[PATCH v2 12/12] accel/tcg: Avoid unnecessary call overhead from qemu_plugin_vcpu_mem_cb

Alex Bennée posted 12 patches 5 months, 1 week ago
Maintainers: Cameron Esfahani <dirty@apple.com>, Roman Bolshakov <rbolshakov@ddn.com>, Paolo Bonzini <pbonzini@redhat.com>, Thomas Huth <thuth@redhat.com>, Laurent Vivier <lvivier@redhat.com>, Richard Henderson <richard.henderson@linaro.org>, "Alex Bennée" <alex.bennee@linaro.org>, Alexandre Iooss <erdnaxe@crans.org>, Mahmoud Mandour <ma.mandourr@gmail.com>, Pierrick Bouvier <pierrick.bouvier@linaro.org>, "Philippe Mathieu-Daudé" <philmd@linaro.org>, "Dr. David Alan Gilbert" <dave@treblig.org>, Alexander Graf <agraf@csgraf.de>, Peter Maydell <peter.maydell@linaro.org>, Marcelo Tosatti <mtosatti@redhat.com>, Nicholas Piggin <npiggin@gmail.com>, Daniel Henrique Barboza <danielhb413@gmail.com>, Halil Pasic <pasic@linux.ibm.com>, Christian Borntraeger <borntraeger@linux.ibm.com>, David Hildenbrand <david@redhat.com>, Ilya Leoshkevich <iii@linux.ibm.com>
[PATCH v2 12/12] accel/tcg: Avoid unnecessary call overhead from qemu_plugin_vcpu_mem_cb
Posted by Alex Bennée 5 months, 1 week ago
From: Max Chou <max.chou@sifive.com>

If there are not any QEMU plugin memory callback functions, checking
before calling the qemu_plugin_vcpu_mem_cb function can reduce the
function call overhead.

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Message-Id: <20240613175122.1299212-2-max.chou@sifive.com>
---
 accel/tcg/ldst_common.c.inc | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/accel/tcg/ldst_common.c.inc b/accel/tcg/ldst_common.c.inc
index c82048e377..87ceb95487 100644
--- a/accel/tcg/ldst_common.c.inc
+++ b/accel/tcg/ldst_common.c.inc
@@ -125,7 +125,9 @@ void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
 
 static void plugin_load_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
 {
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
+        qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    }
 }
 
 uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra)
@@ -188,7 +190,9 @@ Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
 
 static void plugin_store_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
 {
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+    if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
+        qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+    }
 }
 
 void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,
-- 
2.39.2
Re: [PATCH v2 12/12] accel/tcg: Avoid unnecessary call overhead from qemu_plugin_vcpu_mem_cb
Posted by Alwalid Salama 5 months ago
Reviewed-by: Alwalid Salama <quic_asalama@qualcomm.com>

On 6/20/2024 5:22 PM, Alex Bennée wrote:
> From: Max Chou <max.chou@sifive.com>
> 
> If there are not any QEMU plugin memory callback functions, checking
> before calling the qemu_plugin_vcpu_mem_cb function can reduce the
> function call overhead.
> 
> Signed-off-by: Max Chou <max.chou@sifive.com>
> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
> Reviewed-by: Frank Chang <frank.chang@sifive.com>
> Message-Id: <20240613175122.1299212-2-max.chou@sifive.com>
> ---
>   accel/tcg/ldst_common.c.inc | 8 ++++++--
>   1 file changed, 6 insertions(+), 2 deletions(-)
> 
> diff --git a/accel/tcg/ldst_common.c.inc b/accel/tcg/ldst_common.c.inc
> index c82048e377..87ceb95487 100644
> --- a/accel/tcg/ldst_common.c.inc
> +++ b/accel/tcg/ldst_common.c.inc
> @@ -125,7 +125,9 @@ void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
>   
>   static void plugin_load_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
>   {
> -    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
> +    if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
> +        qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
> +    }
>   }
>   
>   uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra)
> @@ -188,7 +190,9 @@ Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
>   
>   static void plugin_store_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
>   {
> -    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
> +    if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
> +        qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
> +    }
>   }
>   
>   void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,

Re: [PATCH v2 12/12] accel/tcg: Avoid unnecessary call overhead from qemu_plugin_vcpu_mem_cb
Posted by Pierrick Bouvier 5 months, 1 week ago
On 6/20/24 08:22, Alex Bennée wrote:
> From: Max Chou <max.chou@sifive.com>
> 
> If there are not any QEMU plugin memory callback functions, checking
> before calling the qemu_plugin_vcpu_mem_cb function can reduce the
> function call overhead.
> 
> Signed-off-by: Max Chou <max.chou@sifive.com>
> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
> Reviewed-by: Frank Chang <frank.chang@sifive.com>
> Message-Id: <20240613175122.1299212-2-max.chou@sifive.com>
> ---
>   accel/tcg/ldst_common.c.inc | 8 ++++++--
>   1 file changed, 6 insertions(+), 2 deletions(-)
> 
> diff --git a/accel/tcg/ldst_common.c.inc b/accel/tcg/ldst_common.c.inc
> index c82048e377..87ceb95487 100644
> --- a/accel/tcg/ldst_common.c.inc
> +++ b/accel/tcg/ldst_common.c.inc
> @@ -125,7 +125,9 @@ void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
>   
>   static void plugin_load_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
>   {
> -    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
> +    if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
> +        qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
> +    }
>   }
>   
>   uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra)
> @@ -188,7 +190,9 @@ Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
>   
>   static void plugin_store_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
>   {
> -    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
> +    if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
> +        qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
> +    }
>   }
>   
>   void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,

You might want to add the same thing in: accel/tcg/atomic_common.c.inc

Pierrick
Re: [PATCH v2 12/12] accel/tcg: Avoid unnecessary call overhead from qemu_plugin_vcpu_mem_cb
Posted by Philippe Mathieu-Daudé 5 months, 1 week ago
On 20/6/24 17:22, Alex Bennée wrote:
> From: Max Chou <max.chou@sifive.com>
> 
> If there are not any QEMU plugin memory callback functions, checking
> before calling the qemu_plugin_vcpu_mem_cb function can reduce the
> function call overhead.
> 
> Signed-off-by: Max Chou <max.chou@sifive.com>
> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
> Reviewed-by: Frank Chang <frank.chang@sifive.com>
> Message-Id: <20240613175122.1299212-2-max.chou@sifive.com>
> ---
>   accel/tcg/ldst_common.c.inc | 8 ++++++--
>   1 file changed, 6 insertions(+), 2 deletions(-)

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>