Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 218 insertions, 87 deletions

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 3a4dfc8bab..2c869f8026 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -13,10 +13,9 @@ endif
 KCOV_INSTRUMENT_init.o := n
 
 obj-y += init.o
-obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o
 obj-y += cacheflush.o
 obj-y += context.o
-obj-y += pgtable.o
 obj-y += pmem.o
 
 ifeq ($(CONFIG_MMU),y)
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index 4e4e469b8d..843107f834 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
 		   TAINT_CPU_OUT_OF_SPEC,
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
index 35484d830f..dd1530af3e 100644
--- a/arch/riscv/mm/extable.c
+++ b/arch/riscv/mm/extable.c
@@ -27,6 +27,14 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex,
 	return true;
 }
 
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+	if (unlikely(!offset || offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
 static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
 				unsigned long val)
 {
@@ -50,6 +58,27 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
 	return true;
 }
 
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+				  struct pt_regs *regs)
+{
+	int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+	int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+	unsigned long data, addr, offset;
+
+	addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+	offset = addr & 0x7UL;
+	addr &= ~0x7UL;
+
+	data = *(unsigned long *)addr >> (offset * 8);
+
+	regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
 bool fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *ex;
@@ -65,6 +94,8 @@ bool fixup_exception(struct pt_regs *regs)
 		return ex_handler_bpf(ex, regs);
 	case EX_TYPE_UACCESS_ERR_ZERO:
 		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+		return ex_handler_load_unaligned_zeropad(ex, regs);
 	}
 
 	BUG();
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 081339ddf4..3ba1d4dde5 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -136,24 +136,24 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (!pgd_present(*pgd_k)) {
+	if (!pgd_present(pgdp_get(pgd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	set_pgd(pgd, *pgd_k);
+	set_pgd(pgd, pgdp_get(pgd_k));
 
 	p4d_k = p4d_offset(pgd_k, addr);
-	if (!p4d_present(*p4d_k)) {
+	if (!p4d_present(p4dp_get(p4d_k))) {
 		no_context(regs, addr);
 		return;
 	}
 
 	pud_k = pud_offset(p4d_k, addr);
-	if (!pud_present(*pud_k)) {
+	if (!pud_present(pudp_get(pud_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pud_leaf(*pud_k))
+	if (pud_leaf(pudp_get(pud_k)))
 		goto flush_tlb;
 
 	/*
@@ -161,11 +161,11 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * to copy individual PTEs
 	 */
 	pmd_k = pmd_offset(pud_k, addr);
-	if (!pmd_present(*pmd_k)) {
+	if (!pmd_present(pmdp_get(pmd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pmd_leaf(*pmd_k))
+	if (pmd_leaf(pmdp_get(pmd_k)))
 		goto flush_tlb;
 
 	/*
@@ -175,7 +175,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * silently loop forever.
 	 */
 	pte_k = pte_offset_kernel(pmd_k, addr);
-	if (!pte_present(*pte_k)) {
+	if (!pte_present(ptep_get(pte_k))) {
 		no_context(regs, addr);
 		return;
 	}
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index fbe9188016..5ef2a68911 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	}
 
 	if (sz == PMD_SIZE) {
-		if (want_pmd_share(vma, addr) && pud_none(*pud))
+		if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud)))
 			pte = huge_pmd_share(mm, vma, addr, pud);
 		else
 			pte = (pte_t *)pmd_alloc(mm, pud, addr);
@@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return NULL;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
@@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pud huge, non-present or none */
 		return (pte_t *)pud;
 
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
@@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pmd huge, non-present or none */
 		return (pte_t *)pmd;
 
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return NULL;
 
 	for_each_napot_order(order) {
@@ -351,7 +351,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
 	if (!pte_napot(pte)) {
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index ee224fe18d..0c00efc756 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -232,7 +232,7 @@ static void __init setup_bootmem(void)
 	 * 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))
+	if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU))
 		kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
 
 	/*
@@ -1395,10 +1395,29 @@ void __init misc_mem_init(void)
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+			       unsigned long addr, unsigned long next)
+{
+	pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL);
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+				unsigned long addr, unsigned long next)
+{
+	vmemmap_verify((pte_t *)pmdp, node, addr, next);
+	return 1;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node, NULL);
+	/*
+	 * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we
+	 * can't use hugepage mappings for 2-level page table because in case of
+	 * memory hotplug, we are not able to update all the page tables with
+	 * the new PMDs.
+	 */
+	return vmemmap_populate_hugepages(start, end, node, NULL);
 }
 #endif
 
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 5e39dcf23f..c301c8d291 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -31,7 +31,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	phys_addr_t phys_addr;
 	pte_t *ptep, *p;
 
-	if (pmd_none(*pmd)) {
+	if (pmd_none(pmdp_get(pmd))) {
 		p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
 		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -39,7 +39,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	ptep = pte_offset_kernel(pmd, vaddr);
 
 	do {
-		if (pte_none(*ptep)) {
+		if (pte_none(ptep_get(ptep))) {
 			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
 			memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE);
@@ -53,7 +53,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	pmd_t *pmdp, *p;
 	unsigned long next;
 
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
 		set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -63,7 +63,8 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	do {
 		next = pmd_addr_end(vaddr, end);
 
-		if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) {
+		if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) &&
+		    (next - vaddr) >= PMD_SIZE) {
 			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
 			if (phys_addr) {
 				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -83,7 +84,7 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	pud_t *pudp, *p;
 	unsigned long next;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
 		set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -93,7 +94,8 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
 			if (phys_addr) {
 				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -113,7 +115,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	p4d_t *p4dp, *p;
 	unsigned long next;
 
-	if (pgd_none(*pgd)) {
+	if (pgd_none(pgdp_get(pgd))) {
 		p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
 		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -123,7 +125,8 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
 			if (phys_addr) {
 				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -145,7 +148,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
 			if (phys_addr) {
@@ -168,7 +171,7 @@ static void __init kasan_early_clear_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
@@ -193,7 +196,7 @@ static void __init kasan_early_clear_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
@@ -239,14 +242,14 @@ static void __init kasan_early_populate_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
 		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd);
 			set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -277,14 +280,14 @@ static void __init kasan_early_populate_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
 		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pud);
 			set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -305,7 +308,7 @@ static void __init kasan_early_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d);
 			set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -381,7 +384,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pud_k)) {
+		if (pud_none(pudp_get(pud_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -401,7 +404,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4d_k)) {
+		if (p4d_none(p4dp_get(p4d_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -420,7 +423,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgd_k)) {
+		if (pgd_none(pgdp_get(pgd_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -438,6 +441,14 @@ static void __init kasan_shallow_populate(void *start, void *end)
 	kasan_shallow_populate_pgd(vaddr, vend);
 }
 
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+	kasan_populate(kasan_mem_to_shadow(start),
+		       kasan_mem_to_shadow(start + size));
+}
+#endif
+
 static void __init create_tmp_mapping(void)
 {
 	void *ptr;
@@ -451,7 +462,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last p4d since it is shared with the kernel mapping. */
 	if (pgtable_l5_enabled) {
-		ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+		ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END)));
 		memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D);
 		set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)],
 			pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE));
@@ -462,7 +473,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last pud since it is shared with the kernel mapping. */
 	if (pgtable_l4_enabled) {
-		ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END)));
+		ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END)));
 		memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD);
 		set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)],
 			pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE));
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 01398fee5c..410056a50a 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -29,7 +29,7 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	p4d_t val = READ_ONCE(*p4d);
+	p4d_t val = p4dp_get(p4d);
 
 	if (p4d_leaf(val)) {
 		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
@@ -42,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pud_t val = READ_ONCE(*pud);
+	pud_t val = pudp_get(pud);
 
 	if (pud_leaf(val)) {
 		val = __pud(set_pageattr_masks(pud_val(val), walk));
@@ -55,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pmd_t val = READ_ONCE(*pmd);
+	pmd_t val = pmdp_get(pmd);
 
 	if (pmd_leaf(val)) {
 		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
@@ -68,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pte_t val = READ_ONCE(*pte);
+	pte_t val = ptep_get(pte);
 
 	val = __pte(set_pageattr_masks(pte_val(val), walk));
 	set_pte(pte, val);
@@ -108,10 +108,10 @@ static int __split_linear_mapping_pmd(pud_t *pudp,
 		    vaddr <= (vaddr & PMD_MASK) && end >= next)
 			continue;
 
-		if (pmd_leaf(*pmdp)) {
+		if (pmd_leaf(pmdp_get(pmdp))) {
 			struct page *pte_page;
-			unsigned long pfn = _pmd_pfn(*pmdp);
-			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pmd_pfn(pmdp_get(pmdp));
+			pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK);
 			pte_t *ptep_new;
 			int i;
 
@@ -148,10 +148,10 @@ static int __split_linear_mapping_pud(p4d_t *p4dp,
 		    vaddr <= (vaddr & PUD_MASK) && end >= next)
 			continue;
 
-		if (pud_leaf(*pudp)) {
+		if (pud_leaf(pudp_get(pudp))) {
 			struct page *pmd_page;
-			unsigned long pfn = _pud_pfn(*pudp);
-			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pud_pfn(pudp_get(pudp));
+			pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK);
 			pmd_t *pmdp_new;
 			int i;
 
@@ -197,10 +197,10 @@ static int __split_linear_mapping_p4d(pgd_t *pgdp,
 		    vaddr <= (vaddr & P4D_MASK) && end >= next)
 			continue;
 
-		if (p4d_leaf(*p4dp)) {
+		if (p4d_leaf(p4dp_get(p4dp))) {
 			struct page *pud_page;
-			unsigned long pfn = _p4d_pfn(*p4dp);
-			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _p4d_pfn(p4dp_get(p4dp));
+			pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK);
 			pud_t *pudp_new;
 			int i;
 
@@ -411,29 +411,29 @@ bool kernel_page_present(struct page *page)
 	pte_t *pte;
 
 	pgd = pgd_offset_k(addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return false;
-	if (pgd_leaf(*pgd))
+	if (pgd_leaf(pgdp_get(pgd)))
 		return true;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return false;
-	if (p4d_leaf(*p4d))
+	if (p4d_leaf(p4dp_get(p4d)))
 		return true;
 
 	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return false;
-	if (pud_leaf(*pud))
+	if (pud_leaf(pudp_get(pud)))
 		return true;
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return false;
-	if (pmd_leaf(*pmd))
+	if (pmd_leaf(pmdp_get(pmd)))
 		return true;
 
 	pte = pte_offset_kernel(pmd, addr);
-	return pte_present(*pte);
+	return pte_present(ptep_get(pte));
 }
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index fef4e7328e..ef887efcb6 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -5,6 +5,47 @@
 #include <linux/kernel.h>
 #include <linux/pgtable.h>
 
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	if (!pte_same(ptep_get(ptep), entry))
+		__set_pte_at(ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+int ptep_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pte_t *ptep)
+{
+	if (!pte_young(ptep_get(ptep)))
+		return 0;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);
+
+#ifdef CONFIG_64BIT
+pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(p4dp_get(p4d)) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -25,7 +66,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
 
 int pud_clear_huge(pud_t *pud)
 {
-	if (!pud_leaf(READ_ONCE(*pud)))
+	if (!pud_leaf(pudp_get(pud)))
 		return 0;
 	pud_clear(pud);
 	return 1;
@@ -33,7 +74,7 @@ int pud_clear_huge(pud_t *pud)
 
 int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd = pud_pgtable(*pud);
+	pmd_t *pmd = pud_pgtable(pudp_get(pud));
 	int i;
 
 	pud_clear(pud);
@@ -63,7 +104,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
 
 int pmd_clear_huge(pmd_t *pmd)
 {
-	if (!pmd_leaf(READ_ONCE(*pmd)))
+	if (!pmd_leaf(pmdp_get(pmd)))
 		return 0;
 	pmd_clear(pmd);
 	return 1;
@@ -71,7 +112,7 @@ int pmd_clear_huge(pmd_t *pmd)
 
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
-	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd));
 
 	pmd_clear(pmd);
 
@@ -88,7 +129,7 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp)));
 	/*
 	 * When leaf PTE entries (regular pages) are collapsed into a leaf
 	 * PMD entry (huge page), a valid non-leaf PTE is converted into a
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 1f90721d22..07d743f87b 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -99,29 +99,23 @@ static void __ipi_flush_tlb_range_asid(void *info)
 	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
 }
 
-static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
-			      unsigned long size, unsigned long stride)
+static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
+			      unsigned long start, unsigned long size,
+			      unsigned long stride)
 {
 	struct flush_tlb_range_data ftd;
-	const struct cpumask *cmask;
-	unsigned long asid = FLUSH_TLB_NO_ASID;
 	bool broadcast;
 
-	if (mm) {
-		unsigned int cpuid;
+	if (cpumask_empty(cmask))
+		return;
 
-		cmask = mm_cpumask(mm);
-		if (cpumask_empty(cmask))
-			return;
+	if (cmask != cpu_online_mask) {
+		unsigned int cpuid;
 
 		cpuid = get_cpu();
 		/* check if the tlbflush needs to be sent to other CPUs */
 		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-
-		if (static_branch_unlikely(&use_asid_allocator))
-			asid = atomic_long_read(&mm->context.id) & asid_mask;
 	} else {
-		cmask = cpu_online_mask;
 		broadcast = true;
 	}
 
@@ -141,25 +135,34 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 		local_flush_tlb_range_asid(start, size, stride, asid);
 	}
 
-	if (mm)
+	if (cmask != cpu_online_mask)
 		put_cpu();
 }
 
+static inline unsigned long get_mm_asid(struct mm_struct *mm)
+{
+	return static_branch_unlikely(&use_asid_allocator) ?
+			atomic_long_read(&mm->context.id) & asid_mask : FLUSH_TLB_NO_ASID;
+}
+
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_mm_range(struct mm_struct *mm,
 			unsigned long start, unsigned long end,
 			unsigned int page_size)
 {
-	__flush_tlb_range(mm, start, end - start, page_size);
+	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+			  start, end - start, page_size);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  addr, PAGE_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -191,18 +194,45 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		}
 	}
 
-	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  start, end - start, stride_size);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
+	__flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID,
+			  start, end - start, PAGE_SIZE);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  start, end - start, PMD_SIZE);
 }
 #endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+	return true;
+}
+
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+			       struct mm_struct *mm,
+			       unsigned long uaddr)
+{
+	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+}
+
+void arch_flush_tlb_batched_pending(struct mm_struct *mm)
+{
+	flush_tlb_mm(mm);
+}
+
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
+			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	cpumask_clear(&batch->cpumask);
+}