1 files changed, 853 insertions, 399 deletions

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 128f70852bf3..495b732d5af3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -17,10 +17,14 @@
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
+#include <linux/memremap.h>
+#include <linux/memory.h>
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/set_memory.h>
+#include <linux/kfence.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -34,19 +38,26 @@
 #include <asm/mmu_context.h>
 #include <asm/ptdump.h>
 #include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm/kfence.h>
 
 #define NO_BLOCK_MAPPINGS	BIT(0)
 #define NO_CONT_MAPPINGS	BIT(1)
-
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
-u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
-
-u64 __section(".mmuoff.data.write") vabits_actual;
-EXPORT_SYMBOL(vabits_actual);
+#define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
 
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
+u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_EL2, BOOT_CPU_MODE_EL1 };
+
+static bool rodata_is_rw __ro_after_init = true;
+
+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ */
+long __section(".mmuoff.data.write") __early_cpu_boot_status;
+
 /*
  * Empty_zero_page is a special page that is used for zero-initialized data
  * and COW.
@@ -54,16 +65,24 @@ EXPORT_SYMBOL(kimage_voffset);
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
 
-static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
-static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
-static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
-
 static DEFINE_SPINLOCK(swapper_pgdir_lock);
+static DEFINE_MUTEX(fixmap_lock);
 
-void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
+void noinstr set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	pgd_t *fixmap_pgdp;
 
+	/*
+	 * Don't bother with the fixmap if swapper_pg_dir is still mapped
+	 * writable in the kernel mapping.
+	 */
+	if (rodata_is_rw) {
+		WRITE_ONCE(*pgdp, pgd);
+		dsb(ishst);
+		isb();
+		return;
+	}
+
 	spin_lock(&swapper_pgdir_lock);
 	fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp));
 	WRITE_ONCE(*fixmap_pgdp, pgd);
@@ -79,7 +98,7 @@ void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
-	if (!pfn_valid(pfn))
+	if (!pfn_is_map_memory(pfn))
 		return pgprot_noncached(vma_prot);
 	else if (file->f_flags & O_SYNC)
 		return pgprot_writecombine(vma_prot);
@@ -92,7 +111,8 @@ static phys_addr_t __init early_pgtable_alloc(int shift)
 	phys_addr_t phys;
 	void *ptr;
 
-	phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+	phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0,
+					 MEMBLOCK_ALLOC_NOLEAKTRACE);
 	if (!phys)
 		panic("Failed to allocate page table page\n");
 
@@ -114,18 +134,22 @@ static phys_addr_t __init early_pgtable_alloc(int shift)
 	return phys;
 }
 
-static bool pgattr_change_is_safe(u64 old, u64 new)
+bool pgattr_change_is_safe(u64 old, u64 new)
 {
 	/*
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
-	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
 
 	/* creating or taking down mappings is always safe */
-	if (old == 0 || new == 0)
+	if (!pte_valid(__pte(old)) || !pte_valid(__pte(new)))
 		return true;
 
+	/* A live entry's pfn should not change */
+	if (pte_pfn(__pte(old)) != pte_pfn(__pte(new)))
+		return false;
+
 	/* live contiguous mappings may not be manipulated at all */
 	if ((old | new) & PTE_CONT)
 		return false;
@@ -134,6 +158,17 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	if (old & ~new & PTE_NG)
 		return false;
 
+	/*
+	 * Changing the memory type between Normal and Normal-Tagged is safe
+	 * since Tagged is considered a permission attribute from the
+	 * mismatched attribute aliases perspective.
+	 */
+	if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+	     (old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) &&
+	    ((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+	     (new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)))
+		mask |= PTE_ATTRINDX_MASK;
+
 	return ((old ^ new) & ~mask) == 0;
 }
 
@@ -144,16 +179,16 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
-		pte_t old_pte = READ_ONCE(*ptep);
+		pte_t old_pte = __ptep_get(ptep);
 
-		set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		__set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
 		 * only allow updates to the permission attributes.
 		 */
 		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
-					      READ_ONCE(pte_val(*ptep))));
+					      pte_val(__ptep_get(ptep))));
 
 		phys += PAGE_SIZE;
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
@@ -172,10 +207,14 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
 	BUG_ON(pmd_sect(pmd));
 	if (pmd_none(pmd)) {
+		pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
 		phys_addr_t pte_phys;
+
+		if (flags & NO_EXEC_MAPPINGS)
+			pmdval |= PMD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc(PAGE_SHIFT);
-		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+		__pmd_populate(pmdp, pte_phys, pmdval);
 		pmd = READ_ONCE(*pmdp);
 	}
 	BUG_ON(pmd_bad(pmd));
@@ -210,7 +249,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		next = pmd_addr_end(addr, end);
 
 		/* try section mapping first */
-		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
+		if (((addr | next | phys) & ~PMD_MASK) == 0 &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
 			pmd_set_huge(pmdp, phys, prot);
 
@@ -246,10 +285,14 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	 */
 	BUG_ON(pud_sect(pud));
 	if (pud_none(pud)) {
+		pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
 		phys_addr_t pmd_phys;
+
+		if (flags & NO_EXEC_MAPPINGS)
+			pudval |= PUD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc(PMD_SHIFT);
-		__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+		__pud_populate(pudp, pmd_phys, pudval);
 		pud = READ_ONCE(*pudp);
 	}
 	BUG_ON(pud_bad(pud));
@@ -270,37 +313,29 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	} while (addr = next, addr != end);
 }
 
-static inline bool use_1G_block(unsigned long addr, unsigned long next,
-			unsigned long phys)
-{
-	if (PAGE_SHIFT != 12)
-		return false;
-
-	if (((addr | next | phys) & ~PUD_MASK) != 0)
-		return false;
-
-	return true;
-}
-
-static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
+static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 			   phys_addr_t phys, pgprot_t prot,
 			   phys_addr_t (*pgtable_alloc)(int),
 			   int flags)
 {
 	unsigned long next;
+	p4d_t p4d = READ_ONCE(*p4dp);
 	pud_t *pudp;
-	pgd_t pgd = READ_ONCE(*pgdp);
 
-	if (pgd_none(pgd)) {
+	if (p4d_none(p4d)) {
+		p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
 		phys_addr_t pud_phys;
+
+		if (flags & NO_EXEC_MAPPINGS)
+			p4dval |= P4D_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc(PUD_SHIFT);
-		__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
-		pgd = READ_ONCE(*pgdp);
+		__p4d_populate(p4dp, pud_phys, p4dval);
+		p4d = READ_ONCE(*p4dp);
 	}
-	BUG_ON(pgd_bad(pgd));
+	BUG_ON(p4d_bad(p4d));
 
-	pudp = pud_set_fixmap_offset(pgdp, addr);
+	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
 
@@ -309,7 +344,8 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 		/*
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
-		if (use_1G_block(addr, next, phys) &&
+		if (pud_sect_supported() &&
+		   ((addr | next | phys) & ~PUD_MASK) == 0 &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
 			pud_set_huge(pudp, phys, prot);
 
@@ -332,14 +368,54 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	pud_clear_fixmap();
 }
 
-static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
-				 unsigned long virt, phys_addr_t size,
-				 pgprot_t prot,
-				 phys_addr_t (*pgtable_alloc)(int),
-				 int flags)
+static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
+			   phys_addr_t phys, pgprot_t prot,
+			   phys_addr_t (*pgtable_alloc)(int),
+			   int flags)
+{
+	unsigned long next;
+	pgd_t pgd = READ_ONCE(*pgdp);
+	p4d_t *p4dp;
+
+	if (pgd_none(pgd)) {
+		pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN;
+		phys_addr_t p4d_phys;
+
+		if (flags & NO_EXEC_MAPPINGS)
+			pgdval |= PGD_TABLE_PXN;
+		BUG_ON(!pgtable_alloc);
+		p4d_phys = pgtable_alloc(P4D_SHIFT);
+		__pgd_populate(pgdp, p4d_phys, pgdval);
+		pgd = READ_ONCE(*pgdp);
+	}
+	BUG_ON(pgd_bad(pgd));
+
+	p4dp = p4d_set_fixmap_offset(pgdp, addr);
+	do {
+		p4d_t old_p4d = READ_ONCE(*p4dp);
+
+		next = p4d_addr_end(addr, end);
+
+		alloc_init_pud(p4dp, addr, next, phys, prot,
+			       pgtable_alloc, flags);
+
+		BUG_ON(p4d_val(old_p4d) != 0 &&
+		       p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp)));
+
+		phys += next - addr;
+	} while (p4dp++, addr = next, addr != end);
+
+	p4d_clear_fixmap();
+}
+
+static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
+					unsigned long virt, phys_addr_t size,
+					pgprot_t prot,
+					phys_addr_t (*pgtable_alloc)(int),
+					int flags)
 {
 	unsigned long addr, end, next;
-	pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
+	pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
 
 	/*
 	 * If the virtual and physical address don't have the same offset
@@ -354,12 +430,31 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
+		alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc,
 			       flags);
 		phys += next - addr;
 	} while (pgdp++, addr = next, addr != end);
 }
 
+static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+				 unsigned long virt, phys_addr_t size,
+				 pgprot_t prot,
+				 phys_addr_t (*pgtable_alloc)(int),
+				 int flags)
+{
+	mutex_lock(&fixmap_lock);
+	__create_pgd_mapping_locked(pgdir, phys, virt, size, prot,
+				    pgtable_alloc, flags);
+	mutex_unlock(&fixmap_lock);
+}
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+extern __alias(__create_pgd_mapping_locked)
+void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
+			     phys_addr_t size, pgprot_t prot,
+			     phys_addr_t (*pgtable_alloc)(int), int flags);
+#endif
+
 static phys_addr_t __pgd_pgtable_alloc(int shift)
 {
 	void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL);
@@ -373,6 +468,7 @@ static phys_addr_t __pgd_pgtable_alloc(int shift)
 static phys_addr_t pgd_pgtable_alloc(int shift)
 {
 	phys_addr_t pa = __pgd_pgtable_alloc(shift);
+	struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa));
 
 	/*
 	 * Call proper page table ctor in case later we need to
@@ -380,12 +476,12 @@ static phys_addr_t pgd_pgtable_alloc(int shift)
 	 * this pre-allocated page table.
 	 *
 	 * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
-	 * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+	 * folded, and if so pagetable_pte_ctor() becomes nop.
 	 */
 	if (shift == PAGE_SHIFT)
-		BUG_ON(!pgtable_pte_page_ctor(phys_to_page(pa)));
+		BUG_ON(!pagetable_pte_ctor(ptdesc));
 	else if (shift == PMD_SHIFT)
-		BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa)));
+		BUG_ON(!pagetable_pmd_ctor(ptdesc));
 
 	return pa;
 }
@@ -395,10 +491,10 @@ static phys_addr_t pgd_pgtable_alloc(int shift)
  * without allocating new levels of table. Note that this permits the
  * creation of new section or page entries.
  */
-static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
-				  phys_addr_t size, pgprot_t prot)
+void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
+				   phys_addr_t size, pgprot_t prot)
 {
-	if ((virt >= PAGE_END) && (virt < VMALLOC_START)) {
+	if (virt < PAGE_OFFSET) {
 		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
@@ -425,7 +521,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
 				phys_addr_t size, pgprot_t prot)
 {
-	if ((virt >= PAGE_END) && (virt < VMALLOC_START)) {
+	if (virt < PAGE_OFFSET) {
 		pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
@@ -450,20 +546,92 @@ void __init mark_linear_text_alias_ro(void)
 	/*
 	 * Remove the write permissions from the linear alias of .text/.rodata
 	 */
-	update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text),
-			    (unsigned long)__init_begin - (unsigned long)_text,
+	update_mapping_prot(__pa_symbol(_stext), (unsigned long)lm_alias(_stext),
+			    (unsigned long)__init_begin - (unsigned long)_stext,
 			    PAGE_KERNEL_RO);
 }
 
+#ifdef CONFIG_KFENCE
+
+bool __ro_after_init kfence_early_init = !!CONFIG_KFENCE_SAMPLE_INTERVAL;
+
+/* early_param() will be parsed before map_mem() below. */
+static int __init parse_kfence_early_init(char *arg)
+{
+	int val;
+
+	if (get_option(&arg, &val))
+		kfence_early_init = !!val;
+	return 0;
+}
+early_param("kfence.sample_interval", parse_kfence_early_init);
+
+static phys_addr_t __init arm64_kfence_alloc_pool(void)
+{
+	phys_addr_t kfence_pool;
+
+	if (!kfence_early_init)
+		return 0;
+
+	kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
+	if (!kfence_pool) {
+		pr_err("failed to allocate kfence pool\n");
+		kfence_early_init = false;
+		return 0;
+	}
+
+	/* Temporarily mark as NOMAP. */
+	memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+
+	return kfence_pool;
+}
+
+static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp)
+{
+	if (!kfence_pool)
+		return;
+
+	/* KFENCE pool needs page-level mapping. */
+	__map_memblock(pgdp, kfence_pool, kfence_pool + KFENCE_POOL_SIZE,
+			pgprot_tagged(PAGE_KERNEL),
+			NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+	memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+	__kfence_pool = phys_to_virt(kfence_pool);
+}
+#else /* CONFIG_KFENCE */
+
+static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; }
+static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { }
+
+#endif /* CONFIG_KFENCE */
+
 static void __init map_mem(pgd_t *pgdp)
 {
-	phys_addr_t kernel_start = __pa_symbol(_text);
+	static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
+	phys_addr_t kernel_start = __pa_symbol(_stext);
 	phys_addr_t kernel_end = __pa_symbol(__init_begin);
-	struct memblock_region *reg;
-	int flags = 0;
+	phys_addr_t start, end;
+	phys_addr_t early_kfence_pool;
+	int flags = NO_EXEC_MAPPINGS;
+	u64 i;
 
-	if (rodata_full || debug_pagealloc_enabled())
-		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+	/*
+	 * Setting hierarchical PXNTable attributes on table entries covering
+	 * the linear region is only possible if it is guaranteed that no table
+	 * entries at any level are being shared between the linear region and
+	 * the vmalloc region. Check whether this is true for the PGD level, in
+	 * which case it is guaranteed to be true for all other levels as well.
+	 * (Unless we are running with support for LPA2, in which case the
+	 * entire reduced VA space is covered by a single pgd_t which will have
+	 * been populated without the PXNTable attribute by the time we get here.)
+	 */
+	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end) &&
+		     pgd_index(_PAGE_OFFSET(VA_BITS_MIN)) != PTRS_PER_PGD - 1);
+
+	early_kfence_pool = arm64_kfence_alloc_pool();
+
+	if (can_set_direct_map())
+		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*
 	 * Take care not to create a writable alias for the
@@ -472,27 +640,22 @@ static void __init map_mem(pgd_t *pgdp)
 	 * the following for-loop
 	 */
 	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
-#ifdef CONFIG_KEXEC_CORE
-	if (crashk_res.end)
-		memblock_mark_nomap(crashk_res.start,
-				    resource_size(&crashk_res));
-#endif
 
 	/* map all the memory banks */
-	for_each_memblock(memory, reg) {
-		phys_addr_t start = reg->base;
-		phys_addr_t end = start + reg->size;
-
+	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
 			break;
-		if (memblock_is_nomap(reg))
-			continue;
-
-		__map_memblock(pgdp, start, end, PAGE_KERNEL, flags);
+		/*
+		 * The linear map must allow allocation tags reading/writing
+		 * if MTE is present. Otherwise, it has the same attributes as
+		 * PAGE_KERNEL.
+		 */
+		__map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
+			       flags);
 	}
 
 	/*
-	 * Map the linear alias of the [_text, __init_begin) interval
+	 * Map the linear alias of the [_stext, __init_begin) interval
 	 * as non-executable now, and remove the write permission in
 	 * mark_linear_text_alias_ro() below (which will be called after
 	 * alternative patching has completed). This makes the contents
@@ -504,21 +667,7 @@ static void __init map_mem(pgd_t *pgdp)
 	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
-
-#ifdef CONFIG_KEXEC_CORE
-	/*
-	 * Use page-level mappings here so that we can shrink the region
-	 * in page granularity and put back unused memory to buddy system
-	 * through /sys/kernel/kexec_crash_size interface.
-	 */
-	if (crashk_res.end) {
-		__map_memblock(pgdp, crashk_res.start, crashk_res.end + 1,
-			       PAGE_KERNEL,
-			       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
-		memblock_clear_nomap(crashk_res.start,
-				     resource_size(&crashk_res));
-	}
-#endif
+	arm64_kfence_map_pool(early_kfence_pool, pgdp);
 }
 
 void mark_rodata_ro(void)
@@ -530,15 +679,14 @@ void mark_rodata_ro(void)
 	 * to cover NOTES and EXCEPTION_TABLE.
 	 */
 	section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
+	WRITE_ONCE(rodata_is_rw, false);
 	update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata,
 			    section_size, PAGE_KERNEL_RO);
-
-	debug_checkwx();
 }
 
-static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
-				      pgprot_t prot, struct vm_struct *vma,
-				      int flags, unsigned long vm_flags)
+static void __init declare_vma(struct vm_struct *vma,
+			       void *va_start, void *va_end,
+			       unsigned long vm_flags)
 {
 	phys_addr_t pa_start = __pa_symbol(va_start);
 	unsigned long size = va_end - va_start;
@@ -546,9 +694,6 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
 	BUG_ON(!PAGE_ALIGNED(pa_start));
 	BUG_ON(!PAGE_ALIGNED(size));
 
-	__create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot,
-			     early_pgtable_alloc, flags);
-
 	if (!(vm_flags & VM_NO_GUARD))
 		size += PAGE_SIZE;
 
@@ -561,28 +706,20 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
 	vm_area_add_early(vma);
 }
 
-static int __init parse_rodata(char *arg)
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static pgprot_t kernel_exec_prot(void)
 {
-	int ret = strtobool(arg, &rodata_enabled);
-	if (!ret) {
-		rodata_full = false;
-		return 0;
-	}
-
-	/* permit 'full' in addition to boolean options */
-	if (strcmp(arg, "full"))
-		return -EINVAL;
-
-	rodata_enabled = true;
-	rodata_full = true;
-	return 0;
+	return rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
 }
-early_param("rodata", parse_rodata);
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static int __init map_entry_trampoline(void)
 {
-	pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+	int i;
+
+	if (!arm64_kernel_unmapped_at_el0())
+		return 0;
+
+	pgprot_t prot = kernel_exec_prot();
 	phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
 
 	/* The trampoline is always mapped and can therefore be global */
@@ -590,18 +727,18 @@ static int __init map_entry_trampoline(void)
 
 	/* Map only the text into the trampoline page table */
 	memset(tramp_pg_dir, 0, PGD_SIZE);
-	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
-			     prot, __pgd_pgtable_alloc, 0);
+	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
+			     entry_tramp_text_size(), prot,
+			     __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS);
 
 	/* Map both the text and data into the kernel page table */
-	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
-		extern char __entry_tramp_data_start[];
+	for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
+		__set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
+			     pa_start + i * PAGE_SIZE, prot);
 
-		__set_fixmap(FIX_ENTRY_TRAMP_DATA,
-			     __pa_symbol(__entry_tramp_data_start),
-			     PAGE_KERNEL_RO);
-	}
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		__set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
+			     pa_start + i * PAGE_SIZE, PAGE_KERNEL_RO);
 
 	return 0;
 }
@@ -609,349 +746,439 @@ core_initcall(map_entry_trampoline);
 #endif
 
 /*
- * Create fine-grained mappings for the kernel.
+ * Declare the VMA areas for the kernel
  */
-static void __init map_kernel(pgd_t *pgdp)
+static void __init declare_kernel_vmas(void)
 {
-	static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext,
-				vmlinux_initdata, vmlinux_data;
+	static struct vm_struct vmlinux_seg[KERNEL_SEGMENT_COUNT];
 
-	/*
-	 * External debuggers may need to write directly to the text
-	 * mapping to install SW breakpoints. Allow this (only) when
-	 * explicitly requested with rodata=off.
-	 */
-	pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+	declare_vma(&vmlinux_seg[0], _stext, _etext, VM_NO_GUARD);
+	declare_vma(&vmlinux_seg[1], __start_rodata, __inittext_begin, VM_NO_GUARD);
+	declare_vma(&vmlinux_seg[2], __inittext_begin, __inittext_end, VM_NO_GUARD);
+	declare_vma(&vmlinux_seg[3], __initdata_begin, __initdata_end, VM_NO_GUARD);
+	declare_vma(&vmlinux_seg[4], _data, _end, 0);
+}
 
-	/*
-	 * Only rodata will be remapped with different permissions later on,
-	 * all other segments are allowed to use contiguous mappings.
-	 */
-	map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0,
-			   VM_NO_GUARD);
-	map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL,
-			   &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
-	map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot,
-			   &vmlinux_inittext, 0, VM_NO_GUARD);
-	map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL,
-			   &vmlinux_initdata, 0, VM_NO_GUARD);
-	map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
-
-	if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) {
-		/*
-		 * The fixmap falls in a separate pgd to the kernel, and doesn't
-		 * live in the carveout for the swapper_pg_dir. We can simply
-		 * re-use the existing dir for the fixmap.
-		 */
-		set_pgd(pgd_offset_raw(pgdp, FIXADDR_START),
-			READ_ONCE(*pgd_offset_k(FIXADDR_START)));
-	} else if (CONFIG_PGTABLE_LEVELS > 3) {
-		pgd_t *bm_pgdp;
-		pud_t *bm_pudp;
-		/*
-		 * The fixmap shares its top level pgd entry with the kernel
-		 * mapping. This can really only occur when we are running
-		 * with 16k/4 levels, so we can simply reuse the pud level
-		 * entry instead.
-		 */
-		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		bm_pgdp = pgd_offset_raw(pgdp, FIXADDR_START);
-		bm_pudp = pud_set_fixmap_offset(bm_pgdp, FIXADDR_START);
-		pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd));
-		pud_clear_fixmap();
-	} else {
-		BUG();
-	}
+void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot,
+		    int level, pte_t *tbl, bool may_use_cont, u64 va_offset);
 
-	kasan_copy_shadow(pgdp);
-}
+static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init,
+	  kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init;
 
-void __init paging_init(void)
+static void __init create_idmap(void)
 {
-	pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
+	u64 start = __pa_symbol(__idmap_text_start);
+	u64 end   = __pa_symbol(__idmap_text_end);
+	u64 ptep  = __pa_symbol(idmap_ptes);
 
-	map_kernel(pgdp);
-	map_mem(pgdp);
+	__pi_map_range(&ptep, start, end, start, PAGE_KERNEL_ROX,
+		       IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false,
+		       __phys_to_virt(ptep) - ptep);
 
-	pgd_clear_fixmap();
+	if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings) {
+		extern u32 __idmap_kpti_flag;
+		u64 pa = __pa_symbol(&__idmap_kpti_flag);
 
-	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
-	init_mm.pgd = swapper_pg_dir;
+		/*
+		 * The KPTI G-to-nG conversion code needs a read-write mapping
+		 * of its synchronization flag in the ID map.
+		 */
+		ptep = __pa_symbol(kpti_ptes);
+		__pi_map_range(&ptep, pa, pa + sizeof(u32), pa, PAGE_KERNEL,
+			       IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false,
+			       __phys_to_virt(ptep) - ptep);
+	}
+}
 
-	memblock_free(__pa_symbol(init_pg_dir),
-		      __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
+void __init paging_init(void)
+{
+	map_mem(swapper_pg_dir);
 
 	memblock_allow_resize();
+
+	create_idmap();
+	declare_kernel_vmas();
 }
 
-/*
- * Check whether a kernel address is valid (derived from arch/x86/).
- */
-int kern_addr_valid(unsigned long addr)
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_hotplug_page_range(struct page *page, size_t size,
+				    struct vmem_altmap *altmap)
 {
-	pgd_t *pgdp;
-	pud_t *pudp, pud;
-	pmd_t *pmdp, pmd;
-	pte_t *ptep, pte;
-
-	if ((((long)addr) >> VA_BITS) != -1UL)
-		return 0;
+	if (altmap) {
+		vmem_altmap_free(altmap, size >> PAGE_SHIFT);
+	} else {
+		WARN_ON(PageReserved(page));
+		free_pages((unsigned long)page_address(page), get_order(size));
+	}
+}
 
-	pgdp = pgd_offset_k(addr);
-	if (pgd_none(READ_ONCE(*pgdp)))
-		return 0;
+static void free_hotplug_pgtable_page(struct page *page)
+{
+	free_hotplug_page_range(page, PAGE_SIZE, NULL);
+}
 
-	pudp = pud_offset(pgdp, addr);
-	pud = READ_ONCE(*pudp);
-	if (pud_none(pud))
-		return 0;
+static bool pgtable_range_aligned(unsigned long start, unsigned long end,
+				  unsigned long floor, unsigned long ceiling,
+				  unsigned long mask)
+{
+	start &= mask;
+	if (start < floor)
+		return false;
 
-	if (pud_sect(pud))
-		return pfn_valid(pud_pfn(pud));
+	if (ceiling) {
+		ceiling &= mask;
+		if (!ceiling)
+			return false;
+	}
 
-	pmdp = pmd_offset(pudp, addr);
-	pmd = READ_ONCE(*pmdp);
-	if (pmd_none(pmd))
-		return 0;
+	if (end - 1 > ceiling - 1)
+		return false;
+	return true;
+}
 
-	if (pmd_sect(pmd))
-		return pfn_valid(pmd_pfn(pmd));
+static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
+{
+	pte_t *ptep, pte;
 
-	ptep = pte_offset_kernel(pmdp, addr);
-	pte = READ_ONCE(*ptep);
-	if (pte_none(pte))
-		return 0;
+	do {
+		ptep = pte_offset_kernel(pmdp, addr);
+		pte = __ptep_get(ptep);
+		if (pte_none(pte))
+			continue;
 
-	return pfn_valid(pte_pfn(pte));
+		WARN_ON(!pte_present(pte));
+		__pte_clear(&init_mm, addr, ptep);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+		if (free_mapped)
+			free_hotplug_page_range(pte_page(pte),
+						PAGE_SIZE, altmap);
+	} while (addr += PAGE_SIZE, addr < end);
 }
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#if !ARM64_SWAPPER_USES_SECTION_MAPS
-int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
-		struct vmem_altmap *altmap)
-{
-	return vmemmap_populate_basepages(start, end, node);
-}
-#else	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
-int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
-		struct vmem_altmap *altmap)
+
+static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
 {
-	unsigned long addr = start;
 	unsigned long next;
-	pgd_t *pgdp;
-	pud_t *pudp;
-	pmd_t *pmdp;
+	pmd_t *pmdp, pmd;
 
 	do {
 		next = pmd_addr_end(addr, end);
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_none(pmd))
+			continue;
 
-		pgdp = vmemmap_pgd_populate(addr, node);
-		if (!pgdp)
-			return -ENOMEM;
+		WARN_ON(!pmd_present(pmd));
+		if (pmd_sect(pmd)) {
+			pmd_clear(pmdp);
 
-		pudp = vmemmap_pud_populate(pgdp, addr, node);
-		if (!pudp)
-			return -ENOMEM;
+			/*
+			 * One TLBI should be sufficient here as the PMD_SIZE
+			 * range is mapped with a single block entry.
+			 */
+			flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+			if (free_mapped)
+				free_hotplug_page_range(pmd_page(pmd),
+							PMD_SIZE, altmap);
+			continue;
+		}
+		WARN_ON(!pmd_table(pmd));
+		unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap);
+	} while (addr = next, addr < end);
+}
 
-		pmdp = pmd_offset(pudp, addr);
-		if (pmd_none(READ_ONCE(*pmdp))) {
-			void *p = NULL;
+static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
+{
+	unsigned long next;
+	pud_t *pudp, pud;
 
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
-			if (!p)
-				return -ENOMEM;
+	do {
+		next = pud_addr_end(addr, end);
+		pudp = pud_offset(p4dp, addr);
+		pud = READ_ONCE(*pudp);
+		if (pud_none(pud))
+			continue;
 
-			pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
-		} else
-			vmemmap_verify((pte_t *)pmdp, node, addr, next);
-	} while (addr = next, addr != end);
+		WARN_ON(!pud_present(pud));
+		if (pud_sect(pud)) {
+			pud_clear(pudp);
 
-	return 0;
-}
-#endif	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
-void vmemmap_free(unsigned long start, unsigned long end,
-		struct vmem_altmap *altmap)
-{
+			/*
+			 * One TLBI should be sufficient here as the PUD_SIZE
+			 * range is mapped with a single block entry.
+			 */
+			flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+			if (free_mapped)
+				free_hotplug_page_range(pud_page(pud),
+							PUD_SIZE, altmap);
+			continue;
+		}
+		WARN_ON(!pud_table(pud));
+		unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap);
+	} while (addr = next, addr < end);
 }
-#endif	/* CONFIG_SPARSEMEM_VMEMMAP */
 
-static inline pud_t * fixmap_pud(unsigned long addr)
+static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
 {
-	pgd_t *pgdp = pgd_offset_k(addr);
-	pgd_t pgd = READ_ONCE(*pgdp);
+	unsigned long next;
+	p4d_t *p4dp, p4d;
 
-	BUG_ON(pgd_none(pgd) || pgd_bad(pgd));
+	do {
+		next = p4d_addr_end(addr, end);
+		p4dp = p4d_offset(pgdp, addr);
+		p4d = READ_ONCE(*p4dp);
+		if (p4d_none(p4d))
+			continue;
 
-	return pud_offset_kimg(pgdp, addr);
+		WARN_ON(!p4d_present(p4d));
+		unmap_hotplug_pud_range(p4dp, addr, next, free_mapped, altmap);
+	} while (addr = next, addr < end);
 }
 
-static inline pmd_t * fixmap_pmd(unsigned long addr)
+static void unmap_hotplug_range(unsigned long addr, unsigned long end,
+				bool free_mapped, struct vmem_altmap *altmap)
 {
-	pud_t *pudp = fixmap_pud(addr);
-	pud_t pud = READ_ONCE(*pudp);
+	unsigned long next;
+	pgd_t *pgdp, pgd;
 
-	BUG_ON(pud_none(pud) || pud_bad(pud));
+	/*
+	 * altmap can only be used as vmemmap mapping backing memory.
+	 * In case the backing memory itself is not being freed, then
+	 * altmap is irrelevant. Warn about this inconsistency when
+	 * encountered.
+	 */
+	WARN_ON(!free_mapped && altmap);
 
-	return pmd_offset_kimg(pudp, addr);
-}
+	do {
+		next = pgd_addr_end(addr, end);
+		pgdp = pgd_offset_k(addr);
+		pgd = READ_ONCE(*pgdp);
+		if (pgd_none(pgd))
+			continue;
 
-static inline pte_t * fixmap_pte(unsigned long addr)
-{
-	return &bm_pte[pte_index(addr)];
+		WARN_ON(!pgd_present(pgd));
+		unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped, altmap);
+	} while (addr = next, addr < end);
 }
 
-/*
- * The p*d_populate functions call virt_to_phys implicitly so they can't be used
- * directly on kernel symbols (bm_p*d). This function is called too early to use
- * lm_alias so __p*d_populate functions must be used to populate with the
- * physical address from __pa_symbol.
- */
-void __init early_fixmap_init(void)
+static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
 {
-	pgd_t *pgdp, pgd;
-	pud_t *pudp;
-	pmd_t *pmdp;
-	unsigned long addr = FIXADDR_START;
+	pte_t *ptep, pte;
+	unsigned long i, start = addr;
+
+	do {
+		ptep = pte_offset_kernel(pmdp, addr);
+		pte = __ptep_get(ptep);
 
-	pgdp = pgd_offset_k(addr);
-	pgd = READ_ONCE(*pgdp);
-	if (CONFIG_PGTABLE_LEVELS > 3 &&
-	    !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) {
 		/*
-		 * We only end up here if the kernel mapping and the fixmap
-		 * share the top level pgd entry, which should only happen on
-		 * 16k/4 levels configurations.
+		 * This is just a sanity check here which verifies that
+		 * pte clearing has been done by earlier unmap loops.
 		 */
-		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pudp = pud_offset_kimg(pgdp, addr);
-	} else {
-		if (pgd_none(pgd))
-			__pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
-		pudp = fixmap_pud(addr);
-	}
-	if (pud_none(READ_ONCE(*pudp)))
-		__pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
-	pmdp = fixmap_pmd(addr);
-	__pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
+		WARN_ON(!pte_none(pte));
+	} while (addr += PAGE_SIZE, addr < end);
+
+	if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK))
+		return;
 
 	/*
-	 * The boot-ioremap range spans multiple pmds, for which
-	 * we are not prepared:
+	 * Check whether we can free the pte page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
 	 */
-	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
-		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
-
-	if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
-	     || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
-		WARN_ON(1);
-		pr_warn("pmdp %p != %p, %p\n",
-			pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
-			fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
-		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);
+	ptep = pte_offset_kernel(pmdp, 0UL);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		if (!pte_none(__ptep_get(&ptep[i])))
+			return;
 	}
+
+	pmd_clear(pmdp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(ptep));
 }
 
-/*
- * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we
- * ever need to use IPIs for TLB broadcasting, then we're in trouble here.
- */
-void __set_fixmap(enum fixed_addresses idx,
-			       phys_addr_t phys, pgprot_t flags)
+static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
 {
-	unsigned long addr = __fix_to_virt(idx);
-	pte_t *ptep;
+	pmd_t *pmdp, pmd;
+	unsigned long i, next, start = addr;
 
-	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
+	do {
+		next = pmd_addr_end(addr, end);
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_none(pmd))
+			continue;
 
-	ptep = fixmap_pte(addr);
+		WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
+		free_empty_pte_table(pmdp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
 
-	if (pgprot_val(flags)) {
-		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
-	} else {
-		pte_clear(&init_mm, addr, ptep);
-		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
+	if (CONFIG_PGTABLE_LEVELS <= 2)
+		return;
+
+	if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK))
+		return;
+
+	/*
+	 * Check whether we can free the pmd page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
+	 */
+	pmdp = pmd_offset(pudp, 0UL);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(READ_ONCE(pmdp[i])))
+			return;
 	}
+
+	pud_clear(pudp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(pmdp));
 }
 
-void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
+static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
 {
-	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
-	int offset;
-	void *dt_virt;
+	pud_t *pudp, pud;
+	unsigned long i, next, start = addr;
 
-	/*
-	 * Check whether the physical FDT address is set and meets the minimum
-	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
-	 * at least 8 bytes so that we can always access the magic and size
-	 * fields of the FDT header after mapping the first chunk, double check
-	 * here if that is indeed the case.
-	 */
-	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
-	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
-		return NULL;
+	do {
+		next = pud_addr_end(addr, end);
+		pudp = pud_offset(p4dp, addr);
+		pud = READ_ONCE(*pudp);
+		if (pud_none(pud))
+			continue;
+
+		WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
+		free_empty_pmd_table(pudp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+
+	if (!pgtable_l4_enabled())
+		return;
+
+	if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK))
+		return;
 
 	/*
-	 * Make sure that the FDT region can be mapped without the need to
-	 * allocate additional translation table pages, so that it is safe
-	 * to call create_mapping_noalloc() this early.
-	 *
-	 * On 64k pages, the FDT will be mapped using PTEs, so we need to
-	 * be in the same PMD as the rest of the fixmap.
-	 * On 4k pages, we'll use section mappings for the FDT so we only
-	 * have to be in the same PUD.
+	 * Check whether we can free the pud page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
 	 */
-	BUILD_BUG_ON(dt_virt_base % SZ_2M);
+	pudp = pud_offset(p4dp, 0UL);
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (!pud_none(READ_ONCE(pudp[i])))
+			return;
+	}
 
-	BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT !=
-		     __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT);
+	p4d_clear(p4dp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(pudp));
+}
 
-	offset = dt_phys % SWAPPER_BLOCK_SIZE;
-	dt_virt = (void *)dt_virt_base + offset;
+static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	p4d_t *p4dp, p4d;
+	unsigned long i, next, start = addr;
 
-	/* map the first chunk so we can read the size from the header */
-	create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE),
-			dt_virt_base, SWAPPER_BLOCK_SIZE, prot);
+	do {
+		next = p4d_addr_end(addr, end);
+		p4dp = p4d_offset(pgdp, addr);
+		p4d = READ_ONCE(*p4dp);
+		if (p4d_none(p4d))
+			continue;
 
-	if (fdt_magic(dt_virt) != FDT_MAGIC)
-		return NULL;
+		WARN_ON(!p4d_present(p4d));
+		free_empty_pud_table(p4dp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
 
-	*size = fdt_totalsize(dt_virt);
-	if (*size > MAX_FDT_SIZE)
-		return NULL;
+	if (!pgtable_l5_enabled())
+		return;
 
-	if (offset + *size > SWAPPER_BLOCK_SIZE)
-		create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
-			       round_up(offset + *size, SWAPPER_BLOCK_SIZE), prot);
+	if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK))
+		return;
 
-	return dt_virt;
+	/*
+	 * Check whether we can free the p4d page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
+	 */
+	p4dp = p4d_offset(pgdp, 0UL);
+	for (i = 0; i < PTRS_PER_P4D; i++) {
+		if (!p4d_none(READ_ONCE(p4dp[i])))
+			return;
+	}
+
+	pgd_clear(pgdp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(p4dp));
 }
 
-int __init arch_ioremap_p4d_supported(void)
+static void free_empty_tables(unsigned long addr, unsigned long end,
+			      unsigned long floor, unsigned long ceiling)
 {
-	return 0;
+	unsigned long next;
+	pgd_t *pgdp, pgd;
+
+	do {
+		next = pgd_addr_end(addr, end);
+		pgdp = pgd_offset_k(addr);
+		pgd = READ_ONCE(*pgdp);
+		if (pgd_none(pgd))
+			continue;
+
+		WARN_ON(!pgd_present(pgd));
+		free_empty_p4d_table(pgdp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
 }
+#endif
 
-int __init arch_ioremap_pud_supported(void)
+void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node,
+			       unsigned long addr, unsigned long next)
 {
-	/*
-	 * Only 4k granule supports level 1 block mappings.
-	 * SW table walks can't handle removal of intermediate entries.
-	 */
-	return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
-	       !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+	pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
 }
 
-int __init arch_ioremap_pmd_supported(void)
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+				unsigned long addr, unsigned long next)
 {
-	/* See arch_ioremap_pud_supported() */
-	return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+	vmemmap_verify((pte_t *)pmdp, node, addr, next);
+	return 1;
 }
 
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+		struct vmem_altmap *altmap)
+{
+	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+		return vmemmap_populate_basepages(start, end, node, altmap);
+	else
+		return vmemmap_populate_hugepages(start, end, node, altmap);
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+void vmemmap_free(unsigned long start, unsigned long end,
+		struct vmem_altmap *altmap)
+{
+	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+	unmap_hotplug_range(start, end, true, altmap);
+	free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
 {
 	pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
@@ -980,6 +1207,12 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
 	return 1;
 }
 
+#ifndef __PAGETABLE_P4D_FOLDED
+void p4d_clear_huge(p4d_t *p4dp)
+{
+}
+#endif
+
 int pud_clear_huge(pud_t *pudp)
 {
 	if (!pud_sect(READ_ONCE(*pudp)))
@@ -1043,41 +1276,262 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
 	return 1;
 }
 
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
 {
-	return 0;	/* Don't attempt a block mapping */
+	unsigned long end = start + size;
+
+	WARN_ON(pgdir != init_mm.pgd);
+	WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
+
+	unmap_hotplug_range(start, end, false, NULL);
+	free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
+}
+
+struct range arch_get_mappable_range(void)
+{
+	struct range mhp_range;
+	u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+	u64 end_linear_pa = __pa(PAGE_END - 1);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		/*
+		 * Check for a wrap, it is possible because of randomized linear
+		 * mapping the start physical address is actually bigger than
+		 * the end physical address. In this case set start to zero
+		 * because [0, end_linear_pa] range must still be able to cover
+		 * all addressable physical addresses.
+		 */
+		if (start_linear_pa > end_linear_pa)
+			start_linear_pa = 0;
+	}
+
+	WARN_ON(start_linear_pa > end_linear_pa);
+
+	/*
+	 * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
+	 * accommodating both its ends but excluding PAGE_END. Max physical
+	 * range which can be mapped inside this linear mapping range, must
+	 * also be derived from its end points.
+	 */
+	mhp_range.start = start_linear_pa;
+	mhp_range.end =  end_linear_pa;
+
+	return mhp_range;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size,
-			struct mhp_restrictions *restrictions)
+		    struct mhp_params *params)
 {
-	int flags = 0;
+	int ret, flags = NO_EXEC_MAPPINGS;
 
-	if (rodata_full || debug_pagealloc_enabled())
-		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+	VM_BUG_ON(!mhp_range_allowed(start, size, true));
+
+	if (can_set_direct_map())
+		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
-			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
+			     size, params->pgprot, __pgd_pgtable_alloc,
+			     flags);
 
 	memblock_clear_nomap(start, size);
 
-	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
-			   restrictions);
+	ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
+			   params);
+	if (ret)
+		__remove_pgd_mapping(swapper_pg_dir,
+				     __phys_to_virt(start), size);
+	else {
+		max_pfn = PFN_UP(start + size);
+		max_low_pfn = max_pfn;
+	}
+
+	return ret;
 }
-void arch_remove_memory(int nid, u64 start, u64 size,
-			struct vmem_altmap *altmap)
+
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
+	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
+}
+
+/*
+ * This memory hotplug notifier helps prevent boot memory from being
+ * inadvertently removed as it blocks pfn range offlining process in
+ * __offline_pages(). Hence this prevents both offlining as well as
+ * removal process for boot memory which is initially always online.
+ * In future if and when boot memory could be removed, this notifier
+ * should be dropped and free_hotplug_page_range() should handle any
+ * reserved pages allocated during boot.
+ */
+static int prevent_bootmem_remove_notifier(struct notifier_block *nb,
+					   unsigned long action, void *data)
+{
+	struct mem_section *ms;
+	struct memory_notify *arg = data;
+	unsigned long end_pfn = arg->start_pfn + arg->nr_pages;
+	unsigned long pfn = arg->start_pfn;
+
+	if ((action != MEM_GOING_OFFLINE) && (action != MEM_OFFLINE))
+		return NOTIFY_OK;
+
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long start = PFN_PHYS(pfn);
+		unsigned long end = start + (1UL << PA_SECTION_SHIFT);
+
+		ms = __pfn_to_section(pfn);
+		if (!early_section(ms))
+			continue;
+
+		if (action == MEM_GOING_OFFLINE) {
+			/*
+			 * Boot memory removal is not supported. Prevent
+			 * it via blocking any attempted offline request
+			 * for the boot memory and just report it.
+			 */
+			pr_warn("Boot memory [%lx %lx] offlining attempted\n", start, end);
+			return NOTIFY_BAD;
+		} else if (action == MEM_OFFLINE) {
+			/*
+			 * This should have never happened. Boot memory
+			 * offlining should have been prevented by this
+			 * very notifier. Probably some memory removal
+			 * procedure might have changed which would then
+			 * require further debug.
+			 */
+			pr_err("Boot memory [%lx %lx] offlined\n", start, end);
+
+			/*
+			 * Core memory hotplug does not process a return
+			 * code from the notifier for MEM_OFFLINE events.
+			 * The error condition has been reported. Return
+			 * from here as if ignored.
+			 */
+			return NOTIFY_DONE;
+		}
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block prevent_bootmem_remove_nb = {
+	.notifier_call = prevent_bootmem_remove_notifier,
+};
+
+/*
+ * This ensures that boot memory sections on the platform are online
+ * from early boot. Memory sections could not be prevented from being
+ * offlined, unless for some reason they are not online to begin with.
+ * This helps validate the basic assumption on which the above memory
+ * event notifier works to prevent boot memory section offlining and
+ * its possible removal.
+ */
+static void validate_bootmem_online(void)
+{
+	phys_addr_t start, end, addr;
+	struct mem_section *ms;
+	u64 i;
+
 	/*
-	 * FIXME: Cleanup page tables (also in arch_add_memory() in case
-	 * adding fails). Until then, this function should only be used
-	 * during memory hotplug (adding memory), not for memory
-	 * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
-	 * unlocked yet.
+	 * Scanning across all memblock might be expensive
+	 * on some big memory systems. Hence enable this
+	 * validation only with DEBUG_VM.
 	 */
-	__remove_pages(start_pfn, nr_pages, altmap);
+	if (!IS_ENABLED(CONFIG_DEBUG_VM))
+		return;
+
+	for_each_mem_range(i, &start, &end) {
+		for (addr = start; addr < end; addr += (1UL << PA_SECTION_SHIFT)) {
+			ms = __pfn_to_section(PHYS_PFN(addr));
+
+			/*
+			 * All memory ranges in the system at this point
+			 * should have been marked as early sections.
+			 */
+			WARN_ON(!early_section(ms));
+
+			/*
+			 * Memory notifier mechanism here to prevent boot
+			 * memory offlining depends on the fact that each
+			 * early section memory on the system is initially
+			 * online. Otherwise a given memory section which
+			 * is already offline will be overlooked and can
+			 * be removed completely. Call out such sections.
+			 */
+			if (!online_section(ms))
+				pr_err("Boot memory [%llx %llx] is offline, can be removed\n",
+					addr, addr + (1UL << PA_SECTION_SHIFT));
+		}
+	}
+}
+
+static int __init prevent_bootmem_remove_init(void)
+{
+	int ret = 0;
+
+	if (!IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+		return ret;
+
+	validate_bootmem_online();
+	ret = register_memory_notifier(&prevent_bootmem_remove_nb);
+	if (ret)
+		pr_err("%s: Notifier registration failed %d\n", __func__, ret);
+
+	return ret;
 }
+early_initcall(prevent_bootmem_remove_init);
 #endif
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
+		/*
+		 * Break-before-make (BBM) is required for all user space mappings
+		 * when the permission changes from executable to non-executable
+		 * in cases where cpu is affected with errata #2645198.
+		 */
+		if (pte_user_exec(ptep_get(ptep)))
+			return ptep_clear_flush(vma, addr, ptep);
+	}
+	return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+			     pte_t old_pte, pte_t pte)
+{
+	set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+
+/*
+ * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
+ * avoiding the possibility of conflicting TLB entries being allocated.
+ */
+void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp)
+{
+	typedef void (ttbr_replace_func)(phys_addr_t);
+	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
+	ttbr_replace_func *replace_phys;
+	unsigned long daif;
+
+	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
+	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
+
+	if (cnp)
+		ttbr1 |= TTBR_CNP_BIT;
+
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
+
+	cpu_install_idmap();
+
+	/*
+	 * We really don't want to take *any* exceptions while TTBR1 is
+	 * in the process of being replaced so mask everything.
+	 */
+	daif = local_daif_save();
+	replace_phys(ttbr1);
+	local_daif_restore(daif);
+
+	cpu_uninstall_idmap();
+}