linux/mm/interval_tree.c

113 lines
3.1 KiB
C
Raw Normal View History

/*
* mm/interval_tree.c - interval tree for mapping->i_mmap
*
* Copyright (C) 2012, Michel Lespinasse <walken@google.com>
*
* This file is released under the GPL v2.
*/
#include <linux/mm.h>
#include <linux/fs.h>
mm anon rmap: replace same_anon_vma linked list with an interval tree. When a large VMA (anon or private file mapping) is first touched, which will populate its anon_vma field, and then split into many regions through the use of mprotect(), the original anon_vma ends up linking all of the vmas on a linked list. This can cause rmap to become inefficient, as we have to walk potentially thousands of irrelevent vmas before finding the one a given anon page might fall into. By replacing the same_anon_vma linked list with an interval tree (where each avc's interval is determined by its vma's start and last pgoffs), we can make rmap efficient for this use case again. While the change is large, all of its pieces are fairly simple. Most places that were walking the same_anon_vma list were looking for a known pgoff, so they can just use the anon_vma_interval_tree_foreach() interval tree iterator instead. The exception here is ksm, where the page's index is not known. It would probably be possible to rework ksm so that the index would be known, but for now I have decided to keep things simple and just walk the entirety of the interval tree there. When updating vma's that already have an anon_vma assigned, we must take care to re-index the corresponding avc's on their interval tree. This is done through the use of anon_vma_interval_tree_pre_update_vma() and anon_vma_interval_tree_post_update_vma(), which remove the avc's from their interval tree before the update and re-insert them after the update. The anon_vma stays locked during the update, so there is no chance that rmap would miss the vmas that are being updated. Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:39 +08:00
#include <linux/rmap.h>
mm: interval tree updates Update the generic interval tree code that was introduced in "mm: replace vma prio_tree with an interval tree". Changes: - fixed 'endpoing' typo noticed by Andrew Morton - replaced include/linux/interval_tree_tmpl.h, which was used as a template (including it automatically defined the interval tree functions) with include/linux/interval_tree_generic.h, which only defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself defines the interval tree functions when invoked. Now that is a very long macro which is unfortunate, but it does make the usage sites (lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously. - make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro, instead of duplicating that code in the interval tree template. - replaced vma_interval_tree_add(), which was actually handling the nonlinear and interval tree cases, with vma_interval_tree_insert_after() which handles only the interval tree case and has an API that is more consistent with the other interval tree handling functions. The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap(). Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:35 +08:00
#include <linux/interval_tree_generic.h>
mm: interval tree updates Update the generic interval tree code that was introduced in "mm: replace vma prio_tree with an interval tree". Changes: - fixed 'endpoing' typo noticed by Andrew Morton - replaced include/linux/interval_tree_tmpl.h, which was used as a template (including it automatically defined the interval tree functions) with include/linux/interval_tree_generic.h, which only defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself defines the interval tree functions when invoked. Now that is a very long macro which is unfortunate, but it does make the usage sites (lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously. - make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro, instead of duplicating that code in the interval tree template. - replaced vma_interval_tree_add(), which was actually handling the nonlinear and interval tree cases, with vma_interval_tree_insert_after() which handles only the interval tree case and has an API that is more consistent with the other interval tree handling functions. The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap(). Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:35 +08:00
static inline unsigned long vma_start_pgoff(struct vm_area_struct *v)
{
return v->vm_pgoff;
}
static inline unsigned long vma_last_pgoff(struct vm_area_struct *v)
{
return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1;
}
INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb,
unsigned long, shared.rb_subtree_last,
mm: interval tree updates Update the generic interval tree code that was introduced in "mm: replace vma prio_tree with an interval tree". Changes: - fixed 'endpoing' typo noticed by Andrew Morton - replaced include/linux/interval_tree_tmpl.h, which was used as a template (including it automatically defined the interval tree functions) with include/linux/interval_tree_generic.h, which only defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself defines the interval tree functions when invoked. Now that is a very long macro which is unfortunate, but it does make the usage sites (lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously. - make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro, instead of duplicating that code in the interval tree template. - replaced vma_interval_tree_add(), which was actually handling the nonlinear and interval tree cases, with vma_interval_tree_insert_after() which handles only the interval tree case and has an API that is more consistent with the other interval tree handling functions. The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap(). Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:35 +08:00
vma_start_pgoff, vma_last_pgoff,, vma_interval_tree)
/* Insert node immediately after prev in the interval tree */
void vma_interval_tree_insert_after(struct vm_area_struct *node,
struct vm_area_struct *prev,
struct rb_root *root)
{
struct rb_node **link;
struct vm_area_struct *parent;
mm: interval tree updates Update the generic interval tree code that was introduced in "mm: replace vma prio_tree with an interval tree". Changes: - fixed 'endpoing' typo noticed by Andrew Morton - replaced include/linux/interval_tree_tmpl.h, which was used as a template (including it automatically defined the interval tree functions) with include/linux/interval_tree_generic.h, which only defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself defines the interval tree functions when invoked. Now that is a very long macro which is unfortunate, but it does make the usage sites (lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously. - make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro, instead of duplicating that code in the interval tree template. - replaced vma_interval_tree_add(), which was actually handling the nonlinear and interval tree cases, with vma_interval_tree_insert_after() which handles only the interval tree case and has an API that is more consistent with the other interval tree handling functions. The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap(). Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:35 +08:00
unsigned long last = vma_last_pgoff(node);
VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);
if (!prev->shared.rb.rb_right) {
mm: interval tree updates Update the generic interval tree code that was introduced in "mm: replace vma prio_tree with an interval tree". Changes: - fixed 'endpoing' typo noticed by Andrew Morton - replaced include/linux/interval_tree_tmpl.h, which was used as a template (including it automatically defined the interval tree functions) with include/linux/interval_tree_generic.h, which only defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself defines the interval tree functions when invoked. Now that is a very long macro which is unfortunate, but it does make the usage sites (lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously. - make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro, instead of duplicating that code in the interval tree template. - replaced vma_interval_tree_add(), which was actually handling the nonlinear and interval tree cases, with vma_interval_tree_insert_after() which handles only the interval tree case and has an API that is more consistent with the other interval tree handling functions. The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap(). Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:35 +08:00
parent = prev;
link = &prev->shared.rb.rb_right;
} else {
parent = rb_entry(prev->shared.rb.rb_right,
struct vm_area_struct, shared.rb);
if (parent->shared.rb_subtree_last < last)
parent->shared.rb_subtree_last = last;
while (parent->shared.rb.rb_left) {
parent = rb_entry(parent->shared.rb.rb_left,
struct vm_area_struct, shared.rb);
if (parent->shared.rb_subtree_last < last)
parent->shared.rb_subtree_last = last;
}
link = &parent->shared.rb.rb_left;
}
node->shared.rb_subtree_last = last;
rb_link_node(&node->shared.rb, &parent->shared.rb, link);
rb_insert_augmented(&node->shared.rb, root,
mm: interval tree updates Update the generic interval tree code that was introduced in "mm: replace vma prio_tree with an interval tree". Changes: - fixed 'endpoing' typo noticed by Andrew Morton - replaced include/linux/interval_tree_tmpl.h, which was used as a template (including it automatically defined the interval tree functions) with include/linux/interval_tree_generic.h, which only defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself defines the interval tree functions when invoked. Now that is a very long macro which is unfortunate, but it does make the usage sites (lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously. - make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro, instead of duplicating that code in the interval tree template. - replaced vma_interval_tree_add(), which was actually handling the nonlinear and interval tree cases, with vma_interval_tree_insert_after() which handles only the interval tree case and has an API that is more consistent with the other interval tree handling functions. The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap(). Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:35 +08:00
&vma_interval_tree_augment);
}
mm anon rmap: replace same_anon_vma linked list with an interval tree. When a large VMA (anon or private file mapping) is first touched, which will populate its anon_vma field, and then split into many regions through the use of mprotect(), the original anon_vma ends up linking all of the vmas on a linked list. This can cause rmap to become inefficient, as we have to walk potentially thousands of irrelevent vmas before finding the one a given anon page might fall into. By replacing the same_anon_vma linked list with an interval tree (where each avc's interval is determined by its vma's start and last pgoffs), we can make rmap efficient for this use case again. While the change is large, all of its pieces are fairly simple. Most places that were walking the same_anon_vma list were looking for a known pgoff, so they can just use the anon_vma_interval_tree_foreach() interval tree iterator instead. The exception here is ksm, where the page's index is not known. It would probably be possible to rework ksm so that the index would be known, but for now I have decided to keep things simple and just walk the entirety of the interval tree there. When updating vma's that already have an anon_vma assigned, we must take care to re-index the corresponding avc's on their interval tree. This is done through the use of anon_vma_interval_tree_pre_update_vma() and anon_vma_interval_tree_post_update_vma(), which remove the avc's from their interval tree before the update and re-insert them after the update. The anon_vma stays locked during the update, so there is no chance that rmap would miss the vmas that are being updated. Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Santos <daniel.santos@pobox.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:31:39 +08:00
static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc)
{
return vma_start_pgoff(avc->vma);
}
static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc)
{
return vma_last_pgoff(avc->vma);
}
INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last,
avc_start_pgoff, avc_last_pgoff,
static inline, __anon_vma_interval_tree)
void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
struct rb_root *root)
{
#ifdef CONFIG_DEBUG_VM_RB
node->cached_vma_start = avc_start_pgoff(node);
node->cached_vma_last = avc_last_pgoff(node);
#endif
__anon_vma_interval_tree_insert(node, root);
}
void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
struct rb_root *root)
{
__anon_vma_interval_tree_remove(node, root);
}
struct anon_vma_chain *
anon_vma_interval_tree_iter_first(struct rb_root *root,
unsigned long first, unsigned long last)
{
return __anon_vma_interval_tree_iter_first(root, first, last);
}
struct anon_vma_chain *
anon_vma_interval_tree_iter_next(struct anon_vma_chain *node,
unsigned long first, unsigned long last)
{
return __anon_vma_interval_tree_iter_next(node, first, last);
}
#ifdef CONFIG_DEBUG_VM_RB
void anon_vma_interval_tree_verify(struct anon_vma_chain *node)
{
WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node));
WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node));
}
#endif