Skip to main content

Browse the archive

Revision 3f758e844aa9800eb660d60ee10226fa802594d4 authored by Paolo Valente on 07 August 2019, 14:17:54 UTC, committed by Jens Axboe on 08 August 2019, 13:30:52 UTC 
block, bfq: move update of waker and woken list to queue freeing
 
Since commit 13a857a4c4e8 ("block, bfq: detect wakers and
unconditionally inject their I/O"), every bfq_queue has a pointer to a
waker bfq_queue and a list of the bfq_queues it may wake. In this
respect, when a bfq_queue, say Q, remains with no I/O source attached
to it, Q cannot be woken by any other bfq_queue, and cannot wake any
other bfq_queue. Then Q must be removed from the woken list of its
possible waker bfq_queue, and all bfq_queues in the woken list of Q
must stop having a waker bfq_queue.

Q remains with no I/O source in two cases: when the last process
associated with Q exits or when such a process gets associated with a
different bfq_queue. Unfortunately, commit 13a857a4c4e8 ("block, bfq:
detect wakers and unconditionally inject their I/O") performed the
above updates only in the first case.

This commit fixes this bug by moving these updates to when Q gets
freed. This is a simple and safe way to handle all cases, as both the
above events, process exit and re-association, lead to Q being freed
soon, and because dangling references would come out only after Q gets
freed (if no update were performed).

Fixes: 13a857a4c4e8 ("block, bfq: detect wakers and unconditionally inject their I/O")
Reported-by: Douglas Anderson <dianders@chromium.org>
Tested-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
1 parent 08d383a
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,, 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