linux-kernel - Re: [PATCH 1/3] kvfree_rcu: Allocate a page for a single argument

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20210120184046.GE2743@paulmck-ThinkPad-P72>
Date:   Wed, 20 Jan 2021 10:40:46 -0800
From:   "Paul E. McKenney" <paulmck@...nel.org>
To:     "Uladzislau Rezki (Sony)" <urezki@...il.com>
Cc:     LKML <linux-kernel@...r.kernel.org>, RCU <rcu@...r.kernel.org>,
        Michael Ellerman <mpe@...erman.id.au>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Daniel Axtens <dja@...ens.net>,
        Frederic Weisbecker <frederic@...nel.org>,
        Neeraj Upadhyay <neeraju@...eaurora.org>,
        Joel Fernandes <joel@...lfernandes.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Michal Hocko <mhocko@...e.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        "Theodore Y . Ts'o" <tytso@....edu>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Oleksiy Avramchenko <oleksiy.avramchenko@...ymobile.com>
Subject: Re: [PATCH 1/3] kvfree_rcu: Allocate a page for a single argument

On Wed, Jan 20, 2021 at 05:21:46PM +0100, Uladzislau Rezki (Sony) wrote:
> For a single argument we can directly request a page from a caller
> context when a "carry page block" is run out of free spots. Instead
> of hitting a slow path we can request an extra page by demand and
> proceed with a fast path.
> 
> A single-argument kvfree_rcu() must be invoked in sleepable contexts,
> and that its fallback is the relatively high latency synchronize_rcu().
> Single-argument kvfree_rcu() therefore uses GFP_KERNEL|__GFP_RETRY_MAYFAIL
> to allow limited sleeping within the memory allocator.
> 
> [ paulmck: Add add_ptr_to_bulk_krc_lock header comment per Michal Hocko. ]
> Signed-off-by: Uladzislau Rezki (Sony) <urezki@...il.com>
> Signed-off-by: Paul E. McKenney <paulmck@...nel.org>

Queued all three for review and testing, thank you!

							Thanx, Paul

> ---
>  kernel/rcu/tree.c | 42 ++++++++++++++++++++++++++----------------
>  1 file changed, 26 insertions(+), 16 deletions(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index e04e336bee42..2014fb22644d 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -3465,37 +3465,50 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
>  	}
>  }
>  
> +// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
> +// state specified by flags.  If can_alloc is true, the caller must
> +// be schedulable and not be holding any locks or mutexes that might be
> +// acquired by the memory allocator or anything that it might invoke.
> +// Returns true if ptr was successfully recorded, else the caller must
> +// use a fallback.
>  static inline bool
> -kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
> +add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
> +	unsigned long *flags, void *ptr, bool can_alloc)
>  {
>  	struct kvfree_rcu_bulk_data *bnode;
>  	int idx;
>  
> -	if (unlikely(!krcp->initialized))
> +	*krcp = krc_this_cpu_lock(flags);
> +	if (unlikely(!(*krcp)->initialized))
>  		return false;
>  
> -	lockdep_assert_held(&krcp->lock);
>  	idx = !!is_vmalloc_addr(ptr);
>  
>  	/* Check if a new block is required. */
> -	if (!krcp->bkvhead[idx] ||
> -			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
> -		bnode = get_cached_bnode(krcp);
> -		/* Switch to emergency path. */
> +	if (!(*krcp)->bkvhead[idx] ||
> +			(*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
> +		bnode = get_cached_bnode(*krcp);
> +		if (!bnode && can_alloc) {
> +			krc_this_cpu_unlock(*krcp, *flags);
> +			bnode = (struct kvfree_rcu_bulk_data *)
> +				__get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
> +			*krcp = krc_this_cpu_lock(flags);
> +		}
> +
>  		if (!bnode)
>  			return false;
>  
>  		/* Initialize the new block. */
>  		bnode->nr_records = 0;
> -		bnode->next = krcp->bkvhead[idx];
> +		bnode->next = (*krcp)->bkvhead[idx];
>  
>  		/* Attach it to the head. */
> -		krcp->bkvhead[idx] = bnode;
> +		(*krcp)->bkvhead[idx] = bnode;
>  	}
>  
>  	/* Finally insert. */
> -	krcp->bkvhead[idx]->records
> -		[krcp->bkvhead[idx]->nr_records++] = ptr;
> +	(*krcp)->bkvhead[idx]->records
> +		[(*krcp)->bkvhead[idx]->nr_records++] = ptr;
>  
>  	return true;
>  }
> @@ -3533,8 +3546,6 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
>  		ptr = (unsigned long *) func;
>  	}
>  
> -	krcp = krc_this_cpu_lock(&flags);
> -
>  	// Queue the object but don't yet schedule the batch.
>  	if (debug_rcu_head_queue(ptr)) {
>  		// Probable double kfree_rcu(), just leak.
> @@ -3542,12 +3553,11 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
>  			  __func__, head);
>  
>  		// Mark as success and leave.
> -		success = true;
> -		goto unlock_return;
> +		return;
>  	}
>  
>  	kasan_record_aux_stack(ptr);
> -	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
> +	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
>  	if (!success) {
>  		run_page_cache_worker(krcp);
>  
> -- 
> 2.20.1
>