get_user(env->vsr[i], &vsregs[i]);
> + for (i = 0; i < 32; i++) {
> + __get_user(env->vsr[i].u64[1], &vsregs[i]);
> }
> }
>
> /* Restore floating point registers. */
> if (env->insns_flags & PPC_FLOAT) {
> uint64_t fpscr;
> - for (i = 0; i < ARRAY_SIZE(env->fpr); i++) {
> - __get_user(env->fpr[i], &frame->mc_fregs[i]);
> + for (i = 0; i < 32; i++) {
> + __get_user(env->vsr[i].u64[0], &frame->mc_fregs[i]);
> }
> __get_user(fpscr, &frame->mc_fregs[32]);
> env->fpscr = (uint32_t) fpscr;
> diff --git a/target/ppc/arch_dump.c b/target/ppc/arch_dump.c
> index cc1460e4e3..c272d0d3d4 100644
> --- a/target/ppc/arch_dump.c
> +++ b/target/ppc/arch_dump.c
> @@ -140,7 +140,7 @@ static void ppc_write_elf_fpregset(NoteFuncArg *arg,
> PowerPCCPU *cpu)
> memset(fpregset, 0, sizeof(*fpregset));
>
> for (i = 0; i < 32; i++) {
> - fpregset->fpr[i] = cpu_to_dump64(s, cpu->env.fpr[i]);
> + fpregset->fpr[i] = cpu_to_dump64(s, cpu->env.vsr[i].u64[0]);
> }
> fpregset->fpscr = cpu_to_dump_reg(s, cpu->env.fpscr);
> }
> @@ -166,11 +166,11 @@ static void ppc_write_elf_vmxregset(NoteFuncArg *arg,
> PowerPCCPU *cpu)
> #endif
>
> if (needs_byteswap) {
> - vmxregset->avr[i].u64[0] = bswap64(cpu->env.avr[i].u64[1]);
> - vmxregset->avr[i].u64[1] = bswap64(cpu->env.avr[i].u64[0]);
> + vmxregset->avr[i].u64[0] = bswap64(cpu->env.vsr[32 + i].u64[1]);
> + vmxregset->avr[i].u64[1] = bswap64(cpu->env.vsr[32 + i].u64[0]);
> } else {
> - vmxregset->avr[i].u64[0] = cpu->env.avr[i].u64[0];
> - vmxregset->avr[i].u64[1] = cpu->env.avr[i].u64[1];
> + vmxregset->avr[i].u64[0] = cpu->env.vsr[32 + i].u64[0];
> + vmxregset->avr[i].u64[1] = cpu->env.vsr[32 + i].u64[1];
> }
> }
> vmxregset->vscr.u32[3] = cpu_to_dump32(s, cpu->env.vscr);
> @@ -188,7 +188,7 @@ static void ppc_write_elf_vsxregset(NoteFuncArg *arg,
> PowerPCCPU *cpu)
> memset(vsxregset, 0, sizeof(*vsxregset));
>
> for (i = 0; i < 32; i++) {
> - vsxregset->vsr[i] = cpu_to_dump64(s, cpu->env.vsr[i]);
> + vsxregset->vsr[i] = cpu_to_dump64(s, cpu->env.vsr[i].u64[1]);
> }
> }
>
> diff --git a/target/ppc/gdbstub.c b/target/ppc/gdbstub.c
> index b6f6693583..8c9dc284c4 100644
> --- a/target/ppc/gdbstub.c
> +++ b/target/ppc/gdbstub.c
> @@ -126,7 +126,7 @@ int ppc_cpu_gdb_read_register(CPUState *cs, uint8_t
> *mem_buf, int n)
> gdb_get_regl(mem_buf, env->gpr[n]);
> } else if (n < 64) {
> /* fprs */
> - stfq_p(mem_buf, env->fpr[n-32]);
> + stfq_p(mem_buf, env->vsr[n - 32].u64[0]);
> } else {
> switch (n) {
> case 64:
> @@ -178,7 +178,7 @@ int ppc_cpu_gdb_read_register_apple(CPUState *cs, uint8_t
> *mem_buf, int n)
> gdb_get_reg64(mem_buf, env->gpr[n]);
> } else if (n < 64) {
> /* fprs */
> - stfq_p(mem_buf, env->fpr[n-32]);
> + stfq_p(mem_buf, env->vsr[n - 32].u64[0]);
> } else if (n < 96) {
> /* Altivec */
> stq_p(mem_buf, n - 64);
> @@ -234,7 +234,7 @@ int ppc_cpu_gdb_write_register(CPUState *cs, uint8_t
> *mem_buf, int n)
> env->gpr[n] = ldtul_p(mem_buf);
> } else if (n < 64) {
> /* fprs */
> - env->fpr[n-32] = ldfq_p(mem_buf);
> + env->vsr[n - 32].u64[0] = ldfq_p(mem_buf);
> } else {
> switch (n) {
> case 64:
> @@ -284,7 +284,7 @@ int ppc_cpu_gdb_write_register_apple(CPUState *cs,
> uint8_t *mem_buf, int n)
> env->gpr[n] = ldq_p(mem_buf);
> } else if (n < 64) {
> /* fprs */
> - env->fpr[n-32] = ldfq_p(mem_buf);
> + env->vsr[n - 32].u64[0] = ldfq_p(mem_buf);
> } else {
> switch (n) {
> case 64 + 32:
> diff --git a/target/ppc/machine.c b/target/ppc/machine.c
> index e7b3725273..451cf376b4 100644
> --- a/target/ppc/machine.c
> +++ b/target/ppc/machine.c
> @@ -45,7 +45,7 @@ static int cpu_load_old(QEMUFile *f, void *opaque, int
> version_id)
> uint64_t l;
> } u;
> u.l = qemu_get_be64(f);
> - env->fpr[i] = u.d;
> + env->vsr[i].u64[0] = u.d;
> }
> qemu_get_be32s(f, &fpscr);
> env->fpscr = fpscr;
> @@ -138,11 +138,73 @@ static const VMStateInfo vmstate_info_avr = {
> };
>
> #define VMSTATE_AVR_ARRAY_V(_f, _s, _n, _v) \
> - VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_avr, ppc_avr_t)
> + VMSTATE_SUB_ARRAY(_f, _s, 32, _n, _v, vmstate_info_avr, ppc_avr_t)
>
> #define VMSTATE_AVR_ARRAY(_f, _s, _n) \
> VMSTATE_AVR_ARRAY_V(_f, _s, _n, 0)
>
> +static int get_fpr(QEMUFile *f, void *pv, size_t size,
> + const VMStateField *field)
> +{
> + ppc_vsr_t *v = pv;
> +
> + v->u64[0] = qemu_get_be64(f);
> +
> + return 0;
> +}
> +
> +static int put_fpr(QEMUFile *f, void *pv, size_t size,
> + const VMStateField *field, QJSON *vmdesc)
> +{
> + ppc_vsr_t *v = pv;
> +
> + qemu_put_be64(f, v->u64[0]);
> + return 0;
> +}
> +
> +static const VMStateInfo vmstate_info_fpr = {
> + .name = "fpr",
> + .get = get_fpr,
> + .put = put_fpr,
> +};
> +
> +#define VMSTATE_FPR_ARRAY_V(_f, _s, _n, _v) \
> + VMSTATE_SUB_ARRAY(_f, _s, 0, _n, _v, vmstate_info_fpr, ppc_vsr_t)
> +
> +#define VMSTATE_FPR_ARRAY(_f, _s, _n) \
> + VMSTATE_FPR_ARRAY_V(_f, _s, _n, 0)
> +
> +static int get_vsr(QEMUFile *f, void *pv, size_t size,
> + const VMStateField *field)
> +{
> + ppc_vsr_t *v = pv;
> +
> + v->u64[1] = qemu_get_be64(f);
> +
> + return 0;
> +}
> +
> +static int put_vsr(QEMUFile *f, void *pv, size_t size,
> + const VMStateField *field, QJSON *vmdesc)
> +{
> + ppc_vsr_t *v = pv;
> +
> + qemu_put_be64(f, v->u64[1]);
> + return 0;
> +}
> +
> +static const VMStateInfo vmstate_info_vsr = {
> + .name = "vsr",
> + .get = get_vsr,
> + .put = put_vsr,
> +};
> +
> +#define VMSTATE_VSR_ARRAY_V(_f, _s, _n, _v) \
> + VMSTATE_SUB_ARRAY(_f, _s, 0, _n, _v, vmstate_info_vsr, ppc_vsr_t)
> +
> +#define VMSTATE_VSR_ARRAY(_f, _s, _n) \
> + VMSTATE_VSR_ARRAY_V(_f, _s, _n, 0)
> +
> static bool cpu_pre_2_8_migration(void *opaque, int version_id)
> {
> PowerPCCPU *cpu = opaque;
> @@ -354,7 +416,7 @@ static const VMStateDescription vmstate_fpu = {
> .minimum_version_id = 1,
> .needed = fpu_needed,
> .fields = (VMStateField[]) {
> - VMSTATE_FLOAT64_ARRAY(env.fpr, PowerPCCPU, 32),
> + VMSTATE_FPR_ARRAY(env.vsr, PowerPCCPU, 32),
> VMSTATE_UINTTL(env.fpscr, PowerPCCPU),
> VMSTATE_END_OF_LIST()
> },
> @@ -373,7 +435,7 @@ static const VMStateDescription vmstate_altivec = {
> .minimum_version_id = 1,
> .needed = altivec_needed,
> .fields = (VMStateField[]) {
> - VMSTATE_AVR_ARRAY(env.avr, PowerPCCPU, 32),
> + VMSTATE_AVR_ARRAY(env.vsr, PowerPCCPU, 32),
> VMSTATE_UINT32(env.vscr, PowerPCCPU),
> VMSTATE_END_OF_LIST()
> },
> @@ -392,7 +454,7 @@ static const VMStateDescription vmstate_vsx = {
> .minimum_version_id = 1,
> .needed = vsx_needed,
> .fields = (VMStateField[]) {
> - VMSTATE_UINT64_ARRAY(env.vsr, PowerPCCPU, 32),
> + VMSTATE_VSR_ARRAY(env.vsr, PowerPCCPU, 32),
> VMSTATE_END_OF_LIST()
> },
> };
> diff --git a/target/ppc/monitor.c b/target/ppc/monitor.c
> index 14915119fc..1db9396b2e 100644
> --- a/target/ppc/monitor.c
> +++ b/target/ppc/monitor.c
> @@ -123,8 +123,8 @@ int target_get_monitor_def(CPUState *cs, const char
> *name, uint64_t *pval)
>
> /* Floating point registers */
> if ((qemu_tolower(name[0]) == 'f') &&
> - ppc_cpu_get_reg_num(name + 1, ARRAY_SIZE(env->fpr), ®num)) {
> - *pval = env->fpr[regnum];
> + ppc_cpu_get_reg_num(name + 1, 32, ®num)) {
> + *pval = env->vsr[regnum].u64[0];
> return 0;
> }
>
> diff --git a/target/ppc/translate.c b/target/ppc/translate.c
> index 5923c688cd..8e89aec14d 100644
> --- a/target/ppc/translate.c
> +++ b/target/ppc/translate.c
> @@ -6657,22 +6657,22 @@ GEN_TM_PRIV_NOOP(trechkpt);
>
> static inline void get_fpr(TCGv_i64 dst, int regno)
> {
> - tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState, fpr[regno]));
> + tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState, vsr[regno].u64[0]));
> }
>
> static inline void set_fpr(int regno, TCGv_i64 src)
> {
> - tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState, fpr[regno]));
> + tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState, vsr[regno].u64[0]));
> }
>
> static inline void get_avr64(TCGv_i64 dst, int regno, bool high)
> {
> #ifdef HOST_WORDS_BIGENDIAN
> tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState,
> - avr[regno].u64[(high ? 0 : 1)]));
> + vsr[32 + regno].u64[(high ? 0 :
> 1)]));
> #else
> tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState,
> - avr[regno].u64[(high ? 1 : 0)]));
> + vsr[32 + regno].u64[(high ? 1 :
> 0)]));
> #endif
> }
>
> @@ -6680,10 +6680,10 @@ static inline void set_avr64(int regno, TCGv_i64 src,
> bool high)
> {
> #ifdef HOST_WORDS_BIGENDIAN
> tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState,
> - avr[regno].u64[(high ? 0 : 1)]));
> + vsr[32 + regno].u64[(high ? 0 :
> 1)]));
> #else
> tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState,
> - avr[regno].u64[(high ? 1 : 0)]));
> + vsr[32 + regno].u64[(high ? 1 :
> 0)]));
> #endif
> }
>
> @@ -7434,7 +7434,7 @@ void ppc_cpu_dump_state(CPUState *cs, FILE *f,
> fprintf_function cpu_fprintf,
> if ((i & (RFPL - 1)) == 0) {
> cpu_fprintf(f, "FPR%02d", i);
> }
> - cpu_fprintf(f, " %016" PRIx64, *((uint64_t *)&env->fpr[i]));
> + cpu_fprintf(f, " %016" PRIx64, *((uint64_t
> *)&env->vsr[i].u64[0]));
> if ((i & (RFPL - 1)) == (RFPL - 1)) {
> cpu_fprintf(f, "\n");
> }
> diff --git a/target/ppc/translate/dfp-impl.inc.c
> b/target/ppc/translate/dfp-impl.inc.c
> index 634ef73b8a..6c556dc2e1 100644
> --- a/target/ppc/translate/dfp-impl.inc.c
> +++ b/target/ppc/translate/dfp-impl.inc.c
> @@ -3,7 +3,7 @@
> static inline TCGv_ptr gen_fprp_ptr(int reg)
> {
> TCGv_ptr r = tcg_temp_new_ptr();
> - tcg_gen_addi_ptr(r, cpu_env, offsetof(CPUPPCState, fpr[reg]));
> + tcg_gen_addi_ptr(r, cpu_env, offsetof(CPUPPCState, vsr[reg].u64[0]));
> return r;
> }
>
> diff --git a/target/ppc/translate/vmx-impl.inc.c
> b/target/ppc/translate/vmx-impl.inc.c
> index 30046c6e31..75d2b2280f 100644
> --- a/target/ppc/translate/vmx-impl.inc.c
> +++ b/target/ppc/translate/vmx-impl.inc.c
> @@ -10,10 +10,15 @@
> static inline TCGv_ptr gen_avr_ptr(int reg)
> {
> TCGv_ptr r = tcg_temp_new_ptr();
> - tcg_gen_addi_ptr(r, cpu_env, offsetof(CPUPPCState, avr[reg]));
> + tcg_gen_addi_ptr(r, cpu_env, offsetof(CPUPPCState, vsr[32 +
> reg].u64[0]));
> return r;
> }
>
> +static inline long avr64_offset(int reg, bool high)
> +{
> + return offsetof(CPUPPCState, vsr[32 + reg].u64[(high ? 0 : 1)]);
> +}
> +
> #define GEN_VR_LDX(name, opc2, opc3)
> \
> static void glue(gen_, name)(DisasContext *ctx)
> \
> {
> \
> diff --git a/target/ppc/translate/vsx-impl.inc.c
> b/target/ppc/translate/vsx-impl.inc.c
> index 20e1fd9324..1608ad48b1 100644
> --- a/target/ppc/translate/vsx-impl.inc.c
> +++ b/target/ppc/translate/vsx-impl.inc.c
> @@ -2,12 +2,12 @@
>
> static inline void get_vsr(TCGv_i64 dst, int n)
> {
> - tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState, vsr[n]));
> + tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState, vsr[n].u64[1]));
> }
>
> static inline void set_vsr(int n, TCGv_i64 src)
> {
> - tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState, vsr[n]));
> + tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState, vsr[n].u64[1]));
> }
>
> static inline void get_cpu_vsrh(TCGv_i64 dst, int n)
> diff --git a/target/ppc/translate_init.inc.c b/target/ppc/translate_init.inc.c
> index 168d0cec28..b83097141c 100644
> --- a/target/ppc/translate_init.inc.c
> +++ b/target/ppc/translate_init.inc.c
> @@ -9486,7 +9486,7 @@ static bool avr_need_swap(CPUPPCState *env)
> static int gdb_get_float_reg(CPUPPCState *env, uint8_t *mem_buf, int n)
> {
> if (n < 32) {
> - stfq_p(mem_buf, env->fpr[n]);
> + stfq_p(mem_buf, env->vsr[n].u64[0]);
> ppc_maybe_bswap_register(env, mem_buf, 8);
> return 8;
> }
> @@ -9502,7 +9502,7 @@ static int gdb_set_float_reg(CPUPPCState *env, uint8_t
> *mem_buf, int n)
> {
> if (n < 32) {
> ppc_maybe_bswap_register(env, mem_buf, 8);
> - env->fpr[n] = ldfq_p(mem_buf);
> + env->vsr[n].u64[0] = ldfq_p(mem_buf);
> return 8;
> }
> if (n == 32) {
> @@ -9517,11 +9517,11 @@ static int gdb_get_avr_reg(CPUPPCState *env, uint8_t
> *mem_buf, int n)
> {
> if (n < 32) {
> if (!avr_need_swap(env)) {
> - stq_p(mem_buf, env->avr[n].u64[0]);
> - stq_p(mem_buf+8, env->avr[n].u64[1]);
> + stq_p(mem_buf, env->vsr[32 + n].u64[0]);
> + stq_p(mem_buf + 8, env->vsr[32 + n].u64[1]);
> } else {
> - stq_p(mem_buf, env->avr[n].u64[1]);
> - stq_p(mem_buf+8, env->avr[n].u64[0]);
> + stq_p(mem_buf, env->vsr[32 + n].u64[1]);
> + stq_p(mem_buf + 8, env->vsr[32 + n].u64[0]);
> }
> ppc_maybe_bswap_register(env, mem_buf, 8);
> ppc_maybe_bswap_register(env, mem_buf + 8, 8);
> @@ -9546,11 +9546,11 @@ static int gdb_set_avr_reg(CPUPPCState *env, uint8_t
> *mem_buf, int n)
> ppc_maybe_bswap_register(env, mem_buf, 8);
> ppc_maybe_bswap_register(env, mem_buf + 8, 8);
> if (!avr_need_swap(env)) {
> - env->avr[n].u64[0] = ldq_p(mem_buf);
> - env->avr[n].u64[1] = ldq_p(mem_buf+8);
> + env->vsr[32 + n].u64[0] = ldq_p(mem_buf);
> + env->vsr[32 + n].u64[1] = ldq_p(mem_buf + 8);
> } else {
> - env->avr[n].u64[1] = ldq_p(mem_buf);
> - env->avr[n].u64[0] = ldq_p(mem_buf+8);
> + env->vsr[32 + n].u64[1] = ldq_p(mem_buf);
> + env->vsr[32 + n].u64[0] = ldq_p(mem_buf + 8);
> }
> return 16;
> }
> @@ -9623,7 +9623,7 @@ static int gdb_set_spe_reg(CPUPPCState *env, uint8_t
> *mem_buf, int n)
> static int gdb_get_vsx_reg(CPUPPCState *env, uint8_t *mem_buf, int n)
> {
> if (n < 32) {
> - stq_p(mem_buf, env->vsr[n]);
> + stq_p(mem_buf, env->vsr[n].u64[1]);
> ppc_maybe_bswap_register(env, mem_buf, 8);
> return 8;
> }
> @@ -9634,7 +9634,7 @@ static int gdb_set_vsx_reg(CPUPPCState *env, uint8_t
> *mem_buf, int n)
> {
> if (n < 32) {
> ppc_maybe_bswap_register(env, mem_buf, 8);
> - env->vsr[n] = ldq_p(mem_buf);
> + env->vsr[n].u64[1] = ldq_p(mem_buf);
> return 8;
> }
> return 0;
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
signature.asc
Description: PGP signature
- [Qemu-ppc] [PATCH 00/34] tcg, target/ppc vector improvements, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 03/34] tcg: Add gvec expanders for nand, nor, eqv, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 05/34] tcg: Add opcodes for vector saturated arithmetic, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 08/34] tcg/i386: Implement vector minmax arithmetic, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 12/34] target/ppc: introduce get_avr64() and set_avr64() helpers for VMX register access, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 16/34] target/ppc: move FP and VMX registers into aligned vsr register array, Richard Henderson, 2018/12/18
- Re: [Qemu-ppc] [PATCH 16/34] target/ppc: move FP and VMX registers into aligned vsr register array,
David Gibson <=
- [Qemu-ppc] [PATCH 01/34] tcg: Add logical simplifications during gvec expand, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 25/34] target/ppc: convert xxsel to vector operations, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 15/34] target/ppc: merge ppc_vsr_t and ppc_avr_t union types, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 06/34] tcg/i386: Implement vector saturating arithmetic, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 18/34] target/ppc: convert vaddu[b, h, w, d] and vsubu[b, h, w, d] over to use vector operations, Richard Henderson, 2018/12/18
- [Qemu-ppc] [PATCH 30/34] target/ppc: Use mtvscr/mfvscr for vmstate, Richard Henderson, 2018/12/18