[PATCH v2] riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required

[PATCH v2] riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required

[Jisheng Zhang]

After commit f51f7a0fc2f4 ("riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC
for !dma_coherent"), for non-coherent platforms with less than 4GB
memory, we rely on users to pass "swiotlb=mmnn,force" kernel parameters
to enable DMA bouncing for unaligned kmalloc() buffers. Now let's go
further: If no bouncing needed for ZONE_DMA, let kernel automatically
allocate 1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing on
non-coherent platforms, so that no need to pass "swiotlb=mmnn,force"
any more.

The math of "1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing"
is taken from arm64. Users can still force smaller swiotlb buffer by
passing "swiotlb=mmnn".

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
---

since v2:
 - fix build error if CONFIG_RISCV_DMA_NONCOHERENT=n

 arch/riscv/include/asm/cache.h |  2 +-
 arch/riscv/mm/init.c           | 16 +++++++++++++++-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
index 2174fe7bac9a..570e9d8acad1 100644
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -26,8 +26,8 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_RISCV_DMA_NONCOHERENT
 extern int dma_cache_alignment;
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
 #define dma_get_cache_alignment dma_get_cache_alignment
 static inline int dma_get_cache_alignment(void)
 {
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 2e011cbddf3a..cbcb9918f721 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -162,11 +162,25 @@ static void print_vm_layout(void) { }
 
 void __init mem_init(void)
 {
+	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
 
-	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
+	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
+	    dma_cache_alignment != 1) {
+		/*
+		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
+		 * buffer per 1GB of RAM for kmalloc() bouncing on
+		 * non-coherent platforms.
+		 */
+		unsigned long size =
+			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
+		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
+		swiotlb = true;
+	}
+
+	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
 	memblock_free_all();
 
 	print_vm_layout();
-- 
2.42.0

Re: [PATCH v2] riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required

[Jisheng Zhang]

On Sat, Dec 02, 2023 at 09:42:24PM +0800, Jisheng Zhang wrote:
> After commit f51f7a0fc2f4 ("riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC
> for !dma_coherent"), for non-coherent platforms with less than 4GB
> memory, we rely on users to pass "swiotlb=mmnn,force" kernel parameters
> to enable DMA bouncing for unaligned kmalloc() buffers. Now let's go
> further: If no bouncing needed for ZONE_DMA, let kernel automatically
> allocate 1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing on
> non-coherent platforms, so that no need to pass "swiotlb=mmnn,force"
> any more.
> 
> The math of "1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing"
> is taken from arm64. Users can still force smaller swiotlb buffer by
> passing "swiotlb=mmnn".

and this one is missed either. let me know if there's something need to
be done for merging.

Thanks in advance,

> 
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> ---
> 
> since v2:
>  - fix build error if CONFIG_RISCV_DMA_NONCOHERENT=n
> 
>  arch/riscv/include/asm/cache.h |  2 +-
>  arch/riscv/mm/init.c           | 16 +++++++++++++++-
>  2 files changed, 16 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
> index 2174fe7bac9a..570e9d8acad1 100644
> --- a/arch/riscv/include/asm/cache.h
> +++ b/arch/riscv/include/asm/cache.h
> @@ -26,8 +26,8 @@
>  
>  #ifndef __ASSEMBLY__
>  
> -#ifdef CONFIG_RISCV_DMA_NONCOHERENT
>  extern int dma_cache_alignment;
> +#ifdef CONFIG_RISCV_DMA_NONCOHERENT
>  #define dma_get_cache_alignment dma_get_cache_alignment
>  static inline int dma_get_cache_alignment(void)
>  {
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index 2e011cbddf3a..cbcb9918f721 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -162,11 +162,25 @@ static void print_vm_layout(void) { }
>  
>  void __init mem_init(void)
>  {
> +	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
>  #ifdef CONFIG_FLATMEM
>  	BUG_ON(!mem_map);
>  #endif /* CONFIG_FLATMEM */
>  
> -	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
> +	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
> +	    dma_cache_alignment != 1) {
> +		/*
> +		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
> +		 * buffer per 1GB of RAM for kmalloc() bouncing on
> +		 * non-coherent platforms.
> +		 */
> +		unsigned long size =
> +			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
> +		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
> +		swiotlb = true;
> +	}
> +
> +	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
>  	memblock_free_all();
>  
>  	print_vm_layout();
> -- 
> 2.42.0
> 
> 
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv

Re: [PATCH v2] riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required

[Alexandre Ghiti]

Hi Jisheng,

On 02/12/2023 14:42, Jisheng Zhang wrote:
> After commit f51f7a0fc2f4 ("riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC
> for !dma_coherent"), for non-coherent platforms with less than 4GB
> memory, we rely on users to pass "swiotlb=mmnn,force" kernel parameters
> to enable DMA bouncing for unaligned kmalloc() buffers. Now let's go
> further: If no bouncing needed for ZONE_DMA, let kernel automatically
> allocate 1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing on
> non-coherent platforms, so that no need to pass "swiotlb=mmnn,force"
> any more.

IIUC, DMA_BOUNCE_UNALIGNED_KMALLOC is enabled for all non-coherent 
platforms, even those with less than 4GB of memory. But the DMA bouncing 
(which is necessary to enable kmalloc-8/16/32/96...) was not enabled 
unless the user specified "swiotlb=mmnn,force" on the kernel command 
line. But does that mean that if the user did not specify 
"swiotlb=mmnn,force", the kmalloc-8/16/32/96 were enabled anyway and the 
behaviour was wrong (by lack of DMA bouncing)?

I'm trying to understand if that's a fix or an enhancement.

Thanks,

Alex


>
> The math of "1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing"
> is taken from arm64. Users can still force smaller swiotlb buffer by
> passing "swiotlb=mmnn".
>
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> ---
>
> since v2:
>   - fix build error if CONFIG_RISCV_DMA_NONCOHERENT=n
>
>   arch/riscv/include/asm/cache.h |  2 +-
>   arch/riscv/mm/init.c           | 16 +++++++++++++++-
>   2 files changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
> index 2174fe7bac9a..570e9d8acad1 100644
> --- a/arch/riscv/include/asm/cache.h
> +++ b/arch/riscv/include/asm/cache.h
> @@ -26,8 +26,8 @@
>   
>   #ifndef __ASSEMBLY__
>   
> -#ifdef CONFIG_RISCV_DMA_NONCOHERENT
>   extern int dma_cache_alignment;
> +#ifdef CONFIG_RISCV_DMA_NONCOHERENT
>   #define dma_get_cache_alignment dma_get_cache_alignment
>   static inline int dma_get_cache_alignment(void)
>   {
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index 2e011cbddf3a..cbcb9918f721 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -162,11 +162,25 @@ static void print_vm_layout(void) { }
>   
>   void __init mem_init(void)
>   {
> +	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
>   #ifdef CONFIG_FLATMEM
>   	BUG_ON(!mem_map);
>   #endif /* CONFIG_FLATMEM */
>   
> -	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
> +	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
> +	    dma_cache_alignment != 1) {
> +		/*
> +		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
> +		 * buffer per 1GB of RAM for kmalloc() bouncing on
> +		 * non-coherent platforms.
> +		 */
> +		unsigned long size =
> +			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
> +		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
> +		swiotlb = true;
> +	}
> +
> +	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
>   	memblock_free_all();
>   
>   	print_vm_layout();

Re: [PATCH v2] riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required

[Jisheng Zhang]

On Tue, Jan 16, 2024 at 09:23:47AM +0100, Alexandre Ghiti wrote:
> Hi Jisheng,
> 
> On 02/12/2023 14:42, Jisheng Zhang wrote:
> > After commit f51f7a0fc2f4 ("riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC
> > for !dma_coherent"), for non-coherent platforms with less than 4GB
> > memory, we rely on users to pass "swiotlb=mmnn,force" kernel parameters
> > to enable DMA bouncing for unaligned kmalloc() buffers. Now let's go
> > further: If no bouncing needed for ZONE_DMA, let kernel automatically
> > allocate 1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing on
> > non-coherent platforms, so that no need to pass "swiotlb=mmnn,force"
> > any more.
> 
> IIUC, DMA_BOUNCE_UNALIGNED_KMALLOC is enabled for all non-coherent
> platforms, even those with less than 4GB of memory. But the DMA bouncing
> (which is necessary to enable kmalloc-8/16/32/96...) was not enabled unless
> the user specified "swiotlb=mmnn,force" on the kernel command line. But does
> that mean that if the user did not specify "swiotlb=mmnn,force", the
> kmalloc-8/16/32/96 were enabled anyway and the behaviour was wrong (by lack
> of DMA bouncing)?

Hi Alex,

For coherent platforms, kmalloc-8/16/32/96 was enabled.

For non-coherent platforms, if memory is more than 4GB, kmalloc-8/16/32/96 was enabled.

For non-coherent platforms, if memory is less than 4GB, kmalloc-8/16/32/96 was not
enabled. If users want kmalloc-8/16/32/96, we rely on users to pass "swiotlb=mmnn,force"

This patch tries to remove the "swiotlb=mmnn,force" requirement for the
last case. After this patch, kernel automatically uses "1MB swiotlb buffer per
1GB of RAM for kmalloc() bouncing" by default.

So this is an enhancement.

Thanks
> 
> I'm trying to understand if that's a fix or an enhancement.
> 
> Thanks,
> 
> Alex
> 
> 
> > 
> > The math of "1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing"
> > is taken from arm64. Users can still force smaller swiotlb buffer by
> > passing "swiotlb=mmnn".
> > 
> > Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> > ---
> > 
> > since v2:
> >   - fix build error if CONFIG_RISCV_DMA_NONCOHERENT=n
> > 
> >   arch/riscv/include/asm/cache.h |  2 +-
> >   arch/riscv/mm/init.c           | 16 +++++++++++++++-
> >   2 files changed, 16 insertions(+), 2 deletions(-)
> > 
> > diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
> > index 2174fe7bac9a..570e9d8acad1 100644
> > --- a/arch/riscv/include/asm/cache.h
> > +++ b/arch/riscv/include/asm/cache.h
> > @@ -26,8 +26,8 @@
> >   #ifndef __ASSEMBLY__
> > -#ifdef CONFIG_RISCV_DMA_NONCOHERENT
> >   extern int dma_cache_alignment;
> > +#ifdef CONFIG_RISCV_DMA_NONCOHERENT
> >   #define dma_get_cache_alignment dma_get_cache_alignment
> >   static inline int dma_get_cache_alignment(void)
> >   {
> > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> > index 2e011cbddf3a..cbcb9918f721 100644
> > --- a/arch/riscv/mm/init.c
> > +++ b/arch/riscv/mm/init.c
> > @@ -162,11 +162,25 @@ static void print_vm_layout(void) { }
> >   void __init mem_init(void)
> >   {
> > +	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
> >   #ifdef CONFIG_FLATMEM
> >   	BUG_ON(!mem_map);
> >   #endif /* CONFIG_FLATMEM */
> > -	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
> > +	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
> > +	    dma_cache_alignment != 1) {
> > +		/*
> > +		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
> > +		 * buffer per 1GB of RAM for kmalloc() bouncing on
> > +		 * non-coherent platforms.
> > +		 */
> > +		unsigned long size =
> > +			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
> > +		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
> > +		swiotlb = true;
> > +	}
> > +
> > +	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
> >   	memblock_free_all();
> >   	print_vm_layout();

Re: [PATCH v2] riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required

[Alexandre Ghiti]

On 16/01/2024 09:47, Jisheng Zhang wrote:
> On Tue, Jan 16, 2024 at 09:23:47AM +0100, Alexandre Ghiti wrote:
>> Hi Jisheng,
>>
>> On 02/12/2023 14:42, Jisheng Zhang wrote:
>>> After commit f51f7a0fc2f4 ("riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC
>>> for !dma_coherent"), for non-coherent platforms with less than 4GB
>>> memory, we rely on users to pass "swiotlb=mmnn,force" kernel parameters
>>> to enable DMA bouncing for unaligned kmalloc() buffers. Now let's go
>>> further: If no bouncing needed for ZONE_DMA, let kernel automatically
>>> allocate 1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing on
>>> non-coherent platforms, so that no need to pass "swiotlb=mmnn,force"
>>> any more.
>> IIUC, DMA_BOUNCE_UNALIGNED_KMALLOC is enabled for all non-coherent
>> platforms, even those with less than 4GB of memory. But the DMA bouncing
>> (which is necessary to enable kmalloc-8/16/32/96...) was not enabled unless
>> the user specified "swiotlb=mmnn,force" on the kernel command line. But does
>> that mean that if the user did not specify "swiotlb=mmnn,force", the
>> kmalloc-8/16/32/96 were enabled anyway and the behaviour was wrong (by lack
>> of DMA bouncing)?
> Hi Alex,
>
> For coherent platforms, kmalloc-8/16/32/96 was enabled.
>
> For non-coherent platforms, if memory is more than 4GB, kmalloc-8/16/32/96 was enabled.
>
> For non-coherent platforms, if memory is less than 4GB, kmalloc-8/16/32/96 was not
> enabled. If users want kmalloc-8/16/32/96, we rely on users to pass "swiotlb=mmnn,force"


That's what I was unsure of :)


>
> This patch tries to remove the "swiotlb=mmnn,force" requirement for the
> last case. After this patch, kernel automatically uses "1MB swiotlb buffer per
> 1GB of RAM for kmalloc() bouncing" by default.
>
> So this is an enhancement.


Great, so you can add:

Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>

Thanks,

Alex


>
> Thanks
>> I'm trying to understand if that's a fix or an enhancement.
>>
>> Thanks,
>>
>> Alex
>>
>>
>>> The math of "1MB swiotlb buffer per 1GB of RAM for kmalloc() bouncing"
>>> is taken from arm64. Users can still force smaller swiotlb buffer by
>>> passing "swiotlb=mmnn".
>>>
>>> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
>>> ---
>>>
>>> since v2:
>>>    - fix build error if CONFIG_RISCV_DMA_NONCOHERENT=n
>>>
>>>    arch/riscv/include/asm/cache.h |  2 +-
>>>    arch/riscv/mm/init.c           | 16 +++++++++++++++-
>>>    2 files changed, 16 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
>>> index 2174fe7bac9a..570e9d8acad1 100644
>>> --- a/arch/riscv/include/asm/cache.h
>>> +++ b/arch/riscv/include/asm/cache.h
>>> @@ -26,8 +26,8 @@
>>>    #ifndef __ASSEMBLY__
>>> -#ifdef CONFIG_RISCV_DMA_NONCOHERENT
>>>    extern int dma_cache_alignment;
>>> +#ifdef CONFIG_RISCV_DMA_NONCOHERENT
>>>    #define dma_get_cache_alignment dma_get_cache_alignment
>>>    static inline int dma_get_cache_alignment(void)
>>>    {
>>> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
>>> index 2e011cbddf3a..cbcb9918f721 100644
>>> --- a/arch/riscv/mm/init.c
>>> +++ b/arch/riscv/mm/init.c
>>> @@ -162,11 +162,25 @@ static void print_vm_layout(void) { }
>>>    void __init mem_init(void)
>>>    {
>>> +	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
>>>    #ifdef CONFIG_FLATMEM
>>>    	BUG_ON(!mem_map);
>>>    #endif /* CONFIG_FLATMEM */
>>> -	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
>>> +	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
>>> +	    dma_cache_alignment != 1) {
>>> +		/*
>>> +		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
>>> +		 * buffer per 1GB of RAM for kmalloc() bouncing on
>>> +		 * non-coherent platforms.
>>> +		 */
>>> +		unsigned long size =
>>> +			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
>>> +		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
>>> +		swiotlb = true;
>>> +	}
>>> +
>>> +	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
>>>    	memblock_free_all();
>>>    	print_vm_layout();