riscv: Implement Zicbom-based cache management operations
From: Heiko Stuebner <heiko@...> Date: Sat, 11 Sep 2021 17:21:36 +0800
Commit-Message
The Zicbom ISA-extension was ratified in november 2021 and introduces instructions for dcache invalidate, clean and flush operations. Implement cache management operations based on them. Of course not all cores will support this, so implement an alternative-based mechanism that replaces empty instructions with ones done around Zicbom instructions. We're using prebuild instructions for the Zicbom instructions for now, to not require a bleeding-edge compiler (gcc-12) for these somewhat simple instructions. Signed-off-by: Heiko Stuebner <heiko@...> Cc: Christoph Hellwig <hch@...> Cc: Atish Patra <atish.patra@...> Cc: Guo Ren <guoren@...>
Patch-Comment
arch/riscv/Kconfig | 15 +++++ arch/riscv/include/asm/cacheflush.h | 6 ++ arch/riscv/include/asm/errata_list.h | 39 +++++++++++- arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/kernel/cpu.c | 1 + arch/riscv/kernel/cpufeature.c | 17 +++++ arch/riscv/kernel/setup.c | 2 + arch/riscv/mm/Makefile | 1 + arch/riscv/mm/dma-noncoherent.c | 92 ++++++++++++++++++++++++++++ 9 files changed, 173 insertions(+), 1 deletion(-) create mode 100644 arch/riscv/mm/dma-noncoherent.c
Statistics
- 173 lines added
- 1 lines removed
Changes
------------------------------ arch/riscv/Kconfig ------------------------------
index 65285b980134..532db45367a7 100644
@@ -363,6 +363,21 @@ config RISCV_ISA_SVPBMT
If you don't know what to do here, say Y.
+config RISCV_ISA_ZICBOM
+ bool "Zicbom extension support for non-coherent dma operation"
+ select ARCH_HAS_DMA_PREP_COHERENT
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
+ select ARCH_HAS_SETUP_DMA_OPS
+ select DMA_DIRECT_REMAP
+ select RISCV_ALTERNATIVE
+ default y
+ help
+ Adds support to dynamically detect the presence of the ZICBOM extension
+ (Cache Block Management Operations) and enable its usage.
+
+ If you don't know what to do here, say Y.
+
config FPU
bool "FPU support"
default y
--------------------- arch/riscv/include/asm/cacheflush.h ----------------------
index 23ff70350992..eb12d014b158 100644
@@ -42,6 +42,12 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
+#ifdef CONFIG_RISCV_ISA_ZICBOM
+void riscv_init_cbom_blocksize(void);
+#else
+static inline void riscv_init_cbom_blocksize(void) { }
+#endif
+
/*
* Bits in sys_riscv_flush_icache()'s flags argument.
*/
--------------------- arch/riscv/include/asm/errata_list.h ---------------------
index 9e2888dbb5b1..eebcd4415049 100644
@@ -20,7 +20,8 @@
#endif
#define CPUFEATURE_SVPBMT 0
+#define CPUFEATURE_CMO 1
+#define CPUFEATURE_NUMBER 2
#ifdef __ASSEMBLY__
@@ -93,6 +94,42 @@ asm volatile(ALTERNATIVE( \
#define ALT_THEAD_PMA(_val)
#endif
+/*
+ * cbo.clean rs1
+ * | 31 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0...01 rs1 010 00000 0001111
+ *
+ * cbo.flush rs1
+ * | 31 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0...10 rs1 010 00000 0001111
+ *
+ * cbo.inval rs1
+ * | 31 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ * 0...00 rs1 010 00000 0001111
+ */
+#define CBO_INVAL_A0 ".long 0x15200F"
+#define CBO_CLEAN_A0 ".long 0x25200F"
+#define CBO_FLUSH_A0 ".long 0x05200F"
+
+#define ALT_CMO_OP(_op, _start, _size, _cachesize) \
+asm volatile(ALTERNATIVE( \
+ "nop\n\t" \
+ "nop\n\t" \
+ "nop\n\t" \
+ "nop\n\t" \
+ "nop", \
+ "mv a0, %1\n\t" \
+ "j 2f\n\t" \
+ "3:\n\t" \
+ CBO_##_op##_A0 "\n\t" \
+ "add a0, a0, %0\n\t" \
+ "2:\n\t" \
+ "bltu a0, %2, 3b\n\t", 0, \
+ CPUFEATURE_CMO, CONFIG_RISCV_ISA_ZICBOM) \
+ : : "r"(_cachesize), \
+ "r"(ALIGN((_start), (_cachesize))), \
+ "r"(ALIGN((_start) + (_size), (_cachesize))))
+
#endif /* __ASSEMBLY__ */
#endif
------------------------ arch/riscv/include/asm/hwcap.h ------------------------
index 4e2486881840..6044e402003d 100644
@@ -53,6 +53,7 @@ extern unsigned long elf_hwcap;
enum riscv_isa_ext_id {
RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
RISCV_ISA_EXT_SVPBMT,
+ RISCV_ISA_EXT_ZICBOM,
RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
};
--------------------------- arch/riscv/kernel/cpu.c ----------------------------
index 40c8776aec12..8f6fc15baa8e 100644
@@ -89,6 +89,7 @@ int riscv_of_parent_hartid(struct device_node *node)
static struct riscv_isa_ext_data isa_ext_arr[] = {
__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+ __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
};
------------------------ arch/riscv/kernel/cpufeature.c ------------------------
index dea3ea19deee..db3c02409a4a 100644
@@ -199,6 +199,7 @@ void __init riscv_fill_hwcap(void)
} else {
SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
+ SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
}
#undef SET_ISA_EXT_MAP
}
@@ -265,12 +266,28 @@ static bool __init_or_module cpufeature_svpbmt_check_func(unsigned int stage)
return false;
}
+static bool __init_or_module cpufeature_cmo_check_func(unsigned int stage)
+{
+ switch (stage) {
+ case RISCV_ALTERNATIVES_EARLY_BOOT:
+ return false;
+ default:
+ return riscv_isa_extension_available(NULL, ZICBOM);
+ }
+
+ return false;
+}
+
static const struct cpufeature_info __initdata_or_module
cpufeature_list[CPUFEATURE_NUMBER] = {
{
.name = "svpbmt",
.check_func = cpufeature_svpbmt_check_func
},
+ {
+ .name = "cmo",
+ .check_func = cpufeature_cmo_check_func
+ },
};
static u32 __init_or_module cpufeature_probe(unsigned int stage)
-------------------------- arch/riscv/kernel/setup.c ---------------------------
index 9162e9a824d2..cc5bfeba499a 100644
@@ -22,6 +22,7 @@
#include <linux/crash_dump.h>
#include <asm/alternative.h>
+#include <asm/cacheflush.h>
#include <asm/cpu_ops.h>
#include <asm/early_ioremap.h>
#include <asm/pgtable.h>
@@ -296,6 +297,7 @@ void __init setup_arch(char **cmdline_p)
#endif
riscv_fill_hwcap();
+ riscv_init_cbom_blocksize();
apply_boot_alternatives();
}
---------------------------- arch/riscv/mm/Makefile ----------------------------
index ac7a25298a04..548f2f3c00e9 100644
@@ -30,3 +30,4 @@ endif
endif
obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+obj-$(CONFIG_RISCV_ISA_ZICBOM) += dma-noncoherent.o
----------------------- arch/riscv/mm/dma-noncoherent.c ------------------------
new file mode 100644
index 000000000000..99decaa25324
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RISC-V specific functions to support DMA for non-coherent devices
+ *
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/libfdt.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+static unsigned int riscv_cbom_block_size = L1_CACHE_BYTES;
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+ switch (dir) {
+ case DMA_TO_DEVICE:
+ ALT_CMO_OP(CLEAN, (unsigned long)phys_to_virt(paddr), size, riscv_cbom_block_size);
+ break;
+ case DMA_FROM_DEVICE:
+ ALT_CMO_OP(INVAL, (unsigned long)phys_to_virt(paddr), size, riscv_cbom_block_size);
+ break;
+ case DMA_BIDIRECTIONAL:
+ ALT_CMO_OP(FLUSH, (unsigned long)phys_to_virt(paddr), size, riscv_cbom_block_size);
+ break;
+ default:
+ break;
+ }
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+ switch (dir) {
+ case DMA_TO_DEVICE:
+ break;
+ case DMA_FROM_DEVICE:
+ case DMA_BIDIRECTIONAL:
+ ALT_CMO_OP(INVAL, (unsigned long)phys_to_virt(paddr), size, riscv_cbom_block_size);
+ break;
+ default:
+ break;
+ }
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+ void *flush_addr = page_address(page);
+
+ memset(flush_addr, 0, size);
+ ALT_CMO_OP(FLUSH, (unsigned long)flush_addr, size, riscv_cbom_block_size);
+}
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *iommu, bool coherent)
+{
+ /* If a specific device is dma-coherent, set it here */
+ dev->dma_coherent = coherent;
+}
+
+void riscv_init_cbom_blocksize(void)
+{
+ struct device_node *node;
+ int ret;
+ u32 val;
+
+ for_each_of_cpu_node(node) {
+ int hartid = riscv_of_processor_hartid(node);
+ int cbom_hartid;
+
+ if (hartid < 0)
+ continue;
+
+ /* set block-size for cbom extension if available */
+ ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
+ if (ret)
+ continue;
+
+ if (!riscv_cbom_block_size) {
+ riscv_cbom_block_size = val;
+ cbom_hartid = hartid;
+ } else {
+ if (riscv_cbom_block_size != val)
+ pr_warn("cbom-block-size mismatched between harts %d and %d\n",
+ cbom_hartid, hartid);
+ }
+ }
+}