diff mbox series

[03/13] target/ppc: Use atomic store for STQ

Message ID 20180626161921.27941-4-richard.henderson@linaro.org
State Superseded
Headers show
Series target/ppc improve atomic operations | expand

Commit Message

Richard Henderson June 26, 2018, 4:19 p.m. UTC 
Section 1.4 of the Power ISA v3.0B states that this insn is
single-copy atomic.  As we cannot (yet) issue 128-bit loads
within TCG, use the generic helpers provided.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/ppc/helper.h     |  4 ++++
 target/ppc/mem_helper.c | 14 ++++++++++++++
 target/ppc/translate.c  | 35 +++++++++++++++++++++++++++--------
 3 files changed, 45 insertions(+), 8 deletions(-)

-- 
2.17.1

Comments

David Gibson June 28, 2018, 3:51 a.m. UTC | #1 
On Tue, Jun 26, 2018 at 09:19:11AM -0700, Richard Henderson wrote:
> Section 1.4 of the Power ISA v3.0B states that this insn is

> single-copy atomic.  As we cannot (yet) issue 128-bit loads


nit: s/loads/stores/

> within TCG, use the generic helpers provided.

> 

> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

> ---

>  target/ppc/helper.h     |  4 ++++

>  target/ppc/mem_helper.c | 14 ++++++++++++++

>  target/ppc/translate.c  | 35 +++++++++++++++++++++++++++--------

>  3 files changed, 45 insertions(+), 8 deletions(-)

> 

> diff --git a/target/ppc/helper.h b/target/ppc/helper.h

> index 3f451a5d7e..cbc1228570 100644

> --- a/target/ppc/helper.h

> +++ b/target/ppc/helper.h

> @@ -803,4 +803,8 @@ DEF_HELPER_FLAGS_1(fixup_thrm, TCG_CALL_NO_RWG, void, env)

>  #if defined(TARGET_PPC64) && defined(CONFIG_ATOMIC128)

>  DEF_HELPER_FLAGS_3(lq_le_parallel, TCG_CALL_NO_WG, i64, env, tl, i32)

>  DEF_HELPER_FLAGS_3(lq_be_parallel, TCG_CALL_NO_WG, i64, env, tl, i32)

> +DEF_HELPER_FLAGS_5(stq_le_parallel, TCG_CALL_NO_WG,

> +                   void, env, tl, i64, i64, i32)

> +DEF_HELPER_FLAGS_5(stq_be_parallel, TCG_CALL_NO_WG,

> +                   void, env, tl, i64, i64, i32)

>  #endif

> diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c

> index 44a8f3445a..57e301edc3 100644

> --- a/target/ppc/mem_helper.c

> +++ b/target/ppc/mem_helper.c

> @@ -231,6 +231,20 @@ uint64_t helper_lq_be_parallel(CPUPPCState *env, target_ulong addr,

>      env->retxh = int128_gethi(ret);

>      return int128_getlo(ret);

>  }

> +

> +void helper_stq_le_parallel(CPUPPCState *env, target_ulong addr,

> +                            uint64_t lo, uint64_t hi, uint32_t opidx)

> +{

> +    Int128 val = int128_make128(lo, hi);

> +    helper_atomic_sto_le_mmu(env, addr, val, opidx, GETPC());

> +}

> +

> +void helper_stq_be_parallel(CPUPPCState *env, target_ulong addr,

> +                            uint64_t lo, uint64_t hi, uint32_t opidx)

> +{

> +    Int128 val = int128_make128(lo, hi);

> +    helper_atomic_sto_be_mmu(env, addr, val, opidx, GETPC());

> +}

>  #endif

>  

>  /*****************************************************************************/

> diff --git a/target/ppc/translate.c b/target/ppc/translate.c

> index 0923cc24e3..3d63a62269 100644

> --- a/target/ppc/translate.c

> +++ b/target/ppc/translate.c

> @@ -2760,6 +2760,7 @@ static void gen_std(DisasContext *ctx)

>      if ((ctx->opcode & 0x3) == 0x2) { /* stq */

>          bool legal_in_user_mode = (ctx->insns_flags2 & PPC2_LSQ_ISA207) != 0;

>          bool le_is_supported = (ctx->insns_flags2 & PPC2_LSQ_ISA207) != 0;

> +        TCGv hi, lo;

>  

>          if (!(ctx->insns_flags & PPC_64BX)) {

>              gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL);

> @@ -2783,20 +2784,38 @@ static void gen_std(DisasContext *ctx)

>          EA = tcg_temp_new();

>          gen_addr_imm_index(ctx, EA, 0x03);

>  

> -        /* We only need to swap high and low halves. gen_qemu_st64_i64 does

> -           necessary 64-bit byteswap already. */

> -        if (unlikely(ctx->le_mode)) {

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs + 1], EA);

> +        /* Note that the low part is always in RS+1, even in LE mode.  */

> +        lo = cpu_gpr[rs + 1];

> +        hi = cpu_gpr[rs];

> +

> +        if (tb_cflags(ctx->base.tb) & CF_PARALLEL) {

> +#ifdef CONFIG_ATOMIC128

> +            TCGv_i32 oi = tcg_temp_new_i32();

> +            if (ctx->le_mode) {

> +                tcg_gen_movi_i32(oi, make_memop_idx(MO_LEQ, ctx->mem_idx));

> +                gen_helper_stq_le_parallel(cpu_env, EA, lo, hi, oi);

> +            } else {

> +                tcg_gen_movi_i32(oi, make_memop_idx(MO_BEQ, ctx->mem_idx));

> +                gen_helper_stq_be_parallel(cpu_env, EA, lo, hi, oi);

> +            }

> +            tcg_temp_free_i32(oi);

> +#else

> +            /* Restart with exclusive lock.  */

> +            gen_helper_exit_atomic(cpu_env);

> +            ctx->base.is_jmp = DISAS_NORETURN;

> +#endif

> +        } else if (ctx->le_mode) {

> +            tcg_gen_qemu_st_i64(lo, EA, ctx->mem_idx, MO_LEQ);

>              gen_addr_add(ctx, EA, EA, 8);

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs], EA);

> +            tcg_gen_qemu_st_i64(hi, EA, ctx->mem_idx, MO_LEQ);

>          } else {

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs], EA);

> +            tcg_gen_qemu_st_i64(hi, EA, ctx->mem_idx, MO_BEQ);

>              gen_addr_add(ctx, EA, EA, 8);

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs + 1], EA);

> +            tcg_gen_qemu_st_i64(lo, EA, ctx->mem_idx, MO_BEQ);

>          }

>          tcg_temp_free(EA);

>      } else {

> -        /* std / stdu*/

> +        /* std / stdu */

>          if (Rc(ctx->opcode)) {

>              if (unlikely(rA(ctx->opcode) == 0)) {

>                  gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL);


-- 
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
David Gibson June 29, 2018, 3:33 a.m. UTC | #2 
On Tue, Jun 26, 2018 at 09:19:11AM -0700, Richard Henderson wrote:
> Section 1.4 of the Power ISA v3.0B states that this insn is

> single-copy atomic.  As we cannot (yet) issue 128-bit loads

> within TCG, use the generic helpers provided.

> 

> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>


Applied to ppc-for-3.0, thanks.

> ---

>  target/ppc/helper.h     |  4 ++++

>  target/ppc/mem_helper.c | 14 ++++++++++++++

>  target/ppc/translate.c  | 35 +++++++++++++++++++++++++++--------

>  3 files changed, 45 insertions(+), 8 deletions(-)

> 

> diff --git a/target/ppc/helper.h b/target/ppc/helper.h

> index 3f451a5d7e..cbc1228570 100644

> --- a/target/ppc/helper.h

> +++ b/target/ppc/helper.h

> @@ -803,4 +803,8 @@ DEF_HELPER_FLAGS_1(fixup_thrm, TCG_CALL_NO_RWG, void, env)

>  #if defined(TARGET_PPC64) && defined(CONFIG_ATOMIC128)

>  DEF_HELPER_FLAGS_3(lq_le_parallel, TCG_CALL_NO_WG, i64, env, tl, i32)

>  DEF_HELPER_FLAGS_3(lq_be_parallel, TCG_CALL_NO_WG, i64, env, tl, i32)

> +DEF_HELPER_FLAGS_5(stq_le_parallel, TCG_CALL_NO_WG,

> +                   void, env, tl, i64, i64, i32)

> +DEF_HELPER_FLAGS_5(stq_be_parallel, TCG_CALL_NO_WG,

> +                   void, env, tl, i64, i64, i32)

>  #endif

> diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c

> index 44a8f3445a..57e301edc3 100644

> --- a/target/ppc/mem_helper.c

> +++ b/target/ppc/mem_helper.c

> @@ -231,6 +231,20 @@ uint64_t helper_lq_be_parallel(CPUPPCState *env, target_ulong addr,

>      env->retxh = int128_gethi(ret);

>      return int128_getlo(ret);

>  }

> +

> +void helper_stq_le_parallel(CPUPPCState *env, target_ulong addr,

> +                            uint64_t lo, uint64_t hi, uint32_t opidx)

> +{

> +    Int128 val = int128_make128(lo, hi);

> +    helper_atomic_sto_le_mmu(env, addr, val, opidx, GETPC());

> +}

> +

> +void helper_stq_be_parallel(CPUPPCState *env, target_ulong addr,

> +                            uint64_t lo, uint64_t hi, uint32_t opidx)

> +{

> +    Int128 val = int128_make128(lo, hi);

> +    helper_atomic_sto_be_mmu(env, addr, val, opidx, GETPC());

> +}

>  #endif

>  

>  /*****************************************************************************/

> diff --git a/target/ppc/translate.c b/target/ppc/translate.c

> index 0923cc24e3..3d63a62269 100644

> --- a/target/ppc/translate.c

> +++ b/target/ppc/translate.c

> @@ -2760,6 +2760,7 @@ static void gen_std(DisasContext *ctx)

>      if ((ctx->opcode & 0x3) == 0x2) { /* stq */

>          bool legal_in_user_mode = (ctx->insns_flags2 & PPC2_LSQ_ISA207) != 0;

>          bool le_is_supported = (ctx->insns_flags2 & PPC2_LSQ_ISA207) != 0;

> +        TCGv hi, lo;

>  

>          if (!(ctx->insns_flags & PPC_64BX)) {

>              gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL);

> @@ -2783,20 +2784,38 @@ static void gen_std(DisasContext *ctx)

>          EA = tcg_temp_new();

>          gen_addr_imm_index(ctx, EA, 0x03);

>  

> -        /* We only need to swap high and low halves. gen_qemu_st64_i64 does

> -           necessary 64-bit byteswap already. */

> -        if (unlikely(ctx->le_mode)) {

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs + 1], EA);

> +        /* Note that the low part is always in RS+1, even in LE mode.  */

> +        lo = cpu_gpr[rs + 1];

> +        hi = cpu_gpr[rs];

> +

> +        if (tb_cflags(ctx->base.tb) & CF_PARALLEL) {

> +#ifdef CONFIG_ATOMIC128

> +            TCGv_i32 oi = tcg_temp_new_i32();

> +            if (ctx->le_mode) {

> +                tcg_gen_movi_i32(oi, make_memop_idx(MO_LEQ, ctx->mem_idx));

> +                gen_helper_stq_le_parallel(cpu_env, EA, lo, hi, oi);

> +            } else {

> +                tcg_gen_movi_i32(oi, make_memop_idx(MO_BEQ, ctx->mem_idx));

> +                gen_helper_stq_be_parallel(cpu_env, EA, lo, hi, oi);

> +            }

> +            tcg_temp_free_i32(oi);

> +#else

> +            /* Restart with exclusive lock.  */

> +            gen_helper_exit_atomic(cpu_env);

> +            ctx->base.is_jmp = DISAS_NORETURN;

> +#endif

> +        } else if (ctx->le_mode) {

> +            tcg_gen_qemu_st_i64(lo, EA, ctx->mem_idx, MO_LEQ);

>              gen_addr_add(ctx, EA, EA, 8);

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs], EA);

> +            tcg_gen_qemu_st_i64(hi, EA, ctx->mem_idx, MO_LEQ);

>          } else {

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs], EA);

> +            tcg_gen_qemu_st_i64(hi, EA, ctx->mem_idx, MO_BEQ);

>              gen_addr_add(ctx, EA, EA, 8);

> -            gen_qemu_st64_i64(ctx, cpu_gpr[rs + 1], EA);

> +            tcg_gen_qemu_st_i64(lo, EA, ctx->mem_idx, MO_BEQ);

>          }

>          tcg_temp_free(EA);

>      } else {

> -        /* std / stdu*/

> +        /* std / stdu */

>          if (Rc(ctx->opcode)) {

>              if (unlikely(rA(ctx->opcode) == 0)) {

>                  gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL);


-- 
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
diff mbox series

Patch

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 3f451a5d7e..cbc1228570 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -803,4 +803,8 @@  DEF_HELPER_FLAGS_1(fixup_thrm, TCG_CALL_NO_RWG, void, env)
 #if defined(TARGET_PPC64) && defined(CONFIG_ATOMIC128)
 DEF_HELPER_FLAGS_3(lq_le_parallel, TCG_CALL_NO_WG, i64, env, tl, i32)
 DEF_HELPER_FLAGS_3(lq_be_parallel, TCG_CALL_NO_WG, i64, env, tl, i32)
+DEF_HELPER_FLAGS_5(stq_le_parallel, TCG_CALL_NO_WG,
+                   void, env, tl, i64, i64, i32)
+DEF_HELPER_FLAGS_5(stq_be_parallel, TCG_CALL_NO_WG,
+                   void, env, tl, i64, i64, i32)
 #endif
diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c
index 44a8f3445a..57e301edc3 100644
--- a/target/ppc/mem_helper.c
+++ b/target/ppc/mem_helper.c
@@ -231,6 +231,20 @@  uint64_t helper_lq_be_parallel(CPUPPCState *env, target_ulong addr,
     env->retxh = int128_gethi(ret);
     return int128_getlo(ret);
 }
+
+void helper_stq_le_parallel(CPUPPCState *env, target_ulong addr,
+                            uint64_t lo, uint64_t hi, uint32_t opidx)
+{
+    Int128 val = int128_make128(lo, hi);
+    helper_atomic_sto_le_mmu(env, addr, val, opidx, GETPC());
+}
+
+void helper_stq_be_parallel(CPUPPCState *env, target_ulong addr,
+                            uint64_t lo, uint64_t hi, uint32_t opidx)
+{
+    Int128 val = int128_make128(lo, hi);
+    helper_atomic_sto_be_mmu(env, addr, val, opidx, GETPC());
+}
 #endif
 
 /*****************************************************************************/
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 0923cc24e3..3d63a62269 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -2760,6 +2760,7 @@  static void gen_std(DisasContext *ctx)
     if ((ctx->opcode & 0x3) == 0x2) { /* stq */
         bool legal_in_user_mode = (ctx->insns_flags2 & PPC2_LSQ_ISA207) != 0;
         bool le_is_supported = (ctx->insns_flags2 & PPC2_LSQ_ISA207) != 0;
+        TCGv hi, lo;
 
         if (!(ctx->insns_flags & PPC_64BX)) {
             gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL);
@@ -2783,20 +2784,38 @@  static void gen_std(DisasContext *ctx)
         EA = tcg_temp_new();
         gen_addr_imm_index(ctx, EA, 0x03);
 
-        /* We only need to swap high and low halves. gen_qemu_st64_i64 does
-           necessary 64-bit byteswap already. */
-        if (unlikely(ctx->le_mode)) {
-            gen_qemu_st64_i64(ctx, cpu_gpr[rs + 1], EA);
+        /* Note that the low part is always in RS+1, even in LE mode.  */
+        lo = cpu_gpr[rs + 1];
+        hi = cpu_gpr[rs];
+
+        if (tb_cflags(ctx->base.tb) & CF_PARALLEL) {
+#ifdef CONFIG_ATOMIC128
+            TCGv_i32 oi = tcg_temp_new_i32();
+            if (ctx->le_mode) {
+                tcg_gen_movi_i32(oi, make_memop_idx(MO_LEQ, ctx->mem_idx));
+                gen_helper_stq_le_parallel(cpu_env, EA, lo, hi, oi);
+            } else {
+                tcg_gen_movi_i32(oi, make_memop_idx(MO_BEQ, ctx->mem_idx));
+                gen_helper_stq_be_parallel(cpu_env, EA, lo, hi, oi);
+            }
+            tcg_temp_free_i32(oi);
+#else
+            /* Restart with exclusive lock.  */
+            gen_helper_exit_atomic(cpu_env);
+            ctx->base.is_jmp = DISAS_NORETURN;
+#endif
+        } else if (ctx->le_mode) {
+            tcg_gen_qemu_st_i64(lo, EA, ctx->mem_idx, MO_LEQ);
             gen_addr_add(ctx, EA, EA, 8);
-            gen_qemu_st64_i64(ctx, cpu_gpr[rs], EA);
+            tcg_gen_qemu_st_i64(hi, EA, ctx->mem_idx, MO_LEQ);
         } else {
-            gen_qemu_st64_i64(ctx, cpu_gpr[rs], EA);
+            tcg_gen_qemu_st_i64(hi, EA, ctx->mem_idx, MO_BEQ);
             gen_addr_add(ctx, EA, EA, 8);
-            gen_qemu_st64_i64(ctx, cpu_gpr[rs + 1], EA);
+            tcg_gen_qemu_st_i64(lo, EA, ctx->mem_idx, MO_BEQ);
         }
         tcg_temp_free(EA);
     } else {
-        /* std / stdu*/
+        /* std / stdu */
         if (Rc(ctx->opcode)) {
             if (unlikely(rA(ctx->opcode) == 0)) {
                 gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL);