Add RX packet classification interface

This patch was originally introduced as:
  [PATCH 1/3] [ethtool] Add rx pkt classification interface
  Signed-off-by: Santwona Behera <santwona.behera@sun.com>
  http://patchwork.ozlabs.org/patch/23223/

I removed the local caching of rules.

I dropped the use of regions as there were multiple issues found.

A network flow classifier is defined using the exact same syntax as
n-tuple, and the tool will correct for the fact that NFC uses the 1's
compliment of the n-tuple mask.

I also updated the ordering of new rules being added.  All new rules will
take the highest numbered open rule when no location is specified.

I split out the addition of bitops and the updates to documentation
into separate patches.  This makes the total patch size a bit more
manageable since the addition of NFC and the merging of it with
n-tuple were combined into this patch.

If we setup a rule and the device has the NTUPLE flag set we will
first try to use set_rx_ntuple.  If that fails with EOPNOTSUPP we then
will attempt to use the network flow classifier rule insertion.

Updated the output to make use of the updated network flow classifier
extensions that have been accepted into the kernel.

Merged the documentation update into this patch.  In addition the
documentation changes were made such that there is only one listing of the
individual options and they are all listed as optional.

Several fixes to address things such as the fact that we were
maintaining the table logic even though we only need it for displaying
all of the rules, or when adding a rule with no location specified.
As such all of the logic for deleting or finding rules in the table
has been removed.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
[bwh: Abbreviated the above commit message. Fixed a minor formatting
 error in the manual page additions.]
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

1 files changed, 1073 insertions, 0 deletions

diff --git a/rxclass.c b/rxclass.c
new file mode 100644
index 0000000..ee486f7
--- /dev/null
+++ b/rxclass.c
@@ -0,0 +1,1073 @@
+/*
+ * Copyright (C) 2008 Sun Microsystems, Inc. All rights reserved.
+ */
+#include <stdio.h>
+#include <stdint.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <linux/sockios.h>
+#include <arpa/inet.h>
+#include "ethtool-util.h"
+#include "ethtool-bitops.h"
+
+static void invert_flow_mask(struct ethtool_rx_flow_spec *fsp)
+{
+	size_t i;
+
+	for (i = 0; i < sizeof(fsp->m_u); i++)
+		fsp->m_u.hdata[i] ^= 0xFF;
+}
+
+static void rxclass_print_ipv4_rule(__be32 sip, __be32 sipm, __be32 dip,
+				    __be32 dipm, u8 tos, u8 tosm)
+{
+	char sip_str[INET_ADDRSTRLEN];
+	char sipm_str[INET_ADDRSTRLEN];
+	char dip_str[INET_ADDRSTRLEN];
+	char dipm_str[INET_ADDRSTRLEN];
+
+	fprintf(stdout,
+		"\tSrc IP addr: %s mask: %s\n"
+		"\tDest IP addr: %s mask: %s\n"
+		"\tTOS: 0x%x mask: 0x%x\n",
+		inet_ntop(AF_INET, &sip, sip_str, INET_ADDRSTRLEN),
+		inet_ntop(AF_INET, &sipm, sipm_str, INET_ADDRSTRLEN),
+		inet_ntop(AF_INET, &dip, dip_str, INET_ADDRSTRLEN),
+		inet_ntop(AF_INET, &dipm, dipm_str, INET_ADDRSTRLEN),
+		tos, tosm);
+}
+
+static void rxclass_print_nfc_spec_ext(struct ethtool_rx_flow_spec *fsp)
+{
+	u64 data, datam;
+	__u16 etype, etypem, tci, tcim;
+
+	if (!(fsp->flow_type & FLOW_EXT))
+		return;
+
+	etype = ntohs(fsp->h_ext.vlan_etype);
+	etypem = ntohs(~fsp->m_ext.vlan_etype);
+	tci = ntohs(fsp->h_ext.vlan_tci);
+	tcim = ntohs(~fsp->m_ext.vlan_tci);
+	data = (u64)ntohl(fsp->h_ext.data[0]) << 32;
+	data = (u64)ntohl(fsp->h_ext.data[1]);
+	datam = (u64)ntohl(~fsp->m_ext.data[0]) << 32;
+	datam |= (u64)ntohl(~fsp->m_ext.data[1]);
+
+	fprintf(stdout,
+		"\tVLAN EtherType: 0x%x mask: 0x%x\n"
+		"\tVLAN: 0x%x mask: 0x%x\n"
+		"\tUser-defined: 0x%llx mask: 0x%llx\n",
+		etype, etypem, tci, tcim, data, datam);
+}
+
+static void rxclass_print_nfc_rule(struct ethtool_rx_flow_spec *fsp)
+{
+	unsigned char	*smac, *smacm, *dmac, *dmacm;
+	__u32		flow_type;
+
+	if (fsp->location != RX_CLS_LOC_UNSPEC)
+		fprintf(stdout,	"Filter: %d\n", fsp->location);
+	else
+		fprintf(stdout,	"Filter: Unspecified\n");
+
+	flow_type = fsp->flow_type & ~FLOW_EXT;
+
+	invert_flow_mask(fsp);
+
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		if (flow_type == TCP_V4_FLOW)
+			fprintf(stdout, "\tRule Type: TCP over IPv4\n");
+		else if (flow_type == UDP_V4_FLOW)
+			fprintf(stdout, "\tRule Type: UDP over IPv4\n");
+		else
+			fprintf(stdout, "\tRule Type: SCTP over IPv4\n");
+		rxclass_print_ipv4_rule(fsp->h_u.tcp_ip4_spec.ip4src,
+				     fsp->m_u.tcp_ip4_spec.ip4src,
+				     fsp->h_u.tcp_ip4_spec.ip4dst,
+				     fsp->m_u.tcp_ip4_spec.ip4dst,
+				     fsp->h_u.tcp_ip4_spec.tos,
+				     fsp->m_u.tcp_ip4_spec.tos);
+		fprintf(stdout,
+			"\tSrc port: %d mask: 0x%x\n"
+			"\tDest port: %d mask: 0x%x\n",
+			ntohs(fsp->h_u.tcp_ip4_spec.psrc),
+			ntohs(fsp->m_u.tcp_ip4_spec.psrc),
+			ntohs(fsp->h_u.tcp_ip4_spec.pdst),
+			ntohs(fsp->m_u.tcp_ip4_spec.pdst));
+		break;
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+		if (flow_type == AH_V4_FLOW)
+			fprintf(stdout, "\tRule Type: IPSEC AH over IPv4\n");
+		else
+			fprintf(stdout, "\tRule Type: IPSEC ESP over IPv4\n");
+		rxclass_print_ipv4_rule(fsp->h_u.ah_ip4_spec.ip4src,
+				     fsp->m_u.ah_ip4_spec.ip4src,
+				     fsp->h_u.ah_ip4_spec.ip4dst,
+				     fsp->m_u.ah_ip4_spec.ip4dst,
+				     fsp->h_u.ah_ip4_spec.tos,
+				     fsp->m_u.ah_ip4_spec.tos);
+		fprintf(stdout,
+			"\tSPI: %d mask: 0x%x\n",
+			ntohl(fsp->h_u.esp_ip4_spec.spi),
+			ntohl(fsp->m_u.esp_ip4_spec.spi));
+		break;
+	case IP_USER_FLOW:
+		fprintf(stdout, "\tRule Type: Raw IPv4\n");
+		rxclass_print_ipv4_rule(fsp->h_u.usr_ip4_spec.ip4src,
+				     fsp->m_u.usr_ip4_spec.ip4src,
+				     fsp->h_u.usr_ip4_spec.ip4dst,
+				     fsp->m_u.usr_ip4_spec.ip4dst,
+				     fsp->h_u.usr_ip4_spec.tos,
+				     fsp->m_u.usr_ip4_spec.tos);
+		fprintf(stdout,
+			"\tProtocol: %d mask: 0x%x\n"
+			"\tL4 bytes: 0x%x mask: 0x%x\n",
+			fsp->h_u.usr_ip4_spec.proto,
+			fsp->m_u.usr_ip4_spec.proto,
+			ntohl(fsp->h_u.usr_ip4_spec.l4_4_bytes),
+			ntohl(fsp->m_u.usr_ip4_spec.l4_4_bytes));
+		break;
+	case ETHER_FLOW:
+		dmac = fsp->h_u.ether_spec.h_dest;
+		dmacm = fsp->m_u.ether_spec.h_dest;
+		smac = fsp->h_u.ether_spec.h_source;
+		smacm = fsp->m_u.ether_spec.h_source;
+
+		fprintf(stdout,
+			"\tFlow Type: Raw Ethernet\n"
+			"\tSrc MAC addr: %02X:%02X:%02X:%02X:%02X:%02X"
+			" mask: %02X:%02X:%02X:%02X:%02X:%02X\n"
+			"\tDest MAC addr: %02X:%02X:%02X:%02X:%02X:%02X"
+			" mask: %02X:%02X:%02X:%02X:%02X:%02X\n"
+			"\tEthertype: 0x%X mask: 0x%X\n",
+			smac[0], smac[1], smac[2], smac[3], smac[4], smac[5],
+			smacm[0], smacm[1], smacm[2], smacm[3], smacm[4],
+			smacm[5], dmac[0], dmac[1], dmac[2], dmac[3], dmac[4],
+			dmac[5], dmacm[0], dmacm[1], dmacm[2], dmacm[3],
+			dmacm[4], dmacm[5],
+			ntohs(fsp->h_u.ether_spec.h_proto),
+			ntohs(fsp->m_u.ether_spec.h_proto));
+		break;
+	default:
+		fprintf(stdout,
+			"\tUnknown Flow type: %d\n", flow_type);
+		break;
+	}
+
+	rxclass_print_nfc_spec_ext(fsp);
+
+	if (fsp->ring_cookie != RX_CLS_FLOW_DISC)
+		fprintf(stdout, "\tAction: Direct to queue %llu\n",
+			fsp->ring_cookie);
+	else
+		fprintf(stdout, "\tAction: Drop\n");
+
+	fprintf(stdout, "\n");
+}
+
+static void rxclass_print_rule(struct ethtool_rx_flow_spec *fsp)
+{
+	/* print the rule in this location */
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case ETHER_FLOW:
+		rxclass_print_nfc_rule(fsp);
+		break;
+	case IP_USER_FLOW:
+		if (fsp->h_u.usr_ip4_spec.ip_ver == ETH_RX_NFC_IP4) {
+			rxclass_print_nfc_rule(fsp);
+			break;
+		}
+		/* IPv6 User Flow falls through to the case below */
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+		fprintf(stderr, "IPv6 flows not implemented\n");
+		break;
+	default:
+		fprintf(stderr, "rxclass: Unknown flow type\n");
+		break;
+	}
+}
+
+static int rxclass_get_count(int fd, struct ifreq *ifr, __u32 *count)
+{
+	struct ethtool_rxnfc nfccmd;
+	int err;
+
+	/* request count and store */
+	nfccmd.cmd = ETHTOOL_GRXCLSRLCNT;
+	nfccmd.rule_cnt = 0;
+	ifr->ifr_data = (caddr_t)&nfccmd;
+	err = ioctl(fd, SIOCETHTOOL, ifr);
+	*count = nfccmd.rule_cnt;
+	if (err < 0)
+		perror("rxclass: Cannot get RX class rule count");
+
+	return err;
+}
+
+int rxclass_rule_get(int fd, struct ifreq *ifr, __u32 loc)
+{
+	struct ethtool_rxnfc nfccmd;
+	int err;
+
+	/* fetch rule from netdev */
+	nfccmd.cmd = ETHTOOL_GRXCLSRULE;
+	memset(&nfccmd.fs, 0, sizeof(struct ethtool_rx_flow_spec));
+	nfccmd.fs.location = loc;
+	ifr->ifr_data = (caddr_t)&nfccmd;
+	err = ioctl(fd, SIOCETHTOOL, ifr);
+	if (err < 0) {
+		perror("rxclass: Cannot get RX class rule");
+		return err;
+	}
+
+	/* display rule */
+	rxclass_print_rule(&nfccmd.fs);
+	return err;
+}
+
+int rxclass_rule_getall(int fd, struct ifreq *ifr)
+{
+	struct ethtool_rxnfc *nfccmd;
+	__u32 *rule_locs;
+	int err, i;
+	__u32 count;
+
+	/* determine rule count */
+	err = rxclass_get_count(fd, ifr, &count);
+	if (err < 0)
+		return err;
+
+	fprintf(stdout, "Total %d rules\n\n", count);
+
+	/* alloc memory for request of location list */
+	nfccmd = calloc(1, sizeof(*nfccmd) + (count * sizeof(__u32)));
+	if (!nfccmd) {
+		perror("rxclass: Cannot allocate memory for"
+		       " RX class rule locations");
+		return -ENOMEM;
+	}
+
+	/* request location list */
+	nfccmd->cmd = ETHTOOL_GRXCLSRLALL;
+	nfccmd->rule_cnt = count;
+	ifr->ifr_data = (caddr_t)nfccmd;
+	err = ioctl(fd, SIOCETHTOOL, ifr);
+	if (err < 0) {
+		perror("rxclass: Cannot get RX class rules");
+		free(nfccmd);
+		return err;
+	}
+
+	/* write locations to bitmap */
+	rule_locs = nfccmd->rule_locs;
+	for (i = 0; i < count; i++) {
+		err = rxclass_rule_get(fd, ifr, rule_locs[i]);
+		if (err < 0)
+			break;
+	}
+
+	/* free memory and set flag to avoid reinit */
+	free(nfccmd);
+
+	return err;
+}
+
+/*
+ * This is a simple rule manager implementation for ordering rx flow
+ * classification rules based on newest rules being first in the list.
+ * The assumption is that this rule manager is the only one adding rules to
+ * the device's hardware classifier.
+ */
+
+struct rmgr_ctrl {
+	/* slot contains a bitmap indicating which filters are valid */
+	unsigned long		*slot;
+	__u32			n_rules;
+	__u32			size;
+};
+
+static struct rmgr_ctrl rmgr;
+static int rmgr_init_done = 0;
+
+static int rmgr_ins(__u32 loc)
+{
+	/* verify location is in rule manager range */
+	if (loc >= rmgr.size) {
+		fprintf(stderr, "rmgr: Location out of range\n");
+		return -1;
+	}
+
+	/* set bit for the rule */
+	set_bit(loc, rmgr.slot);
+
+	return 0;
+}
+
+static int rmgr_find_empty_slot(struct ethtool_rx_flow_spec *fsp)
+{
+	__u32 loc;
+	__u32 slot_num;
+
+	/* start at the end of the list since it is lowest priority */
+	loc = rmgr.size - 1;
+
+	/* locate the first slot a rule can be placed in */
+	slot_num = loc / BITS_PER_LONG;
+
+	/*
+	 * Avoid testing individual bits by inverting the word and checking
+	 * to see if any bits are left set, if so there are empty spots.  By
+	 * moving 1 + loc % BITS_PER_LONG we align ourselves to the last bit
+	 * in the previous word.
+	 *
+	 * If loc rolls over it should be greater than or equal to rmgr.size
+	 * and as such we know we have reached the end of the list.
+	 */
+	if (!~(rmgr.slot[slot_num] | (~1UL << rmgr.size % BITS_PER_LONG))) {
+		loc -= 1 + (loc % BITS_PER_LONG);
+		slot_num--;
+	}
+
+	/*
+	 * Now that we are aligned with the last bit in each long we can just
+	 * go though and eliminate all the longs with no free bits
+	 */
+	while (loc < rmgr.size && !~(rmgr.slot[slot_num])) {
+		loc -= BITS_PER_LONG;
+		slot_num--;
+	}
+
+	/*
+	 * If we still are inside the range, test individual bits as one is
+	 * likely available for our use.
+	 */
+	while (loc < rmgr.size && test_bit(loc, rmgr.slot))
+		loc--;
+
+	/* location found, insert rule */
+	if (loc < rmgr.size) {
+		fsp->location = loc;
+		return rmgr_ins(loc);
+	}
+
+	/* No space to add this rule */
+	fprintf(stderr, "rmgr: Cannot find appropriate slot to insert rule\n");
+
+	return -1;
+}
+
+static int rmgr_init(int fd, struct ifreq *ifr)
+{
+	struct ethtool_rxnfc *nfccmd;
+	int err, i;
+	__u32 *rule_locs;
+
+	if (rmgr_init_done)
+		return 0;
+
+	/* clear rule manager settings */
+	memset(&rmgr, 0, sizeof(struct rmgr_ctrl));
+
+	/* request count and store in rmgr.n_rules */
+	err = rxclass_get_count(fd, ifr, &rmgr.n_rules);
+	if (err < 0)
+		return err;
+
+	/* alloc memory for request of location list */
+	nfccmd = calloc(1, sizeof(*nfccmd) + (rmgr.n_rules * sizeof(__u32)));
+	if (!nfccmd) {
+		perror("rmgr: Cannot allocate memory for"
+		       " RX class rule locations");
+		return -1;
+	}
+
+	/* request location list */
+	nfccmd->cmd = ETHTOOL_GRXCLSRLALL;
+	nfccmd->rule_cnt = rmgr.n_rules;
+	ifr->ifr_data = (caddr_t)nfccmd;
+	err = ioctl(fd, SIOCETHTOOL, ifr);
+	if (err < 0) {
+		perror("rmgr: Cannot get RX class rules");
+		free(nfccmd);
+		return err;
+	}
+
+	/* make certain the table size is valid */
+	rmgr.size = nfccmd->data;
+	if (rmgr.size == 0 || rmgr.size < rmgr.n_rules) {
+		perror("rmgr: Invalid RX class rules table size");
+		return -1;
+	}
+
+	/* initialize bitmap for storage of valid locations */
+	rmgr.slot = calloc(1, BITS_TO_LONGS(rmgr.size) * sizeof(long));
+	if (!rmgr.slot) {
+		perror("rmgr: Cannot allocate memory for RX class rules");
+		return -1;
+	}
+
+	/* write locations to bitmap */
+	rule_locs = nfccmd->rule_locs;
+	for (i = 0; i < rmgr.n_rules; i++) {
+		err = rmgr_ins(rule_locs[i]);
+		if (err < 0)
+			break;
+	}
+
+	/* free memory and set flag to avoid reinit */
+	free(nfccmd);
+	rmgr_init_done = 1;
+
+	return err;
+}
+
+static void rmgr_cleanup(void)
+{
+	if (!rmgr_init_done)
+		return;
+
+	rmgr_init_done = 0;
+
+	free(rmgr.slot);
+	rmgr.slot = NULL;
+	rmgr.size = 0;
+}
+
+static int rmgr_set_location(int fd, struct ifreq *ifr,
+			     struct ethtool_rx_flow_spec *fsp)
+{
+	int err;
+
+	/* init table of available rules */
+	err = rmgr_init(fd, ifr);
+	if (err < 0)
+		return err;
+
+	/* verify rule location */
+	err = rmgr_find_empty_slot(fsp);
+
+	/* cleanup table and free resources */
+	rmgr_cleanup();
+
+	return err;
+}
+
+int rxclass_rule_ins(int fd, struct ifreq *ifr,
+		     struct ethtool_rx_flow_spec *fsp)
+{
+	struct ethtool_rxnfc nfccmd;
+	__u32 loc = fsp->location;
+	int err;
+
+	/*
+	 * if location is unspecified pull rules from device
+	 * and allocate a free rule for our use
+	 */
+	if (loc == RX_CLS_LOC_UNSPEC) {
+		err = rmgr_set_location(fd, ifr, fsp);
+		if (err < 0)
+			return err;
+	}
+
+	/* notify netdev of new rule */
+	nfccmd.cmd = ETHTOOL_SRXCLSRLINS;
+	nfccmd.fs = *fsp;
+	ifr->ifr_data = (caddr_t)&nfccmd;
+	err = ioctl(fd, SIOCETHTOOL, ifr);
+	if (err < 0)
+		perror("rmgr: Cannot insert RX class rule");
+	else if (loc == RX_CLS_LOC_UNSPEC)
+		printf("Added rule with ID %d\n", fsp->location);
+
+	return 0;
+}
+
+int rxclass_rule_del(int fd, struct ifreq *ifr, __u32 loc)
+{
+	struct ethtool_rxnfc nfccmd;
+	int err;
+
+	/* notify netdev of rule removal */
+	nfccmd.cmd = ETHTOOL_SRXCLSRLDEL;
+	nfccmd.fs.location = loc;
+	ifr->ifr_data = (caddr_t)&nfccmd;
+	err = ioctl(fd, SIOCETHTOOL, ifr);
+	if (err < 0)
+		perror("rmgr: Cannot delete RX class rule");
+
+	return err;
+}
+
+typedef enum {
+	OPT_NONE = 0,
+	OPT_S32,
+	OPT_U8,
+	OPT_U16,
+	OPT_U32,
+	OPT_U64,
+	OPT_BE16,
+	OPT_BE32,
+	OPT_BE64,
+	OPT_IP4,
+	OPT_MAC,
+} rule_opt_type_t;
+
+#define NFC_FLAG_RING		0x001
+#define NFC_FLAG_LOC		0x002
+#define NFC_FLAG_SADDR		0x004
+#define NFC_FLAG_DADDR		0x008
+#define NFC_FLAG_SPORT		0x010
+#define NFC_FLAG_DPORT		0x020
+#define NFC_FLAG_SPI		0x030
+#define NFC_FLAG_TOS		0x040
+#define NFC_FLAG_PROTO		0x080
+#define NTUPLE_FLAG_VLAN	0x100
+#define NTUPLE_FLAG_UDEF	0x200
+#define NTUPLE_FLAG_VETH	0x400
+
+struct rule_opts {
+	const char	*name;
+	rule_opt_type_t	type;
+	u32		flag;
+	int		offset;
+	int		moffset;
+};
+
+static struct rule_opts rule_nfc_tcp_ip4[] = {
+	{ "src-ip", OPT_IP4, NFC_FLAG_SADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.tcp_ip4_spec.ip4src),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.tcp_ip4_spec.ip4src) },
+	{ "dst-ip", OPT_IP4, NFC_FLAG_DADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.tcp_ip4_spec.ip4dst),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.tcp_ip4_spec.ip4dst) },
+	{ "tos", OPT_U8, NFC_FLAG_TOS,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.tcp_ip4_spec.tos),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.tcp_ip4_spec.tos) },
+	{ "src-port", OPT_BE16, NFC_FLAG_SPORT,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.tcp_ip4_spec.psrc),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.tcp_ip4_spec.psrc) },
+	{ "dst-port", OPT_BE16, NFC_FLAG_DPORT,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.tcp_ip4_spec.pdst),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.tcp_ip4_spec.pdst) },
+	{ "action", OPT_U64, NFC_FLAG_RING,
+	  offsetof(struct ethtool_rx_flow_spec, ring_cookie), -1 },
+	{ "loc", OPT_U32, NFC_FLAG_LOC,
+	  offsetof(struct ethtool_rx_flow_spec, location), -1 },
+	{ "vlan-etype", OPT_BE16, NTUPLE_FLAG_VETH,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_etype),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_etype) },
+	{ "vlan", OPT_BE16, NTUPLE_FLAG_VLAN,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_tci),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_tci) },
+	{ "user-def", OPT_BE64, NTUPLE_FLAG_UDEF,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.data),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.data) },
+};
+
+static struct rule_opts rule_nfc_esp_ip4[] = {
+	{ "src-ip", OPT_IP4, NFC_FLAG_SADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.esp_ip4_spec.ip4src),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.esp_ip4_spec.ip4src) },
+	{ "dst-ip", OPT_IP4, NFC_FLAG_DADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.esp_ip4_spec.ip4dst),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.esp_ip4_spec.ip4dst) },
+	{ "tos", OPT_U8, NFC_FLAG_TOS,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.esp_ip4_spec.tos),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.esp_ip4_spec.tos) },
+	{ "spi", OPT_BE32, NFC_FLAG_SPI,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.esp_ip4_spec.spi),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.esp_ip4_spec.spi) },
+	{ "action", OPT_U64, NFC_FLAG_RING,
+	  offsetof(struct ethtool_rx_flow_spec, ring_cookie), -1 },
+	{ "loc", OPT_U32, NFC_FLAG_LOC,
+	  offsetof(struct ethtool_rx_flow_spec, location), -1 },
+	{ "vlan-etype", OPT_BE16, NTUPLE_FLAG_VETH,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_etype),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_etype) },
+	{ "vlan", OPT_BE16, NTUPLE_FLAG_VLAN,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_tci),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_tci) },
+	{ "user-def", OPT_BE64, NTUPLE_FLAG_UDEF,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.data),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.data) },
+};
+
+static struct rule_opts rule_nfc_usr_ip4[] = {
+	{ "src-ip", OPT_IP4, NFC_FLAG_SADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.ip4src),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.ip4src) },
+	{ "dst-ip", OPT_IP4, NFC_FLAG_DADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.ip4dst),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.ip4dst) },
+	{ "tos", OPT_U8, NFC_FLAG_TOS,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.tos),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.tos) },
+	{ "l4proto", OPT_U8, NFC_FLAG_PROTO,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.proto),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.proto) },
+	{ "spi", OPT_BE32, NFC_FLAG_SPI,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.l4_4_bytes),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.l4_4_bytes) },
+	{ "src-port", OPT_BE16, NFC_FLAG_SPORT,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.l4_4_bytes),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.l4_4_bytes) },
+	{ "dst-port", OPT_BE16, NFC_FLAG_DPORT,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.usr_ip4_spec.l4_4_bytes) + 2,
+	  offsetof(struct ethtool_rx_flow_spec, m_u.usr_ip4_spec.l4_4_bytes) + 2 },
+	{ "action", OPT_U64, NFC_FLAG_RING,
+	  offsetof(struct ethtool_rx_flow_spec, ring_cookie), -1 },
+	{ "loc", OPT_U32, NFC_FLAG_LOC,
+	  offsetof(struct ethtool_rx_flow_spec, location), -1 },
+	{ "vlan-etype", OPT_BE16, NTUPLE_FLAG_VETH,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_etype),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_etype) },
+	{ "vlan", OPT_BE16, NTUPLE_FLAG_VLAN,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_tci),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_tci) },
+	{ "user-def", OPT_BE64, NTUPLE_FLAG_UDEF,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.data),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.data) },
+};
+
+static struct rule_opts rule_nfc_ether[] = {
+	{ "src", OPT_MAC, NFC_FLAG_SADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.ether_spec.h_dest),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.ether_spec.h_dest) },
+	{ "dst", OPT_MAC, NFC_FLAG_DADDR,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.ether_spec.h_source),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.ether_spec.h_source) },
+	{ "proto", OPT_BE16, NFC_FLAG_PROTO,
+	  offsetof(struct ethtool_rx_flow_spec, h_u.ether_spec.h_proto),
+	  offsetof(struct ethtool_rx_flow_spec, m_u.ether_spec.h_proto) },
+	{ "action", OPT_U64, NFC_FLAG_RING,
+	  offsetof(struct ethtool_rx_flow_spec, ring_cookie), -1 },
+	{ "loc", OPT_U32, NFC_FLAG_LOC,
+	  offsetof(struct ethtool_rx_flow_spec, location), -1 },
+	{ "vlan-etype", OPT_BE16, NTUPLE_FLAG_VETH,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_etype),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_etype) },
+	{ "vlan", OPT_BE16, NTUPLE_FLAG_VLAN,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.vlan_tci),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.vlan_tci) },
+	{ "user-def", OPT_BE64, NTUPLE_FLAG_UDEF,
+	  offsetof(struct ethtool_rx_flow_spec, h_ext.data),
+	  offsetof(struct ethtool_rx_flow_spec, m_ext.data) },
+};
+
+static int rxclass_get_long(char *str, long long *val, int size)
+{
+	long long max = ~0ULL >> (65 - size);
+	char *endp;
+
+	errno = 0;
+
+	*val = strtoll(str, &endp, 0);
+
+	if (*endp || errno || (*val > max) || (*val < ~max))
+		return -1;
+
+	return 0;
+}
+
+static int rxclass_get_ulong(char *str, unsigned long long *val, int size)
+{
+	long long max = ~0ULL >> (64 - size);
+	char *endp;
+
+	errno = 0;
+
+	*val = strtoull(str, &endp, 0);
+
+	if (*endp || errno || (*val > max))
+		return -1;
+
+	return 0;
+}
+
+static int rxclass_get_ipv4(char *str, __be32 *val)
+{
+	if (!inet_pton(AF_INET, str, val))
+		return -1;
+
+	return 0;
+}
+
+static int rxclass_get_ether(char *str, unsigned char *val)
+{
+	unsigned int buf[ETH_ALEN];
+	int count;
+
+	if (!strchr(str, ':'))
+		return -1;
+
+	count = sscanf(str, "%2x:%2x:%2x:%2x:%2x:%2x",
+		       &buf[0], &buf[1], &buf[2],
+		       &buf[3], &buf[4], &buf[5]);
+
+	if (count != ETH_ALEN)
+		return -1;
+
+	do {
+		count--;
+		val[count] = buf[count];
+	} while (count);
+
+	return 0;
+}
+
+static int rxclass_get_val(char *str, unsigned char *p, u32 *flags,
+			   const struct rule_opts *opt)
+{
+	unsigned long long mask = ~0ULL;
+	int err = 0;
+
+	if (*flags & opt->flag)
+		return -1;
+
+	*flags |= opt->flag;
+
+	switch (opt->type) {
+	case OPT_S32: {
+		long long val;
+		err = rxclass_get_long(str, &val, 32);
+		if (err)
+			return -1;
+		*(int *)&p[opt->offset] = (int)val;
+		if (opt->moffset >= 0)
+			*(int *)&p[opt->moffset] = (int)mask;
+		break;
+	}
+	case OPT_U8: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 8);
+		if (err)
+			return -1;
+		*(u8 *)&p[opt->offset] = (u8)val;
+		if (opt->moffset >= 0)
+			*(u8 *)&p[opt->moffset] = (u8)mask;
+		break;
+	}
+	case OPT_U16: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 16);
+		if (err)
+			return -1;
+		*(u16 *)&p[opt->offset] = (u16)val;
+		if (opt->moffset >= 0)
+			*(u16 *)&p[opt->moffset] = (u16)mask;
+		break;
+	}
+	case OPT_U32: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 32);
+		if (err)
+			return -1;
+		*(u32 *)&p[opt->offset] = (u32)val;
+		if (opt->moffset >= 0)
+			*(u32 *)&p[opt->moffset] = (u32)mask;
+		break;
+	}
+	case OPT_U64: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 64);
+		if (err)
+			return -1;
+		*(u64 *)&p[opt->offset] = (u64)val;
+		if (opt->moffset >= 0)
+			*(u64 *)&p[opt->moffset] = (u64)mask;
+		break;
+	}
+	case OPT_BE16: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 16);
+		if (err)
+			return -1;
+		*(__be16 *)&p[opt->offset] = htons((u16)val);
+		if (opt->moffset >= 0)
+			*(__be16 *)&p[opt->moffset] = (__be16)mask;
+		break;
+	}
+	case OPT_BE32: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 32);
+		if (err)
+			return -1;
+		*(__be32 *)&p[opt->offset] = htonl((u32)val);
+		if (opt->moffset >= 0)
+			*(__be32 *)&p[opt->moffset] = (__be32)mask;
+		break;
+	}
+	case OPT_BE64: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 64);
+		if (err)
+			return -1;
+		*(__be64 *)&p[opt->offset] = htonll((u64)val);
+		if (opt->moffset >= 0)
+			*(__be64 *)&p[opt->moffset] = (__be64)mask;
+		break;
+	}
+	case OPT_IP4: {
+		__be32 val;
+		err = rxclass_get_ipv4(str, &val);
+		if (err)
+			return -1;
+		*(__be32 *)&p[opt->offset] = val;
+		if (opt->moffset >= 0)
+			*(__be32 *)&p[opt->moffset] = (__be32)mask;
+		break;
+	}
+	case OPT_MAC: {
+		unsigned char val[ETH_ALEN];
+		err = rxclass_get_ether(str, val);
+		if (err)
+			return -1;
+		memcpy(&p[opt->offset], val, ETH_ALEN);
+		if (opt->moffset >= 0)
+			memcpy(&p[opt->moffset], &mask, ETH_ALEN);
+		break;
+	}
+	case OPT_NONE:
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+static int rxclass_get_mask(char *str, unsigned char *p,
+			    const struct rule_opts *opt)
+{
+	int err = 0;
+
+	if (opt->moffset < 0)
+		return -1;
+
+	switch (opt->type) {
+	case OPT_S32: {
+		long long val;
+		err = rxclass_get_long(str, &val, 32);
+		if (err)
+			return -1;
+		*(int *)&p[opt->moffset] = ~(int)val;
+		break;
+	}
+	case OPT_U8: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 8);
+		if (err)
+			return -1;
+		*(u8 *)&p[opt->moffset] = ~(u8)val;
+		break;
+	}
+	case OPT_U16: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 16);
+		if (err)
+			return -1;
+		*(u16 *)&p[opt->moffset] = ~(u16)val;
+		break;
+	}
+	case OPT_U32: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 32);
+		if (err)
+			return -1;
+		*(u32 *)&p[opt->moffset] = ~(u32)val;
+		break;
+	}
+	case OPT_U64: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 64);
+		if (err)
+			return -1;
+		*(u64 *)&p[opt->moffset] = ~(u64)val;
+		break;
+	}
+	case OPT_BE16: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 16);
+		if (err)
+			return -1;
+		*(__be16 *)&p[opt->moffset] = ~htons((u16)val);
+		break;
+	}
+	case OPT_BE32: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 32);
+		if (err)
+			return -1;
+		*(__be32 *)&p[opt->moffset] = ~htonl((u32)val);
+		break;
+	}
+	case OPT_BE64: {
+		unsigned long long val;
+		err = rxclass_get_ulong(str, &val, 64);
+		if (err)
+			return -1;
+		*(__be64 *)&p[opt->moffset] = ~htonll((u64)val);
+		break;
+	}
+	case OPT_IP4: {
+		__be32 val;
+		err = rxclass_get_ipv4(str, &val);
+		if (err)
+			return -1;
+		*(__be32 *)&p[opt->moffset] = ~val;
+		break;
+	}
+	case OPT_MAC: {
+		unsigned char val[ETH_ALEN];
+		int i;
+		err = rxclass_get_ether(str, val);
+		if (err)
+			return -1;
+
+		for (i = 0; i < ETH_ALEN; i++)
+			val[i] = ~val[i];
+
+		memcpy(&p[opt->moffset], val, ETH_ALEN);
+		break;
+	}
+	case OPT_NONE:
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+int rxclass_parse_ruleopts(char **argp, int argc,
+			   struct ethtool_rx_flow_spec *fsp)
+{
+	const struct rule_opts *options;
+	unsigned char *p = (unsigned char *)fsp;
+	int i = 0, n_opts, err;
+	u32 flags = 0;
+	int flow_type;
+
+	if (argc < 1)
+		goto syntax_err;
+
+	if (!strcmp(argp[0], "tcp4"))
+		flow_type = TCP_V4_FLOW;
+	else if (!strcmp(argp[0], "udp4"))
+		flow_type = UDP_V4_FLOW;
+	else if (!strcmp(argp[0], "sctp4"))
+		flow_type = SCTP_V4_FLOW;
+	else if (!strcmp(argp[0], "ah4"))
+		flow_type = AH_V4_FLOW;
+	else if (!strcmp(argp[0], "esp4"))
+		flow_type = ESP_V4_FLOW;
+	else if (!strcmp(argp[0], "ip4"))
+		flow_type = IP_USER_FLOW;
+	else if (!strcmp(argp[0], "ether"))
+		flow_type = ETHER_FLOW;
+	else
+		goto syntax_err;
+
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		options = rule_nfc_tcp_ip4;
+		n_opts = ARRAY_SIZE(rule_nfc_tcp_ip4);
+		break;
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+		options = rule_nfc_esp_ip4;
+		n_opts = ARRAY_SIZE(rule_nfc_esp_ip4);
+		break;
+	case IP_USER_FLOW:
+		options = rule_nfc_usr_ip4;
+		n_opts = ARRAY_SIZE(rule_nfc_usr_ip4);
+		break;
+	case ETHER_FLOW:
+		options = rule_nfc_ether;
+		n_opts = ARRAY_SIZE(rule_nfc_ether);
+		break;
+	default:
+		fprintf(stderr, "Add rule, invalid rule type[%s]\n", argp[0]);
+		return -1;
+	}
+
+	memset(p, 0, sizeof(*fsp));
+	fsp->flow_type = flow_type;
+	fsp->location = RX_CLS_LOC_UNSPEC;
+
+	for (i = 1; i < argc;) {
+		const struct rule_opts *opt;
+		int idx;
+		for (opt = options, idx = 0; idx < n_opts; idx++, opt++) {
+			char mask_name[16];
+
+			if (strcmp(argp[i], opt->name))
+				continue;
+
+			i++;
+			if (i >= argc)
+				break;
+
+			err = rxclass_get_val(argp[i], p, &flags, opt);
+			if (err) {
+				fprintf(stderr, "Invalid %s value[%s]\n",
+					opt->name, argp[i]);
+				return -1;
+			}
+
+			i++;
+			if (i >= argc)
+				break;
+
+			sprintf(mask_name, "%s-mask", opt->name);
+			if (strcmp(argp[i], "m") && strcmp(argp[i], mask_name))
+				break;
+
+			i++;
+			if (i >= argc)
+				goto syntax_err;
+
+			err = rxclass_get_mask(argp[i], p, opt);
+			if (err) {
+				fprintf(stderr, "Invalid %s mask[%s]\n",
+					opt->name, argp[i]);
+				return -1;
+			}
+
+			i++;
+
+			break;
+		}
+		if (idx == n_opts) {
+			fprintf(stdout, "Add rule, unrecognized option[%s]\n",
+				argp[i]);
+			return -1;
+		}
+	}
+
+	if (flags & (NTUPLE_FLAG_VLAN | NTUPLE_FLAG_UDEF | NTUPLE_FLAG_VETH))
+		fsp->flow_type |= FLOW_EXT;
+
+	return 0;
+
+syntax_err:
+	fprintf(stderr, "Add rule, invalid syntax\n");
+	return -1;
+}