Merge tag 'riscv-for-linus-5.14-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:
 "We have a handful of new features for 5.14:

   - Support for transparent huge pages.

   - Support for generic PCI resources mapping.

   - Support for the mem= kernel parameter.

   - Support for KFENCE.

   - A handful of fixes to avoid W+X mappings in the kernel.

   - Support for VMAP_STACK based overflow detection.

   - An optimized copy_{to,from}_user"

* tag 'riscv-for-linus-5.14-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (37 commits)
  riscv: xip: Fix duplicate included asm/pgtable.h
  riscv: Fix PTDUMP output now BPF region moved back to module region
  riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall
  riscv: add VMAP_STACK overflow detection
  riscv: ptrace: add argn syntax
  riscv: mm: fix build errors caused by mk_pmd()
  riscv: Introduce structure that group all variables regarding kernel mapping
  riscv: Map the kernel with correct permissions the first time
  riscv: Introduce set_kernel_memory helper
  riscv: Enable KFENCE for riscv64
  RISC-V: Use asm-generic for {in,out}{bwlq}
  riscv: add ASID-based tlbflushing methods
  riscv: pass the mm_struct to __sbi_tlb_flush_range
  riscv: Add mem kernel parameter support
  riscv: Simplify xip and !xip kernel address conversion macros
  riscv: Remove CONFIG_PHYS_RAM_BASE_FIXED
  riscv: Only initialize swiotlb when necessary
  riscv: fix typo in init.c
  riscv: Cleanup unused functions
  riscv: mm: Use better bitmap_zalloc()
  ...

37 files changed, 901 insertions, 360 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index c711ccd7047e..8fcceb8eda07 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -65,11 +65,14 @@ config RISCV
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
 	select HAVE_ARCH_KASAN if MMU && 64BIT
 	select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT
+	select HAVE_ARCH_KFENCE if MMU && 64BIT
 	select HAVE_ARCH_KGDB if !XIP_KERNEL
 	select HAVE_ARCH_KGDB_QXFER_PKT
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
+	select HAVE_ARCH_VMAP_STACK if MMU && 64BIT
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_KMEMLEAK
@@ -83,11 +86,14 @@ config RISCV
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL
 	select HAVE_KRETPROBES if !XIP_KERNEL
+	select HAVE_MOVE_PMD
+	select HAVE_MOVE_PUD
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
@@ -488,13 +494,8 @@ config STACKPROTECTOR_PER_TASK
 	def_bool y
 	depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS
 
-config PHYS_RAM_BASE_FIXED
-	bool "Explicitly specified physical RAM address"
-	default n
-
 config PHYS_RAM_BASE
 	hex "Platform Physical RAM address"
-	depends on PHYS_RAM_BASE_FIXED
 	default "0x80000000"
 	help
 	  This is the physical address of RAM in the system. It has to be
@@ -507,7 +508,6 @@ config XIP_KERNEL
 	# This prevents XIP from being enabled by all{yes,mod}config, which
 	# fail to build since XIP doesn't support large kernels.
 	depends on !COMPILE_TEST
-	select PHYS_RAM_BASE_FIXED
 	help
 	  Execute-In-Place allows the kernel to run from non-volatile storage
 	  directly addressable by the CPU, such as NOR flash. This saves RAM
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 2a652b0c987d..ef386fcf3939 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -25,4 +25,7 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
+asmlinkage unsigned long get_overflow_stack(void);
+asmlinkage void handle_bad_stack(struct pt_regs *regs);
+
 #endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index c025a746a148..69605a474270 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -52,19 +52,6 @@
 #define __io_pbw()	__asm__ __volatile__ ("fence iow,o" : : : "memory");
 #define __io_paw()	__asm__ __volatile__ ("fence o,io"  : : : "memory");
 
-#define inb(c)		({ u8  __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
-#define inw(c)		({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
-#define inl(c)		({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
-
-#define outb(v,c)	({ __io_pbw(); writeb_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
-#define outw(v,c)	({ __io_pbw(); writew_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
-#define outl(v,c)	({ __io_pbw(); writel_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
-
-#ifdef CONFIG_64BIT
-#define inq(c)		({ u64 __v; __io_pbr(); __v = readq_cpu((void*)(c)); __io_par(__v); __v; })
-#define outq(v,c)	({ __io_pbw(); writeq_cpu((v),(void*)(c)); __io_paw(); })
-#endif
-
 /*
  * Accesses from a single hart to a single I/O address must be ordered.  This
  * allows us to use the raw read macros, but we still need to fence before and
diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
new file mode 100644
index 000000000000..d887a54042aa
--- /dev/null
+++ b/arch/riscv/include/asm/kfence.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_KFENCE_H
+#define _ASM_RISCV_KFENCE_H
+
+#include <linux/kfence.h>
+#include <linux/pfn.h>
+#include <asm-generic/pgalloc.h>
+#include <asm/pgtable.h>
+
+static inline int split_pmd_page(unsigned long addr)
+{
+	int i;
+	unsigned long pfn = PFN_DOWN(__pa((addr & PMD_MASK)));
+	pmd_t *pmd = pmd_off_k(addr);
+	pte_t *pte = pte_alloc_one_kernel(&init_mm);
+
+	if (!pte)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(pte + i, pfn_pte(pfn + i, PAGE_KERNEL));
+	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(pte)), PAGE_TABLE));
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	return 0;
+}
+
+static inline bool arch_kfence_init_pool(void)
+{
+	int ret;
+	unsigned long addr;
+	pmd_t *pmd;
+
+	for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr);
+	     addr += PAGE_SIZE) {
+		pmd = pmd_off_k(addr);
+
+		if (pmd_leaf(*pmd)) {
+			ret = split_pmd_page(addr);
+			if (ret)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	pte_t *pte = virt_to_kpte(addr);
+
+	if (protect)
+		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+	else
+		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	return true;
+}
+
+#endif /* _ASM_RISCV_KFENCE_H */
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
index 4647d38018f6..9ea9b5ec3113 100644
--- a/arch/riscv/include/asm/kprobes.h
+++ b/arch/riscv/include/asm/kprobes.h
@@ -29,18 +29,11 @@ struct prev_kprobe {
 	unsigned int status;
 };
 
-/* Single step context for kprobe */
-struct kprobe_step_ctx {
-	unsigned long ss_pending;
-	unsigned long match_addr;
-};
-
 /* per-cpu kprobe control block */
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	unsigned long saved_status;
 	struct prev_kprobe prev_kprobe;
-	struct kprobe_step_ctx ss_ctx;
 };
 
 void arch_remove_kprobe(struct kprobe *p);
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index b0659413a080..7030837adc1a 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -33,6 +33,8 @@ static inline int init_new_context(struct task_struct *tsk,
 	return 0;
 }
 
+DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 6a7761c86ec2..cca8764aed83 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -37,16 +37,6 @@
 
 #ifndef __ASSEMBLY__
 
-#define PAGE_UP(addr)	(((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
-#define PAGE_DOWN(addr)	((addr)&(~((PAGE_SIZE)-1)))
-
-/* align addr on a size boundary - adjust address up/down if needed */
-#define _ALIGN_UP(addr, size)	(((addr)+((size)-1))&(~((size)-1)))
-#define _ALIGN_DOWN(addr, size)	((addr)&(~((size)-1)))
-
-/* align addr on a size boundary - adjust address up if needed */
-#define _ALIGN(addr, size)	_ALIGN_UP(addr, size)
-
 #define clear_page(pgaddr)			memset((pgaddr), 0, PAGE_SIZE)
 #define copy_page(to, from)			memcpy((to), (from), PAGE_SIZE)
 
@@ -89,59 +79,68 @@ typedef struct page *pgtable_t;
 #endif
 
 #ifdef CONFIG_MMU
-extern unsigned long va_pa_offset;
-#ifdef CONFIG_64BIT
-extern unsigned long va_kernel_pa_offset;
-#endif
-#ifdef CONFIG_XIP_KERNEL
-extern unsigned long va_kernel_xip_pa_offset;
-#endif
 extern unsigned long pfn_base;
 #define ARCH_PFN_OFFSET		(pfn_base)
 #else
-#define va_pa_offset		0
-#ifdef CONFIG_64BIT
-#define va_kernel_pa_offset	0
-#endif
 #define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
 #endif /* CONFIG_MMU */
 
-extern unsigned long kernel_virt_addr;
-
+struct kernel_mapping {
+	unsigned long virt_addr;
+	uintptr_t phys_addr;
+	uintptr_t size;
+	/* Offset between linear mapping virtual address and kernel load address */
+	unsigned long va_pa_offset;
 #ifdef CONFIG_64BIT
-#define linear_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + va_pa_offset))
+	/* Offset between kernel mapping virtual address and kernel load address */
+	unsigned long va_kernel_pa_offset;
+#endif
+	unsigned long va_kernel_xip_pa_offset;
 #ifdef CONFIG_XIP_KERNEL
+	uintptr_t xiprom;
+	uintptr_t xiprom_sz;
+#endif
+};
+
+extern struct kernel_mapping kernel_map;
+
+#ifdef CONFIG_64BIT
+#define is_kernel_mapping(x)	\
+	((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))
+#define is_linear_mapping(x)	\
+	((x) >= PAGE_OFFSET && (x) < kernel_map.virt_addr)
+
+#define linear_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + kernel_map.va_pa_offset))
 #define kernel_mapping_pa_to_va(y)	({						\
 	unsigned long _y = y;								\
 	(_y >= CONFIG_PHYS_RAM_BASE) ?							\
-		(void *)((unsigned long)(_y) + va_kernel_pa_offset + XIP_OFFSET) :	\
-		(void *)((unsigned long)(_y) + va_kernel_xip_pa_offset);		\
+		(void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET) :	\
+		(void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset);		\
 	})
-#else
-#define kernel_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + va_kernel_pa_offset))
-#endif
 #define __pa_to_va_nodebug(x)		linear_mapping_pa_to_va(x)
 
-#define linear_mapping_va_to_pa(x)	((unsigned long)(x) - va_pa_offset)
-#ifdef CONFIG_XIP_KERNEL
+#define linear_mapping_va_to_pa(x)	((unsigned long)(x) - kernel_map.va_pa_offset)
 #define kernel_mapping_va_to_pa(y) ({						\
 	unsigned long _y = y;							\
-	(_y < kernel_virt_addr + XIP_OFFSET) ?					\
-		((unsigned long)(_y) - va_kernel_xip_pa_offset) :		\
-		((unsigned long)(_y) - va_kernel_pa_offset - XIP_OFFSET);	\
+	(_y < kernel_map.virt_addr + XIP_OFFSET) ?					\
+		((unsigned long)(_y) - kernel_map.va_kernel_xip_pa_offset) :		\
+		((unsigned long)(_y) - kernel_map.va_kernel_pa_offset - XIP_OFFSET);	\
 	})
-#else
-#define kernel_mapping_va_to_pa(x)	((unsigned long)(x) - va_kernel_pa_offset)
-#endif
+
 #define __va_to_pa_nodebug(x)	({						\
 	unsigned long _x = x;							\
-	(_x < kernel_virt_addr) ?						\
+	is_linear_mapping(_x) ?							\
 		linear_mapping_va_to_pa(_x) : kernel_mapping_va_to_pa(_x);	\
 	})
 #else
-#define __pa_to_va_nodebug(x)  ((void *)((unsigned long) (x) + va_pa_offset))
-#define __va_to_pa_nodebug(x)  ((unsigned long)(x) - va_pa_offset)
-#endif
+#define is_kernel_mapping(x)	\
+	((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))
+#define is_linear_mapping(x)	\
+	((x) >= PAGE_OFFSET)
+
+#define __pa_to_va_nodebug(x)  ((void *)((unsigned long) (x) + kernel_map.va_pa_offset))
+#define __va_to_pa_nodebug(x)  ((unsigned long)(x) - kernel_map.va_pa_offset)
+#endif /* CONFIG_64BIT */
 
 #ifdef CONFIG_DEBUG_VIRTUAL
 extern phys_addr_t __virt_to_phys(unsigned long x);
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
index 658e112c3ce7..7fd52a30e605 100644
--- a/arch/riscv/include/asm/pci.h
+++ b/arch/riscv/include/asm/pci.h
@@ -18,6 +18,8 @@
 /* RISC-V shim does not initialize PCI bus */
 #define pcibios_assign_all_busses() 1
 
+#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1
+
 extern int isa_dma_bridge_buggy;
 
 #ifdef CONFIG_PCI
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 0e863f3f7187..228261aa9628 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -46,8 +46,7 @@ static inline int pud_bad(pud_t pud)
 #define pud_leaf	pud_leaf
 static inline int pud_leaf(pud_t pud)
 {
-	return pud_present(pud) &&
-	       (pud_val(pud) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+	return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -80,6 +79,8 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 	return pmd_val(pmd) >> _PAGE_PFN_SHIFT;
 }
 
+#define mk_pmd(page, prot)    pfn_pmd(page_to_pfn(page), prot)
+
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
 
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index bbaeb5d35842..2ee413912926 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -39,5 +39,10 @@
 #define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
 					  _PAGE_WRITE | _PAGE_EXEC |	\
 					  _PAGE_USER | _PAGE_GLOBAL))
+/*
+ * when all of R/W/X are zero, the PTE is a pointer to the next level
+ * of the page table; otherwise, it is a leaf PTE.
+ */
+#define _PAGE_LEAF (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 
 #endif /* _ASM_RISCV_PGTABLE_BITS_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 62f3fe7368f3..39b550310ec6 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -76,6 +76,8 @@
 
 #ifdef CONFIG_XIP_KERNEL
 #define XIP_OFFSET		SZ_8M
+#else
+#define XIP_OFFSET		0
 #endif
 
 #ifndef __ASSEMBLY__
@@ -133,7 +135,8 @@
 				| _PAGE_WRITE \
 				| _PAGE_PRESENT \
 				| _PAGE_ACCESSED \
-				| _PAGE_DIRTY)
+				| _PAGE_DIRTY \
+				| _PAGE_GLOBAL)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
 #define PAGE_KERNEL_READ	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
@@ -171,10 +174,23 @@ extern pgd_t swapper_pg_dir[];
 #define __S110	PAGE_SHARED_EXEC
 #define __S111	PAGE_SHARED_EXEC
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_present(pmd_t pmd)
+{
+	/*
+	 * Checking for _PAGE_LEAF is needed too because:
+	 * When splitting a THP, split_huge_page() will temporarily clear
+	 * the present bit, in this situation, pmd_present() and
+	 * pmd_trans_huge() still needs to return true.
+	 */
+	return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE | _PAGE_LEAF));
+}
+#else
 static inline int pmd_present(pmd_t pmd)
 {
 	return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
 }
+#endif
 
 static inline int pmd_none(pmd_t pmd)
 {
@@ -183,14 +199,13 @@ static inline int pmd_none(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	return !pmd_present(pmd);
+	return !pmd_present(pmd) || (pmd_val(pmd) & _PAGE_LEAF);
 }
 
 #define pmd_leaf	pmd_leaf
 static inline int pmd_leaf(pmd_t pmd)
 {
-	return pmd_present(pmd) &&
-	       (pmd_val(pmd) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+	return pmd_present(pmd) && (pmd_val(pmd) & _PAGE_LEAF);
 }
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
@@ -228,6 +243,11 @@ static inline pte_t pmd_pte(pmd_t pmd)
 	return __pte(pmd_val(pmd));
 }
 
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
 /* Yields the page frame number (PFN) of a page table entry */
 static inline unsigned long pte_pfn(pte_t pte)
 {
@@ -266,8 +286,7 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_huge(pte_t pte)
 {
-	return pte_present(pte)
-		&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+	return pte_present(pte) && (pte_val(pte) & _PAGE_LEAF);
 }
 
 static inline int pte_dirty(pte_t pte)
@@ -370,6 +389,14 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 	local_flush_tlb_page(address);
 }
 
+static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp)
+{
+	pte_t *ptep = (pte_t *)pmdp;
+
+	update_mmu_cache(vma, address, ptep);
+}
+
 #define __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
@@ -464,6 +491,137 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 }
 
 /*
+ * THP functions
+ */
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline pmd_t pmd_mkinvalid(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) & ~(_PAGE_PRESENT|_PAGE_PROT_NONE));
+}
+
+#define __pmd_to_phys(pmd)  (pmd_val(pmd) >> _PAGE_PFN_SHIFT << PAGE_SHIFT)
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	return ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT);
+}
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
+#define pmd_write pmd_write
+static inline int pmd_write(pmd_t pmd)
+{
+	return pte_write(pmd_pte(pmd));
+}
+
+static inline int pmd_dirty(pmd_t pmd)
+{
+	return pte_dirty(pmd_pte(pmd));
+}
+
+static inline int pmd_young(pmd_t pmd)
+{
+	return pte_young(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+	return pte_pmd(pte_mkold(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+	return pte_pmd(pte_mkyoung(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkwrite(pmd_t pmd)
+{
+	return pte_pmd(pte_mkwrite(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_wrprotect(pmd_t pmd)
+{
+	return pte_pmd(pte_wrprotect(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	return pte_pmd(pte_mkclean(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_mkdirty(pmd_t pmd)
+{
+	return pte_pmd(pte_mkdirty(pmd_pte(pmd)));
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+				pmd_t *pmdp, pmd_t pmd)
+{
+	return set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+}
+
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+				pud_t *pudp, pud_t pud)
+{
+	return set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return pmd_leaf(pmd);
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp)
+{
+	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
+}
+
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					unsigned long address, pmd_t *pmdp)
+{
+	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+					unsigned long address, pmd_t *pmdp)
+{
+	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
+}
+
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+				unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd)));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
  * Encode and decode a swap entry
  *
  * Format of swap PTE:
@@ -532,7 +690,6 @@ extern uintptr_t _dtb_early_pa;
 #define dtb_early_pa	_dtb_early_pa
 #endif /* CONFIG_XIP_KERNEL */
 
-void setup_bootmem(void);
 void paging_init(void);
 void misc_mem_init(void);
 
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index 09ad4e923510..6ecd461129d2 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -141,6 +141,37 @@ static inline unsigned long regs_get_register(struct pt_regs *regs,
 
 	return *(unsigned long *)((unsigned long)regs + offset);
 }
+
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:       pt_regs of that context
+ * @n:          function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note you can get the parameter correctly if the function has no
+ * more than eight arguments.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						unsigned int n)
+{
+	static const int nr_reg_arguments = 8;
+	static const unsigned int argument_offs[] = {
+		offsetof(struct pt_regs, a0),
+		offsetof(struct pt_regs, a1),
+		offsetof(struct pt_regs, a2),
+		offsetof(struct pt_regs, a3),
+		offsetof(struct pt_regs, a4),
+		offsetof(struct pt_regs, a5),
+		offsetof(struct pt_regs, a6),
+		offsetof(struct pt_regs, a7),
+	};
+
+	if (n < nr_reg_arguments)
+		return regs_get_register(regs, argument_offs[n]);
+	return 0;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h
index 8a303fb1ee3b..32336e8a17cb 100644
--- a/arch/riscv/include/asm/sections.h
+++ b/arch/riscv/include/asm/sections.h
@@ -6,6 +6,7 @@
 #define __ASM_SECTIONS_H
 
 #include <asm-generic/sections.h>
+#include <linux/mm.h>
 
 extern char _start[];
 extern char _start_kernel[];
@@ -13,4 +14,20 @@ extern char __init_data_begin[], __init_data_end[];
 extern char __init_text_begin[], __init_text_end[];
 extern char __alt_start[], __alt_end[];
 
+static inline bool is_va_kernel_text(uintptr_t va)
+{
+	uintptr_t start = (uintptr_t)_start;
+	uintptr_t end = (uintptr_t)__init_data_begin;
+
+	return va >= start && va < end;
+}
+
+static inline bool is_va_kernel_lm_alias_text(uintptr_t va)
+{
+	uintptr_t start = (uintptr_t)lm_alias(_start);
+	uintptr_t end = (uintptr_t)lm_alias(__init_data_begin);
+
+	return va >= start && va < end;
+}
+
 #endif /* __ASM_SECTIONS_H */
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
index 086f757e8ba3..a2c14d4b3993 100644
--- a/arch/riscv/include/asm/set_memory.h
+++ b/arch/riscv/include/asm/set_memory.h
@@ -16,20 +16,28 @@ int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
 int set_memory_rw_nx(unsigned long addr, int numpages);
-void protect_kernel_text_data(void);
+static __always_inline int set_kernel_memory(char *startp, char *endp,
+					     int (*set_memory)(unsigned long start,
+							       int num_pages))
+{
+	unsigned long start = (unsigned long)startp;
+	unsigned long end = (unsigned long)endp;
+	int num_pages = PAGE_ALIGN(end - start) >> PAGE_SHIFT;
+
+	return set_memory(start, num_pages);
+}
 #else
 static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
-static inline void protect_kernel_text_data(void) {}
 static inline int set_memory_rw_nx(unsigned long addr, int numpages) { return 0; }
-#endif
-
-#if defined(CONFIG_64BIT) && defined(CONFIG_STRICT_KERNEL_RWX)
-void protect_kernel_linear_mapping_text_rodata(void);
-#else
-static inline void protect_kernel_linear_mapping_text_rodata(void) {}
+static inline int set_kernel_memory(char *startp, char *endp,
+				    int (*set_memory)(unsigned long start,
+						      int num_pages))
+{
+	return 0;
+}
 #endif
 
 int set_direct_map_invalid_noflush(struct page *page);
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 407bcc96a710..0a3f4f95c555 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_RISCV_SWITCH_TO_H
 #define _ASM_RISCV_SWITCH_TO_H
 
+#include <linux/jump_label.h>
 #include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
@@ -55,9 +56,13 @@ static inline void __switch_to_aux(struct task_struct *prev,
 	fstate_restore(next, task_pt_regs(next));
 }
 
-extern bool has_fpu;
+extern struct static_key_false cpu_hwcap_fpu;
+static __always_inline bool has_fpu(void)
+{
+	return static_branch_likely(&cpu_hwcap_fpu);
+}
 #else
-#define has_fpu false
+static __always_inline bool has_fpu(void) { return false; }
 #define fstate_save(task, regs) do { } while (0)
 #define fstate_restore(task, regs) do { } while (0)
 #define __switch_to_aux(__prev, __next) do { } while (0)
@@ -70,7 +75,7 @@ extern struct task_struct *__switch_to(struct task_struct *,
 do {							\
 	struct task_struct *__prev = (prev);		\
 	struct task_struct *__next = (next);		\
-	if (has_fpu)					\
+	if (has_fpu())					\
 		__switch_to_aux(__prev, __next);	\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 0e549a3089b3..60da0dcacf14 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -19,6 +19,21 @@
 #endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
+/*
+ * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by
+ * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry
+ * assembly.
+ */
+#ifdef CONFIG_VMAP_STACK
+#define THREAD_ALIGN            (2 * THREAD_SIZE)
+#else
+#define THREAD_ALIGN            THREAD_SIZE
+#endif
+
+#define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
+#define OVERFLOW_STACK_SIZE     SZ_4K
+#define SHADOW_OVERFLOW_STACK_SIZE (1024)
+
 #ifndef __ASSEMBLY__
 
 #include <asm/processor.h>
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index c84218ad7afc..801019381dea 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -33,6 +33,11 @@ void flush_tlb_mm(struct mm_struct *mm);
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			unsigned long end);
+#endif
 #else /* CONFIG_SMP && CONFIG_MMU */
 
 #define flush_tlb_all() local_flush_tlb_all()
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 9ef33346853c..90f8ce64fa6f 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -311,4 +311,6 @@ void asm_offsets(void)
 	 * ensures the alignment is sane.
 	 */
 	DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
+
+	OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr);
 }
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index ac202f44a670..d959d207a40d 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -19,7 +19,7 @@ unsigned long elf_hwcap __read_mostly;
 static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 
 #ifdef CONFIG_FPU
-bool has_fpu __read_mostly;
+__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu);
 #endif
 
 /**
@@ -59,7 +59,7 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
 }
 EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
 
-void riscv_fill_hwcap(void)
+void __init riscv_fill_hwcap(void)
 {
 	struct device_node *node;
 	const char *isa;
@@ -146,6 +146,6 @@ void riscv_fill_hwcap(void)
 
 #ifdef CONFIG_FPU
 	if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))
-		has_fpu = true;
+		static_branch_enable(&cpu_hwcap_fpu);
 #endif
 }
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 80d5a9e017b0..98f502654edd 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -30,6 +30,15 @@ ENTRY(handle_exception)
 _restore_kernel_tpsp:
 	csrr tp, CSR_SCRATCH
 	REG_S sp, TASK_TI_KERNEL_SP(tp)
+
+#ifdef CONFIG_VMAP_STACK
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	srli sp, sp, THREAD_SHIFT
+	andi sp, sp, 0x1
+	bnez sp, handle_kernel_stack_overflow
+	REG_L sp, TASK_TI_KERNEL_SP(tp)
+#endif
+
 _save_context:
 	REG_S sp, TASK_TI_USER_SP(tp)
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
@@ -376,6 +385,105 @@ handle_syscall_trace_exit:
 	call do_syscall_trace_exit
 	j ret_from_exception
 
+#ifdef CONFIG_VMAP_STACK
+handle_kernel_stack_overflow:
+	la sp, shadow_stack
+	addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE
+
+	//save caller register to shadow stack
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	REG_S x1,  PT_RA(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	la ra, restore_caller_reg
+	tail get_overflow_stack
+
+restore_caller_reg:
+	//save per-cpu overflow stack
+	REG_S a0, -8(sp)
+	//restore caller register from shadow_stack
+	REG_L x1,  PT_RA(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	//load per-cpu overflow stack
+	REG_L sp, -8(sp)
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+
+	//save context to overflow stack
+	REG_S x1,  PT_RA(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	REG_L s0, TASK_TI_KERNEL_SP(tp)
+	csrr s1, CSR_STATUS
+	csrr s2, CSR_EPC
+	csrr s3, CSR_TVAL
+	csrr s4, CSR_CAUSE
+	csrr s5, CSR_SCRATCH
+	REG_S s0, PT_SP(sp)
+	REG_S s1, PT_STATUS(sp)
+	REG_S s2, PT_EPC(sp)
+	REG_S s3, PT_BADADDR(sp)
+	REG_S s4, PT_CAUSE(sp)
+	REG_S s5, PT_TP(sp)
+	move a0, sp
+	tail handle_bad_stack
+#endif
+
 END(handle_exception)
 
 ENTRY(ret_from_fork)
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 89cc58ab52b4..fce5184b22c3 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -81,9 +81,9 @@ pe_head_start:
 #ifdef CONFIG_MMU
 relocate:
 	/* Relocate return address */
-	la a1, kernel_virt_addr
+	la a1, kernel_map
 	XIP_FIXUP_OFFSET a1
-	REG_L a1, 0(a1)
+	REG_L a1, KERNEL_MAP_VIRT_ADDR(a1)
 	la a2, _start
 	sub a1, a1, a2
 	add ra, ra, a1
diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S
index 88c3beabe9b4..a80b52a74f58 100644
--- a/arch/riscv/kernel/kexec_relocate.S
+++ b/arch/riscv/kernel/kexec_relocate.S
@@ -20,7 +20,7 @@ SYM_CODE_START(riscv_kexec_relocate)
 	 * s4: Pointer to the destination address for the relocation
 	 * s5: (const) Number of words per page
 	 * s6: (const) 1, used for subtraction
-	 * s7: (const) va_pa_offset, used when switching MMU off
+	 * s7: (const) kernel_map.va_pa_offset, used when switching MMU off
 	 * s8: (const) Physical address of the main loop
 	 * s9: (debug) indirection page counter
 	 * s10: (debug) entry counter
@@ -159,7 +159,7 @@ SYM_CODE_START(riscv_kexec_norelocate)
 	 * s0: (const) Phys address to jump to
 	 * s1: (const) Phys address of the FDT image
 	 * s2: (const) The hartid of the current hart
-	 * s3: (const) va_pa_offset, used when switching MMU off
+	 * s3: (const) kernel_map.va_pa_offset, used when switching MMU off
 	 */
 	mv	s0, a1
 	mv	s1, a2
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index 9e99e1db156b..e6eca271a4d6 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -189,6 +189,6 @@ machine_kexec(struct kimage *image)
 	/* Jump to the relocation code */
 	pr_notice("Bye...\n");
 	kexec_method(first_ind_entry, jump_addr, fdt_addr,
-		     this_hart_id, va_pa_offset);
+		     this_hart_id, kernel_map.va_pa_offset);
 	unreachable();
 }
diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
index 247e33fa5bc7..00088dc6da4b 100644
--- a/arch/riscv/kernel/probes/kprobes.c
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -17,7 +17,7 @@ DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 static void __kprobes
-post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
+post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *);
 
 static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
 {
@@ -43,7 +43,7 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
 		p->ainsn.api.handler((u32)p->opcode,
 					(unsigned long)p->addr, regs);
 
-	post_kprobe_handler(kcb, regs);
+	post_kprobe_handler(p, kcb, regs);
 }
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
@@ -151,21 +151,6 @@ static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
 	regs->status = kcb->saved_status;
 }
 
-static void __kprobes
-set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr, struct kprobe *p)
-{
-	unsigned long offset = GET_INSN_LENGTH(p->opcode);
-
-	kcb->ss_ctx.ss_pending = true;
-	kcb->ss_ctx.match_addr = addr + offset;
-}
-
-static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb)
-{
-	kcb->ss_ctx.ss_pending = false;
-	kcb->ss_ctx.match_addr = 0;
-}
-
 static void __kprobes setup_singlestep(struct kprobe *p,
 				       struct pt_regs *regs,
 				       struct kprobe_ctlblk *kcb, int reenter)
@@ -184,8 +169,6 @@ static void __kprobes setup_singlestep(struct kprobe *p,
 		/* prepare for single stepping */
 		slot = (unsigned long)p->ainsn.api.insn;
 
-		set_ss_context(kcb, slot, p);	/* mark pending ss */
-
 		/* IRQs and single stepping do not mix well. */
 		kprobes_save_local_irqflag(kcb, regs);
 
@@ -221,13 +204,8 @@ static int __kprobes reenter_kprobe(struct kprobe *p,
 }
 
 static void __kprobes
-post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs)
 {
-	struct kprobe *cur = kprobe_running();
-
-	if (!cur)
-		return;
-
 	/* return addr restore if non-branching insn */
 	if (cur->ainsn.api.restore != 0)
 		regs->epc = cur->ainsn.api.restore;
@@ -342,16 +320,16 @@ bool __kprobes
 kprobe_single_step_handler(struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long addr = instruction_pointer(regs);
+	struct kprobe *cur = kprobe_running();
 
-	if ((kcb->ss_ctx.ss_pending)
-	    && (kcb->ss_ctx.match_addr == instruction_pointer(regs))) {
-		clear_ss_context(kcb);	/* clear pending ss */
-
+	if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) &&
+	    ((unsigned long)&cur->ainsn.api.insn[0] + GET_INSN_LENGTH(cur->opcode) == addr)) {
 		kprobes_restore_local_irqflag(kcb, regs);
-
-		post_kprobe_handler(kcb, regs);
+		post_kprobe_handler(cur, kcb, regs);
 		return true;
 	}
+	/* not ours, kprobes should ignore it */
 	return false;
 }
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index f9cd57c9c67d..03ac3aa611f5 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -87,7 +87,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 	unsigned long sp)
 {
 	regs->status = SR_PIE;
-	if (has_fpu) {
+	if (has_fpu()) {
 		regs->status |= SR_FS_INITIAL;
 		/*
 		 * Restore the initial value to the FP register
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 8e318f207ac6..18bd0e4bc36c 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -17,7 +17,6 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/sched/task.h>
-#include <linux/swiotlb.h>
 #include <linux/smp.h>
 #include <linux/efi.h>
 #include <linux/crash_dump.h>
@@ -273,7 +272,6 @@ void __init setup_arch(char **cmdline_p)
 	parse_early_param();
 
 	efi_init();
-	setup_bootmem();
 	paging_init();
 #if IS_ENABLED(CONFIG_BUILTIN_DTB)
 	unflatten_and_copy_device_tree();
@@ -288,15 +286,6 @@ void __init setup_arch(char **cmdline_p)
 	init_resources();
 	sbi_init();
 
-	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
-		protect_kernel_text_data();
-		protect_kernel_linear_mapping_text_rodata();
-	}
-
-#ifdef CONFIG_SWIOTLB
-	swiotlb_init(1);
-#endif
-
 #ifdef CONFIG_KASAN
 	kasan_init();
 #endif
@@ -331,11 +320,10 @@ subsys_initcall(topology_init);
 
 void free_initmem(void)
 {
-	unsigned long init_begin = (unsigned long)__init_begin;
-	unsigned long init_end = (unsigned long)__init_end;
-
 	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
-		set_memory_rw_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT);
+		set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end),
+				  IS_ENABLED(CONFIG_64BIT) ?
+					set_memory_rw : set_memory_rw_nx);
 
 	free_initmem_default(POISON_FREE_INITMEM);
 }
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 65942b3748b4..c2d5ecbe5526 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -90,7 +90,7 @@ static long restore_sigcontext(struct pt_regs *regs,
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs));
 	/* Restore the floating-point state. */
-	if (has_fpu)
+	if (has_fpu())
 		err |= restore_fp_state(regs, &sc->sc_fpregs);
 	return err;
 }
@@ -143,7 +143,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame,
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs));
 	/* Save the floating-point state. */
-	if (has_fpu)
+	if (has_fpu())
 		err |= save_fp_state(regs, &sc->sc_fpregs);
 	return err;
 }
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 7bc88d8aab97..0a98fd0ddfe9 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -203,3 +203,38 @@ int is_valid_bugaddr(unsigned long pc)
 void __init trap_init(void)
 {
 }
+
+#ifdef CONFIG_VMAP_STACK
+static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
+		overflow_stack)__aligned(16);
+/*
+ * shadow stack, handled_ kernel_ stack_ overflow(in kernel/entry.S) is used
+ * to get per-cpu overflow stack(get_overflow_stack).
+ */
+long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)];
+asmlinkage unsigned long get_overflow_stack(void)
+{
+	return (unsigned long)this_cpu_ptr(overflow_stack) +
+		OVERFLOW_STACK_SIZE;
+}
+
+asmlinkage void handle_bad_stack(struct pt_regs *regs)
+{
+	unsigned long tsk_stk = (unsigned long)current->stack;
+	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
+
+	console_verbose();
+
+	pr_emerg("Insufficient stack space to handle exception!\n");
+	pr_emerg("Task stack:     [0x%016lx..0x%016lx]\n",
+			tsk_stk, tsk_stk + THREAD_SIZE);
+	pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n",
+			ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE);
+
+	__show_regs(regs);
+	panic("Kernel stack overflow");
+
+	for (;;)
+		wait_for_interrupt();
+}
+#endif
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
index a3ff09c4c3f9..af776555ded9 100644
--- a/arch/riscv/kernel/vmlinux-xip.lds.S
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -12,7 +12,6 @@
 
 #include <asm/vmlinux.lds.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 891742ff75a7..502d0826ecb1 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -117,7 +117,7 @@ SECTIONS
 	. = ALIGN(SECTION_ALIGN);
 	_data = .;
 
-	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
 	.sdata : {
 		__global_pointer$ = . + 0x800;
 		*(.sdata*)
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index fceaeb18cc64..bceb0629e440 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -19,50 +19,161 @@ ENTRY(__asm_copy_from_user)
 	li t6, SR_SUM
 	csrs CSR_STATUS, t6
 
-	add a3, a1, a2
-	/* Use word-oriented copy only if low-order bits match */
-	andi t0, a0, SZREG-1
-	andi t1, a1, SZREG-1
-	bne t0, t1, 2f
+	/* Save for return value */
+	mv	t5, a2
 
-	addi t0, a1, SZREG-1
-	andi t1, a3, ~(SZREG-1)
-	andi t0, t0, ~(SZREG-1)
 	/*
-	 * a3: terminal address of source region
-	 * t0: lowest XLEN-aligned address in source
-	 * t1: highest XLEN-aligned address in source
+	 * Register allocation for code below:
+	 * a0 - start of uncopied dst
+	 * a1 - start of uncopied src
+	 * a2 - size
+	 * t0 - end of uncopied dst
 	 */
-	bgeu t0, t1, 2f
-	bltu a1, t0, 4f
+	add	t0, a0, a2
+	bgtu	a0, t0, 5f
+
+	/*
+	 * Use byte copy only if too small.
+	 */
+	li	a3, 8*SZREG /* size must be larger than size in word_copy */
+	bltu	a2, a3, .Lbyte_copy_tail
+
+	/*
+	 * Copy first bytes until dst is align to word boundary.
+	 * a0 - start of dst
+	 * t1 - start of aligned dst
+	 */
+	addi	t1, a0, SZREG-1
+	andi	t1, t1, ~(SZREG-1)
+	/* dst is already aligned, skip */
+	beq	a0, t1, .Lskip_first_bytes
 1:
-	fixup REG_L, t2, (a1), 10f
-	fixup REG_S, t2, (a0), 10f
-	addi a1, a1, SZREG
-	addi a0, a0, SZREG
-	bltu a1, t1, 1b
+	/* a5 - one byte for copying data */
+	fixup lb      a5, 0(a1), 10f
+	addi	a1, a1, 1	/* src */
+	fixup sb      a5, 0(a0), 10f
+	addi	a0, a0, 1	/* dst */
+	bltu	a0, t1, 1b	/* t1 - start of aligned dst */
+
+.Lskip_first_bytes:
+	/*
+	 * Now dst is aligned.
+	 * Use shift-copy if src is misaligned.
+	 * Use word-copy if both src and dst are aligned because
+	 * can not use shift-copy which do not require shifting
+	 */
+	/* a1 - start of src */
+	andi	a3, a1, SZREG-1
+	bnez	a3, .Lshift_copy
+
+.Lword_copy:
+        /*
+	 * Both src and dst are aligned, unrolled word copy
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of aligned src
+	 * a3 - a1 & mask:(SZREG-1)
+	 * t0 - end of aligned dst
+	 */
+	addi	t0, t0, -(8*SZREG-1) /* not to over run */
 2:
-	bltu a1, a3, 5f
+	fixup REG_L   a4,        0(a1), 10f
+	fixup REG_L   a5,    SZREG(a1), 10f
+	fixup REG_L   a6,  2*SZREG(a1), 10f
+	fixup REG_L   a7,  3*SZREG(a1), 10f
+	fixup REG_L   t1,  4*SZREG(a1), 10f
+	fixup REG_L   t2,  5*SZREG(a1), 10f
+	fixup REG_L   t3,  6*SZREG(a1), 10f
+	fixup REG_L   t4,  7*SZREG(a1), 10f
+	fixup REG_S   a4,        0(a0), 10f
+	fixup REG_S   a5,    SZREG(a0), 10f
+	fixup REG_S   a6,  2*SZREG(a0), 10f
+	fixup REG_S   a7,  3*SZREG(a0), 10f
+	fixup REG_S   t1,  4*SZREG(a0), 10f
+	fixup REG_S   t2,  5*SZREG(a0), 10f
+	fixup REG_S   t3,  6*SZREG(a0), 10f
+	fixup REG_S   t4,  7*SZREG(a0), 10f
+	addi	a0, a0, 8*SZREG
+	addi	a1, a1, 8*SZREG
+	bltu	a0, t0, 2b
+
+	addi	t0, t0, 8*SZREG-1 /* revert to original value */
+	j	.Lbyte_copy_tail
+
+.Lshift_copy:
+
+	/*
+	 * Word copy with shifting.
+	 * For misaligned copy we still perform aligned word copy, but
+	 * we need to use the value fetched from the previous iteration and
+	 * do some shifts.
+	 * This is safe because reading less than a word size.
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of src
+	 * a3 - a1 & mask:(SZREG-1)
+	 * t0 - end of uncopied dst
+	 * t1 - end of aligned dst
+	 */
+	/* calculating aligned word boundary for dst */
+	andi	t1, t0, ~(SZREG-1)
+	/* Converting unaligned src to aligned arc */
+	andi	a1, a1, ~(SZREG-1)
+
+	/*
+	 * Calculate shifts
+	 * t3 - prev shift
+	 * t4 - current shift
+	 */
+	slli	t3, a3, LGREG
+	li	a5, SZREG*8
+	sub	t4, a5, t3
+
+	/* Load the first word to combine with seceond word */
+	fixup REG_L   a5, 0(a1), 10f
 
 3:
+	/* Main shifting copy
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of aligned src
+	 * t1 - end of aligned dst
+	 */
+
+	/* At least one iteration will be executed */
+	srl	a4, a5, t3
+	fixup REG_L   a5, SZREG(a1), 10f
+	addi	a1, a1, SZREG
+	sll	a2, a5, t4
+	or	a2, a2, a4
+	fixup REG_S   a2, 0(a0), 10f
+	addi	a0, a0, SZREG
+	bltu	a0, t1, 3b
+
+	/* Revert src to original unaligned value  */
+	add	a1, a1, a3
+
+.Lbyte_copy_tail:
+	/*
+	 * Byte copy anything left.
+	 *
+	 * a0 - start of remaining dst
+	 * a1 - start of remaining src
+	 * t0 - end of remaining dst
+	 */
+	bgeu	a0, t0, 5f
+4:
+	fixup lb      a5, 0(a1), 10f
+	addi	a1, a1, 1	/* src */
+	fixup sb      a5, 0(a0), 10f
+	addi	a0, a0, 1	/* dst */
+	bltu	a0, t0, 4b	/* t0 - end of dst */
+
+5:
 	/* Disable access to user memory */
 	csrc CSR_STATUS, t6
-	li a0, 0
+	li	a0, 0
 	ret
-4: /* Edge case: unalignment */
-	fixup lbu, t2, (a1), 10f
-	fixup sb, t2, (a0), 10f
-	addi a1, a1, 1
-	addi a0, a0, 1
-	bltu a1, t0, 4b
-	j 1b
-5: /* Edge case: remainder */
-	fixup lbu, t2, (a1), 10f
-	fixup sb, t2, (a0), 10f
-	addi a1, a1, 1
-	addi a0, a0, 1
-	bltu a1, a3, 5b
-	j 3b
 ENDPROC(__asm_copy_to_user)
 ENDPROC(__asm_copy_from_user)
 EXPORT_SYMBOL(__asm_copy_to_user)
@@ -117,7 +228,7 @@ EXPORT_SYMBOL(__clear_user)
 10:
 	/* Disable access to user memory */
 	csrs CSR_STATUS, t6
-	mv a0, a2
+	mv a0, t5
 	ret
 11:
 	csrs CSR_STATUS, t6
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 68aa312fc352..ee3459cb6750 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -18,7 +18,7 @@
 
 #ifdef CONFIG_MMU
 
-static DEFINE_STATIC_KEY_FALSE(use_asid_allocator);
+DEFINE_STATIC_KEY_FALSE(use_asid_allocator);
 
 static unsigned long asid_bits;
 static unsigned long num_asids;
@@ -213,7 +213,7 @@ static inline void set_mm(struct mm_struct *mm, unsigned int cpu)
 		set_mm_noasid(mm);
 }
 
-static int asids_init(void)
+static int __init asids_init(void)
 {
 	unsigned long old;
 
@@ -243,8 +243,7 @@ static int asids_init(void)
 	if (num_asids > (2 * num_possible_cpus())) {
 		atomic_long_set(&current_version, num_asids);
 
-		context_asid_map = kcalloc(BITS_TO_LONGS(num_asids),
-				   sizeof(*context_asid_map), GFP_KERNEL);
+		context_asid_map = bitmap_zalloc(num_asids, GFP_KERNEL);
 		if (!context_asid_map)
 			panic("Failed to allocate bitmap for %lu ASIDs\n",
 			      num_asids);
@@ -280,11 +279,12 @@ static inline void set_mm(struct mm_struct *mm, unsigned int cpu)
  * cache flush to be performed before execution resumes on each hart.  This
  * actually performs that local instruction cache flush, which implicitly only
  * refers to the current hart.
+ *
+ * The "cpu" argument must be the current local CPU number.
  */
-static inline void flush_icache_deferred(struct mm_struct *mm)
+static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu)
 {
 #ifdef CONFIG_SMP
-	unsigned int cpu = smp_processor_id();
 	cpumask_t *mask = &mm->context.icache_stale_mask;
 
 	if (cpumask_test_cpu(cpu, mask)) {
@@ -320,5 +320,5 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	set_mm(next, cpu);
 
-	flush_icache_deferred(next);
+	flush_icache_deferred(next, cpu);
 }
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 096463cc6fff..aa08dd2f8fae 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/signal.h>
 #include <linux/uaccess.h>
 #include <linux/kprobes.h>
+#include <linux/kfence.h>
 
 #include <asm/ptrace.h>
 #include <asm/tlbflush.h>
@@ -45,7 +46,15 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr)
 	 * Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice.
 	 */
-	msg = (addr < PAGE_SIZE) ? "NULL pointer dereference" : "paging request";
+	if (addr < PAGE_SIZE)
+		msg = "NULL pointer dereference";
+	else {
+		if (kfence_handle_page_fault(addr, regs->cause == EXC_STORE_PAGE_FAULT, regs))
+			return;
+
+		msg = "paging request";
+	}
+
 	die_kernel_fault(msg, addr, regs);
 }
 
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 4c4c92ce0bb8..269fc648ef3d 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -11,6 +11,7 @@
 #include <linux/memblock.h>
 #include <linux/initrd.h>
 #include <linux/swap.h>
+#include <linux/swiotlb.h>
 #include <linux/sizes.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
@@ -29,10 +30,14 @@
 
 #include "../kernel/head.h"
 
-unsigned long kernel_virt_addr = KERNEL_LINK_ADDR;
-EXPORT_SYMBOL(kernel_virt_addr);
+struct kernel_mapping kernel_map __ro_after_init;
+EXPORT_SYMBOL(kernel_map);
 #ifdef CONFIG_XIP_KERNEL
-#define kernel_virt_addr       (*((unsigned long *)XIP_FIXUP(&kernel_virt_addr)))
+#define kernel_map	(*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
+#endif
+
+#ifdef CONFIG_XIP_KERNEL
+extern char _xiprom[], _exiprom[];
 #endif
 
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
@@ -53,7 +58,7 @@ struct pt_alloc_ops {
 #endif
 };
 
-static phys_addr_t dma32_phys_limit __ro_after_init;
+static phys_addr_t dma32_phys_limit __initdata;
 
 static void __init zone_sizes_init(void)
 {
@@ -67,11 +72,6 @@ static void __init zone_sizes_init(void)
 	free_area_init(max_zone_pfns);
 }
 
-static void __init setup_zero_page(void)
-{
-	memset((void *)empty_zero_page, 0, PAGE_SIZE);
-}
-
 #if defined(CONFIG_MMU) && defined(CONFIG_DEBUG_VM)
 static inline void print_mlk(char *name, unsigned long b, unsigned long t)
 {
@@ -113,25 +113,53 @@ void __init mem_init(void)
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
 
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > PFN_DOWN(dma32_phys_limit))
+		swiotlb_init(1);
+	else
+		swiotlb_force = SWIOTLB_NO_FORCE;
+#endif
 	high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
 	memblock_free_all();
 
 	print_vm_layout();
 }
 
-void __init setup_bootmem(void)
+/*
+ * The default maximal physical memory size is -PAGE_OFFSET,
+ * limit the memory size via mem.
+ */
+static phys_addr_t memory_limit = -PAGE_OFFSET;
+
+static int __init early_mem(char *p)
+{
+	u64 size;
+
+	if (!p)
+		return 1;
+
+	size = memparse(p, &p) & PAGE_MASK;
+	memory_limit = min_t(u64, size, memory_limit);
+
+	pr_notice("Memory limited to %lldMB\n", (u64)memory_limit >> 20);
+
+	return 0;
+}
+early_param("mem", early_mem);
+
+static void __init setup_bootmem(void)
 {
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
-	phys_addr_t dram_end = memblock_end_of_DRAM();
 	phys_addr_t max_mapped_addr = __pa(~(ulong)0);
+	phys_addr_t dram_end;
 
 #ifdef CONFIG_XIP_KERNEL
 	vmlinux_start = __pa_symbol(&_sdata);
 #endif
 
-	/* The maximal physical memory size is -PAGE_OFFSET. */
-	memblock_enforce_memory_limit(-PAGE_OFFSET);
+	memblock_enforce_memory_limit(memory_limit);
 
 	/*
 	 * Reserve from the start of the kernel to the end of the kernel
@@ -146,6 +174,7 @@ void __init setup_bootmem(void)
 #endif
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
+	dram_end = memblock_end_of_DRAM();
 	/*
 	 * 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
@@ -176,15 +205,8 @@ void __init setup_bootmem(void)
 	memblock_allow_resize();
 }
 
-#ifdef CONFIG_XIP_KERNEL
-
-extern char _xiprom[], _exiprom[];
-extern char _sdata[], _edata[];
-
-#endif /* CONFIG_XIP_KERNEL */
-
 #ifdef CONFIG_MMU
-static struct pt_alloc_ops _pt_ops __ro_after_init;
+static struct pt_alloc_ops _pt_ops __initdata;
 
 #ifdef CONFIG_XIP_KERNEL
 #define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&_pt_ops))
@@ -192,31 +214,12 @@ static struct pt_alloc_ops _pt_ops __ro_after_init;
 #define pt_ops _pt_ops
 #endif
 
-/* Offset between linear mapping virtual address and kernel load address */
-unsigned long va_pa_offset __ro_after_init;
-EXPORT_SYMBOL(va_pa_offset);
-#ifdef CONFIG_XIP_KERNEL
-#define va_pa_offset   (*((unsigned long *)XIP_FIXUP(&va_pa_offset)))
-#endif
-/* Offset between kernel mapping virtual address and kernel load address */
-#ifdef CONFIG_64BIT
-unsigned long va_kernel_pa_offset;
-EXPORT_SYMBOL(va_kernel_pa_offset);
-#endif
-#ifdef CONFIG_XIP_KERNEL
-#define va_kernel_pa_offset    (*((unsigned long *)XIP_FIXUP(&va_kernel_pa_offset)))
-#endif
-unsigned long va_kernel_xip_pa_offset;
-EXPORT_SYMBOL(va_kernel_xip_pa_offset);
-#ifdef CONFIG_XIP_KERNEL
-#define va_kernel_xip_pa_offset        (*((unsigned long *)XIP_FIXUP(&va_kernel_xip_pa_offset)))
-#endif
 unsigned long pfn_base __ro_after_init;
 EXPORT_SYMBOL(pfn_base);
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
-pte_t fixmap_pte[PTRS_PER_PTE] __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);
 
@@ -253,7 +256,7 @@ static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa)
 	return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
 }
 
-static inline pte_t *get_pte_virt_late(phys_addr_t pa)
+static inline pte_t *__init get_pte_virt_late(phys_addr_t pa)
 {
 	return (pte_t *) __va(pa);
 }
@@ -272,7 +275,7 @@ static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va)
 	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
 }
 
-static phys_addr_t alloc_pte_late(uintptr_t va)
+static phys_addr_t __init alloc_pte_late(uintptr_t va)
 {
 	unsigned long vaddr;
 
@@ -296,10 +299,10 @@ static void __init create_pte_mapping(pte_t *ptep,
 
 #ifndef __PAGETABLE_PMD_FOLDED
 
-pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss;
-pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
-pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
-pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
+static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
+static pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
 #ifdef CONFIG_XIP_KERNEL
 #define trampoline_pmd ((pmd_t *)XIP_FIXUP(trampoline_pmd))
@@ -319,14 +322,14 @@ static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa)
 	return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
 }
 
-static pmd_t *get_pmd_virt_late(phys_addr_t pa)
+static pmd_t *__init get_pmd_virt_late(phys_addr_t pa)
 {
 	return (pmd_t *) __va(pa);
 }
 
 static phys_addr_t __init alloc_pmd_early(uintptr_t va)
 {
-	BUG_ON((va - kernel_virt_addr) >> PGDIR_SHIFT);
+	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
 
 	return (uintptr_t)early_pmd;
 }
@@ -336,7 +339,7 @@ static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va)
 	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
 }
 
-static phys_addr_t alloc_pmd_late(uintptr_t va)
+static phys_addr_t __init alloc_pmd_late(uintptr_t va)
 {
 	unsigned long vaddr;
 
@@ -436,6 +439,43 @@ asmlinkage void __init __copy_data(void)
 }
 #endif
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+static __init pgprot_t pgprot_from_va(uintptr_t va)
+{
+	if (is_va_kernel_text(va))
+		return PAGE_KERNEL_READ_EXEC;
+
+	/*
+	 * In 64-bit kernel, the kernel mapping is outside the linear mapping so
+	 * we must protect its linear mapping alias from being executed and
+	 * written.
+	 * And rodata section is marked readonly in mark_rodata_ro.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT) && is_va_kernel_lm_alias_text(va))
+		return PAGE_KERNEL_READ;
+
+	return PAGE_KERNEL;
+}
+
+void mark_rodata_ro(void)
+{
+	set_kernel_memory(__start_rodata, _data, set_memory_ro);
+	if (IS_ENABLED(CONFIG_64BIT))
+		set_kernel_memory(lm_alias(__start_rodata), lm_alias(_data),
+				  set_memory_ro);
+
+	debug_checkwx();
+}
+#else
+static __init pgprot_t pgprot_from_va(uintptr_t va)
+{
+	if (IS_ENABLED(CONFIG_64BIT) && !is_kernel_mapping(va))
+		return PAGE_KERNEL;
+
+	return PAGE_KERNEL_EXEC;
+}
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+
 /*
  * setup_vm() is called from head.S with MMU-off.
  *
@@ -454,45 +494,39 @@ asmlinkage void __init __copy_data(void)
 #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
 #endif
 
-uintptr_t load_pa, load_sz;
 #ifdef CONFIG_XIP_KERNEL
-#define load_pa        (*((uintptr_t *)XIP_FIXUP(&load_pa)))
-#define load_sz        (*((uintptr_t *)XIP_FIXUP(&load_sz)))
-#endif
-
-#ifdef CONFIG_XIP_KERNEL
-uintptr_t xiprom, xiprom_sz;
-#define xiprom_sz      (*((uintptr_t *)XIP_FIXUP(&xiprom_sz)))
-#define xiprom         (*((uintptr_t *)XIP_FIXUP(&xiprom)))
-
-static void __init create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size)
+static void __init create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size,
+					    __always_unused bool early)
 {
 	uintptr_t va, end_va;
 
 	/* Map the flash resident part */
-	end_va = kernel_virt_addr + xiprom_sz;
-	for (va = kernel_virt_addr; va < end_va; va += map_size)
+	end_va = kernel_map.virt_addr + kernel_map.xiprom_sz;
+	for (va = kernel_map.virt_addr; va < end_va; va += map_size)
 		create_pgd_mapping(pgdir, va,
-				   xiprom + (va - kernel_virt_addr),
+				   kernel_map.xiprom + (va - kernel_map.virt_addr),
 				   map_size, PAGE_KERNEL_EXEC);
 
 	/* Map the data in RAM */
-	end_va = kernel_virt_addr + XIP_OFFSET + load_sz;
-	for (va = kernel_virt_addr + XIP_OFFSET; va < end_va; va += map_size)
+	end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
+	for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += map_size)
 		create_pgd_mapping(pgdir, va,
-				   load_pa + (va - (kernel_virt_addr + XIP_OFFSET)),
+				   kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
 				   map_size, PAGE_KERNEL);
 }
 #else
-static void __init create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size)
+static void __init create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size,
+					    bool early)
 {
 	uintptr_t va, end_va;
 
-	end_va = kernel_virt_addr + load_sz;
-	for (va = kernel_virt_addr; va < end_va; va += map_size)
+	end_va = kernel_map.virt_addr + kernel_map.size;
+	for (va = kernel_map.virt_addr; va < end_va; va += map_size)
 		create_pgd_mapping(pgdir, va,
-				   load_pa + (va - kernel_virt_addr),
-				   map_size, PAGE_KERNEL_EXEC);
+				   kernel_map.phys_addr + (va - kernel_map.virt_addr),
+				   map_size,
+				   early ?
+					PAGE_KERNEL_EXEC : pgprot_from_va(va));
 }
 #endif
 
@@ -504,25 +538,27 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	pmd_t fix_bmap_spmd, fix_bmap_epmd;
 #endif
 
+	kernel_map.virt_addr = KERNEL_LINK_ADDR;
+
 #ifdef CONFIG_XIP_KERNEL
-	xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
-	xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
+	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
+	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
-	load_pa = (uintptr_t)CONFIG_PHYS_RAM_BASE;
-	load_sz = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
+	kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
+	kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
 
-	va_kernel_xip_pa_offset = kernel_virt_addr - xiprom;
+	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
 #else
-	load_pa = (uintptr_t)(&_start);
-	load_sz = (uintptr_t)(&_end) - load_pa;
+	kernel_map.phys_addr = (uintptr_t)(&_start);
+	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
 #endif
 
-	va_pa_offset = PAGE_OFFSET - load_pa;
+	kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
 #ifdef CONFIG_64BIT
-	va_kernel_pa_offset = kernel_virt_addr - load_pa;
+	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
 #endif
 
-	pfn_base = PFN_DOWN(load_pa);
+	pfn_base = PFN_DOWN(kernel_map.phys_addr);
 
 	/*
 	 * Enforce boot alignment requirements of RV32 and
@@ -532,7 +568,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	/* Sanity check alignment and size */
 	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
-	BUG_ON((load_pa % map_size) != 0);
+	BUG_ON((kernel_map.phys_addr % map_size) != 0);
 
 	pt_ops.alloc_pte = alloc_pte_early;
 	pt_ops.get_pte_virt = get_pte_virt_early;
@@ -549,19 +585,19 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	create_pmd_mapping(fixmap_pmd, FIXADDR_START,
 			   (uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE);
 	/* Setup trampoline PGD and PMD */
-	create_pgd_mapping(trampoline_pg_dir, kernel_virt_addr,
+	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
 			   (uintptr_t)trampoline_pmd, PGDIR_SIZE, PAGE_TABLE);
 #ifdef CONFIG_XIP_KERNEL
-	create_pmd_mapping(trampoline_pmd, kernel_virt_addr,
-			   xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
+	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
+			   kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
 #else
-	create_pmd_mapping(trampoline_pmd, kernel_virt_addr,
-			   load_pa, PMD_SIZE, PAGE_KERNEL_EXEC);
+	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
+			   kernel_map.phys_addr, PMD_SIZE, PAGE_KERNEL_EXEC);
 #endif
 #else
 	/* Setup trampoline PGD */
-	create_pgd_mapping(trampoline_pg_dir, kernel_virt_addr,
-			   load_pa, PGDIR_SIZE, PAGE_KERNEL_EXEC);
+	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
+			   kernel_map.phys_addr, PGDIR_SIZE, PAGE_KERNEL_EXEC);
 #endif
 
 	/*
@@ -569,7 +605,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	 * us to reach paging_init(). We map all memory banks later
 	 * in setup_vm_final() below.
 	 */
-	create_kernel_page_table(early_pg_dir, map_size);
+	create_kernel_page_table(early_pg_dir, map_size, true);
 
 #ifndef __PAGETABLE_PMD_FOLDED
 	/* Setup early PMD for DTB */
@@ -645,22 +681,6 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 #endif
 }
 
-#if defined(CONFIG_64BIT) && defined(CONFIG_STRICT_KERNEL_RWX)
-void protect_kernel_linear_mapping_text_rodata(void)
-{
-	unsigned long text_start = (unsigned long)lm_alias(_start);
-	unsigned long init_text_start = (unsigned long)lm_alias(__init_text_begin);
-	unsigned long rodata_start = (unsigned long)lm_alias(__start_rodata);
-	unsigned long data_start = (unsigned long)lm_alias(_data);
-
-	set_memory_ro(text_start, (init_text_start - text_start) >> PAGE_SHIFT);
-	set_memory_nx(text_start, (init_text_start - text_start) >> PAGE_SHIFT);
-
-	set_memory_ro(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT);
-	set_memory_nx(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT);
-}
-#endif
-
 static void __init setup_vm_final(void)
 {
 	uintptr_t va, map_size;
@@ -693,21 +713,15 @@ static void __init setup_vm_final(void)
 		map_size = best_map_size(start, end - start);
 		for (pa = start; pa < end; pa += map_size) {
 			va = (uintptr_t)__va(pa);
-			create_pgd_mapping(swapper_pg_dir, va, pa,
-					   map_size,
-#ifdef CONFIG_64BIT
-					   PAGE_KERNEL
-#else
-					   PAGE_KERNEL_EXEC
-#endif
-					);
 
+			create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
+					   pgprot_from_va(va));
 		}
 	}
 
 #ifdef CONFIG_64BIT
 	/* Map the kernel */
-	create_kernel_page_table(swapper_pg_dir, PMD_SIZE);
+	create_kernel_page_table(swapper_pg_dir, PMD_SIZE, false);
 #endif
 
 	/* Clear fixmap PTE and PMD mappings */
@@ -738,39 +752,6 @@ static inline void setup_vm_final(void)
 }
 #endif /* CONFIG_MMU */
 
-#ifdef CONFIG_STRICT_KERNEL_RWX
-void __init protect_kernel_text_data(void)
-{
-	unsigned long text_start = (unsigned long)_start;
-	unsigned long init_text_start = (unsigned long)__init_text_begin;
-	unsigned long init_data_start = (unsigned long)__init_data_begin;
-	unsigned long rodata_start = (unsigned long)__start_rodata;
-	unsigned long data_start = (unsigned long)_data;
-#if defined(CONFIG_64BIT) && defined(CONFIG_MMU)
-	unsigned long end_va = kernel_virt_addr + load_sz;
-#else
-	unsigned long end_va = (unsigned long)(__va(PFN_PHYS(max_low_pfn)));
-#endif
-
-	set_memory_ro(text_start, (init_text_start - text_start) >> PAGE_SHIFT);
-	set_memory_ro(init_text_start, (init_data_start - init_text_start) >> PAGE_SHIFT);
-	set_memory_nx(init_data_start, (rodata_start - init_data_start) >> PAGE_SHIFT);
-	/* rodata section is marked readonly in mark_rodata_ro */
-	set_memory_nx(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT);
-	set_memory_nx(data_start, (end_va - data_start) >> PAGE_SHIFT);
-}
-
-void mark_rodata_ro(void)
-{
-	unsigned long rodata_start = (unsigned long)__start_rodata;
-	unsigned long data_start = (unsigned long)_data;
-
-	set_memory_ro(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT);
-
-	debug_checkwx();
-}
-#endif
-
 #ifdef CONFIG_KEXEC_CORE
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
@@ -858,7 +839,7 @@ static void __init reserve_crashkernel(void)
  * reserved once we call early_init_fdt_scan_reserved_mem()
  * later on.
  */
-static int elfcore_hdr_setup(struct reserved_mem *rmem)
+static int __init elfcore_hdr_setup(struct reserved_mem *rmem)
 {
 	elfcorehdr_addr = rmem->base;
 	elfcorehdr_size = rmem->size;
@@ -870,8 +851,8 @@ RESERVEDMEM_OF_DECLARE(elfcorehdr, "linux,elfcorehdr", elfcore_hdr_setup);
 
 void __init paging_init(void)
 {
+	setup_bootmem();
 	setup_vm_final();
-	setup_zero_page();
 }
 
 void __init misc_mem_init(void)
diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c
index 35703d5ef5fd..e7fd0c253c7b 100644
--- a/arch/riscv/mm/physaddr.c
+++ b/arch/riscv/mm/physaddr.c
@@ -23,7 +23,7 @@ EXPORT_SYMBOL(__virt_to_phys);
 
 phys_addr_t __phys_addr_symbol(unsigned long x)
 {
-	unsigned long kernel_start = (unsigned long)kernel_virt_addr;
+	unsigned long kernel_start = kernel_map.virt_addr;
 	unsigned long kernel_end = (unsigned long)_end;
 
 	/*
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 0536ac84b730..830e7de65e3a 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -98,8 +98,8 @@ static struct addr_marker address_markers[] = {
 	{0, "vmalloc() end"},
 	{0, "Linear mapping"},
 #ifdef CONFIG_64BIT
-	{0, "Modules mapping"},
-	{0, "Kernel mapping (kernel, BPF)"},
+	{0, "Modules/BPF mapping"},
+	{0, "Kernel mapping"},
 #endif
 	{-1, NULL},
 };
@@ -379,7 +379,7 @@ static int __init ptdump_init(void)
 	address_markers[PAGE_OFFSET_NR].start_address = PAGE_OFFSET;
 #ifdef CONFIG_64BIT
 	address_markers[MODULES_MAPPING_NR].start_address = MODULES_VADDR;
-	address_markers[KERNEL_MAPPING_NR].start_address = kernel_virt_addr;
+	address_markers[KERNEL_MAPPING_NR].start_address = kernel_map.virt_addr;
 #endif
 
 	kernel_ptd_info.base_addr = KERN_VIRT_START;
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 720b443c4528..64f8201237c2 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -4,36 +4,66 @@
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <asm/sbi.h>
+#include <asm/mmu_context.h>
+
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma x0, %0"
+			:
+			: "r" (asid)
+			: "memory");
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+		unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma %0, %1"
+			:
+			: "r" (addr), "r" (asid)
+			: "memory");
+}
 
 void flush_tlb_all(void)
 {
 	sbi_remote_sfence_vma(NULL, 0, -1);
 }
 
-/*
- * This function must not be called with cmask being null.
- * Kernel may panic if cmask is NULL.
- */
-static void __sbi_tlb_flush_range(struct cpumask *cmask, unsigned long start,
-				  unsigned long size)
+static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
+				  unsigned long size, unsigned long stride)
 {
+	struct cpumask *cmask = mm_cpumask(mm);
 	struct cpumask hmask;
 	unsigned int cpuid;
+	bool broadcast;
 
 	if (cpumask_empty(cmask))
 		return;
 
 	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)) {
+		unsigned long asid = atomic_long_read(&mm->context.id);
 
-	if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) {
-		/* local cpu is the only cpu present in cpumask */
-		if (size <= PAGE_SIZE)
+		if (broadcast) {
+			riscv_cpuid_to_hartid_mask(cmask, &hmask);
+			sbi_remote_sfence_vma_asid(cpumask_bits(&hmask),
+						   start, size, asid);
+		} else if (size <= stride) {
+			local_flush_tlb_page_asid(start, asid);
+		} else {
+			local_flush_tlb_all_asid(asid);
+		}
+	} else {
+		if (broadcast) {
+			riscv_cpuid_to_hartid_mask(cmask, &hmask);
+			sbi_remote_sfence_vma(cpumask_bits(&hmask),
+					      start, size);
+		} else if (size <= stride) {
 			local_flush_tlb_page(start);
-		else
+		} else {
 			local_flush_tlb_all();
-	} else {
-		riscv_cpuid_to_hartid_mask(cmask, &hmask);
-		sbi_remote_sfence_vma(cpumask_bits(&hmask), start, size);
+		}
 	}
 
 	put_cpu();
@@ -41,16 +71,23 @@ static void __sbi_tlb_flush_range(struct cpumask *cmask, unsigned long start,
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__sbi_tlb_flush_range(mm_cpumask(mm), 0, -1);
+	__sbi_tlb_flush_range(mm, 0, -1, PAGE_SIZE);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__sbi_tlb_flush_range(mm_cpumask(vma->vm_mm), addr, PAGE_SIZE);
+	__sbi_tlb_flush_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__sbi_tlb_flush_range(mm_cpumask(vma->vm_mm), start, end - start);
+	__sbi_tlb_flush_range(vma->vm_mm, 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)
+{
+	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PMD_SIZE);
 }
+#endif