diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 8dc686f549b66cdf880656912b52f38ce4b7fd67..ea1a0e237211093d26aa4f5842080f2a80982cdb 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -90,6 +90,14 @@ typedef struct page *pgtable_t;
 #define PTE_FMT "%08lx"
 #endif
 
+#ifdef CONFIG_64BIT
+/*
+ * We override this value as its generic definition uses __pa too early in
+ * the boot process (before kernel_map.va_pa_offset is set).
+ */
+#define MIN_MEMBLOCK_ADDR      0
+#endif
+
 #ifdef CONFIG_MMU
 #define ARCH_PFN_OFFSET		(PFN_DOWN((unsigned long)phys_ram_base))
 #else
@@ -121,7 +129,11 @@ extern phys_addr_t phys_ram_base;
 #define is_linear_mapping(x)	\
 	((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE))
 
+#ifndef CONFIG_DEBUG_VIRTUAL
 #define linear_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + kernel_map.va_pa_offset))
+#else
+void *linear_mapping_pa_to_va(unsigned long x);
+#endif
 #define kernel_mapping_pa_to_va(y)	({					\
 	unsigned long _y = (unsigned long)(y);					\
 	(IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ?			\
@@ -130,7 +142,11 @@ extern phys_addr_t phys_ram_base;
 	})
 #define __pa_to_va_nodebug(x)		linear_mapping_pa_to_va(x)
 
+#ifndef CONFIG_DEBUG_VIRTUAL
 #define linear_mapping_va_to_pa(x)	((unsigned long)(x) - kernel_map.va_pa_offset)
+#else
+phys_addr_t linear_mapping_va_to_pa(unsigned long x);
+#endif
 #define kernel_mapping_va_to_pa(y) ({						\
 	unsigned long _y = (unsigned long)(y);					\
 	(IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ? \
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index ed07ae111f3a4866149ba4e931eb42f5c88bad77..7bd66795165da946798cd50bdcb2177d9233c85d 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -213,6 +213,14 @@ static void __init setup_bootmem(void)
 	phys_ram_end = memblock_end_of_DRAM();
 	if (!IS_ENABLED(CONFIG_XIP_KERNEL))
 		phys_ram_base = memblock_start_of_DRAM();
+
+	/*
+	 * In 64-bit, any use of __va/__pa before this point is wrong as we
+	 * did not know the start of DRAM before.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT))
+		kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
+
 	/*
 	 * memblock allocator is not aware of the fact that last 4K bytes of
 	 * the addressable memory can not be mapped because of IS_ERR_VALUE
@@ -667,9 +675,16 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 
 static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 {
-	/* Upgrade to PMD_SIZE mappings whenever possible */
-	base &= PMD_SIZE - 1;
-	if (!base && size >= PMD_SIZE)
+	if (!(base & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
+		return PGDIR_SIZE;
+
+	if (!(base & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+		return P4D_SIZE;
+
+	if (!(base & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+		return PUD_SIZE;
+
+	if (!(base & (PMD_SIZE - 1)) && size >= PMD_SIZE)
 		return PMD_SIZE;
 
 	return PAGE_SIZE;
@@ -978,11 +993,22 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	set_satp_mode();
 #endif
 
-	kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
+	/*
+	 * In 64-bit, we defer the setup of va_pa_offset to setup_bootmem,
+	 * where we have the system memory layout: this allows us to align
+	 * the physical and virtual mappings and then make use of PUD/P4D/PGD
+	 * for the linear mapping. This is only possible because the kernel
+	 * mapping lies outside the linear mapping.
+	 * In 32-bit however, as the kernel resides in the linear mapping,
+	 * setup_vm_final can not change the mapping established here,
+	 * otherwise the same kernel addresses would get mapped to different
+	 * physical addresses (if the start of dram is different from the
+	 * kernel physical address start).
+	 */
+	kernel_map.va_pa_offset = IS_ENABLED(CONFIG_64BIT) ?
+				0UL : PAGE_OFFSET - kernel_map.phys_addr;
 	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
 
-	phys_ram_base = kernel_map.phys_addr;
-
 	/*
 	 * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
 	 * kernel, whereas for 64-bit kernel, the end of the virtual address
@@ -1106,6 +1132,17 @@ static void __init create_linear_mapping_page_table(void)
 	phys_addr_t start, end;
 	u64 i;
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+	phys_addr_t ktext_start = __pa_symbol(_start);
+	phys_addr_t ktext_size = __init_data_begin - _start;
+	phys_addr_t krodata_start = __pa_symbol(__start_rodata);
+	phys_addr_t krodata_size = _data - __start_rodata;
+
+	/* Isolate kernel text and rodata so they don't get mapped with a PUD */
+	memblock_mark_nomap(ktext_start,  ktext_size);
+	memblock_mark_nomap(krodata_start, krodata_size);
+#endif
+
 	/* Map all memory banks in the linear mapping */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -1118,6 +1155,15 @@ static void __init create_linear_mapping_page_table(void)
 
 		create_linear_mapping_range(start, end);
 	}
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+	create_linear_mapping_range(ktext_start, ktext_start + ktext_size);
+	create_linear_mapping_range(krodata_start,
+				    krodata_start + krodata_size);
+
+	memblock_clear_nomap(ktext_start,  ktext_size);
+	memblock_clear_nomap(krodata_start, krodata_size);
+#endif
 }
 
 static void __init setup_vm_final(void)
diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c
index 9b18bda74154e8a3b2b807cd0ae2065eb7c28612..18706f457da7ecf84591510ea26789f7ae3e9abf 100644
--- a/arch/riscv/mm/physaddr.c
+++ b/arch/riscv/mm/physaddr.c
@@ -33,3 +33,19 @@ phys_addr_t __phys_addr_symbol(unsigned long x)
 	return __va_to_pa_nodebug(x);
 }
 EXPORT_SYMBOL(__phys_addr_symbol);
+
+phys_addr_t linear_mapping_va_to_pa(unsigned long x)
+{
+	BUG_ON(!kernel_map.va_pa_offset);
+
+	return ((unsigned long)(x) - kernel_map.va_pa_offset);
+}
+EXPORT_SYMBOL(linear_mapping_va_to_pa);
+
+void *linear_mapping_pa_to_va(unsigned long x)
+{
+	BUG_ON(!kernel_map.va_pa_offset);
+
+	return ((void *)((unsigned long)(x) + kernel_map.va_pa_offset));
+}
+EXPORT_SYMBOL(linear_mapping_pa_to_va);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index d1a68b6d03b3f1df3789511a432b92ca15911e2a..d14735a8130117181035dff535e2f4876c787555 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -887,12 +887,13 @@ const void * __init of_flat_dt_match_machine(const void *default_match,
 static void __early_init_dt_declare_initrd(unsigned long start,
 					   unsigned long end)
 {
-	/* ARM64 would cause a BUG to occur here when CONFIG_DEBUG_VM is
-	 * enabled since __va() is called too early. ARM64 does make use
-	 * of phys_initrd_start/phys_initrd_size so we can skip this
-	 * conversion.
+	/*
+	 * __va() is not yet available this early on some platforms. In that
+	 * case, the platform uses phys_initrd_start/phys_initrd_size instead
+	 * and does the VA conversion itself.
 	 */
-	if (!IS_ENABLED(CONFIG_ARM64)) {
+	if (!IS_ENABLED(CONFIG_ARM64) &&
+	    !(IS_ENABLED(CONFIG_RISCV) && IS_ENABLED(CONFIG_64BIT))) {
 		initrd_start = (unsigned long)__va(start);
 		initrd_end = (unsigned long)__va(end);
 		initrd_below_start_ok = 1;