Re: PATCH [1/1]: audit: acquire creds selectively to reduce atomicop overhead

[Jiri Kosina]

On Mon, 21 Mar 2011, Eric Paris wrote:

> > Commit c69e8d9c01db added calls to get_task_cred and put_cred in
> > audit_filter_rules.  Profiling with a large number of audit rules active on the
> > exit chain shows that we are spending upto 48% in this routine for syscall
> > intensive tests, most of which is in the atomic ops.
> > 
> > 1. The code should be accessing tsk->cred rather than tsk->real_cred.  
> > 2. Since tsk is current (or tsk is being created by copy_process) access to 
> > tsk->cred without rcu read lock is possible.  At the request of the audit
> > maintainer, a new flag has been added to audit_filter_rules in order to make 
> > this explicit and guide future code.
> > 
> > Signed-off-by: Tony Jones <tonyj@xxxxxxx>
> 
> Acked-by: Eric Paris <eparis@xxxxxxxxxx>

I don't see the patch in linux-next as of today. As it has been acked by 
subsystem maintainer, I have picked it up into my tree ("retransmission 
mode").

If anyone has any objections, please let me know. Thanks.

> 
> > ---
> >  kernel/auditsc.c |   27 +++++++++++++++++----------
> >  1 files changed, 17 insertions(+), 10 deletions(-)
> > 
> > diff --git a/kernel/auditsc.c b/kernel/auditsc.c
> > index f49a031..281dcf1 100644
> > --- a/kernel/auditsc.c
> > +++ b/kernel/auditsc.c
> > @@ -443,17 +443,25 @@ static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree)
> >  
> >  /* Determine if any context name data matches a rule's watch data */
> >  /* Compare a task_struct with an audit_rule.  Return 1 on match, 0
> > - * otherwise. */
> > + * otherwise.
> > + *
> > + * If task_creation is true, this is an explicit indication that we are
> > + * filtering a task rule at task creation time.  This and tsk == current are
> > + * the only situations where tsk->cred may be accessed without an rcu read lock.
> > + */
> >  static int audit_filter_rules(struct task_struct *tsk,
> >  			      struct audit_krule *rule,
> >  			      struct audit_context *ctx,
> >  			      struct audit_names *name,
> > -			      enum audit_state *state)
> > +			      enum audit_state *state,
> > +			      bool task_creation)
> >  {
> > -	const struct cred *cred = get_task_cred(tsk);
> > +	const struct cred *cred;
> >  	int i, j, need_sid = 1;
> >  	u32 sid;
> >  
> > +	cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation);
> > +
> >  	for (i = 0; i < rule->field_count; i++) {
> >  		struct audit_field *f = &rule->fields[i];
> >  		int result = 0;
> > @@ -637,10 +645,8 @@ static int audit_filter_rules(struct task_struct *tsk,
> >  			break;
> >  		}
> >  
> > -		if (!result) {
> > -			put_cred(cred);
> > +		if (!result)
> >  			return 0;
> > -		}
> >  	}
> >  
> >  	if (ctx) {
> > @@ -656,7 +662,6 @@ static int audit_filter_rules(struct task_struct *tsk,
> >  	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
> >  	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
> >  	}
> > -	put_cred(cred);
> >  	return 1;
> >  }
> >  
> > @@ -671,7 +676,8 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
> >  
> >  	rcu_read_lock();
> >  	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
> > -		if (audit_filter_rules(tsk, &e->rule, NULL, NULL, &state)) {
> > +		if (audit_filter_rules(tsk, &e->rule, NULL, NULL,
> > +				       &state, true)) {
> >  			if (state == AUDIT_RECORD_CONTEXT)
> >  				*key = kstrdup(e->rule.filterkey, GFP_ATOMIC);
> >  			rcu_read_unlock();
> > @@ -705,7 +711,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
> >  		list_for_each_entry_rcu(e, list, list) {
> >  			if ((e->rule.mask[word] & bit) == bit &&
> >  			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
> > -					       &state)) {
> > +					       &state, false)) {
> >  				rcu_read_unlock();
> >  				ctx->current_state = state;
> >  				return state;
> > @@ -743,7 +749,8 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
> >  
> >  		list_for_each_entry_rcu(e, list, list) {
> >  			if ((e->rule.mask[word] & bit) == bit &&
> > -			    audit_filter_rules(tsk, &e->rule, ctx, n, &state)) {
> > +			    audit_filter_rules(tsk, &e->rule, ctx, n,
> > +				    	       &state, false)) {
> >  				rcu_read_unlock();
> >  				ctx->current_state = state;
> >  				return;

-- 
Jiri Kosina
SUSE Labs, Novell Inc.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/