mm: protect mm_rb tree with a rwlock
This change is inspired by the Peter's proposal patch [1] which was
protecting the VMA using SRCU. Unfortunately, SRCU is not scaling well in
that particular case, and it is introducing major performance degradation
due to excessive scheduling operations.
To allow access to the mm_rb tree without grabbing the mmap_sem, this patch
is protecting it access using a rwlock. As the mm_rb tree is a O(log n)
search it is safe to protect it using such a lock. The VMA cache is not
protected by the new rwlock and it should not be used without holding the
mmap_sem.
To allow the picked VMA structure to be used once the rwlock is released, a
use count is added to the VMA structure. When the VMA is allocated it is
set to 1. Each time the VMA is picked with the rwlock held its use count
is incremented. Each time the VMA is released it is decremented. When the
use count hits zero, this means that the VMA is no more used and should be
freed.
This patch is preparing for 2 kind of VMA access :
- as usual, under the control of the mmap_sem,
- without holding the mmap_sem for the speculative page fault handler.
Access done under the control the mmap_sem doesn't require to grab the
rwlock to protect read access to the mm_rb tree, but access in write must
be done under the protection of the rwlock too. This affects inserting and
removing of elements in the RB tree.
The patch is introducing 2 new functions:
- vma_get() to find a VMA based on an address by holding the new rwlock.
- vma_put() to release the VMA when its no more used.
These services are designed to be used when access are made to the RB tree
without holding the mmap_sem.
When a VMA is removed from the RB tree, its vma->vm_rb field is cleared and
we rely on the WMB done when releasing the rwlock to serialize the write
with the RMB done in a later patch to check for the VMA's validity.
When free_vma is called, the file associated with the VMA is closed
immediately, but the policy and the file structure remained in used until
the VMA's use count reach 0, which may happens later when exiting an
in progress speculative page fault.
[1] https://patchwork.kernel.org/patch/5108281/
Change-Id: I9ecc922b8efa4b28975cc6a8e9531284c24ac14e
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Patch-mainline: linux-mm @ Tue, 17 Apr 2018 16:33:23
[vinmenon@codeaurora.org: fix the return of put_vma]
Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a4143ec..a432b68 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1187,6 +1187,7 @@
INIT_LIST_HEAD(&vma->anon_vma_chain);
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
seqcount_init(&vma->vm_sequence);
+ atomic_set(&vma->vm_ref_count, 1);
#endif
}
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0568861..cb2cc30 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -367,6 +367,7 @@
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
seqcount_t vm_sequence;
+ atomic_t vm_ref_count; /* see vma_get(), vma_put() */
#endif
};
@@ -406,6 +407,9 @@
struct mm_struct {
struct vm_area_struct *mmap; /* list of VMAs */
struct rb_root mm_rb;
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+ rwlock_t mm_rb_lock;
+#endif
u32 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_MMU
unsigned long (*get_unmapped_area) (struct file *filp,
diff --git a/kernel/fork.c b/kernel/fork.c
index 89ee0bb..965c091 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -764,6 +764,9 @@
mm->mmap = NULL;
mm->mm_rb = RB_ROOT;
mm->vmacache_seqnum = 0;
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+ rwlock_init(&mm->mm_rb_lock);
+#endif
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 975e49f..4d21629 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -16,6 +16,9 @@
struct mm_struct init_mm = {
.mm_rb = RB_ROOT,
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+ .mm_rb_lock = __RW_LOCK_UNLOCKED(init_mm.mm_rb_lock),
+#endif
.pgd = swapper_pg_dir,
.mm_users = ATOMIC_INIT(2),
.mm_count = ATOMIC_INIT(1),
diff --git a/mm/internal.h b/mm/internal.h
index 6aa1c51..ba41583 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -38,6 +38,12 @@
int do_swap_page(struct fault_env *fe, pte_t orig_pte);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+extern struct vm_area_struct *get_vma(struct mm_struct *mm,
+ unsigned long addr);
+extern void put_vma(struct vm_area_struct *vma);
+#endif
+
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
diff --git a/mm/mmap.c b/mm/mmap.c
index 17b8308..f549597 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -160,6 +160,27 @@
}
}
+static void __free_vma(struct vm_area_struct *vma)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ mpol_put(vma_policy(vma));
+ kmem_cache_free(vm_area_cachep, vma);
+}
+
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+void put_vma(struct vm_area_struct *vma)
+{
+ if (atomic_dec_and_test(&vma->vm_ref_count))
+ __free_vma(vma);
+}
+#else
+static inline void put_vma(struct vm_area_struct *vma)
+{
+ __free_vma(vma);
+}
+#endif
+
/*
* Close a vm structure and free it, returning the next.
*/
@@ -170,10 +191,7 @@
might_sleep();
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
- if (vma->vm_file)
- fput(vma->vm_file);
- mpol_put(vma_policy(vma));
- kmem_cache_free(vm_area_cachep, vma);
+ put_vma(vma);
return next;
}
@@ -391,6 +409,14 @@
#define validate_mm(mm) do { } while (0)
#endif
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+#define mm_rb_write_lock(mm) write_lock(&(mm)->mm_rb_lock)
+#define mm_rb_write_unlock(mm) write_unlock(&(mm)->mm_rb_lock)
+#else
+#define mm_rb_write_lock(mm) do { } while (0)
+#define mm_rb_write_unlock(mm) do { } while (0)
+#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */
+
RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb,
unsigned long, rb_subtree_gap, vma_compute_subtree_gap)
@@ -409,26 +435,37 @@
}
static inline void vma_rb_insert(struct vm_area_struct *vma,
- struct rb_root *root)
+ struct mm_struct *mm)
{
+ struct rb_root *root = &mm->mm_rb;
+
/* 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)
+static void __vma_rb_erase(struct vm_area_struct *vma, struct mm_struct *mm)
{
+ struct rb_root *root = &mm->mm_rb;
/*
* Note rb_erase_augmented is a fairly large inline function,
* so make sure we instantiate it only once with our desired
* augmented rbtree callbacks.
*/
+ mm_rb_write_lock(mm);
rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
+ mm_rb_write_unlock(mm); /* wmb */
+
+ /*
+ * Ensure the removal is complete before clearing the node.
+ * Matched by vma_has_changed()/handle_speculative_fault().
+ */
+ RB_CLEAR_NODE(&vma->vm_rb);
}
static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
- struct rb_root *root,
+ struct mm_struct *mm,
struct vm_area_struct *ignore)
{
/*
@@ -436,21 +473,21 @@
* with the possible exception of the "next" vma being erased if
* next->vm_start was reduced.
*/
- validate_mm_rb(root, ignore);
+ validate_mm_rb(&mm->mm_rb, ignore);
- __vma_rb_erase(vma, root);
+ __vma_rb_erase(vma, mm);
}
static __always_inline void vma_rb_erase(struct vm_area_struct *vma,
- struct rb_root *root)
+ struct mm_struct *mm)
{
/*
* All rb_subtree_gap values must be consistent prior to erase,
* with the possible exception of the vma being erased.
*/
- validate_mm_rb(root, vma);
+ validate_mm_rb(&mm->mm_rb, vma);
- __vma_rb_erase(vma, root);
+ __vma_rb_erase(vma, mm);
}
/*
@@ -565,10 +602,12 @@
* immediately update the gap to the correct value. Finally we
* rebalance the rbtree after all augmented values have been set.
*/
+ mm_rb_write_lock(mm);
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);
+ vma_rb_insert(vma, mm);
+ mm_rb_write_unlock(mm);
}
static void __vma_link_file(struct vm_area_struct *vma)
@@ -644,7 +683,7 @@
{
struct vm_area_struct *next;
- vma_rb_erase_ignore(vma, &mm->mm_rb, ignore);
+ vma_rb_erase_ignore(vma, mm, ignore);
next = vma->vm_next;
if (has_prev)
prev->vm_next = next;
@@ -921,16 +960,13 @@
}
if (remove_next) {
- if (file) {
+ if (file)
uprobe_munmap(next, next->vm_start, next->vm_end);
- fput(file);
- }
if (next->anon_vma)
anon_vma_merge(vma, next);
mm->map_count--;
- mpol_put(vma_policy(next));
vm_raw_write_end(next);
- kmem_cache_free(vm_area_cachep, next);
+ put_vma(next);
/*
* In mprotect's case 6 (see comments on vma_merge),
* we must remove another next too. It would clutter
@@ -2161,15 +2197,11 @@
EXPORT_SYMBOL(get_unmapped_area);
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
-struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+static struct vm_area_struct *__find_vma(struct mm_struct *mm,
+ unsigned long addr)
{
struct rb_node *rb_node;
- struct vm_area_struct *vma;
-
- /* Check the cache first. */
- vma = vmacache_find(mm, addr);
- if (likely(vma))
- return vma;
+ struct vm_area_struct *vma = NULL;
rb_node = mm->mm_rb.rb_node;
@@ -2187,13 +2219,40 @@
rb_node = rb_node->rb_right;
}
+ return vma;
+}
+
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma;
+
+ /* Check the cache first. */
+ vma = vmacache_find(mm, addr);
+ if (likely(vma))
+ return vma;
+
+ vma = __find_vma(mm, addr);
if (vma)
vmacache_update(addr, vma);
return vma;
}
-
EXPORT_SYMBOL(find_vma);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+struct vm_area_struct *get_vma(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma = NULL;
+
+ read_lock(&mm->mm_rb_lock);
+ vma = __find_vma(mm, addr);
+ if (vma)
+ atomic_inc(&vma->vm_ref_count);
+ read_unlock(&mm->mm_rb_lock);
+
+ return vma;
+}
+#endif
+
/*
* Same as find_vma, but also return a pointer to the previous VMA in *pprev.
*/
@@ -2566,7 +2625,7 @@
insertion_point = (prev ? &prev->vm_next : &mm->mmap);
vma->vm_prev = NULL;
do {
- vma_rb_erase(vma, &mm->mm_rb);
+ vma_rb_erase(vma, mm);
mm->map_count--;
tail_vma = vma;
vma = vma->vm_next;