riscv: Reduce ARCH_KMALLOC_MINALIGN to 8
v2 cover riscv: Reduce ARCH_KMALLOC_MINALIGN to 8
Currently, riscv defines ARCH_DMA_MINALIGN as L1_CACHE_BYTES, I.E 64Bytes, if CONFIG_RISCV_DMA_NONCOHERENT=y. To support unified kernel Image, usually we have to enable CONFIG_RISCV_DMA_NONCOHERENT, thus it brings some bad effects to coherent platforms:
Firstly, it wastes memory, kmalloc-96, kmalloc-32, kmalloc-16 and kmalloc-8 slab caches don't exist any more, they are replaced with either kmalloc-128 or kmalloc-64.
Secondly, larger than necessary kmalloc aligned allocations results in unnecessary cache/TLB pressure.
This issue also exists on arm64 platforms. From last year, Catalin tried to solve this issue by decoupling ARCH_KMALLOC_MINALIGN from ARCH_DMA_MINALIGN, limiting kmalloc() minimum alignment to dma_get_cache_alignment() and replacing ARCH_KMALLOC_MINALIGN usage in various drivers with ARCH_DMA_MINALIGN etc.[1]
One fact we can make use of for riscv: if the CPU doesn't support ZICBOM or T-HEAD CMO, we know the platform is coherent. Based on Catalin's work and above fact, we can easily solve the kmalloc align issue for riscv: we can override dma_get_cache_alignment(), then let it return ARCH_DMA_MINALIGN at the beginning and return 1 once we know the underlying HW neither supports ZICBOM nor supports T-HEAD CMO.
So what about if the CPU supports ZICBOM and T-HEAD CMO, but all the devices are dma coherent? Well, we use ARCH_DMA_MINALIGN as the kmalloc minimum alignment, nothing changed in this case. This case can be improved in the future.
After this patch, a simple test of booting to a small buildroot rootfs on qemu shows:
kmalloc-96 5041 5041 96 ... kmalloc-64 9606 9606 64 ... kmalloc-32 5128 5128 32 ... kmalloc-16 7682 7682 16 ... kmalloc-8 10246 10246 8 ...
So we save about 1268KB memory. The saving will be much larger in normal OS env on real HW platforms.
patch1 allows kmalloc() caches aligned to the smallest value. patch2 enables DMA_BOUNCE_UNALIGNED_KMALLOC.
After this series:
As for coherent platforms, kmalloc-{8,16,32,96} caches come back on coherent both RV32 and RV64 platforms, I.E !ZICBOM and !THEAD_CMO.
As for noncoherent RV32 platforms, nothing changed.
As for noncoherent RV64 platforms, I.E either ZICBOM or THEAD_CMO, the above kmalloc caches also come back if > 4GB memory or users pass "swiotlb=mmnn,force" to force swiotlb creation if <= 4GB memory. How much mmnn should be depends on the specific platform, it need to be tried and tested all possible usage case on the specific hardware. For example, I can use the minimal I/O TLB slabs on Sipeed M1S Dock.
[1] Link: https://lore.kernel.org/linux-arm-kernel/[email protected]/
Since v1
- remove preparation patches since they have been merged
- adjust Kconfig entry to keep entries sorted
- add new function riscv_set_dma_cache_alignment() to set the dma_cache_alignment var.
Jisheng Zhang (2):
riscv: allow kmalloc() caches aligned to the smallest value
riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC for !dma_coherent
arch/riscv/Kconfig | 1 + arch/riscv/include/asm/cache.h | 14 ++++++++++++++ arch/riscv/include/asm/cacheflush.h | 2 ++ arch/riscv/kernel/setup.c | 1 + arch/riscv/mm/dma-noncoherent.c | 8 ++++++++ 5 files changed, 26 insertions(+)
Signature · 1 line
2.40.1
PATCH v2 1/2 riscv: allow kmalloc() caches aligned to the smallest value
Currently, riscv defines ARCH_DMA_MINALIGN as L1_CACHE_BYTES, I.E 64Bytes, if CONFIG_RISCV_DMA_NONCOHERENT=y. To support unified kernel Image, usually we have to enable CONFIG_RISCV_DMA_NONCOHERENT, thus it brings some bad effects to coherent platforms:
Firstly, it wastes memory, kmalloc-96, kmalloc-32, kmalloc-16 and kmalloc-8 slab caches don't exist any more, they are replaced with either kmalloc-128 or kmalloc-64.
Secondly, larger than necessary kmalloc aligned allocations results in unnecessary cache/TLB pressure.
This issue also exists on arm64 platforms. From last year, Catalin tried to solve this issue by decoupling ARCH_KMALLOC_MINALIGN from ARCH_DMA_MINALIGN, limiting kmalloc() minimum alignment to dma_get_cache_alignment() and replacing ARCH_KMALLOC_MINALIGN usage in various drivers with ARCH_DMA_MINALIGN etc.[1]
One fact we can make use of for riscv: if the CPU doesn't support ZICBOM or T-HEAD CMO, we know the platform is coherent. Based on Catalin's work and above fact, we can easily solve the kmalloc align issue for riscv: we can override dma_get_cache_alignment(), then let it return ARCH_DMA_MINALIGN at the beginning and return 1 once we know the underlying HW neither supports ZICBOM nor supports T-HEAD CMO.
So what about if the CPU supports ZICBOM and T-HEAD CMO, but all the devices are dma coherent? Well, we use ARCH_DMA_MINALIGN as the kmalloc minimum alignment, nothing changed in this case. This case can be improved in the future.
After this patch, a simple test of booting to a small buildroot rootfs on qemu shows:
kmalloc-96 5041 5041 96 ... kmalloc-64 9606 9606 64 ... kmalloc-32 5128 5128 32 ... kmalloc-16 7682 7682 16 ... kmalloc-8 10246 10246 8 ...
So we save about 1268KB memory. The saving will be much larger in normal OS env on real HW platforms.
[1] Link: https://lore.kernel.org/linux-arm-kernel/[email protected]/
--- arch/riscv/include/asm/cache.h | 14 ++++++++++++++ arch/riscv/include/asm/cacheflush.h | 2 ++ arch/riscv/kernel/setup.c | 1 + arch/riscv/mm/dma-noncoherent.c | 8 ++++++++ 4 files changed, 25 insertions(+)
arch/riscv/include/asm/cache.h +14 -0
@@ -13,6 +13,7 @@#ifdef CONFIG_RISCV_DMA_NONCOHERENT #define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_KMALLOC_MINALIGN (8)#endif /*
@@ -23,4 +24,17 @@#define ARCH_SLAB_MINALIGN 16#endif +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +extern int dma_cache_alignment; +#define dma_get_cache_alignment dma_get_cache_alignment +static inline int dma_get_cache_alignment (void ) +{ +return dma_cache_alignment; +} +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_RISCV_CACHE_H */
arch/riscv/include/asm/cacheflush.h +2 -0
@@ -55,8 +55,10 @@ void riscv_init_cbo_blocksizes(void);#ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported (void ); +void __init riscv_set_dma_cache_alignment (void );#else static inline void riscv_noncoherent_supported (void ) {} +static inline void riscv_set_dma_cache_alignment (void ) {}#endif /*
arch/riscv/kernel/setup.c +1 -0
@@ -311,6 +311,7 @@ void __init setup_arch(char **cmdline_p)if (IS_ENABLED (CONFIG_RISCV_ISA_ZICBOM ) &&riscv_isa_extension_available (NULL ,ZICBOM ))riscv_noncoherent_supported (); +riscv_set_dma_cache_alignment (); }static int __init topology_init (void )
arch/riscv/mm/dma-noncoherent.c +8 -0
@@ -11,6 +11,8 @@#include <asm/cacheflush.h> static bool noncoherent_supported__ro_after_init ; +int dma_cache_alignment__ro_after_init =ARCH_DMA_MINALIGN ; +EXPORT_SYMBOL (dma_cache_alignment);void arch_sync_dma_for_device (phys_addr_t paddr,size_t size,enum dma_data_direction dir)
@@ -78,3 +80,9 @@ void riscv_noncoherent_supported(void) "Non-coherent DMA support enabled without a block size\n"); noncoherent_supported = true; } + +void __init riscv_set_dma_cache_alignment (void ) +{ +if (!noncoherent_supported) + dma_cache_alignment =1 ; +}
Signature · 1 line
2.40.1
Re: [PATCH v2 1/2] riscv: allow kmalloc() caches aligned to the smallest value
Hey Jisheng,
Quoted 39 lines · Jisheng Zhang
Currently, riscv defines
ARCH_DMA_MINALIGNasL1_CACHE_BYTES, I.E 64Bytes, ifCONFIG_RISCV_DMA_NONCOHERENT=y. To support unified kernel Image, usually we have to enableCONFIG_RISCV_DMA_NONCOHERENT, thus it brings some bad effects to coherent platforms:Firstly, it wastes memory, kmalloc-96, kmalloc-32, kmalloc-16 and kmalloc-8 slab caches don't exist any more, they are replaced with either kmalloc-128 or kmalloc-64.
Secondly, larger than necessary kmalloc aligned allocations results in unnecessary cache/TLB pressure.
This issue also exists on arm64 platforms. From last year, Catalin tried to solve this issue by decoupling
ARCH_KMALLOC_MINALIGNfromARCH_DMA_MINALIGN, limitingkmalloc()minimum alignment todma_get_cache_alignment()and replacingARCH_KMALLOC_MINALIGNusage in various drivers withARCH_DMA_MINALIGNetc.[1]One fact we can make use of for riscv: if the CPU doesn't support ZICBOM or T-HEAD CMO, we know the platform is coherent. Based on Catalin's work and above fact, we can easily solve the kmalloc align issue for riscv: we can override
dma_get_cache_alignment(), then let it returnARCH_DMA_MINALIGNat the beginning and return 1 once we know the underlying HW neither supports ZICBOM nor supports T-HEAD CMO.So what about if the CPU supports ZICBOM and T-HEAD CMO, but all the devices are dma coherent? Well, we use
ARCH_DMA_MINALIGNas the kmalloc minimum alignment, nothing changed in this case. This case can be improved in the future.After this patch, a simple test of booting to a small buildroot rootfs on qemu shows:
kmalloc-96 5041 5041 96 ... kmalloc-64 9606 9606 64 ... kmalloc-32 5128 5128 32 ... kmalloc-16 7682 7682 16 ... kmalloc-8 10246 10246 8 ...
Quoted 4 lines
So we save about 1268KB memory. The saving will be much larger in normal OS env on real HW platforms.
[1] Link: https://lore.kernel.org/linux-arm-kernel/[email protected]/
In the future,
Quoted 2 lines
Signed-off-by Jisheng Zhang <[email protected]>Change-Id Ica249d0f8058a02bd4bc6543b4ffc2946a4734a2
How come this has ended up with a Change-ID? Checkpatch says this is something to do with Gerrit & needs to be removed.
Quoted 69 lines
--- arch/riscv/include/asm/cache.h | 14 ++++++++++++++ arch/riscv/include/asm/cacheflush.h | 2 ++ arch/riscv/kernel/setup.c | 1 + arch/riscv/mm/dma-noncoherent.c | 8 ++++++++ 4 files changed, 25 insertions(+)arch/riscv/include/asm/cache.h +14
-0@@ -13,6 +13,7 @@#ifdef CONFIG_RISCV_DMA_NONCOHERENT #define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_KMALLOC_MINALIGN (8)#endif /* @@ -23,4 +24,17 @@#define ARCH_SLAB_MINALIGN 16#endif +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +extern int dma_cache_alignment; +#define dma_get_cache_alignment dma_get_cache_alignment +static inline int dma_get_cache_alignment (void ) +{ +return dma_cache_alignment; +} +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_RISCV_CACHE_H */ arch/riscv/include/asm/cacheflush.h +2
-0@@ -55,8 +55,10 @@ void riscv_init_cbo_blocksizes(void);#ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported (void ); +void __init riscv_set_dma_cache_alignment (void );#else static inline void riscv_noncoherent_supported (void ) {} +static inline void riscv_set_dma_cache_alignment (void ) {}#endif /* arch/riscv/kernel/setup.c +1
-0@@ -311,6 +311,7 @@ void __init setup_arch(char **cmdline_p)if (IS_ENABLED (CONFIG_RISCV_ISA_ZICBOM ) &&riscv_isa_extension_available (NULL ,ZICBOM ))riscv_noncoherent_supported (); +riscv_set_dma_cache_alignment (); }static int __init topology_init (void )arch/riscv/mm/dma-noncoherent.c +0
-0
arch/riscv/mm/dma-noncoherent.c line 15
Quoted 5 lines
arch/riscv/mm/dma-noncoherent.c +2
-0@@ -11,6 +11,8 @@#include <asm/cacheflush.h> static bool noncoherent_supported__ro_after_init ; +int dma_cache_alignment__ro_after_init =ARCH_DMA_MINALIGN ; +EXPORT_SYMBOL (dma_cache_alignment);
Why is this not EXPORT_SYMBOL_GPL()?
Otherwise, this is generally good to me, thanks.
Conor.
Quoted 16 lines
arch/riscv/mm/dma-noncoherent.c +6
-0void arch_sync_dma_for_device (phys_addr_t paddr,size_t size,enum dma_data_direction dir)@@ -78,3 +80,9 @@ void riscv_noncoherent_supported(void) "Non-coherent DMA support enabled without a block size\n"); noncoherent_supported = true; } + +void __init riscv_set_dma_cache_alignment (void ) +{ +if (!noncoherent_supported) + dma_cache_alignment =1 ; +}Signature · 1 line
2.40.1
Re: [PATCH v2 1/2] riscv: allow kmalloc() caches aligned to the smallest value
Quoted 49 lines · Conor Dooley
Hey Jisheng,
Quoted 39 lines · Jisheng Zhang
Currently, riscv defines
ARCH_DMA_MINALIGNasL1_CACHE_BYTES, I.E 64Bytes, ifCONFIG_RISCV_DMA_NONCOHERENT=y. To support unified kernel Image, usually we have to enableCONFIG_RISCV_DMA_NONCOHERENT, thus it brings some bad effects to coherent platforms:Firstly, it wastes memory, kmalloc-96, kmalloc-32, kmalloc-16 and kmalloc-8 slab caches don't exist any more, they are replaced with either kmalloc-128 or kmalloc-64.
Secondly, larger than necessary kmalloc aligned allocations results in unnecessary cache/TLB pressure.
This issue also exists on arm64 platforms. From last year, Catalin tried to solve this issue by decoupling
ARCH_KMALLOC_MINALIGNfromARCH_DMA_MINALIGN, limitingkmalloc()minimum alignment todma_get_cache_alignment()and replacingARCH_KMALLOC_MINALIGNusage in various drivers withARCH_DMA_MINALIGNetc.[1]One fact we can make use of for riscv: if the CPU doesn't support ZICBOM or T-HEAD CMO, we know the platform is coherent. Based on Catalin's work and above fact, we can easily solve the kmalloc align issue for riscv: we can override
dma_get_cache_alignment(), then let it returnARCH_DMA_MINALIGNat the beginning and return 1 once we know the underlying HW neither supports ZICBOM nor supports T-HEAD CMO.So what about if the CPU supports ZICBOM and T-HEAD CMO, but all the devices are dma coherent? Well, we use
ARCH_DMA_MINALIGNas the kmalloc minimum alignment, nothing changed in this case. This case can be improved in the future.After this patch, a simple test of booting to a small buildroot rootfs on qemu shows:
kmalloc-96 5041 5041 96 ... kmalloc-64 9606 9606 64 ... kmalloc-32 5128 5128 32 ... kmalloc-16 7682 7682 16 ... kmalloc-8 10246 10246 8 ...Quoted 4 lines
So we save about 1268KB memory. The saving will be much larger in normal OS env on real HW platforms.
[1] Link: https://lore.kernel.org/linux-arm-kernel/[email protected]/
In the future,
Quoted 7 lines
Quoted 2 lines
Signed-off-by Jisheng Zhang <[email protected]>Change-Id Ica249d0f8058a02bd4bc6543b4ffc2946a4734a2How come this has ended up with a Change-ID? Checkpatch says this is something to do with Gerrit & needs to be removed.
Oops, when amending, I forgot to add "-n". And I thought only amending doesn't need to try checkpatch. Will fix it soon.
Thank you.
Quoted 98 lines
Quoted 70 lines
--- arch/riscv/include/asm/cache.h | 14 ++++++++++++++ arch/riscv/include/asm/cacheflush.h | 2 ++ arch/riscv/kernel/setup.c | 1 + arch/riscv/mm/dma-noncoherent.c | 8 ++++++++ 4 files changed, 25 insertions(+)arch/riscv/include/asm/cache.h +14
-0@@ -13,6 +13,7 @@#ifdef CONFIG_RISCV_DMA_NONCOHERENT #define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_KMALLOC_MINALIGN (8)#endif /* @@ -23,4 +24,17 @@#define ARCH_SLAB_MINALIGN 16#endif +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +extern int dma_cache_alignment; +#define dma_get_cache_alignment dma_get_cache_alignment +static inline int dma_get_cache_alignment (void ) +{ +return dma_cache_alignment; +} +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_RISCV_CACHE_H */ arch/riscv/include/asm/cacheflush.h +2
-0@@ -55,8 +55,10 @@ void riscv_init_cbo_blocksizes(void);#ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported (void ); +void __init riscv_set_dma_cache_alignment (void );#else static inline void riscv_noncoherent_supported (void ) {} +static inline void riscv_set_dma_cache_alignment (void ) {}#endif /* arch/riscv/kernel/setup.c +1
-0@@ -311,6 +311,7 @@ void __init setup_arch(char **cmdline_p)if (IS_ENABLED (CONFIG_RISCV_ISA_ZICBOM ) &&riscv_isa_extension_available (NULL ,ZICBOM ))riscv_noncoherent_supported (); +riscv_set_dma_cache_alignment (); }static int __init topology_init (void )arch/riscv/mm/dma-noncoherent.c +0
-0arch/riscv/mm/dma-noncoherent.c line 15
Quoted 5 lines
arch/riscv/mm/dma-noncoherent.c +2
-0@@ -11,6 +11,8 @@#include <asm/cacheflush.h> static bool noncoherent_supported__ro_after_init ; +int dma_cache_alignment__ro_after_init =ARCH_DMA_MINALIGN ; +EXPORT_SYMBOL (dma_cache_alignment);Why is this not
EXPORT_SYMBOL_GPL()?Otherwise, this is generally good to me, thanks.
Conor.
Quoted 16 lines
arch/riscv/mm/dma-noncoherent.c +6
-0void arch_sync_dma_for_device (phys_addr_t paddr,size_t size,enum dma_data_direction dir)@@ -78,3 +80,9 @@ void riscv_noncoherent_supported(void) "Non-coherent DMA support enabled without a block size\n"); noncoherent_supported = true; } + +void __init riscv_set_dma_cache_alignment (void ) +{ +if (!noncoherent_supported) + dma_cache_alignment =1 ; +}Signature · 1 line
2.40.1
PATCH v2 2/2 riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC for !dma_coherent
In reply to Jisheng ZhangWith the DMA bouncing of unaligned kmalloc() buffers now in place, enable it for riscv when RISCV_DMA_NONCOHERENT=y to allow the kmalloc-{8,16,32,96} caches. Since RV32 doesn't enable SWIOTLB yet, and I didn't see any dma noncoherent RV32 platforms in the mainline, so skip RV32 now by only enabling DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB is available. Once we see such requirement on RV32, we can enable it then.
NOTE: we didn't force to create the swiotlb buffer even when the end of RAM is within the 32-bit physical address range. That's to say:
For RV64 with > 4GB memory, the feature is enabled.
For RV64 with <= 4GB memory, the feature isn't enabled by default. We rely on users to pass "swiotlb=mmnn,force" where mmnn is the Number of I/O TLB slabs, see kernel-parameters.txt for details.
Tested on Sipeed Lichee Pi 4A with 8GB DDR and Sipeed M1S BL808 Dock board.
--- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+)
arch/riscv/Kconfig +1 -0
@@ -267,6 +267,7 @@ config RISCV_DMA_NONCOHERENT select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB select DMA_DIRECT_REMAP config AS_HAS_INSN
Signature · 1 line
2.40.1
Re: [PATCH v2 2/2] riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC for !dma_coherent
Quoted 16 lines · Jisheng Zhang
With the DMA bouncing of unaligned
kmalloc()buffers now in place, enable it for riscv when RISCV_DMA_NONCOHERENT=y to allow the kmalloc-{8,16,32,96} caches. Since RV32 doesn't enable SWIOTLB yet, and I didn't see any dma noncoherent RV32 platforms in the mainline, so skip RV32 now by only enablingDMA_BOUNCE_UNALIGNED_KMALLOCif SWIOTLB is available. Once we see such requirement on RV32, we can enable it then.NOTE: we didn't force to create the swiotlb buffer even when the end of RAM is within the 32-bit physical address range. That's to say:
For RV64 with > 4GB memory, the feature is enabled.
For RV64 with <= 4GB memory, the feature isn't enabled by default. We rely on users to pass "swiotlb=mmnn,force" where mmnn is the Number of I/O TLB slabs, see kernel-parameters.txt for details.
Quoted 4 lines
Tested on Sipeed Lichee Pi 4A with 8GB DDR and Sipeed M1S BL808 Dock board.
Signed-off-by Jisheng Zhang <[email protected]>
Thanks,
Conor.
Quoted 6 lines · Jisheng Zhang
Since v1
- remove preparation patches since they have been merged
- adjustKconfigentry to keep entries sorted- add new function
riscv_set_dma_cache_alignment()to set thedma_cache_alignmentvar.
Yeah, looks a lot more straightforward now than in v1, thanks.