/*
 * xfrm_output.c - Common IPsec encapsulation code.
 *
 * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/errno.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
#include <net/xfrm.h>

static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);

static int xfrm_skb_check_space(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev)
		- skb_headroom(skb);
	int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);

	if (nhead <= 0) {
		if (ntail <= 0)
			return 0;
		nhead = 0;
	} else if (ntail < 0)
		ntail = 0;

	return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
}

/* Children define the path of the packet through the
 * Linux networking.  Thus, destinations are stackable.
 */

static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
{
	struct dst_entry *child = dst_clone(skb_dst(skb)->child);

	skb_dst_drop(skb);
	return child;
}

static int xfrm_output_one(struct sk_buff *skb, int err)
{
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_state *x = dst->xfrm;
	struct net *net = xs_net(x);

	if (err <= 0)
		goto resume;

	do {
		err = xfrm_skb_check_space(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			goto error_nolock;
		}

		err = x->outer_mode->output(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
			goto error_nolock;
		}

		spin_lock_bh(&x->lock);

		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
			err = -EINVAL;
			goto error;
		}

		err = xfrm_state_check_expire(x);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
			goto error;
		}

		err = x->repl->overflow(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
			goto error;
		}

		x->curlft.bytes += skb->len;
		x->curlft.packets++;

		spin_unlock_bh(&x->lock);

		skb_dst_force(skb);

		/* Inner headers are invalid now. */
		skb->encapsulation = 0;

		err = x->type->output(x, skb);
		if (err == -EINPROGRESS)
			goto out;

resume:
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			goto error_nolock;
		}

		dst = skb_dst_pop(skb);
		if (!dst) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			err = -EHOSTUNREACH;
			goto error_nolock;
		}
		skb_dst_set(skb, dst);
		x = dst->xfrm;
	} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));

	return 0;

error:
	spin_unlock_bh(&x->lock);
error_nolock:
	kfree_skb(skb);
out:
	return err;
}

int xfrm_output_resume(struct sk_buff *skb, int err)
{
	struct net *net = xs_net(skb_dst(skb)->xfrm);

	while (likely((err = xfrm_output_one(skb, err)) == 0)) {
		nf_reset(skb);

		err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
		if (unlikely(err != 1))
			goto out;

		if (!skb_dst(skb)->xfrm)
			return dst_output(net, skb->sk, skb);

		err = nf_hook(skb_dst(skb)->ops->family,
			      NF_INET_POST_ROUTING, net, skb->sk, skb,
			      NULL, skb_dst(skb)->dev, xfrm_output2);
		if (unlikely(err != 1))
			goto out;
	}

	if (err == -EINPROGRESS)
		err = 0;

out:
	return err;
}
EXPORT_SYMBOL_GPL(xfrm_output_resume);

static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	return xfrm_output_resume(skb, 1);
}

static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct sk_buff *segs;

	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
	segs = skb_gso_segment(skb, 0);
	kfree_skb(skb);
	if (IS_ERR(segs))
		return PTR_ERR(segs);
	if (segs == NULL)
		return -EINVAL;

	do {
		struct sk_buff *nskb = segs->next;
		int err;

		segs->next = NULL;
		err = xfrm_output2(net, sk, segs);

		if (unlikely(err)) {
			kfree_skb_list(nskb);
			return err;
		}

		segs = nskb;
	} while (segs);

	return 0;
}

int xfrm_output(struct sock *sk, struct sk_buff *skb)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	int err;

	if (skb_is_gso(skb))
		return xfrm_output_gso(net, sk, skb);

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		err = skb_checksum_help(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			kfree_skb(skb);
			return err;
		}
	}

	return xfrm_output2(net, sk, skb);
}
EXPORT_SYMBOL_GPL(xfrm_output);

int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
	struct xfrm_mode *inner_mode;
	if (x->sel.family == AF_UNSPEC)
		inner_mode = xfrm_ip2inner_mode(x,
				xfrm_af2proto(skb_dst(skb)->ops->family));
	else
		inner_mode = x->inner_mode;

	if (inner_mode == NULL)
		return -EAFNOSUPPORT;
	return inner_mode->afinfo->extract_output(x, skb);
}
EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);

void xfrm_local_error(struct sk_buff *skb, int mtu)
{
	unsigned int proto;
	struct xfrm_state_afinfo *afinfo;

	if (skb->protocol == htons(ETH_P_IP))
		proto = AF_INET;
	else if (skb->protocol == htons(ETH_P_IPV6))
		proto = AF_INET6;
	else
		return;

	afinfo = xfrm_state_get_afinfo(proto);
	if (afinfo)
		afinfo->local_error(skb, mtu);
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(xfrm_local_error);
ower/utils/cpufreq-set.c?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/tools/power/cpupower/utils/cpufreq-set.c?id=966d2b04e070bc040319aaebfec09e0144dc3341'>tools/power/cpupower/utils/cpufreq-set.c</a></td></tr>
<tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/tools/power/cpupower/utils/cpufreq-set.c?id=1b1bc42c1692e9b62756323c675a44cb1a1f9dbd'>1b1bc42c1692e9b62756323c675a44cb1a1f9dbd</a> (<a href='/cgit.cgi/linux/net-next.git/diff/tools/power/cpupower/utils/cpufreq-set.c?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 'tools/power/cpupower/utils/cpufreq-set.c')</div><table summary='diffstat' class='diffstat'>