Merge patch series "RISC-V: ACPI improvements"

Sunil V L <sunilvl@ventanamicro.com> says:

This series is a set of patches which were originally part of RFC v1 series
[1] to add ACPI support in RISC-V interrupt controllers. Since these
patches are independent of the interrupt controllers, creating this new
series which helps to merge instead of waiting for big series.

This set of patches primarily adds support below ECR [2] which is approved
by the ASWG and adds below features.

- Get CBO block sizes from RHCT on ACPI based systems.

Additionally, the series contains a patch to improve acpi_os_ioremap().

[1] - https://lore.kernel.org/lkml/20230803175202.3173957-1-sunilvl@ventanamicro.com/
[2] - https://drive.google.com/file/d/1sKbOa8m1UZw1JkquZYe3F1zQBN1xXsaf/view?usp=sharing

* b4-shazam-merge:
  RISC-V: cacheflush: Initialize CBO variables on ACPI systems
  RISC-V: ACPI: RHCT: Add function to get CBO block sizes
  RISC-V: ACPI: Update the return value of acpi_get_rhct()
  RISC-V: ACPI: Enhance acpi_os_ioremap with MMIO remapping

Link: https://lore.kernel.org/r/20231018124007.1306159-1-sunilvl@ventanamicro.comSigned-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/Kconfig

@@ -39,6 +39,7 @@ config RISCV
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAS_VDSO_DATA
+	select ARCH_KEEP_MEMBLOCK if ACPI
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK

arch/riscv/include/asm/acpi.h

@@ -66,6 +66,8 @@ int acpi_get_riscv_isa(struct acpi_table_header *table,
 		       unsigned int cpu, const char **isa);
 
 static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
+			     u32 *cboz_size, u32 *cbop_size);
 #else
 static inline void acpi_init_rintc_map(void) { }
 static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu)
@@ -79,6 +81,10 @@ static inline int acpi_get_riscv_isa(struct acpi_table_header *table,
 	return -EINVAL;
 }
 
+static inline void acpi_get_cbo_block_size(struct acpi_table_header *table,
+					   u32 *cbom_size, u32 *cboz_size,
+					   u32 *cbop_size) { }
+
 #endif /* CONFIG_ACPI */
 
 #endif /*_ASM_ACPI_H*/

arch/riscv/kernel/acpi.c

@@ -14,9 +14,10 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/efi.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 #include <linux/pci.h>
-#include <linux/efi.h>
 
 int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
 int acpi_disabled = 1;
@@ -217,7 +218,89 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
 
 void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 {
-	return (void __iomem *)memremap(phys, size, MEMREMAP_WB);
+	efi_memory_desc_t *md, *region = NULL;
+	pgprot_t prot;
+
+	if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP)))
+		return NULL;
+
+	for_each_efi_memory_desc(md) {
+		u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+
+		if (phys < md->phys_addr || phys >= end)
+			continue;
+
+		if (phys + size > end) {
+			pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n");
+			return NULL;
+		}
+		region = md;
+		break;
+	}
+
+	/*
+	 * It is fine for AML to remap regions that are not represented in the
+	 * EFI memory map at all, as it only describes normal memory, and MMIO
+	 * regions that require a virtual mapping to make them accessible to
+	 * the EFI runtime services.
+	 */
+	prot = PAGE_KERNEL_IO;
+	if (region) {
+		switch (region->type) {
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+		case EFI_PERSISTENT_MEMORY:
+			if (memblock_is_map_memory(phys) ||
+			    !memblock_is_region_memory(phys, size)) {
+				pr_warn(FW_BUG "requested region covers kernel memory\n");
+				return NULL;
+			}
+
+			/*
+			 * Mapping kernel memory is permitted if the region in
+			 * question is covered by a single memblock with the
+			 * NOMAP attribute set: this enables the use of ACPI
+			 * table overrides passed via initramfs.
+			 * This particular use case only requires read access.
+			 */
+			fallthrough;
+
+		case EFI_RUNTIME_SERVICES_CODE:
+			/*
+			 * This would be unusual, but not problematic per se,
+			 * as long as we take care not to create a writable
+			 * mapping for executable code.
+			 */
+			prot = PAGE_KERNEL_RO;
+			break;
+
+		case EFI_ACPI_RECLAIM_MEMORY:
+			/*
+			 * ACPI reclaim memory is used to pass firmware tables
+			 * and other data that is intended for consumption by
+			 * the OS only, which may decide it wants to reclaim
+			 * that memory and use it for something else. We never
+			 * do that, but we usually add it to the linear map
+			 * anyway, in which case we should use the existing
+			 * mapping.
+			 */
+			if (memblock_is_map_memory(phys))
+				return (void __iomem *)__va(phys);
+			fallthrough;
+
+		default:
+			if (region->attribute & EFI_MEMORY_WB)
+				prot = PAGE_KERNEL;
+			else if ((region->attribute & EFI_MEMORY_WC) ||
+				 (region->attribute & EFI_MEMORY_WT))
+				prot = pgprot_writecombine(PAGE_KERNEL);
+		}
+	}
+
+	return ioremap_prot(phys, size, pgprot_val(prot));
 }
 
 #ifdef CONFIG_PCI

arch/riscv/mm/cacheflush.c

@@ -3,7 +3,9 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/acpi.h>
 #include <linux/of.h>
+#include <asm/acpi.h>
 #include <asm/cacheflush.h>
 
 #ifdef CONFIG_SMP
@@ -124,7 +126,10 @@ void __init riscv_init_cbo_blocksizes(void)
 	unsigned long cbom_hartid, cboz_hartid;
 	u32 cbom_block_size = 0, cboz_block_size = 0;
 	struct device_node *node;
+	struct acpi_table_header *rhct;
+	acpi_status status;
 
+	if (acpi_disabled) {
 		for_each_of_cpu_node(node) {
 			/* set block-size for cbom and/or cboz extension if available */
 			cbo_get_block_size(node, "riscv,cbom-block-size",
@@ -132,6 +137,14 @@ void __init riscv_init_cbo_blocksizes(void)
 			cbo_get_block_size(node, "riscv,cboz-block-size",
 					   &cboz_block_size, &cboz_hartid);
 		}
+	} else {
+		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
+		if (ACPI_FAILURE(status))
+			return;
+
+		acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL);
+		acpi_put_table((struct acpi_table_header *)rhct);
+	}
 
 	if (cbom_block_size)
 		riscv_cbom_block_size = cbom_block_size;

drivers/acpi/riscv/rhct.c

@@ -8,8 +8,9 @@
 #define pr_fmt(fmt)     "ACPI: RHCT: " fmt
 
 #include <linux/acpi.h>
+#include <linux/bits.h>
 
-static struct acpi_table_header *acpi_get_rhct(void)
+static struct acpi_table_rhct *acpi_get_rhct(void)
 {
 	static struct acpi_table_header *rhct;
 	acpi_status status;
@@ -26,7 +27,7 @@ static struct acpi_table_header *acpi_get_rhct(void)
 		}
 	}
 
-	return rhct;
+	return (struct acpi_table_rhct *)rhct;
 }
 
 /*
@@ -48,7 +49,7 @@ int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const
 	BUG_ON(acpi_disabled);
 
 	if (!table) {
-		rhct = (struct acpi_table_rhct *)acpi_get_rhct();
+		rhct = acpi_get_rhct();
 		if (!rhct)
 			return -ENOENT;
 	} else {
@@ -81,3 +82,89 @@ int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const
 
 	return -1;
 }
+
+static void acpi_parse_hart_info_cmo_node(struct acpi_table_rhct *rhct,
+					  struct acpi_rhct_hart_info *hart_info,
+					  u32 *cbom_size, u32 *cboz_size, u32 *cbop_size)
+{
+	u32 size_hartinfo = sizeof(struct acpi_rhct_hart_info);
+	u32 size_hdr = sizeof(struct acpi_rhct_node_header);
+	struct acpi_rhct_node_header *ref_node;
+	struct acpi_rhct_cmo_node *cmo_node;
+	u32 *hart_info_node_offset;
+
+	hart_info_node_offset = ACPI_ADD_PTR(u32, hart_info, size_hartinfo);
+	for (int i = 0; i < hart_info->num_offsets; i++) {
+		ref_node = ACPI_ADD_PTR(struct acpi_rhct_node_header,
+					rhct, hart_info_node_offset[i]);
+		if (ref_node->type == ACPI_RHCT_NODE_TYPE_CMO) {
+			cmo_node = ACPI_ADD_PTR(struct acpi_rhct_cmo_node,
+						ref_node, size_hdr);
+			if (cbom_size && cmo_node->cbom_size <= 30) {
+				if (!*cbom_size)
+					*cbom_size = BIT(cmo_node->cbom_size);
+				else if (*cbom_size != BIT(cmo_node->cbom_size))
+					pr_warn("CBOM size is not the same across harts\n");
+			}
+
+			if (cboz_size && cmo_node->cboz_size <= 30) {
+				if (!*cboz_size)
+					*cboz_size = BIT(cmo_node->cboz_size);
+				else if (*cboz_size != BIT(cmo_node->cboz_size))
+					pr_warn("CBOZ size is not the same across harts\n");
+			}
+
+			if (cbop_size && cmo_node->cbop_size <= 30) {
+				if (!*cbop_size)
+					*cbop_size = BIT(cmo_node->cbop_size);
+				else if (*cbop_size != BIT(cmo_node->cbop_size))
+					pr_warn("CBOP size is not the same across harts\n");
+			}
+		}
+	}
+}
+
+/*
+ * During early boot, the caller should call acpi_get_table() and pass its pointer to
+ * these functions (and free up later). At run time, since this table can be used
+ * multiple times, pass NULL so that the table remains in memory.
+ */
+void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
+			     u32 *cboz_size, u32 *cbop_size)
+{
+	u32 size_hdr = sizeof(struct acpi_rhct_node_header);
+	struct acpi_rhct_node_header *node, *end;
+	struct acpi_rhct_hart_info *hart_info;
+	struct acpi_table_rhct *rhct;
+
+	if (acpi_disabled)
+		return;
+
+	if (table) {
+		rhct = (struct acpi_table_rhct *)table;
+	} else {
+		rhct = acpi_get_rhct();
+		if (!rhct)
+			return;
+	}
+
+	if (cbom_size)
+		*cbom_size = 0;
+
+	if (cboz_size)
+		*cboz_size = 0;
+
+	if (cbop_size)
+		*cbop_size = 0;
+
+	end = ACPI_ADD_PTR(struct acpi_rhct_node_header, rhct, rhct->header.length);
+	for (node = ACPI_ADD_PTR(struct acpi_rhct_node_header, rhct, rhct->node_offset);
+	     node < end;
+	     node = ACPI_ADD_PTR(struct acpi_rhct_node_header, node, node->length)) {
+		if (node->type == ACPI_RHCT_NODE_TYPE_HART_INFO) {
+			hart_info = ACPI_ADD_PTR(struct acpi_rhct_hart_info, node, size_hdr);
+			acpi_parse_hart_info_cmo_node(rhct, hart_info, cbom_size,
+						      cboz_size, cbop_size);
+		}
+	}
+}