#include <linux/module.h>

#include <linux/inet_diag.h>
#include <linux/sock_diag.h>

#include <net/inet_sock.h>
#include <net/raw.h>
#include <net/rawv6.h>

#ifdef pr_fmt
# undef pr_fmt
#endif

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

static struct raw_hashinfo *
raw_get_hashinfo(const struct inet_diag_req_v2 *r)
{
	if (r->sdiag_family == AF_INET) {
		return &raw_v4_hashinfo;
#if IS_ENABLED(CONFIG_IPV6)
	} else if (r->sdiag_family == AF_INET6) {
		return &raw_v6_hashinfo;
#endif
	} else {
		pr_warn_once("Unexpected inet family %d\n",
			     r->sdiag_family);
		WARN_ON_ONCE(1);
		return ERR_PTR(-EINVAL);
	}
}

/*
 * Due to requirement of not breaking user API we can't simply
 * rename @pad field in inet_diag_req_v2 structure, instead
 * use helper to figure it out.
 */

static struct sock *raw_lookup(struct net *net, struct sock *from,
			       const struct inet_diag_req_v2 *req)
{
	struct inet_diag_req_raw *r = (void *)req;
	struct sock *sk = NULL;

	if (r->sdiag_family == AF_INET)
		sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
				     r->id.idiag_dst[0],
				     r->id.idiag_src[0],
				     r->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
	else
		sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
				     (const struct in6_addr *)r->id.idiag_src,
				     (const struct in6_addr *)r->id.idiag_dst,
				     r->id.idiag_if);
#endif
	return sk;
}

static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
{
	struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
	struct sock *sk = NULL, *s;
	int slot;

	if (IS_ERR(hashinfo))
		return ERR_CAST(hashinfo);

	read_lock(&hashinfo->lock);
	for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
		sk_for_each(s, &hashinfo->ht[slot]) {
			sk = raw_lookup(net, s, r);
			if (sk) {
				/*
				 * Grab it and keep until we fill
				 * diag meaage to be reported, so
				 * caller should call sock_put then.
				 * We can do that because we're keeping
				 * hashinfo->lock here.
				 */
				sock_hold(sk);
				goto out_unlock;
			}
		}
	}
out_unlock:
	read_unlock(&hashinfo->lock);

	return sk ? sk : ERR_PTR(-ENOENT);
}

static int raw_diag_dump_one(struct sk_buff *in_skb,
			     const struct nlmsghdr *nlh,
			     const struct inet_diag_req_v2 *r)
{
	struct net *net = sock_net(in_skb->sk);
	struct sk_buff *rep;
	struct sock *sk;
	int err;

	sk = raw_sock_get(net, r);
	if (IS_ERR(sk))
		return PTR_ERR(sk);

	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
			sizeof(struct inet_diag_meminfo) + 64,
			GFP_KERNEL);
	if (!rep) {
		sock_put(sk);
		return -ENOMEM;
	}

	err = inet_sk_diag_fill(sk, NULL, rep, r,
				sk_user_ns(NETLINK_CB(in_skb).sk),
				NETLINK_CB(in_skb).portid,
				nlh->nlmsg_seq, 0, nlh,
				netlink_net_capable(in_skb, CAP_NET_ADMIN));
	sock_put(sk);

	if (err < 0) {
		kfree_skb(rep);
		return err;
	}

	err = netlink_unicast(net->diag_nlsk, rep,
			      NETLINK_CB(in_skb).portid,
			      MSG_DONTWAIT);
	if (err > 0)
		err = 0;
	return err;
}

static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
			struct netlink_callback *cb,
			const struct inet_diag_req_v2 *r,
			struct nlattr *bc, bool net_admin)
{
	if (!inet_diag_bc_sk(bc, sk))
		return 0;

	return inet_sk_diag_fill(sk, NULL, skb, r,
				 sk_user_ns(NETLINK_CB(cb->skb).sk),
				 NETLINK_CB(cb->skb).portid,
				 cb->nlh->nlmsg_seq, NLM_F_MULTI,
				 cb->nlh, net_admin);
}

static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
			  const struct inet_diag_req_v2 *r, struct nlattr *bc)
{
	bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
	struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
	struct net *net = sock_net(skb->sk);
	int num, s_num, slot, s_slot;
	struct sock *sk = NULL;

	if (IS_ERR(hashinfo))
		return;

	s_slot = cb->args[0];
	num = s_num = cb->args[1];

	read_lock(&hashinfo->lock);
	for (slot = s_slot; slot < RAW_HTABLE_SIZE; s_num = 0, slot++) {
		num = 0;

		sk_for_each(sk, &hashinfo->ht[slot]) {
			struct inet_sock *inet = inet_sk(sk);

			if (!net_eq(sock_net(sk), net))
				continue;
			if (num < s_num)
				goto next;
			if (sk->sk_family != r->sdiag_family)
				goto next;
			if (r->id.idiag_sport != inet->inet_sport &&
			    r->id.idiag_sport)
				goto next;
			if (r->id.idiag_dport != inet->inet_dport &&
			    r->id.idiag_dport)
				goto next;
			if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0)
				goto out_unlock;
next:
			num++;
		}
	}

out_unlock:
	read_unlock(&hashinfo->lock);

	cb->args[0] = slot;
	cb->args[1] = num;
}

static void raw_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
			      void *info)
{
	r->idiag_rqueue = sk_rmem_alloc_get(sk);
	r->idiag_wqueue = sk_wmem_alloc_get(sk);
}

#ifdef CONFIG_INET_DIAG_DESTROY
static int raw_diag_destroy(struct sk_buff *in_skb,
			    const struct inet_diag_req_v2 *r)
{
	struct net *net = sock_net(in_skb->sk);
	struct sock *sk;
	int err;

	sk = raw_sock_get(net, r);
	if (IS_ERR(sk))
		return PTR_ERR(sk);
	err = sock_diag_destroy(sk, ECONNABORTED);
	sock_put(sk);
	return err;
}
#endif

static const struct inet_diag_handler raw_diag_handler = {
	.dump			= raw_diag_dump,
	.dump_one		= raw_diag_dump_one,
	.idiag_get_info		= raw_diag_get_info,
	.idiag_type		= IPPROTO_RAW,
	.idiag_info_size	= 0,
#ifdef CONFIG_INET_DIAG_DESTROY
	.destroy		= raw_diag_destroy,
#endif
};

static void __always_unused __check_inet_diag_req_raw(void)
{
	/*
	 * Make sure the two structures are identical,
	 * except the @pad field.
	 */
#define __offset_mismatch(m1, m2)			\
	(offsetof(struct inet_diag_req_v2, m1) !=	\
	 offsetof(struct inet_diag_req_raw, m2))

	BUILD_BUG_ON(sizeof(struct inet_diag_req_v2) !=
		     sizeof(struct inet_diag_req_raw));
	BUILD_BUG_ON(__offset_mismatch(sdiag_family, sdiag_family));
	BUILD_BUG_ON(__offset_mismatch(sdiag_protocol, sdiag_protocol));
	BUILD_BUG_ON(__offset_mismatch(idiag_ext, idiag_ext));
	BUILD_BUG_ON(__offset_mismatch(pad, sdiag_raw_protocol));
	BUILD_BUG_ON(__offset_mismatch(idiag_states, idiag_states));
	BUILD_BUG_ON(__offset_mismatch(id, id));
#undef __offset_mismatch
}

static int __init raw_diag_init(void)
{
	return inet_diag_register(&raw_diag_handler);
}

static void __exit raw_diag_exit(void)
{
	inet_diag_unregister(&raw_diag_handler);
}

module_init(raw_diag_init);
module_exit(raw_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
er does not require ACPI/CPPC to enable HWP, and
so it runs in HWP mode, exposing this incorrect BIOS configuration.

There are several ways to address this problem.

First, Linux can also run in legacy P-state mode on this system.
As intel_pstate is how Linux enables HWP, booting with
"intel_pstate=disable"
will run in acpi-cpufreq/ondemand legacy p-state mode.

Or second, the "performance" governor can be used with intel_pstate,
which will modify HWP.EPP to 0.

Or third, starting in 4.10, the
/sys/devices/system/cpu/cpufreq/policy*/energy_performance_preference
attribute in can be updated from "balance_power" to "performance".

Or fourth, apply this patch, which fixes the erroneous setting of
MSR_IA32_POWER_CTL BIT_EE on this model, allowing the default
configuration to function as designed.

Signed-off-by: Srinivas Pandruvada &lt;srinivas.pandruvada@linux.intel.com&gt;
Reviewed-by: Len Brown &lt;len.brown@intel.com&gt;
Cc: 4.6+ &lt;stable@vger.kernel.org&gt; # 4.6+
Signed-off-by: Rafael J. Wysocki &lt;rafael.j.wysocki@intel.com&gt;
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?id=6e978b22efa1db9f6e71b24440b5f1d93e968ee3'>Diffstat</a> (limited to 'tools/power')</div><table summary='diffstat' class='diffstat'>