mm: remove rb tree.

Remove the RB tree and start using the maple tree for vm_area_struct
tracking.

Drop validate_mm() calls in expand_upwards() and expand_downwards() as the
lock is not held.

Link: https://lkml.kernel.org/r/20220906194824.2110408-18-Liam.Howlett@oracle.comSigned-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: SeongJae Park <sj@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/x86/kernel/tboot.c

@@ -95,7 +95,6 @@ void __init tboot_probe(void)
 
 static pgd_t *tboot_pg_dir;
 static struct mm_struct tboot_mm = {
-	.mm_rb          = RB_ROOT,
 	.mm_mt          = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, tboot_mm.mmap_lock),
 	.pgd            = swapper_pg_dir,
 	.mm_users       = ATOMIC_INIT(2),

drivers/firmware/efi/efi.c

@@ -57,7 +57,6 @@ static unsigned long __initdata mem_reserve = EFI_INVALID_TABLE_ADDR;
 static unsigned long __initdata rt_prop = EFI_INVALID_TABLE_ADDR;
 
 struct mm_struct efi_mm = {
-	.mm_rb			= RB_ROOT,
 	.mm_mt			= MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, efi_mm.mmap_lock),
 	.mm_users		= ATOMIC_INIT(2),
 	.mm_count		= ATOMIC_INIT(1),

include/linux/mm.h

@@ -2654,8 +2654,6 @@ extern int __split_vma(struct mm_struct *, struct vm_area_struct *,
 extern int split_vma(struct mm_struct *, struct vm_area_struct *,
 	unsigned long addr, int new_below);
 extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
-extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
-	struct rb_node **, struct rb_node *);
 extern void unlink_file_vma(struct vm_area_struct *);
 extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	unsigned long addr, unsigned long len, pgoff_t pgoff,

include/linux/mm_types.h

@@ -410,19 +410,6 @@ struct vm_area_struct {
 
 	/* linked list of VM areas per task, sorted by address */
 	struct vm_area_struct *vm_next, *vm_prev;
-
-	struct rb_node vm_rb;
-
-	/*
-	 * Largest free memory gap in bytes to the left of this VMA.
-	 * Either between this VMA and vma->vm_prev, or between one of the
-	 * VMAs below us in the VMA rbtree and its ->vm_prev. This helps
-	 * get_unmapped_area find a free area of the right size.
-	 */
-	unsigned long rb_subtree_gap;
-
-	/* Second cache line starts here. */
-
 	struct mm_struct *vm_mm;	/* The address space we belong to. */
 
 	/*
@@ -488,7 +475,6 @@ struct mm_struct {
 	struct {
 		struct vm_area_struct *mmap;		/* list of VMAs */
 		struct maple_tree mm_mt;
-		struct rb_root mm_rb;
 		u64 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 		unsigned long (*get_unmapped_area) (struct file *filp,

kernel/fork.c

@@ -581,7 +581,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 					struct mm_struct *oldmm)
 {
 	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
-	struct rb_node **rb_link, *rb_parent;
 	int retval;
 	unsigned long charge = 0;
 	LIST_HEAD(uf);
@@ -608,8 +607,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	mm->exec_vm = oldmm->exec_vm;
 	mm->stack_vm = oldmm->stack_vm;
 
-	rb_link = &mm->mm_rb.rb_node;
-	rb_parent = NULL;
 	pprev = &mm->mmap;
 	retval = ksm_fork(mm, oldmm);
 	if (retval)
@@ -701,10 +698,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		tmp->vm_prev = prev;
 		prev = tmp;
 
-		__vma_link_rb(mm, tmp, rb_link, rb_parent);
-		rb_link = &tmp->vm_rb.rb_right;
-		rb_parent = &tmp->vm_rb;
-
 		/* Link the vma into the MT */
 		mas.index = tmp->vm_start;
 		mas.last = tmp->vm_end - 1;
@@ -1133,7 +1126,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	struct user_namespace *user_ns)
 {
 	mm->mmap = NULL;
-	mm->mm_rb = RB_ROOT;
 	mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
 	mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
 	mm->vmacache_seqnum = 0;

mm/init-mm.c

 // SPDX-License-Identifier: GPL-2.0
 #include <linux/mm_types.h>
-#include <linux/rbtree.h>
 #include <linux/maple_tree.h>
 #include <linux/rwsem.h>
 #include <linux/spinlock.h>
@@ -29,7 +28,6 @@
  * and size this cpu_bitmask to NR_CPUS.
  */
 struct mm_struct init_mm = {
-	.mm_rb		= RB_ROOT,
 	.mm_mt		= MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, init_mm.mmap_lock),
 	.pgd		= swapper_pg_dir,
 	.mm_users	= ATOMIC_INIT(2),

mm/nommu.c

@@ -566,9 +566,9 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas)
  */
 static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct vm_area_struct *pvma, *prev;
 	struct address_space *mapping;
-	struct rb_node **p, *parent, *rb_prev;
+	struct vm_area_struct *prev;
+	MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_end);
 
 	BUG_ON(!vma->vm_region);
 
@@ -586,42 +586,10 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 		i_mmap_unlock_write(mapping);
 	}
 
+	prev = mas_prev(&mas, 0);
+	mas_reset(&mas);
 	/* add the VMA to the tree */
-	parent = rb_prev = NULL;
-	p = &mm->mm_rb.rb_node;
-	while (*p) {
-		parent = *p;
-		pvma = rb_entry(parent, struct vm_area_struct, vm_rb);
-
-		/* sort by: start addr, end addr, VMA struct addr in that order
-		 * (the latter is necessary as we may get identical VMAs) */
-		if (vma->vm_start < pvma->vm_start)
-			p = &(*p)->rb_left;
-		else if (vma->vm_start > pvma->vm_start) {
-			rb_prev = parent;
-			p = &(*p)->rb_right;
-		} else if (vma->vm_end < pvma->vm_end)
-			p = &(*p)->rb_left;
-		else if (vma->vm_end > pvma->vm_end) {
-			rb_prev = parent;
-			p = &(*p)->rb_right;
-		} else if (vma < pvma)
-			p = &(*p)->rb_left;
-		else if (vma > pvma) {
-			rb_prev = parent;
-			p = &(*p)->rb_right;
-		} else
-			BUG();
-	}
-
-	rb_link_node(&vma->vm_rb, parent, p);
-	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
-
-	/* add VMA to the VMA list also */
-	prev = NULL;
-	if (rb_prev)
-		prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
-
+	vma_mas_store(vma, &mas);
 	__vma_link_list(mm, vma, prev);
 }
 
@@ -634,6 +602,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	struct address_space *mapping;
 	struct mm_struct *mm = vma->vm_mm;
 	struct task_struct *curr = current;
+	MA_STATE(mas, &vma->vm_mm->mm_mt, 0, 0);
 
 	mm->map_count--;
 	for (i = 0; i < VMACACHE_SIZE; i++) {
@@ -656,8 +625,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	}
 
 	/* remove from the MM's tree and list */
-	rb_erase(&vma->vm_rb, &mm->mm_rb);
-
+	vma_mas_remove(vma, &mas);
 	__vma_unlink_list(mm, vma);
 }
 
@@ -681,24 +649,19 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
 	struct vm_area_struct *vma;
+	MA_STATE(mas, &mm->mm_mt, addr, addr);
 
 	/* check the cache first */
 	vma = vmacache_find(mm, addr);
 	if (likely(vma))
 		return vma;
 
-	/* trawl the list (there may be multiple mappings in which addr
-	 * resides) */
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (vma->vm_start > addr)
-			return NULL;
-		if (vma->vm_end > addr) {
-			vmacache_update(addr, vma);
-			return vma;
-		}
-	}
+	vma = mas_walk(&mas);
 
-	return NULL;
+	if (vma)
+		vmacache_update(addr, vma);
+
+	return vma;
 }
 EXPORT_SYMBOL(find_vma);
 
@@ -730,26 +693,23 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 {
 	struct vm_area_struct *vma;
 	unsigned long end = addr + len;
+	MA_STATE(mas, &mm->mm_mt, addr, addr);
 
 	/* check the cache first */
 	vma = vmacache_find_exact(mm, addr, end);
 	if (vma)
 		return vma;
 
-	/* trawl the list (there may be multiple mappings in which addr
-	 * resides) */
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (vma->vm_start < addr)
-			continue;
-		if (vma->vm_start > addr)
-			return NULL;
-		if (vma->vm_end == end) {
-			vmacache_update(addr, vma);
-			return vma;
-		}
-	}
+	vma = mas_walk(&mas);
+	if (!vma)
+		return NULL;
+	if (vma->vm_start != addr)
+		return NULL;
+	if (vma->vm_end != end)
+		return NULL;
 
-	return NULL;
+	vmacache_update(addr, vma);
+	return vma;
 }
 
 /*
@@ -1546,6 +1506,7 @@ void exit_mmap(struct mm_struct *mm)
 		delete_vma(mm, vma);
 		cond_resched();
 	}
+	__mt_destroy(&mm->mm_mt);
 }
 
 int vm_brk(unsigned long addr, unsigned long len)

mm/util.c

@@ -288,6 +288,8 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 	vma->vm_next = next;
 	if (next)
 		next->vm_prev = vma;
+	else
+		mm->highest_vm_end = vm_end_gap(vma);
 }
 
 void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma)
@@ -300,8 +302,14 @@ void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma)
 		prev->vm_next = next;
 	else
 		mm->mmap = next;
-	if (next)
+	if (next) {
 		next->vm_prev = prev;
+	} else {
+		if (prev)
+			mm->highest_vm_end = vm_end_gap(prev);
+		else
+			mm->highest_vm_end = 0;
+	}
 }
 
 /* Check if the vma is being used as a stack by this task */