Skip to main content

Browse the archive

Revision a6a0251c6fce496744121b4e08c899f45270dbcc authored by Huang Ying on 18 October 2021, 22:15:35 UTC, committed by Linus Torvalds on 19 October 2021, 06:22:03 UTC 
mm/migrate: fix CPUHP state to update node demotion order
 
The node demotion order needs to be updated during CPU hotplug.  Because
whether a NUMA node has CPU may influence the demotion order.  The
update function should be called during CPU online/offline after the
node_states[N_CPU] has been updated.  That is done in
CPUHP_AP_ONLINE_DYN during CPU online and in CPUHP_MM_VMSTAT_DEAD during
CPU offline.  But in commit 884a6e5d1f93 ("mm/migrate: update node
demotion order on hotplug events"), the function to update node demotion
order is called in CPUHP_AP_ONLINE_DYN during CPU online/offline.  This
doesn't satisfy the order requirement.

For example, there are 4 CPUs (P0, P1, P2, P3) in 2 sockets (P0, P1 in S0
and P2, P3 in S1), the demotion order is

 - S0 -> NUMA_NO_NODE
 - S1 -> NUMA_NO_NODE

After P2 and P3 is offlined, because S1 has no CPU now, the demotion
order should have been changed to

 - S0 -> S1
 - S1 -> NO_NODE

but it isn't changed, because the order updating callback for CPU
hotplug doesn't see the new nodemask.  After that, if P1 is offlined,
the demotion order is changed to the expected order as above.

So in this patch, we added CPUHP_AP_MM_DEMOTION_ONLINE and
CPUHP_MM_DEMOTION_DEAD to be called after CPUHP_AP_ONLINE_DYN and
CPUHP_MM_VMSTAT_DEAD during CPU online and offline, and register the
update function on them.

Link: https://lkml.kernel.org/r/20210929060351.7293-1-ying.huang@intel.com
Fixes: 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Wei Xu <weixugc@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Keith Busch <kbusch@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 76af6a0
Raw File
interval_tree.c 
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/interval_tree.c - interval tree for mapping->i_mmap
 *
 * Copyright (C) 2012, Michel Lespinasse <walken@google.com>
 */

#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/rmap.h>
#include <linux/interval_tree_generic.h>

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 + vma_pages(v) - 1;
}

INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb,
		     unsigned long, shared.rb_subtree_last,
		     vma_start_pgoff, vma_last_pgoff, /* empty */, 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_cached *root)
{
	struct rb_node **link;
	struct vm_area_struct *parent;
	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) {
		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->rb_root,
			    &vma_interval_tree_augment);
}

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_cached *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_cached *root)
{
	__anon_vma_interval_tree_remove(node, root);
}

struct anon_vma_chain *
anon_vma_interval_tree_iter_first(struct rb_root_cached *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
back to top