Merge patch series "riscv: Reduce ARCH_KMALLOC_MINALIGN to 8"

Jisheng Zhang <jszhang@kernel.org> says:

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 or 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 once we see such platforms in mainline.

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 needs 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.

* b4-shazam-merge:
  riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC for !dma_coherent
  riscv: allow kmalloc() caches aligned to the smallest value

Link: https://lore.kernel.org/linux-arm-kernel/20230524171904.3967031-1-catalin.marinas@arm.com/ [1]
Link: https://lore.kernel.org/r/20230718152214.2907-1-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

5 files changed, 26 insertions, 0 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index f3c6c7d3acb5..8715bcc7b2bf 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -272,6 +272,7 @@ 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
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
index d3036df23ccb..2174fe7bac9a 100644
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -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 */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8091b8bf4883..c640ab6f843b 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -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
 
 /*
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 376f5d49ce85..32c2e1eb71bd 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -316,6 +316,7 @@ 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)
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index d51a75864e53..7270b4d8c05b 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -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_GPL(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;
+}