@@ -111,6 +111,10 @@ For more detail on SR-IOV, please refer to the following documents:
by setting the ``devargs`` parameter like ``-a 18:01.0,no-poll-on-link-down=1``
when IAVF is backed by an Intel\ |reg| E810 device or an Intel\ |reg| 700 Series Ethernet device.
+ Enable mbuf check for Tx diagnostics by setting the devargs parameter like
+ ``-a 18:01.0,mbuf_check=[mbuf,<case1>,<case2>]`` when IAVF is backed by an
+ Intel\ |reg| E810 device or an Intel\ |reg| 700 Series Ethernet device.
+
The PCIE host-interface of Intel Ethernet Switch FM10000 Series VF infrastructure
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -113,9 +113,14 @@ struct iavf_ipsec_crypto_stats {
} ierrors;
};
+struct iavf_mbuf_stats {
+ uint64_t tx_pkt_errors;
+};
+
struct iavf_eth_xstats {
struct virtchnl_eth_stats eth_stats;
struct iavf_ipsec_crypto_stats ips_stats;
+ struct iavf_mbuf_stats mbuf_stats;
};
/* Structure that defines a VSI, associated with a adapter. */
@@ -309,10 +314,16 @@ struct iavf_devargs {
uint32_t watchdog_period;
int auto_reset;
int no_poll_on_link_down;
+ int mbuf_check;
};
struct iavf_security_ctx;
+#define IAVF_MBUF_CHECK_F_TX_MBUF (1ULL << 0)
+#define IAVF_MBUF_CHECK_F_TX_SIZE (1ULL << 1)
+#define IAVF_MBUF_CHECK_F_TX_SEGMENT (1ULL << 2)
+#define IAVF_MBUF_CHECK_F_TX_OFFLOAD (1ULL << 3)
+
enum iavf_rx_burst_type {
IAVF_RX_BURST_DEFAULT,
IAVF_RX_BURST_FRXD,
@@ -368,6 +379,7 @@ struct iavf_adapter {
bool no_poll;
enum iavf_rx_burst_type rx_burst_type;
enum iavf_tx_burst_type tx_burst_type;
+ uint64_t mc_flags; /* mbuf check flags. */
uint16_t fdir_ref_cnt;
struct iavf_devargs devargs;
};
@@ -13,6 +13,7 @@
#include <inttypes.h>
#include <rte_byteorder.h>
#include <rte_common.h>
+#include <rte_os_shim.h>
#include <rte_interrupts.h>
#include <rte_debug.h>
@@ -39,6 +40,8 @@
#define IAVF_RESET_WATCHDOG_ARG "watchdog_period"
#define IAVF_ENABLE_AUTO_RESET_ARG "auto_reset"
#define IAVF_NO_POLL_ON_LINK_DOWN_ARG "no-poll-on-link-down"
+#define IAVF_MBUF_CHECK_ARG "mbuf_check"
+
uint64_t iavf_timestamp_dynflag;
int iavf_timestamp_dynfield_offset = -1;
@@ -48,6 +51,7 @@ static const char * const iavf_valid_args[] = {
IAVF_RESET_WATCHDOG_ARG,
IAVF_ENABLE_AUTO_RESET_ARG,
IAVF_NO_POLL_ON_LINK_DOWN_ARG,
+ IAVF_MBUF_CHECK_ARG,
NULL
};
@@ -174,6 +178,7 @@ static const struct rte_iavf_xstats_name_off rte_iavf_stats_strings[] = {
{"tx_broadcast_packets", _OFF_OF(eth_stats.tx_broadcast)},
{"tx_dropped_packets", _OFF_OF(eth_stats.tx_discards)},
{"tx_error_packets", _OFF_OF(eth_stats.tx_errors)},
+ {"tx_mbuf_error_packets", _OFF_OF(mbuf_stats.tx_pkt_errors)},
{"inline_ipsec_crypto_ipackets", _OFF_OF(ips_stats.icount)},
{"inline_ipsec_crypto_ibytes", _OFF_OF(ips_stats.ibytes)},
@@ -1881,6 +1886,8 @@ static int iavf_dev_xstats_get(struct rte_eth_dev *dev,
{
int ret;
unsigned int i;
+ struct iavf_tx_queue *txq;
+ uint64_t mbuf_errors = 0;
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
@@ -1904,6 +1911,15 @@ static int iavf_dev_xstats_get(struct rte_eth_dev *dev,
if (iavf_ipsec_crypto_supported(adapter))
iavf_dev_update_ipsec_xstats(dev, &iavf_xtats.ips_stats);
+ if (adapter->devargs.mbuf_check) {
+ for (i = 0; i < dev->data->nb_tx_queues; i++) {
+ txq = dev->data->tx_queues[i];
+ mbuf_errors += __atomic_load_n(&txq->mbuf_errors,
+ __ATOMIC_RELAXED);
+ }
+ iavf_xtats.mbuf_stats.tx_pkt_errors = mbuf_errors;
+ }
+
/* loop over xstats array and values from pstats */
for (i = 0; i < IAVF_NB_XSTATS; i++) {
xstats[i].id = i;
@@ -2286,6 +2302,50 @@ iavf_parse_watchdog_period(__rte_unused const char *key, const char *value, void
return 0;
}
+static int
+iavf_parse_mbuf_check(__rte_unused const char *key, const char *value, void *args)
+{
+ char *cur;
+ char *tmp;
+ int str_len;
+ int valid_len;
+
+ int ret = 0;
+ uint64_t *mc_flags = args;
+ char *str2 = strdup(value);
+ if (str2 == NULL)
+ return -1;
+
+ str_len = strlen(str2);
+ if (str2[0] == '[' && str2[str_len - 1] == ']') {
+ if (str_len < 3) {
+ ret = -1;
+ goto mdd_end;
+ }
+ valid_len = str_len - 2;
+ memmove(str2, str2 + 1, valid_len);
+ memset(str2 + valid_len, '\0', 2);
+ }
+ cur = strtok_r(str2, ",", &tmp);
+ while (cur != NULL) {
+ if (!strcmp(cur, "mbuf"))
+ *mc_flags |= IAVF_MBUF_CHECK_F_TX_MBUF;
+ else if (!strcmp(cur, "size"))
+ *mc_flags |= IAVF_MBUF_CHECK_F_TX_SIZE;
+ else if (!strcmp(cur, "segment"))
+ *mc_flags |= IAVF_MBUF_CHECK_F_TX_SEGMENT;
+ else if (!strcmp(cur, "offload"))
+ *mc_flags |= IAVF_MBUF_CHECK_F_TX_OFFLOAD;
+ else
+ PMD_DRV_LOG(ERR, "Unsupported mdd check type: %s", cur);
+ cur = strtok_r(NULL, ",", &tmp);
+ }
+
+mdd_end:
+ free(str2);
+ return ret;
+}
+
static int iavf_parse_devargs(struct rte_eth_dev *dev)
{
struct iavf_adapter *ad =
@@ -2340,6 +2400,14 @@ static int iavf_parse_devargs(struct rte_eth_dev *dev)
goto bail;
}
+ ret = rte_kvargs_process(kvlist, IAVF_MBUF_CHECK_ARG,
+ &iavf_parse_mbuf_check, &ad->mc_flags);
+ if (ret)
+ goto bail;
+
+ if (ad->mc_flags)
+ ad->devargs.mbuf_check = 1;
+
ret = rte_kvargs_process(kvlist, IAVF_ENABLE_AUTO_RESET_ARG,
&parse_bool, &ad->devargs.auto_reset);
if (ret)
@@ -3807,6 +3807,97 @@ iavf_xmit_pkts_no_poll(void *tx_queue, struct rte_mbuf **tx_pkts,
tx_pkts, nb_pkts);
}
+/* Tx mbuf check */
+static uint16_t
+iavf_xmit_pkts_check(void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t idx;
+ uint64_t ol_flags;
+ struct rte_mbuf *mb;
+ uint16_t good_pkts = nb_pkts;
+ const char *reason = NULL;
+ bool pkt_error = false;
+ struct iavf_tx_queue *txq = tx_queue;
+ struct iavf_adapter *adapter = txq->vsi->adapter;
+ enum iavf_tx_burst_type tx_burst_type =
+ txq->vsi->adapter->tx_burst_type;
+
+ for (idx = 0; idx < nb_pkts; idx++) {
+ mb = tx_pkts[idx];
+ ol_flags = mb->ol_flags;
+
+ if ((adapter->mc_flags & IAVF_MBUF_CHECK_F_TX_MBUF) &&
+ (rte_mbuf_check(mb, 1, &reason) != 0)) {
+ PMD_TX_LOG(ERR, "INVALID mbuf: %s\n", reason);
+ pkt_error = true;
+ break;
+ }
+
+ if ((adapter->mc_flags & IAVF_MBUF_CHECK_F_TX_SIZE) &&
+ (mb->data_len < IAVF_TX_MIN_PKT_LEN ||
+ mb->data_len > adapter->vf.max_pkt_len)) {
+ PMD_TX_LOG(ERR, "INVALID mbuf: data_len (%u) is out "
+ "of range, reasonable range (%d - %u)\n", mb->data_len,
+ IAVF_TX_MIN_PKT_LEN, adapter->vf.max_pkt_len);
+ pkt_error = true;
+ break;
+ }
+
+ if (adapter->mc_flags & IAVF_MBUF_CHECK_F_TX_SEGMENT) {
+ /* Check condition for nb_segs > IAVF_TX_MAX_MTU_SEG. */
+ if (!(ol_flags & (RTE_MBUF_F_TX_TCP_SEG | RTE_MBUF_F_TX_UDP_SEG))) {
+ if (mb->nb_segs > IAVF_TX_MAX_MTU_SEG) {
+ PMD_TX_LOG(ERR, "INVALID mbuf: nb_segs (%d) exceeds "
+ "HW limit, maximum allowed value is %d\n", mb->nb_segs,
+ IAVF_TX_MAX_MTU_SEG);
+ pkt_error = true;
+ break;
+ }
+ } else if ((mb->tso_segsz < IAVF_MIN_TSO_MSS) ||
+ (mb->tso_segsz > IAVF_MAX_TSO_MSS)) {
+ /* MSS outside the range are considered malicious */
+ PMD_TX_LOG(ERR, "INVALID mbuf: tso_segsz (%u) is out "
+ "of range, reasonable range (%d - %u)\n", mb->tso_segsz,
+ IAVF_MIN_TSO_MSS, IAVF_MAX_TSO_MSS);
+ pkt_error = true;
+ break;
+ } else if (mb->nb_segs > txq->nb_tx_desc) {
+ PMD_TX_LOG(ERR, "INVALID mbuf: nb_segs out "
+ "of ring length\n");
+ pkt_error = true;
+ break;
+ }
+ }
+
+ if (adapter->mc_flags & IAVF_MBUF_CHECK_F_TX_OFFLOAD) {
+ if (ol_flags & IAVF_TX_OFFLOAD_NOTSUP_MASK) {
+ PMD_TX_LOG(ERR, "INVALID mbuf: TX offload "
+ "is not supported\n");
+ pkt_error = true;
+ break;
+ }
+
+ if (!rte_validate_tx_offload(mb)) {
+ PMD_TX_LOG(ERR, "INVALID mbuf: TX offload "
+ "setup error\n");
+ pkt_error = true;
+ break;
+ }
+ }
+ }
+
+ if (pkt_error) {
+ __atomic_fetch_add(&txq->mbuf_errors, 1, __ATOMIC_RELAXED);
+ good_pkts = idx;
+ if (good_pkts == 0)
+ return 0;
+ }
+
+ return iavf_tx_pkt_burst_ops[tx_burst_type].tx_pkt_burst(tx_queue,
+ tx_pkts, good_pkts);
+}
+
/* choose rx function*/
void
iavf_set_rx_function(struct rte_eth_dev *dev)
@@ -4098,6 +4189,7 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
struct iavf_adapter *adapter =
IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
enum iavf_tx_burst_type tx_burst_type;
+ int mbuf_check = adapter->devargs.mbuf_check;
int no_poll_on_link_down = adapter->devargs.no_poll_on_link_down;
#ifdef RTE_ARCH_X86
struct iavf_tx_queue *txq;
@@ -4194,6 +4286,9 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
if (no_poll_on_link_down) {
adapter->tx_burst_type = tx_burst_type;
dev->tx_pkt_burst = iavf_xmit_pkts_no_poll;
+ } else if (mbuf_check) {
+ adapter->tx_burst_type = tx_burst_type;
+ dev->tx_pkt_burst = iavf_xmit_pkts_check;
}
return;
}
@@ -4209,6 +4304,9 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
if (no_poll_on_link_down) {
adapter->tx_burst_type = tx_burst_type;
dev->tx_pkt_burst = iavf_xmit_pkts_no_poll;
+ } else if (mbuf_check) {
+ adapter->tx_burst_type = tx_burst_type;
+ dev->tx_pkt_burst = iavf_xmit_pkts_check;
}
}
@@ -305,6 +305,8 @@ struct iavf_tx_queue {
uint16_t next_rs; /* next to check DD, for VPMD */
uint16_t ipsec_crypto_pkt_md_offset;
+ uint64_t mbuf_errors;
+
bool q_set; /* if rx queue has been configured */
bool tx_deferred_start; /* don't start this queue in dev start */
const struct iavf_txq_ops *ops;