[PATCH v4 65/66] mm: Remove the vma linked list
From: Liam Howlett
Date: Wed Dec 01 2021 - 09:39:47 EST
From: "Liam R. Howlett" <Liam.Howlett@xxxxxxxxxx>
Replace any vm_next use with vma_find().
Update free_pgtables(), unmap_vmas(), and zap_page_range() to use the
maple tree.
Use the new free_pgtables() and unmap_vmas() in do_mas_align_munmap().
At the same time, alter the loop to be more compact.
Now that free_pgtables() and unmap_vmas() take a maple tree as an
argument, rearrange do_mas_align_munmap() to use the new table to hold
the lock
Remove __vma_link_list() and __vma_unlink_list() as they are exclusively
used to update the linked list
Rework validation of tree as it was depending on the linked list.
Signed-off-by: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
---
include/linux/mm.h | 5 +-
include/linux/mm_types.h | 4 -
kernel/fork.c | 13 +-
mm/debug.c | 14 +-
mm/gup.c | 2 +-
mm/internal.h | 10 +-
mm/memory.c | 33 ++-
mm/mmap.c | 497 ++++++++++++++++++---------------------
mm/nommu.c | 2 -
mm/util.c | 40 ----
10 files changed, 269 insertions(+), 351 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 199f66716eef..f5a1394bad61 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1883,8 +1883,9 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size);
void zap_page_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size);
-void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
- unsigned long start, unsigned long end);
+void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
+ struct vm_area_struct *start_vma, unsigned long start,
+ unsigned long end);
struct mmu_notifier_range;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1ab6260fb164..1d41cef68f73 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -400,8 +400,6 @@ struct vm_area_struct {
unsigned long vm_end; /* The first byte after our end address
within vm_mm. */
- /* linked list of VM areas per task, sorted by address */
- struct vm_area_struct *vm_next, *vm_prev;
struct mm_struct *vm_mm; /* The address space we belong to. */
/*
@@ -454,7 +452,6 @@ struct vm_area_struct {
struct kioctx_table;
struct mm_struct {
struct {
- struct vm_area_struct *mmap; /* list of VMAs */
struct maple_tree mm_mt;
#ifdef CONFIG_MMU
unsigned long (*get_unmapped_area) (struct file *filp,
@@ -469,7 +466,6 @@ struct mm_struct {
unsigned long mmap_compat_legacy_base;
#endif
unsigned long task_size; /* size of task vm space */
- unsigned long highest_vm_end; /* highest vma end address */
pgd_t * pgd;
#ifdef CONFIG_MEMBARRIER
diff --git a/kernel/fork.c b/kernel/fork.c
index 6de302e93519..c748b7457693 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -363,7 +363,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
*/
*new = data_race(*orig);
INIT_LIST_HEAD(&new->anon_vma_chain);
- new->vm_next = new->vm_prev = NULL;
}
return new;
}
@@ -497,7 +496,7 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
static __latent_entropy int dup_mmap(struct mm_struct *mm,
struct mm_struct *oldmm)
{
- struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
+ struct vm_area_struct *mpnt, *tmp, *prev;
int retval;
unsigned long charge = 0;
MA_STATE(old_mas, &oldmm->mm_mt, 0, 0);
@@ -524,7 +523,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mm->exec_vm = oldmm->exec_vm;
mm->stack_vm = oldmm->stack_vm;
- pprev = &mm->mmap;
retval = ksm_fork(mm, oldmm);
if (retval)
goto out;
@@ -605,14 +603,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
if (is_vm_hugetlb_page(tmp))
reset_vma_resv_huge_pages(tmp);
- /*
- * Link in the new vma and copy the page table entries.
- */
- *pprev = tmp;
- pprev = &tmp->vm_next;
- tmp->vm_prev = prev;
- prev = tmp;
-
/* Link the vma into the MT */
mas.index = tmp->vm_start;
mas.last = tmp->vm_end - 1;
@@ -1052,7 +1042,6 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
struct user_namespace *user_ns)
{
- mm->mmap = NULL;
mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
atomic_set(&mm->mm_users, 1);
diff --git a/mm/debug.c b/mm/debug.c
index 440a0614d14a..3b6fb26934c1 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -191,13 +191,11 @@ EXPORT_SYMBOL(dump_page);
void dump_vma(const struct vm_area_struct *vma)
{
- pr_emerg("vma %px start %px end %px\n"
- "next %px prev %px mm %px\n"
+ pr_emerg("vma %px start %px end %px mm %px\n"
"prot %lx anon_vma %px vm_ops %px\n"
"pgoff %lx file %px private_data %px\n"
"flags: %#lx(%pGv)\n",
- vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
- vma->vm_prev, vma->vm_mm,
+ vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_mm,
(unsigned long)pgprot_val(vma->vm_page_prot),
vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
vma->vm_file, vma->vm_private_data,
@@ -207,11 +205,11 @@ EXPORT_SYMBOL(dump_vma);
void dump_mm(const struct mm_struct *mm)
{
- pr_emerg("mm %px mmap %px task_size %lu\n"
+ pr_emerg("mm %px task_size %lu\n"
#ifdef CONFIG_MMU
"get_unmapped_area %px\n"
#endif
- "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
+ "mmap_base %lu mmap_legacy_base %lu\n"
"pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
"pinned_vm %llx data_vm %lx exec_vm %lx stack_vm %lx\n"
@@ -235,11 +233,11 @@ void dump_mm(const struct mm_struct *mm)
"tlb_flush_pending %d\n"
"def_flags: %#lx(%pGv)\n",
- mm, mm->mmap, mm->task_size,
+ mm, mm->task_size,
#ifdef CONFIG_MMU
mm->get_unmapped_area,
#endif
- mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
+ mm->mmap_base, mm->mmap_legacy_base,
mm->pgd, atomic_read(&mm->mm_users),
atomic_read(&mm->mm_count),
mm_pgtables_bytes(mm),
diff --git a/mm/gup.c b/mm/gup.c
index 60892e5df6a2..ba6249fab982 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1731,7 +1731,7 @@ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
mmap_read_lock(mm);
vma = find_vma(mm, nstart);
} else if (nstart >= vma->vm_end)
- vma = vma->vm_next;
+ vma = find_vma(mm, vma->vm_end);
if (!vma || vma->vm_start >= end)
break;
nend = end ? min(end, vma->vm_end) : vma->vm_end;
diff --git a/mm/internal.h b/mm/internal.h
index 7ec79cef3ea9..c617291f6d5f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -65,8 +65,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf);
void folio_rotate_reclaimable(struct folio *folio);
bool __folio_end_writeback(struct folio *folio);
-void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
- unsigned long floor, unsigned long ceiling);
+void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
+ struct vm_area_struct *start_vma, unsigned long floor,
+ unsigned long ceiling);
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
static inline bool can_madv_lru_vma(struct vm_area_struct *vma)
@@ -455,11 +456,6 @@ static inline int vma_mas_remove(struct vm_area_struct *vma, struct ma_state *ma
return ret;
}
-/* mm/util.c */
-void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev);
-void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma);
-
#ifdef CONFIG_MMU
extern long populate_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *locked);
diff --git a/mm/memory.c b/mm/memory.c
index 8f1de811a1dc..445c4a06d7f7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -398,12 +398,21 @@ void free_pgd_range(struct mmu_gather *tlb,
} while (pgd++, addr = next, addr != end);
}
-void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
- unsigned long floor, unsigned long ceiling)
+void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
+ struct vm_area_struct *vma, unsigned long floor,
+ unsigned long ceiling)
{
- while (vma) {
- struct vm_area_struct *next = vma->vm_next;
+ MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
+
+ do {
unsigned long addr = vma->vm_start;
+ struct vm_area_struct *next;
+
+ /*
+ * Note: USER_PGTABLES_CEILING may be passed as ceiling and may
+ * be 0. This will underflow and is okay.
+ */
+ next = mas_find(&mas, ceiling - 1);
/*
* Hide vma from rmap and truncate_pagecache before freeing
@@ -422,7 +431,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
while (next && next->vm_start <= vma->vm_end + PMD_SIZE
&& !is_vm_hugetlb_page(next)) {
vma = next;
- next = vma->vm_next;
+ next = mas_find(&mas, ceiling - 1);
unlink_anon_vmas(vma);
unlink_file_vma(vma);
}
@@ -430,7 +439,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
floor, next ? next->vm_start : ceiling);
}
vma = next;
- }
+ } while (vma);
}
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
@@ -1602,17 +1611,19 @@ static void unmap_single_vma(struct mmu_gather *tlb,
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
-void unmap_vmas(struct mmu_gather *tlb,
+void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr)
{
struct mmu_notifier_range range;
+ MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
- for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
+ do {
unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
+ } while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
mmu_notifier_invalidate_range_end(&range);
}
@@ -1627,8 +1638,11 @@ void unmap_vmas(struct mmu_gather *tlb,
void zap_page_range(struct vm_area_struct *vma, unsigned long start,
unsigned long size)
{
+ struct maple_tree *mt = &vma->vm_mm->mm_mt;
+ unsigned long end = start + size;
struct mmu_notifier_range range;
struct mmu_gather tlb;
+ MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
lru_add_drain();
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
@@ -1636,8 +1650,9 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
tlb_gather_mmu(&tlb, vma->vm_mm);
update_hiwater_rss(vma->vm_mm);
mmu_notifier_invalidate_range_start(&range);
- for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next)
+ do {
unmap_single_vma(&tlb, vma, start, range.end, NULL);
+ } while ((vma = mas_find(&mas, end - 1)) != NULL);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
diff --git a/mm/mmap.c b/mm/mmap.c
index dde74e0b195d..e13c6ef76697 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -74,9 +74,10 @@ int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
static bool ignore_rlimit_data;
core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
-static void unmap_region(struct mm_struct *mm,
+static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
struct vm_area_struct *vma, struct vm_area_struct *prev,
- unsigned long start, unsigned long end);
+ struct vm_area_struct *next, unsigned long start,
+ unsigned long end);
/* description of effects of mapping type and prot in current implementation.
* this is due to the limited x86 page protection hardware. The expected
@@ -173,10 +174,8 @@ void unlink_file_vma(struct vm_area_struct *vma)
/*
* Close a vm structure and free it, returning the next.
*/
-static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+static void remove_vma(struct vm_area_struct *vma)
{
- struct vm_area_struct *next = vma->vm_next;
-
might_sleep();
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
@@ -184,15 +183,14 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
fput(vma->vm_file);
mpol_put(vma_policy(vma));
vm_area_free(vma);
- return next;
}
static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
unsigned long newbrk, unsigned long oldbrk,
struct list_head *uf);
-static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *brkvma,
- unsigned long addr, unsigned long request,
- unsigned long flags);
+static int do_brk_flags(struct ma_state *mas, struct ma_state *ma_prev,
+ struct vm_area_struct *brkvma, unsigned long addr,
+ unsigned long request, unsigned long flags);
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
unsigned long newbrk, oldbrk, origbrk;
@@ -203,6 +201,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
bool downgraded = false;
LIST_HEAD(uf);
MA_STATE(mas, &mm->mm_mt, 0, 0);
+ struct ma_state ma_neighbour;
if (mmap_write_lock_killable(mm))
return -EINTR;
@@ -259,7 +258,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
* before calling do_brk_munmap().
*/
mm->brk = brk;
- mas.last = oldbrk - 1;
ret = do_brk_munmap(&mas, brkvma, newbrk, oldbrk, &uf);
if (ret == 1) {
downgraded = true;
@@ -270,26 +268,26 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
mm->brk = origbrk;
goto out;
}
+ ma_neighbour = mas;
+ next = mas_next(&ma_neighbour, newbrk + PAGE_SIZE + stack_guard_gap);
/* Only check if the next VMA is within the stack_guard_gap of the
* expansion area */
- next = mas_next(&mas, newbrk + PAGE_SIZE + stack_guard_gap);
/* Check against existing mmap mappings. */
if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
goto out;
- brkvma = mas_prev(&mas, mm->start_brk);
+ brkvma = mas_prev(&ma_neighbour, mm->start_brk);
if (brkvma) {
if (brkvma->vm_start >= oldbrk)
goto out; // Trying to map over another vma.
- if (brkvma->vm_end <= min_brk) {
+ if (brkvma->vm_end <= min_brk)
brkvma = NULL;
- mas_reset(&mas);
- }
}
/* Ok, looks good - let it rip. */
- if (do_brk_flags(&mas, brkvma, oldbrk, newbrk - oldbrk, 0) < 0)
+ if (do_brk_flags(&mas, &ma_neighbour, brkvma, oldbrk,
+ newbrk - oldbrk, 0) < 0)
goto out;
mm->brk = brk;
@@ -300,6 +298,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
mmap_read_unlock(mm);
else
mmap_write_unlock(mm);
+
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(oldbrk, newbrk - oldbrk);
@@ -318,44 +317,22 @@ extern void mt_dump(const struct maple_tree *mt);
static void validate_mm_mt(struct mm_struct *mm)
{
struct maple_tree *mt = &mm->mm_mt;
- struct vm_area_struct *vma_mt, *vma = mm->mmap;
+ struct vm_area_struct *vma_mt;
MA_STATE(mas, mt, 0, 0);
- mas_for_each(&mas, vma_mt, ULONG_MAX) {
- if (xa_is_zero(vma_mt))
- continue;
- if (!vma)
- break;
-
- if ((vma != vma_mt) ||
- (vma->vm_start != vma_mt->vm_start) ||
- (vma->vm_end != vma_mt->vm_end) ||
- (vma->vm_start != mas.index) ||
- (vma->vm_end - 1 != mas.last)) {
+ mas_for_each(&mas, vma_mt, ULONG_MAX) {
+ if ((vma_mt->vm_start != mas.index) ||
+ (vma_mt->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 vm_next\n");
- dump_vma(vma->vm_next);
-#endif
+#endif // CONFIG_DEBUG_VM
pr_emerg("mt piv: %px %lu - %lu\n", vma_mt,
mas.index, mas.last);
pr_emerg("mt vma: %px %lu - %lu\n", vma_mt,
vma_mt->vm_start, vma_mt->vm_end);
- if (vma->vm_prev) {
- pr_emerg("ll prev: %px %lu - %lu\n",
- vma->vm_prev, vma->vm_prev->vm_start,
- vma->vm_prev->vm_end);
- }
- pr_emerg("ll vma: %px %lu - %lu\n", vma,
- vma->vm_start, vma->vm_end);
- if (vma->vm_next) {
- pr_emerg("ll next: %px %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) {
@@ -372,11 +349,7 @@ static void validate_mm_mt(struct mm_struct *mm)
}
VM_BUG_ON_MM(vma_mt->vm_start != mas.index, mm);
}
- VM_BUG_ON(vma != vma_mt);
- vma = vma->vm_next;
-
}
- VM_BUG_ON(vma);
mt_validate(&mm->mm_mt);
}
@@ -384,12 +357,12 @@ static void validate_mm(struct mm_struct *mm)
{
int bug = 0;
int i = 0;
- unsigned long highest_address = 0;
- struct vm_area_struct *vma = mm->mmap;
+ struct vm_area_struct *vma;
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
validate_mm_mt(mm);
- while (vma) {
+ mas_for_each(&mas, vma, ULONG_MAX) {
#ifdef CONFIG_DEBUG_VM_RB
struct anon_vma *anon_vma = vma->anon_vma;
struct anon_vma_chain *avc;
@@ -401,20 +374,12 @@ static void validate_mm(struct mm_struct *mm)
anon_vma_unlock_read(anon_vma);
}
#endif
-
- highest_address = vm_end_gap(vma);
- vma = vma->vm_next;
i++;
}
if (i != mm->map_count) {
pr_emerg("map_count %d vm_next %d\n", mm->map_count, i);
bug = 1;
}
- if (highest_address != mm->highest_vm_end) {
- pr_emerg("mm->highest_vm_end %lx, found %lx\n",
- mm->highest_vm_end, highest_address);
- bug = 1;
- }
VM_BUG_ON_MM(bug, mm);
}
@@ -472,29 +437,13 @@ bool range_has_overlap(struct mm_struct *mm, unsigned long start,
struct vm_area_struct *existing;
MA_STATE(mas, &mm->mm_mt, start, start);
+ rcu_read_lock();
existing = mas_find(&mas, end - 1);
*pprev = mas_prev(&mas, 0);
+ rcu_read_unlock();
return existing ? true : false;
}
-/*
- * __vma_next() - Get the next VMA.
- * @mm: The mm_struct.
- * @vma: The current vma.
- *
- * If @vma is NULL, return the first vma in the mm.
- *
- * Returns: The next VMA after @vma.
- */
-static inline struct vm_area_struct *__vma_next(struct mm_struct *mm,
- struct vm_area_struct *vma)
-{
- if (!vma)
- return mm->mmap;
-
- return vma->vm_next;
-}
-
static unsigned long count_vma_pages_range(struct mm_struct *mm,
unsigned long addr, unsigned long end)
{
@@ -559,8 +508,7 @@ void vma_store(struct mm_struct *mm, struct vm_area_struct *vma)
mas_store_gfp(&mas, vma, GFP_KERNEL);
}
-static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev)
+static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma)
{
struct address_space *mapping = NULL;
@@ -570,7 +518,6 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
}
vma_store(mm, vma);
- __vma_link_list(mm, vma, prev);
__vma_link_file(vma);
if (mapping)
@@ -586,12 +533,7 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
*/
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
- struct vm_area_struct *prev;
- MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_start);
-
- prev = mas_prev(&mas, 0);
vma_store(mm, vma);
- __vma_link_list(mm, vma, prev);
mm->map_count++;
}
@@ -650,15 +592,8 @@ inline int vma_expand(struct ma_state *mas, struct vm_area_struct *vma,
}
/* Expanding over the next vma */
- if (remove_next) {
- /* Remove from mm linked list - also updates highest_vm_end */
- __vma_unlink_list(mm, next);
-
- if (file)
- __remove_shared_vm_struct(next, file, mapping);
-
- } else if (!next) {
- mm->highest_vm_end = vm_end_gap(vma);
+ if (remove_next && file) {
+ __remove_shared_vm_struct(next, file, mapping);
}
if (anon_vma) {
@@ -699,7 +634,8 @@ 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 = 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;
@@ -741,7 +677,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
*/
remove_next = 1 + (end > next->vm_end);
VM_WARN_ON(remove_next == 2 &&
- end != next->vm_next->vm_end);
+ end != find_vma(mm, next->vm_end)->vm_end);
/* trim end to next, for case 6 first pass */
end = next->vm_end;
}
@@ -754,7 +690,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
* next, if the vma overlaps with it.
*/
if (remove_next == 2 && !next->anon_vma)
- exporter = next->vm_next;
+ exporter = find_vma(mm, next->vm_end);
} else if (end > next->vm_start) {
/*
@@ -845,8 +781,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
} else
vma_changed = true;
vma->vm_end = end;
- if (!next)
- mm->highest_vm_end = vm_end_gap(vma);
}
if (vma_changed) {
@@ -871,10 +805,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
flush_dcache_mmap_unlock(mapping);
}
- if (remove_next) {
- __vma_unlink_list(mm, next);
- if (file)
- __remove_shared_vm_struct(next, file, mapping);
+ if (remove_next && file) {
+ __remove_shared_vm_struct(next, file, mapping);
} else if (insert) {
/*
* split_vma has split insert from vma, and needs
@@ -921,7 +853,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
* "next->vm_prev->vm_end" changed and the
* "vma->vm_next" gap must be updated.
*/
- next = vma->vm_next;
+ next = find_vma(mm, vma->vm_end);
} else {
/*
* For the scope of the comment "next" and
@@ -939,33 +871,14 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
remove_next = 1;
end = next->vm_end;
goto again;
- } else if (!next) {
- /*
- * If remove_next == 2 we obviously can't
- * reach this path.
- *
- * If remove_next == 3 we can't reach this
- * path because pre-swap() next is always not
- * NULL. pre-swap() "next" is not being
- * removed and its next->vm_end is not altered
- * (and furthermore "end" already matches
- * next->vm_end in remove_next == 3).
- *
- * We reach this only in the remove_next == 1
- * case if the "next" vma that was removed was
- * the highest vma of the mm. However in such
- * case next->vm_end == "end" and the extended
- * "vma" has vma->vm_end == next->vm_end so
- * mm->highest_vm_end doesn't need any update
- * in remove_next == 1 case.
- */
- VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
}
}
- if (insert && file)
+ if (insert && file) {
uprobe_mmap(insert);
+ }
validate_mm(mm);
+
return 0;
}
@@ -1119,10 +1032,10 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
if (vm_flags & VM_SPECIAL)
return NULL;
- next = __vma_next(mm, prev);
+ next = find_vma(mm, prev ? prev->vm_end : 0);
area = next;
if (area && area->vm_end == end) /* cases 6, 7, 8 */
- next = next->vm_next;
+ next = find_vma(mm, next->vm_end);
/* verify some invariant that must be enforced by the caller */
VM_WARN_ON(prev && addr <= prev->vm_start);
@@ -1256,18 +1169,24 @@ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_
*/
struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
{
+ MA_STATE(mas, &vma->vm_mm->mm_mt, vma->vm_end, vma->vm_end);
struct anon_vma *anon_vma = NULL;
+ struct vm_area_struct *prev, *next;
/* Try next first. */
- if (vma->vm_next) {
- anon_vma = reusable_anon_vma(vma->vm_next, vma, vma->vm_next);
+ next = mas_walk(&mas);
+ if (next) {
+ anon_vma = reusable_anon_vma(next, vma, next);
if (anon_vma)
return anon_vma;
}
+ prev = mas_prev(&mas, 0);
+ VM_BUG_ON_VMA(prev != vma, vma);
+ prev = mas_prev(&mas, 0);
/* Try prev next. */
- if (vma->vm_prev)
- anon_vma = reusable_anon_vma(vma->vm_prev, vma->vm_prev, vma);
+ if (prev)
+ anon_vma = reusable_anon_vma(prev, prev, vma);
/*
* We might reach here with anon_vma == NULL if we can't find
@@ -1906,10 +1825,10 @@ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
unsigned long start_addr,
unsigned long end_addr)
{
- MA_STATE(mas, &mm->mm_mt, start_addr, start_addr);
+ unsigned long index = start_addr;
mmap_assert_locked(mm);
- return mas_find(&mas, end_addr - 1);
+ return mt_find(&mm->mm_mt, &index, end_addr - 1);
}
EXPORT_SYMBOL(find_vma_intersection);
@@ -1923,8 +1842,10 @@ EXPORT_SYMBOL(find_vma_intersection);
*/
inline struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
- // Note find_vma_intersection will decrease 0 to underflow to ULONG_MAX
- return find_vma_intersection(mm, addr, 0);
+ unsigned long index = addr;
+
+ mmap_assert_locked(mm);
+ return mt_find(&mm->mm_mt, &index, ULONG_MAX);
}
EXPORT_SYMBOL(find_vma);
@@ -2026,7 +1947,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
if (gap_addr < address || gap_addr > TASK_SIZE)
gap_addr = TASK_SIZE;
- next = vma->vm_next;
+ next = vma_find(mm, vma->vm_end);
if (next && next->vm_start < gap_addr && vma_is_accessible(next)) {
if (!(next->vm_flags & VM_GROWSUP))
return -ENOMEM;
@@ -2072,8 +1993,6 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
vma->vm_end = address;
vma_store(mm, vma);
anon_vma_interval_tree_post_update_vma(vma);
- if (!vma->vm_next)
- mm->highest_vm_end = vm_end_gap(vma);
spin_unlock(&mm->page_table_lock);
perf_event_mmap(vma);
@@ -2100,7 +2019,7 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address)
return -EPERM;
/* Enforce stack_guard_gap */
- prev = vma->vm_prev;
+ find_vma_prev(mm, vma->vm_start, &prev);
/* Check that both stack segments have the same anon_vma? */
if (prev && !(prev->vm_flags & VM_GROWSDOWN) &&
vma_is_accessible(prev)) {
@@ -2235,20 +2154,22 @@ EXPORT_SYMBOL_GPL(find_extend_vma);
*
* Called with the mm semaphore held.
*/
-static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
+static inline void remove_mt(struct mm_struct *mm, struct maple_tree *detached)
{
unsigned long nr_accounted = 0;
+ unsigned long index = 0;
+ struct vm_area_struct *vma;
/* Update high watermark before we lower total_vm */
update_hiwater_vm(mm);
- do {
+ mt_for_each(detached, vma, index, ULONG_MAX) {
long nrpages = vma_pages(vma);
if (vma->vm_flags & VM_ACCOUNT)
nr_accounted += nrpages;
vm_stat_account(mm, vma->vm_flags, -nrpages);
- vma = remove_vma(vma);
- } while (vma);
+ remove_vma(vma);
+ }
vm_unacct_memory(nr_accounted);
validate_mm(mm);
}
@@ -2258,18 +2179,18 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
*
* Called with the mm semaphore held.
*/
-static void unmap_region(struct mm_struct *mm,
+static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
struct vm_area_struct *vma, struct vm_area_struct *prev,
+ struct vm_area_struct *next,
unsigned long start, unsigned long end)
{
- struct vm_area_struct *next = __vma_next(mm, prev);
struct mmu_gather tlb;
lru_add_drain();
tlb_gather_mmu(&tlb, mm);
update_hiwater_rss(mm);
- unmap_vmas(&tlb, vma, start, end);
- free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
+ unmap_vmas(&tlb, mt, vma, start, end);
+ free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
next ? next->vm_start : USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb);
}
@@ -2310,8 +2231,9 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
if (err)
goto out_free_mpol;
- if (new->vm_file)
+ if (new->vm_file) {
get_file(new->vm_file);
+ }
if (new->vm_ops && new->vm_ops->open)
new->vm_ops->open(new);
@@ -2353,28 +2275,6 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
return __split_vma(mm, vma, addr, new_below);
}
-static inline int
-unlock_range(struct vm_area_struct *start, struct vm_area_struct **tail,
- unsigned long limit)
-{
- struct mm_struct *mm = start->vm_mm;
- struct vm_area_struct *tmp = start;
- int count = 0;
-
- while (tmp && tmp->vm_start < limit) {
- *tail = tmp;
- count++;
- if (tmp->vm_flags & VM_LOCKED) {
- mm->locked_vm -= vma_pages(tmp);
- munlock_vma_pages_all(tmp);
- }
-
- tmp = tmp->vm_next;
- }
-
- return count;
-}
-
/*
* do_mas_align_munmap() - munmap the aligned region from @start to @end.
* @mas: The maple_state, ideally set up to alter the correct tree location.
@@ -2393,9 +2293,14 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
struct mm_struct *mm, unsigned long start,
unsigned long end, struct list_head *uf, bool downgrade)
{
- struct vm_area_struct *prev, *last;
- /* we have start < vma->vm_end */
+ struct vm_area_struct *prev, *next;
+ struct maple_tree mt_detach;
+ int count = 0;
+ MA_STATE(mas_detach, &mt_detach, start, end - 1);
+ mt_init_flags(&mt_detach, MM_MT_FLAGS);
+ mt_set_external_lock(&mt_detach, &mm->mmap_lock);
+ prev = next = NULL;
/*
* If we need to split any vma, do it now to save pain later.
*
@@ -2403,6 +2308,8 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
* unmapped vm_area_struct will remain in use: so lower split_vma
* places tmp vma above, and higher split_vma places tmp vma below.
*/
+
+ /* Does it split the first one? */
if (start > vma->vm_start) {
int error;
@@ -2414,31 +2321,49 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
- error = __split_vma(mm, vma, start, 0);
+ /*
+ * mas_pause() is not needed since mas->index needs to be set
+ * differently than vma->vm_end anyways.
+ */
+ error = __split_vma(mm, vma, start, 1);
if (error)
return error;
- prev = vma;
- vma = __vma_next(mm, prev);
- mas->index = start;
- mas_reset(mas);
+
+ mas_set(mas, start - 1);
+ prev = mas_walk(mas);
} else {
- prev = vma->vm_prev;
+ prev = mas_prev(mas, 0);
+ if (unlikely((!prev)))
+ mas_set(mas, start);
}
- if (vma->vm_end >= end)
- last = vma;
- else
- last = find_vma_intersection(mm, end - 1, end);
+ /*
+ * Detach a range of VMAs from the mm. Using next as a temp variable as
+ * it is always overwritten.
+ */
+ mas_for_each(mas, next, end - 1) {
+ /* Does it split the end? */
+ if (next->vm_end > end) {
+ int error;
- /* Does it split the last one? */
- if (last && end < last->vm_end) {
- int error = __split_vma(mm, last, end, 1);
- if (error)
- return error;
- vma = __vma_next(mm, prev);
- mas_reset(mas);
+ error = __split_vma(mm, next, end, 0);
+ if (error)
+ return error;
+ mas_set(mas, end);
+ }
+ count++;
+#ifdef CONFIG_DEBUG_MAPLE_TREE
+ BUG_ON(next->vm_start < start);
+ BUG_ON(next->vm_start > end);
+#endif
+ vma_mas_store(next, &mas_detach);
+ if (next->vm_flags & VM_LOCKED) {
+ mm->locked_vm -= vma_pages(next);
+ munlock_vma_pages_all(next);
+ }
}
+ next = mas_find(mas, ULONG_MAX);
if (unlikely(uf)) {
/*
* If userfaultfd_unmap_prep returns an error the vmas
@@ -2455,47 +2380,48 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
return error;
}
- /*
- * unlock any mlock()ed ranges before detaching vmas, count the number
- * of VMAs to be dropped, and return the tail entry of the affected
- * area.
- */
- mm->map_count -= unlock_range(vma, &last, end);
- /* Drop removed area from the tree */
+ /* Point of no return */
+ mas_set_range(mas, start, end - 1);
+#if defined(CONFIG_DEBUG_MAPLE_TREE)
+ /* Make sure no VMAs are about to be lost. */
+ {
+ MA_STATE(test, &mt_detach, start, end - 1);
+ struct vm_area_struct *vma_mas, *vma_test;
+ int test_count = 0;
+
+ rcu_read_lock();
+ vma_test = mas_find(&test, end - 1);
+ mas_for_each(mas, vma_mas, end - 1) {
+ BUG_ON(vma_mas != vma_test);
+ test_count++;
+ vma_test = mas_next(&test, end - 1);
+ }
+ rcu_read_unlock();
+ BUG_ON(count != test_count);
+ mas_set_range(mas, start, end - 1);
+ }
+#endif
mas_store_gfp(mas, NULL, GFP_KERNEL);
-
- /* Detach vmas from the MM linked list */
- vma->vm_prev = NULL;
- if (prev)
- prev->vm_next = last->vm_next;
- else
- mm->mmap = last->vm_next;
-
- if (last->vm_next) {
- last->vm_next->vm_prev = prev;
- last->vm_next = NULL;
- } else
- mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
-
+ mm->map_count -= count;
/*
* Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or
* VM_GROWSUP VMA. Such VMAs can change their size under
* down_read(mmap_lock) and collide with the VMA we are about to unmap.
*/
if (downgrade) {
- if (last && (last->vm_flags & VM_GROWSDOWN))
+ if (next && (next->vm_flags & VM_GROWSDOWN))
downgrade = false;
else if (prev && (prev->vm_flags & VM_GROWSUP))
downgrade = false;
- else {
+ else
mmap_write_downgrade(mm);
- }
}
- unmap_region(mm, vma, prev, start, end);
-
- /* Fix up all other VM information */
- remove_vma_list(mm, vma);
+ unmap_region(mm, &mt_detach, vma, prev, next, start, end);
+ /* Statistics and freeing VMAs */
+ remove_mt(mm, &mt_detach);
+ validate_mm(mm);
+ __mt_destroy(&mt_detach);
return downgrade ? 1 : 0;
}
@@ -2661,6 +2587,11 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
}
vma->vm_file = get_file(file);
+ /*
+ * call_mmap() may sleep, but will not alter the maple tree
+ * since the mmap_lock is held. This is safe and will be
+ * changed later.
+ */
error = call_mmap(file, vma);
if (error)
goto unmap_and_free_vma;
@@ -2724,7 +2655,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
i_mmap_lock_write(vma->vm_file->f_mapping);
vma_mas_store(vma, &mas);
- __vma_link_list(mm, vma, prev);
mm->map_count++;
if (vma->vm_file) {
if (vma->vm_flags & VM_SHARED)
@@ -2775,7 +2705,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
vma->vm_file = NULL;
/* Undo any partial mapping done by a device driver. */
- unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
+ unmap_region(mm, mas.tree, vma, prev, next, vma->vm_start, vma->vm_end);
charged = 0;
if (vm_flags & VM_SHARED)
mapping_unmap_writable(file->f_mapping);
@@ -2864,11 +2794,12 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
goto out;
if (start + size > vma->vm_end) {
- struct vm_area_struct *next;
+ VMA_ITERATOR(vmi, mm, vma->vm_end);
+ struct vm_area_struct *next, *prev = vma;
- for (next = vma->vm_next; next; next = next->vm_next) {
+ for_each_vma_range(vmi, next, start + size) {
/* hole between vmas ? */
- if (next->vm_start != next->vm_prev->vm_end)
+ if (next->vm_start != prev->vm_end)
goto out;
if (next->vm_file != vma->vm_file)
@@ -2877,8 +2808,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
if (next->vm_flags != vma->vm_flags)
goto out;
- if (start + size <= next->vm_end)
- break;
+ prev = next;
}
if (!next)
@@ -2924,7 +2854,7 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
struct list_head *uf)
{
struct mm_struct *mm = vma->vm_mm;
- struct vm_area_struct unmap;
+ struct vm_area_struct unmap, *next;
unsigned long unmap_pages;
int ret;
@@ -2941,6 +2871,7 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
ret = userfaultfd_unmap_prep(mm, newbrk, oldbrk, uf);
if (ret)
return ret;
+
ret = 1;
// Change the oldbrk of vma to the newbrk of the munmap area
@@ -2954,9 +2885,12 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
vma_init(&unmap, mm);
unmap.vm_start = newbrk;
unmap.vm_end = oldbrk;
+ if (vma->anon_vma)
+ vma_set_anonymous(&unmap);
if (vma_mas_remove(&unmap, mas))
goto mas_store_fail;
+ vma->vm_end = newbrk;
if (vma->anon_vma) {
anon_vma_interval_tree_post_update_vma(vma);
anon_vma_unlock_write(vma->anon_vma);
@@ -2968,8 +2902,9 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
munlock_vma_pages_range(&unmap, newbrk, oldbrk);
}
+ next = mas_next(mas, ULONG_MAX);
mmap_write_downgrade(mm);
- unmap_region(mm, &unmap, vma, newbrk, oldbrk);
+ unmap_region(mm, mas->tree, &unmap, vma, next, newbrk, oldbrk);
/* Statistics */
vm_stat_account(mm, unmap.vm_flags, -unmap_pages);
if (unmap.vm_flags & VM_ACCOUNT)
@@ -2980,6 +2915,7 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
return ret;
mas_store_fail:
+ mas_unlock(mas);
vma->vm_end = oldbrk;
if (vma->anon_vma) {
anon_vma_interval_tree_post_update_vma(vma);
@@ -3000,15 +2936,14 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
* do not match then create a new anonymous VMA. Eventually we may be able to
* do some brk-specific accounting here.
*/
-static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
- unsigned long addr, unsigned long len,
- unsigned long flags)
+static int do_brk_flags(struct ma_state *mas, struct ma_state *ma_prev,
+ struct vm_area_struct *vma, unsigned long addr,
+ unsigned long len, unsigned long flags)
{
struct mm_struct *mm = current->mm;
- struct vm_area_struct *prev = NULL;
int error;
unsigned long mapped_addr;
- validate_mm_mt(mm);
+ validate_mm(mm);
/* Until we need other flags, refuse anything except VM_EXEC. */
if ((flags & (~VM_EXEC)) != 0)
@@ -3033,7 +2968,6 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
- mas->last = addr + len - 1;
if (vma) {
/* Expand the existing vma if possible; almost never a singular
* list, so this will almost always fail. */
@@ -3041,7 +2975,8 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
if ((!vma->anon_vma ||
list_is_singular(&vma->anon_vma_chain)) &&
((vma->vm_flags & ~VM_SOFTDIRTY) == flags)){
- mas->index = vma->vm_start;
+ ma_prev->index = vma->vm_start;
+ ma_prev->last = addr + len - 1;
vma_adjust_trans_huge(vma, addr, addr + len, 0);
if (vma->anon_vma) {
@@ -3050,7 +2985,24 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
}
vma->vm_end = addr + len;
vma->vm_flags |= VM_SOFTDIRTY;
- if (mas_store_gfp(mas, vma, GFP_KERNEL))
+
+#if defined(CONFIG_DEBUG_MAPLE_TREE)
+ /* Make sure no VMAs are about to be lost. */
+ {
+ MA_STATE(test, ma_prev->tree, vma->vm_start,
+ vma->vm_end - 1);
+ struct vm_area_struct *vma_mas;
+ int count = 0;
+
+ mas_for_each(&test, vma_mas, vma->vm_end - 1)
+ count++;
+
+ BUG_ON(count != 1);
+ mas_set_range(ma_prev, vma->vm_start,
+ vma->vm_end - 1);
+ }
+#endif
+ if (mas_store_gfp(ma_prev, vma, GFP_KERNEL))
goto mas_mod_fail;
if (vma->anon_vma) {
@@ -3060,10 +3012,7 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
khugepaged_enter_vma_merge(vma, flags);
goto out;
}
- prev = vma;
}
- mas->index = addr;
- mas_walk(mas);
/* create a vma struct for an anonymous mapping */
vma = vm_area_alloc(mm);
@@ -3076,14 +3025,15 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
vma->vm_pgoff = addr >> PAGE_SHIFT;
vma->vm_flags = flags;
vma->vm_page_prot = vm_get_page_prot(flags);
- if (vma_mas_store(vma, mas))
- goto mas_store_fail;
-
- if (!prev)
- prev = mas_prev(mas, 0);
-
- __vma_link_list(mm, vma, prev);
+ if (vma->vm_file)
+ i_mmap_lock_write(vma->vm_file->f_mapping);
+ vma_mas_store(vma, mas);
mm->map_count++;
+ if (vma->vm_file) {
+ __vma_link_file(vma);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+ }
+
out:
perf_event_mmap(vma);
mm->total_vm += len >> PAGE_SHIFT;
@@ -3091,10 +3041,9 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
if (flags & VM_LOCKED)
mm->locked_vm += (len >> PAGE_SHIFT);
vma->vm_flags |= VM_SOFTDIRTY;
- validate_mm_mt(mm);
+ validate_mm(mm);
return 0;
-mas_store_fail:
vm_area_free(vma);
vma_alloc_fail:
vm_unacct_memory(len >> PAGE_SHIFT);
@@ -3128,9 +3077,7 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
if (mmap_write_lock_killable(mm))
return -EINTR;
- // This vma left intentionally blank.
- mas_walk(&mas);
- ret = do_brk_flags(&mas, vma, addr, len, flags);
+ ret = do_brk_flags(&mas, &mas, vma, addr, len, flags);
populate = ((mm->def_flags & VM_LOCKED) != 0);
mmap_write_unlock(mm);
if (populate && !ret)
@@ -3151,6 +3098,8 @@ void exit_mmap(struct mm_struct *mm)
struct mmu_gather tlb;
struct vm_area_struct *vma;
unsigned long nr_accounted = 0;
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
+ int count = 0;
/* mm's last user has gone, and its about to be pulled down */
mmu_notifier_release(mm);
@@ -3186,12 +3135,19 @@ void exit_mmap(struct mm_struct *mm)
* Lockdep will complain about not holding the mmap_lock, so we lie.
*/
rwsem_acquire(&mm->mmap_lock.dep_map, 0, 0, _THIS_IP_);
- if (mm->locked_vm)
- unlock_range(mm->mmap, &vma, ULONG_MAX);
+ if (mm->locked_vm) {
+ mas_for_each(&mas, vma, ULONG_MAX) {
+ if (vma->vm_flags & VM_LOCKED) {
+ mm->locked_vm -= vma_pages(vma);
+ munlock_vma_pages_all(vma);
+ }
+ }
+ mas_set(&mas, 0);
+ }
arch_exit_mmap(mm);
- vma = mm->mmap;
+ vma = mas_find(&mas, ULONG_MAX);
if (!vma) /* Can happen if dup_mmap() received an OOM */
return;
@@ -3200,20 +3156,24 @@ void exit_mmap(struct mm_struct *mm)
tlb_gather_mmu_fullmm(&tlb, mm);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
- unmap_vmas(&tlb, vma, 0, -1);
- free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
+ unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX);
+ free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb);
/*
- * Walk the list again, actually closing and freeing it,
- * with preemption enabled, without holding any MM locks.
+ * Walk the list again, actually closing and freeing it, with preemption
+ * enabled, without holding any MM locks besides the unreachable
+ * mmap_write_lock.
*/
- while (vma) {
+ do {
if (vma->vm_flags & VM_ACCOUNT)
nr_accounted += vma_pages(vma);
- vma = remove_vma(vma);
+ remove_vma(vma);
+ count++;
cond_resched();
- }
+ } while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
+
+ BUG_ON(count != mm->map_count);
trace_exit_mmap(mm);
__mt_destroy(&mm->mm_mt);
@@ -3254,7 +3214,7 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
}
- vma_link(mm, vma, prev);
+ vma_link(mm, vma);
return 0;
}
@@ -3282,7 +3242,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
faulted_in_anon_vma = false;
}
- if (range_has_overlap(mm, addr, addr + len, &prev))
+ new_vma = find_vma_prev(mm, addr, &prev);
+ if (new_vma->vm_start < addr + len)
return NULL; /* should never get here */
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
@@ -3325,7 +3286,7 @@ 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);
+ vma_link(mm, new_vma);
*need_rmap_locks = false;
}
validate_mm_mt(mm);
@@ -3625,12 +3586,13 @@ int mm_take_all_locks(struct mm_struct *mm)
{
struct vm_area_struct *vma;
struct anon_vma_chain *avc;
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
BUG_ON(mmap_read_trylock(mm));
mutex_lock(&mm_all_locks_mutex);
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ mas_for_each(&mas, vma, ULONG_MAX) {
if (signal_pending(current))
goto out_unlock;
if (vma->vm_file && vma->vm_file->f_mapping &&
@@ -3638,7 +3600,8 @@ int mm_take_all_locks(struct mm_struct *mm)
vm_lock_mapping(mm, vma->vm_file->f_mapping);
}
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ mas_set(&mas, 0);
+ mas_for_each(&mas, vma, ULONG_MAX) {
if (signal_pending(current))
goto out_unlock;
if (vma->vm_file && vma->vm_file->f_mapping &&
@@ -3646,7 +3609,8 @@ int mm_take_all_locks(struct mm_struct *mm)
vm_lock_mapping(mm, vma->vm_file->f_mapping);
}
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ mas_set(&mas, 0);
+ mas_for_each(&mas, vma, ULONG_MAX) {
if (signal_pending(current))
goto out_unlock;
if (vma->anon_vma)
@@ -3705,11 +3669,12 @@ void mm_drop_all_locks(struct mm_struct *mm)
{
struct vm_area_struct *vma;
struct anon_vma_chain *avc;
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
BUG_ON(mmap_read_trylock(mm));
BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ mas_for_each(&mas, vma, ULONG_MAX) {
if (vma->anon_vma)
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
vm_unlock_anon_vma(avc->anon_vma);
diff --git a/mm/nommu.c b/mm/nommu.c
index acb9aafb0afc..cb03f9c304d6 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -574,7 +574,6 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
mas_reset(&mas);
/* add the VMA to the tree */
vma_mas_store(vma, &mas);
- __vma_link_list(mm, vma, prev);
}
/*
@@ -599,7 +598,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
/* remove from the MM's tree and list */
vma_mas_remove(vma, &mas);
- __vma_unlink_list(vma->vm_mm, vma);
}
/*
diff --git a/mm/util.c b/mm/util.c
index ab02382c2d57..934a120d1c96 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -271,46 +271,6 @@ void *memdup_user_nul(const void __user *src, size_t len)
}
EXPORT_SYMBOL(memdup_user_nul);
-void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev)
-{
- struct vm_area_struct *next;
-
- vma->vm_prev = prev;
- if (prev) {
- next = prev->vm_next;
- prev->vm_next = vma;
- } else {
- next = mm->mmap;
- mm->mmap = 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)
-{
- struct vm_area_struct *prev, *next;
-
- next = vma->vm_next;
- prev = vma->vm_prev;
- if (prev)
- prev->vm_next = next;
- else
- mm->mmap = 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 */
int vma_is_stack_for_current(struct vm_area_struct *vma)
{
--
2.30.2