[PATCH v3 1/2] drivers: base: cacheinfo: Add variable to record max cache line size

[PATCH v3 1/2] drivers: base: cacheinfo: Add variable to record max cache line size

[Shaokun Zhang]

Add coherency_max_size variable to record the maximum cache line size
for different cache levels. We will synchronize it with CTR_EL0.CWG
reporting in cache_line_size() for arm64.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jeremy Linton <jeremy.linton@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
---
ChangeLog since v2:
  -- Rebase to 5.2-rc2
  -- Export cache_line_size for I/O driver
ChangeLog since v1:
  -- Move coherency_max_size to drivers/base/cacheinfo.c
  -- Address Catalin's comments
  Link: https://www.spinics.net/lists/arm-kernel/msg723615.html

 drivers/base/cacheinfo.c  | 5 +++++
 include/linux/cacheinfo.h | 2 ++
 2 files changed, 7 insertions(+)

diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index a7359535caf5..8827c60f51e2 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -213,6 +213,8 @@ int __weak cache_setup_acpi(unsigned int cpu)
 	return -ENOTSUPP;
 }
 
+unsigned int coherency_max_size;
+
 static int cache_shared_cpu_map_setup(unsigned int cpu)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
@@ -251,6 +253,9 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
 			}
 		}
+		/* record the maximum cache line size */
+		if (this_leaf->coherency_line_size > coherency_max_size)
+			coherency_max_size = this_leaf->coherency_line_size;
 	}
 
 	return 0;
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 70e19bc6cc9f..46b92cd61d0c 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -17,6 +17,8 @@ enum cache_type {
 	CACHE_TYPE_UNIFIED = BIT(2),
 };
 
+extern unsigned int coherency_max_size;
+
 /**
  * struct cacheinfo - represent a cache leaf node
  * @id: This cache's id. It is unique among caches with the same (type, level).
-- 
2.7.4

[PATCH v3 2/2] arm64: cacheinfo: Update cache_line_size detected from DT or PPTT

[Shaokun Zhang]

cache_line_size is derived from CTR_EL0.CWG field and is called mostly
for I/O device drivers. For HiSilicon certain plantform, like the
Kunpeng920 server SoC, cache line sizes are different between L1/2
cache and L3 cache while L1 cache line size is 64-byte and L3 is 128-byte,
but CTR_EL0.CWG is misreporting using L1 cache line size.

We shall correct the right value which is important for I/O performance.
Let's update the cache line size if it is detected from DT or PPTT
information.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Jeremy Linton <jeremy.linton@arm.com>
Cc: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
Reported-by: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
---
 arch/arm64/include/asm/cache.h |  6 +-----
 arch/arm64/kernel/cacheinfo.c  | 11 +++++++++++
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 926434f413fa..758af6340314 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -91,11 +91,7 @@ static inline u32 cache_type_cwg(void)
 
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
-static inline int cache_line_size(void)
-{
-	u32 cwg = cache_type_cwg();
-	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
-}
+int cache_line_size(void);
 
 /*
  * Read the effective value of CTR_EL0.
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 0bf0a835122f..3d54b0024246 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -28,6 +28,17 @@
 #define CLIDR_CTYPE(clidr, level)	\
 	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
 
+int cache_line_size(void)
+{
+	u32 cwg = cache_type_cwg();
+
+	if (coherency_max_size != 0)
+		return coherency_max_size;
+
+	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
+}
+EXPORT_SYMBOL(cache_line_size);
+
 static inline enum cache_type get_cache_type(int level)
 {
 	u64 clidr;
-- 
2.7.4

Re: [PATCH v3 2/2] arm64: cacheinfo: Update cache_line_size detected from DT or PPTT

[Greg KH]

On Mon, May 27, 2019 at 10:06:08AM +0800, Shaokun Zhang wrote:
> cache_line_size is derived from CTR_EL0.CWG field and is called mostly
> for I/O device drivers. For HiSilicon certain plantform, like the
> Kunpeng920 server SoC, cache line sizes are different between L1/2
> cache and L3 cache while L1 cache line size is 64-byte and L3 is 128-byte,
> but CTR_EL0.CWG is misreporting using L1 cache line size.
> 
> We shall correct the right value which is important for I/O performance.
> Let's update the cache line size if it is detected from DT or PPTT
> information.
> 
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: Sudeep Holla <sudeep.holla@arm.com>
> Cc: Jeremy Linton <jeremy.linton@arm.com>
> Cc: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
> Reported-by: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
> Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
> Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
> ---
>  arch/arm64/include/asm/cache.h |  6 +-----
>  arch/arm64/kernel/cacheinfo.c  | 11 +++++++++++
>  2 files changed, 12 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
> index 926434f413fa..758af6340314 100644
> --- a/arch/arm64/include/asm/cache.h
> +++ b/arch/arm64/include/asm/cache.h
> @@ -91,11 +91,7 @@ static inline u32 cache_type_cwg(void)
>  
>  #define __read_mostly __attribute__((__section__(".data..read_mostly")))
>  
> -static inline int cache_line_size(void)
> -{
> -	u32 cwg = cache_type_cwg();
> -	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
> -}
> +int cache_line_size(void);
>  
>  /*
>   * Read the effective value of CTR_EL0.
> diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
> index 0bf0a835122f..3d54b0024246 100644
> --- a/arch/arm64/kernel/cacheinfo.c
> +++ b/arch/arm64/kernel/cacheinfo.c
> @@ -28,6 +28,17 @@
>  #define CLIDR_CTYPE(clidr, level)	\
>  	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
>  
> +int cache_line_size(void)
> +{
> +	u32 cwg = cache_type_cwg();
> +
> +	if (coherency_max_size != 0)
> +		return coherency_max_size;

Ah, you use it here.

> +
> +	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;

Shouldn't you set the variable if it is 0 here as well?

> +}
> +EXPORT_SYMBOL(cache_line_size);

EXPORT_SYMBOL_GPL()?

thanks,

greg k-h

Re: [PATCH v3 2/2] arm64: cacheinfo: Update cache_line_size detected from DT or PPTT

[Zhangshaokun]

Hi Greg,

On 2019/5/27 14:08, Greg KH wrote:
> On Mon, May 27, 2019 at 10:06:08AM +0800, Shaokun Zhang wrote:
>> cache_line_size is derived from CTR_EL0.CWG field and is called mostly
>> for I/O device drivers. For HiSilicon certain plantform, like the
>> Kunpeng920 server SoC, cache line sizes are different between L1/2
>> cache and L3 cache while L1 cache line size is 64-byte and L3 is 128-byte,
>> but CTR_EL0.CWG is misreporting using L1 cache line size.
>>
>> We shall correct the right value which is important for I/O performance.
>> Let's update the cache line size if it is detected from DT or PPTT
>> information.
>>
>> Cc: Catalin Marinas <catalin.marinas@arm.com>
>> Cc: Will Deacon <will.deacon@arm.com>
>> Cc: Sudeep Holla <sudeep.holla@arm.com>
>> Cc: Jeremy Linton <jeremy.linton@arm.com>
>> Cc: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
>> Reported-by: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
>> Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
>> Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
>> ---
>>  arch/arm64/include/asm/cache.h |  6 +-----
>>  arch/arm64/kernel/cacheinfo.c  | 11 +++++++++++
>>  2 files changed, 12 insertions(+), 5 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
>> index 926434f413fa..758af6340314 100644
>> --- a/arch/arm64/include/asm/cache.h
>> +++ b/arch/arm64/include/asm/cache.h
>> @@ -91,11 +91,7 @@ static inline u32 cache_type_cwg(void)
>>  
>>  #define __read_mostly __attribute__((__section__(".data..read_mostly")))
>>  
>> -static inline int cache_line_size(void)
>> -{
>> -	u32 cwg = cache_type_cwg();
>> -	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
>> -}
>> +int cache_line_size(void);
>>  
>>  /*
>>   * Read the effective value of CTR_EL0.
>> diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
>> index 0bf0a835122f..3d54b0024246 100644
>> --- a/arch/arm64/kernel/cacheinfo.c
>> +++ b/arch/arm64/kernel/cacheinfo.c
>> @@ -28,6 +28,17 @@
>>  #define CLIDR_CTYPE(clidr, level)	\
>>  	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
>>  
>> +int cache_line_size(void)
>> +{
>> +	u32 cwg = cache_type_cwg();
>> +
>> +	if (coherency_max_size != 0)
>> +		return coherency_max_size;
> 
> Ah, you use it here.
> 

Yeah, we check it here.

>> +
>> +	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
> 
> Shouldn't you set the variable if it is 0 here as well?
> 

As discussed this with Catalin,
https://www.spinics.net/lists/arm-kernel/msg723848.html

I think it is unnecessary, if coherency_max_size is not detected from firmware,
We will return the cpu core reporting value as the cache line size and
coherency_max_size won't be used in other place.

>> +}
>> +EXPORT_SYMBOL(cache_line_size);
> 
> EXPORT_SYMBOL_GPL()?
> 

Ok.

Thanks,
Shaokun

> thanks,
> 
> greg k-h
> 
> .
> 

Re: [PATCH v3 1/2] drivers: base: cacheinfo: Add variable to record max cache line size

[Greg Kroah-Hartman]

On Mon, May 27, 2019 at 10:06:07AM +0800, Shaokun Zhang wrote:
> Add coherency_max_size variable to record the maximum cache line size
> for different cache levels. We will synchronize it with CTR_EL0.CWG
> reporting in cache_line_size() for arm64.
> 
> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Cc: "Rafael J. Wysocki" <rafael@kernel.org>
> Cc: Sudeep Holla <sudeep.holla@arm.com>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Jeremy Linton <jeremy.linton@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
> ---
> ChangeLog since v2:
>   -- Rebase to 5.2-rc2
>   -- Export cache_line_size for I/O driver
> ChangeLog since v1:
>   -- Move coherency_max_size to drivers/base/cacheinfo.c
>   -- Address Catalin's comments
>   Link: https://www.spinics.net/lists/arm-kernel/msg723615.html
> 
>  drivers/base/cacheinfo.c  | 5 +++++
>  include/linux/cacheinfo.h | 2 ++
>  2 files changed, 7 insertions(+)
> 
> diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
> index a7359535caf5..8827c60f51e2 100644
> --- a/drivers/base/cacheinfo.c
> +++ b/drivers/base/cacheinfo.c
> @@ -213,6 +213,8 @@ int __weak cache_setup_acpi(unsigned int cpu)
>  	return -ENOTSUPP;
>  }
>  
> +unsigned int coherency_max_size;

Why are you creating a global variable?

Where are the other patches in this series?

thanks,

greg k-h