[PATCH 2/2] [RFC] packet: experimental support for 64-bit timestamps
From: Arnd Bergmann
Date: Mon Nov 27 2017 - 11:21:29 EST
I tried to figure out what it would take to do a version 4 mmap packet
socket interface to completely avoid the y2106 overflow problem. This is
what I came up with, reusing most of the v3 code, except for the parts
where we access the timestamps.
For kselftest, I'm adding support for testing v4 in addition to v1-v3,
but the test currently does not look at the timestamps, so it won't
check that the timestamp format actually works as intended, only that
I didn't break the parts that worked in the v3 selftest.
Overall, this is more of a mess than I expected, so it's probably not
worth doing a v4 format just for the timestamp, but the patch can serve
as a reference for anyone that needs a new format for other reasons and
fixes this along with the other changes.
Signed-off-by: Arnd Bergmann <arnd@xxxxxxxx>
---
Untested and rather invasive, so don't apply this part without
discussion and testing
---
include/uapi/linux/if_packet.h | 24 +++++-
net/packet/af_packet.c | 115 ++++++++++++++++++++--------
tools/testing/selftests/net/psock_tpacket.c | 65 +++++++++-------
3 files changed, 142 insertions(+), 62 deletions(-)
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 67b61d91d89b..c2cf29acdd40 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -177,8 +177,27 @@ struct tpacket3_hdr {
__u8 tp_padding[8];
};
+struct tpacket4_hdr {
+ __u32 tp_next_offset;
+ __u32 tp_nsec_hi;
+ __u32 tp_nsec_lo;
+ __u32 tp_snaplen;
+ __u32 tp_len;
+ __u32 tp_status;
+ __u16 tp_mac;
+ __u16 tp_net;
+ /* pkt_hdr variants */
+ union {
+ struct tpacket_hdr_variant1 hv1;
+ };
+ __u8 tp_padding[8];
+};
+
struct tpacket_bd_ts {
- unsigned int ts_sec;
+ union {
+ unsigned int ts_nsec_hi;
+ unsigned int ts_sec;
+ };
union {
unsigned int ts_usec;
unsigned int ts_nsec;
@@ -250,7 +269,8 @@ struct tpacket_block_desc {
enum tpacket_versions {
TPACKET_V1,
TPACKET_V2,
- TPACKET_V3
+ TPACKET_V3,
+ TPACKET_V4,
};
/*
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 7432c6699818..34a07e4a93a5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -164,6 +164,7 @@ union tpacket_uhdr {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
struct tpacket3_hdr *h3;
+ struct tpacket4_hdr *h4;
void *raw;
};
@@ -200,7 +201,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *,
struct packet_sock *, unsigned int status);
static int prb_queue_frozen(struct tpacket_kbdq_core *);
static void prb_open_block(struct tpacket_kbdq_core *,
- struct tpacket_block_desc *);
+ struct tpacket_block_desc *, struct packet_sock *po);
static void prb_retire_rx_blk_timer_expired(struct timer_list *);
static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *);
static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *);
@@ -404,6 +405,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
break;
case TPACKET_V3:
+ case TPACKET_V4:
h.h3->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h3->tp_status));
break;
@@ -430,6 +432,7 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
return h.h2->tp_status;
case TPACKET_V3:
+ case TPACKET_V4:
flush_dcache_page(pgv_to_page(&h.h3->tp_status));
return h.h3->tp_status;
default:
@@ -439,17 +442,17 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
}
}
-static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts,
+static __u32 tpacket_get_timestamp(struct sk_buff *skb, s64 *stamp,
unsigned int flags)
{
struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
if (shhwtstamps &&
(flags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
- ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts))
+ (*stamp = ktime_to_ns(shhwtstamps->hwtstamp)))
return TP_STATUS_TS_RAW_HARDWARE;
- if (ktime_to_timespec64_cond(skb->tstamp, ts))
+ if ((*stamp = ktime_to_ns(skb->tstamp)))
return TP_STATUS_TS_SOFTWARE;
return 0;
@@ -460,19 +463,15 @@ static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
{
union tpacket_uhdr h;
struct timespec64 ts;
+ s64 stamp;
__u32 ts_status;
- if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+ if (!(ts_status = tpacket_get_timestamp(skb, &stamp, po->tp_tstamp)))
return 0;
h.raw = frame;
- /*
- * versions 1 through 3 overflow the timestamps in y2106, since they
- * all store the seconds in a 32-bit unsigned integer.
- * If we create a version 4, that should have a 64-bit timestamp,
- * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit
- * nanoseconds.
- */
+
+ ts = ns_to_timespec64(stamp);
switch (po->tp_version) {
case TPACKET_V1:
h.h1->tp_sec = ts.tv_sec;
@@ -486,6 +485,9 @@ static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
h.h3->tp_sec = ts.tv_sec;
h.h3->tp_nsec = ts.tv_nsec;
break;
+ case TPACKET_V4:
+ h.h4->tp_nsec_hi = upper_32_bits(stamp);
+ h.h4->tp_nsec_lo = lower_32_bits(stamp);
default:
WARN(1, "TPACKET version not supported.\n");
BUG();
@@ -633,7 +635,7 @@ static void init_prb_bdqc(struct packet_sock *po,
p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
prb_init_ft_ops(p1, req_u);
prb_setup_retire_blk_timer(po);
- prb_open_block(p1, pbd);
+ prb_open_block(p1, pbd, po);
}
/* Do NOT update the last_blk_num first.
@@ -730,7 +732,7 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t)
* opening a block thaws the queue,restarts timer
* Thawing/timer-refresh is a side effect.
*/
- prb_open_block(pkc, pbd);
+ prb_open_block(pkc, pbd, po);
goto out;
}
}
@@ -792,30 +794,43 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
{
__u32 status = TP_STATUS_USER | stat;
- struct tpacket3_hdr *last_pkt;
+ struct tpacket3_hdr *last_pkt_v3;
+ struct tpacket4_hdr *last_pkt_v4;
struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
struct sock *sk = &po->sk;
if (po->stats.stats3.tp_drops)
status |= TP_STATUS_LOSING;
- last_pkt = (struct tpacket3_hdr *)pkc1->prev;
- last_pkt->tp_next_offset = 0;
+ last_pkt_v3 = (struct tpacket3_hdr *)pkc1->prev;
+ last_pkt_v4 = (struct tpacket4_hdr *)pkc1->prev;
+ last_pkt_v3->tp_next_offset = 0;
/* Get the ts of the last pkt */
if (BLOCK_NUM_PKTS(pbd1)) {
- h1->ts_last_pkt.ts_sec = last_pkt->tp_sec;
- h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec;
+ if (po->tp_version == TPACKET_V3) {
+ h1->ts_last_pkt.ts_sec = last_pkt_v3->tp_sec;
+ h1->ts_last_pkt.ts_nsec = last_pkt_v3->tp_nsec;
+ } else {
+ h1->ts_last_pkt.ts_nsec_hi = last_pkt_v4->tp_nsec_hi;
+ h1->ts_last_pkt.ts_nsec = last_pkt_v4->tp_nsec_lo;
+ }
} else {
/* Ok, we tmo'd - so get the current time.
*
* It shouldn't really happen as we don't close empty
* blocks. See prb_retire_rx_blk_timer_expired().
*/
- struct timespec64 ts;
- ktime_get_real_ts64(&ts);
- h1->ts_last_pkt.ts_sec = ts.tv_sec;
- h1->ts_last_pkt.ts_nsec = ts.tv_nsec;
+ if (po->tp_version == TPACKET_V3) {
+ struct timespec64 ts;
+ ktime_get_real_ts64(&ts);
+ h1->ts_last_pkt.ts_sec = ts.tv_sec;
+ h1->ts_last_pkt.ts_nsec = ts.tv_nsec;
+ } else {
+ u64 ns = ktime_get_real_ns();
+ h1->ts_last_pkt.ts_nsec_hi = upper_32_bits(ns);
+ h1->ts_last_pkt.ts_nsec = lower_32_bits(ns);
+ }
}
smp_wmb();
@@ -841,9 +856,8 @@ static void prb_thaw_queue(struct tpacket_kbdq_core *pkc)
*
*/
static void prb_open_block(struct tpacket_kbdq_core *pkc1,
- struct tpacket_block_desc *pbd1)
+ struct tpacket_block_desc *pbd1, struct packet_sock *po)
{
- struct timespec64 ts;
struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
smp_rmb();
@@ -856,10 +870,19 @@ static void prb_open_block(struct tpacket_kbdq_core *pkc1,
BLOCK_NUM_PKTS(pbd1) = 0;
BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
- ktime_get_real_ts64(&ts);
- h1->ts_first_pkt.ts_sec = ts.tv_sec;
- h1->ts_first_pkt.ts_nsec = ts.tv_nsec;
+ if (po->tp_version == TPACKET_V3) {
+ struct timespec64 ts;
+
+ ktime_get_real_ts64(&ts);
+ h1->ts_first_pkt.ts_sec = ts.tv_sec;
+ h1->ts_first_pkt.ts_nsec = ts.tv_nsec;
+ } else {
+ s64 ns = ktime_get_real_ns();
+
+ h1->ts_first_pkt.ts_nsec_hi = upper_32_bits(ns);
+ h1->ts_first_pkt.ts_nsec = lower_32_bits(ns);
+ }
pkc1->pkblk_start = (char *)pbd1;
pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
@@ -936,7 +959,7 @@ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc,
* open this block and return the offset where the first packet
* needs to get stored.
*/
- prb_open_block(pkc, pbd);
+ prb_open_block(pkc, pbd, po);
return (void *)pkc->nxt_offset;
}
@@ -1068,7 +1091,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po,
* opening a block also thaws the queue.
* Thawing is a side effect.
*/
- prb_open_block(pkc, pbd);
+ prb_open_block(pkc, pbd, po);
}
}
@@ -1113,6 +1136,7 @@ static void *packet_current_rx_frame(struct packet_sock *po,
po->rx_ring.head, status);
return curr;
case TPACKET_V3:
+ case TPACKET_V4:
return __packet_lookup_frame_in_block(po, skb, status, len);
default:
WARN(1, "TPACKET version not supported\n");
@@ -1171,6 +1195,7 @@ static void packet_increment_rx_head(struct packet_sock *po,
case TPACKET_V2:
return packet_increment_head(rb);
case TPACKET_V3:
+ case TPACKET_V4:
default:
WARN(1, "TPACKET version not supported.\n");
BUG();
@@ -1279,7 +1304,7 @@ static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
return ROOM_NONE;
}
- if (po->tp_version == TPACKET_V3) {
+ if (po->tp_version == TPACKET_V3 || po->tp_version == TPACKET_V4) {
if (__tpacket_v3_has_room(po, ROOM_POW_OFF))
ret = ROOM_NORMAL;
else if (__tpacket_v3_has_room(po, 0))
@@ -2192,6 +2217,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
unsigned short macoff, netoff, hdrlen;
struct sk_buff *copy_skb = NULL;
struct timespec64 ts;
+ u64 ns;
__u32 ts_status;
bool is_drop_n_account = false;
bool do_vnet = false;
@@ -2318,7 +2344,9 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
- if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+ if ((ts_status = tpacket_get_timestamp(skb, &ns, po->tp_tstamp)))
+ ts = ns_to_timespec64(ns);
+ else
ktime_get_real_ts64(&ts);
status |= ts_status;
@@ -2365,6 +2393,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding));
hdrlen = sizeof(*h.h3);
break;
+ case TPACKET_V4:
+ /* identical to v3, except for the timestamp */
+ h.h4->tp_status |= status;
+ h.h4->tp_len = skb->len;
+ h.h4->tp_snaplen = snaplen;
+ h.h4->tp_mac = macoff;
+ h.h4->tp_net = netoff;
+ ns = timespec64_to_ns(&ts);
+ h.h4->tp_nsec_hi = upper_32_bits(ns);
+ h.h4->tp_nsec_lo = lower_32_bits(ns);
+ memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding));
+ hdrlen = sizeof(*h.h3);
+ break;
default:
BUG();
}
@@ -2570,6 +2611,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
ph.raw = frame;
switch (po->tp_version) {
+ case TPACKET_V4:
case TPACKET_V3:
if (ph.h3->tp_next_offset != 0) {
pr_warn_once("variable sized slot not supported");
@@ -2596,6 +2638,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
off_max = po->tx_ring.frame_size - tp_len;
if (po->sk.sk_type == SOCK_DGRAM) {
switch (po->tp_version) {
+ case TPACKET_V4:
case TPACKET_V3:
off = ph.h3->tp_net;
break;
@@ -2608,6 +2651,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
}
} else {
switch (po->tp_version) {
+ case TPACKET_V4:
case TPACKET_V3:
off = ph.h3->tp_mac;
break;
@@ -3658,6 +3702,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
len = sizeof(req_u.req);
break;
case TPACKET_V3:
+ case TPACKET_V4:
default:
len = sizeof(req_u.req3);
break;
@@ -3693,6 +3738,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
case TPACKET_V1:
case TPACKET_V2:
case TPACKET_V3:
+ case TPACKET_V4:
break;
default:
return -EINVAL;
@@ -3868,7 +3914,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
memset(&po->stats, 0, sizeof(po->stats));
spin_unlock_bh(&sk->sk_receive_queue.lock);
- if (po->tp_version == TPACKET_V3) {
+ if (po->tp_version == TPACKET_V3 || po->tp_version == TPACKET_V4) {
lv = sizeof(struct tpacket_stats_v3);
st.stats3.tp_packets += st.stats3.tp_drops;
data = &st.stats3;
@@ -3906,6 +3952,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
val = sizeof(struct tpacket2_hdr);
break;
case TPACKET_V3:
+ case TPACKET_V4:
val = sizeof(struct tpacket3_hdr);
break;
default:
@@ -4250,6 +4297,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
po->tp_hdrlen = TPACKET2_HDRLEN;
break;
case TPACKET_V3:
+ case TPACKET_V4:
po->tp_hdrlen = TPACKET3_HDRLEN;
break;
}
@@ -4284,6 +4332,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
if (unlikely(!pg_vec))
goto out;
switch (po->tp_version) {
+ case TPACKET_V4:
case TPACKET_V3:
/* Block transmit is not supported yet */
if (!tx_ring) {
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 7f6cd9fdacf3..b497632b6a70 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -3,7 +3,8 @@
* Author: Daniel Borkmann <dborkman@xxxxxxxxxx>
* Chetan Loke <loke.chetan@xxxxxxxxx> (TPACKET_V3 usage example)
*
- * A basic test of packet socket's TPACKET_V1/TPACKET_V2/TPACKET_V3 behavior.
+ * A basic test of packet socket's TPACKET_V1/TPACKET_V2/TPACKET_V3/TPACKET_V4
+ * behavior.
*
* Control:
* Test the setup of the TPACKET socket with different patterns that are
@@ -19,6 +20,7 @@
* - TPACKET_V1: RX_RING, TX_RING
* - TPACKET_V2: RX_RING, TX_RING
* - TPACKET_V3: RX_RING
+ * - TPACKET_V4: RX_RING
*
* License (GPLv2):
*
@@ -310,12 +312,12 @@ static inline void __v2_tx_user_ready(struct tpacket2_hdr *hdr)
__sync_synchronize();
}
-static inline int __v3_tx_kernel_ready(struct tpacket3_hdr *hdr)
+static inline int __v3_v4_tx_kernel_ready(struct tpacket3_hdr *hdr)
{
return !(hdr->tp_status & (TP_STATUS_SEND_REQUEST | TP_STATUS_SENDING));
}
-static inline void __v3_tx_user_ready(struct tpacket3_hdr *hdr)
+static inline void __v3_v4_tx_user_ready(struct tpacket3_hdr *hdr)
{
hdr->tp_status = TP_STATUS_SEND_REQUEST;
__sync_synchronize();
@@ -329,7 +331,8 @@ static inline int __tx_kernel_ready(void *base, int version)
case TPACKET_V2:
return __v2_tx_kernel_ready(base);
case TPACKET_V3:
- return __v3_tx_kernel_ready(base);
+ case TPACKET_V4:
+ return __v3_v4_tx_kernel_ready(base);
default:
bug_on(1);
return 0;
@@ -346,7 +349,8 @@ static inline void __tx_user_ready(void *base, int version)
__v2_tx_user_ready(base);
break;
case TPACKET_V3:
- __v3_tx_user_ready(base);
+ case TPACKET_V4:
+ __v3_v4_tx_user_ready(base);
break;
}
}
@@ -372,6 +376,7 @@ static inline void *get_next_frame(struct ring *ring, int n)
case TPACKET_V2:
return ring->rd[n].iov_base;
case TPACKET_V3:
+ case TPACKET_V4:
return f0 + (n * ring->req3.tp_frame_size);
default:
bug_on(1);
@@ -454,7 +459,8 @@ static void walk_tx(int sock, struct ring *ring)
packet_len);
total_bytes += ppd.v2->tp_h.tp_snaplen;
break;
- case TPACKET_V3: {
+ case TPACKET_V3:
+ case TPACKET_V4: {
struct tpacket3_hdr *tx = next;
tx->tp_snaplen = packet_len;
@@ -517,22 +523,22 @@ static void walk_v1_v2(int sock, struct ring *ring)
walk_tx(sock, ring);
}
-static uint64_t __v3_prev_block_seq_num = 0;
+static uint64_t __v3_v4_prev_block_seq_num = 0;
-void __v3_test_block_seq_num(struct block_desc *pbd)
+void __v3_v4_test_block_seq_num(struct block_desc *pbd)
{
- if (__v3_prev_block_seq_num + 1 != pbd->h1.seq_num) {
+ if (__v3_v4_prev_block_seq_num + 1 != pbd->h1.seq_num) {
fprintf(stderr, "\nprev_block_seq_num:%"PRIu64", expected "
"seq:%"PRIu64" != actual seq:%"PRIu64"\n",
- __v3_prev_block_seq_num, __v3_prev_block_seq_num + 1,
+ __v3_v4_prev_block_seq_num, __v3_v4_prev_block_seq_num + 1,
(uint64_t) pbd->h1.seq_num);
exit(1);
}
- __v3_prev_block_seq_num = pbd->h1.seq_num;
+ __v3_v4_prev_block_seq_num = pbd->h1.seq_num;
}
-static void __v3_test_block_len(struct block_desc *pbd, uint32_t bytes, int block_num)
+static void __v3_v4_test_block_len(struct block_desc *pbd, uint32_t bytes, int block_num)
{
if (pbd->h1.num_pkts && bytes != pbd->h1.blk_len) {
fprintf(stderr, "\nblock:%u with %upackets, expected "
@@ -542,23 +548,23 @@ static void __v3_test_block_len(struct block_desc *pbd, uint32_t bytes, int bloc
}
}
-static void __v3_test_block_header(struct block_desc *pbd, const int block_num)
+static void __v3_v4_test_block_header(struct block_desc *pbd, const int block_num)
{
if ((pbd->h1.block_status & TP_STATUS_USER) == 0) {
fprintf(stderr, "\nblock %u: not in TP_STATUS_USER\n", block_num);
exit(1);
}
- __v3_test_block_seq_num(pbd);
+ __v3_v4_test_block_seq_num(pbd);
}
-static void __v3_walk_block(struct block_desc *pbd, const int block_num)
+static void __v3_v4_walk_block(struct block_desc *pbd, const int block_num)
{
int num_pkts = pbd->h1.num_pkts, i;
unsigned long bytes = 0, bytes_with_padding = ALIGN_8(sizeof(*pbd));
struct tpacket3_hdr *ppd;
- __v3_test_block_header(pbd, block_num);
+ __v3_v4_test_block_header(pbd, block_num);
ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd +
pbd->h1.offset_to_first_pkt);
@@ -580,17 +586,17 @@ static void __v3_walk_block(struct block_desc *pbd, const int block_num)
__sync_synchronize();
}
- __v3_test_block_len(pbd, bytes_with_padding, block_num);
+ __v3_v4_test_block_len(pbd, bytes_with_padding, block_num);
total_bytes += bytes;
}
-void __v3_flush_block(struct block_desc *pbd)
+void __v3_v4_flush_block(struct block_desc *pbd)
{
pbd->h1.block_status = TP_STATUS_KERNEL;
__sync_synchronize();
}
-static void walk_v3_rx(int sock, struct ring *ring)
+static void walk_v3_v4_rx(int sock, struct ring *ring)
{
unsigned int block_num = 0;
struct pollfd pfd;
@@ -614,8 +620,8 @@ static void walk_v3_rx(int sock, struct ring *ring)
while ((pbd->h1.block_status & TP_STATUS_USER) == 0)
poll(&pfd, 1, 1);
- __v3_walk_block(pbd, block_num);
- __v3_flush_block(pbd);
+ __v3_v4_walk_block(pbd, block_num);
+ __v3_v4_flush_block(pbd);
block_num = (block_num + 1) % ring->rd_num;
}
@@ -623,7 +629,7 @@ static void walk_v3_rx(int sock, struct ring *ring)
pair_udp_close(udp_sock);
if (total_packets != 2 * NUM_PACKETS) {
- fprintf(stderr, "walk_v3_rx: received %u out of %u pkts\n",
+ fprintf(stderr, "walk_v3_v4_rx: received %u out of %u pkts\n",
total_packets, NUM_PACKETS);
exit(1);
}
@@ -631,10 +637,10 @@ static void walk_v3_rx(int sock, struct ring *ring)
fprintf(stderr, " %u pkts (%u bytes)", NUM_PACKETS, total_bytes >> 1);
}
-static void walk_v3(int sock, struct ring *ring)
+static void walk_v3_v4(int sock, struct ring *ring)
{
if (ring->type == PACKET_RX_RING)
- walk_v3_rx(sock, ring);
+ walk_v3_v4_rx(sock, ring);
else
walk_tx(sock, ring);
}
@@ -655,7 +661,7 @@ static void __v1_v2_fill(struct ring *ring, unsigned int blocks)
ring->flen = ring->req.tp_frame_size;
}
-static void __v3_fill(struct ring *ring, unsigned int blocks, int type)
+static void __v3_v4_fill(struct ring *ring, unsigned int blocks, int type)
{
if (type == PACKET_RX_RING) {
ring->req3.tp_retire_blk_tov = 64;
@@ -671,7 +677,7 @@ static void __v3_fill(struct ring *ring, unsigned int blocks, int type)
ring->req3.tp_block_nr;
ring->mm_len = ring->req3.tp_block_size * ring->req3.tp_block_nr;
- ring->walk = walk_v3;
+ ring->walk = walk_v3_v4;
ring->rd_num = ring->req3.tp_block_nr;
ring->flen = ring->req3.tp_block_size;
}
@@ -695,7 +701,8 @@ static void setup_ring(int sock, struct ring *ring, int version, int type)
break;
case TPACKET_V3:
- __v3_fill(ring, blocks, type);
+ case TPACKET_V4:
+ __v3_v4_fill(ring, blocks, type);
ret = setsockopt(sock, SOL_PACKET, type, &ring->req3,
sizeof(ring->req3));
break;
@@ -804,6 +811,7 @@ static const char *tpacket_str[] = {
[TPACKET_V1] = "TPACKET_V1",
[TPACKET_V2] = "TPACKET_V2",
[TPACKET_V3] = "TPACKET_V3",
+ [TPACKET_V4] = "TPACKET_V4",
};
static const char *type_str[] = {
@@ -854,6 +862,9 @@ int main(void)
ret |= test_tpacket(TPACKET_V3, PACKET_RX_RING);
ret |= test_tpacket(TPACKET_V3, PACKET_TX_RING);
+ ret |= test_tpacket(TPACKET_V4, PACKET_RX_RING);
+ ret |= test_tpacket(TPACKET_V4, PACKET_TX_RING);
+
if (ret)
return 1;
--
2.9.0