riscv: Add support for non-coherent devices using zicbom extension

The Zicbom ISA-extension was ratified in november 2021
and introduces instructions for dcache invalidate, clean
and flush operations.

Implement cache management operations for non-coherent devices
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.

As discussed in previous versions, assume the platform
being coherent by default so that non-coherent devices need
to get marked accordingly by firmware.

Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Heiko Stuebner <[email protected]>
Reviewed-by: Guo Ren <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 32ffef9f6e5b4f116034fb1c65388e80d082c361..897ae28abf81ec93085d84e0e222f6243a7ba767 100644 (file)
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -113,6 +113,7 @@ config RISCV
        select MODULES_USE_ELF_RELA if MODULES
        select MODULE_SECTIONS if MODULES
        select OF
+       select OF_DMA_DEFAULT_COHERENT
        select OF_EARLY_FLATTREE
        select OF_IRQ
        select PCI_DOMAINS_GENERIC if PCI
@@ -218,6 +219,14 @@ config PGTABLE_LEVELS
 config LOCKDEP_SUPPORT
        def_bool y
 
+config RISCV_DMA_NONCOHERENT
+       bool
+       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
+
 source "arch/riscv/Kconfig.socs"
 source "arch/riscv/Kconfig.erratas"
 
@@ -376,6 +385,28 @@ config RISCV_ISA_SVPBMT
 
           If you don't know what to do here, say Y.
 
+config CC_HAS_ZICBOM
+       bool
+       default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+       default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+
+config RISCV_ISA_ZICBOM
+       bool "Zicbom extension support for non-coherent DMA operation"
+       depends on CC_HAS_ZICBOM
+       depends on !XIP_KERNEL
+       select RISCV_DMA_NONCOHERENT
+       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.
+
+          The Zicbom extension can be used to handle for example
+          non-coherent DMA support on devices that need it.
+
+          If you don't know what to do here, say Y.
+
 config FPU
        bool "FPU support"
        default y

diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 34cf8a598617b8cd0585d31a2068c1a97b8b8069..fbaabc98b3d2a447b21f5436e9cedd6449d8c6de 100644 (file)
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -56,6 +56,10 @@ riscv-march-$(CONFIG_RISCV_ISA_C)    := $(riscv-march-y)c
 toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zicsr_zifencei)
 riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei
 
+# Check if the toolchain supports Zicbom extension
+toolchain-supports-zicbom := $(call cc-option-yn, -march=$(riscv-march-y)_zicbom)
+riscv-march-$(toolchain-supports-zicbom) := $(riscv-march-y)_zicbom
+
 KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
 KBUILD_AFLAGS += -march=$(riscv-march-y)
 

diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
index 9b58b104559ee8c535d99a9ce63a93a29c09cfa9..d3036df23ccbba79830dbd37528ea8c937743e8d 100644 (file)
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -11,6 +11,10 @@
 
 #define L1_CACHE_BYTES         (1 << L1_CACHE_SHIFT)
 
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#endif
+
 /*
  * RISC-V requires the stack pointer to be 16-byte aligned, so ensure that
  * the flat loader aligns it accordingly.

diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 23ff7035099261a7c8cc972bb0259aca45437fc7..a60acaecfedab6ad09e578b1f1a98b04a08541c7 100644 (file)
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -42,6 +42,16 @@ 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
+
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+void riscv_noncoherent_supported(void);
+#endif
+
 /*
  * Bits in sys_riscv_flush_icache()'s flags argument.
  */

diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 9e2888dbb5b1316b8a66990067b9b9cd50c6246b..f7c0150058478db81f15a22c4277ccbdc1e711ff 100644 (file)
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -20,7 +20,8 @@
 #endif
 
 #define        CPUFEATURE_SVPBMT 0
-#define        CPUFEATURE_NUMBER 1
+#define        CPUFEATURE_ZICBOM 1
+#define        CPUFEATURE_NUMBER 2
 
 #ifdef __ASSEMBLY__
 
@@ -93,6 +94,22 @@ asm volatile(ALTERNATIVE(                                            \
 #define ALT_THEAD_PMA(_val)
 #endif
 
+#define ALT_CMO_OP(_op, _start, _size, _cachesize)                     \
+asm volatile(ALTERNATIVE(                                              \
+       __nops(5),                                                      \
+       "mv a0, %1\n\t"                                                 \
+       "j 2f\n\t"                                                      \
+       "3:\n\t"                                                        \
+       "cbo." __stringify(_op) " (a0)\n\t"                             \
+       "add a0, a0, %0\n\t"                                            \
+       "2:\n\t"                                                        \
+       "bltu a0, %2, 3b\n\t", 0,                                       \
+               CPUFEATURE_ZICBOM, CONFIG_RISCV_ISA_ZICBOM)             \
+       : : "r"(_cachesize),                                            \
+           "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),       \
+           "r"((unsigned long)(_start) + (_size))                      \
+       : "a0")
+
 #endif /* __ASSEMBLY__ */
 
 #endif

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index e48eebdd26315eb457a9f5e759ffa9eb951dd467..ed4045e70f7a9e4fd2f0397635e97797e0b59252 100644 (file)
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -54,6 +54,7 @@ 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,
 };
 

diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index fba9e9f46a8c7aa4cc54c681341caaab368f9f1a..0365557f712249bed323adcf8f507dd171c31d6a 100644 (file)
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -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),
 };
 

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 1b3ec44e25f56ae103451b32c9e31b789e99fe51..1e33beda4f017ad7c34b392492015e5ffa4dde28 100644 (file)
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <asm/alternative.h>
+#include <asm/cacheflush.h>
 #include <asm/errata_list.h>
 #include <asm/hwcap.h>
 #include <asm/patch.h>
@@ -198,6 +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
                }
@@ -259,6 +261,25 @@ static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage)
        return false;
 }
 
+static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage)
+{
+#ifdef CONFIG_RISCV_ISA_ZICBOM
+       switch (stage) {
+       case RISCV_ALTERNATIVES_EARLY_BOOT:
+               return false;
+       default:
+               if (riscv_isa_extension_available(NULL, ZICBOM)) {
+                       riscv_noncoherent_supported();
+                       return true;
+               } else {
+                       return false;
+               }
+       }
+#endif
+
+       return false;
+}
+
 /*
  * Probe presence of individual extensions.
  *
@@ -273,6 +294,9 @@ static u32 __init_or_module cpufeature_probe(unsigned int stage)
        if (cpufeature_probe_svpbmt(stage))
                cpu_req_feature |= (1U << CPUFEATURE_SVPBMT);
 
+       if (cpufeature_probe_zicbom(stage))
+               cpu_req_feature |= (1U << CPUFEATURE_ZICBOM);
+
        return cpu_req_feature;
 }
 

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f0f36a4a0e9b811a17922f32d62b306696419e8c..95ef6e2bf45c02faffaa4228ae50393d9146c6fd 100644 (file)
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -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();
 }
 

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index ac7a25298a04af665ff0552d99a95e1671013ddd..d76aabf4b94d6a8bf4ef20eab680de4d4be16ff9 100644 (file)
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -30,3 +30,4 @@ endif
 endif
 
 obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o

diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
new file mode 100644 (file)
index 0000000..a8dc0bd
--- /dev/null
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -0,0 +1,112 @@
+// 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/mm.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <asm/cacheflush.h>
+
+static unsigned int riscv_cbom_block_size = L1_CACHE_BYTES;
+static bool noncoherent_supported;
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+                             enum dma_data_direction dir)
+{
+       void *vaddr = phys_to_virt(paddr);
+
+       switch (dir) {
+       case DMA_TO_DEVICE:
+               ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+               break;
+       case DMA_FROM_DEVICE:
+               ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+               break;
+       case DMA_BIDIRECTIONAL:
+               ALT_CMO_OP(flush, vaddr, 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)
+{
+       void *vaddr = phys_to_virt(paddr);
+
+       switch (dir) {
+       case DMA_TO_DEVICE:
+               break;
+       case DMA_FROM_DEVICE:
+       case DMA_BIDIRECTIONAL:
+               ALT_CMO_OP(flush, vaddr, 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);
+
+       ALT_CMO_OP(flush, 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)
+{
+       WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
+                  TAINT_CPU_OUT_OF_SPEC,
+                  "%s %s: ARCH_DMA_MINALIGN smaller than riscv,cbom-block-size (%d < %d)",
+                  dev_driver_string(dev), dev_name(dev),
+                  ARCH_DMA_MINALIGN, riscv_cbom_block_size);
+
+       WARN_TAINT(!coherent && !noncoherent_supported, TAINT_CPU_OUT_OF_SPEC,
+                  "%s %s: device non-coherent but no non-coherent operations supported",
+                  dev_driver_string(dev), dev_name(dev));
+
+       dev->dma_coherent = coherent;
+}
+
+#ifdef CONFIG_RISCV_ISA_ZICBOM
+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);
+               }
+       }
+}
+#endif
+
+void riscv_noncoherent_supported(void)
+{
+       noncoherent_supported = true;
+}