Merge tag 'riscv-for-linus-5.18-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for Sv57-based virtual memory.

 - Various improvements for the MicroChip PolarFire SOC and the
   associated Icicle dev board, which should allow upstream kernels to
   boot without any additional modifications.

 - An improved memmove() implementation.

 - Support for the new Ssconfpmf and SBI PMU extensions, which allows
   for a much more useful perf implementation on RISC-V systems.

 - Support for restartable sequences.

* tag 'riscv-for-linus-5.18-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (36 commits)
  rseq/selftests: Add support for RISC-V
  RISC-V: Add support for restartable sequence
  MAINTAINERS: Add entry for RISC-V PMU drivers
  Documentation: riscv: Remove the old documentation
  RISC-V: Add sscofpmf extension support
  RISC-V: Add perf platform driver based on SBI PMU extension
  RISC-V: Add RISC-V SBI PMU extension definitions
  RISC-V: Add a simple platform driver for RISC-V legacy perf
  RISC-V: Add a perf core library for pmu drivers
  RISC-V: Add CSR encodings for all HPMCOUNTERS
  RISC-V: Remove the current perf implementation
  RISC-V: Improve /proc/cpuinfo output for ISA extensions
  RISC-V: Do no continue isa string parsing without correct XLEN
  RISC-V: Implement multi-letter ISA extension probing framework
  RISC-V: Extract multi-letter extension names from "riscv, isa"
  RISC-V: Minimal parser for "riscv, isa" strings
  RISC-V: Correctly print supported extensions
  riscv: Fixed misaligned memory access. Fixed pointer comparison.
  MAINTAINERS: update riscv/microchip entry
  riscv: dts: microchip: add new peripherals to icicle kit device tree
  ...

2 files changed, 286 insertions, 37 deletions

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f6275b317129..9535bea8688c 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -38,14 +38,16 @@ EXPORT_SYMBOL(kernel_map);
 #endif
 
 #ifdef CONFIG_64BIT
-u64 satp_mode = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_48 : SATP_MODE_39;
+u64 satp_mode __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_57 : SATP_MODE_39;
 #else
-u64 satp_mode = SATP_MODE_32;
+u64 satp_mode __ro_after_init = SATP_MODE_32;
 #endif
 EXPORT_SYMBOL(satp_mode);
 
 bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
+bool pgtable_l5_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
 EXPORT_SYMBOL(pgtable_l4_enabled);
+EXPORT_SYMBOL(pgtable_l5_enabled);
 
 phys_addr_t phys_ram_base __ro_after_init;
 EXPORT_SYMBOL(phys_ram_base);
@@ -227,6 +229,7 @@ pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
 
 pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+static p4d_t __maybe_unused early_dtb_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
 static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
 static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
@@ -318,6 +321,16 @@ static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 #define early_pmd      ((pmd_t *)XIP_FIXUP(early_pmd))
 #endif /* CONFIG_XIP_KERNEL */
 
+static p4d_t trampoline_p4d[PTRS_PER_P4D] __page_aligned_bss;
+static p4d_t fixmap_p4d[PTRS_PER_P4D] __page_aligned_bss;
+static p4d_t early_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define trampoline_p4d ((p4d_t *)XIP_FIXUP(trampoline_p4d))
+#define fixmap_p4d     ((p4d_t *)XIP_FIXUP(fixmap_p4d))
+#define early_p4d      ((p4d_t *)XIP_FIXUP(early_p4d))
+#endif /* CONFIG_XIP_KERNEL */
+
 static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss;
 static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss;
 static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
@@ -432,6 +445,44 @@ static phys_addr_t alloc_pud_late(uintptr_t va)
 	return __pa(vaddr);
 }
 
+static p4d_t *__init get_p4d_virt_early(phys_addr_t pa)
+{
+	return (p4d_t *)((uintptr_t)pa);
+}
+
+static p4d_t *__init get_p4d_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_P4D);
+	return (p4d_t *)set_fixmap_offset(FIX_P4D, pa);
+}
+
+static p4d_t *__init get_p4d_virt_late(phys_addr_t pa)
+{
+	return (p4d_t *)__va(pa);
+}
+
+static phys_addr_t __init alloc_p4d_early(uintptr_t va)
+{
+	/* Only one P4D is available for early mapping */
+	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+
+	return (uintptr_t)early_p4d;
+}
+
+static phys_addr_t __init alloc_p4d_fixmap(uintptr_t va)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t alloc_p4d_late(uintptr_t va)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr);
+	return __pa(vaddr);
+}
+
 static void __init create_pud_mapping(pud_t *pudp,
 				      uintptr_t va, phys_addr_t pa,
 				      phys_addr_t sz, pgprot_t prot)
@@ -459,21 +510,55 @@ static void __init create_pud_mapping(pud_t *pudp,
 	create_pmd_mapping(nextp, va, pa, sz, prot);
 }
 
-#define pgd_next_t		pud_t
-#define alloc_pgd_next(__va)	(pgtable_l4_enabled ?			\
-		pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va))
-#define get_pgd_next_virt(__pa)	(pgtable_l4_enabled ?			\
-		pt_ops.get_pud_virt(__pa) : (pgd_next_t *)pt_ops.get_pmd_virt(__pa))
+static void __init create_p4d_mapping(p4d_t *p4dp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	pud_t *nextp;
+	phys_addr_t next_phys;
+	uintptr_t p4d_index = p4d_index(va);
+
+	if (sz == P4D_SIZE) {
+		if (p4d_val(p4dp[p4d_index]) == 0)
+			p4dp[p4d_index] = pfn_p4d(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (p4d_val(p4dp[p4d_index]) == 0) {
+		next_phys = pt_ops.alloc_pud(va);
+		p4dp[p4d_index] = pfn_p4d(PFN_DOWN(next_phys), PAGE_TABLE);
+		nextp = pt_ops.get_pud_virt(next_phys);
+		memset(nextp, 0, PAGE_SIZE);
+	} else {
+		next_phys = PFN_PHYS(_p4d_pfn(p4dp[p4d_index]));
+		nextp = pt_ops.get_pud_virt(next_phys);
+	}
+
+	create_pud_mapping(nextp, va, pa, sz, prot);
+}
+
+#define pgd_next_t		p4d_t
+#define alloc_pgd_next(__va)	(pgtable_l5_enabled ?			\
+		pt_ops.alloc_p4d(__va) : (pgtable_l4_enabled ?		\
+		pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va)))
+#define get_pgd_next_virt(__pa)	(pgtable_l5_enabled ?			\
+		pt_ops.get_p4d_virt(__pa) : (pgd_next_t *)(pgtable_l4_enabled ?	\
+		pt_ops.get_pud_virt(__pa) : (pud_t *)pt_ops.get_pmd_virt(__pa)))
 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
+				(pgtable_l5_enabled ?			\
+		create_p4d_mapping(__nextp, __va, __pa, __sz, __prot) : \
 				(pgtable_l4_enabled ?			\
-		create_pud_mapping(__nextp, __va, __pa, __sz, __prot) :	\
-		create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot))
-#define fixmap_pgd_next		(pgtable_l4_enabled ?			\
-		(uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd)
-#define trampoline_pgd_next	(pgtable_l4_enabled ?			\
-		(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)
-#define early_dtb_pgd_next	(pgtable_l4_enabled ?			\
-		(uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd)
+		create_pud_mapping((pud_t *)__nextp, __va, __pa, __sz, __prot) :	\
+		create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot)))
+#define fixmap_pgd_next		(pgtable_l5_enabled ?			\
+		(uintptr_t)fixmap_p4d : (pgtable_l4_enabled ?		\
+		(uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd))
+#define trampoline_pgd_next	(pgtable_l5_enabled ?			\
+		(uintptr_t)trampoline_p4d : (pgtable_l4_enabled ?	\
+		(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd))
+#define early_dtb_pgd_next	(pgtable_l5_enabled ?			\
+		(uintptr_t)early_dtb_p4d : (pgtable_l4_enabled ?	\
+		(uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd))
 #else
 #define pgd_next_t		pte_t
 #define alloc_pgd_next(__va)	pt_ops.alloc_pte(__va)
@@ -482,6 +567,7 @@ static void __init create_pud_mapping(pud_t *pudp,
 	create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
 #define fixmap_pgd_next		((uintptr_t)fixmap_pte)
 #define early_dtb_pgd_next	((uintptr_t)early_dtb_pmd)
+#define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot)
 #define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot)
 #define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot)
 #endif /* __PAGETABLE_PMD_FOLDED */
@@ -575,6 +661,13 @@ static __init pgprot_t pgprot_from_va(uintptr_t va)
 #endif /* CONFIG_STRICT_KERNEL_RWX */
 
 #ifdef CONFIG_64BIT
+static void __init disable_pgtable_l5(void)
+{
+	pgtable_l5_enabled = false;
+	kernel_map.page_offset = PAGE_OFFSET_L4;
+	satp_mode = SATP_MODE_48;
+}
+
 static void __init disable_pgtable_l4(void)
 {
 	pgtable_l4_enabled = false;
@@ -591,12 +684,12 @@ static void __init disable_pgtable_l4(void)
 static __init void set_satp_mode(void)
 {
 	u64 identity_satp, hw_satp;
-	uintptr_t set_satp_mode_pmd;
+	uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
+	bool check_l4 = false;
 
-	set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
-	create_pgd_mapping(early_pg_dir,
-			   set_satp_mode_pmd, (uintptr_t)early_pud,
-			   PGDIR_SIZE, PAGE_TABLE);
+	create_p4d_mapping(early_p4d,
+			set_satp_mode_pmd, (uintptr_t)early_pud,
+			P4D_SIZE, PAGE_TABLE);
 	create_pud_mapping(early_pud,
 			   set_satp_mode_pmd, (uintptr_t)early_pmd,
 			   PUD_SIZE, PAGE_TABLE);
@@ -608,6 +701,11 @@ static __init void set_satp_mode(void)
 			   set_satp_mode_pmd + PMD_SIZE,
 			   set_satp_mode_pmd + PMD_SIZE,
 			   PMD_SIZE, PAGE_KERNEL_EXEC);
+retry:
+	create_pgd_mapping(early_pg_dir,
+			   set_satp_mode_pmd,
+			   check_l4 ? (uintptr_t)early_pud : (uintptr_t)early_p4d,
+			   PGDIR_SIZE, PAGE_TABLE);
 
 	identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;
 
@@ -616,10 +714,17 @@ static __init void set_satp_mode(void)
 	hw_satp = csr_swap(CSR_SATP, 0ULL);
 	local_flush_tlb_all();
 
-	if (hw_satp != identity_satp)
+	if (hw_satp != identity_satp) {
+		if (!check_l4) {
+			disable_pgtable_l5();
+			check_l4 = true;
+			goto retry;
+		}
 		disable_pgtable_l4();
+	}
 
 	memset(early_pg_dir, 0, PAGE_SIZE);
+	memset(early_p4d, 0, PAGE_SIZE);
 	memset(early_pud, 0, PAGE_SIZE);
 	memset(early_pmd, 0, PAGE_SIZE);
 }
@@ -693,10 +798,13 @@ static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
 			   PGDIR_SIZE,
 			   IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);
 
-	if (pgtable_l4_enabled) {
+	if (pgtable_l5_enabled)
+		create_p4d_mapping(early_dtb_p4d, DTB_EARLY_BASE_VA,
+				   (uintptr_t)early_dtb_pud, P4D_SIZE, PAGE_TABLE);
+
+	if (pgtable_l4_enabled)
 		create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA,
 				   (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE);
-	}
 
 	if (IS_ENABLED(CONFIG_64BIT)) {
 		create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
@@ -732,6 +840,8 @@ void __init pt_ops_set_early(void)
 	pt_ops.get_pmd_virt = get_pmd_virt_early;
 	pt_ops.alloc_pud = alloc_pud_early;
 	pt_ops.get_pud_virt = get_pud_virt_early;
+	pt_ops.alloc_p4d = alloc_p4d_early;
+	pt_ops.get_p4d_virt = get_p4d_virt_early;
 #endif
 }
 
@@ -752,6 +862,8 @@ void __init pt_ops_set_fixmap(void)
 	pt_ops.get_pmd_virt = kernel_mapping_pa_to_va((uintptr_t)get_pmd_virt_fixmap);
 	pt_ops.alloc_pud = kernel_mapping_pa_to_va((uintptr_t)alloc_pud_fixmap);
 	pt_ops.get_pud_virt = kernel_mapping_pa_to_va((uintptr_t)get_pud_virt_fixmap);
+	pt_ops.alloc_p4d = kernel_mapping_pa_to_va((uintptr_t)alloc_p4d_fixmap);
+	pt_ops.get_p4d_virt = kernel_mapping_pa_to_va((uintptr_t)get_p4d_virt_fixmap);
 #endif
 }
 
@@ -768,6 +880,8 @@ void __init pt_ops_set_late(void)
 	pt_ops.get_pmd_virt = get_pmd_virt_late;
 	pt_ops.alloc_pud = alloc_pud_late;
 	pt_ops.get_pud_virt = get_pud_virt_late;
+	pt_ops.alloc_p4d = alloc_p4d_late;
+	pt_ops.get_p4d_virt = get_p4d_virt_late;
 #endif
 }
 
@@ -828,6 +942,10 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 			   fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
 
 #ifndef __PAGETABLE_PMD_FOLDED
+	/* Setup fixmap P4D and PUD */
+	if (pgtable_l5_enabled)
+		create_p4d_mapping(fixmap_p4d, FIXADDR_START,
+				   (uintptr_t)fixmap_pud, P4D_SIZE, PAGE_TABLE);
 	/* Setup fixmap PUD and PMD */
 	if (pgtable_l4_enabled)
 		create_pud_mapping(fixmap_pud, FIXADDR_START,
@@ -837,6 +955,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	/* Setup trampoline PGD and PMD */
 	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
 			   trampoline_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+	if (pgtable_l5_enabled)
+		create_p4d_mapping(trampoline_p4d, kernel_map.virt_addr,
+				   (uintptr_t)trampoline_pud, P4D_SIZE, PAGE_TABLE);
 	if (pgtable_l4_enabled)
 		create_pud_mapping(trampoline_pud, kernel_map.virt_addr,
 				   (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE);
@@ -938,6 +1059,7 @@ static void __init setup_vm_final(void)
 	clear_fixmap(FIX_PTE);
 	clear_fixmap(FIX_PMD);
 	clear_fixmap(FIX_PUD);
+	clear_fixmap(FIX_P4D);
 
 	/* Move to swapper page table */
 	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | satp_mode);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index cd1a145257b7..a22e418dbd82 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -111,6 +111,8 @@ static void __init kasan_populate_pud(pgd_t *pgd,
 		 * pt_ops facility.
 		 */
 		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
+	} else if (pgd_none(*pgd)) {
+		base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
 	} else {
 		base_pud = (pud_t *)pgd_page_vaddr(*pgd);
 		if (base_pud == lm_alias(kasan_early_shadow_pud)) {
@@ -152,13 +154,72 @@ static void __init kasan_populate_pud(pgd_t *pgd,
 		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
 }
 
-#define kasan_early_shadow_pgd_next			(pgtable_l4_enabled ?	\
+static void __init kasan_populate_p4d(pgd_t *pgd,
+				      unsigned long vaddr, unsigned long end,
+				      bool early)
+{
+	phys_addr_t phys_addr;
+	p4d_t *p4dp, *base_p4d;
+	unsigned long next;
+
+	if (early) {
+		/*
+		 * We can't use pgd_page_vaddr here as it would return a linear
+		 * mapping address but it is not mapped yet, but when populating
+		 * early_pg_dir, we need the physical address and when populating
+		 * swapper_pg_dir, we need the kernel virtual address so use
+		 * pt_ops facility.
+		 */
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd)));
+	} else {
+		base_p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+		if (base_p4d == lm_alias(kasan_early_shadow_p4d))
+			base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE);
+	}
+
+	p4dp = base_p4d + p4d_index(vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
+			if (early) {
+				phys_addr = __pa(((uintptr_t)kasan_early_shadow_pud));
+				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
+				continue;
+			} else {
+				phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
+				if (phys_addr) {
+					set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
+					continue;
+				}
+			}
+		}
+
+		kasan_populate_pud((pgd_t *)p4dp, vaddr, next, early);
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	/*
+	 * Wait for the whole P4D to be populated before setting the P4D in
+	 * the page table, otherwise, if we did set the P4D before populating
+	 * it entirely, memblock could allocate a page at a physical address
+	 * where KASAN is not populated yet and then we'd get a page fault.
+	 */
+	if (!early)
+		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_p4d)), PAGE_TABLE));
+}
+
+#define kasan_early_shadow_pgd_next			(pgtable_l5_enabled ?	\
+				(uintptr_t)kasan_early_shadow_p4d :		\
+							(pgtable_l4_enabled ?	\
 				(uintptr_t)kasan_early_shadow_pud :		\
-				(uintptr_t)kasan_early_shadow_pmd)
+				(uintptr_t)kasan_early_shadow_pmd))
 #define kasan_populate_pgd_next(pgdp, vaddr, next, early)			\
+		(pgtable_l5_enabled ?						\
+		kasan_populate_p4d(pgdp, vaddr, next, early) :			\
 		(pgtable_l4_enabled ?						\
 			kasan_populate_pud(pgdp, vaddr, next, early) :		\
-			kasan_populate_pmd((pud_t *)pgdp, vaddr, next))
+			kasan_populate_pmd((pud_t *)pgdp, vaddr, next)))
 
 static void __init kasan_populate_pgd(pgd_t *pgdp,
 				      unsigned long vaddr, unsigned long end,
@@ -221,6 +282,14 @@ asmlinkage void __init kasan_early_init(void)
 					PAGE_TABLE));
 	}
 
+	if (pgtable_l5_enabled) {
+		for (i = 0; i < PTRS_PER_P4D; ++i)
+			set_p4d(kasan_early_shadow_p4d + i,
+				pfn_p4d(PFN_DOWN
+					(__pa(((uintptr_t)kasan_early_shadow_pud))),
+					PAGE_TABLE));
+	}
+
 	kasan_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
 			   KASAN_SHADOW_START, KASAN_SHADOW_END, true);
 
@@ -246,9 +315,27 @@ static void __init kasan_populate(void *start, void *end)
 	memset(start, KASAN_SHADOW_INIT, end - start);
 }
 
+static void __init kasan_shallow_populate_pmd(pgd_t *pgdp,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	pmd_t *pmdp, *base_pmd;
+	bool is_kasan_pte;
+
+	base_pmd = (pmd_t *)pgd_page_vaddr(*pgdp);
+	pmdp = base_pmd + pmd_index(vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+		is_kasan_pte = (pmd_pgtable(*pmdp) == lm_alias(kasan_early_shadow_pte));
+
+		if (is_kasan_pte)
+			pmd_clear(pmdp);
+	} while (pmdp++, vaddr = next, vaddr != end);
+}
+
 static void __init kasan_shallow_populate_pud(pgd_t *pgdp,
-					      unsigned long vaddr, unsigned long end,
-					      bool kasan_populate)
+					      unsigned long vaddr, unsigned long end)
 {
 	unsigned long next;
 	pud_t *pudp, *base_pud;
@@ -258,21 +345,60 @@ static void __init kasan_shallow_populate_pud(pgd_t *pgdp,
 	base_pud = (pud_t *)pgd_page_vaddr(*pgdp);
 	pudp = base_pud + pud_index(vaddr);
 
-	if (kasan_populate)
-		memcpy(base_pud, (void *)kasan_early_shadow_pgd_next,
-		       sizeof(pud_t) * PTRS_PER_PUD);
-
 	do {
 		next = pud_addr_end(vaddr, end);
 		is_kasan_pmd = (pud_pgtable(*pudp) == lm_alias(kasan_early_shadow_pmd));
 
-		if (is_kasan_pmd) {
-			base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-			set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
-		}
+		if (!is_kasan_pmd)
+			continue;
+
+		base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+
+		if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE)
+			continue;
+
+		memcpy(base_pmd, (void *)kasan_early_shadow_pmd, PAGE_SIZE);
+		kasan_shallow_populate_pmd((pgd_t *)pudp, vaddr, next);
 	} while (pudp++, vaddr = next, vaddr != end);
 }
 
+static void __init kasan_shallow_populate_p4d(pgd_t *pgdp,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	p4d_t *p4dp, *base_p4d;
+	pud_t *base_pud;
+	bool is_kasan_pud;
+
+	base_p4d = (p4d_t *)pgd_page_vaddr(*pgdp);
+	p4dp = base_p4d + p4d_index(vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+		is_kasan_pud = (p4d_pgtable(*p4dp) == lm_alias(kasan_early_shadow_pud));
+
+		if (!is_kasan_pud)
+			continue;
+
+		base_pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		set_p4d(p4dp, pfn_p4d(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
+
+		if (IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE)
+			continue;
+
+		memcpy(base_pud, (void *)kasan_early_shadow_pud, PAGE_SIZE);
+		kasan_shallow_populate_pud((pgd_t *)p4dp, vaddr, next);
+	} while (p4dp++, vaddr = next, vaddr != end);
+}
+
+#define kasan_shallow_populate_pgd_next(pgdp, vaddr, next)			\
+		(pgtable_l5_enabled ?						\
+		kasan_shallow_populate_p4d(pgdp, vaddr, next) :			\
+		(pgtable_l4_enabled ?						\
+		kasan_shallow_populate_pud(pgdp, vaddr, next) :			\
+		kasan_shallow_populate_pmd(pgdp, vaddr, next)))
+
 static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end)
 {
 	unsigned long next;
@@ -293,7 +419,8 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long
 		if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE)
 			continue;
 
-		kasan_shallow_populate_pud(pgd_k, vaddr, next, is_kasan_pgd_next);
+		memcpy(p, (void *)kasan_early_shadow_pgd_next, PAGE_SIZE);
+		kasan_shallow_populate_pgd_next(pgd_k, vaddr, next);
 	} while (pgd_k++, vaddr = next, vaddr != end);
 }