1 files changed, 491 insertions, 131 deletions

diff --git a/mm/mremap.c b/mm/mremap.c
index af363063ea23..e465ffe279bb 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/hugetlb.h>
 #include <linux/shm.h>
 #include <linux/ksm.h>
@@ -22,20 +23,20 @@
 #include <linux/syscalls.h>
 #include <linux/mmu_notifier.h>
 #include <linux/uaccess.h>
-#include <linux/mm-arch-hooks.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/mempolicy.h>
 
 #include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/pgalloc.h>
 
 #include "internal.h"
 
-static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
+static pud_t *get_old_pud(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd_none_or_clear_bad(pgd))
@@ -49,6 +50,18 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	if (pud_none_or_clear_bad(pud))
 		return NULL;
 
+	return pud;
+}
+
+static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = get_old_pud(mm, addr);
+	if (!pud)
+		return NULL;
+
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return NULL;
@@ -56,19 +69,27 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	return pmd;
 }
 
-static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+static pud_t *alloc_new_pud(struct mm_struct *mm, struct vm_area_struct *vma,
 			    unsigned long addr)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	p4d = p4d_alloc(mm, pgd, addr);
 	if (!p4d)
 		return NULL;
-	pud = pud_alloc(mm, p4d, addr);
+
+	return pud_alloc(mm, p4d, addr);
+}
+
+static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			    unsigned long addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = alloc_new_pud(mm, vma, addr);
 	if (!pud)
 		return NULL;
 
@@ -133,7 +154,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	 * such races:
 	 *
 	 * - During exec() shift_arg_pages(), we use a specially tagged vma
-	 *   which rmap call sites look for using is_vma_temporary_stack().
+	 *   which rmap call sites look for using vma_is_temporary_stack().
 	 *
 	 * - During mremap(), new_vma is often known to be placed after vma
 	 *   in rmap traversal order. This ensures rmap will always observe
@@ -146,7 +167,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 
 	/*
 	 * We don't have to worry about the ordering of src and dst
-	 * pte locks because exclusive mmap_sem prevents deadlock.
+	 * pte locks because exclusive mmap_lock prevents deadlock.
 	 */
 	old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl);
 	new_pte = pte_offset_map(new_pmd, new_addr);
@@ -191,29 +212,54 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		drop_rmap_locks(vma);
 }
 
+#ifndef arch_supports_page_table_move
+#define arch_supports_page_table_move arch_supports_page_table_move
+static inline bool arch_supports_page_table_move(void)
+{
+	return IS_ENABLED(CONFIG_HAVE_MOVE_PMD) ||
+		IS_ENABLED(CONFIG_HAVE_MOVE_PUD);
+}
+#endif
+
 #ifdef CONFIG_HAVE_MOVE_PMD
 static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
-		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t pmd;
 
-	if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK)
-	    || old_end - old_addr < PMD_SIZE)
+	if (!arch_supports_page_table_move())
 		return false;
-
 	/*
 	 * The destination pmd shouldn't be established, free_pgtables()
-	 * should have release it.
+	 * should have released it.
+	 *
+	 * However, there's a case during execve() where we use mremap
+	 * to move the initial stack, and in that case the target area
+	 * may overlap the source area (always moving down).
+	 *
+	 * If everything is PMD-aligned, that works fine, as moving
+	 * each pmd down will clear the source pmd. But if we first
+	 * have a few 4kB-only pages that get moved down, and then
+	 * hit the "now the rest is PMD-aligned, let's do everything
+	 * one pmd at a time", we will still have the old (now empty
+	 * of any 4kB pages, but still there) PMD in the page table
+	 * tree.
+	 *
+	 * Warn on it once - because we really should try to figure
+	 * out how to do this better - but then say "I won't move
+	 * this pmd".
+	 *
+	 * One alternative might be to just unmap the target pmd at
+	 * this point, and verify that it really is empty. We'll see.
 	 */
-	if (WARN_ON(!pmd_none(*new_pmd)))
+	if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
 		return false;
 
 	/*
 	 * We don't have to worry about the ordering of src and dst
-	 * ptlocks because exclusive mmap_sem prevents deadlock.
+	 * ptlocks because exclusive mmap_lock prevents deadlock.
 	 */
 	old_ptl = pmd_lock(vma->vm_mm, old_pmd);
 	new_ptl = pmd_lockptr(mm, new_pmd);
@@ -226,8 +272,7 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 
 	VM_BUG_ON(!pmd_none(*new_pmd));
 
-	/* Set the new pmd */
-	set_pmd_at(mm, new_addr, new_pmd, pmd);
+	pmd_populate(mm, new_pmd, pmd_pgtable(pmd));
 	flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
@@ -235,77 +280,285 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 
 	return true;
 }
+#else
+static inline bool move_normal_pmd(struct vm_area_struct *vma,
+		unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd,
+		pmd_t *new_pmd)
+{
+	return false;
+}
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_HAVE_MOVE_PUD)
+static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
+		  unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
+{
+	spinlock_t *old_ptl, *new_ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	pud_t pud;
+
+	if (!arch_supports_page_table_move())
+		return false;
+	/*
+	 * The destination pud shouldn't be established, free_pgtables()
+	 * should have released it.
+	 */
+	if (WARN_ON_ONCE(!pud_none(*new_pud)))
+		return false;
+
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_lock prevents deadlock.
+	 */
+	old_ptl = pud_lock(vma->vm_mm, old_pud);
+	new_ptl = pud_lockptr(mm, new_pud);
+	if (new_ptl != old_ptl)
+		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+
+	/* Clear the pud */
+	pud = *old_pud;
+	pud_clear(old_pud);
+
+	VM_BUG_ON(!pud_none(*new_pud));
+
+	pud_populate(mm, new_pud, pud_pgtable(pud));
+	flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
+	if (new_ptl != old_ptl)
+		spin_unlock(new_ptl);
+	spin_unlock(old_ptl);
+
+	return true;
+}
+#else
+static inline bool move_normal_pud(struct vm_area_struct *vma,
+		unsigned long old_addr, unsigned long new_addr, pud_t *old_pud,
+		pud_t *new_pud)
+{
+	return false;
+}
+#endif
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static bool move_huge_pud(struct vm_area_struct *vma, unsigned long old_addr,
+			  unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
+{
+	spinlock_t *old_ptl, *new_ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	pud_t pud;
+
+	/*
+	 * The destination pud shouldn't be established, free_pgtables()
+	 * should have released it.
+	 */
+	if (WARN_ON_ONCE(!pud_none(*new_pud)))
+		return false;
+
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_lock prevents deadlock.
+	 */
+	old_ptl = pud_lock(vma->vm_mm, old_pud);
+	new_ptl = pud_lockptr(mm, new_pud);
+	if (new_ptl != old_ptl)
+		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+
+	/* Clear the pud */
+	pud = *old_pud;
+	pud_clear(old_pud);
+
+	VM_BUG_ON(!pud_none(*new_pud));
+
+	/* Set the new pud */
+	/* mark soft_ditry when we add pud level soft dirty support */
+	set_pud_at(mm, new_addr, new_pud, pud);
+	flush_pud_tlb_range(vma, old_addr, old_addr + HPAGE_PUD_SIZE);
+	if (new_ptl != old_ptl)
+		spin_unlock(new_ptl);
+	spin_unlock(old_ptl);
+
+	return true;
+}
+#else
+static bool move_huge_pud(struct vm_area_struct *vma, unsigned long old_addr,
+			  unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
+{
+	WARN_ON_ONCE(1);
+	return false;
+
+}
 #endif
 
+enum pgt_entry {
+	NORMAL_PMD,
+	HPAGE_PMD,
+	NORMAL_PUD,
+	HPAGE_PUD,
+};
+
+/*
+ * Returns an extent of the corresponding size for the pgt_entry specified if
+ * valid. Else returns a smaller extent bounded by the end of the source and
+ * destination pgt_entry.
+ */
+static __always_inline unsigned long get_extent(enum pgt_entry entry,
+			unsigned long old_addr, unsigned long old_end,
+			unsigned long new_addr)
+{
+	unsigned long next, extent, mask, size;
+
+	switch (entry) {
+	case HPAGE_PMD:
+	case NORMAL_PMD:
+		mask = PMD_MASK;
+		size = PMD_SIZE;
+		break;
+	case HPAGE_PUD:
+	case NORMAL_PUD:
+		mask = PUD_MASK;
+		size = PUD_SIZE;
+		break;
+	default:
+		BUILD_BUG();
+		break;
+	}
+
+	next = (old_addr + size) & mask;
+	/* even if next overflowed, extent below will be ok */
+	extent = next - old_addr;
+	if (extent > old_end - old_addr)
+		extent = old_end - old_addr;
+	next = (new_addr + size) & mask;
+	if (extent > next - new_addr)
+		extent = next - new_addr;
+	return extent;
+}
+
+/*
+ * Attempts to speedup the move by moving entry at the level corresponding to
+ * pgt_entry. Returns true if the move was successful, else false.
+ */
+static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma,
+			unsigned long old_addr, unsigned long new_addr,
+			void *old_entry, void *new_entry, bool need_rmap_locks)
+{
+	bool moved = false;
+
+	/* See comment in move_ptes() */
+	if (need_rmap_locks)
+		take_rmap_locks(vma);
+
+	switch (entry) {
+	case NORMAL_PMD:
+		moved = move_normal_pmd(vma, old_addr, new_addr, old_entry,
+					new_entry);
+		break;
+	case NORMAL_PUD:
+		moved = move_normal_pud(vma, old_addr, new_addr, old_entry,
+					new_entry);
+		break;
+	case HPAGE_PMD:
+		moved = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+			move_huge_pmd(vma, old_addr, new_addr, old_entry,
+				      new_entry);
+		break;
+	case HPAGE_PUD:
+		moved = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+			move_huge_pud(vma, old_addr, new_addr, old_entry,
+				      new_entry);
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	if (need_rmap_locks)
+		drop_rmap_locks(vma);
+
+	return moved;
+}
+
 unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
 		bool need_rmap_locks)
 {
-	unsigned long extent, next, old_end;
+	unsigned long extent, old_end;
 	struct mmu_notifier_range range;
 	pmd_t *old_pmd, *new_pmd;
+	pud_t *old_pud, *new_pud;
+
+	if (!len)
+		return 0;
 
 	old_end = old_addr + len;
-	flush_cache_range(vma, old_addr, old_end);
 
+	if (is_vm_hugetlb_page(vma))
+		return move_hugetlb_page_tables(vma, new_vma, old_addr,
+						new_addr, len);
+
+	flush_cache_range(vma, old_addr, old_end);
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
 				old_addr, old_end);
 	mmu_notifier_invalidate_range_start(&range);
 
 	for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
 		cond_resched();
-		next = (old_addr + PMD_SIZE) & PMD_MASK;
-		/* even if next overflowed, extent below will be ok */
-		extent = next - old_addr;
-		if (extent > old_end - old_addr)
-			extent = old_end - old_addr;
+		/*
+		 * If extent is PUD-sized try to speed up the move by moving at the
+		 * PUD level if possible.
+		 */
+		extent = get_extent(NORMAL_PUD, old_addr, old_end, new_addr);
+
+		old_pud = get_old_pud(vma->vm_mm, old_addr);
+		if (!old_pud)
+			continue;
+		new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr);
+		if (!new_pud)
+			break;
+		if (pud_trans_huge(*old_pud) || pud_devmap(*old_pud)) {
+			if (extent == HPAGE_PUD_SIZE) {
+				move_pgt_entry(HPAGE_PUD, vma, old_addr, new_addr,
+					       old_pud, new_pud, need_rmap_locks);
+				/* We ignore and continue on error? */
+				continue;
+			}
+		} else if (IS_ENABLED(CONFIG_HAVE_MOVE_PUD) && extent == PUD_SIZE) {
+
+			if (move_pgt_entry(NORMAL_PUD, vma, old_addr, new_addr,
+					   old_pud, new_pud, true))
+				continue;
+		}
+
+		extent = get_extent(NORMAL_PMD, old_addr, old_end, new_addr);
 		old_pmd = get_old_pmd(vma->vm_mm, old_addr);
 		if (!old_pmd)
 			continue;
 		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
-		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd)) {
-			if (extent == HPAGE_PMD_SIZE) {
-				bool moved;
-				/* See comment in move_ptes() */
-				if (need_rmap_locks)
-					take_rmap_locks(vma);
-				moved = move_huge_pmd(vma, old_addr, new_addr,
-						    old_end, old_pmd, new_pmd);
-				if (need_rmap_locks)
-					drop_rmap_locks(vma);
-				if (moved)
-					continue;
-			}
+		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) ||
+		    pmd_devmap(*old_pmd)) {
+			if (extent == HPAGE_PMD_SIZE &&
+			    move_pgt_entry(HPAGE_PMD, vma, old_addr, new_addr,
+					   old_pmd, new_pmd, need_rmap_locks))
+				continue;
 			split_huge_pmd(vma, old_pmd, old_addr);
 			if (pmd_trans_unstable(old_pmd))
 				continue;
-		} else if (extent == PMD_SIZE) {
-#ifdef CONFIG_HAVE_MOVE_PMD
+		} else if (IS_ENABLED(CONFIG_HAVE_MOVE_PMD) &&
+			   extent == PMD_SIZE) {
 			/*
 			 * If the extent is PMD-sized, try to speed the move by
 			 * moving at the PMD level if possible.
 			 */
-			bool moved;
-
-			if (need_rmap_locks)
-				take_rmap_locks(vma);
-			moved = move_normal_pmd(vma, old_addr, new_addr,
-					old_end, old_pmd, new_pmd);
-			if (need_rmap_locks)
-				drop_rmap_locks(vma);
-			if (moved)
+			if (move_pgt_entry(NORMAL_PMD, vma, old_addr, new_addr,
+					   old_pmd, new_pmd, true))
 				continue;
-#endif
 		}
 
 		if (pte_alloc(new_vma->vm_mm, new_pmd))
 			break;
-		next = (new_addr + PMD_SIZE) & PMD_MASK;
-		if (extent > next - new_addr)
-			extent = next - new_addr;
 		move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
 			  new_pmd, new_addr, need_rmap_locks);
 	}
@@ -318,9 +571,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 static unsigned long move_vma(struct vm_area_struct *vma,
 		unsigned long old_addr, unsigned long old_len,
 		unsigned long new_len, unsigned long new_addr,
-		bool *locked, struct vm_userfaultfd_ctx *uf,
-		struct list_head *uf_unmap)
+		bool *locked, unsigned long flags,
+		struct vm_userfaultfd_ctx *uf, struct list_head *uf_unmap)
 {
+	long to_account = new_len - old_len;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *new_vma;
 	unsigned long vm_flags = vma->vm_flags;
@@ -329,7 +583,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	unsigned long excess = 0;
 	unsigned long hiwater_vm;
 	int split = 0;
-	int err;
+	int err = 0;
 	bool need_rmap_locks;
 
 	/*
@@ -339,6 +593,18 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (mm->map_count >= sysctl_max_map_count - 3)
 		return -ENOMEM;
 
+	if (unlikely(flags & MREMAP_DONTUNMAP))
+		to_account = new_len;
+
+	if (vma->vm_ops && vma->vm_ops->may_split) {
+		if (vma->vm_start != old_addr)
+			err = vma->vm_ops->may_split(vma, old_addr);
+		if (!err && vma->vm_end != old_addr + old_len)
+			err = vma->vm_ops->may_split(vma, old_addr + old_len);
+		if (err)
+			return err;
+	}
+
 	/*
 	 * Advise KSM to break any KSM pages in the area to be moved:
 	 * it would be confusing if they were to turn up at the new
@@ -351,11 +617,19 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (err)
 		return err;
 
+	if (vm_flags & VM_ACCOUNT) {
+		if (security_vm_enough_memory_mm(mm, to_account >> PAGE_SHIFT))
+			return -ENOMEM;
+	}
+
 	new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT);
 	new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff,
 			   &need_rmap_locks);
-	if (!new_vma)
+	if (!new_vma) {
+		if (vm_flags & VM_ACCOUNT)
+			vm_unacct_memory(to_account >> PAGE_SHIFT);
 		return -ENOMEM;
+	}
 
 	moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
 				     need_rmap_locks);
@@ -379,12 +653,14 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		new_addr = err;
 	} else {
 		mremap_userfaultfd_prep(new_vma, uf);
-		arch_remap(mm, old_addr, old_addr + old_len,
-			   new_addr, new_addr + new_len);
+	}
+
+	if (is_vm_hugetlb_page(vma)) {
+		clear_vma_resv_huge_pages(vma);
 	}
 
 	/* Conceal VM_ACCOUNT so old reservation is not undone */
-	if (vm_flags & VM_ACCOUNT) {
+	if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) {
 		vma->vm_flags &= ~VM_ACCOUNT;
 		excess = vma->vm_end - vma->vm_start - old_len;
 		if (old_addr > vma->vm_start &&
@@ -408,36 +684,55 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
 		untrack_pfn_moved(vma);
 
+	if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) {
+		/* We always clear VM_LOCKED[ONFAULT] on the old vma */
+		vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
+
+		/*
+		 * anon_vma links of the old vma is no longer needed after its page
+		 * table has been moved.
+		 */
+		if (new_vma != vma && vma->vm_start == old_addr &&
+			vma->vm_end == (old_addr + old_len))
+			unlink_anon_vmas(vma);
+
+		/* Because we won't unmap we don't need to touch locked_vm */
+		return new_addr;
+	}
+
 	if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
-		vm_unacct_memory(excess >> PAGE_SHIFT);
+		if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP))
+			vm_acct_memory(old_len >> PAGE_SHIFT);
 		excess = 0;
 	}
+
+	if (vm_flags & VM_LOCKED) {
+		mm->locked_vm += new_len >> PAGE_SHIFT;
+		*locked = true;
+	}
+
 	mm->hiwater_vm = hiwater_vm;
 
 	/* Restore VM_ACCOUNT if one or two pieces of vma left */
 	if (excess) {
 		vma->vm_flags |= VM_ACCOUNT;
 		if (split)
-			vma->vm_next->vm_flags |= VM_ACCOUNT;
-	}
-
-	if (vm_flags & VM_LOCKED) {
-		mm->locked_vm += new_len >> PAGE_SHIFT;
-		*locked = true;
+			find_vma(mm, vma->vm_end)->vm_flags |= VM_ACCOUNT;
 	}
 
 	return new_addr;
 }
 
 static struct vm_area_struct *vma_to_resize(unsigned long addr,
-	unsigned long old_len, unsigned long new_len, unsigned long *p)
+	unsigned long old_len, unsigned long new_len, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma = find_vma(mm, addr);
+	struct vm_area_struct *vma;
 	unsigned long pgoff;
 
-	if (!vma || vma->vm_start > addr)
+	vma = vma_lookup(mm, addr);
+	if (!vma)
 		return ERR_PTR(-EFAULT);
 
 	/*
@@ -453,7 +748,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (is_vm_hugetlb_page(vma))
+	if ((flags & MREMAP_DONTUNMAP) &&
+			(vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)))
 		return ERR_PTR(-EINVAL);
 
 	/* We can't remap across vm area boundaries */
@@ -472,40 +768,26 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 	if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))
 		return ERR_PTR(-EFAULT);
 
-	if (vma->vm_flags & VM_LOCKED) {
-		unsigned long locked, lock_limit;
-		locked = mm->locked_vm << PAGE_SHIFT;
-		lock_limit = rlimit(RLIMIT_MEMLOCK);
-		locked += new_len - old_len;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			return ERR_PTR(-EAGAIN);
-	}
+	if (mlock_future_check(mm, vma->vm_flags, new_len - old_len))
+		return ERR_PTR(-EAGAIN);
 
 	if (!may_expand_vm(mm, vma->vm_flags,
 				(new_len - old_len) >> PAGE_SHIFT))
 		return ERR_PTR(-ENOMEM);
 
-	if (vma->vm_flags & VM_ACCOUNT) {
-		unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
-		if (security_vm_enough_memory_mm(mm, charged))
-			return ERR_PTR(-ENOMEM);
-		*p = charged;
-	}
-
 	return vma;
 }
 
 static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 		unsigned long new_addr, unsigned long new_len, bool *locked,
-		struct vm_userfaultfd_ctx *uf,
+		unsigned long flags, struct vm_userfaultfd_ctx *uf,
 		struct list_head *uf_unmap_early,
 		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long ret = -EINVAL;
-	unsigned long charged = 0;
-	unsigned long map_flags;
+	unsigned long map_flags = 0;
 
 	if (offset_in_page(new_addr))
 		goto out;
@@ -526,7 +808,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	 * So, to avoid such scenario we can pre-compute if the whole
 	 * operation has high chances to success map-wise.
 	 * Worst-scenario case is when both vma's (new_addr and old_addr) get
-	 * split in 3 before unmaping it.
+	 * split in 3 before unmapping it.
 	 * That means 2 more maps (1 for each) to the ones we already hold.
 	 * Check whether current map count plus 2 still leads us to 4 maps below
 	 * the threshold, otherwise return -ENOMEM here to be more safe.
@@ -534,24 +816,35 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if ((mm->map_count + 2) >= sysctl_max_map_count - 3)
 		return -ENOMEM;
 
-	ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
-	if (ret)
-		goto out;
+	if (flags & MREMAP_FIXED) {
+		ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
+		if (ret)
+			goto out;
+	}
 
-	if (old_len >= new_len) {
+	if (old_len > new_len) {
 		ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap);
-		if (ret && old_len != new_len)
+		if (ret)
 			goto out;
 		old_len = new_len;
 	}
 
-	vma = vma_to_resize(addr, old_len, new_len, &charged);
+	vma = vma_to_resize(addr, old_len, new_len, flags);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;
 	}
 
-	map_flags = MAP_FIXED;
+	/* MREMAP_DONTUNMAP expands by old_len since old_len == new_len */
+	if (flags & MREMAP_DONTUNMAP &&
+		!may_expand_vm(mm, vma->vm_flags, old_len >> PAGE_SHIFT)) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (flags & MREMAP_FIXED)
+		map_flags |= MAP_FIXED;
+
 	if (vma->vm_flags & VM_MAYSHARE)
 		map_flags |= MAP_SHARED;
 
@@ -559,14 +852,14 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 				((addr - vma->vm_start) >> PAGE_SHIFT),
 				map_flags);
 	if (IS_ERR_VALUE(ret))
-		goto out1;
+		goto out;
+
+	/* We got a new mapping */
+	if (!(flags & MREMAP_FIXED))
+		new_addr = ret;
 
-	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf,
+	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, uf,
 		       uf_unmap);
-	if (!(offset_in_page(ret)))
-		goto out;
-out1:
-	vm_unacct_memory(charged);
 
 out:
 	return ret;
@@ -575,9 +868,10 @@ out:
 static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
 {
 	unsigned long end = vma->vm_end + delta;
+
 	if (end < vma->vm_end) /* overflow */
 		return 0;
-	if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */
+	if (find_vma_intersection(vma->vm_mm, vma->vm_end, end))
 		return 0;
 	if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start,
 			      0, MAP_FIXED) & ~PAGE_MASK)
@@ -599,21 +893,39 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long ret = -EINVAL;
-	unsigned long charged = 0;
 	bool locked = false;
 	bool downgraded = false;
 	struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
 	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
+	/*
+	 * There is a deliberate asymmetry here: we strip the pointer tag
+	 * from the old address but leave the new address alone. This is
+	 * for consistency with mmap(), where we prevent the creation of
+	 * aliasing mappings in userspace by leaving the tag bits of the
+	 * mapping address intact. A non-zero tag will cause the subsequent
+	 * range checks to reject the address as invalid.
+	 *
+	 * See Documentation/arm64/tagged-address-abi.rst for more information.
+	 */
 	addr = untagged_addr(addr);
 
-	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
+	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP))
 		return ret;
 
 	if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
 		return ret;
 
+	/*
+	 * MREMAP_DONTUNMAP is always a move and it does not allow resizing
+	 * in the process.
+	 */
+	if (flags & MREMAP_DONTUNMAP &&
+			(!(flags & MREMAP_MAYMOVE) || old_len != new_len))
+		return ret;
+
+
 	if (offset_in_page(addr))
 		return ret;
 
@@ -628,32 +940,61 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	if (!new_len)
 		return ret;
 
-	if (down_write_killable(&current->mm->mmap_sem))
+	if (mmap_write_lock_killable(current->mm))
 		return -EINTR;
+	vma = vma_lookup(mm, addr);
+	if (!vma) {
+		ret = -EFAULT;
+		goto out;
+	}
 
-	if (flags & MREMAP_FIXED) {
+	if (is_vm_hugetlb_page(vma)) {
+		struct hstate *h __maybe_unused = hstate_vma(vma);
+
+		old_len = ALIGN(old_len, huge_page_size(h));
+		new_len = ALIGN(new_len, huge_page_size(h));
+
+		/* addrs must be huge page aligned */
+		if (addr & ~huge_page_mask(h))
+			goto out;
+		if (new_addr & ~huge_page_mask(h))
+			goto out;
+
+		/*
+		 * Don't allow remap expansion, because the underlying hugetlb
+		 * reservation is not yet capable to handle split reservation.
+		 */
+		if (new_len > old_len)
+			goto out;
+	}
+
+	if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,
-				&locked, &uf, &uf_unmap_early, &uf_unmap);
+				&locked, flags, &uf, &uf_unmap_early,
+				&uf_unmap);
 		goto out;
 	}
 
 	/*
 	 * Always allow a shrinking remap: that just unmaps
 	 * the unnecessary pages..
-	 * __do_munmap does all the needed commit accounting, and
-	 * downgrades mmap_sem to read if so directed.
+	 * do_mas_munmap does all the needed commit accounting, and
+	 * downgrades mmap_lock to read if so directed.
 	 */
 	if (old_len >= new_len) {
 		int retval;
+		MA_STATE(mas, &mm->mm_mt, addr + new_len, addr + new_len);
 
-		retval = __do_munmap(mm, addr+new_len, old_len - new_len,
-				  &uf_unmap, true);
-		if (retval < 0 && old_len != new_len) {
+		retval = do_mas_munmap(&mas, mm, addr + new_len,
+				       old_len - new_len, &uf_unmap, true);
+		/* Returning 1 indicates mmap_lock is downgraded to read. */
+		if (retval == 1) {
+			downgraded = true;
+		} else if (retval < 0 && old_len != new_len) {
 			ret = retval;
 			goto out;
-		/* Returning 1 indicates mmap_sem is downgraded to read. */
-		} else if (retval == 1)
-			downgraded = true;
+		}
+
 		ret = addr;
 		goto out;
 	}
@@ -661,7 +1002,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	/*
 	 * Ok, we need to grow..
 	 */
-	vma = vma_to_resize(addr, old_len, new_len, &charged);
+	vma = vma_to_resize(addr, old_len, new_len, flags);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;
@@ -672,10 +1013,31 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	if (old_len == vma->vm_end - addr) {
 		/* can we just expand the current mapping? */
 		if (vma_expandable(vma, new_len - old_len)) {
-			int pages = (new_len - old_len) >> PAGE_SHIFT;
+			long pages = (new_len - old_len) >> PAGE_SHIFT;
+			unsigned long extension_start = addr + old_len;
+			unsigned long extension_end = addr + new_len;
+			pgoff_t extension_pgoff = vma->vm_pgoff + (old_len >> PAGE_SHIFT);
+
+			if (vma->vm_flags & VM_ACCOUNT) {
+				if (security_vm_enough_memory_mm(mm, pages)) {
+					ret = -ENOMEM;
+					goto out;
+				}
+			}
 
-			if (vma_adjust(vma, vma->vm_start, addr + new_len,
-				       vma->vm_pgoff, NULL)) {
+			/*
+			 * Function vma_merge() is called on the extension we are adding to
+			 * the already existing vma, vma_merge() will merge this extension with
+			 * the already existing vma (expand operation itself) and possibly also
+			 * with the next vma if it becomes adjacent to the expanded vma and
+			 * otherwise compatible.
+			 */
+			vma = vma_merge(mm, vma, extension_start, extension_end,
+					vma->vm_flags, vma->anon_vma, vma->vm_file,
+					extension_pgoff, vma_policy(vma),
+					vma->vm_userfaultfd_ctx, anon_vma_name(vma));
+			if (!vma) {
+				vm_unacct_memory(pages);
 				ret = -ENOMEM;
 				goto out;
 			}
@@ -711,21 +1073,19 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 		}
 
 		ret = move_vma(vma, addr, old_len, new_len, new_addr,
-			       &locked, &uf, &uf_unmap);
+			       &locked, flags, &uf, &uf_unmap);
 	}
 out:
-	if (offset_in_page(ret)) {
-		vm_unacct_memory(charged);
-		locked = 0;
-	}
+	if (offset_in_page(ret))
+		locked = false;
 	if (downgraded)
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 	else
-		up_write(&current->mm->mmap_sem);
+		mmap_write_unlock(current->mm);
 	if (locked && new_len > old_len)
 		mm_populate(new_addr + old_len, new_len - old_len);
 	userfaultfd_unmap_complete(mm, &uf_unmap_early);
-	mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
+	mremap_userfaultfd_complete(&uf, addr, ret, old_len);
 	userfaultfd_unmap_complete(mm, &uf_unmap);
 	return ret;
 }