Resguardo inicial

linux-7.2.3/net/packet/Kconfig

@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Packet configuration
+#
+
+config PACKET
+	tristate "Packet socket"
+	help
+	  The Packet protocol is used by applications which communicate
+	  directly with network devices without an intermediate network
+	  protocol implemented in the kernel, e.g. tcpdump.  If you want them
+	  to work, choose Y.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called af_packet.
+
+	  If unsure, say Y.
+
+config PACKET_DIAG
+	tristate "Packet: sockets monitoring interface"
+	depends on PACKET
+	default n
+	help
+	  Support for PF_PACKET sockets monitoring interface used by the ss tool.
+	  If unsure, say Y.

linux-7.2.3/net/packet/Makefile

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the packet AF.
+#
+
+obj-$(CONFIG_PACKET) += af_packet.o
+obj-$(CONFIG_PACKET_DIAG) += af_packet_diag.o
+af_packet_diag-y += diag.o

linux-7.2.3/net/packet/diag.c

@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/sock_diag.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/packet_diag.h>
+#include <linux/percpu.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+
+#include "internal.h"
+
+static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb)
+{
+	struct packet_diag_info pinfo;
+
+	pinfo.pdi_index = po->ifindex;
+	pinfo.pdi_version = po->tp_version;
+	pinfo.pdi_reserve = po->tp_reserve;
+	pinfo.pdi_copy_thresh = READ_ONCE(po->copy_thresh);
+	pinfo.pdi_tstamp = READ_ONCE(po->tp_tstamp);
+
+	pinfo.pdi_flags = 0;
+	if (packet_sock_flag(po, PACKET_SOCK_RUNNING))
+		pinfo.pdi_flags |= PDI_RUNNING;
+	if (packet_sock_flag(po, PACKET_SOCK_AUXDATA))
+		pinfo.pdi_flags |= PDI_AUXDATA;
+	if (packet_sock_flag(po, PACKET_SOCK_ORIGDEV))
+		pinfo.pdi_flags |= PDI_ORIGDEV;
+	if (READ_ONCE(po->vnet_hdr_sz))
+		pinfo.pdi_flags |= PDI_VNETHDR;
+	if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS))
+		pinfo.pdi_flags |= PDI_LOSS;
+
+	return nla_put(nlskb, PACKET_DIAG_INFO, sizeof(pinfo), &pinfo);
+}
+
+static int pdiag_put_mclist(const struct packet_sock *po, struct sk_buff *nlskb)
+{
+	struct nlattr *mca;
+	struct packet_mclist *ml;
+
+	mca = nla_nest_start_noflag(nlskb, PACKET_DIAG_MCLIST);
+	if (!mca)
+		return -EMSGSIZE;
+
+	rtnl_lock();
+	for (ml = po->mclist; ml; ml = ml->next) {
+		struct packet_diag_mclist *dml;
+
+		dml = nla_reserve_nohdr(nlskb, sizeof(*dml));
+		if (!dml) {
+			rtnl_unlock();
+			nla_nest_cancel(nlskb, mca);
+			return -EMSGSIZE;
+		}
+
+		dml->pdmc_index = ml->ifindex;
+		dml->pdmc_type = ml->type;
+		dml->pdmc_alen = ml->alen;
+		dml->pdmc_count = ml->count;
+		BUILD_BUG_ON(sizeof(dml->pdmc_addr) != sizeof(ml->addr));
+		memcpy(dml->pdmc_addr, ml->addr, sizeof(ml->addr));
+	}
+
+	rtnl_unlock();
+	nla_nest_end(nlskb, mca);
+
+	return 0;
+}
+
+static int pdiag_put_ring(struct packet_ring_buffer *ring, int ver, int nl_type,
+		struct sk_buff *nlskb)
+{
+	struct packet_diag_ring pdr;
+
+	if (!ring->pg_vec)
+		return 0;
+
+	pdr.pdr_block_size = ring->pg_vec_pages << PAGE_SHIFT;
+	pdr.pdr_block_nr = ring->pg_vec_len;
+	pdr.pdr_frame_size = ring->frame_size;
+	pdr.pdr_frame_nr = ring->frame_max + 1;
+
+	if (ver > TPACKET_V2) {
+		pdr.pdr_retire_tmo = ktime_to_ms(ring->prb_bdqc.interval_ktime);
+		pdr.pdr_sizeof_priv = ring->prb_bdqc.blk_sizeof_priv;
+		pdr.pdr_features = ring->prb_bdqc.feature_req_word;
+	} else {
+		pdr.pdr_retire_tmo = 0;
+		pdr.pdr_sizeof_priv = 0;
+		pdr.pdr_features = 0;
+	}
+
+	return nla_put(nlskb, nl_type, sizeof(pdr), &pdr);
+}
+
+static int pdiag_put_rings_cfg(struct packet_sock *po, struct sk_buff *skb)
+{
+	int ret;
+
+	mutex_lock(&po->pg_vec_lock);
+	ret = pdiag_put_ring(&po->rx_ring, po->tp_version,
+			PACKET_DIAG_RX_RING, skb);
+	if (!ret)
+		ret = pdiag_put_ring(&po->tx_ring, po->tp_version,
+				PACKET_DIAG_TX_RING, skb);
+	mutex_unlock(&po->pg_vec_lock);
+
+	return ret;
+}
+
+static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb)
+{
+	int ret = 0;
+
+	mutex_lock(&fanout_mutex);
+	if (po->fanout) {
+		u32 val;
+
+		val = (u32)po->fanout->id | ((u32)po->fanout->type << 16);
+		ret = nla_put_u32(nlskb, PACKET_DIAG_FANOUT, val);
+	}
+	mutex_unlock(&fanout_mutex);
+
+	return ret;
+}
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
+			struct packet_diag_req *req,
+			bool may_report_filterinfo,
+			struct user_namespace *user_ns,
+			u32 portid, u32 seq, u32 flags, u64 sk_ino)
+{
+	struct nlmsghdr *nlh;
+	struct packet_diag_msg *rp;
+	struct packet_sock *po = pkt_sk(sk);
+
+	nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rp), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	rp = nlmsg_data(nlh);
+	rp->pdiag_family = AF_PACKET;
+	rp->pdiag_type = sk->sk_type;
+	rp->pdiag_num = ntohs(READ_ONCE(po->num));
+	rp->pdiag_ino = sk_ino;
+	sock_diag_save_cookie(sk, rp->pdiag_cookie);
+
+	if ((req->pdiag_show & PACKET_SHOW_INFO) &&
+			pdiag_put_info(po, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_INFO) &&
+	    nla_put_u32(skb, PACKET_DIAG_UID,
+			from_kuid_munged(user_ns, sk_uid(sk))))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_MCLIST) &&
+			pdiag_put_mclist(po, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_RING_CFG) &&
+			pdiag_put_rings_cfg(po, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_FANOUT) &&
+			pdiag_put_fanout(po, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_MEMINFO) &&
+	    sock_diag_put_meminfo(sk, skb, PACKET_DIAG_MEMINFO))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
+	    sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+				     PACKET_DIAG_FILTER))
+		goto out_nlmsg_trim;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+out_nlmsg_trim:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int num = 0, s_num = cb->args[0];
+	struct packet_diag_req *req;
+	struct net *net;
+	struct sock *sk;
+	bool may_report_filterinfo;
+
+	net = sock_net(skb->sk);
+	req = nlmsg_data(cb->nlh);
+	may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
+
+	mutex_lock(&net->packet.sklist_lock);
+	sk_for_each(sk, &net->packet.sklist) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		if (num < s_num)
+			goto next;
+
+		if (sk_diag_fill(sk, skb, req,
+				 may_report_filterinfo,
+				 sk_user_ns(NETLINK_CB(cb->skb).sk),
+				 NETLINK_CB(cb->skb).portid,
+				 cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				 sock_i_ino(sk)) < 0)
+			goto done;
+next:
+		num++;
+	}
+done:
+	mutex_unlock(&net->packet.sklist_lock);
+	cb->args[0] = num;
+
+	return skb->len;
+}
+
+static int packet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+	int hdrlen = sizeof(struct packet_diag_req);
+	struct net *net = sock_net(skb->sk);
+	struct packet_diag_req *req;
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	req = nlmsg_data(h);
+	/* Make it possible to support protocol filtering later */
+	if (req->sdiag_protocol)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = packet_diag_dump,
+		};
+		return netlink_dump_start(net->diag_nlsk, skb, h, &c);
+	} else
+		return -EOPNOTSUPP;
+}
+
+static const struct sock_diag_handler packet_diag_handler = {
+	.owner = THIS_MODULE,
+	.family = AF_PACKET,
+	.dump = packet_diag_handler_dump,
+};
+
+static int __init packet_diag_init(void)
+{
+	return sock_diag_register(&packet_diag_handler);
+}
+
+static void __exit packet_diag_exit(void)
+{
+	sock_diag_unregister(&packet_diag_handler);
+}
+
+module_init(packet_diag_init);
+module_exit(packet_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("PACKET socket monitoring via SOCK_DIAG");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 17 /* AF_PACKET */);

linux-7.2.3/net/packet/internal.h

@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PACKET_INTERNAL_H__
+#define __PACKET_INTERNAL_H__
+
+#include <linux/refcount.h>
+
+struct packet_mclist {
+	struct packet_mclist	*next;
+	int			ifindex;
+	int			count;
+	unsigned short		type;
+	unsigned short		alen;
+	unsigned char		addr[MAX_ADDR_LEN];
+	struct list_head	remove_list;
+};
+
+/* kbdq - kernel block descriptor queue */
+struct tpacket_kbdq_core {
+	struct pgv	*pkbdq;
+	unsigned int	feature_req_word;
+	unsigned int	hdrlen;
+	unsigned char	reset_pending_on_curr_blk;
+	unsigned short	kactive_blk_num;
+	unsigned short	blk_sizeof_priv;
+
+	unsigned short  version;
+
+	char		*pkblk_start;
+	char		*pkblk_end;
+	int		kblk_size;
+	unsigned int	max_frame_len;
+	unsigned int	knum_blocks;
+	uint64_t	knxt_seq_num;
+	char		*prev;
+	char		*nxt_offset;
+
+	struct sk_buff	*skb;
+
+	rwlock_t	blk_fill_in_prog_lock;
+
+	/* Default is set to 8ms */
+#define DEFAULT_PRB_RETIRE_TOV	(8)
+
+	ktime_t		interval_ktime;
+
+	/* timer to retire an outstanding block */
+	struct hrtimer  retire_blk_timer;
+};
+
+struct pgv {
+	char *buffer;
+};
+
+struct packet_ring_buffer {
+	struct pgv		*pg_vec;
+
+	unsigned int		head;
+	unsigned int		frames_per_block;
+	unsigned int		frame_size;
+	unsigned int		frame_max;
+
+	unsigned int		pg_vec_order;
+	unsigned int		pg_vec_pages;
+	unsigned int		pg_vec_len;
+
+	unsigned int __percpu	*pending_refcnt;
+
+	union {
+		unsigned long			*rx_owner_map;
+		struct tpacket_kbdq_core	prb_bdqc;
+	};
+};
+
+extern struct mutex fanout_mutex;
+#define PACKET_FANOUT_MAX	(1 << 16)
+
+struct packet_fanout {
+	possible_net_t		net;
+	unsigned int		num_members;
+	u32			max_num_members;
+	u16			id;
+	u8			type;
+	u8			flags;
+	union {
+		atomic_t		rr_cur;
+		struct bpf_prog __rcu	*bpf_prog;
+	};
+	struct list_head	list;
+	spinlock_t		lock;
+	refcount_t		sk_ref;
+	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
+	struct sock	__rcu	*arr[] __counted_by(max_num_members);
+};
+
+struct packet_rollover {
+	int			sock;
+	atomic_long_t		num;
+	atomic_long_t		num_huge;
+	atomic_long_t		num_failed;
+#define ROLLOVER_HLEN	(L1_CACHE_BYTES / sizeof(u32))
+	u32			history[ROLLOVER_HLEN] ____cacheline_aligned;
+} ____cacheline_aligned_in_smp;
+
+struct packet_sock {
+	/* struct sock has to be the first member of packet_sock */
+	struct sock		sk;
+	struct packet_fanout	*fanout;
+	union  tpacket_stats_u	stats;
+	struct packet_ring_buffer	rx_ring;
+	struct packet_ring_buffer	tx_ring;
+	int			copy_thresh;
+	spinlock_t		bind_lock;
+	struct mutex		pg_vec_lock;
+	unsigned long		flags;
+	int			ifindex;	/* bound device		*/
+	u8			vnet_hdr_sz;
+	__be16			num;
+	struct packet_rollover	*rollover;
+	struct packet_mclist	*mclist;
+	atomic_long_t		mapped;
+	enum tpacket_versions	tp_version;
+	unsigned int		tp_hdrlen;
+	unsigned int		tp_reserve;
+	unsigned int		tp_tstamp;
+	struct completion	skb_completion;
+	struct net_device __rcu	*cached_dev;
+	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
+	atomic_t		tp_drops ____cacheline_aligned_in_smp;
+};
+
+#define pkt_sk(ptr) container_of_const(ptr, struct packet_sock, sk)
+
+enum packet_sock_flags {
+	PACKET_SOCK_ORIGDEV,
+	PACKET_SOCK_AUXDATA,
+	PACKET_SOCK_TX_HAS_OFF,
+	PACKET_SOCK_TP_LOSS,
+	PACKET_SOCK_RUNNING,
+	PACKET_SOCK_PRESSURE,
+	PACKET_SOCK_QDISC_BYPASS,
+};
+
+static inline void packet_sock_flag_set(struct packet_sock *po,
+					enum packet_sock_flags flag,
+					bool val)
+{
+	if (val)
+		set_bit(flag, &po->flags);
+	else
+		clear_bit(flag, &po->flags);
+}
+
+static inline bool packet_sock_flag(const struct packet_sock *po,
+				    enum packet_sock_flags flag)
+{
+	return test_bit(flag, &po->flags);
+}
+
+#endif