linux-kernel - Re: [PATCH v8 4/5] ipc: message queue copy feature introduced

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: <20121024144128.5964e88a.akpm@linux-foundation.org>
Date:	Wed, 24 Oct 2012 14:41:28 -0700
From:	Andrew Morton <akpm@...ux-foundation.org>
To:	Stanislav Kinsbursky <skinsbursky@...allels.com>
Cc:	serge.hallyn@...onical.com, ebiederm@...ssion.com,
	linux-kernel@...r.kernel.org, xemul@...allels.com,
	catalin.marinas@....com, will.deacon@....com, jmorris@...ei.org,
	cmetcalf@...era.com, joe.korty@...r.com, dhowells@...hat.com,
	dledford@...hat.com, viro@...iv.linux.org.uk,
	kosaki.motohiro@...fujitsu.com, linux-api@...r.kernel.org,
	serue@...ibm.com, tglx@...utronix.de, paulmck@...ux.vnet.ibm.com,
	devel@...nvz.org, mtk.manpages@...il.com
Subject: Re: [PATCH v8 4/5] ipc: message queue copy feature introduced

On Wed, 24 Oct 2012 19:35:20 +0400
Stanislav Kinsbursky <skinsbursky@...allels.com> wrote:

> This patch is required for checkpoint/restore in userspace.
> IOW, c/r requires some way to get all pending IPC messages without deleting
> them from the queue (checkpoint can fail and in this case tasks will be resumed,
> so queue have to be valid).
> To achive this, new operation flag MSG_COPY for sys_msgrcv() system call was
> introduced. If this flag was specified, then mtype is interpreted as number of
> the message to copy.
> If MSG_COPY is set, then kernel will allocate dummy message with passed size,
> and then use new copy_msg() helper function to copy desired message (instead of
> unlinking it from the queue).
> 
> ...
>
> @@ -777,19 +777,48 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
>  	struct msg_msg *msg;
>  	int mode;
>  	struct ipc_namespace *ns;
> +#ifdef CONFIG_CHECKPOINT_RESTORE
> +	struct msg_msg *copy = NULL;
> +	unsigned long copy_number = 0;
> +#endif
>  
>  	if (msqid < 0 || (long) bufsz < 0)
>  		return -EINVAL;
> +	if (msgflg & MSG_COPY) {
> +#ifdef CONFIG_CHECKPOINT_RESTORE
> +
> +		if (msgflg & MSG_COPY) {

This test is't needed.

> +			copy_number = msgtyp;
> +			msgtyp = 0;
> +		}
> +
> +		/*
> +		 * Create dummy message to copy real message to.
> +		 */
> +		copy = load_msg(buf, bufsz);
> +		if (IS_ERR(copy))
> +			return PTR_ERR(copy);
> +		copy->m_ts = bufsz;
> +#else
> +		return -ENOSYS;
> +#endif
> +	}
>  	mode = convert_mode(&msgtyp, msgflg);
>  	ns = current->nsproxy->ipc_ns;
>  
>  	msq = msg_lock_check(ns, msqid);
> -	if (IS_ERR(msq))
> +	if (IS_ERR(msq)) {
> +#ifdef CONFIG_CHECKPOINT_RESTORE
> +		if (msgflg & MSG_COPY)
> +			free_msg(copy);
> +#endif
>  		return PTR_ERR(msq);
> +	}
>  
>  	for (;;) {
>  		struct msg_receiver msr_d;
>  		struct list_head *tmp;
> +		long msg_counter = 0;
>  
>  		msg = ERR_PTR(-EACCES);
>  		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
> @@ -809,8 +838,16 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
>  				if (mode == SEARCH_LESSEQUAL &&
>  						walk_msg->m_type != 1) {
>  					msgtyp = walk_msg->m_type - 1;
> +#ifdef CONFIG_CHECKPOINT_RESTORE
> +				} else if (msgflg & MSG_COPY) {
> +					if (copy_number == msg_counter) {
> +						msg = copy_msg(walk_msg, copy);
> +						break;
> +					}
> +#endif
>  				} else
>  					break;
> +				msg_counter++;
>  			}
>  			tmp = tmp->next;
>  		}
> @@ -823,6 +860,10 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
>  				msg = ERR_PTR(-E2BIG);
>  				goto out_unlock;
>  			}
> +#ifdef CONFIG_CHECKPOINT_RESTORE
> +			if (msgflg & MSG_COPY)
> +				goto out_unlock;
> +#endif
>  			list_del(&msg->m_list);
>  			msq->q_qnum--;
>  			msq->q_rtime = get_seconds();
> @@ -906,8 +947,13 @@ out_unlock:
>  			break;
>  		}
>  	}
> -	if (IS_ERR(msg))
> +	if (IS_ERR(msg)) {
> +#ifdef CONFIG_CHECKPOINT_RESTORE
> +		if (msgflg & MSG_COPY)
> +			free_msg(copy);
> +#endif
>  		return PTR_ERR(msg);
> +	}
>  
>  	bufsz = msg_handler(buf, msg, bufsz);
>  	free_msg(msg);

It's all a bit ugly, but I don't really see much we can practically do
about that.

You could add something like

#ifdef CONFIG_CHECKPOINT_RESTORE
static inline void free_copy(void *p, int msgflg, struct msg_msg *copy)
{
	if (IS_ERR(p) && (msgflg & MSG_COPY))
		free_msg(copy);
}
#else
/* As a macro because `copy' will be undefined */
#define free_copy(p, msgflg, copy) do {} while (0)
#endif

and use that in a couple of places.  But that won't help much.


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