[PATCH v3 8/8] target/ppc: Add SMT support to time facilities

Nicholas Piggin posted 8 patches 12 months ago
Maintainers: Nicholas Piggin <npiggin@gmail.com>, Daniel Henrique Barboza <danielhb413@gmail.com>, "Cédric Le Goater" <clg@kaod.org>, "Frédéric Barrat" <fbarrat@linux.ibm.com>
[PATCH v3 8/8] target/ppc: Add SMT support to time facilities
Posted by Nicholas Piggin 12 months ago
The TB, VTB, PURR, HDEC SPRs are per-LPAR registers, and the TFMR is a
per-core register. Add the necessary SMT synchronisation and value
sharing.

The TFMR can only drive the timebase state machine via thread 0 of the
core, which is almost certainly not right, but it is enough for skiboot
and certain other proprietary firmware.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 target/ppc/timebase_helper.c | 105 ++++++++++++++++++++++++++++++++---
 target/ppc/translate.c       |  42 +++++++++++++-
 2 files changed, 136 insertions(+), 11 deletions(-)

diff --git a/target/ppc/timebase_helper.c b/target/ppc/timebase_helper.c
index bc1d54a427..a23fbf75ff 100644
--- a/target/ppc/timebase_helper.c
+++ b/target/ppc/timebase_helper.c
@@ -60,19 +60,55 @@ target_ulong helper_load_purr(CPUPPCState *env)
 
 void helper_store_purr(CPUPPCState *env, target_ulong val)
 {
-    cpu_ppc_store_purr(env, val);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+
+    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
+        cpu_ppc_store_purr(env, val);
+        return;
+    }
+
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+        cpu_ppc_store_purr(cenv, val);
+    }
 }
 #endif
 
 #if !defined(CONFIG_USER_ONLY)
 void helper_store_tbl(CPUPPCState *env, target_ulong val)
 {
-    cpu_ppc_store_tbl(env, val);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+
+    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
+        cpu_ppc_store_tbl(env, val);
+        return;
+    }
+
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+        cpu_ppc_store_tbl(cenv, val);
+    }
 }
 
 void helper_store_tbu(CPUPPCState *env, target_ulong val)
 {
-    cpu_ppc_store_tbu(env, val);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+
+    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
+        cpu_ppc_store_tbu(env, val);
+        return;
+    }
+
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+        cpu_ppc_store_tbu(cenv, val);
+    }
 }
 
 void helper_store_atbl(CPUPPCState *env, target_ulong val)
@@ -102,17 +138,53 @@ target_ulong helper_load_hdecr(CPUPPCState *env)
 
 void helper_store_hdecr(CPUPPCState *env, target_ulong val)
 {
-    cpu_ppc_store_hdecr(env, val);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+
+    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
+        cpu_ppc_store_hdecr(env, val);
+        return;
+    }
+
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+        cpu_ppc_store_hdecr(cenv, val);
+    }
 }
 
 void helper_store_vtb(CPUPPCState *env, target_ulong val)
 {
-    cpu_ppc_store_vtb(env, val);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+
+    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
+        cpu_ppc_store_vtb(env, val);
+        return;
+    }
+
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+        cpu_ppc_store_vtb(cenv, val);
+    }
 }
 
 void helper_store_tbu40(CPUPPCState *env, target_ulong val)
 {
-    cpu_ppc_store_tbu40(env, val);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+
+    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
+        cpu_ppc_store_tbu40(env, val);
+        return;
+    }
+
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+        cpu_ppc_store_tbu40(cenv, val);
+    }
 }
 
 target_ulong helper_load_40x_pit(CPUPPCState *env)
@@ -211,6 +283,21 @@ static uint64_t tfmr_new_tb_state(uint64_t tfmr, unsigned int tbst)
     return tfmr;
 }
 
+static void write_tfmr(CPUPPCState *env, target_ulong val)
+{
+    CPUState *cs = env_cpu(env);
+
+    if (cs->nr_threads == 1) {
+        env->spr[SPR_TFMR] = val;
+    } else {
+        CPUState *ccs;
+        THREAD_SIBLING_FOREACH(cs, ccs) {
+            CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
+            cenv->spr[SPR_TFMR] = val;
+        }
+    }
+}
+
 static void tb_state_machine_step(CPUPPCState *env)
 {
     uint64_t tfmr = env->spr[SPR_TFMR];
@@ -224,7 +311,7 @@ static void tb_state_machine_step(CPUPPCState *env)
         env->pnv_tod_tbst.tb_sync_pulse_timer--;
     } else {
         tfmr |= TFMR_TB_SYNC_OCCURED;
-        env->spr[SPR_TFMR] = tfmr;
+        write_tfmr(env, tfmr);
     }
 
     if (env->pnv_tod_tbst.tb_state_timer) {
@@ -262,7 +349,7 @@ static void tb_state_machine_step(CPUPPCState *env)
         }
     }
 
-    env->spr[SPR_TFMR] = tfmr;
+    write_tfmr(env, tfmr);
 }
 
 target_ulong helper_load_tfmr(CPUPPCState *env)
@@ -357,7 +444,7 @@ void helper_store_tfmr(CPUPPCState *env, target_ulong val)
     }
 
 out:
-    env->spr[SPR_TFMR] = tfmr;
+    write_tfmr(env, tfmr);
 }
 #endif
 
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 329da4d518..bd103b1026 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -247,13 +247,24 @@ static inline bool gen_serialize(DisasContext *ctx)
     return true;
 }
 
-#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY)
+#if !defined(CONFIG_USER_ONLY)
+#if defined(TARGET_PPC64)
+static inline bool gen_serialize_core(DisasContext *ctx)
+{
+    if (ctx->flags & POWERPC_FLAG_SMT) {
+        return gen_serialize(ctx);
+    }
+    return true;
+}
+#endif
+
 static inline bool gen_serialize_core_lpar(DisasContext *ctx)
 {
+#if defined(TARGET_PPC64)
     if (ctx->flags & POWERPC_FLAG_SMT_1LPAR) {
         return gen_serialize(ctx);
     }
-
+#endif
     return true;
 }
 #endif
@@ -667,12 +678,20 @@ void spr_read_atbu(DisasContext *ctx, int gprn, int sprn)
 #if !defined(CONFIG_USER_ONLY)
 void spr_write_tbl(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core_lpar(ctx)) {
+        return;
+    }
+
     translator_io_start(&ctx->base);
     gen_helper_store_tbl(tcg_env, cpu_gpr[gprn]);
 }
 
 void spr_write_tbu(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core_lpar(ctx)) {
+        return;
+    }
+
     translator_io_start(&ctx->base);
     gen_helper_store_tbu(tcg_env, cpu_gpr[gprn]);
 }
@@ -696,6 +715,9 @@ void spr_read_purr(DisasContext *ctx, int gprn, int sprn)
 
 void spr_write_purr(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core_lpar(ctx)) {
+        return;
+    }
     translator_io_start(&ctx->base);
     gen_helper_store_purr(tcg_env, cpu_gpr[gprn]);
 }
@@ -709,6 +731,9 @@ void spr_read_hdecr(DisasContext *ctx, int gprn, int sprn)
 
 void spr_write_hdecr(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core_lpar(ctx)) {
+        return;
+    }
     translator_io_start(&ctx->base);
     gen_helper_store_hdecr(tcg_env, cpu_gpr[gprn]);
 }
@@ -721,12 +746,18 @@ void spr_read_vtb(DisasContext *ctx, int gprn, int sprn)
 
 void spr_write_vtb(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core_lpar(ctx)) {
+        return;
+    }
     translator_io_start(&ctx->base);
     gen_helper_store_vtb(tcg_env, cpu_gpr[gprn]);
 }
 
 void spr_write_tbu40(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core_lpar(ctx)) {
+        return;
+    }
     translator_io_start(&ctx->base);
     gen_helper_store_tbu40(tcg_env, cpu_gpr[gprn]);
 }
@@ -1220,11 +1251,18 @@ void spr_write_hmer(DisasContext *ctx, int sprn, int gprn)
 
 void spr_read_tfmr(DisasContext *ctx, int gprn, int sprn)
 {
+    /* Reading TFMR can cause it to be updated, so serialize threads here too */
+    if (!gen_serialize_core(ctx)) {
+        return;
+    }
     gen_helper_load_tfmr(cpu_gpr[gprn], tcg_env);
 }
 
 void spr_write_tfmr(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core(ctx)) {
+        return;
+    }
     gen_helper_store_tfmr(tcg_env, cpu_gpr[gprn]);
 }
 
-- 
2.42.0
Re: [PATCH v3 8/8] target/ppc: Add SMT support to time facilities
Posted by Cédric Le Goater 10 months, 1 week ago
On 12/1/23 13:16, Nicholas Piggin wrote:
> The TB, VTB, PURR, HDEC SPRs are per-LPAR registers, and the TFMR is a
> per-core register. Add the necessary SMT synchronisation and value
> sharing.
> 
> The TFMR can only drive the timebase state machine via thread 0 of the
> core, which is almost certainly not right, but it is enough for skiboot
> and certain other proprietary firmware.
> 
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>


Acked-by: Cédric Le Goater <clg@kaod.org>

Thanks,

C.


> ---
>   target/ppc/timebase_helper.c | 105 ++++++++++++++++++++++++++++++++---
>   target/ppc/translate.c       |  42 +++++++++++++-
>   2 files changed, 136 insertions(+), 11 deletions(-)
> 
> diff --git a/target/ppc/timebase_helper.c b/target/ppc/timebase_helper.c
> index bc1d54a427..a23fbf75ff 100644
> --- a/target/ppc/timebase_helper.c
> +++ b/target/ppc/timebase_helper.c
> @@ -60,19 +60,55 @@ target_ulong helper_load_purr(CPUPPCState *env)
>   
>   void helper_store_purr(CPUPPCState *env, target_ulong val)
>   {
> -    cpu_ppc_store_purr(env, val);
> +    CPUState *cs = env_cpu(env);
> +    CPUState *ccs;
> +    uint32_t nr_threads = cs->nr_threads;
> +
> +    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
> +        cpu_ppc_store_purr(env, val);
> +        return;
> +    }
> +
> +    THREAD_SIBLING_FOREACH(cs, ccs) {
> +        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +        cpu_ppc_store_purr(cenv, val);
> +    }
>   }
>   #endif
>   
>   #if !defined(CONFIG_USER_ONLY)
>   void helper_store_tbl(CPUPPCState *env, target_ulong val)
>   {
> -    cpu_ppc_store_tbl(env, val);
> +    CPUState *cs = env_cpu(env);
> +    CPUState *ccs;
> +    uint32_t nr_threads = cs->nr_threads;
> +
> +    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
> +        cpu_ppc_store_tbl(env, val);
> +        return;
> +    }
> +
> +    THREAD_SIBLING_FOREACH(cs, ccs) {
> +        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +        cpu_ppc_store_tbl(cenv, val);
> +    }
>   }
>   
>   void helper_store_tbu(CPUPPCState *env, target_ulong val)
>   {
> -    cpu_ppc_store_tbu(env, val);
> +    CPUState *cs = env_cpu(env);
> +    CPUState *ccs;
> +    uint32_t nr_threads = cs->nr_threads;
> +
> +    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
> +        cpu_ppc_store_tbu(env, val);
> +        return;
> +    }
> +
> +    THREAD_SIBLING_FOREACH(cs, ccs) {
> +        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +        cpu_ppc_store_tbu(cenv, val);
> +    }
>   }
>   
>   void helper_store_atbl(CPUPPCState *env, target_ulong val)
> @@ -102,17 +138,53 @@ target_ulong helper_load_hdecr(CPUPPCState *env)
>   
>   void helper_store_hdecr(CPUPPCState *env, target_ulong val)
>   {
> -    cpu_ppc_store_hdecr(env, val);
> +    CPUState *cs = env_cpu(env);
> +    CPUState *ccs;
> +    uint32_t nr_threads = cs->nr_threads;
> +
> +    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
> +        cpu_ppc_store_hdecr(env, val);
> +        return;
> +    }
> +
> +    THREAD_SIBLING_FOREACH(cs, ccs) {
> +        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +        cpu_ppc_store_hdecr(cenv, val);
> +    }
>   }
>   
>   void helper_store_vtb(CPUPPCState *env, target_ulong val)
>   {
> -    cpu_ppc_store_vtb(env, val);
> +    CPUState *cs = env_cpu(env);
> +    CPUState *ccs;
> +    uint32_t nr_threads = cs->nr_threads;
> +
> +    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
> +        cpu_ppc_store_vtb(env, val);
> +        return;
> +    }
> +
> +    THREAD_SIBLING_FOREACH(cs, ccs) {
> +        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +        cpu_ppc_store_vtb(cenv, val);
> +    }
>   }
>   
>   void helper_store_tbu40(CPUPPCState *env, target_ulong val)
>   {
> -    cpu_ppc_store_tbu40(env, val);
> +    CPUState *cs = env_cpu(env);
> +    CPUState *ccs;
> +    uint32_t nr_threads = cs->nr_threads;
> +
> +    if (nr_threads == 1 || !(env->flags & POWERPC_FLAG_SMT_1LPAR)) {
> +        cpu_ppc_store_tbu40(env, val);
> +        return;
> +    }
> +
> +    THREAD_SIBLING_FOREACH(cs, ccs) {
> +        CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +        cpu_ppc_store_tbu40(cenv, val);
> +    }
>   }
>   
>   target_ulong helper_load_40x_pit(CPUPPCState *env)
> @@ -211,6 +283,21 @@ static uint64_t tfmr_new_tb_state(uint64_t tfmr, unsigned int tbst)
>       return tfmr;
>   }
>   
> +static void write_tfmr(CPUPPCState *env, target_ulong val)
> +{
> +    CPUState *cs = env_cpu(env);
> +
> +    if (cs->nr_threads == 1) {
> +        env->spr[SPR_TFMR] = val;
> +    } else {
> +        CPUState *ccs;
> +        THREAD_SIBLING_FOREACH(cs, ccs) {
> +            CPUPPCState *cenv = &POWERPC_CPU(ccs)->env;
> +            cenv->spr[SPR_TFMR] = val;
> +        }
> +    }
> +}
> +
>   static void tb_state_machine_step(CPUPPCState *env)
>   {
>       uint64_t tfmr = env->spr[SPR_TFMR];
> @@ -224,7 +311,7 @@ static void tb_state_machine_step(CPUPPCState *env)
>           env->pnv_tod_tbst.tb_sync_pulse_timer--;
>       } else {
>           tfmr |= TFMR_TB_SYNC_OCCURED;
> -        env->spr[SPR_TFMR] = tfmr;
> +        write_tfmr(env, tfmr);
>       }
>   
>       if (env->pnv_tod_tbst.tb_state_timer) {
> @@ -262,7 +349,7 @@ static void tb_state_machine_step(CPUPPCState *env)
>           }
>       }
>   
> -    env->spr[SPR_TFMR] = tfmr;
> +    write_tfmr(env, tfmr);
>   }
>   
>   target_ulong helper_load_tfmr(CPUPPCState *env)
> @@ -357,7 +444,7 @@ void helper_store_tfmr(CPUPPCState *env, target_ulong val)
>       }
>   
>   out:
> -    env->spr[SPR_TFMR] = tfmr;
> +    write_tfmr(env, tfmr);
>   }
>   #endif
>   
> diff --git a/target/ppc/translate.c b/target/ppc/translate.c
> index 329da4d518..bd103b1026 100644
> --- a/target/ppc/translate.c
> +++ b/target/ppc/translate.c
> @@ -247,13 +247,24 @@ static inline bool gen_serialize(DisasContext *ctx)
>       return true;
>   }
>   
> -#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY)
> +#if !defined(CONFIG_USER_ONLY)
> +#if defined(TARGET_PPC64)
> +static inline bool gen_serialize_core(DisasContext *ctx)
> +{
> +    if (ctx->flags & POWERPC_FLAG_SMT) {
> +        return gen_serialize(ctx);
> +    }
> +    return true;
> +}
> +#endif
> +
>   static inline bool gen_serialize_core_lpar(DisasContext *ctx)
>   {
> +#if defined(TARGET_PPC64)
>       if (ctx->flags & POWERPC_FLAG_SMT_1LPAR) {
>           return gen_serialize(ctx);
>       }
> -
> +#endif
>       return true;
>   }
>   #endif
> @@ -667,12 +678,20 @@ void spr_read_atbu(DisasContext *ctx, int gprn, int sprn)
>   #if !defined(CONFIG_USER_ONLY)
>   void spr_write_tbl(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core_lpar(ctx)) {
> +        return;
> +    }
> +
>       translator_io_start(&ctx->base);
>       gen_helper_store_tbl(tcg_env, cpu_gpr[gprn]);
>   }
>   
>   void spr_write_tbu(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core_lpar(ctx)) {
> +        return;
> +    }
> +
>       translator_io_start(&ctx->base);
>       gen_helper_store_tbu(tcg_env, cpu_gpr[gprn]);
>   }
> @@ -696,6 +715,9 @@ void spr_read_purr(DisasContext *ctx, int gprn, int sprn)
>   
>   void spr_write_purr(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core_lpar(ctx)) {
> +        return;
> +    }
>       translator_io_start(&ctx->base);
>       gen_helper_store_purr(tcg_env, cpu_gpr[gprn]);
>   }
> @@ -709,6 +731,9 @@ void spr_read_hdecr(DisasContext *ctx, int gprn, int sprn)
>   
>   void spr_write_hdecr(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core_lpar(ctx)) {
> +        return;
> +    }
>       translator_io_start(&ctx->base);
>       gen_helper_store_hdecr(tcg_env, cpu_gpr[gprn]);
>   }
> @@ -721,12 +746,18 @@ void spr_read_vtb(DisasContext *ctx, int gprn, int sprn)
>   
>   void spr_write_vtb(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core_lpar(ctx)) {
> +        return;
> +    }
>       translator_io_start(&ctx->base);
>       gen_helper_store_vtb(tcg_env, cpu_gpr[gprn]);
>   }
>   
>   void spr_write_tbu40(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core_lpar(ctx)) {
> +        return;
> +    }
>       translator_io_start(&ctx->base);
>       gen_helper_store_tbu40(tcg_env, cpu_gpr[gprn]);
>   }
> @@ -1220,11 +1251,18 @@ void spr_write_hmer(DisasContext *ctx, int sprn, int gprn)
>   
>   void spr_read_tfmr(DisasContext *ctx, int gprn, int sprn)
>   {
> +    /* Reading TFMR can cause it to be updated, so serialize threads here too */
> +    if (!gen_serialize_core(ctx)) {
> +        return;
> +    }
>       gen_helper_load_tfmr(cpu_gpr[gprn], tcg_env);
>   }
>   
>   void spr_write_tfmr(DisasContext *ctx, int sprn, int gprn)
>   {
> +    if (!gen_serialize_core(ctx)) {
> +        return;
> +    }
>       gen_helper_store_tfmr(tcg_env, cpu_gpr[gprn]);
>   }
>