Commit 524e00b3 authored by Liam R. Howlett's avatar Liam R. Howlett Committed by Andrew Morton

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: default avatarLiam R. Howlett <Liam.Howlett@Oracle.com>
Tested-by: default avatarYu 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: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 0c563f14
......@@ -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),
......
......@@ -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),
......
......@@ -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,
......
......@@ -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,
......
......@@ -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;
......
// 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),
......
......@@ -39,7 +39,6 @@
#include <linux/audit.h>
#include <linux/khugepaged.h>
#include <linux/uprobes.h>
#include <linux/rbtree_augmented.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/printk.h>
......@@ -247,93 +246,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
return origbrk;
}
static inline unsigned long vma_compute_gap(struct vm_area_struct *vma)
{
unsigned long gap, prev_end;
/*
* Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
* allow two stack_guard_gaps between them here, and when choosing
* an unmapped area; whereas when expanding we only require one.
* That's a little inconsistent, but keeps the code here simpler.
*/
gap = vm_start_gap(vma);
if (vma->vm_prev) {
prev_end = vm_end_gap(vma->vm_prev);
if (gap > prev_end)
gap -= prev_end;
else
gap = 0;
}
return gap;
}
#ifdef CONFIG_DEBUG_VM_RB
static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma)
{
unsigned long max = vma_compute_gap(vma), subtree_gap;
if (vma->vm_rb.rb_left) {
subtree_gap = rb_entry(vma->vm_rb.rb_left,
struct vm_area_struct, vm_rb)->rb_subtree_gap;
if (subtree_gap > max)
max = subtree_gap;
}
if (vma->vm_rb.rb_right) {
subtree_gap = rb_entry(vma->vm_rb.rb_right,
struct vm_area_struct, vm_rb)->rb_subtree_gap;
if (subtree_gap > max)
max = subtree_gap;
}
return max;
}
static int browse_rb(struct mm_struct *mm)
{
struct rb_root *root = &mm->mm_rb;
int i = 0, j, bug = 0;
struct rb_node *nd, *pn = NULL;
unsigned long prev = 0, pend = 0;
for (nd = rb_first(root); nd; nd = rb_next(nd)) {
struct vm_area_struct *vma;
vma = rb_entry(nd, struct vm_area_struct, vm_rb);
if (vma->vm_start < prev) {
pr_emerg("vm_start %lx < prev %lx\n",
vma->vm_start, prev);
bug = 1;
}
if (vma->vm_start < pend) {
pr_emerg("vm_start %lx < pend %lx\n",
vma->vm_start, pend);
bug = 1;
}
if (vma->vm_start > vma->vm_end) {
pr_emerg("vm_start %lx > vm_end %lx\n",
vma->vm_start, vma->vm_end);
bug = 1;
}
spin_lock(&mm->page_table_lock);
if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
pr_emerg("free gap %lx, correct %lx\n",
vma->rb_subtree_gap,
vma_compute_subtree_gap(vma));
bug = 1;
}
spin_unlock(&mm->page_table_lock);
i++;
pn = nd;
prev = vma->vm_start;
pend = vma->vm_end;
}
j = 0;
for (nd = pn; nd; nd = rb_prev(nd))
j++;
if (i != j) {
pr_emerg("backwards %d, forwards %d\n", j, i);
bug = 1;
}
return bug ? -1 : i;
}
#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
extern void mt_validate(struct maple_tree *mt);
extern void mt_dump(const struct maple_tree *mt);
......@@ -361,19 +273,25 @@ static void validate_mm_mt(struct mm_struct *mm)
(vma->vm_end - 1 != mas.last)) {
pr_emerg("issue in %s\n", current->comm);
dump_stack();
#ifdef CONFIG_DEBUG_VM
dump_vma(vma_mt);
pr_emerg("and next in rb\n");
pr_emerg("and vm_next\n");
dump_vma(vma->vm_next);
#endif
pr_emerg("mt piv: %p %lu - %lu\n", vma_mt,
mas.index, mas.last);
pr_emerg("mt vma: %p %lu - %lu\n", vma_mt,
vma_mt->vm_start, vma_mt->vm_end);
pr_emerg("rb vma: %p %lu - %lu\n", vma,
if (vma->vm_prev) {
pr_emerg("ll prev: %p %lu - %lu\n",
vma->vm_prev, vma->vm_prev->vm_start,
vma->vm_prev->vm_end);
}
pr_emerg("ll vma: %p %lu - %lu\n", vma,
vma->vm_start, vma->vm_end);
pr_emerg("rb->next = %p %lu - %lu\n", vma->vm_next,
vma->vm_next->vm_start, vma->vm_next->vm_end);
if (vma->vm_next) {
pr_emerg("ll next: %p %lu - %lu\n",
vma->vm_next, vma->vm_next->vm_start,
vma->vm_next->vm_end);
}
mt_dump(mas.tree);
if (vma_mt->vm_end != mas.last + 1) {
......@@ -396,21 +314,6 @@ static void validate_mm_mt(struct mm_struct *mm)
}
VM_BUG_ON(vma);
}
#else
#define validate_mm_mt(root) do { } while (0)
#endif
static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
{
struct rb_node *nd;
for (nd = rb_first(root); nd; nd = rb_next(nd)) {
struct vm_area_struct *vma;
vma = rb_entry(nd, struct vm_area_struct, vm_rb);
VM_BUG_ON_VMA(vma != ignore &&
vma->rb_subtree_gap != vma_compute_subtree_gap(vma),
vma);
}
}
static void validate_mm(struct mm_struct *mm)
{
......@@ -419,7 +322,10 @@ static void validate_mm(struct mm_struct *mm)
unsigned long highest_address = 0;
struct vm_area_struct *vma = mm->mmap;
validate_mm_mt(mm);
while (vma) {
#ifdef CONFIG_DEBUG_VM_RB
struct anon_vma *anon_vma = vma->anon_vma;
struct anon_vma_chain *avc;
......@@ -429,6 +335,7 @@ static void validate_mm(struct mm_struct *mm)
anon_vma_interval_tree_verify(avc);
anon_vma_unlock_read(anon_vma);
}
#endif
highest_address = vm_end_gap(vma);
vma = vma->vm_next;
......@@ -443,80 +350,13 @@ static void validate_mm(struct mm_struct *mm)
mm->highest_vm_end, highest_address);
bug = 1;
}
i = browse_rb(mm);
if (i != mm->map_count) {
if (i != -1)
pr_emerg("map_count %d rb %d\n", mm->map_count, i);
bug = 1;
}
VM_BUG_ON_MM(bug, mm);
}
#else
#define validate_mm_rb(root, ignore) do { } while (0)
#else /* !CONFIG_DEBUG_VM_MAPLE_TREE */
#define validate_mm_mt(root) do { } while (0)
#define validate_mm(mm) do { } while (0)
#endif
RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks,
struct vm_area_struct, vm_rb,
unsigned long, rb_subtree_gap, vma_compute_gap)
/*
* Update augmented rbtree rb_subtree_gap values after vma->vm_start or
* vma->vm_prev->vm_end values changed, without modifying the vma's position
* in the rbtree.
*/
static void vma_gap_update(struct vm_area_struct *vma)
{
/*
* As it turns out, RB_DECLARE_CALLBACKS_MAX() already created
* a callback function that does exactly what we want.
*/
vma_gap_callbacks_propagate(&vma->vm_rb, NULL);
}
static inline void vma_rb_insert(struct vm_area_struct *vma,
struct rb_root *root)
{
/* All rb_subtree_gap values must be consistent prior to insertion */
validate_mm_rb(root, NULL);
rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
}
static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
{
/*
* Note rb_erase_augmented is a fairly large inline function,
* so make sure we instantiate it only once with our desired
* augmented rbtree callbacks.
*/
rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
}
static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
struct rb_root *root,
struct vm_area_struct *ignore)
{
/*
* All rb_subtree_gap values must be consistent prior to erase,
* with the possible exception of
*
* a. the "next" vma being erased if next->vm_start was reduced in
* __vma_adjust() -> __vma_unlink()
* b. the vma being erased in detach_vmas_to_be_unmapped() ->
* vma_rb_erase()
*/
validate_mm_rb(root, ignore);
__vma_rb_erase(vma, root);
}
static __always_inline void vma_rb_erase(struct vm_area_struct *vma,
struct rb_root *root)
{
vma_rb_erase_ignore(vma, root, vma);
}
#endif /* CONFIG_DEBUG_VM_MAPLE_TREE */
/*
* vma has some anon_vma assigned, and is already inserted on that
......@@ -550,39 +390,26 @@ anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
}
static int find_vma_links(struct mm_struct *mm, unsigned long addr,
unsigned long end, struct vm_area_struct **pprev,
struct rb_node ***rb_link, struct rb_node **rb_parent)
/*
* range_has_overlap() - Check the @start - @end range for overlapping VMAs and
* sets up a pointer to the previous VMA
* @mm: the mm struct
* @start: the start address of the range
* @end: the end address of the range
* @pprev: the pointer to the pointer of the previous VMA
*
* Returns: True if there is an overlapping VMA, false otherwise
*/
static inline
bool range_has_overlap(struct mm_struct *mm, unsigned long start,
unsigned long end, struct vm_area_struct **pprev)
{
struct rb_node **__rb_link, *__rb_parent, *rb_prev;
mmap_assert_locked(mm);
__rb_link = &mm->mm_rb.rb_node;
rb_prev = __rb_parent = NULL;
while (*__rb_link) {
struct vm_area_struct *vma_tmp;
__rb_parent = *__rb_link;
vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);
struct vm_area_struct *existing;
if (vma_tmp->vm_end > addr) {
/* Fail if an existing vma overlaps the area */
if (vma_tmp->vm_start < end)
return -ENOMEM;
__rb_link = &__rb_parent->rb_left;
} else {
rb_prev = __rb_parent;
__rb_link = &__rb_parent->rb_right;
}
}
*pprev = NULL;
if (rb_prev)
*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
*rb_link = __rb_link;
*rb_parent = __rb_parent;
return 0;
MA_STATE(mas, &mm->mm_mt, start, start);
existing = mas_find(&mas, end - 1);
*pprev = mas_prev(&mas, 0);
return existing ? true : false;
}
/*
......@@ -609,8 +436,6 @@ static inline struct vm_area_struct *__vma_next(struct mm_struct *mm,
* @start: The start of the range.
* @len: The length of the range.
* @pprev: pointer to the pointer that will be set to previous vm_area_struct
* @rb_link: the rb_node
* @rb_parent: the parent rb_node
*
* Find all the vm_area_struct that overlap from @start to
* @end and munmap them. Set @pprev to the previous vm_area_struct.
......@@ -619,14 +444,11 @@ static inline struct vm_area_struct *__vma_next(struct mm_struct *mm,
*/
static inline int
munmap_vma_range(struct mm_struct *mm, unsigned long start, unsigned long len,
struct vm_area_struct **pprev, struct rb_node ***link,
struct rb_node **parent, struct list_head *uf)
struct vm_area_struct **pprev, struct list_head *uf)
{
while (find_vma_links(mm, start, start + len, pprev, link, parent))
while (range_has_overlap(mm, start, start + len, pprev))
if (do_munmap(mm, start, len, uf))
return -ENOMEM;
return 0;
}
......@@ -647,30 +469,6 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm,
return nr_pages;
}
void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
struct rb_node **rb_link, struct rb_node *rb_parent)
{
/* Update tracking information for the gap following the new vma. */
if (vma->vm_next)
vma_gap_update(vma->vm_next);
else
mm->highest_vm_end = vm_end_gap(vma);
/*
* vma->vm_prev wasn't known when we followed the rbtree to find the
* correct insertion point for that vma. As a result, we could not
* update the vma vm_rb parents rb_subtree_gap values on the way down.
* So, we first insert the vma with a zero rb_subtree_gap value
* (to be consistent with what we did on the way down), and then
* immediately update the gap to the correct value. Finally we
* rebalance the rbtree after all augmented values have been set.
*/
rb_link_node(&vma->vm_rb, rb_parent, rb_link);
vma->rb_subtree_gap = 0;
vma_gap_update(vma);
vma_rb_insert(vma, &mm->mm_rb);
}
static void __vma_link_file(struct vm_area_struct *vma)
{
struct file *file;
......@@ -738,18 +536,8 @@ static inline void vma_mas_szero(struct ma_state *mas, unsigned long start,
mas_store_prealloc(mas, NULL);
}
static void
__vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node **rb_link,
struct rb_node *rb_parent)
{
__vma_link_list(mm, vma, prev);
__vma_link_rb(mm, vma, rb_link, rb_parent);
}
static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node **rb_link,
struct rb_node *rb_parent)
struct vm_area_struct *prev)
{
MA_STATE(mas, &mm->mm_mt, 0, 0);
struct address_space *mapping = NULL;
......@@ -763,7 +551,7 @@ static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
}
vma_mas_store(vma, &mas);
__vma_link(mm, vma, prev, rb_link, rb_parent);
__vma_link_list(mm, vma, prev);
__vma_link_file(vma);
if (mapping)
......@@ -776,34 +564,20 @@ static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
/*
* Helper for vma_adjust() in the split_vma insert case: insert a vma into the
* mm's list and rbtree. It has already been inserted into the interval tree.
* mm's list and the mm tree. It has already been inserted into the interval tree.
*/
static void __insert_vm_struct(struct mm_struct *mm, struct ma_state *mas,
struct vm_area_struct *vma)
{
struct vm_area_struct *prev;
struct rb_node **rb_link, *rb_parent;
if (find_vma_links(mm, vma->vm_start, vma->vm_end,
&prev, &rb_link, &rb_parent))
BUG();
mas_set(mas, vma->vm_start);
prev = mas_prev(mas, 0);
vma_mas_store(vma, mas);
__vma_link_list(mm, vma, prev);
__vma_link_rb(mm, vma, rb_link, rb_parent);
mm->map_count++;
}
static __always_inline void __vma_unlink(struct mm_struct *mm,
struct vm_area_struct *vma,
struct vm_area_struct *ignore)
{
vma_rb_erase_ignore(vma, &mm->mm_rb, ignore);
__vma_unlink_list(mm, vma);
/* Kill the cache */
vmacache_invalidate(mm);
}
/*
* We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that
* is already present in an i_mmap tree without adjusting the tree.
......@@ -816,21 +590,18 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
struct vm_area_struct *expand)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *next = vma->vm_next, *orig_vma = vma;
struct vm_area_struct *next_next;
struct vm_area_struct *next_next, *next = find_vma(mm, vma->vm_end);
struct vm_area_struct *orig_vma = vma;
struct address_space *mapping = NULL;
struct rb_root_cached *root = NULL;
struct anon_vma *anon_vma = NULL;
struct file *file = vma->vm_file;
bool start_changed = false, end_changed = false;
bool vma_changed = false;
long adjust_next = 0;
int remove_next = 0;
MA_STATE(mas, &mm->mm_mt, 0, 0);
struct vm_area_struct *exporter = NULL, *importer = NULL;
validate_mm(mm);
validate_mm_mt(mm);
if (next && !insert) {
if (end >= next->vm_end) {
/*
......@@ -957,21 +728,21 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
}
if (start != vma->vm_start) {
unsigned long old_start = vma->vm_start;
if (vma->vm_start < start)
vma_mas_szero(&mas, vma->vm_start, start);
vma_changed = true;
vma->vm_start = start;
if (old_start < start)
vma_mas_szero(&mas, old_start, start);
start_changed = true;
}
if (end != vma->vm_end) {
unsigned long old_end = vma->vm_end;
if (vma->vm_end > end)
vma_mas_szero(&mas, end, vma->vm_end);
vma_changed = true;
vma->vm_end = end;
if (old_end > end)
vma_mas_szero(&mas, end, old_end);
end_changed = true;
if (!next)
mm->highest_vm_end = vm_end_gap(vma);
}
if (end_changed || start_changed)
if (vma_changed)
vma_mas_store(vma, &mas);
vma->vm_pgoff = pgoff;
......@@ -995,22 +766,12 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
* Since we have expanded over this vma, the maple tree will
* have overwritten by storing the value
*/
if (remove_next != 3) {
__vma_unlink(mm, next, next);
if (remove_next == 2)
__vma_unlink(mm, next_next, next_next);
} else {
/*
* vma is not before next if they've been
* swapped.
*
* pre-swap() next->vm_start was reduced so
* tell validate_mm_rb to ignore pre-swap()
* "next" (which is stored in post-swap()
* "vma").
*/
__vma_unlink(mm, next, vma);
}
__vma_unlink_list(mm, next);
if (remove_next == 2)
__vma_unlink_list(mm, next_next);
/* Kill the cache */
vmacache_invalidate(mm);
if (file) {
__remove_shared_vm_struct(next, file, mapping);
if (remove_next == 2)
......@@ -1023,15 +784,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
* (it may either follow vma or precede it).
*/
__insert_vm_struct(mm, &mas, insert);
} else {
if (start_changed)
vma_gap_update(vma);
if (end_changed) {
if (!next)
mm->highest_vm_end = vm_end_gap(vma);
else if (!adjust_next)
vma_gap_update(next);
}
}
if (anon_vma) {
......@@ -1059,7 +811,10 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
anon_vma_merge(vma, next);
mm->map_count--;
mpol_put(vma_policy(next));
if (remove_next != 2)
BUG_ON(vma->vm_end < next->vm_end);
vm_area_free(next);
/*
* In mprotect's case 6 (see comments on vma_merge),
* we must remove another next too. It would clutter
......@@ -1089,10 +844,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
if (remove_next == 2) {
remove_next = 1;
goto again;
}
else if (next)
vma_gap_update(next);
else {
} else if (!next) {
/*
* If remove_next == 2 we obviously can't
* reach this path.
......@@ -1119,8 +871,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
uprobe_mmap(insert);
validate_mm(mm);
validate_mm_mt(mm);
return 0;
}
......@@ -1273,7 +1023,6 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
struct vm_area_struct *area, *next;
int err;
validate_mm_mt(mm);
/*
* We later require that vma->vm_flags == vm_flags,
* so this tests vma->vm_flags & VM_SPECIAL, too.
......@@ -1349,7 +1098,6 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
khugepaged_enter_vma(area, vm_flags);
return area;
}
validate_mm_mt(mm);
return NULL;
}
......@@ -1519,6 +1267,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
vm_flags_t vm_flags;
int pkey = 0;
validate_mm(mm);
*populate = 0;
if (!len)
......@@ -1829,10 +1578,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev, *merge;
int error;
struct rb_node **rb_link, *rb_parent;
unsigned long charged = 0;
validate_mm_mt(mm);
/* Check against address space limit. */
if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) {
unsigned long nr_pages;
......@@ -1848,8 +1595,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
return -ENOMEM;
}
/* Clear old maps, set up prev, rb_link, rb_parent, and uf */
if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf))
/* Clear old maps, set up prev and uf */
if (munmap_vma_range(mm, addr, len, &prev, uf))
return -ENOMEM;
/*
* Private writable mapping: check memory availability
......@@ -1947,7 +1694,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
goto free_vma;
}
if (vma_link(mm, vma, prev, rb_link, rb_parent)) {
if (vma_link(mm, vma, prev)) {
error = -ENOMEM;
if (file)
goto unmap_and_free_vma;
......@@ -1993,7 +1740,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
vma_set_page_prot(vma);
validate_mm_mt(mm);
return addr;
unmap_and_free_vma:
......@@ -2009,7 +1755,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
unacct_error:
if (charged)
vm_unacct_memory(charged);
validate_mm_mt(mm);
return error;
}
......@@ -2367,7 +2112,6 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
int error = 0;
MA_STATE(mas, &mm->mm_mt, 0, 0);
validate_mm_mt(mm);
if (!(vma->vm_flags & VM_GROWSUP))
return -EFAULT;
......@@ -2419,15 +2163,13 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
error = acct_stack_growth(vma, size, grow);
if (!error) {
/*
* vma_gap_update() doesn't support concurrent
* updates, but we only hold a shared mmap_lock
* lock here, so we need to protect against
* concurrent vma expansions.
* anon_vma_lock_write() doesn't help here, as
* we don't guarantee that all growable vmas
* in a mm share the same root anon vma.
* So, we reuse mm->page_table_lock to guard
* against concurrent vma expansions.
* We only hold a shared mmap_lock lock here, so
* we need to protect against concurrent vma
* expansions. anon_vma_lock_write() doesn't
* help here, as we don't guarantee that all
* growable vmas in a mm share the same root
* anon vma. So, we reuse mm->page_table_lock
* to guard against concurrent vma expansions.
*/
spin_lock(&mm->page_table_lock);
if (vma->vm_flags & VM_LOCKED)
......@@ -2438,9 +2180,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
/* Overwrite old entry in mtree. */
vma_mas_store(vma, &mas);
anon_vma_interval_tree_post_update_vma(vma);
if (vma->vm_next)
vma_gap_update(vma->vm_next);
else
if (!vma->vm_next)
mm->highest_vm_end = vm_end_gap(vma);
spin_unlock(&mm->page_table_lock);
......@@ -2450,8 +2190,6 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
}
anon_vma_unlock_write(vma->anon_vma);
khugepaged_enter_vma(vma, vma->vm_flags);
validate_mm(mm);
validate_mm_mt(mm);
mas_destroy(&mas);
return error;
}
......@@ -2460,15 +2198,13 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
/*
* vma is the first one with address < vma->vm_start. Have to extend vma.
*/
int expand_downwards(struct vm_area_struct *vma,
unsigned long address)
int expand_downwards(struct vm_area_struct *vma, unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *prev;
int error = 0;
MA_STATE(mas, &mm->mm_mt, 0, 0);
validate_mm(mm);
address &= PAGE_MASK;
if (address < mmap_min_addr)
return -EPERM;
......@@ -2510,15 +2246,13 @@ int expand_downwards(struct vm_area_struct *vma,
error = acct_stack_growth(vma, size, grow);
if (!error) {
/*
* vma_gap_update() doesn't support concurrent
* updates, but we only hold a shared mmap_lock
* lock here, so we need to protect against
* concurrent vma expansions.
* anon_vma_lock_write() doesn't help here, as
* we don't guarantee that all growable vmas
* in a mm share the same root anon vma.
* So, we reuse mm->page_table_lock to guard
* against concurrent vma expansions.
* We only hold a shared mmap_lock lock here, so
* we need to protect against concurrent vma
* expansions. anon_vma_lock_write() doesn't
* help here, as we don't guarantee that all
* growable vmas in a mm share the same root
* anon vma. So, we reuse mm->page_table_lock
* to guard against concurrent vma expansions.
*/
spin_lock(&mm->page_table_lock);
if (vma->vm_flags & VM_LOCKED)
......@@ -2530,7 +2264,6 @@ int expand_downwards(struct vm_area_struct *vma,
/* Overwrite old entry in mtree. */
vma_mas_store(vma, &mas);
anon_vma_interval_tree_post_update_vma(vma);
vma_gap_update(vma);
spin_unlock(&mm->page_table_lock);
perf_event_mmap(vma);
......@@ -2539,7 +2272,6 @@ int expand_downwards(struct vm_area_struct *vma,
}
anon_vma_unlock_write(vma->anon_vma);
khugepaged_enter_vma(vma, vma->vm_flags);
validate_mm(mm);
mas_destroy(&mas);
return error;
}
......@@ -2671,10 +2403,8 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct ma_state *mas,
insertion_point = (prev ? &prev->vm_next : &mm->mmap);
vma->vm_prev = NULL;
mas_set_range(mas, vma->vm_start, end - 1);
mas_store_prealloc(mas, NULL);
vma_mas_szero(mas, vma->vm_start, end);
do {
vma_rb_erase(vma, &mm->mm_rb);
if (vma->vm_flags & VM_LOCKED)
mm->locked_vm -= vma_pages(vma);
mm->map_count--;
......@@ -2682,10 +2412,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct ma_state *mas,
vma = vma->vm_next;
} while (vma && vma->vm_start < end);
*insertion_point = vma;
if (vma) {
if (vma)
vma->vm_prev = prev;
vma_gap_update(vma);
} else
else
mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
tail_vma->vm_next = NULL;
......@@ -2807,11 +2536,7 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
if (len == 0)
return -EINVAL;
/*
* arch_unmap() might do unmaps itself. It must be called
* and finish any rbtree manipulation before this code
* runs and also starts to manipulate the rbtree.
*/
/* arch_unmap() might do unmaps itself. */
arch_unmap(mm, start, end);
/* Find the first overlapping VMA where start < vma->vm_end */
......@@ -2822,6 +2547,11 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
if (mas_preallocate(&mas, vma, GFP_KERNEL))
return -ENOMEM;
prev = vma->vm_prev;
/* we have start < vma->vm_end */
/* if it doesn't overlap, we have nothing.. */
if (vma->vm_start >= end)
return 0;
/*
* If we need to split any vma, do it now to save pain later.
......@@ -2882,6 +2612,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
/* Fix up all other VM information */
remove_vma_list(mm, vma);
validate_mm(mm);
return downgrade ? 1 : 0;
map_count_exceeded:
......@@ -3020,11 +2752,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
* anonymous maps. eventually we may be able to do some
* brk-specific accounting here.
*/
static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf)
static int do_brk_flags(unsigned long addr, unsigned long len,
unsigned long flags, struct list_head *uf)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
struct rb_node **rb_link, *rb_parent;
pgoff_t pgoff = addr >> PAGE_SHIFT;
int error;
unsigned long mapped_addr;
......@@ -3043,8 +2775,8 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
if (error)
return error;
/* Clear old maps, set up prev, rb_link, rb_parent, and uf */
if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf))
/* Clear old maps, set up prev and uf */
if (munmap_vma_range(mm, addr, len, &prev, uf))
return -ENOMEM;
/* Check against address space limits *after* clearing old maps... */
......@@ -3078,7 +2810,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
vma->vm_pgoff = pgoff;
vma->vm_flags = flags;
vma->vm_page_prot = vm_get_page_prot(flags);
if (vma_link(mm, vma, prev, rb_link, rb_parent))
if (vma_link(mm, vma, prev))
goto no_vma_link;
out:
......@@ -3197,29 +2929,12 @@ void exit_mmap(struct mm_struct *mm)
int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
struct vm_area_struct *prev;
struct rb_node **rb_link, *rb_parent;
unsigned long start = vma->vm_start;
struct vm_area_struct *overlap = NULL;
unsigned long charged = vma_pages(vma);
if (find_vma_links(mm, vma->vm_start, vma->vm_end,
&prev, &rb_link, &rb_parent))
if (find_vma_intersection(mm, vma->vm_start, vma->vm_end))
if (range_has_overlap(mm, vma->vm_start, vma->vm_end, &prev))
return -ENOMEM;
overlap = mt_find(&mm->mm_mt, &start, vma->vm_end - 1);
if (overlap) {
pr_err("Found vma ending at %lu\n", start - 1);
pr_err("vma : %lu => %lu-%lu\n", (unsigned long)overlap,
overlap->vm_start, overlap->vm_end - 1);
#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
mt_dump(&mm->mm_mt);
#endif
BUG();
}
if ((vma->vm_flags & VM_ACCOUNT) &&
security_vm_enough_memory_mm(mm, charged))
return -ENOMEM;
......@@ -3241,7 +2956,7 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
}
if (vma_link(mm, vma, prev, rb_link, rb_parent)) {
if (vma_link(mm, vma, prev)) {
vm_unacct_memory(charged);
return -ENOMEM;
}
......@@ -3261,9 +2976,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
unsigned long vma_start = vma->vm_start;
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *new_vma, *prev;
struct rb_node **rb_link, *rb_parent;
bool faulted_in_anon_vma = true;
unsigned long index = addr;
validate_mm_mt(mm);
/*
......@@ -3275,10 +2988,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
faulted_in_anon_vma = false;
}
if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
if (range_has_overlap(mm, addr, addr + len, &prev))
return NULL; /* should never get here */
if (mt_find(&mm->mm_mt, &index, addr+len - 1))
BUG();
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx, anon_vma_name(vma));
......@@ -3319,12 +3031,16 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
get_file(new_vma->vm_file);
if (new_vma->vm_ops && new_vma->vm_ops->open)
new_vma->vm_ops->open(new_vma);
vma_link(mm, new_vma, prev, rb_link, rb_parent);
if (vma_link(mm, new_vma, prev))
goto out_vma_link;
*need_rmap_locks = false;
}
validate_mm_mt(mm);
return new_vma;
out_vma_link:
if (new_vma->vm_ops && new_vma->vm_ops->close)
new_vma->vm_ops->close(new_vma);
out_free_mempol:
mpol_put(vma_policy(new_vma));
out_free_vma:
......
......@@ -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)
......
......@@ -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 */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment