Merge tag 'riscv-for-linus-5.10-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:
 "A handful of cleanups and new features:

   - A handful of cleanups for our page fault handling

   - Improvements to how we fill out cacheinfo

   - Support for EFI-based systems"

* tag 'riscv-for-linus-5.10-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (22 commits)
  RISC-V: Add page table dump support for uefi
  RISC-V: Add EFI runtime services
  RISC-V: Add EFI stub support.
  RISC-V: Add PE/COFF header for EFI stub
  RISC-V: Implement late mapping page table allocation functions
  RISC-V: Add early ioremap support
  RISC-V: Move DT mapping outof fixmap
  RISC-V: Fix duplicate included thread_info.h
  riscv/mm/fault: Set FAULT_FLAG_INSTRUCTION flag in do_page_fault()
  riscv/mm/fault: Fix inline placement in vmalloc_fault() declaration
  riscv: Add cache information in AUX vector
  riscv: Define AT_VECTOR_SIZE_ARCH for ARCH_DLINFO
  riscv: Set more data to cacheinfo
  riscv/mm/fault: Move access error check to function
  riscv/mm/fault: Move FAULT_FLAG_WRITE handling in do_page_fault()
  riscv/mm/fault: Simplify mm_fault_error()
  riscv/mm/fault: Move fault error handling to mm_fault_error()
  riscv/mm/fault: Simplify fault error handling
  riscv/mm/fault: Move vmalloc fault handling to vmalloc_fault()
  riscv/mm/fault: Move bad area handling to bad_area()
  ...

3 files changed, 384 insertions, 210 deletions

diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 716d64e36f83..1359e21c0c62 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -19,6 +19,167 @@
 
 #include "../kernel/head.h"
 
+static inline void no_context(struct pt_regs *regs, unsigned long addr)
+{
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice.
+	 */
+	bust_spinlocks(1);
+	pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
+		(addr < PAGE_SIZE) ? "NULL pointer dereference" :
+		"paging request", addr);
+	die(regs, "Oops");
+	do_exit(SIGKILL);
+}
+
+static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
+{
+	if (fault & VM_FAULT_OOM) {
+		/*
+		 * We ran out of memory, call the OOM killer, and return the userspace
+		 * (which will retry the fault, or kill us if we got oom-killed).
+		 */
+		if (!user_mode(regs)) {
+			no_context(regs, addr);
+			return;
+		}
+		pagefault_out_of_memory();
+		return;
+	} else if (fault & VM_FAULT_SIGBUS) {
+		/* Kernel mode? Handle exceptions or die */
+		if (!user_mode(regs)) {
+			no_context(regs, addr);
+			return;
+		}
+		do_trap(regs, SIGBUS, BUS_ADRERR, addr);
+		return;
+	}
+	BUG();
+}
+
+static inline void bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr)
+{
+	/*
+	 * Something tried to access memory that isn't in our memory map.
+	 * Fix it, but check if it's kernel or user first.
+	 */
+	mmap_read_unlock(mm);
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		do_trap(regs, SIGSEGV, code, addr);
+		return;
+	}
+
+	no_context(regs, addr);
+}
+
+static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr)
+{
+	pgd_t *pgd, *pgd_k;
+	pud_t *pud, *pud_k;
+	p4d_t *p4d, *p4d_k;
+	pmd_t *pmd, *pmd_k;
+	pte_t *pte_k;
+	int index;
+
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs))
+		return do_trap(regs, SIGSEGV, code, addr);
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "tsk->active_mm->pgd" here.
+	 * We might be inside an interrupt in the middle
+	 * of a task switch.
+	 */
+	index = pgd_index(addr);
+	pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
+	pgd_k = init_mm.pgd + index;
+
+	if (!pgd_present(*pgd_k)) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pgd(pgd, *pgd_k);
+
+	p4d = p4d_offset(pgd, addr);
+	p4d_k = p4d_offset(pgd_k, addr);
+	if (!p4d_present(*p4d_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	pud = pud_offset(p4d, addr);
+	pud_k = pud_offset(p4d_k, addr);
+	if (!pud_present(*pud_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * Since the vmalloc area is global, it is unnecessary
+	 * to copy individual PTEs
+	 */
+	pmd = pmd_offset(pud, addr);
+	pmd_k = pmd_offset(pud_k, addr);
+	if (!pmd_present(*pmd_k)) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pmd(pmd, *pmd_k);
+
+	/*
+	 * Make sure the actual PTE exists as well to
+	 * catch kernel vmalloc-area accesses to non-mapped
+	 * addresses. If we don't do this, this will just
+	 * silently loop forever.
+	 */
+	pte_k = pte_offset_kernel(pmd_k, addr);
+	if (!pte_present(*pte_k)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * The kernel assumes that TLBs don't cache invalid
+	 * entries, but in RISC-V, SFENCE.VMA specifies an
+	 * ordering constraint, not a cache flush; it is
+	 * necessary even after writing invalid entries.
+	 */
+	local_flush_tlb_page(addr);
+}
+
+static inline bool access_error(unsigned long cause, struct vm_area_struct *vma)
+{
+	switch (cause) {
+	case EXC_INST_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_EXEC)) {
+			return true;
+		}
+		break;
+	case EXC_LOAD_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_READ)) {
+			return true;
+		}
+		break;
+	case EXC_STORE_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_WRITE)) {
+			return true;
+		}
+		break;
+	default:
+		panic("%s: unhandled cause %lu", __func__, cause);
+	}
+	return false;
+}
+
 /*
  * This routine handles page faults.  It determines the address and the
  * problem, and then passes it off to one of the appropriate routines.
@@ -48,8 +209,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	 * only copy the information from the master page table,
 	 * nothing more.
 	 */
-	if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END)))
-		goto vmalloc_fault;
+	if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END))) {
+		vmalloc_fault(regs, code, addr);
+		return;
+	}
 
 	/* Enable interrupts if they were enabled in the parent context. */
 	if (likely(regs->status & SR_PIE))
@@ -59,25 +222,37 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	 * If we're in an interrupt, have no user context, or are running
 	 * in an atomic region, then we must not take the fault.
 	 */
-	if (unlikely(faulthandler_disabled() || !mm))
-		goto no_context;
+	if (unlikely(faulthandler_disabled() || !mm)) {
+		no_context(regs, addr);
+		return;
+	}
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
+	if (cause == EXC_STORE_PAGE_FAULT)
+		flags |= FAULT_FLAG_WRITE;
+	else if (cause == EXC_INST_PAGE_FAULT)
+		flags |= FAULT_FLAG_INSTRUCTION;
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, addr);
-	if (unlikely(!vma))
-		goto bad_area;
+	if (unlikely(!vma)) {
+		bad_area(regs, mm, code, addr);
+		return;
+	}
 	if (likely(vma->vm_start <= addr))
 		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
-		goto bad_area;
-	if (unlikely(expand_stack(vma, addr)))
-		goto bad_area;
+	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
+		bad_area(regs, mm, code, addr);
+		return;
+	}
+	if (unlikely(expand_stack(vma, addr))) {
+		bad_area(regs, mm, code, addr);
+		return;
+	}
 
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
@@ -86,22 +261,9 @@ retry:
 good_area:
 	code = SEGV_ACCERR;
 
-	switch (cause) {
-	case EXC_INST_PAGE_FAULT:
-		if (!(vma->vm_flags & VM_EXEC))
-			goto bad_area;
-		break;
-	case EXC_LOAD_PAGE_FAULT:
-		if (!(vma->vm_flags & VM_READ))
-			goto bad_area;
-		break;
-	case EXC_STORE_PAGE_FAULT:
-		if (!(vma->vm_flags & VM_WRITE))
-			goto bad_area;
-		flags |= FAULT_FLAG_WRITE;
-		break;
-	default:
-		panic("%s: unhandled cause %lu", __func__, cause);
+	if (unlikely(access_error(cause, vma))) {
+		bad_area(regs, mm, code, addr);
+		return;
 	}
 
 	/*
@@ -119,144 +281,22 @@ good_area:
 	if (fault_signal_pending(fault, regs))
 		return;
 
-	if (unlikely(fault & VM_FAULT_ERROR)) {
-		if (fault & VM_FAULT_OOM)
-			goto out_of_memory;
-		else if (fault & VM_FAULT_SIGBUS)
-			goto do_sigbus;
-		BUG();
-	}
-
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_RETRY) {
-			flags |= FAULT_FLAG_TRIED;
+	if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) {
+		flags |= FAULT_FLAG_TRIED;
 
-			/*
-			 * No need to mmap_read_unlock(mm) as we would
-			 * have already released it in __lock_page_or_retry
-			 * in mm/filemap.c.
-			 */
-			goto retry;
-		}
+		/*
+		 * No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
+		goto retry;
 	}
 
 	mmap_read_unlock(mm);
-	return;
 
-	/*
-	 * Something tried to access memory that isn't in our memory map.
-	 * Fix it, but check if it's kernel or user first.
-	 */
-bad_area:
-	mmap_read_unlock(mm);
-	/* User mode accesses just cause a SIGSEGV */
-	if (user_mode(regs)) {
-		do_trap(regs, SIGSEGV, code, addr);
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		mm_fault_error(regs, addr, fault);
 		return;
 	}
-
-no_context:
-	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs))
-		return;
-
-	/*
-	 * Oops. The kernel tried to access some bad page. We'll have to
-	 * terminate things with extreme prejudice.
-	 */
-	bust_spinlocks(1);
-	pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
-		(addr < PAGE_SIZE) ? "NULL pointer dereference" :
-		"paging request", addr);
-	die(regs, "Oops");
-	do_exit(SIGKILL);
-
-	/*
-	 * We ran out of memory, call the OOM killer, and return the userspace
-	 * (which will retry the fault, or kill us if we got oom-killed).
-	 */
-out_of_memory:
-	mmap_read_unlock(mm);
-	if (!user_mode(regs))
-		goto no_context;
-	pagefault_out_of_memory();
-	return;
-
-do_sigbus:
-	mmap_read_unlock(mm);
-	/* Kernel mode? Handle exceptions or die */
-	if (!user_mode(regs))
-		goto no_context;
-	do_trap(regs, SIGBUS, BUS_ADRERR, addr);
 	return;
-
-vmalloc_fault:
-	{
-		pgd_t *pgd, *pgd_k;
-		pud_t *pud, *pud_k;
-		p4d_t *p4d, *p4d_k;
-		pmd_t *pmd, *pmd_k;
-		pte_t *pte_k;
-		int index;
-
-		/* User mode accesses just cause a SIGSEGV */
-		if (user_mode(regs))
-			return do_trap(regs, SIGSEGV, code, addr);
-
-		/*
-		 * Synchronize this task's top level page-table
-		 * with the 'reference' page table.
-		 *
-		 * Do _not_ use "tsk->active_mm->pgd" here.
-		 * We might be inside an interrupt in the middle
-		 * of a task switch.
-		 */
-		index = pgd_index(addr);
-		pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
-		pgd_k = init_mm.pgd + index;
-
-		if (!pgd_present(*pgd_k))
-			goto no_context;
-		set_pgd(pgd, *pgd_k);
-
-		p4d = p4d_offset(pgd, addr);
-		p4d_k = p4d_offset(pgd_k, addr);
-		if (!p4d_present(*p4d_k))
-			goto no_context;
-
-		pud = pud_offset(p4d, addr);
-		pud_k = pud_offset(p4d_k, addr);
-		if (!pud_present(*pud_k))
-			goto no_context;
-
-		/*
-		 * Since the vmalloc area is global, it is unnecessary
-		 * to copy individual PTEs
-		 */
-		pmd = pmd_offset(pud, addr);
-		pmd_k = pmd_offset(pud_k, addr);
-		if (!pmd_present(*pmd_k))
-			goto no_context;
-		set_pmd(pmd, *pmd_k);
-
-		/*
-		 * Make sure the actual PTE exists as well to
-		 * catch kernel vmalloc-area accesses to non-mapped
-		 * addresses. If we don't do this, this will just
-		 * silently loop forever.
-		 */
-		pte_k = pte_offset_kernel(pmd_k, addr);
-		if (!pte_present(*pte_k))
-			goto no_context;
-
-		/*
-		 * The kernel assumes that TLBs don't cache invalid
-		 * entries, but in RISC-V, SFENCE.VMA specifies an
-		 * ordering constraint, not a cache flush; it is
-		 * necessary even after writing invalid entries.
-		 */
-		local_flush_tlb_page(addr);
-
-		return;
-	}
 }
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 1dc89303b679..ea933b789a88 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -28,7 +28,18 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 EXPORT_SYMBOL(empty_zero_page);
 
 extern char _start[];
-void *dtb_early_va;
+#define DTB_EARLY_BASE_VA      PGDIR_SIZE
+void *dtb_early_va __initdata;
+uintptr_t dtb_early_pa __initdata;
+
+struct pt_alloc_ops {
+	pte_t *(*get_pte_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pte)(uintptr_t va);
+#ifndef __PAGETABLE_PMD_FOLDED
+	pmd_t *(*get_pmd_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pmd)(uintptr_t va);
+#endif
+};
 
 static void __init zone_sizes_init(void)
 {
@@ -141,8 +152,6 @@ disable:
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-static phys_addr_t dtb_early_pa __initdata;
-
 void __init setup_bootmem(void)
 {
 	phys_addr_t mem_size = 0;
@@ -194,6 +203,8 @@ void __init setup_bootmem(void)
 }
 
 #ifdef CONFIG_MMU
+static struct pt_alloc_ops pt_ops;
+
 unsigned long va_pa_offset;
 EXPORT_SYMBOL(va_pa_offset);
 unsigned long pfn_base;
@@ -202,7 +213,6 @@ 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 bool mmu_enabled;
 
 #define MAX_EARLY_MAPPING_SIZE	SZ_128M
 
@@ -224,27 +234,46 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 	local_flush_tlb_page(addr);
 }
 
-static pte_t *__init get_pte_virt(phys_addr_t pa)
+static inline pte_t *__init get_pte_virt_early(phys_addr_t pa)
 {
-	if (mmu_enabled) {
-		clear_fixmap(FIX_PTE);
-		return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
-	} else {
-		return (pte_t *)((uintptr_t)pa);
-	}
+	return (pte_t *)((uintptr_t)pa);
 }
 
-static phys_addr_t __init alloc_pte(uintptr_t va)
+static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PTE);
+	return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
+}
+
+static inline pte_t *get_pte_virt_late(phys_addr_t pa)
+{
+	return (pte_t *) __va(pa);
+}
+
+static inline phys_addr_t __init alloc_pte_early(uintptr_t va)
 {
 	/*
 	 * We only create PMD or PGD early mappings so we
 	 * should never reach here with MMU disabled.
 	 */
-	BUG_ON(!mmu_enabled);
+	BUG();
+}
 
+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)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	if (!vaddr || !pgtable_pte_page_ctor(virt_to_page(vaddr)))
+		BUG();
+	return __pa(vaddr);
+}
+
 static void __init create_pte_mapping(pte_t *ptep,
 				      uintptr_t va, phys_addr_t pa,
 				      phys_addr_t sz, pgprot_t prot)
@@ -269,28 +298,46 @@ pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
 #endif
 pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE);
 
-static pmd_t *__init get_pmd_virt(phys_addr_t pa)
+static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
 {
-	if (mmu_enabled) {
-		clear_fixmap(FIX_PMD);
-		return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
-	} else {
-		return (pmd_t *)((uintptr_t)pa);
-	}
+	/* Before MMU is enabled */
+	return (pmd_t *)((uintptr_t)pa);
 }
 
-static phys_addr_t __init alloc_pmd(uintptr_t va)
+static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa)
 {
-	uintptr_t pmd_num;
+	clear_fixmap(FIX_PMD);
+	return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
+}
 
-	if (mmu_enabled)
-		return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+static pmd_t *get_pmd_virt_late(phys_addr_t pa)
+{
+	return (pmd_t *) __va(pa);
+}
+
+static phys_addr_t __init alloc_pmd_early(uintptr_t va)
+{
+	uintptr_t pmd_num;
 
 	pmd_num = (va - PAGE_OFFSET) >> PGDIR_SHIFT;
 	BUG_ON(pmd_num >= NUM_EARLY_PMDS);
 	return (uintptr_t)&early_pmd[pmd_num * PTRS_PER_PMD];
 }
 
+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)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr);
+	return __pa(vaddr);
+}
+
 static void __init create_pmd_mapping(pmd_t *pmdp,
 				      uintptr_t va, phys_addr_t pa,
 				      phys_addr_t sz, pgprot_t prot)
@@ -306,34 +353,34 @@ static void __init create_pmd_mapping(pmd_t *pmdp,
 	}
 
 	if (pmd_none(pmdp[pmd_idx])) {
-		pte_phys = alloc_pte(va);
+		pte_phys = pt_ops.alloc_pte(va);
 		pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pte_phys), PAGE_TABLE);
-		ptep = get_pte_virt(pte_phys);
+		ptep = pt_ops.get_pte_virt(pte_phys);
 		memset(ptep, 0, PAGE_SIZE);
 	} else {
 		pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_idx]));
-		ptep = get_pte_virt(pte_phys);
+		ptep = pt_ops.get_pte_virt(pte_phys);
 	}
 
 	create_pte_mapping(ptep, va, pa, sz, prot);
 }
 
 #define pgd_next_t		pmd_t
-#define alloc_pgd_next(__va)	alloc_pmd(__va)
-#define get_pgd_next_virt(__pa)	get_pmd_virt(__pa)
+#define alloc_pgd_next(__va)	pt_ops.alloc_pmd(__va)
+#define get_pgd_next_virt(__pa)	pt_ops.get_pmd_virt(__pa)
 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
 	create_pmd_mapping(__nextp, __va, __pa, __sz, __prot)
 #define fixmap_pgd_next		fixmap_pmd
 #else
 #define pgd_next_t		pte_t
-#define alloc_pgd_next(__va)	alloc_pte(__va)
-#define get_pgd_next_virt(__pa)	get_pte_virt(__pa)
+#define alloc_pgd_next(__va)	pt_ops.alloc_pte(__va)
+#define get_pgd_next_virt(__pa)	pt_ops.get_pte_virt(__pa)
 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
 	create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
 #define fixmap_pgd_next		fixmap_pte
 #endif
 
-static void __init create_pgd_mapping(pgd_t *pgdp,
+void __init create_pgd_mapping(pgd_t *pgdp,
 				      uintptr_t va, phys_addr_t pa,
 				      phys_addr_t sz, pgprot_t prot)
 {
@@ -389,10 +436,13 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {
-	uintptr_t va, end_va;
+	uintptr_t va, pa, end_va;
 	uintptr_t load_pa = (uintptr_t)(&_start);
 	uintptr_t load_sz = (uintptr_t)(&_end) - load_pa;
 	uintptr_t map_size = best_map_size(load_pa, MAX_EARLY_MAPPING_SIZE);
+#ifndef __PAGETABLE_PMD_FOLDED
+	pmd_t fix_bmap_spmd, fix_bmap_epmd;
+#endif
 
 	va_pa_offset = PAGE_OFFSET - load_pa;
 	pfn_base = PFN_DOWN(load_pa);
@@ -408,6 +458,12 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	BUG_ON((load_pa % map_size) != 0);
 	BUG_ON(load_sz > MAX_EARLY_MAPPING_SIZE);
 
+	pt_ops.alloc_pte = alloc_pte_early;
+	pt_ops.get_pte_virt = get_pte_virt_early;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_early;
+	pt_ops.get_pmd_virt = get_pmd_virt_early;
+#endif
 	/* Setup early PGD for fixmap */
 	create_pgd_mapping(early_pg_dir, FIXADDR_START,
 			   (uintptr_t)fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
@@ -438,17 +494,44 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 				   load_pa + (va - PAGE_OFFSET),
 				   map_size, PAGE_KERNEL_EXEC);
 
-	/* Create fixed mapping for early FDT parsing */
-	end_va = __fix_to_virt(FIX_FDT) + FIX_FDT_SIZE;
-	for (va = __fix_to_virt(FIX_FDT); va < end_va; va += PAGE_SIZE)
-		create_pte_mapping(fixmap_pte, va,
-				   dtb_pa + (va - __fix_to_virt(FIX_FDT)),
-				   PAGE_SIZE, PAGE_KERNEL);
-
-	/* Save pointer to DTB for early FDT parsing */
-	dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK);
-	/* Save physical address for memblock reservation */
+	/* Create two consecutive PGD mappings for FDT early scan */
+	pa = dtb_pa & ~(PGDIR_SIZE - 1);
+	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
+			   pa, PGDIR_SIZE, PAGE_KERNEL);
+	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE,
+			   pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL);
+	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1));
 	dtb_early_pa = dtb_pa;
+
+	/*
+	 * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
+	 * range can not span multiple pmds.
+	 */
+	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+
+#ifndef __PAGETABLE_PMD_FOLDED
+	/*
+	 * Early ioremap fixmap is already created as it lies within first 2MB
+	 * of fixmap region. We always map PMD_SIZE. Thus, both FIX_BTMAP_END
+	 * FIX_BTMAP_BEGIN should lie in the same pmd. Verify that and warn
+	 * the user if not.
+	 */
+	fix_bmap_spmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_BEGIN))];
+	fix_bmap_epmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_END))];
+	if (pmd_val(fix_bmap_spmd) != pmd_val(fix_bmap_epmd)) {
+		WARN_ON(1);
+		pr_warn("fixmap btmap start [%08lx] != end [%08lx]\n",
+			pmd_val(fix_bmap_spmd), pmd_val(fix_bmap_epmd));
+		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+			fix_to_virt(FIX_BTMAP_BEGIN));
+		pr_warn("fix_to_virt(FIX_BTMAP_END):   %08lx\n",
+			fix_to_virt(FIX_BTMAP_END));
+
+		pr_warn("FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
+		pr_warn("FIX_BTMAP_BEGIN:     %d\n", FIX_BTMAP_BEGIN);
+	}
+#endif
 }
 
 static void __init setup_vm_final(void)
@@ -457,9 +540,16 @@ static void __init setup_vm_final(void)
 	phys_addr_t pa, start, end;
 	u64 i;
 
-	/* Set mmu_enabled flag */
-	mmu_enabled = true;
-
+	/**
+	 * MMU is enabled at this point. But page table setup is not complete yet.
+	 * fixmap page table alloc functions should be used at this point
+	 */
+	pt_ops.alloc_pte = alloc_pte_fixmap;
+	pt_ops.get_pte_virt = get_pte_virt_fixmap;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_fixmap;
+	pt_ops.get_pmd_virt = get_pmd_virt_fixmap;
+#endif
 	/* Setup swapper PGD for fixmap */
 	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
 			   __pa_symbol(fixmap_pgd_next),
@@ -488,6 +578,14 @@ static void __init setup_vm_final(void)
 	/* Move to swapper page table */
 	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
 	local_flush_tlb_all();
+
+	/* generic page allocation functions must be used to setup page table */
+	pt_ops.alloc_pte = alloc_pte_late;
+	pt_ops.get_pte_virt = get_pte_virt_late;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_late;
+	pt_ops.get_pmd_virt = get_pmd_virt_late;
+#endif
 }
 #else
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 0831c2e61a8f..ace74dec7492 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2019 SiFive
  */
 
+#include <linux/efi.h>
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -49,6 +50,14 @@ struct addr_marker {
 	const char *name;
 };
 
+/* Private information for debugfs */
+struct ptd_mm_info {
+	struct mm_struct		*mm;
+	const struct addr_marker	*markers;
+	unsigned long base_addr;
+	unsigned long end;
+};
+
 static struct addr_marker address_markers[] = {
 #ifdef CONFIG_KASAN
 	{KASAN_SHADOW_START,	"Kasan shadow start"},
@@ -68,6 +77,28 @@ static struct addr_marker address_markers[] = {
 	{-1, NULL},
 };
 
+static struct ptd_mm_info kernel_ptd_info = {
+	.mm		= &init_mm,
+	.markers	= address_markers,
+	.base_addr	= KERN_VIRT_START,
+	.end		= ULONG_MAX,
+};
+
+#ifdef CONFIG_EFI
+static struct addr_marker efi_addr_markers[] = {
+		{ 0,		"UEFI runtime start" },
+		{ SZ_1G,	"UEFI runtime end" },
+		{ -1,		NULL }
+};
+
+static struct ptd_mm_info efi_ptd_info = {
+	.mm		= &efi_mm,
+	.markers	= efi_addr_markers,
+	.base_addr	= 0,
+	.end		= SZ_2G,
+};
+#endif
+
 /* Page Table Entry */
 struct prot_bits {
 	u64 mask;
@@ -245,22 +276,22 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr,
 	}
 }
 
-static void ptdump_walk(struct seq_file *s)
+static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo)
 {
 	struct pg_state st = {
 		.seq = s,
-		.marker = address_markers,
+		.marker = pinfo->markers,
 		.level = -1,
 		.ptdump = {
 			.note_page = note_page,
 			.range = (struct ptdump_range[]) {
-				{KERN_VIRT_START, ULONG_MAX},
+				{pinfo->base_addr, pinfo->end},
 				{0, 0}
 			}
 		}
 	};
 
-	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+	ptdump_walk_pgd(&st.ptdump, pinfo->mm, NULL);
 }
 
 void ptdump_check_wx(void)
@@ -293,7 +324,7 @@ void ptdump_check_wx(void)
 
 static int ptdump_show(struct seq_file *m, void *v)
 {
-	ptdump_walk(m);
+	ptdump_walk(m, m->private);
 
 	return 0;
 }
@@ -308,8 +339,13 @@ static int ptdump_init(void)
 		for (j = 0; j < ARRAY_SIZE(pte_bits); j++)
 			pg_level[i].mask |= pte_bits[j].mask;
 
-	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
+	debugfs_create_file("kernel_page_tables", 0400, NULL, &kernel_ptd_info,
 			    &ptdump_fops);
+#ifdef CONFIG_EFI
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		debugfs_create_file("efi_page_tables", 0400, NULL, &efi_ptd_info,
+				    &ptdump_fops);
+#endif
 
 	return 0;
 }