Re: [PATCH v2 00/12] uprobes: add batched register/unregister APIs and per-CPU RW semaphore

[Peter Zijlstra]

On Tue, Jul 02, 2024 at 01:54:47PM +0200, Peter Zijlstra wrote:

> @@ -668,12 +677,25 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
>  static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
>  {
>  	struct uprobe *uprobe;
> +	unsigned seq;
>  
> +	guard(rcu)();
>  
> +	do {
> +		seq = read_seqcount_begin(&uprobes_seqcount);
> +		uprobes = __find_uprobe(inode, offset);
> +		if (uprobes) {
> +			/*
> +			 * Lockless RB-tree lookups are prone to false-negatives.
> +			 * If they find something, it's good. If they do not find,
> +			 * it needs to be validated.
> +			 */
> +			return uprobes;
> +		}
> +	} while (read_seqcount_retry(&uprobes_seqcount, seq));
> +
> +	/* Really didn't find anything. */
> +	return NULL;
>  }
>  
>  static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
> @@ -702,7 +724,9 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe)
>  	struct uprobe *u;
>  
>  	write_lock(&uprobes_treelock);
> +	write_seqcount_begin(&uprobes_seqcount);
>  	u = __insert_uprobe(uprobe);
> +	write_seqcount_end(&uprobes_seqcount);
>  	write_unlock(&uprobes_treelock);
>  
>  	return u;

Strictly speaking I suppose we should add rb_find_rcu() and
rc_find_add_rcu() that sprinkle some rcu_dereference_raw() and
rb_link_node_rcu() around. See the examples in __lt_find() and
__lt_insert().