https://github.com/torvalds/linux
Revision efd1535270c1deb0487527bf0c3c827301a69c93 authored by Bob Liu on 07 June 2016, 14:43:15 UTC, committed by Konrad Rzeszutek Wilk on 08 June 2016, 17:54:39 UTC
Sometimes blkfront may twice receive blkback_changed() notification
(XenbusStateConnected) after migration, which will cause
talk_to_blkback() to be called twice too and confuse xen-blkback.

The flow is as follow:
   blkfront                                        blkback
blkfront_resume()
 > talk_to_blkback()
  > Set blkfront to XenbusStateInitialised
                                                front changed()
                                                 > Connect()
                                                  > Set blkback to XenbusStateConnected

blkback_changed()
 > Skip talk_to_blkback()
   because frontstate == XenbusStateInitialised
 > blkfront_connect()
  > Set blkfront to XenbusStateConnected

-----
And here we get another XenbusStateConnected notification leading
to:
-----
blkback_changed()
 > because now frontstate != XenbusStateInitialised
   talk_to_blkback() is also called again
  > blkfront state changed from
  XenbusStateConnected to XenbusStateInitialised
    (Which is not correct!)

						front_changed():
                                                 > Do nothing because blkback
                                                   already in XenbusStateConnected

Now blkback is in XenbusStateConnected but blkfront is still
in XenbusStateInitialised - leading to no disks.

Poking of the XenbusStateConnected state is allowed (to deal with
block disk change) and has to be dealt with. The most likely
cause of this bug are custom udev scripts hooking up the disks
and then validating the size.

Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
1 parent 116f7d4
Raw File
Tip revision: efd1535270c1deb0487527bf0c3c827301a69c93 authored by Bob Liu on 07 June 2016, 14:43:15 UTC
xen-blkfront: don't call talk_to_blkback when already connected to blkback
Tip revision: efd1535
sysctl_net.c
/* -*- linux-c -*-
 * sysctl_net.c: sysctl interface to net subsystem.
 *
 * Begun April 1, 1996, Mike Shaver.
 * Added /proc/sys/net directories for each protocol family. [MS]
 *
 * Revision 1.2  1996/05/08  20:24:40  shaver
 * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and
 * NET_IPV4_IP_FORWARD.
 *
 *
 */

#include <linux/mm.h>
#include <linux/export.h>
#include <linux/sysctl.h>
#include <linux/nsproxy.h>

#include <net/sock.h>

#ifdef CONFIG_INET
#include <net/ip.h>
#endif

#ifdef CONFIG_NET
#include <linux/if_ether.h>
#endif

static struct ctl_table_set *
net_ctl_header_lookup(struct ctl_table_root *root, struct nsproxy *namespaces)
{
	return &namespaces->net_ns->sysctls;
}

static int is_seen(struct ctl_table_set *set)
{
	return &current->nsproxy->net_ns->sysctls == set;
}

/* Return standard mode bits for table entry. */
static int net_ctl_permissions(struct ctl_table_header *head,
			       struct ctl_table *table)
{
	struct net *net = container_of(head->set, struct net, sysctls);
	kuid_t root_uid = make_kuid(net->user_ns, 0);
	kgid_t root_gid = make_kgid(net->user_ns, 0);

	/* Allow network administrator to have same access as root. */
	if (ns_capable(net->user_ns, CAP_NET_ADMIN) ||
	    uid_eq(root_uid, current_euid())) {
		int mode = (table->mode >> 6) & 7;
		return (mode << 6) | (mode << 3) | mode;
	}
	/* Allow netns root group to have the same access as the root group */
	if (in_egroup_p(root_gid)) {
		int mode = (table->mode >> 3) & 7;
		return (mode << 3) | mode;
	}
	return table->mode;
}

static struct ctl_table_root net_sysctl_root = {
	.lookup = net_ctl_header_lookup,
	.permissions = net_ctl_permissions,
};

static int __net_init sysctl_net_init(struct net *net)
{
	setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen);
	return 0;
}

static void __net_exit sysctl_net_exit(struct net *net)
{
	retire_sysctl_set(&net->sysctls);
}

static struct pernet_operations sysctl_pernet_ops = {
	.init = sysctl_net_init,
	.exit = sysctl_net_exit,
};

static struct ctl_table_header *net_header;
__init int net_sysctl_init(void)
{
	static struct ctl_table empty[1];
	int ret = -ENOMEM;
	/* Avoid limitations in the sysctl implementation by
	 * registering "/proc/sys/net" as an empty directory not in a
	 * network namespace.
	 */
	net_header = register_sysctl("net", empty);
	if (!net_header)
		goto out;
	ret = register_pernet_subsys(&sysctl_pernet_ops);
	if (ret)
		goto out1;
	register_sysctl_root(&net_sysctl_root);
out:
	return ret;
out1:
	unregister_sysctl_table(net_header);
	net_header = NULL;
	goto out;
}

struct ctl_table_header *register_net_sysctl(struct net *net,
	const char *path, struct ctl_table *table)
{
	return __register_sysctl_table(&net->sysctls, path, table);
}
EXPORT_SYMBOL_GPL(register_net_sysctl);

void unregister_net_sysctl_table(struct ctl_table_header *header)
{
	unregister_sysctl_table(header);
}
EXPORT_SYMBOL_GPL(unregister_net_sysctl_table);
back to top