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  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]
Date:   Sun, 3 May 2020 19:42:50 -0400
From:   Joel Fernandes <joel@...lfernandes.org>
To:     "Paul E. McKenney" <paulmck@...nel.org>
Cc:     "Uladzislau Rezki (Sony)" <urezki@...il.com>,
        LKML <linux-kernel@...r.kernel.org>, linux-mm@...ck.org,
        Andrew Morton <akpm@...ux-foundation.org>,
        "Theodore Y . Ts'o" <tytso@....edu>,
        Matthew Wilcox <willy@...radead.org>,
        RCU <rcu@...r.kernel.org>,
        Oleksiy Avramchenko <oleksiy.avramchenko@...ymobile.com>
Subject: Re: [PATCH 11/24] rcu/tree: Maintain separate array for vmalloc ptrs

On Fri, May 01, 2020 at 02:37:53PM -0700, Paul E. McKenney wrote:
[...]
> > @@ -2993,41 +2994,73 @@ put_cached_bnode(struct kfree_rcu_cpu *krcp,
> >  static void kfree_rcu_work(struct work_struct *work)
> >  {
> >  	unsigned long flags;
> > +	struct kvfree_rcu_bulk_data *bkhead, *bvhead, *bnext;
> >  	struct rcu_head *head, *next;
> > -	struct kfree_rcu_bulk_data *bhead, *bnext;
> >  	struct kfree_rcu_cpu *krcp;
> >  	struct kfree_rcu_cpu_work *krwp;
> > +	int i;
> >  
> >  	krwp = container_of(to_rcu_work(work),
> >  			    struct kfree_rcu_cpu_work, rcu_work);
> >  	krcp = krwp->krcp;
> > +
> >  	raw_spin_lock_irqsave(&krcp->lock, flags);
> > +	/* Channel 1. */
> > +	bkhead = krwp->bkvhead_free[0];
> > +	krwp->bkvhead_free[0] = NULL;
> > +
> > +	/* Channel 2. */
> > +	bvhead = krwp->bkvhead_free[1];
> > +	krwp->bkvhead_free[1] = NULL;
> > +
> > +	/* Channel 3. */
> >  	head = krwp->head_free;
> >  	krwp->head_free = NULL;
> > -	bhead = krwp->bhead_free;
> > -	krwp->bhead_free = NULL;
> >  	raw_spin_unlock_irqrestore(&krcp->lock, flags);
> >  
> > -	/* "bhead" is now private, so traverse locklessly. */
> > -	for (; bhead; bhead = bnext) {
> > -		bnext = bhead->next;
> > -
> > -		debug_rcu_bhead_unqueue(bhead);
> > +	/* kmalloc()/kfree() channel. */
> > +	for (; bkhead; bkhead = bnext) {
> > +		bnext = bkhead->next;
> > +		debug_rcu_bhead_unqueue(bkhead);
> >  
> >  		rcu_lock_acquire(&rcu_callback_map);
> 
> Given that rcu_lock_acquire() only affects lockdep, I have to ask exactly
> what concurrency design you are using here...

I believe the rcu_callback_map usage above follows a similar pattern from old
code where the rcu_callback_map is acquired before doing the kfree.

static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
{
        rcu_callback_t f;
        unsigned long offset = (unsigned long)head->func;

        rcu_lock_acquire(&rcu_callback_map);
        if (__is_kfree_rcu_offset(offset)) {
                trace_rcu_invoke_kfree_callback(rn, head, offset);
                kfree((void *)head - offset);
                rcu_lock_release(&rcu_callback_map);

So when kfree_rcu() was rewritten, the rcu_lock_acquire() of rcu_callback_map
got carried.

I believe it is for detecting recursion where we possibly try to free
RCU-held memory while already freeing memory. Or was there anoher purpose of
the rcu_callback_map?

thanks,

 - Joel


> >  		trace_rcu_invoke_kfree_bulk_callback(rcu_state.name,
> > -			bhead->nr_records, bhead->records);
> > +			bkhead->nr_records, bkhead->records);
> > +
> > +		kfree_bulk(bkhead->nr_records, bkhead->records);
> > +		rcu_lock_release(&rcu_callback_map);
> > +
> > +		krcp = krc_this_cpu_lock(&flags);
> > +		if (put_cached_bnode(krcp, bkhead))
> > +			bkhead = NULL;
> > +		krc_this_cpu_unlock(krcp, flags);
> > +
> > +		if (bkhead)
> > +			free_page((unsigned long) bkhead);
> > +
> > +		cond_resched_tasks_rcu_qs();
> > +	}
> > +
> > +	/* vmalloc()/vfree() channel. */
> > +	for (; bvhead; bvhead = bnext) {
> > +		bnext = bvhead->next;
> > +		debug_rcu_bhead_unqueue(bvhead);
> >  
> > -		kfree_bulk(bhead->nr_records, bhead->records);
> > +		rcu_lock_acquire(&rcu_callback_map);
> 
> And the same here.
> 
> > +		for (i = 0; i < bvhead->nr_records; i++) {
> > +			trace_rcu_invoke_kfree_callback(rcu_state.name,
> > +				(struct rcu_head *) bvhead->records[i], 0);
> > +			vfree(bvhead->records[i]);
> > +		}
> >  		rcu_lock_release(&rcu_callback_map);
> >  
> >  		krcp = krc_this_cpu_lock(&flags);
> > -		if (put_cached_bnode(krcp, bhead))
> > -			bhead = NULL;
> > +		if (put_cached_bnode(krcp, bvhead))
> > +			bvhead = NULL;
> >  		krc_this_cpu_unlock(krcp, flags);
> >  
> > -		if (bhead)
> > -			free_page((unsigned long) bhead);
> > +		if (bvhead)
> > +			free_page((unsigned long) bvhead);
> >  
> >  		cond_resched_tasks_rcu_qs();
> >  	}
> > @@ -3047,7 +3080,7 @@ static void kfree_rcu_work(struct work_struct *work)
> >  		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
> >  
> >  		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset)))
> > -			kfree(ptr);
> > +			kvfree(ptr);
> >  
> >  		rcu_lock_release(&rcu_callback_map);
> >  		cond_resched_tasks_rcu_qs();
> > @@ -3072,21 +3105,34 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
> >  		krwp = &(krcp->krw_arr[i]);
> >  
> >  		/*
> > -		 * Try to detach bhead or head and attach it over any
> > +		 * Try to detach bkvhead or head and attach it over any
> >  		 * available corresponding free channel. It can be that
> >  		 * a previous RCU batch is in progress, it means that
> >  		 * immediately to queue another one is not possible so
> >  		 * return false to tell caller to retry.
> >  		 */
> > -		if ((krcp->bhead && !krwp->bhead_free) ||
> > +		if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
> > +			(krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
> >  				(krcp->head && !krwp->head_free)) {
> > -			/* Channel 1. */
> > -			if (!krwp->bhead_free) {
> > -				krwp->bhead_free = krcp->bhead;
> > -				krcp->bhead = NULL;
> > +			/*
> > +			 * Channel 1 corresponds to SLAB ptrs.
> > +			 */
> > +			if (!krwp->bkvhead_free[0]) {
> > +				krwp->bkvhead_free[0] = krcp->bkvhead[0];
> > +				krcp->bkvhead[0] = NULL;
> >  			}
> >  
> > -			/* Channel 2. */
> > +			/*
> > +			 * Channel 2 corresponds to vmalloc ptrs.
> > +			 */
> > +			if (!krwp->bkvhead_free[1]) {
> > +				krwp->bkvhead_free[1] = krcp->bkvhead[1];
> > +				krcp->bkvhead[1] = NULL;
> > +			}
> 
> Why not a "for" loop here?  Duplicate code is most certainly not what
> we want, as it can cause all sorts of trouble down the road.
> 
> 							Thanx, Paul
> 
> > +			/*
> > +			 * Channel 3 corresponds to emergency path.
> > +			 */
> >  			if (!krwp->head_free) {
> >  				krwp->head_free = krcp->head;
> >  				krcp->head = NULL;
> > @@ -3095,16 +3141,17 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
> >  			WRITE_ONCE(krcp->count, 0);
> >  
> >  			/*
> > -			 * One work is per one batch, so there are two "free channels",
> > -			 * "bhead_free" and "head_free" the batch can handle. It can be
> > -			 * that the work is in the pending state when two channels have
> > -			 * been detached following each other, one by one.
> > +			 * One work is per one batch, so there are three
> > +			 * "free channels", the batch can handle. It can
> > +			 * be that the work is in the pending state when
> > +			 * channels have been detached following by each
> > +			 * other.
> >  			 */
> >  			queue_rcu_work(system_wq, &krwp->rcu_work);
> >  		}
> >  
> >  		/* Repeat if any "free" corresponding channel is still busy. */
> > -		if (krcp->bhead || krcp->head)
> > +		if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head)
> >  			repeat = true;
> >  	}
> >  
> > @@ -3146,23 +3193,22 @@ static void kfree_rcu_monitor(struct work_struct *work)
> >  }
> >  
> >  static inline bool
> > -kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
> > -	struct rcu_head *head, rcu_callback_t func)
> > +kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
> >  {
> > -	struct kfree_rcu_bulk_data *bnode;
> > +	struct kvfree_rcu_bulk_data *bnode;
> > +	int idx;
> >  
> >  	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->bhead ||
> > -			krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) {
> > +	if (!krcp->bkvhead[idx] ||
> > +			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
> >  		bnode = get_cached_bnode(krcp);
> >  		if (!bnode) {
> > -			WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE);
> > -
> >  			/*
> >  			 * To keep this path working on raw non-preemptible
> >  			 * sections, prevent the optional entry into the
> > @@ -3175,7 +3221,7 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
> >  			if (IS_ENABLED(CONFIG_PREEMPT_RT))
> >  				return false;
> >  
> > -			bnode = (struct kfree_rcu_bulk_data *)
> > +			bnode = (struct kvfree_rcu_bulk_data *)
> >  				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
> >  		}
> >  
> > @@ -3185,30 +3231,30 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
> >  
> >  		/* Initialize the new block. */
> >  		bnode->nr_records = 0;
> > -		bnode->next = krcp->bhead;
> > +		bnode->next = krcp->bkvhead[idx];
> >  
> >  		/* Attach it to the head. */
> > -		krcp->bhead = bnode;
> > +		krcp->bkvhead[idx] = bnode;
> >  	}
> >  
> >  	/* Finally insert. */
> > -	krcp->bhead->records[krcp->bhead->nr_records++] =
> > -		(void *) head - (unsigned long) func;
> > +	krcp->bkvhead[idx]->records
> > +		[krcp->bkvhead[idx]->nr_records++] = ptr;
> >  
> >  	return true;
> >  }
> >  
> >  /*
> > - * Queue a request for lazy invocation of kfree_bulk()/kfree() after a grace
> > - * period. Please note there are two paths are maintained, one is the main one
> > - * that uses kfree_bulk() interface and second one is emergency one, that is
> > - * used only when the main path can not be maintained temporary, due to memory
> > - * pressure.
> > + * Queue a request for lazy invocation of appropriate free routine after a
> > + * grace period. Please note there are three paths are maintained, two are the
> > + * main ones that use array of pointers interface and third one is emergency
> > + * one, that is used only when the main path can not be maintained temporary,
> > + * due to memory pressure.
> >   *
> >   * Each kfree_call_rcu() request is added to a batch. The batch will be drained
> >   * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
> >   * be free'd in workqueue context. This allows us to: batch requests together to
> > - * reduce the number of grace periods during heavy kfree_rcu() load.
> > + * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
> >   */
> >  void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
> >  {
> > @@ -3231,7 +3277,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
> >  	 * Under high memory pressure GFP_NOWAIT can fail,
> >  	 * in that case the emergency path is maintained.
> >  	 */
> > -	if (unlikely(!kfree_call_rcu_add_ptr_to_bulk(krcp, head, func))) {
> > +	if (unlikely(!kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr))) {
> >  		head->func = func;
> >  		head->next = krcp->head;
> >  		krcp->head = head;
> > @@ -4212,7 +4258,7 @@ static void __init kfree_rcu_batch_init(void)
> >  
> >  	for_each_possible_cpu(cpu) {
> >  		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
> > -		struct kfree_rcu_bulk_data *bnode;
> > +		struct kvfree_rcu_bulk_data *bnode;
> >  
> >  		for (i = 0; i < KFREE_N_BATCHES; i++) {
> >  			INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
> > @@ -4220,7 +4266,7 @@ static void __init kfree_rcu_batch_init(void)
> >  		}
> >  
> >  		for (i = 0; i < rcu_min_cached_objs; i++) {
> > -			bnode = (struct kfree_rcu_bulk_data *)
> > +			bnode = (struct kvfree_rcu_bulk_data *)
> >  				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
> >  
> >  			if (bnode)
> > -- 
> > 2.20.1
> > 

Powered by blists - more mailing lists