RISC-V: ACPI: Enhance acpi_os_ioremap with MMIO remapping

Enhance the acpi_os_ioremap() to support opregions in MMIO space. Also,
have strict checks using EFI memory map to allow remapping the RAM similar
to arm64.

Signed-off-by: Sunil V L <sunilvl@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231018124007.1306159-2-sunilvl@ventanamicro.com
Signed-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/kernel/acpi.c

@@ -14,9 +14,10 @@
  */
 
 #include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/pci.h>
 #include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/pci.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