Merge patch series "Add non-coherent DMA support for AX45MP"

Prabhakar <prabhakar.csengg@gmail.com> says:

From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>

non-coherent DMA support for AX45MP
====================================

On the Andes AX45MP core, cache coherency is a specification option so it
may not be supported. In this case DMA will fail. To get around with this
issue this patch series does the below:

1] Andes alternative ports is implemented as errata which checks if the
IOCP is missing and only then applies to CMO errata. One vendor specific
SBI EXT (ANDES_SBI_EXT_IOCP_SW_WORKAROUND) is implemented as part of
errata.

Below are the configs which Andes port provides (and are selected by
RZ/Five):
      - ERRATA_ANDES
      - ERRATA_ANDES_CMO

OpenSBI patch supporting ANDES_SBI_EXT_IOCP_SW_WORKAROUND SBI is now
part v1.3 release.

2] Andes AX45MP core has a Programmable Physical Memory Attributes (PMA)
block that allows dynamic adjustment of memory attributes in the runtime.
It contains a configurable amount of PMA entries implemented as CSR
registers to control the attributes of memory locations in interest.
OpenSBI configures the PMA regions as required and creates a reserve memory
node and propagates it to the higher boot stack.

Currently OpenSBI (upstream) configures the required PMA region and passes
this a shared DMA pool to Linux.

    reserved-memory {
        #address-cells = <2>;
        #size-cells = <2>;
        ranges;

        pma_resv0@58000000 {
            compatible = "shared-dma-pool";
            reg = <0x0 0x58000000 0x0 0x08000000>;
            no-map;
            linux,dma-default;
        };
    };

The above shared DMA pool gets appended to Linux DTB so the DMA memory
requests go through this region.

3] We provide callbacks to synchronize specific content between memory and
cache.

4] RZ/Five SoC selects the below configs
        - AX45MP_L2_CACHE
        - DMA_GLOBAL_POOL
        - ERRATA_ANDES
        - ERRATA_ANDES_CMO

----------x---------------------x--------------------x---------------x----

* b4-shazam-merge:
  soc: renesas: Kconfig: Select the required configs for RZ/Five SoC
  cache: Add L2 cache management for Andes AX45MP RISC-V core
  dt-bindings: cache: andestech,ax45mp-cache: Add DT binding documentation for L2 cache controller
  riscv: mm: dma-noncoherent: nonstandard cache operations support
  riscv: errata: Add Andes alternative ports
  riscv: asm: vendorid_list: Add Andes Technology to the vendors list

Link: https://lore.kernel.org/r/20230818135723.80612-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

12 files changed, 194 insertions, 0 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 5138dce1a0b4..468063780a93 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -275,6 +275,13 @@ config RISCV_DMA_NONCOHERENT
 	select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB
 	select DMA_DIRECT_REMAP
 
+config RISCV_NONSTANDARD_CACHE_OPS
+	bool
+	depends on RISCV_DMA_NONCOHERENT
+	help
+	  This enables function pointer support for non-standard noncoherent
+	  systems to handle cache management.
+
 config AS_HAS_INSN
 	def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero)
 
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 0c8f4652cd82..92c779764b27 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -1,5 +1,26 @@
 menu "CPU errata selection"
 
+config ERRATA_ANDES
+	bool "Andes AX45MP errata"
+	depends on RISCV_ALTERNATIVE
+	help
+	  All Andes errata Kconfig depend on this Kconfig. Disabling
+	  this Kconfig will disable all Andes errata. Please say "Y"
+	  here if your platform uses Andes CPU cores.
+
+	  Otherwise, please say "N" here to avoid unnecessary overhead.
+
+config ERRATA_ANDES_CMO
+	bool "Apply Andes cache management errata"
+	depends on ERRATA_ANDES && MMU && ARCH_R9A07G043
+	select RISCV_DMA_NONCOHERENT
+	default y
+	help
+	  This will apply the cache management errata to handle the
+	  non-standard handling on non-coherent operations on Andes cores.
+
+	  If you don't know what to do here, say "Y".
+
 config ERRATA_SIFIVE
 	bool "SiFive errata"
 	depends on RISCV_ALTERNATIVE
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index 7b2637c8c332..8a2739485123 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -2,5 +2,6 @@ ifdef CONFIG_RELOCATABLE
 KBUILD_CFLAGS += -fno-pie
 endif
 
+obj-$(CONFIG_ERRATA_ANDES) += andes/
 obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
 obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/errata/andes/Makefile b/arch/riscv/errata/andes/Makefile
new file mode 100644
index 000000000000..2d644e19caef
--- /dev/null
+++ b/arch/riscv/errata/andes/Makefile
@@ -0,0 +1 @@
+obj-y += errata.o
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
new file mode 100644
index 000000000000..197db68cc8da
--- /dev/null
+++ b/arch/riscv/errata/andes/errata.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Erratas to be applied for Andes CPU cores
+ *
+ *  Copyright (C) 2023 Renesas Electronics Corporation.
+ *
+ * Author: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+ */
+
+#include <linux/memory.h>
+#include <linux/module.h>
+
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/errata_list.h>
+#include <asm/patch.h>
+#include <asm/processor.h>
+#include <asm/sbi.h>
+#include <asm/vendorid_list.h>
+
+#define ANDESTECH_AX45MP_MARCHID	0x8000000000008a45UL
+#define ANDESTECH_AX45MP_MIMPID		0x500UL
+#define ANDESTECH_SBI_EXT_ANDES		0x0900031E
+
+#define ANDES_SBI_EXT_IOCP_SW_WORKAROUND	1
+
+static long ax45mp_iocp_sw_workaround(void)
+{
+	struct sbiret ret;
+
+	/*
+	 * ANDES_SBI_EXT_IOCP_SW_WORKAROUND SBI EXT checks if the IOCP is missing and
+	 * cache is controllable only then CMO will be applied to the platform.
+	 */
+	ret = sbi_ecall(ANDESTECH_SBI_EXT_ANDES, ANDES_SBI_EXT_IOCP_SW_WORKAROUND,
+			0, 0, 0, 0, 0, 0);
+
+	return ret.error ? 0 : ret.value;
+}
+
+static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO))
+		return false;
+
+	if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID)
+		return false;
+
+	if (!ax45mp_iocp_sw_workaround())
+		return false;
+
+	/* Set this just to make core cbo code happy */
+	riscv_cbom_block_size = 1;
+	riscv_noncoherent_supported();
+
+	return true;
+}
+
+void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+					      unsigned long archid, unsigned long impid,
+					      unsigned int stage)
+{
+	errata_probe_iocp(stage, archid, impid);
+
+	/* we have nothing to patch here ATM so just return back */
+}
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 58ccd2f8cab7..3c2b59b25017 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -45,6 +45,9 @@ struct alt_entry {
 	u32 patch_id;		/* The patch ID (erratum ID or cpufeature ID) */
 };
 
+void andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			     unsigned long archid, unsigned long impid,
+			     unsigned int stage);
 void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			      unsigned long archid, unsigned long impid,
 			      unsigned int stage);
diff --git a/arch/riscv/include/asm/dma-noncoherent.h b/arch/riscv/include/asm/dma-noncoherent.h
new file mode 100644
index 000000000000..312cfa0858fb
--- /dev/null
+++ b/arch/riscv/include/asm/dma-noncoherent.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+
+#ifndef __ASM_DMA_NONCOHERENT_H
+#define __ASM_DMA_NONCOHERENT_H
+
+#include <linux/dma-direct.h>
+
+/*
+ * struct riscv_nonstd_cache_ops - Structure for non-standard CMO function pointers
+ *
+ * @wback: Function pointer for cache writeback
+ * @inv: Function pointer for invalidating cache
+ * @wback_inv: Function pointer for flushing the cache (writeback + invalidating)
+ */
+struct riscv_nonstd_cache_ops {
+	void (*wback)(phys_addr_t paddr, size_t size);
+	void (*inv)(phys_addr_t paddr, size_t size);
+	void (*wback_inv)(phys_addr_t paddr, size_t size);
+};
+
+extern struct riscv_nonstd_cache_ops noncoherent_cache_ops;
+
+void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops);
+
+#endif	/* __ASM_DMA_NONCOHERENT_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index fb1a810f3d8c..e2ecd01bfac7 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -11,6 +11,11 @@
 #include <asm/hwcap.h>
 #include <asm/vendorid_list.h>
 
+#ifdef CONFIG_ERRATA_ANDES
+#define ERRATA_ANDESTECH_NO_IOCP	0
+#define ERRATA_ANDESTECH_NUMBER		1
+#endif
+
 #ifdef CONFIG_ERRATA_SIFIVE
 #define	ERRATA_SIFIVE_CIP_453 0
 #define	ERRATA_SIFIVE_CIP_1200 1
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
index cb89af3f0704..e55407ace0c3 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -5,6 +5,7 @@
 #ifndef ASM_VENDOR_LIST_H
 #define ASM_VENDOR_LIST_H
 
+#define ANDESTECH_VENDOR_ID	0x31e
 #define SIFIVE_VENDOR_ID	0x489
 #define THEAD_VENDOR_ID		0x5b7
 
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 85056153fa23..319a1da0358b 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -42,6 +42,11 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 #endif
 
 	switch (cpu_mfr_info->vendor_id) {
+#ifdef CONFIG_ERRATA_ANDES
+	case ANDESTECH_VENDOR_ID:
+		cpu_mfr_info->patch_func = andes_errata_patch_func;
+		break;
+#endif
 #ifdef CONFIG_ERRATA_SIFIVE
 	case SIFIVE_VENDOR_ID:
 		cpu_mfr_info->patch_func = sifive_errata_patch_func;
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index f269990e26c3..b76e7e192eb1 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -9,15 +9,28 @@
 #include <linux/dma-map-ops.h>
 #include <linux/mm.h>
 #include <asm/cacheflush.h>
+#include <asm/dma-noncoherent.h>
 
 static bool noncoherent_supported __ro_after_init;
 int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN;
 EXPORT_SYMBOL_GPL(dma_cache_alignment);
 
+struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init = {
+	.wback = NULL,
+	.inv = NULL,
+	.wback_inv = NULL,
+};
+
 static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback)) {
+		noncoherent_cache_ops.wback(paddr, size);
+		return;
+	}
+#endif
 	ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
 }
 
@@ -25,6 +38,13 @@ static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.inv)) {
+		noncoherent_cache_ops.inv(paddr, size);
+		return;
+	}
+#endif
+
 	ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
 }
 
@@ -32,6 +52,13 @@ static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback_inv)) {
+		noncoherent_cache_ops.wback_inv(paddr, size);
+		return;
+	}
+#endif
+
 	ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
 }
 
@@ -97,6 +124,13 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 {
 	void *flush_addr = page_address(page);
 
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback_inv)) {
+		noncoherent_cache_ops.wback_inv(page_to_phys(page), size);
+		return;
+	}
+#endif
+
 	ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
 }
 
@@ -128,3 +162,12 @@ void __init riscv_set_dma_cache_alignment(void)
 	if (!noncoherent_supported)
 		dma_cache_alignment = 1;
 }
+
+void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
+{
+	if (!ops)
+		return;
+
+	noncoherent_cache_ops = *ops;
+}
+EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);
diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c
index 089df92ae876..c5fc5ec96f6d 100644
--- a/arch/riscv/mm/pmem.c
+++ b/arch/riscv/mm/pmem.c
@@ -7,15 +7,28 @@
 #include <linux/libnvdimm.h>
 
 #include <asm/cacheflush.h>
+#include <asm/dma-noncoherent.h>
 
 void arch_wb_cache_pmem(void *addr, size_t size)
 {
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback)) {
+		noncoherent_cache_ops.wback(virt_to_phys(addr), size);
+		return;
+	}
+#endif
 	ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
 void arch_invalidate_pmem(void *addr, size_t size)
 {
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.inv)) {
+		noncoherent_cache_ops.inv(virt_to_phys(addr), size);
+		return;
+	}
+#endif
 	ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);