/*
 * xfrm6_mode_tunnel.c - Tunnel mode encapsulation for IPv6.
 *
 * Copyright (C) 2002 USAGI/WIDE Project
 * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
 */

#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/stringify.h>
#include <net/dsfield.h>
#include <net/dst.h>
#include <net/inet_ecn.h>
#include <net/ip6_route.h>
#include <net/ipv6.h>
#include <net/xfrm.h>

static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
{
	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);

	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
		IP6_ECN_set_ce(skb, inner_iph);
}

/* Add encapsulation header.
 *
 * The top IP header will be constructed per RFC 2401.
 */
static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct ipv6hdr *top_iph;
	int dsfield;

	skb_set_network_header(skb, -x->props.header_len);
	skb->mac_header = skb->network_header +
			  offsetof(struct ipv6hdr, nexthdr);
	skb->transport_header = skb->network_header + sizeof(*top_iph);
	top_iph = ipv6_hdr(skb);

	top_iph->version = 6;

	memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
	       sizeof(top_iph->flow_lbl));
	top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);

	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
		dsfield = 0;
	else
		dsfield = XFRM_MODE_SKB_CB(skb)->tos;
	dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
	if (x->props.flags & XFRM_STATE_NOECN)
		dsfield &= ~INET_ECN_MASK;
	ipv6_change_dsfield(top_iph, 0, dsfield);
	top_iph->hop_limit = ip6_dst_hoplimit(dst->child);
	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
	return 0;
}

#define for_each_input_rcu(head, handler)	\
	for (handler = rcu_dereference(head);	\
	     handler != NULL;			\
	     handler = rcu_dereference(handler->next))


static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
	int err = -EINVAL;

	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
		goto out;
	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		goto out;

	err = skb_unclone(skb, GFP_ATOMIC);
	if (err)
		goto out;

	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
		ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
			       ipipv6_hdr(skb));
	if (!(x->props.flags & XFRM_STATE_NOECN))
		ipip6_ecn_decapsulate(skb);

	skb_reset_network_header(skb);
	skb_mac_header_rebuild(skb);

	err = 0;

out:
	return err;
}

static struct xfrm_mode xfrm6_tunnel_mode = {
	.input2 = xfrm6_mode_tunnel_input,
	.input = xfrm_prepare_input,
	.output2 = xfrm6_mode_tunnel_output,
	.output = xfrm6_prepare_output,
	.owner = THIS_MODULE,
	.encap = XFRM_MODE_TUNNEL,
	.flags = XFRM_MODE_FLAG_TUNNEL,
};

static int __init xfrm6_mode_tunnel_init(void)
{
	return xfrm_register_mode(&xfrm6_tunnel_mode, AF_INET6);
}

static void __exit xfrm6_mode_tunnel_exit(void)
{
	int err;

	err = xfrm_unregister_mode(&xfrm6_tunnel_mode, AF_INET6);
	BUG_ON(err);
}

module_init(xfrm6_mode_tunnel_init);
module_exit(xfrm6_mode_tunnel_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TUNNEL);
='/cgit.cgi/linux/net-next.git/log/net/irda/parameters.c?h=nds-private-remove&amp;id=5b2ec6f2be512485cb9fde7eb1119279af524c28'>parameters.c</a></div><div class='content'><table class='list nowrap'><tr class='nohover'><th class='left'>Age</th><th class='left'>Commit message (<a href='/cgit.cgi/linux/net-next.git/log/net/irda/parameters.c?h=nds-private-remove&amp;id=5b2ec6f2be512485cb9fde7eb1119279af524c28&amp;showmsg=1'>Expand</a>)</th><th class='left'>Author</th><th class='left'>Files</th><th class='left'>Lines</th></tr>
is.form.submit();'><option value='1'>1</option><option value='2'>2</option><option value='3' selected='selected'>3</option><option value='4'>4</option><option value='5'>5</option><option value='6'>6</option><option value='7'>7</option><option value='8'>8</option><option value='9'>9</option><option value='10'>10</option><option value='15'>15</option><option value='20'>20</option><option value='25'>25</option><option value='30'>30</option><option value='35'>35</option><option value='40'>40</option></select></td></tr><tr><td class='label'>space:</td><td class='ctrl'><select name='ignorews' onchange='this.form.submit();'><option value='0' selected='selected'>include</option><option value='1'>ignore</option></select></td></tr><tr><td class='label'>mode:</td><td class='ctrl'><select name='dt' onchange='this.form.submit();'><option value='0' selected='selected'>unified</option><option value='1'>ssdiff</option><option value='2'>stat only</option></select></td></tr><tr><td/><td class='ctrl'><noscript><input type='submit' value='reload'/></noscript></td></tr></table></form></div><table summary='commit info' class='commit-info'>
<tr><th>author</th><td>Douglas Miller &lt;dougmill@linux.vnet.ibm.com&gt;</td><td class='right'>2017-01-28 06:42:20 -0600</td></tr>
<tr><th>committer</th><td>Tejun Heo &lt;tj@kernel.org&gt;</td><td class='right'>2017-01-28 07:49:42 -0500</td></tr>
<tr><th>commit</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/include/dt-bindings/clock/qcom,gcc-ipq4019.h?id=966d2b04e070bc040319aaebfec09e0144dc3341'>966d2b04e070bc040319aaebfec09e0144dc3341</a> (<a href='/cgit.cgi/linux/net-next.git/patch/include/dt-bindings/clock/qcom,gcc-ipq4019.h?id=966d2b04e070bc040319aaebfec09e0144dc3341'>patch</a>)</td></tr>
<tr><th>tree</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/tree/?id=966d2b04e070bc040319aaebfec09e0144dc3341'>4b96156e3d1dd4dfd6039b7c219c9dc4616da52d</a> /<a href='/cgit.cgi/linux/net-next.git/tree/include/dt-bindings/clock/qcom,gcc-ipq4019.h?id=966d2b04e070bc040319aaebfec09e0144dc3341'>include/dt-bindings/clock/qcom,gcc-ipq4019.h</a></td></tr>
<tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/include/dt-bindings/clock/qcom,gcc-ipq4019.h?id=1b1bc42c1692e9b62756323c675a44cb1a1f9dbd'>1b1bc42c1692e9b62756323c675a44cb1a1f9dbd</a> (<a href='/cgit.cgi/linux/net-next.git/diff/include/dt-bindings/clock/qcom,gcc-ipq4019.h?id=966d2b04e070bc040319aaebfec09e0144dc3341&amp;id2=1b1bc42c1692e9b62756323c675a44cb1a1f9dbd'>diff</a>)</td></tr></table>
<div class='commit-subject'>percpu-refcount: fix reference leak during percpu-atomic transition</div><div class='commit-msg'>percpu_ref_tryget() and percpu_ref_tryget_live() should return
"true" IFF they acquire a reference. But the return value from
atomic_long_inc_not_zero() is a long and may have high bits set,
e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines
is bool so the reference may actually be acquired but the routines
return "false" which results in a reference leak since the caller
assumes it does not need to do a corresponding percpu_ref_put().

This was seen when performing CPU hotplug during I/O, as hangs in
blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start)
raced with percpu_ref_tryget (blk_mq_timeout_work).
Sample stack trace:

__switch_to+0x2c0/0x450
__schedule+0x2f8/0x970
schedule+0x48/0xc0
blk_mq_freeze_queue_wait+0x94/0x120
blk_mq_queue_reinit_work+0xb8/0x180
blk_mq_queue_reinit_prepare+0x84/0xa0
cpuhp_invoke_callback+0x17c/0x600
cpuhp_up_callbacks+0x58/0x150
_cpu_up+0xf0/0x1c0
do_cpu_up+0x120/0x150
cpu_subsys_online+0x64/0xe0
device_online+0xb4/0x120
online_store+0xb4/0xc0
dev_attr_store+0x68/0xa0
sysfs_kf_write+0x80/0xb0
kernfs_fop_write+0x17c/0x250
__vfs_write+0x6c/0x1e0
vfs_write+0xd0/0x270
SyS_write+0x6c/0x110
system_call+0x38/0xe0

Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS,
and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests.
However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0
and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set.

The fix is to make the tryget routines use an actual boolean internally instead
of the atomic long result truncated to a int.

Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints
Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751
Signed-off-by: Douglas Miller &lt;dougmill@linux.vnet.ibm.com&gt;
Reviewed-by: Jens Axboe &lt;axboe@fb.com&gt;
Signed-off-by: Tejun Heo &lt;tj@kernel.org&gt;
Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints")
Cc: stable@vger.kernel.org # v3.18+
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?id=966d2b04e070bc040319aaebfec09e0144dc3341'>Diffstat</a> (limited to 'include/dt-bindings/clock/qcom,gcc-ipq4019.h')</div><table summary='diffstat' class='diffstat'>