Merge ~paelzer/ubuntu/+source/dpdk:merge-17.11.10-BIONIC into ubuntu/+source/dpdk:ubuntu/bionic-devel

[Christian Ehrhardt ]

[Christian Ehrhardt  (paelzer)]

Intentionally not taking any of the latter packaging changes as they might change the SRU too much.
Instead these are clean cherry-picks from the upstream branches.
At https://salsa.debian.org/debian/dpdk/-/tree/upstream-17.11-stable there are gbp import based commits to pick for that which I did.

If you look at just the diff you'll see a lot due to the upstream changes, but commit by commit they should be easy to review.

A few changes were droppable due to upstream integrating them.

PPA: https://launchpad.net/~ci-train-ppa-service/+archive/ubuntu/4131/+packages

[Christian Ehrhardt  (paelzer)]

Interesting arm64 build error:

 /<<PKGBUILDDIR>>/debian/build/static-root/lib/librte_pmd_mlx5.a(mlx5_rxtx_vec.o): In function `rxq_burst_v':
 /<<PKGBUILDDIR>>/drivers/net/mlx5/mlx5_rxtx_vec_neon.h:1035: undefined reference to `rte_cio_wmb'

Due to
https://git.dpdk.org/dpdk-stable/commit/?id=4cd784b02d29f706ff2297b6f65eeb680c0af9ff

[Christian Ehrhardt  (paelzer)]

https://git.dpdk.org/dpdk/commit/?id=52bd60a5 missing on 17.11.x is the issue

I've let upstream know and added it to our build.
New upload in the PPA.
Changes pushed to this branch.

[Rafael David Tinoco (rafaeldtinoco)]

Ill review this one...

[Rafael David Tinoco (rafaeldtinoco)]

Debian (origin/upstream-17.11-stable)

5168a4ac New upstream version 17.11.10
25bc9f91 New upstream version 17.11.9

$ git log -p 25bc9f91..5168a4ac | diffstat -s
 147 files changed, 1709 insertions(+), 788 deletions(-)

Ubuntu (merge-17.11.10-BIONIC)

11e2c6d6c changelog 17.11.10-0ubuntu0.1 for bionic
453349ac6 d/p/eal-arm64-define-coherent-I-O-memory-barriers.patch
2d81cb9aa drop d/p/fix_kernel_53_build.patch being in 17.11.10
3a2dd7836 New upstream version 17.11.10
e1b4486d3 17.11.9-0ubuntu18.04.2 (patches unapplied)

$ git log -p e1b4486d3..3a2dd7836 | diffstat -s
 147 files changed, 1709 insertions(+), 788 deletions(-)

Pretty much the same.. analysing the delta now...

[Rafael David Tinoco (rafaeldtinoco)]

For commit:

commit 2d81cb9aa
Author: Christian Ehrhardt <email address hidden>
Date: Thu Jul 2 07:16:16 2020

    drop d/p/fix_kernel_53_build.patch being in 17.11.10

    Signed-off-by: Christian Ehrhardt <email address hidden>

Reversion is good:

$ patch -p1 -R < debian/patches/fix_kernel_53_build.patch
patching file lib/librte_eal/linuxapp/kni/kni_net.c

[Rafael David Tinoco (rafaeldtinoco)]

For commit:

commit 453349ac6
Author: Christian Ehrhardt <email address hidden>
Date: Thu Jul 2 12:19:56 2020

    d/p/eal-arm64-define-coherent-I-O-memory-barriers.patch: fix FTBFS on arm64

    Signed-off-by: Christian Ehrhardt <email address hidden>

solves:

...mlx5/mlx5_rxtx_vec_neon.h:1035: undefined reference to `rte_cio_wmb'

for build issue.

[Rafael David Tinoco (rafaeldtinoco)]

# CHECKLIST
----------------------------
 [.] changelog entry correct:
 [.] targeted to correct codename
 [.] version number is correct
 [.] update-maintainer has been run before
 ----
 [-] changes forwarded upstream/debian (if appropriate)
 [.] patches match what was proposed upstream
 ----
 [.] patches correctly included in debian/patches/series?
 [.] patches have correct DEP3 metadata
 ----
 [.] relying on PPA only for build check ?
 [-] if relying on PPA, did it install correctly ?
     - I'll rely on your functional tests, doing logical
       review only. Let me know if you need more, pls.
 ----
 [-] if building locally, was source build good ?
 [-] if building locally, was binary build good ?
 ----
 [-] was autopkgtest tested ?
 ----
 [.] is this a SRU ?
 [.] if a SRU, does the public bug have a template ?
 [.] is this a bundle of fixes ?
 ----
 [.] is this a MERGE ?
 [.] if MERGE, is there a public bug referred ?
 [.] if MERGE, does it add/remove existing packages ?
 [-] if MERGE, does it bump library SONAME ?
----------------------------
 [.] = ok | [x] = not ok | [?] = question | [!] = note | [-] = n/a
----------------------------

# comments:

 dpdk | 2.2.0-0ubuntu7 | xenial | source
 dpdk | 2.2.0-0ubuntu8 | xenial-updates | source
 dpdk | 17.11.1-6 | bionic | source
 dpdk | 17.11.9-0ubuntu18.04.2 | bionic-security | source
 dpdk | 17.11.9-0ubuntu18.04.2 | bionic-updates | source
 dpdk | 18.11.2-4 | eoan | source
 dpdk | 18.11.5-0ubuntu0.19.10.2 | eoan-security | source
 dpdk | 18.11.5-0ubuntu0.19.10.2 | eoan-updates | source
 dpdk | 19.11.1-0ubuntu1 | focal | source
 dpdk | 19.11.1-0ubuntu1.1 | focal-security | source
 dpdk | 19.11.1-0ubuntu1.1 | focal-updates | source
 dpdk | 19.11.3-1 | groovy | source

All good, +1.

review: Approve

[Christian Ehrhardt  (paelzer)]

To ssh://git.launchpad.net/~usd-import-team/ubuntu/+source/dpdk
 * [new tag] upload/17.11.10-0ubuntu0.1 -> upload/17.11.10-0ubuntu0.1

Uploading to ubuntu (via ftp to upload.ubuntu.com):
  Uploading dpdk_17.11.10-0ubuntu0.1.dsc: done.
  Uploading dpdk_17.11.10.orig.tar.xz: done.
  Uploading dpdk_17.11.10-0ubuntu0.1.debian.tar.xz: done.
  Uploading dpdk_17.11.10-0ubuntu0.1_source.buildinfo: done.
  Uploading dpdk_17.11.10-0ubuntu0.1_source.changes: done.
Successfully uploaded packages.

diff --git a/MAINTAINERS b/MAINTAINERS
index 1837bb5..4c9dd84 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -28,7 +28,8 @@ M: Ferruh Yigit <[e-mail]>
 T: git://dpdk.org/dpdk
 
 Stable Branches
-M: Yuanhan Liu <[e-mail]>
+M: Luca Boccassi <[e-mail]>
+M: Kevin Traynor <[e-mail]>
 T: git://dpdk.org/dpdk-stable
 
 Security Issues
diff --git a/app/proc_info/main.c b/app/proc_info/main.c
index 2893bec..caf4e48 100644
--- a/app/proc_info/main.c
+++ b/app/proc_info/main.c
@@ -196,7 +196,7 @@ proc_info_preparse_args(int argc, char **argv)
 		int err = gethostname(host_id, MAX_LONG_OPT_SZ-1);
 
 		if (err)
-			strcpy(host_id, "unknown");
+			strlcpy(host_id, "unknown", sizeof(host_id));
 	}
 
 	return 0;
@@ -363,50 +363,50 @@ static void collectd_resolve_cnt_type(char *cnt_type, size_t cnt_type_len,
 	if ((type_end != NULL) &&
 	    (strncmp(cnt_name, "rx_", strlen("rx_")) == 0)) {
 		if (strncmp(type_end, "_errors", strlen("_errors")) == 0)
-			strncpy(cnt_type, "if_rx_errors", cnt_type_len);
+			strlcpy(cnt_type, "if_rx_errors", cnt_type_len);
 		else if (strncmp(type_end, "_dropped", strlen("_dropped")) == 0)
-			strncpy(cnt_type, "if_rx_dropped", cnt_type_len);
+			strlcpy(cnt_type, "if_rx_dropped", cnt_type_len);
 		else if (strncmp(type_end, "_bytes", strlen("_bytes")) == 0)
-			strncpy(cnt_type, "if_rx_octets", cnt_type_len);
+			strlcpy(cnt_type, "if_rx_octets", cnt_type_len);
 		else if (strncmp(type_end, "_packets", strlen("_packets")) == 0)
-			strncpy(cnt_type, "if_rx_packets", cnt_type_len);
+			strlcpy(cnt_type, "if_rx_packets", cnt_type_len);
 		else if (strncmp(type_end, "_placement",
 				 strlen("_placement")) == 0)
-			strncpy(cnt_type, "if_rx_errors", cnt_type_len);
+			strlcpy(cnt_type, "if_rx_errors", cnt_type_len);
 		else if (strncmp(type_end, "_buff", strlen("_buff")) == 0)
-			strncpy(cnt_type, "if_rx_errors", cnt_type_len);
+			strlcpy(cnt_type, "if_rx_errors", cnt_type_len);
 		else
 			/* Does not fit obvious type: use a more generic one */
-			strncpy(cnt_type, "derive", cnt_type_len);
+			strlcpy(cnt_type, "derive", cnt_type_len);
 	} else if ((type_end != NULL) &&
 		(strncmp(cnt_name, "tx_", strlen("tx_"))) == 0) {
 		if (strncmp(type_end, "_errors", strlen("_errors")) == 0)
-			strncpy(cnt_type, "if_tx_errors", cnt_type_len);
+			strlcpy(cnt_type, "if_tx_errors", cnt_type_len);
 		else if (strncmp(type_end, "_dropped", strlen("_dropped")) == 0)
-			strncpy(cnt_type, "if_tx_dropped", cnt_type_len);
+			strlcpy(cnt_type, "if_tx_dropped", cnt_type_len);
 		else if (strncmp(type_end, "_bytes", strlen("_bytes")) == 0)
-			strncpy(cnt_type, "if_tx_octets", cnt_type_len);
+			strlcpy(cnt_type, "if_tx_octets", cnt_type_len);
 		else if (strncmp(type_end, "_packets", strlen("_packets")) == 0)
-			strncpy(cnt_type, "if_tx_packets", cnt_type_len);
+			strlcpy(cnt_type, "if_tx_packets", cnt_type_len);
 		else
 			/* Does not fit obvious type: use a more generic one */
-			strncpy(cnt_type, "derive", cnt_type_len);
+			strlcpy(cnt_type, "derive", cnt_type_len);
 	} else if ((type_end != NULL) &&
 		   (strncmp(cnt_name, "flow_", strlen("flow_"))) == 0) {
 		if (strncmp(type_end, "_filters", strlen("_filters")) == 0)
-			strncpy(cnt_type, "operations", cnt_type_len);
+			strlcpy(cnt_type, "operations", cnt_type_len);
 		else if (strncmp(type_end, "_errors", strlen("_errors")) == 0)
-			strncpy(cnt_type, "errors", cnt_type_len);
+			strlcpy(cnt_type, "errors", cnt_type_len);
 		else if (strncmp(type_end, "_filters", strlen("_filters")) == 0)
-			strncpy(cnt_type, "filter_result", cnt_type_len);
+			strlcpy(cnt_type, "filter_result", cnt_type_len);
 	} else if ((type_end != NULL) &&
 		   (strncmp(cnt_name, "mac_", strlen("mac_"))) == 0) {
 		if (strncmp(type_end, "_errors", strlen("_errors")) == 0)
-			strncpy(cnt_type, "errors", cnt_type_len);
+			strlcpy(cnt_type, "errors", cnt_type_len);
 	} else {
 		/* Does not fit obvious type, or strrchr error: */
 		/* use a more generic type */
-		strncpy(cnt_type, "derive", cnt_type_len);
+		strlcpy(cnt_type, "derive", cnt_type_len);
 	}
 }
 
diff --git a/app/test-crypto-perf/cperf_test_verify.c b/app/test-crypto-perf/cperf_test_verify.c
index 6945c8b..2935642 100644
--- a/app/test-crypto-perf/cperf_test_verify.c
+++ b/app/test-crypto-perf/cperf_test_verify.c
@@ -230,11 +230,19 @@ cperf_mbuf_set(struct rte_mbuf *mbuf,
 {
 	uint32_t segment_sz = options->segment_sz;
 	uint8_t *mbuf_data;
-	uint8_t *test_data =
-			(options->cipher_op == RTE_CRYPTO_CIPHER_OP_ENCRYPT) ?
+	uint8_t *test_data;
+	uint32_t remaining_bytes = options->max_buffer_size;
+
+	if (options->op_type == CPERF_AEAD) {
+		test_data = (options->aead_op == RTE_CRYPTO_AEAD_OP_ENCRYPT) ?
 					test_vector->plaintext.data :
 					test_vector->ciphertext.data;
-	uint32_t remaining_bytes = options->max_buffer_size;
+	} else {
+		test_data =
+			(options->cipher_op == RTE_CRYPTO_CIPHER_OP_ENCRYPT) ?
+				test_vector->plaintext.data :
+				test_vector->ciphertext.data;
+	}
 
 	while (remaining_bytes) {
 		mbuf_data = rte_pktmbuf_mtod(mbuf, uint8_t *);
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
index 7a3a818..2365249 100644
--- a/app/test-pmd/cmdline.c
+++ b/app/test-pmd/cmdline.c
@@ -799,6 +799,9 @@ static void cmd_help_long_parsed(void *parsed_result,
 			"port close (port_id|all)\n"
 			"    Close all ports or port_id.\n\n"
 
+			"port reset (port_id|all)\n"
+			"    Reset all ports or port_id.\n\n"
+
 			"port attach (ident)\n"
 			"    Attach physical or virtual dev by pci address or virtual device name\n\n"
 
@@ -1974,7 +1977,6 @@ cmd_config_rss_hash_key_parsed(void *parsed_result,
 	uint8_t hash_key_size;
 	uint32_t key_len;
 
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(res->port_id, &dev_info);
 	if (dev_info.hash_key_size > 0 &&
 			dev_info.hash_key_size <= sizeof(hash_key))
@@ -2214,7 +2216,6 @@ cmd_set_rss_reta_parsed(void *parsed_result,
 	struct rte_eth_rss_reta_entry64 reta_conf[8];
 	struct cmd_config_rss_reta *res = parsed_result;
 
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(res->port_id, &dev_info);
 	if (dev_info.reta_size == 0) {
 		printf("Redirection table size is 0 which is "
@@ -2334,7 +2335,6 @@ cmd_showport_reta_parsed(void *parsed_result,
 	struct rte_eth_dev_info dev_info;
 	uint16_t max_reta_size;
 
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(res->port_id, &dev_info);
 	max_reta_size = RTE_MIN(dev_info.reta_size, ETH_RSS_RETA_SIZE_512);
 	if (res->size == 0 || res->size > max_reta_size) {
@@ -10046,7 +10046,6 @@ cmd_flow_director_filter_parsed(void *parsed_result,
 		else if (!strncmp(res->pf_vf, "vf", 2)) {
 			struct rte_eth_dev_info dev_info;
 
-			memset(&dev_info, 0, sizeof(dev_info));
 			rte_eth_dev_info_get(res->port_id, &dev_info);
 			errno = 0;
 			vf_id = strtoul(res->pf_vf + 2, &end, 10);
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index 61608d1..4e3531b 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -242,6 +242,10 @@ nic_xstats_display(portid_t port_id)
 	int cnt_xstats, idx_xstat;
 	struct rte_eth_xstat_name *xstats_names;
 
+	if (port_id_is_invalid(port_id, ENABLED_WARN)) {
+		print_valid_ports();
+		return;
+	}
 	printf("###### NIC extended statistics for port %-2d\n", port_id);
 	if (!rte_eth_dev_is_valid_port(port_id)) {
 		printf("Error: Invalid port number %i\n", port_id);
@@ -297,6 +301,10 @@ nic_xstats_display(portid_t port_id)
 void
 nic_xstats_clear(portid_t port_id)
 {
+	if (port_id_is_invalid(port_id, ENABLED_WARN)) {
+		print_valid_ports();
+		return;
+	}
 	rte_eth_xstats_reset(port_id);
 }
 
@@ -429,7 +437,6 @@ port_infos_display(portid_t port_id)
 	}
 	port = &ports[port_id];
 	rte_eth_link_get_nowait(port_id, &link);
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(port_id, &dev_info);
 	printf("\n%s Infos for port %-2d %s\n",
 	       info_border, port_id, info_border);
@@ -1558,7 +1565,6 @@ ring_rx_descriptor_display(const struct rte_memzone *ring_mz,
 #ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
 	struct rte_eth_dev_info dev_info;
 
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(port_id, &dev_info);
 	if (strstr(dev_info.driver_name, "i40e") != NULL) {
 		/* 32 bytes RX descriptor, i40e only */
diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
index ae59e76..70f3b39 100644
--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c
@@ -432,6 +432,9 @@ process_outer_cksums(void *outer_l3_hdr, struct testpmd_offload_info *info,
 
 	udp_hdr = (struct udp_hdr *)((char *)outer_l3_hdr + info->outer_l3_len);
 
+	if (tso_enabled)
+		ol_flags |= PKT_TX_TCP_SEG;
+
 	/* outer UDP checksum is done in software as we have no hardware
 	 * supporting it today, and no API for it. In the other side, for
 	 * UDP tunneling, like VXLAN or Geneve, outer UDP checksum can be
diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index 1dfbcc4..8fcd72d 100644
--- a/app/test-pmd/parameters.c
+++ b/app/test-pmd/parameters.c
@@ -168,8 +168,8 @@ usage(char* progname)
 	printf("  --disable-hw-vlan-extend: disable hardware vlan extend.\n");
 	printf("  --enable-drop-en: enable per queue packet drop.\n");
 	printf("  --disable-rss: disable rss.\n");
-	printf("  --port-topology=N: set port topology (N: paired (default) or "
-	       "chained).\n");
+	printf("  --port-topology=<paired|chained|loop>: set port topology (paired "
+	       "is default).\n");
 	printf("  --forward-mode=N: set forwarding mode (N: %s).\n",
 	       list_pkt_forwarding_modes());
 	printf("  --rss-ip: set RSS functions to IPv4/IPv6 only .\n");
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index f8c76a6..c2d6a75 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -1860,6 +1860,13 @@ reset_port(portid_t pid)
 	if (port_id_is_invalid(pid, ENABLED_WARN))
 		return;
 
+	port = &ports[pid];
+	if ((pid == (portid_t)RTE_PORT_ALL && !all_ports_stopped()) ||
+		(pid != (portid_t)RTE_PORT_ALL && !((port->port_status != RTE_PORT_STOPPED) && (port->slave_flag == 0)))) {
+		printf("Can not reset port(s), please stop port(s) first.\n");
+		return;
+	}
+
 	printf("Resetting ports...\n");
 
 	RTE_ETH_FOREACH_DEV(pi) {
diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
index 4ce4d61..c9e6db9 100644
--- a/app/test-pmd/txonly.c
+++ b/app/test-pmd/txonly.c
@@ -234,7 +234,7 @@ pkt_burst_transmit(struct fwd_stream *fs)
 		pkt->data_len = tx_pkt_seg_lengths[0];
 		pkt_seg = pkt;
 		if (tx_pkt_split == TX_PKT_SPLIT_RND)
-			nb_segs = random() % tx_pkt_nb_segs + 1;
+			nb_segs = rte_rand() % tx_pkt_nb_segs + 1;
 		else
 			nb_segs = tx_pkt_nb_segs;
 		pkt_len = pkt->data_len;
diff --git a/config/common_base b/config/common_base
index 7b47922..4355cad 100644
--- a/config/common_base
+++ b/config/common_base
@@ -99,7 +99,6 @@ CONFIG_RTE_LOG_DP_LEVEL=RTE_LOG_INFO
 CONFIG_RTE_LOG_HISTORY=256
 CONFIG_RTE_BACKTRACE=y
 CONFIG_RTE_LIBEAL_USE_HPET=n
-CONFIG_RTE_EAL_ALLOW_INV_SOCKET_ID=n
 CONFIG_RTE_EAL_ALWAYS_PANIC_ON_ERROR=n
 CONFIG_RTE_EAL_IGB_UIO=n
 CONFIG_RTE_EAL_VFIO=n
diff --git a/debian/changelog b/debian/changelog
index d1e3458..0b80de6 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,3 +1,21 @@
+dpdk (17.11.10-0ubuntu0.1) bionic; urgency=medium
+
+  * Merge latest stable DPDK release 17.11.10; for a full list of changes see:
+    https://doc.dpdk.org/guides-17.11/rel_notes/release_17_11.html#id13
+    After 17.11.8 being a security release and 17.11.9 a regression fix
+    for 17.11.8 this is the fiirst "real" stable release in a while.
+    (LP: #1885915)
+  * Remaining changes:
+    - SECURITY UPDATE: Integer overflow in vhost_user_set_log_base()
+    - SECURITY UPDATE: Int truncation in vhost_user_check_and_alloc_queue_pair()
+  * Dropped changes:
+    - d/p/fix_kernel_53_build.patch is part of 17.11.10
+  * Added changes
+    - d/p/eal-arm64-define-coherent-I-O-memory-barriers.patch: fix FTBFS of
+      17.11.10 on arm64
+
+ -- Christian Ehrhardt <[e-mail]>  Thu, 02 Jul 2020 09:16:48 +0200
+
 dpdk (17.11.9-0ubuntu18.04.2) bionic-security; urgency=medium
 
   * SECURITY UPDATE: Integer overflow in vhost_user_set_log_base()
diff --git a/debian/patches/eal-arm64-define-coherent-I-O-memory-barriers.patch b/debian/patches/eal-arm64-define-coherent-I-O-memory-barriers.patch
new file mode 100644
index 0000000..de5da03
--- /dev/null
+++ b/debian/patches/eal-arm64-define-coherent-I-O-memory-barriers.patch
@@ -0,0 +1,34 @@
+From 52bd60a5cf0b05793f66cd507df0388402499f2a Mon Sep 17 00:00:00 2001
+From: Yongseok Koh <[e-mail]>
+Date: Thu, 25 Jan 2018 13:02:47 -0800
+Subject: [PATCH] eal/arm64: define coherent I/O memory barriers
+
+Signed-off-by: Yongseok Koh <[e-mail]>
+Acked-by: Thomas Speier <[e-mail]>
+Acked-by: Jianbo Liu <[e-mail]>
+
+Origin: upstream, https://git.dpdk.org/dpdk/commit/?id=52bd60a5
+Last-Update: 2020-07-02
+
+---
+ lib/librte_eal/common/include/arch/arm/rte_atomic_64.h | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h b/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h
+index b6bbd0b32..ee0d0d15a 100644
+--- a/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h
++++ b/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h
+@@ -36,6 +36,10 @@ extern "C" {
+ 
+ #define rte_io_rmb() rte_rmb()
+ 
++#define rte_cio_wmb() dmb(oshst)
++
++#define rte_cio_rmb() dmb(oshld)
++
+ #ifdef __cplusplus
+ }
+ #endif
+-- 
+2.27.0
+
diff --git a/debian/patches/fix_kernel_53_build.patch b/debian/patches/fix_kernel_53_build.patch
deleted file mode 100644
index 3bc3846..0000000
--- a/debian/patches/fix_kernel_53_build.patch
+++ /dev/null
@@ -1,32 +0,0 @@
-From 61cba437cf3ec7dc186cb3dad27ae9829787d8c6 Mon Sep 17 00:00:00 2001
-From: Christian Ehrhardt <[e-mail]>
-Date: Thu, 24 Oct 2019 08:34:35 +0200
-Subject: [PATCH] kni: fix build with kernel 5.3
-
-The include of kni_fifo should be local as kni provides it.
-With newer kernels build systems this will run into an issue on
-external module compilation.
-
-/var/lib/dkms/dpdk-rte-kni/17.11.6/build/kni_net.c:40:10:
-fatal error: kni_fifo.h: No such file or directory
- #include <kni_fifo.h>
-          ^~~~~~~~~~~~
-
-Like the includes to kni_dev.h this should be local as well.
-
-Signed-off-by: Christian Ehrhardt <[e-mail]>
----
- lib/librte_eal/linuxapp/kni/kni_net.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
---- a/lib/librte_eal/linuxapp/kni/kni_net.c
-+++ b/lib/librte_eal/linuxapp/kni/kni_net.c
-@@ -37,7 +37,7 @@
- #include <linux/delay.h>
- 
- #include <exec-env/rte_kni_common.h>
--#include <kni_fifo.h>
-+#include "kni_fifo.h"
- 
- #include "compat.h"
- #include "kni_dev.h"
diff --git a/debian/patches/series b/debian/patches/series
index 28ba70a..c0215af 100644
--- a/debian/patches/series
+++ b/debian/patches/series
@@ -1,6 +1,6 @@
 fix-vhost-user-socket-permission.patch
 testpmd-link-virtio.patch
 app-testpmd-add-ethernet-peer-command.patch
-fix_kernel_53_build.patch
 0001-vhost-check-log-mmap-offset-and-size-overflow.patch
 0002-vhost-fix-vring-index-check.patch
+eal-arm64-define-coherent-I-O-memory-barriers.patch
diff --git a/doc/guides/conf.py b/doc/guides/conf.py
index 084512d..ed9bb5b 100644
--- a/doc/guides/conf.py
+++ b/doc/guides/conf.py
@@ -94,6 +94,9 @@ custom_latex_preamble = r"""
 \usepackage{helvet}
 \renewcommand{\familydefault}{\sfdefault}
 \RecustomVerbatimEnvironment{Verbatim}{Verbatim}{xleftmargin=5mm}
+\usepackage{etoolbox}
+\robustify\(
+\robustify\)
 """
 
 # Configuration for the latex/pdf docs.
diff --git a/doc/guides/contributing/coding_style.rst b/doc/guides/contributing/coding_style.rst
index d8e4a0f..38acd5a 100644
--- a/doc/guides/contributing/coding_style.rst
+++ b/doc/guides/contributing/coding_style.rst
@@ -619,10 +619,10 @@ In the DPDK environment, use the logging interface provided:
 
  /* log in debug level */
  rte_log_set_global_level(RTE_LOG_DEBUG);
- RTE_LOG(DEBUG, my_logtype1, "this is is a debug level message\n");
- RTE_LOG(INFO, my_logtype1, "this is is a info level message\n");
- RTE_LOG(WARNING, my_logtype1, "this is is a warning level message\n");
- RTE_LOG(WARNING, my_logtype2, "this is is a debug level message (not displayed)\n");
+ RTE_LOG(DEBUG, my_logtype1, "this is a debug level message\n");
+ RTE_LOG(INFO, my_logtype1, "this is a info level message\n");
+ RTE_LOG(WARNING, my_logtype1, "this is a warning level message\n");
+ RTE_LOG(WARNING, my_logtype2, "this is a debug level message (not displayed)\n");
 
  /* log in info level */
  rte_log_set_global_level(RTE_LOG_INFO);
diff --git a/doc/guides/contributing/versioning.rst b/doc/guides/contributing/versioning.rst
index 4000906..fe15e9a 100644
--- a/doc/guides/contributing/versioning.rst
+++ b/doc/guides/contributing/versioning.rst
@@ -149,11 +149,11 @@ library so that older binaries need not be immediately recompiled.
 The macros exported are:
 
 * ``VERSION_SYMBOL(b, e, n)``: Creates a symbol version table entry binding
-  versioned symbol ``b@DPDK_n`` to the internal function ``b_e``.
+  versioned symbol ``b@DPDK_n`` to the internal function ``be``.
 
 * ``BIND_DEFAULT_SYMBOL(b, e, n)``: Creates a symbol version entry instructing
   the linker to bind references to symbol ``b`` to the internal symbol
-  ``b_e``.
+  ``be``.
 
 * ``MAP_STATIC_SYMBOL(f, p)``: Declare the prototype ``f``, and map it to the
   fully qualified function ``p``, so that if a symbol becomes versioned, it
diff --git a/doc/guides/cryptodevs/aesni_gcm.rst b/doc/guides/cryptodevs/aesni_gcm.rst
index a1f5848..9a03dec 100644
--- a/doc/guides/cryptodevs/aesni_gcm.rst
+++ b/doc/guides/cryptodevs/aesni_gcm.rst
@@ -48,11 +48,12 @@ AEAD algorithms:
 
 * RTE_CRYPTO_AEAD_AES_GCM
 
-
 Limitations
 -----------
 
 * Chained mbufs are supported but only out-of-place (destination mbuf must be contiguous).
+* Chained mbufs are only supported by RTE_CRYPTO_AEAD_AES_GCM algorithm,
+  not RTE_CRYPTO_AUTH_AES_GMAC.
 * Cipher only is not supported.
 
 
diff --git a/doc/guides/cryptodevs/zuc.rst b/doc/guides/cryptodevs/zuc.rst
index 7fcfc07..bf33479 100644
--- a/doc/guides/cryptodevs/zuc.rst
+++ b/doc/guides/cryptodevs/zuc.rst
@@ -54,7 +54,7 @@ Limitations
 * ZUC (EIA3) supported only if hash offset field is byte-aligned.
 * ZUC (EEA3) supported only if cipher length, cipher offset fields are byte-aligned.
 * ZUC PMD cannot be built as a shared library, due to limitations in
-  in the underlying library.
+  the underlying library.
 
 
 Installation
diff --git a/doc/guides/linux_gsg/nic_perf_intel_platform.rst b/doc/guides/linux_gsg/nic_perf_intel_platform.rst
index 2ef6ed7..dd0c622 100644
--- a/doc/guides/linux_gsg/nic_perf_intel_platform.rst
+++ b/doc/guides/linux_gsg/nic_perf_intel_platform.rst
@@ -152,7 +152,7 @@ Configurations before running DPDK
       # Mount to the specific folder.
       mount -t hugetlbfs nodev /mnt/huge
 
-2. Check the CPU layout using using the DPDK ``cpu_layout`` utility:
+2. Check the CPU layout using the DPDK ``cpu_layout`` utility:
 
    .. code-block:: console
 
diff --git a/doc/guides/nics/fm10k.rst b/doc/guides/nics/fm10k.rst
index b47fc0d..c23f411 100644
--- a/doc/guides/nics/fm10k.rst
+++ b/doc/guides/nics/fm10k.rst
@@ -156,7 +156,7 @@ Switch manager
 
 The Intel FM10000 family of NICs integrate a hardware switch and multiple host
 interfaces. The FM10000 PMD driver only manages host interfaces. For the
-switch component another switch driver has to be loaded prior to to the
+switch component another switch driver has to be loaded prior to the
 FM10000 PMD driver. The switch driver can be acquired from Intel support.
 Only Testpoint is validated with DPDK, the latest version that has been
 validated with DPDK is 4.1.6.
@@ -172,8 +172,8 @@ the Rx/Tx queues. When switch comes up, a LSC event indicating ``LINK_UP`` is
 sent to the app, which can then restart the FM10000 port to resume network
 processing.
 
-CRC striping
-~~~~~~~~~~~~
+CRC stripping
+~~~~~~~~~~~~~
 
 The FM10000 family of NICs strip the CRC for every packets coming into the
 host interface.  So, CRC will be stripped even when the
diff --git a/doc/guides/nics/liquidio.rst b/doc/guides/nics/liquidio.rst
index 7bc1604..fffa7b5 100644
--- a/doc/guides/nics/liquidio.rst
+++ b/doc/guides/nics/liquidio.rst
@@ -225,8 +225,8 @@ Ring size
 
 Number of descriptors for Rx/Tx ring should be in the range 128 to 512.
 
-CRC striping
-~~~~~~~~~~~~
+CRC stripping
+~~~~~~~~~~~~~
 
 LiquidIO adapters strip ethernet FCS of every packet coming to the host
 interface. So, CRC will be stripped even when the ``rxmode.hw_strip_crc``
diff --git a/doc/guides/nics/octeontx.rst b/doc/guides/nics/octeontx.rst
index 90bb9e5..8da0867 100644
--- a/doc/guides/nics/octeontx.rst
+++ b/doc/guides/nics/octeontx.rst
@@ -209,8 +209,8 @@ This driver will only work with ``octeontx_fpavf`` external mempool handler
 as it is the most performance effective way for packet allocation and Tx buffer
 recycling on OCTEONTX SoC platform.
 
-CRC striping
-~~~~~~~~~~~~
+CRC stripping
+~~~~~~~~~~~~~
 
 The OCTEONTX SoC family NICs strip the CRC for every packets coming into the
 host interface. So, CRC will be stripped even when the
diff --git a/doc/guides/nics/tap.rst b/doc/guides/nics/tap.rst
index 04086b1..a85921a 100644
--- a/doc/guides/nics/tap.rst
+++ b/doc/guides/nics/tap.rst
@@ -102,7 +102,7 @@ Please change the IP addresses as you see fit.
 
 If routing is enabled on the host you can also communicate with the DPDK App
 over the internet via a standard socket layer application as long as you
-account for the protocol handing in the application.
+account for the protocol handling in the application.
 
 If you have a Network Stack in your DPDK application or something like it you
 can utilize that stack to handle the network protocols. Plus you would be able
@@ -146,9 +146,9 @@ As rules are translated to TC, it is possible to show them with something like::
 Examples of testpmd flow rules
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Drop packets for destination IP 192.168.0.1::
+Drop packets for destination IP 192.0.2.1::
 
-   testpmd> flow create 0 priority 1 ingress pattern eth / ipv4 dst is 1.1.1.1 \
+   testpmd> flow create 0 priority 1 ingress pattern eth / ipv4 dst is 192.0.2.1 \
             / end actions drop / end
 
 Ensure packets from a given MAC address are received on a queue 2::
diff --git a/doc/guides/nics/thunderx.rst b/doc/guides/nics/thunderx.rst
index 45bc690..f889684 100644
--- a/doc/guides/nics/thunderx.rst
+++ b/doc/guides/nics/thunderx.rst
@@ -354,8 +354,8 @@ The nicvf thunderx driver will make use of attached secondary VFs automatically 
 Limitations
 -----------
 
-CRC striping
-~~~~~~~~~~~~
+CRC stripping
+~~~~~~~~~~~~~
 
 The ThunderX SoC family NICs strip the CRC for every packets coming into the
 host interface. So, CRC will be stripped even when the
diff --git a/doc/guides/nics/virtio.rst b/doc/guides/nics/virtio.rst
index 9d05cca..6672d7f 100644
--- a/doc/guides/nics/virtio.rst
+++ b/doc/guides/nics/virtio.rst
@@ -34,7 +34,6 @@ Poll Mode Driver for Emulated Virtio NIC
 Virtio is a para-virtualization framework initiated by IBM, and supported by KVM hypervisor.
 In the Data Plane Development Kit (DPDK),
 we provide a virtio Poll Mode Driver (PMD) as a software solution, comparing to SRIOV hardware solution,
-
 for fast guest VM to guest VM communication and guest VM to host communication.
 
 Vhost is a kernel acceleration module for virtio qemu backend.
diff --git a/doc/guides/prog_guide/generic_segmentation_offload_lib.rst b/doc/guides/prog_guide/generic_segmentation_offload_lib.rst
index ef1de53..008b9dd 100644
--- a/doc/guides/prog_guide/generic_segmentation_offload_lib.rst
+++ b/doc/guides/prog_guide/generic_segmentation_offload_lib.rst
@@ -223,7 +223,7 @@ To segment an outgoing packet, an application must:
 2. Set the appropriate ol_flags in the mbuf.
 
    - The GSO library use the value of an mbuf's ``ol_flags`` attribute to
-     to determine how a packet should be segmented. It is the application's
+     determine how a packet should be segmented. It is the application's
      responsibility to ensure that these flags are set.
 
    - For example, in order to segment TCP/IPv4 packets, the application should
diff --git a/doc/guides/prog_guide/packet_classif_access_ctrl.rst b/doc/guides/prog_guide/packet_classif_access_ctrl.rst
index a6bee9b..a5748e2 100644
--- a/doc/guides/prog_guide/packet_classif_access_ctrl.rst
+++ b/doc/guides/prog_guide/packet_classif_access_ctrl.rst
@@ -181,7 +181,7 @@ To define classification for the IPv6 2-tuple: <protocol, IPv6 source address> o
 
 .. code-block:: c
 
-    struct struct ipv6_hdr {
+    struct ipv6_hdr {
         uint32_t vtc_flow;     /* IP version, traffic class & flow label. */
         uint16_t payload_len;  /* IP packet length - includes sizeof(ip_header). */
         uint8_t proto;         /* Protocol, next header. */
@@ -194,7 +194,7 @@ The following array of field definitions can be used:
 
 .. code-block:: c
 
-    struct struct rte_acl_field_def ipv6_2tuple_defs[5] = {
+    struct rte_acl_field_def ipv6_2tuple_defs[5] = {
         {
             .type = RTE_ACL_FIELD_TYPE_BITMASK,
             .size = sizeof (uint8_t),
diff --git a/doc/guides/prog_guide/rte_security.rst b/doc/guides/prog_guide/rte_security.rst
index 71be036..4253ee9 100644
--- a/doc/guides/prog_guide/rte_security.rst
+++ b/doc/guides/prog_guide/rte_security.rst
@@ -76,7 +76,7 @@ however all security protocol related headers are still attached to the
 packet. e.g. In case of IPSec, the IPSec tunnel headers (if any),
 ESP/AH headers will remain in the packet but the received packet
 contains the decrypted data where the encrypted data was when the packet
-arrived. The driver Rx path check the descriptors and and based on the
+arrived. The driver Rx path check the descriptors and based on the
 crypto status sets additional flags in the rte_mbuf.ol_flags field.
 
 .. note::
@@ -90,7 +90,7 @@ Egress Data path - The software prepares the egress packet by adding
 relevant security protocol headers. Only the data will not be
 encrypted by the software. The driver will accordingly configure the
 tx descriptors. The hardware device will encrypt the data before sending the
-the packet out.
+packet out.
 
 .. note::
 
diff --git a/doc/guides/rel_notes/release_17_11.rst b/doc/guides/rel_notes/release_17_11.rst
index bc1d88d..2d8e667 100644
--- a/doc/guides/rel_notes/release_17_11.rst
+++ b/doc/guides/rel_notes/release_17_11.rst
@@ -459,7 +459,7 @@ API Changes
 * **Added mbuf flags PKT_RX_VLAN and PKT_RX_QINQ.**
 
   Two ``mbuf`` flags have been added to indicate that the VLAN
-  identifier has been saved in in the ``mbuf`` structure. For instance:
+  identifier has been saved in the ``mbuf`` structure. For instance:
 
   - If VLAN is not stripped and TCI is saved: ``PKT_RX_VLAN``
   - If VLAN is stripped and TCI is saved: ``PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED``
@@ -2015,3 +2015,247 @@ Fixes skipped and status unresolved
   * http://doc.dpdk.org/dts/test_plans/virtio_pvp_regression_test_plan.html
   * http://doc.dpdk.org/dts/test_plans/vhost_dequeue_zero_copy_test_plan.html
   * http://doc.dpdk.org/dts/test_plans/vm2vm_virtio_pmd_test_plan.html
+
+17.11.10 Release Notes
+----------------------
+
+17.11.10 Fixes
+~~~~~~~~~~~~~~
+
+* app/crypto-perf: fix input of AEAD decrypt
+* app/proc_info: fix string copying to use strlcpy
+* app/testpmd: block xstats for hidden ports
+* app/testpmd: fix crash on port reset
+* app/testpmd: fix help for loop topology option
+* app/testpmd: fix Tx checksum when TSO enabled
+* app/testpmd: use better randomness for Tx split
+* bus/pci: align next mapping address on page boundary
+* bus/pci: fix Intel IOMMU sysfs access check
+* bus/pci: remove useless link dependency on ethdev
+* cryptodev: fix checks related to device id
+* cryptodev: fix initialization on multi-process
+* cryptodev: fix missing device id range checking
+* crypto/dpaa2_sec: fix length retrieved from hardware
+* crypto/openssl: use local copy for session contexts
+* crypto/qat: fix digest length in XCBC capability
+* crypto/qat: fix null auth issues when using vfio_pci
+* doc: fix a common typo in NIC guides
+* doc: fix AESNI-GCM limitations in crypto guide
+* doc: fix description of versioning macros
+* doc: fix format in virtio guide
+* doc: fix tap guide
+* doc: fix typo in l2fwd-crypto guide
+* doc/guides: clean repeated words
+* doc: robustify PDF build
+* drivers/crypto: remove some invalid comments
+* eal: remove dead code on NUMA node detection
+* ethdev: fix endian annotation for SPI item
+* ethdev: fix include of ethernet header file
+* ethdev: fix typos for ENOTSUP
+* ethdev: limit maximum number of queues
+* ethdev: remove redundant device info cleanup before get
+* event/dpaa2: fix default queue configuration
+* event/octeontx: fix partial Rx packet handling
+* event/sw: fix xstats reset value
+* examples/ipsec-secgw: fix default configuration
+* examples/ipsec-secgw: fix GCM IV length
+* examples/ipsec-secgw: fix SHA256-HMAC digest length
+* examples/l3fwd-power: fix Rx interrupt disabling
+* examples/multi_process: fix client crash with sparse ports
+* examples/vm_power: fix build without i40e
+* examples/vm_power: fix type of cmdline token in cli
+* kni: fix build with kernel 5.3
+* lib/distributor: fix deadlock on aarch64
+* lib: fix doxygen typos
+* lib: fix log typos
+* maintainers: update for stable branches
+* malloc: fix realloc copy size
+* malloc: fix realloc padded element size
+* malloc: set pad to 0 on free
+* mempool/dpaa2: report error on endless loop in mbuf release
+* mk: remove library search path from binary
+* net/af_packet: fix stale sockets
+* net/af_packet: improve Tx statistics accuracy
+* net/bnxt: cleanup comments
+* net/bnxt: enforce IO barrier for doorbell command
+* net/bnxt: expose some missing counters in port stats
+* net/bnxt: fix async link handling and update
+* net/bnxt: fix coding style
+* net/bnxt: fix crash in secondary process
+* net/bnxt: fix crash in xstats get
+* net/bnxt: fix dereference before null check
+* net/bnxt: fix log message level
+* net/bnxt: fix mbuf free when clearing Tx queue
+* net/bnxt: fix memory leak
+* net/bnxt: fix multicast filter programming
+* net/bnxt: fix Rx queue count
+* net/bnxt: fix setting default MAC address
+* net/bnxt: get default HWRM command timeout from FW
+* net/bnxt: move macro definitions to header file
+* net/bnxt: remove commented out code
+* net/bnxt: remove duplicate barrier
+* net/bnxt: remove redundant header file inclusion
+* net/bnxt: remove unnecessary variable assignment
+* net/bnxt: return error if setting link up fails
+* net/bonding: fix LACP fast queue Rx handler
+* net/bonding: fix link speed update in broadcast mode
+* net/bonding: fix OOB access in other aggregator modes
+* net/bonding: fix port ID check
+* net/bonding: fix selection logic
+* net/bonding: fix slave id types
+* net/bonding: fix unicast packets filtering
+* net/bonding: use non deprecated PCI API
+* net/cxgbe: fix prefetch for non-coalesced Tx packets
+* net/dpaa2: add retry and timeout in packet enqueue API
+* net/dpaa2: fix possible use of uninitialized vars
+* net/dpaa2: set port in mbuf
+* net/e1000: fix link status
+* net/fm10k: fix mbuf free in vector Rx
+* net/fm10k: fix stats crash in multi-process
+* net/i40e: downgrade error log
+* net/i40e: fix address of first segment
+* net/i40e: remove compiler barrier from NEON Rx
+* net/i40e: remove memory barrier from NEON Rx
+* net/igb: fix global variable multiple definitions
+* net/igb: fix PHY status if PHY reset is not blocked
+* net/ixgbe: enable new PF host mbox version
+* net/ixgbe: fix address of first segment
+* net/ixgbe: fix link status
+* net/ixgbe: fix link status
+* net/ixgbe: fix queue interrupt for X552/557
+* net/ixgbe: fix VF RSS offloads configuration
+* net/ixgbe: fix X553 speed capability
+* net/ixgbe: remove memory barrier from NEON Rx
+* net/ixgbe: remove redundant assignment
+* net/ixgbe: support packet type with NEON
+* net/mlx4: fix build on ppc64
+* net/mlx5: fix Rx CQ doorbell synchronization on aarch64
+* net/mlx: fix build with make and recent gcc
+* net/mlx: fix debug build with icc
+* net/qede: fix setting MTU
+* net/qede: fix setting VLAN strip mode
+* net/qede: limit Rx ring index read for debug
+* net/sfc: fix adapter lock usage on rule creation
+* net/tap: fix blocked Rx packets
+* net/vhost: fix redundant queue state event
+* net/virtio: fix descriptor addressed in Tx
+* net/virtio: fix mbuf data and packet length mismatch
+* net/virtio: fix Tx checksum offloads
+* net/virtio: get all pending Rx packets in vectorized paths
+* net/virtio: init MTU in case no control channel
+* net/virtio: reject deferred Rx start
+* net/virtio: reject deferred Tx start
+* net/virtio-user: fix setting filters
+* power: fix socket indicator value
+* power: handle frequency increase with turbo disabled
+* ring: enforce reading tail before slots
+* security: fix doxygen fields
+* service: use log for error messages
+* test/bonding: fix LSC related cases
+* test: fix global variable multiple definitions
+* test/interrupt: account for race with callback
+* test/lpm: fix measured cycles for delete
+* test/mbuf: fix forged mbuf in clone test
+* test: optimise fd closing in forks
+* test/service: fix wait for service core
+* test/test: fix test app defining unused variable
+* usertools: fix pmdinfo with python 3 and pyelftools>=0.24
+* version: 17.11.10-rc1
+* vfio: fix truncated BAR offset for 32-bit
+* vhost: convert buffer addresses to GPA for logging
+* vhost: fix IPv4 checksum
+* vhost: fix slave request fd leak
+* vhost: fix virtqueue not accessible
+* vhost: fix vring address handling during live migration
+* vhost: fix vring memory partially mapped
+* vhost: forbid reallocation when running
+* vhost: prevent zero copy mode if IOMMU is on
+* vhost: protect vring access done by application
+* vhost: translate incoming log address to GPA
+* vhost: un-inline dirty pages logging functions
+
+17.11.10 Validation
+~~~~~~~~~~~~~~~~~~~
+
+* Red Hat(R) Testing
+
+   * RHEL 7.8
+   * Functionality
+
+      * PF assignment
+      * VF assignment
+      * vhost single/multi queues and cross-NUMA
+      * vhostclient reconnect
+      * vhost live migration with single/multi queues and cross-NUMA
+      * OVS PVP
+
+* Intel(R) Testing
+
+   * Basic Intel(R) NIC(ixgbe and i40e) testing
+
+      * PF (i40e)
+      * PF (ixgbe)
+      * VF
+      * Compile Testing
+      * Intel NIC single core/NIC performance
+
+   * Basic cryptodev and virtio testing
+
+      * cryptodev
+      * vhost/virtio basic loopback, PVP and performance test
+
+* Mellanox(R) Testing
+
+   * Basic functionality with testpmd
+
+      * Tx/Rx
+      * xstats
+      * Timestamps
+      * Link status
+      * RTE flow and flow_director
+      * RSS
+      * VLAN stripping and insertion
+      * Checksum/TSO
+      * ptype
+      * Multi-process
+
+   * ConnectX-5
+
+      * RHEL 7.4
+      * Kernel 3.10.0-693.el7.x86_64
+      * Driver MLNX_OFED_LINUX-4.7-3.2.9.0
+      * fw 16.26.4012
+
+   * ConnectX-4 Lx
+
+      * RHEL 7.4
+      * Kernel 3.10.0-693.el7.x86_64
+      * Driver MLNX_OFED_LINUX-4.7-3.2.9.0
+      * fw 14.26.4012
+
+* Intel(R) Testing with Open vSwitch
+
+   * OVS testing with OVS branches 2.10 and 2.19 with VSPERF
+
+   * Tested NICs
+
+      * i40e (X710)
+      * ixgbe (82599ES)
+
+   * Functionality
+
+      * P2P
+      * PVP
+      * Hotplug
+      * Multiqueue
+      * Vhostuserclient reconnect
+      * Vhost cross-NUMA awareness
+      * Jumbo frames
+      * Rate limiting
+      * QoS policer
+
+17.11.10 Known Issues
+~~~~~~~~~~~~~~~~~~~~~
+
+* MLX4/5 and rte_flow: count actions and rules with vlan items are not supported, and MLNX_OFED_LINUX 4.6-1.0.1.1 is not compatible
+* DPDK 17.11.10 contains fixes up to DPDK v19.11. Issues identified/fixed in DPDK master branch after DPDK v19.11 may be present in DPDK 17.11.10
diff --git a/doc/guides/sample_app_ug/ethtool.rst b/doc/guides/sample_app_ug/ethtool.rst
index 6dd11dc..4cefc2f 100644
--- a/doc/guides/sample_app_ug/ethtool.rst
+++ b/doc/guides/sample_app_ug/ethtool.rst
@@ -68,7 +68,7 @@ The application is console-driven using the cmdline DPDK interface:
         EthApp>
 
 From this interface the available commands and descriptions of what
-they do as as follows:
+they do as follows:
 
 * ``drvinfo``: Print driver info
 * ``eeprom``: Dump EEPROM to file
diff --git a/doc/guides/sample_app_ug/l2_forward_crypto.rst b/doc/guides/sample_app_ug/l2_forward_crypto.rst
index 1e85b4a..2d3c949 100644
--- a/doc/guides/sample_app_ug/l2_forward_crypto.rst
+++ b/doc/guides/sample_app_ug/l2_forward_crypto.rst
@@ -223,7 +223,7 @@ Crypto operation specification
 All the packets received in all the ports get transformed by the crypto device/s
 (ciphering and/or authentication).
 The crypto operation to be performed on the packet is parsed from the command line
-(go to "Running the Application section for all the options).
+(go to "Running the Application" section for all the options).
 
 If no parameter is passed, the default crypto operation is:
 
diff --git a/doc/guides/sample_app_ug/performance_thread.rst b/doc/guides/sample_app_ug/performance_thread.rst
index 57391ca..b194c3b 100644
--- a/doc/guides/sample_app_ug/performance_thread.rst
+++ b/doc/guides/sample_app_ug/performance_thread.rst
@@ -308,7 +308,7 @@ functionality into different threads, and the pairs of RX and TX threads are
 interconnected via software rings.
 
 On initialization an L-thread scheduler is started on every EAL thread. On all
-but the master EAL thread only a a dummy L-thread is initially started.
+but the master EAL thread only a dummy L-thread is initially started.
 The L-thread started on the master EAL thread then spawns other L-threads on
 different L-thread schedulers according the the command line parameters.
 
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
index 285dd56..e2d1715 100644
--- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
+++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
@@ -60,7 +60,7 @@ If you type a partial command and hit ``<TAB>`` you get a list of the available 
 
 .. note::
 
-   Some examples in this document are too long to fit on one line are are shown wrapped at `"\\"` for display purposes::
+   Some examples in this document are too long to fit on one line are shown wrapped at `"\\"` for display purposes::
 
       testpmd> set flow_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \
                (pause_time) (send_xon) (port_id)
@@ -1704,6 +1704,15 @@ Close all ports or a specific port::
 
    testpmd> port close (port_id|all)
 
+port reset
+~~~~~~~~~~
+
+Reset all ports or a specific port::
+
+   testpmd> port reset (port_id|all)
+
+User should stop port(s) before resetting and (re-)start after reset.
+
 port start/stop queue
 ~~~~~~~~~~~~~~~~~~~~~
 
@@ -2173,7 +2182,7 @@ Traffic Management
 ------------------
 
 The following section shows functions for configuring traffic management on
-on the ethernet device through the use of generic TM API.
+the ethernet device through the use of generic TM API.
 
 show port traffic management capability
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h
index ece1a7d..4f7e49c 100644
--- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h
+++ b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h
@@ -63,6 +63,8 @@
 #define DPAA2_DQRR_RING_SIZE	16
 	/** <Maximum number of slots available in RX ring*/
 
+#define DPAA2_MAX_TX_RETRY_COUNT	10000
+
 #define MC_PORTAL_INDEX		0
 #define NUM_DPIO_REGIONS	2
 #define NUM_DQS_PER_QUEUE       2
diff --git a/drivers/bus/pci/Makefile b/drivers/bus/pci/Makefile
index f3df1c4..37663de 100644
--- a/drivers/bus/pci/Makefile
+++ b/drivers/bus/pci/Makefile
@@ -50,7 +50,7 @@ CFLAGS += -I$(RTE_SDK)/lib/librte_eal/common
 CFLAGS += -I$(RTE_SDK)/lib/librte_eal/$(SYSTEM)app/eal
 
 LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
-LDLIBS += -lrte_ethdev -lrte_pci
+LDLIBS += -lrte_pci
 
 include $(RTE_SDK)/drivers/bus/pci/$(SYSTEM)/Makefile
 SRCS-$(CONFIG_RTE_LIBRTE_PCI_BUS) := $(addprefix $(SYSTEM)/,$(SRCS))
diff --git a/drivers/bus/pci/linux/pci.c b/drivers/bus/pci/linux/pci.c
index aabaa63..a51d00a 100644
--- a/drivers/bus/pci/linux/pci.c
+++ b/drivers/bus/pci/linux/pci.c
@@ -593,18 +593,19 @@ pci_one_device_iommu_support_va(struct rte_pci_device *dev)
 		 "%s/" PCI_PRI_FMT "/iommu/intel-iommu/cap",
 		 rte_pci_get_sysfs_path(), addr->domain, addr->bus, addr->devid,
 		 addr->function);
-	if (access(filename, F_OK) == -1) {
-		/* We don't have an Intel IOMMU, assume VA supported*/
-		return true;
-	}
 
-	/* We have an intel IOMMU */
 	fp = fopen(filename, "r");
 	if (fp == NULL) {
-		RTE_LOG(ERR, EAL, "%s(): can't open %s\n", __func__, filename);
+		/* We don't have an Intel IOMMU, assume VA supported */
+		if (errno == ENOENT)
+			return true;
+
+		RTE_LOG(ERR, EAL, "%s(): can't open %s: %s\n",
+			__func__, filename, strerror(errno));
 		return false;
 	}
 
+	/* We have an Intel IOMMU */
 	if (fscanf(fp, "%" PRIx64, &vtd_cap_reg) != 1) {
 		RTE_LOG(ERR, EAL, "%s(): can't read %s\n", __func__, filename);
 		fclose(fp);
diff --git a/drivers/bus/pci/linux/pci_uio.c b/drivers/bus/pci/linux/pci_uio.c
index 39176ac..2b2ad77 100644
--- a/drivers/bus/pci/linux/pci_uio.c
+++ b/drivers/bus/pci/linux/pci_uio.c
@@ -358,6 +358,8 @@ pci_uio_map_resource_by_index(struct rte_pci_device *dev, int res_idx,
 	pci_map_addr = RTE_PTR_ADD(mapaddr,
 			(size_t)dev->mem_resource[res_idx].len);
 
+	pci_map_addr = RTE_PTR_ALIGN(pci_map_addr, sysconf(_SC_PAGE_SIZE));
+
 	maps[map_idx].phaddr = dev->mem_resource[res_idx].phys_addr;
 	maps[map_idx].size = dev->mem_resource[res_idx].len;
 	maps[map_idx].addr = mapaddr;
diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
index 5093265..8b485de 100644
--- a/drivers/bus/pci/linux/pci_vfio.c
+++ b/drivers/bus/pci/linux/pci_vfio.c
@@ -356,7 +356,8 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 		int bar_index, int additional_flags)
 {
 	struct memreg {
-		unsigned long offset, size;
+		uint64_t offset;
+		size_t   size;
 	} memreg[2] = {};
 	void *bar_addr;
 	struct pci_msix_table *msix_table = &vfio_res->msix_table;
@@ -392,7 +393,8 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 		RTE_LOG(DEBUG, EAL,
 			"Trying to map BAR%d that contains the MSI-X "
 			"table. Trying offsets: "
-			"0x%04lx:0x%04lx, 0x%04lx:0x%04lx\n", bar_index,
+			"0x%04" PRIx64 ":0x%04zx, 0x%04" PRIx64 ":0x%04zx\n",
+			bar_index,
 			memreg[0].offset, memreg[0].size,
 			memreg[1].offset, memreg[1].size);
 	} else {
@@ -417,8 +419,8 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 		if (map_addr != MAP_FAILED
 			&& memreg[1].offset && memreg[1].size) {
 			void *second_addr = RTE_PTR_ADD(bar_addr,
-							memreg[1].offset -
-							(uintptr_t)bar->offset);
+						(uintptr_t)(memreg[1].offset -
+						bar->offset));
 			map_addr = pci_map_resource(second_addr,
 							vfio_dev_fd,
 							memreg[1].offset,
@@ -530,6 +532,9 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 		bar_addr = pci_map_addr;
 		pci_map_addr = RTE_PTR_ADD(bar_addr, (size_t) reg.size);
 
+		pci_map_addr = RTE_PTR_ALIGN(pci_map_addr,
+					sysconf(_SC_PAGE_SIZE));
+
 		maps[i].addr = bar_addr;
 		maps[i].offset = reg.offset;
 		maps[i].size = reg.size;
diff --git a/drivers/crypto/armv8/rte_armv8_pmd.c b/drivers/crypto/armv8/rte_armv8_pmd.c
index 97719f2..d757ebf 100644
--- a/drivers/crypto/armv8/rte_armv8_pmd.c
+++ b/drivers/crypto/armv8/rte_armv8_pmd.c
@@ -803,7 +803,6 @@ cryptodev_armv8_crypto_create(const char *name,
 			RTE_CRYPTODEV_FF_CPU_NEON |
 			RTE_CRYPTODEV_FF_CPU_ARM_CE;
 
-	/* Set vector instructions mode supported */
 	internals = dev->data->dev_private;
 
 	internals->max_nb_qpairs = init_params->max_nb_queue_pairs;
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
index 8ccb663..56259ce 100644
--- a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
+++ b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
@@ -716,7 +716,7 @@ sec_simple_fd_to_mbuf(const struct qbman_fd *fd, __rte_unused uint8_t id)
 {
 	struct rte_crypto_op *op;
 	uint16_t len = DPAA2_GET_FD_LEN(fd);
-	uint16_t diff = 0;
+	int16_t diff = 0;
 	dpaa2_sec_session *sess_priv;
 
 	struct rte_mbuf *mbuf = DPAA2_INLINE_MBUF_FROM_BUF(
diff --git a/drivers/crypto/mrvl/rte_mrvl_pmd.c b/drivers/crypto/mrvl/rte_mrvl_pmd.c
index 31f3fe5..95276a9 100644
--- a/drivers/crypto/mrvl/rte_mrvl_pmd.c
+++ b/drivers/crypto/mrvl/rte_mrvl_pmd.c
@@ -743,7 +743,6 @@ cryptodev_mrvl_crypto_create(const char *name,
 			RTE_CRYPTODEV_FF_SYM_OPERATION_CHAINING |
 			RTE_CRYPTODEV_FF_HW_ACCELERATED;
 
-	/* Set vector instructions mode supported */
 	internals = dev->data->dev_private;
 
 	internals->max_nb_qpairs = init_params->max_nb_queue_pairs;
diff --git a/drivers/crypto/openssl/rte_openssl_pmd.c b/drivers/crypto/openssl/rte_openssl_pmd.c
index 06e1a6d..24304d5 100644
--- a/drivers/crypto/openssl/rte_openssl_pmd.c
+++ b/drivers/crypto/openssl/rte_openssl_pmd.c
@@ -1296,6 +1296,7 @@ process_openssl_combined_op
 	int srclen, aadlen, status = -1;
 	uint32_t offset;
 	uint8_t taglen;
+	EVP_CIPHER_CTX *ctx_copy;
 
 	/*
 	 * Segmented destination buffer is not supported for
@@ -1332,6 +1333,8 @@ process_openssl_combined_op
 	}
 
 	taglen = sess->auth.digest_length;
+	ctx_copy = EVP_CIPHER_CTX_new();
+	EVP_CIPHER_CTX_copy(ctx_copy, sess->cipher.ctx);
 
 	if (sess->cipher.direction == RTE_CRYPTO_CIPHER_OP_ENCRYPT) {
 		if (sess->auth.algo == RTE_CRYPTO_AUTH_AES_GMAC ||
@@ -1339,12 +1342,12 @@ process_openssl_combined_op
 			status = process_openssl_auth_encryption_gcm(
 					mbuf_src, offset, srclen,
 					aad, aadlen, iv,
-					dst, tag, sess->cipher.ctx);
+					dst, tag, ctx_copy);
 		else
 			status = process_openssl_auth_encryption_ccm(
 					mbuf_src, offset, srclen,
 					aad, aadlen, iv,
-					dst, tag, taglen, sess->cipher.ctx);
+					dst, tag, taglen, ctx_copy);
 
 	} else {
 		if (sess->auth.algo == RTE_CRYPTO_AUTH_AES_GMAC ||
@@ -1352,14 +1355,15 @@ process_openssl_combined_op
 			status = process_openssl_auth_decryption_gcm(
 					mbuf_src, offset, srclen,
 					aad, aadlen, iv,
-					dst, tag, sess->cipher.ctx);
+					dst, tag, ctx_copy);
 		else
 			status = process_openssl_auth_decryption_ccm(
 					mbuf_src, offset, srclen,
 					aad, aadlen, iv,
-					dst, tag, taglen, sess->cipher.ctx);
+					dst, tag, taglen, ctx_copy);
 	}
 
+	EVP_CIPHER_CTX_free(ctx_copy);
 	if (status != 0) {
 		if (status == (-EFAULT) &&
 				sess->auth.operation ==
@@ -1378,6 +1382,7 @@ process_openssl_cipher_op
 {
 	uint8_t *dst, *iv;
 	int srclen, status;
+	EVP_CIPHER_CTX *ctx_copy;
 
 	/*
 	 * Segmented destination buffer is not supported for
@@ -1394,22 +1399,25 @@ process_openssl_cipher_op
 
 	iv = rte_crypto_op_ctod_offset(op, uint8_t *,
 			sess->iv.offset);
+	ctx_copy = EVP_CIPHER_CTX_new();
+	EVP_CIPHER_CTX_copy(ctx_copy, sess->cipher.ctx);
 
 	if (sess->cipher.mode == OPENSSL_CIPHER_LIB)
 		if (sess->cipher.direction == RTE_CRYPTO_CIPHER_OP_ENCRYPT)
 			status = process_openssl_cipher_encrypt(mbuf_src, dst,
 					op->sym->cipher.data.offset, iv,
-					srclen, sess->cipher.ctx);
+					srclen, ctx_copy);
 		else
 			status = process_openssl_cipher_decrypt(mbuf_src, dst,
 					op->sym->cipher.data.offset, iv,
-					srclen, sess->cipher.ctx);
+					srclen, ctx_copy);
 	else
 		status = process_openssl_cipher_des3ctr(mbuf_src, dst,
 				op->sym->cipher.data.offset, iv,
 				sess->cipher.key.data, srclen,
-				sess->cipher.ctx);
+				ctx_copy);
 
+	EVP_CIPHER_CTX_free(ctx_copy);
 	if (status != 0)
 		op->status = RTE_CRYPTO_OP_STATUS_ERROR;
 }
@@ -1513,6 +1521,8 @@ process_openssl_auth_op(struct openssl_qp *qp, struct rte_crypto_op *op,
 {
 	uint8_t *dst;
 	int srclen, status;
+	EVP_MD_CTX *ctx_a;
+	HMAC_CTX *ctx_h;
 
 	srclen = op->sym->auth.data.length;
 
@@ -1528,14 +1538,20 @@ process_openssl_auth_op(struct openssl_qp *qp, struct rte_crypto_op *op,
 
 	switch (sess->auth.mode) {
 	case OPENSSL_AUTH_AS_AUTH:
+		ctx_a = EVP_MD_CTX_create();
+		EVP_MD_CTX_copy_ex(ctx_a, sess->auth.auth.ctx);
 		status = process_openssl_auth(mbuf_src, dst,
 				op->sym->auth.data.offset, NULL, NULL, srclen,
-				sess->auth.auth.ctx, sess->auth.auth.evp_algo);
+				ctx_a, sess->auth.auth.evp_algo);
+		EVP_MD_CTX_destroy(ctx_a);
 		break;
 	case OPENSSL_AUTH_AS_HMAC:
+		ctx_h = HMAC_CTX_new();
+		HMAC_CTX_copy(ctx_h, sess->auth.hmac.ctx);
 		status = process_openssl_auth_hmac(mbuf_src, dst,
 				op->sym->auth.data.offset, srclen,
-				sess->auth.hmac.ctx);
+				ctx_h);
+		HMAC_CTX_free(ctx_h);
 		break;
 	default:
 		status = -1;
@@ -1690,7 +1706,6 @@ cryptodev_openssl_create(const char *name,
 			RTE_CRYPTODEV_FF_CPU_AESNI |
 			RTE_CRYPTODEV_FF_MBUF_SCATTER_GATHER;
 
-	/* Set vector instructions mode supported */
 	internals = dev->data->dev_private;
 
 	internals->max_nb_qpairs = init_params->max_nb_queue_pairs;
diff --git a/drivers/crypto/qat/qat_crypto.c b/drivers/crypto/qat/qat_crypto.c
index 85a9ba0..05b37e6 100644
--- a/drivers/crypto/qat/qat_crypto.c
+++ b/drivers/crypto/qat/qat_crypto.c
@@ -1370,10 +1370,8 @@ qat_write_hw_desc_entry(struct rte_crypto_op *op, uint8_t *out_msg,
 
 		}
 		min_ofs = auth_ofs;
-
-		if (likely(ctx->qat_hash_alg != ICP_QAT_HW_AUTH_ALGO_NULL))
-			auth_param->auth_res_addr =
-					op->sym->auth.digest.phys_addr;
+		auth_param->auth_res_addr =
+			op->sym->auth.digest.phys_addr;
 
 	}
 
diff --git a/drivers/crypto/qat/qat_crypto_capabilities.h b/drivers/crypto/qat/qat_crypto_capabilities.h
index 89ba27d..9e8bc41 100644
--- a/drivers/crypto/qat/qat_crypto_capabilities.h
+++ b/drivers/crypto/qat/qat_crypto_capabilities.h
@@ -174,8 +174,8 @@
 					.increment = 0			\
 				},					\
 				.digest_size = {			\
-					.min = 16,			\
-					.max = 16,			\
+					.min = 12,			\
+					.max = 12,			\
 					.increment = 0			\
 				},					\
 				.aad_size = { 0 },			\
diff --git a/drivers/event/dpaa2/dpaa2_eventdev.c b/drivers/event/dpaa2/dpaa2_eventdev.c
index 56ea124..bf1b493 100644
--- a/drivers/event/dpaa2/dpaa2_eventdev.c
+++ b/drivers/event/dpaa2/dpaa2_eventdev.c
@@ -1,7 +1,7 @@
 /*-
  *   BSD LICENSE
  *
- *   Copyright 2017 NXP.
+ *   Copyright 2017,2019 NXP.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -395,8 +395,7 @@ dpaa2_eventdev_queue_def_conf(struct rte_eventdev *dev, uint8_t queue_id,
 	RTE_SET_USED(queue_conf);
 
 	queue_conf->nb_atomic_flows = DPAA2_EVENT_QUEUE_ATOMIC_FLOWS;
-	queue_conf->schedule_type = RTE_SCHED_TYPE_ATOMIC |
-				      RTE_SCHED_TYPE_PARALLEL;
+	queue_conf->schedule_type = RTE_SCHED_TYPE_PARALLEL;
 	queue_conf->priority = RTE_EVENT_DEV_PRIORITY_NORMAL;
 }
 
diff --git a/drivers/event/octeontx/Makefile b/drivers/event/octeontx/Makefile
index 2604412..2c029cb 100644
--- a/drivers/event/octeontx/Makefile
+++ b/drivers/event/octeontx/Makefile
@@ -42,6 +42,7 @@ CFLAGS += -I$(RTE_SDK)/drivers/mempool/octeontx/
 CFLAGS += -I$(RTE_SDK)/drivers/net/octeontx/
 
 LDLIBS += -lrte_eal -lrte_eventdev -lrte_mempool_octeontx -lrte_pmd_octeontx
+LDLIBS += -lrte_mempool
 LDLIBS += -lrte_bus_pci
 LDLIBS += -lrte_bus_vdev
 
diff --git a/drivers/event/octeontx/ssovf_worker.h b/drivers/event/octeontx/ssovf_worker.h
index 4c9a4c4..7e7d0a7 100644
--- a/drivers/event/octeontx/ssovf_worker.h
+++ b/drivers/event/octeontx/ssovf_worker.h
@@ -60,8 +60,7 @@ ssovf_octeontx_wqe_to_pkt(uint64_t work, uint16_t port_info)
 	rte_prefetch_non_temporal(wqe);
 
 	/* Get mbuf from wqe */
-	mbuf = (struct rte_mbuf *)((uintptr_t)wqe -
-			OCTTX_PACKET_WQE_SKIP);
+	mbuf = (struct rte_mbuf *)((uintptr_t)wqe - OCTTX_PACKET_WQE_SKIP);
 	mbuf->packet_type =
 		ptype_table[wqe->s.w2.lcty][wqe->s.w2.lety][wqe->s.w2.lfty];
 	mbuf->data_off = RTE_PTR_DIFF(wqe->s.w3.addr, mbuf->buf_addr);
@@ -74,6 +73,16 @@ ssovf_octeontx_wqe_to_pkt(uint64_t work, uint16_t port_info)
 	return mbuf;
 }
 
+static __rte_always_inline void
+ssovf_octeontx_wqe_free(uint64_t work)
+{
+	octtx_wqe_t *wqe = (octtx_wqe_t *)(uintptr_t)work;
+	struct rte_mbuf *mbuf;
+
+	mbuf = (struct rte_mbuf *)((uintptr_t)wqe - OCTTX_PACKET_WQE_SKIP);
+	rte_pktmbuf_free(mbuf);
+}
+
 static __rte_always_inline uint16_t
 ssows_get_work(struct ssows *ws, struct rte_event *ev)
 {
@@ -87,9 +96,13 @@ ssows_get_work(struct ssows *ws, struct rte_event *ev)
 	ws->cur_grp = sched_type_queue >> 2;
 	sched_type_queue = sched_type_queue << 38;
 	ev->event = sched_type_queue | (get_work0 & 0xffffffff);
+
 	if (get_work1 && ev->event_type == RTE_EVENT_TYPE_ETHDEV) {
 		ev->mbuf = ssovf_octeontx_wqe_to_pkt(get_work1,
 				(ev->event >> 20) & 0x7F);
+	} else if (unlikely((get_work0 & 0xFFFFFFFF) == 0xFFFFFFFF)) {
+		ssovf_octeontx_wqe_free(get_work1);
+		return 0;
 	} else {
 		ev->u64 = get_work1;
 	}
diff --git a/drivers/event/sw/sw_evdev_xstats.c b/drivers/event/sw/sw_evdev_xstats.c
index 61a5c33..bed222f 100644
--- a/drivers/event/sw/sw_evdev_xstats.c
+++ b/drivers/event/sw/sw_evdev_xstats.c
@@ -521,7 +521,7 @@ sw_xstats_update(struct sw_evdev *sw, enum rte_event_dev_xstats_mode mode,
 			values[xidx] = val;
 
 		if (xs->reset_allowed && reset)
-			xs->reset_value = val;
+			xs->reset_value += val;
 
 		xidx++;
 	}
@@ -574,8 +574,7 @@ sw_xstats_reset_range(struct sw_evdev *sw, uint32_t start, uint32_t num)
 		if (!xs->reset_allowed)
 			continue;
 
-		uint64_t val = xs->fn(sw, xs->obj_idx, xs->stat, xs->extra_arg)
-					- xs->reset_value;
+		uint64_t val = xs->fn(sw, xs->obj_idx, xs->stat, xs->extra_arg);
 		xs->reset_value = val;
 	}
 }
diff --git a/drivers/mempool/dpaa2/dpaa2_hw_mempool.c b/drivers/mempool/dpaa2/dpaa2_hw_mempool.c
index 8bcbaa8..81b7e85 100644
--- a/drivers/mempool/dpaa2/dpaa2_hw_mempool.c
+++ b/drivers/mempool/dpaa2/dpaa2_hw_mempool.c
@@ -200,7 +200,7 @@ rte_dpaa2_mbuf_release(struct rte_mempool *pool __rte_unused,
 	struct qbman_release_desc releasedesc;
 	struct qbman_swp *swp;
 	int ret;
-	int i, n;
+	int i, n, retry_count;
 	uint64_t bufs[DPAA2_MBUF_MAX_ACQ_REL];
 
 	if (unlikely(!DPAA2_PER_LCORE_DPIO)) {
@@ -233,9 +233,15 @@ rte_dpaa2_mbuf_release(struct rte_mempool *pool __rte_unused,
 	}
 
 	/* feed them to bman */
-	do {
-		ret = qbman_swp_release(swp, &releasedesc, bufs, n);
-	} while (ret == -EBUSY);
+	retry_count = 0;
+	while ((ret = qbman_swp_release(swp, &releasedesc, bufs, n)) ==
+			-EBUSY) {
+		retry_count++;
+		if (retry_count > DPAA2_MAX_TX_RETRY_COUNT) {
+			DPAA2_MEMPOOL_ERR("bman release retry exceeded, low fbpr?");
+			return;
+		}
+	}
 
 aligned:
 	/* if there are more buffers to free */
@@ -251,10 +257,15 @@ aligned:
 #endif
 		}
 
-		do {
-			ret = qbman_swp_release(swp, &releasedesc, bufs,
-						DPAA2_MBUF_MAX_ACQ_REL);
-		} while (ret == -EBUSY);
+		retry_count = 0;
+		while ((ret = qbman_swp_release(swp, &releasedesc, bufs,
+					DPAA2_MBUF_MAX_ACQ_REL)) == -EBUSY) {
+			retry_count++;
+			if (retry_count > DPAA2_MAX_TX_RETRY_COUNT) {
+				DPAA2_MEMPOOL_ERR("bman release retry exceeded, low fbpr?");
+				return;
+			}
+		}
 		n += DPAA2_MBUF_MAX_ACQ_REL;
 	}
 }
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c b/drivers/net/af_packet/rte_eth_af_packet.c
index 5cb348f..ae9b0e2 100644
--- a/drivers/net/af_packet/rte_eth_af_packet.c
+++ b/drivers/net/af_packet/rte_eth_af_packet.c
@@ -263,8 +263,14 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 	}
 
 	/* kick-off transmits */
-	if (sendto(pkt_q->sockfd, NULL, 0, MSG_DONTWAIT, NULL, 0) == -1) {
-		/* error sending -- no packets transmitted */
+	if (sendto(pkt_q->sockfd, NULL, 0, MSG_DONTWAIT, NULL, 0) == -1 &&
+			errno != ENOBUFS && errno != EAGAIN) {
+		/*
+		 * In case of a ENOBUFS/EAGAIN error all of the enqueued
+		 * packets will be considered successful even though only some
+		 * are sent.
+		 */
+
 		num_tx = 0;
 		num_tx_bytes = 0;
 	}
@@ -982,6 +988,7 @@ rte_pmd_af_packet_remove(struct rte_vdev_device *dev)
 {
 	struct rte_eth_dev *eth_dev = NULL;
 	struct pmd_internals *internals;
+	struct tpacket_req *req;
 	unsigned q;
 
 	RTE_LOG(INFO, PMD, "Closing AF_PACKET ethdev on numa socket %u\n",
@@ -996,7 +1003,10 @@ rte_pmd_af_packet_remove(struct rte_vdev_device *dev)
 		return -1;
 
 	internals = eth_dev->data->dev_private;
+	req = &internals->req;
 	for (q = 0; q < internals->nb_queues; q++) {
+		munmap(internals->rx_queue[q].map,
+			2 * req->tp_block_size * req->tp_block_nr);
 		rte_free(internals->rx_queue[q].rd);
 		rte_free(internals->tx_queue[q].rd);
 	}
diff --git a/drivers/net/bnxt/bnxt.h b/drivers/net/bnxt/bnxt.h
index 3bc2b93..3c29ee5 100644
--- a/drivers/net/bnxt/bnxt.h
+++ b/drivers/net/bnxt/bnxt.h
@@ -47,6 +47,46 @@
 
 #include "bnxt_cpr.h"
 
+/* Vendor ID */
+#define PCI_VENDOR_ID_BROADCOM 0x14E4
+
+/* Device IDs */
+#define BROADCOM_DEV_ID_STRATUS_NIC_VF 0x1609
+#define BROADCOM_DEV_ID_STRATUS_NIC 0x1614
+#define BROADCOM_DEV_ID_57414_VF 0x16c1
+#define BROADCOM_DEV_ID_57301 0x16c8
+#define BROADCOM_DEV_ID_57302 0x16c9
+#define BROADCOM_DEV_ID_57304_PF 0x16ca
+#define BROADCOM_DEV_ID_57304_VF 0x16cb
+#define BROADCOM_DEV_ID_57417_MF 0x16cc
+#define BROADCOM_DEV_ID_NS2 0x16cd
+#define BROADCOM_DEV_ID_57311 0x16ce
+#define BROADCOM_DEV_ID_57312 0x16cf
+#define BROADCOM_DEV_ID_57402 0x16d0
+#define BROADCOM_DEV_ID_57404 0x16d1
+#define BROADCOM_DEV_ID_57406_PF 0x16d2
+#define BROADCOM_DEV_ID_57406_VF 0x16d3
+#define BROADCOM_DEV_ID_57402_MF 0x16d4
+#define BROADCOM_DEV_ID_57407_RJ45 0x16d5
+#define BROADCOM_DEV_ID_57412 0x16d6
+#define BROADCOM_DEV_ID_57414 0x16d7
+#define BROADCOM_DEV_ID_57416_RJ45 0x16d8
+#define BROADCOM_DEV_ID_57417_RJ45 0x16d9
+#define BROADCOM_DEV_ID_5741X_VF 0x16dc
+#define BROADCOM_DEV_ID_57412_MF 0x16de
+#define BROADCOM_DEV_ID_57314 0x16df
+#define BROADCOM_DEV_ID_57317_RJ45 0x16e0
+#define BROADCOM_DEV_ID_5731X_VF 0x16e1
+#define BROADCOM_DEV_ID_57417_SFP 0x16e2
+#define BROADCOM_DEV_ID_57416_SFP 0x16e3
+#define BROADCOM_DEV_ID_57317_SFP 0x16e4
+#define BROADCOM_DEV_ID_57404_MF 0x16e7
+#define BROADCOM_DEV_ID_57406_MF 0x16e8
+#define BROADCOM_DEV_ID_57407_SFP 0x16e9
+#define BROADCOM_DEV_ID_57407_MF 0x16ea
+#define BROADCOM_DEV_ID_57414_MF 0x16ec
+#define BROADCOM_DEV_ID_57416_MF 0x16ee
+
 #define BNXT_MAX_MTU		9500
 #define VLAN_TAG_SIZE		4
 #define BNXT_MAX_LED		4
@@ -246,6 +286,11 @@ struct bnxt {
 	uint16_t			max_req_len;
 	uint16_t			max_resp_len;
 
+	 /* default command timeout value of 50ms */
+#define HWRM_CMD_TIMEOUT		50000
+	/* default HWRM request timeout value */
+	uint32_t			hwrm_cmd_timeout;
+
 	struct bnxt_link_info	link_info;
 	struct bnxt_cos_queue_info	cos_queue[BNXT_COS_QUEUE_COUNT];
 
diff --git a/drivers/net/bnxt/bnxt_cpr.c b/drivers/net/bnxt/bnxt_cpr.c
index cde8adc..f3f0805 100644
--- a/drivers/net/bnxt/bnxt_cpr.c
+++ b/drivers/net/bnxt/bnxt_cpr.c
@@ -34,7 +34,6 @@
 #include <rte_malloc.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ring.h"
 #include "hsi_struct_def_dpdk.h"
@@ -49,13 +48,11 @@ void bnxt_handle_async_event(struct bnxt *bp,
 				(struct hwrm_async_event_cmpl *)cmp;
 	uint16_t event_id = rte_le_to_cpu_16(async_cmp->event_id);
 
-	/* TODO: HWRM async events are not defined yet */
-	/* Needs to handle: link events, error events, etc. */
 	switch (event_id) {
 	case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
 	case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE:
 	case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE:
-		bnxt_link_update_op(bp->eth_dev, 1);
+		bnxt_link_update_op(bp->eth_dev, 0);
 		break;
 	default:
 		RTE_LOG(DEBUG, PMD, "handle_async_event id = 0x%x\n", event_id);
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index bc7b82f..e73a683 100644
--- a/drivers/net/bnxt/bnxt_ethdev.c
+++ b/drivers/net/bnxt/bnxt_ethdev.c
@@ -41,7 +41,6 @@
 #include <rte_cycles.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_filter.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_irq.h"
@@ -59,44 +58,6 @@
 static const char bnxt_version[] =
 	"Broadcom Cumulus driver " DRV_MODULE_NAME "\n";
 
-#define PCI_VENDOR_ID_BROADCOM 0x14E4
-
-#define BROADCOM_DEV_ID_STRATUS_NIC_VF 0x1609
-#define BROADCOM_DEV_ID_STRATUS_NIC 0x1614
-#define BROADCOM_DEV_ID_57414_VF 0x16c1
-#define BROADCOM_DEV_ID_57301 0x16c8
-#define BROADCOM_DEV_ID_57302 0x16c9
-#define BROADCOM_DEV_ID_57304_PF 0x16ca
-#define BROADCOM_DEV_ID_57304_VF 0x16cb
-#define BROADCOM_DEV_ID_57417_MF 0x16cc
-#define BROADCOM_DEV_ID_NS2 0x16cd
-#define BROADCOM_DEV_ID_57311 0x16ce
-#define BROADCOM_DEV_ID_57312 0x16cf
-#define BROADCOM_DEV_ID_57402 0x16d0
-#define BROADCOM_DEV_ID_57404 0x16d1
-#define BROADCOM_DEV_ID_57406_PF 0x16d2
-#define BROADCOM_DEV_ID_57406_VF 0x16d3
-#define BROADCOM_DEV_ID_57402_MF 0x16d4
-#define BROADCOM_DEV_ID_57407_RJ45 0x16d5
-#define BROADCOM_DEV_ID_57412 0x16d6
-#define BROADCOM_DEV_ID_57414 0x16d7
-#define BROADCOM_DEV_ID_57416_RJ45 0x16d8
-#define BROADCOM_DEV_ID_57417_RJ45 0x16d9
-#define BROADCOM_DEV_ID_5741X_VF 0x16dc
-#define BROADCOM_DEV_ID_57412_MF 0x16de
-#define BROADCOM_DEV_ID_57314 0x16df
-#define BROADCOM_DEV_ID_57317_RJ45 0x16e0
-#define BROADCOM_DEV_ID_5731X_VF 0x16e1
-#define BROADCOM_DEV_ID_57417_SFP 0x16e2
-#define BROADCOM_DEV_ID_57416_SFP 0x16e3
-#define BROADCOM_DEV_ID_57317_SFP 0x16e4
-#define BROADCOM_DEV_ID_57404_MF 0x16e7
-#define BROADCOM_DEV_ID_57406_MF 0x16e8
-#define BROADCOM_DEV_ID_57407_SFP 0x16e9
-#define BROADCOM_DEV_ID_57407_MF 0x16ea
-#define BROADCOM_DEV_ID_57414_MF 0x16ec
-#define BROADCOM_DEV_ID_57416_MF 0x16ee
-
 static const struct rte_pci_id bnxt_pci_id_map[] = {
 	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM,
 			 BROADCOM_DEV_ID_STRATUS_NIC_VF) },
@@ -164,6 +125,9 @@ static void bnxt_free_mem(struct bnxt *bp)
 	bnxt_free_tx_rings(bp);
 	bnxt_free_rx_rings(bp);
 	bnxt_free_def_cp_ring(bp);
+
+	rte_free(bp->grp_info);
+	bp->grp_info = NULL;
 }
 
 static int bnxt_alloc_mem(struct bnxt *bp)
@@ -433,6 +397,7 @@ static int bnxt_init_nic(struct bnxt *bp)
 static void bnxt_dev_info_get_op(struct rte_eth_dev *eth_dev,
 				  struct rte_eth_dev_info *dev_info)
 {
+	struct rte_pci_device *pdev = RTE_DEV_TO_PCI(eth_dev->device);
 	struct bnxt *bp = (struct bnxt *)eth_dev->data->dev_private;
 	uint16_t max_vnics, i, j, vpool, vrxq;
 	unsigned int max_rx_rings;
@@ -445,7 +410,7 @@ static void bnxt_dev_info_get_op(struct rte_eth_dev *eth_dev,
 
 	/* PF/VF specifics */
 	if (BNXT_PF(bp))
-		dev_info->max_vfs = bp->pdev->max_vfs;
+		dev_info->max_vfs = pdev->max_vfs;
 	max_rx_rings = RTE_MIN(bp->max_vnics, RTE_MIN(bp->max_l2_ctx,
 						RTE_MIN(bp->max_rsscos_ctx,
 						bp->max_stat_ctx)));
@@ -592,6 +557,8 @@ static int bnxt_dev_start_op(struct rte_eth_dev *eth_dev)
 	}
 	bp->dev_stopped = 0;
 
+	bnxt_enable_int(bp);
+
 	rc = bnxt_init_chip(bp);
 	if (rc)
 		goto error;
@@ -626,7 +593,7 @@ static int bnxt_dev_set_link_up_op(struct rte_eth_dev *eth_dev)
 		eth_dev->data->dev_link.link_status = 1;
 
 	bnxt_print_link_info(eth_dev);
-	return 0;
+	return rc;
 }
 
 static int bnxt_dev_set_link_down_op(struct rte_eth_dev *eth_dev)
@@ -644,15 +611,29 @@ static int bnxt_dev_set_link_down_op(struct rte_eth_dev *eth_dev)
 static void bnxt_dev_stop_op(struct rte_eth_dev *eth_dev)
 {
 	struct bnxt *bp = (struct bnxt *)eth_dev->data->dev_private;
+	struct rte_intr_handle *intr_handle
+		= &bp->pdev->intr_handle;
 
 	if (bp->eth_dev->data->dev_started) {
 		/* TBD: STOP HW queues DMA */
 		eth_dev->data->dev_link.link_status = 0;
 	}
-	bnxt_set_hwrm_link_config(bp, false);
+	bnxt_dev_set_link_down_op(eth_dev);
+	/* Wait for link to be reset and the async notification to process. */
+	rte_delay_ms(BNXT_LINK_WAIT_INTERVAL * 2);
+
+	/* Clean queue intr-vector mapping */
+	rte_intr_efd_disable(intr_handle);
+	if (intr_handle->intr_vec != NULL) {
+		rte_free(intr_handle->intr_vec);
+		intr_handle->intr_vec = NULL;
+	}
+
 	bnxt_hwrm_port_clr_stats(bp);
 	bnxt_free_tx_mbufs(bp);
 	bnxt_free_rx_mbufs(bp);
+	/* Process any remaining notifications in default completion queue */
+	bnxt_int_handler(eth_dev);
 	bnxt_shutdown_nic(bp);
 	bp->dev_stopped = 1;
 }
@@ -734,7 +715,7 @@ static int bnxt_mac_addr_add_op(struct rte_eth_dev *eth_dev,
 	/* Attach requested MAC address to the new l2_filter */
 	STAILQ_FOREACH(filter, &vnic->filter, next) {
 		if (filter->mac_index == index) {
-			RTE_LOG(ERR, PMD,
+			RTE_LOG(DEBUG, PMD,
 				"MAC addr already existed for pool %d\n", pool);
 			return 0;
 		}
@@ -1429,15 +1410,18 @@ bnxt_set_default_mac_addr_op(struct rte_eth_dev *dev, struct ether_addr *addr)
 		rc = bnxt_hwrm_clear_l2_filter(bp, filter);
 		if (rc)
 			break;
-		memcpy(filter->l2_addr, bp->mac_addr, ETHER_ADDR_LEN);
+		memcpy(filter->l2_addr, addr, ETHER_ADDR_LEN);
 		memset(filter->l2_addr_mask, 0xff, ETHER_ADDR_LEN);
 		filter->flags |= HWRM_CFA_L2_FILTER_ALLOC_INPUT_FLAGS_PATH_RX;
 		filter->enables |=
 			HWRM_CFA_L2_FILTER_ALLOC_INPUT_ENABLES_L2_ADDR |
 			HWRM_CFA_L2_FILTER_ALLOC_INPUT_ENABLES_L2_ADDR_MASK;
 		rc = bnxt_hwrm_set_l2_filter(bp, vnic->fw_vnic_id, filter);
-		if (rc)
+		if (rc) {
+			memcpy(filter->l2_addr, bp->mac_addr,
+			       ETHER_ADDR_LEN);
 			break;
+		}
 		filter->mac_index = 0;
 		RTE_LOG(DEBUG, PMD, "Set MAC addr\n");
 	}
@@ -1468,6 +1452,10 @@ bnxt_dev_set_mc_addr_list_op(struct rte_eth_dev *eth_dev,
 	}
 
 	vnic->mc_addr_cnt = i;
+	if (vnic->mc_addr_cnt)
+		vnic->flags |= BNXT_VNIC_INFO_MCAST;
+	else
+		vnic->flags &= ~BNXT_VNIC_INFO_MCAST;
 
 allmulti:
 	return bnxt_hwrm_cfa_l2_set_rx_mask(bp, vnic, 0, NULL);
@@ -1628,39 +1616,22 @@ bnxt_rx_queue_count_op(struct rte_eth_dev *dev, uint16_t rx_queue_id)
 	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_rx_queue *rxq;
 	struct rx_pkt_cmpl *rxcmp;
-	uint16_t cmp_type;
-	uint8_t cmp = 1;
-	bool valid;
 
 	rxq = dev->data->rx_queues[rx_queue_id];
 	cpr = rxq->cp_ring;
-	valid = cpr->valid;
+	raw_cons = cpr->cp_raw_cons;
 
-	while (raw_cons < rxq->nb_rx_desc) {
+	while (1) {
 		cons = RING_CMP(cpr->cp_ring_struct, raw_cons);
+		rte_prefetch0(&cpr->cp_desc_ring[cons]);
 		rxcmp = (struct rx_pkt_cmpl *)&cpr->cp_desc_ring[cons];
 
-		if (!CMPL_VALID(rxcmp, valid))
-			goto nothing_to_do;
-		valid = FLIP_VALID(cons, cpr->cp_ring_struct->ring_mask, valid);
-		cmp_type = CMP_TYPE(rxcmp);
-		if (cmp_type == RX_TPA_END_CMPL_TYPE_RX_TPA_END) {
-			cmp = (rte_le_to_cpu_32(
-					((struct rx_tpa_end_cmpl *)
-					 (rxcmp))->agg_bufs_v1) &
-			       RX_TPA_END_CMPL_AGG_BUFS_MASK) >>
-				RX_TPA_END_CMPL_AGG_BUFS_SFT;
-			desc++;
-		} else if (cmp_type == 0x11) {
-			desc++;
-			cmp = (rxcmp->agg_bufs_v1 &
-				   RX_PKT_CMPL_AGG_BUFS_MASK) >>
-				RX_PKT_CMPL_AGG_BUFS_SFT;
+		if (!CMP_VALID(rxcmp, raw_cons, cpr->cp_ring_struct)) {
+			break;
 		} else {
-			cmp = 1;
+			raw_cons++;
+			desc++;
 		}
-nothing_to_do:
-		raw_cons += cmp ? cmp : 2;
 	}
 
 	return desc;
@@ -1973,9 +1944,6 @@ parse_ntuple_filter(struct bnxt *bp,
 		return -EINVAL;
 	}
 
-	//TODO Priority
-	//nfilter->priority = (uint8_t)filter->priority;
-
 	bfilter->enables = en;
 	return 0;
 }
@@ -2342,7 +2310,6 @@ bnxt_parse_fdir_filter(struct bnxt *bp,
 		return -EINVAL;
 	}
 
-
 	if (fdir_mode == RTE_FDIR_MODE_PERFECT_MAC_VLAN) {
 		rte_memcpy(filter->dst_macaddr,
 			fdir->input.flow.mac_vlan_flow.mac_addr.addr_bytes, 6);
@@ -2846,6 +2813,13 @@ bnxt_dev_init(struct rte_eth_dev *eth_dev)
 	if (version_printed++ == 0)
 		RTE_LOG(INFO, PMD, "%s\n", bnxt_version);
 
+	eth_dev->dev_ops = &bnxt_dev_ops;
+	eth_dev->rx_pkt_burst = &bnxt_recv_pkts;
+	eth_dev->tx_pkt_burst = &bnxt_xmit_pkts;
+
+	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+		return 0;
+
 	rte_eth_copy_pci_info(eth_dev, pci_dev);
 
 	bp = eth_dev->data->dev_private;
@@ -2853,9 +2827,6 @@ bnxt_dev_init(struct rte_eth_dev *eth_dev)
 	rte_atomic64_init(&bp->rx_mbuf_alloc_fail);
 	bp->dev_stopped = 1;
 
-	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		goto skip_init;
-
 	if (bnxt_vf_pciid(pci_dev->id.device_id))
 		bp->flags |= BNXT_FLAG_VF;
 
@@ -2865,12 +2836,6 @@ bnxt_dev_init(struct rte_eth_dev *eth_dev)
 			"Board initialization failed rc: %x\n", rc);
 		goto error;
 	}
-skip_init:
-	eth_dev->dev_ops = &bnxt_dev_ops;
-	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return 0;
-	eth_dev->rx_pkt_burst = &bnxt_recv_pkts;
-	eth_dev->tx_pkt_burst = &bnxt_xmit_pkts;
 
 	if (BNXT_PF(bp) && pci_dev->id.device_id != BROADCOM_DEV_ID_NS2) {
 		snprintf(mz_name, RTE_MEMZONE_NAMESIZE,
@@ -3114,10 +3079,6 @@ bnxt_dev_uninit(struct rte_eth_dev *eth_dev) {
 		rte_free(eth_dev->data->mac_addrs);
 		eth_dev->data->mac_addrs = NULL;
 	}
-	if (bp->grp_info != NULL) {
-		rte_free(bp->grp_info);
-		bp->grp_info = NULL;
-	}
 	rc = bnxt_hwrm_func_driver_unregister(bp, 0);
 	bnxt_free_hwrm_resources(bp);
 	rte_memzone_free((const struct rte_memzone *)bp->tx_mem_zone);
diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 815bad9..0636c66 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -39,9 +39,9 @@
 #include <rte_malloc.h>
 #include <rte_memzone.h>
 #include <rte_version.h>
+#include <rte_io.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_filter.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_rxq.h"
@@ -52,10 +52,6 @@
 #include "bnxt_vnic.h"
 #include "hsi_struct_def_dpdk.h"
 
-#include <rte_io.h>
-
-#define HWRM_CMD_TIMEOUT		10000
-
 struct bnxt_plcmodes_cfg {
 	uint32_t	flags;
 	uint16_t	jumbo_thresh;
@@ -90,9 +86,9 @@ static int page_roundup(size_t size)
 
 /*
  * HWRM Functions (sent to HWRM)
- * These are named bnxt_hwrm_*() and return -1 if bnxt_hwrm_send_message()
- * fails (ie: a timeout), and a positive non-zero HWRM error code if the HWRM
- * command was failed by the ChiMP.
+ * These are named bnxt_hwrm_*() and return 0 on success or -110 if the
+ * HWRM command times out, or a negative error code if the HWRM
+ * command was failed by the FW.
  */
 
 static int bnxt_hwrm_send_message(struct bnxt *bp, void *msg,
@@ -123,9 +119,6 @@ static int bnxt_hwrm_send_message(struct bnxt *bp, void *msg,
 		data = (uint32_t *)&short_input;
 		msg_len = sizeof(short_input);
 
-		/* Sync memory write before updating doorbell */
-		rte_wmb();
-
 		max_req_len = BNXT_HWRM_SHORT_REQ_LEN;
 	}
 
@@ -145,6 +138,12 @@ static int bnxt_hwrm_send_message(struct bnxt *bp, void *msg,
 	/* Ring channel doorbell */
 	bar = (uint8_t *)bp->bar0 + 0x100;
 	rte_write32(1, bar);
+	/*
+	 * Make sure the channel doorbell ring command complete before
+	 * reading the response to avoid getting stale or invalid
+	 * responses.
+	 */
+	rte_io_mb();
 
 	/* Poll for the valid bit */
 	for (i = 0; i < HWRM_CMD_TIMEOUT; i++) {
@@ -172,11 +171,11 @@ err_ret:
 }
 
 /*
- * HWRM_PREP() should be used to prepare *ALL* HWRM commands.  It grabs the
+ * HWRM_PREP() should be used to prepare *ALL* HWRM commands. It grabs the
  * spinlock, and does initial processing.
  *
  * HWRM_CHECK_RESULT() returns errors on failure and may not be used.  It
- * releases the spinlock only if it returns.  If the regular int return codes
+ * releases the spinlock only if it returns. If the regular int return codes
  * are not used by the function, HWRM_CHECK_RESULT() should not be used
  * directly, rather it should be copied and modified to suit the function.
  *
@@ -266,20 +265,17 @@ int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp,
 	HWRM_PREP(req, CFA_L2_SET_RX_MASK);
 	req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
 
-	/* FIXME add multicast flag, when multicast adding options is supported
-	 * by ethtool.
-	 */
 	if (vnic->flags & BNXT_VNIC_INFO_BCAST)
 		mask |= HWRM_CFA_L2_SET_RX_MASK_INPUT_MASK_BCAST;
 	if (vnic->flags & BNXT_VNIC_INFO_UNTAGGED)
 		mask |= HWRM_CFA_L2_SET_RX_MASK_INPUT_MASK_VLAN_NONVLAN;
+
 	if (vnic->flags & BNXT_VNIC_INFO_PROMISC)
 		mask |= HWRM_CFA_L2_SET_RX_MASK_INPUT_MASK_PROMISCUOUS;
-	if (vnic->flags & BNXT_VNIC_INFO_ALLMULTI)
+
+	if (vnic->flags & BNXT_VNIC_INFO_ALLMULTI) {
 		mask |= HWRM_CFA_L2_SET_RX_MASK_INPUT_MASK_ALL_MCAST;
-	if (vnic->flags & BNXT_VNIC_INFO_MCAST)
-		mask |= HWRM_CFA_L2_SET_RX_MASK_INPUT_MASK_MCAST;
-	if (vnic->mc_addr_cnt) {
+	} else if (vnic->flags & BNXT_VNIC_INFO_MCAST) {
 		mask |= HWRM_CFA_L2_SET_RX_MASK_INPUT_MASK_MCAST;
 		req.num_mc_entries = rte_cpu_to_le_32(vnic->mc_addr_cnt);
 		req.mc_tbl_addr = rte_cpu_to_le_64(vnic->mc_list_dma_addr);
@@ -614,6 +610,13 @@ int bnxt_hwrm_ver_get(struct bnxt *bp)
 	fw_version |= resp->hwrm_intf_min << 8;
 	fw_version |= resp->hwrm_intf_upd;
 
+	/* def_req_timeout value is in milliseconds */
+	bp->hwrm_cmd_timeout = rte_le_to_cpu_16(resp->def_req_timeout);
+	/* convert timeout to usec */
+	bp->hwrm_cmd_timeout *= 1000;
+	if (!bp->hwrm_cmd_timeout)
+		bp->hwrm_cmd_timeout = HWRM_CMD_TIMEOUT;
+
 	if (resp->hwrm_intf_maj != HWRM_VERSION_MAJOR) {
 		RTE_LOG(ERR, PMD, "Unsupported firmware API version\n");
 		rc = -EINVAL;
@@ -1001,8 +1004,7 @@ int bnxt_hwrm_ring_grp_alloc(struct bnxt *bp, unsigned int idx)
 
 	HWRM_CHECK_RESULT();
 
-	bp->grp_info[idx].fw_grp_id =
-	    rte_le_to_cpu_16(resp->ring_group_id);
+	bp->grp_info[idx].fw_grp_id = rte_le_to_cpu_16(resp->ring_group_id);
 
 	HWRM_UNLOCK();
 
@@ -1060,8 +1062,7 @@ int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	req.update_period_ms = rte_cpu_to_le_32(0);
 
-	req.stats_dma_addr =
-	    rte_cpu_to_le_64(cpr->hw_stats_map);
+	req.stats_dma_addr = rte_cpu_to_le_64(cpr->hw_stats_map);
 
 	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req));
 
@@ -1562,10 +1563,6 @@ int bnxt_hwrm_func_clr_stats(struct bnxt *bp, uint16_t fid)
 	return rc;
 }
 
-/*
- * HWRM utility functions
- */
-
 int bnxt_clear_all_hwrm_stat_ctxs(struct bnxt *bp)
 {
 	unsigned int i;
@@ -1767,6 +1764,10 @@ int bnxt_alloc_all_hwrm_ring_grps(struct bnxt *bp)
 	return rc;
 }
 
+/*
+ * HWRM utility functions
+ */
+
 void bnxt_free_hwrm_resources(struct bnxt *bp)
 {
 	/* Release memzone */
@@ -1815,8 +1816,6 @@ int bnxt_clear_hwrm_vnic_filters(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 		else
 			rc = bnxt_hwrm_clear_l2_filter(bp, filter);
 		STAILQ_REMOVE(&vnic->filter, filter, bnxt_filter_info, next);
-		//if (rc)
-			//break;
 	}
 	return rc;
 }
@@ -1840,8 +1839,6 @@ bnxt_clear_hwrm_vnic_flows(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 
 		STAILQ_REMOVE(&vnic->flow_list, flow, rte_flow, next);
 		rte_free(flow);
-		//if (rc)
-			//break;
 	}
 	return rc;
 }
@@ -2933,7 +2930,6 @@ int bnxt_hwrm_ctx_qstats(struct bnxt *bp, uint32_t cid, int idx,
 		stats->q_errors[idx] += rte_le_to_cpu_64(resp->tx_err_pkts);
 	}
 
-
 	HWRM_UNLOCK();
 
 	return rc;
@@ -3532,7 +3528,6 @@ int bnxt_hwrm_set_ntuple_filter(struct bnxt *bp,
 	      HWRM_CFA_NTUPLE_FILTER_ALLOC_INPUT_ENABLES_DST_ID;
 	req.dst_id = rte_cpu_to_le_16(dst_id);
 
-
 	if (filter->ip_addr_type) {
 		req.ip_addr_type = filter->ip_addr_type;
 		enables |=
@@ -3545,10 +3540,6 @@ int bnxt_hwrm_set_ntuple_filter(struct bnxt *bp,
 	    HWRM_CFA_NTUPLE_FILTER_ALLOC_INPUT_ENABLES_SRC_MACADDR)
 		memcpy(req.src_macaddr, filter->src_macaddr,
 		       ETHER_ADDR_LEN);
-	//if (enables &
-	    //HWRM_CFA_NTUPLE_FILTER_ALLOC_INPUT_ENABLES_DST_MACADDR)
-		//memcpy(req.dst_macaddr, filter->dst_macaddr,
-		       //ETHER_ADDR_LEN);
 	if (enables &
 	    HWRM_CFA_NTUPLE_FILTER_ALLOC_INPUT_ENABLES_ETHERTYPE)
 		req.ethertype = rte_cpu_to_be_16(filter->ethertype);
diff --git a/drivers/net/bnxt/bnxt_irq.c b/drivers/net/bnxt/bnxt_irq.c
index 49436cf..7d69505 100644
--- a/drivers/net/bnxt/bnxt_irq.c
+++ b/drivers/net/bnxt/bnxt_irq.c
@@ -36,7 +36,6 @@
 #include <rte_malloc.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_irq.h"
 #include "bnxt_ring.h"
 #include "hsi_struct_def_dpdk.h"
@@ -45,7 +44,7 @@
  * Interrupts
  */
 
-static void bnxt_int_handler(void *param)
+void bnxt_int_handler(void *param)
 {
 	struct rte_eth_dev *eth_dev = (struct rte_eth_dev *)param;
 	struct bnxt *bp = (struct bnxt *)eth_dev->data->dev_private;
diff --git a/drivers/net/bnxt/bnxt_irq.h b/drivers/net/bnxt/bnxt_irq.h
index 4d2f7af..3162217 100644
--- a/drivers/net/bnxt/bnxt_irq.h
+++ b/drivers/net/bnxt/bnxt_irq.h
@@ -50,5 +50,6 @@ void bnxt_disable_int(struct bnxt *bp);
 void bnxt_enable_int(struct bnxt *bp);
 int bnxt_setup_int(struct bnxt *bp);
 int bnxt_request_int(struct bnxt *bp);
+void bnxt_int_handler(void *param);
 
 #endif
diff --git a/drivers/net/bnxt/bnxt_ring.c b/drivers/net/bnxt/bnxt_ring.c
index 59d1035..b5527d2 100644
--- a/drivers/net/bnxt/bnxt_ring.c
+++ b/drivers/net/bnxt/bnxt_ring.c
@@ -36,7 +36,6 @@
 #include <unistd.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ring.h"
 #include "bnxt_rxq.h"
diff --git a/drivers/net/bnxt/bnxt_rxq.c b/drivers/net/bnxt/bnxt_rxq.c
index 5088e9d..b42562f 100644
--- a/drivers/net/bnxt/bnxt_rxq.c
+++ b/drivers/net/bnxt/bnxt_rxq.c
@@ -36,7 +36,6 @@
 #include <rte_malloc.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_filter.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ring.h"
@@ -372,10 +371,9 @@ bnxt_rx_queue_intr_enable_op(struct rte_eth_dev *eth_dev, uint16_t queue_id)
 
 	if (eth_dev->data->rx_queues) {
 		rxq = eth_dev->data->rx_queues[queue_id];
-		if (!rxq) {
-			rc = -EINVAL;
-			return rc;
-		}
+		if (!rxq)
+			return -EINVAL;
+
 		cpr = rxq->cp_ring;
 		B_CP_DB_ARM(cpr);
 	}
@@ -391,10 +389,9 @@ bnxt_rx_queue_intr_disable_op(struct rte_eth_dev *eth_dev, uint16_t queue_id)
 
 	if (eth_dev->data->rx_queues) {
 		rxq = eth_dev->data->rx_queues[queue_id];
-		if (!rxq) {
-			rc = -EINVAL;
-			return rc;
-		}
+		if (!rxq)
+			return -EINVAL;
+
 		cpr = rxq->cp_ring;
 		B_CP_DB_DISARM(cpr);
 	}
diff --git a/drivers/net/bnxt/bnxt_rxr.c b/drivers/net/bnxt/bnxt_rxr.c
index 4aaad35..6f91675 100644
--- a/drivers/net/bnxt/bnxt_rxr.c
+++ b/drivers/net/bnxt/bnxt_rxr.c
@@ -40,7 +40,6 @@
 #include <rte_memory.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_ring.h"
 #include "bnxt_rxr.h"
 #include "bnxt_rxq.h"
@@ -88,18 +87,22 @@ static inline int bnxt_alloc_ag_data(struct bnxt_rx_queue *rxq,
 	struct bnxt_sw_rx_bd *rx_buf = &rxr->ag_buf_ring[prod];
 	struct rte_mbuf *data;
 
+	if (rxbd == NULL) {
+		RTE_LOG(ERR, PMD, "Jumbo Frame. rxbd is NULL\n");
+		return -EINVAL;
+	}
+
+	if (rx_buf == NULL) {
+		RTE_LOG(ERR, PMD, "Jumbo Frame. rx_buf is NULL\n");
+		return -EINVAL;
+	}
+
 	data = __bnxt_alloc_rx_data(rxq->mb_pool);
 	if (!data) {
 		rte_atomic64_inc(&rxq->bp->rx_mbuf_alloc_fail);
 		return -ENOMEM;
 	}
 
-	if (rxbd == NULL)
-		RTE_LOG(ERR, PMD, "Jumbo Frame. rxbd is NULL\n");
-	if (rx_buf == NULL)
-		RTE_LOG(ERR, PMD, "Jumbo Frame. rx_buf is NULL\n");
-
-
 	rx_buf->mbuf = data;
 
 	rxbd->addr = rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR(rx_buf->mbuf));
diff --git a/drivers/net/bnxt/bnxt_stats.c b/drivers/net/bnxt/bnxt_stats.c
index f8bb4ed..46a3db8 100644
--- a/drivers/net/bnxt/bnxt_stats.c
+++ b/drivers/net/bnxt/bnxt_stats.c
@@ -108,6 +108,22 @@ static const struct bnxt_xstats_name_off bnxt_rx_stats_strings[] = {
 				rx_runt_bytes)},
 	{"rx_runt_frames", offsetof(struct rx_port_stats,
 				rx_runt_frames)},
+	{"rx_pfc_ena_frames_pri0", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri0)},
+	{"rx_pfc_ena_frames_pri1", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri1)},
+	{"rx_pfc_ena_frames_pri2", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri2)},
+	{"rx_pfc_ena_frames_pri3", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri3)},
+	{"rx_pfc_ena_frames_pri4", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri4)},
+	{"rx_pfc_ena_frames_pri5", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri5)},
+	{"rx_pfc_ena_frames_pri6", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri6)},
+	{"rx_pfc_ena_frames_pri7", offsetof(struct rx_port_stats,
+				rx_pfc_ena_frames_pri7)},
 };
 
 static const struct bnxt_xstats_name_off bnxt_tx_stats_strings[] = {
@@ -163,6 +179,22 @@ static const struct bnxt_xstats_name_off bnxt_tx_stats_strings[] = {
 				tx_total_collisions)},
 	{"tx_bytes", offsetof(struct tx_port_stats,
 				tx_bytes)},
+	{"tx_pfc_ena_frames_pri0", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri0)},
+	{"tx_pfc_ena_frames_pri1", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri1)},
+	{"tx_pfc_ena_frames_pri2", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri2)},
+	{"tx_pfc_ena_frames_pri3", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri3)},
+	{"tx_pfc_ena_frames_pri4", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri4)},
+	{"tx_pfc_ena_frames_pri5", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri5)},
+	{"tx_pfc_ena_frames_pri6", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri6)},
+	{"tx_pfc_ena_frames_pri7", offsetof(struct tx_port_stats,
+				tx_pfc_ena_frames_pri7)},
 };
 
 static const struct bnxt_xstats_name_off bnxt_func_stats_strings[] = {
@@ -284,6 +316,9 @@ int bnxt_dev_xstats_get_op(struct rte_eth_dev *eth_dev,
 		return 0;
 	}
 
+	if (xstats == NULL)
+		return 0;
+
 	bnxt_hwrm_port_qstats(bp);
 	bnxt_hwrm_func_qstats_tx_drop(bp, 0xffff, &tx_drop_pkts);
 
diff --git a/drivers/net/bnxt/bnxt_txq.c b/drivers/net/bnxt/bnxt_txq.c
index 99ddddd..f0098c3 100644
--- a/drivers/net/bnxt/bnxt_txq.c
+++ b/drivers/net/bnxt/bnxt_txq.c
@@ -36,7 +36,6 @@
 #include <rte_malloc.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_ring.h"
 #include "bnxt_txq.h"
 #include "bnxt_txr.h"
@@ -62,7 +61,7 @@ static void bnxt_tx_queue_release_mbufs(struct bnxt_tx_queue *txq)
 	if (sw_ring) {
 		for (i = 0; i < txq->tx_ring->tx_ring_struct->ring_size; i++) {
 			if (sw_ring[i].mbuf) {
-				rte_pktmbuf_free(sw_ring[i].mbuf);
+				rte_pktmbuf_free_seg(sw_ring[i].mbuf);
 				sw_ring[i].mbuf = NULL;
 			}
 		}
diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
index e558413..abb705c 100644
--- a/drivers/net/bnxt/bnxt_txr.c
+++ b/drivers/net/bnxt/bnxt_txr.c
@@ -37,7 +37,6 @@
 #include <rte_malloc.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_ring.h"
 #include "bnxt_txq.h"
 #include "bnxt_txr.h"
diff --git a/drivers/net/bonding/rte_eth_bond_8023ad.c b/drivers/net/bonding/rte_eth_bond_8023ad.c
index 14b82bb..d369576 100644
--- a/drivers/net/bonding/rte_eth_bond_8023ad.c
+++ b/drivers/net/bonding/rte_eth_bond_8023ad.c
@@ -659,7 +659,7 @@ tx_machine(struct bond_dev_private *internals, uint16_t slave_id)
 	SM_FLAG_CLR(port, NTT);
 }
 
-static uint8_t
+static uint16_t
 max_index(uint64_t *a, int n)
 {
 	if (n <= 0)
@@ -690,11 +690,11 @@ selection_logic(struct bond_dev_private *internals, uint8_t slave_id)
 	struct port *agg, *port;
 	uint16_t slaves_count, new_agg_id, i, j = 0;
 	uint16_t *slaves;
-	uint64_t agg_bandwidth[8] = {0};
-	uint64_t agg_count[8] = {0};
+	uint64_t agg_bandwidth[RTE_MAX_ETHPORTS] = {0};
+	uint64_t agg_count[RTE_MAX_ETHPORTS] = {0};
 	uint16_t default_slave = 0;
-	uint8_t mode_count_id, mode_band_id;
 	struct rte_eth_link link_info;
+	uint16_t agg_new_idx = 0;
 
 	slaves = internals->active_slaves;
 	slaves_count = internals->active_slave_count;
@@ -707,9 +707,9 @@ selection_logic(struct bond_dev_private *internals, uint8_t slave_id)
 		if (agg->aggregator_port_id != slaves[i])
 			continue;
 
-		agg_count[agg->aggregator_port_id] += 1;
+		agg_count[i] += 1;
 		rte_eth_link_get_nowait(slaves[i], &link_info);
-		agg_bandwidth[agg->aggregator_port_id] += link_info.link_speed;
+		agg_bandwidth[i] += link_info.link_speed;
 
 		/* Actors system ID is not checked since all slave device have the same
 		 * ID (MAC address). */
@@ -729,24 +729,22 @@ selection_logic(struct bond_dev_private *internals, uint8_t slave_id)
 
 	switch (internals->mode4.agg_selection) {
 	case AGG_COUNT:
-		mode_count_id = max_index(
-				(uint64_t *)agg_count, slaves_count);
-		new_agg_id = mode_count_id;
+		agg_new_idx = max_index(agg_count, slaves_count);
+		new_agg_id = slaves[agg_new_idx];
 		break;
 	case AGG_BANDWIDTH:
-		mode_band_id = max_index(
-				(uint64_t *)agg_bandwidth, slaves_count);
-		new_agg_id = mode_band_id;
+		agg_new_idx = max_index(agg_bandwidth, slaves_count);
+		new_agg_id = slaves[agg_new_idx];
 		break;
 	case AGG_STABLE:
 		if (default_slave == slaves_count)
-			new_agg_id = slave_id;
+			new_agg_id = slaves[slave_id];
 		else
 			new_agg_id = slaves[default_slave];
 		break;
 	default:
 		if (default_slave == slaves_count)
-			new_agg_id = slave_id;
+			new_agg_id = slaves[slave_id];
 		else
 			new_agg_id = slaves[default_slave];
 		break;
@@ -1322,11 +1320,12 @@ rte_eth_bond_8023ad_agg_selection_set(uint16_t port_id,
 	struct bond_dev_private *internals;
 	struct mode8023ad_private *mode4;
 
+	if (valid_bonded_port_id(port_id) != 0)
+		return -EINVAL;
+
 	bond_dev = &rte_eth_devices[port_id];
 	internals = bond_dev->data->dev_private;
 
-	if (valid_bonded_port_id(port_id) != 0)
-		return -EINVAL;
 	if (internals->mode != 4)
 		return -EINVAL;
 
@@ -1343,11 +1342,12 @@ int rte_eth_bond_8023ad_agg_selection_get(uint16_t port_id)
 	struct bond_dev_private *internals;
 	struct mode8023ad_private *mode4;
 
+	if (valid_bonded_port_id(port_id) != 0)
+		return -EINVAL;
+
 	bond_dev = &rte_eth_devices[port_id];
 	internals = bond_dev->data->dev_private;
 
-	if (valid_bonded_port_id(port_id) != 0)
-		return -EINVAL;
 	if (internals->mode != 4)
 		return -EINVAL;
 	mode4 = &internals->mode4;
@@ -1600,9 +1600,14 @@ int
 rte_eth_bond_8023ad_dedicated_queues_enable(uint16_t port)
 {
 	int retval = 0;
-	struct rte_eth_dev *dev = &rte_eth_devices[port];
-	struct bond_dev_private *internals = (struct bond_dev_private *)
-		dev->data->dev_private;
+	struct rte_eth_dev *dev;
+	struct bond_dev_private *internals;
+
+	if (valid_bonded_port_id(port) != 0)
+		return -EINVAL;
+
+	dev = &rte_eth_devices[port];
+	internals = dev->data->dev_private;
 
 	if (check_for_bonded_ethdev(dev) != 0)
 		return -1;
@@ -1624,9 +1629,14 @@ int
 rte_eth_bond_8023ad_dedicated_queues_disable(uint16_t port)
 {
 	int retval = 0;
-	struct rte_eth_dev *dev = &rte_eth_devices[port];
-	struct bond_dev_private *internals = (struct bond_dev_private *)
-		dev->data->dev_private;
+	struct rte_eth_dev *dev;
+	struct bond_dev_private *internals;
+
+	if (valid_bonded_port_id(port) != 0)
+		return -EINVAL;
+
+	dev = &rte_eth_devices[port];
+	internals = dev->data->dev_private;
 
 	if (check_for_bonded_ethdev(dev) != 0)
 		return -1;
diff --git a/drivers/net/bonding/rte_eth_bond_args.c b/drivers/net/bonding/rte_eth_bond_args.c
index 8c94cc6..e543f53 100644
--- a/drivers/net/bonding/rte_eth_bond_args.c
+++ b/drivers/net/bonding/rte_eth_bond_args.c
@@ -92,11 +92,10 @@ find_port_id_by_dev_name(const char *name)
 static inline int
 bond_pci_addr_cmp(const struct rte_device *dev, const void *_pci_addr)
 {
-	struct rte_pci_device *pdev;
+	const struct rte_pci_device *pdev = RTE_DEV_TO_PCI_CONST(dev);
 	const struct rte_pci_addr *paddr = _pci_addr;
 
-	pdev = RTE_DEV_TO_PCI(*(struct rte_device **)(void *)&dev);
-	return rte_eal_compare_pci_addr(&pdev->addr, paddr);
+	return rte_pci_addr_cmp(&pdev->addr, paddr);
 }
 
 /**
diff --git a/drivers/net/bonding/rte_eth_bond_pmd.c b/drivers/net/bonding/rte_eth_bond_pmd.c
index 9694cfb..b58873a 100644
--- a/drivers/net/bonding/rte_eth_bond_pmd.c
+++ b/drivers/net/bonding/rte_eth_bond_pmd.c
@@ -31,6 +31,7 @@
  *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include <stdlib.h>
+#include <stdbool.h>
 #include <netinet/in.h>
 
 #include <rte_mbuf.h>
@@ -283,45 +284,6 @@ bond_ethdev_8023ad_flow_set(struct rte_eth_dev *bond_dev, uint16_t slave_port) {
 }
 
 static uint16_t
-bond_ethdev_rx_burst_8023ad_fast_queue(void *queue, struct rte_mbuf **bufs,
-		uint16_t nb_pkts)
-{
-	struct bond_rx_queue *bd_rx_q = (struct bond_rx_queue *)queue;
-	struct bond_dev_private *internals = bd_rx_q->dev_private;
-	uint16_t num_rx_total = 0;	/* Total number of received packets */
-	uint16_t slaves[RTE_MAX_ETHPORTS];
-	uint16_t slave_count;
-	uint16_t active_slave;
-	uint16_t i;
-
-	/* Copy slave list to protect against slave up/down changes during tx
-	 * bursting */
-	slave_count = internals->active_slave_count;
-	active_slave = internals->active_slave;
-	memcpy(slaves, internals->active_slaves,
-			sizeof(internals->active_slaves[0]) * slave_count);
-
-	for (i = 0; i < slave_count && nb_pkts; i++) {
-		uint16_t num_rx_slave;
-
-		/* Read packets from this slave */
-		num_rx_slave = rte_eth_rx_burst(slaves[active_slave],
-						bd_rx_q->queue_id,
-						bufs + num_rx_total, nb_pkts);
-		num_rx_total += num_rx_slave;
-		nb_pkts -= num_rx_slave;
-
-		if (++active_slave == slave_count)
-			active_slave = 0;
-	}
-
-	if (++internals->active_slave >= slave_count)
-		internals->active_slave = 0;
-
-	return num_rx_total;
-}
-
-static uint16_t
 bond_ethdev_tx_burst_8023ad_fast_queue(void *queue, struct rte_mbuf **bufs,
 		uint16_t nb_pkts)
 {
@@ -406,10 +368,9 @@ bond_ethdev_tx_burst_8023ad_fast_queue(void *queue, struct rte_mbuf **bufs,
 	return num_tx_total;
 }
 
-
-static uint16_t
-bond_ethdev_rx_burst_8023ad(void *queue, struct rte_mbuf **bufs,
-		uint16_t nb_pkts)
+static inline uint16_t
+rx_burst_8023ad(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts,
+		bool dedicated_rxq)
 {
 	/* Cast to structure, containing bonded device's port id and queue id */
 	struct bond_rx_queue *bd_rx_q = (struct bond_rx_queue *)queue;
@@ -454,23 +415,22 @@ bond_ethdev_rx_burst_8023ad(void *queue, struct rte_mbuf **bufs,
 
 		/* Handle slow protocol packets. */
 		while (j < num_rx_total) {
-
-			/* If packet is not pure L2 and is known, skip it */
-			if ((bufs[j]->packet_type & ~RTE_PTYPE_L2_ETHER) != 0) {
-				j++;
-				continue;
-			}
-
 			if (j + 3 < num_rx_total)
 				rte_prefetch0(rte_pktmbuf_mtod(bufs[j + 3], void *));
 
 			hdr = rte_pktmbuf_mtod(bufs[j], struct ether_hdr *);
 			subtype = ((struct slow_protocol_frame *)hdr)->slow_protocol.subtype;
 
-			/* Remove packet from array if it is slow packet or slave is not
-			 * in collecting state or bonding interface is not in promiscuous
-			 * mode and packet address does not match. */
-			if (unlikely(is_lacp_packets(hdr->ether_type, subtype, bufs[j]) ||
+			/* Remove packet from array if:
+			 * - it is slow packet but no dedicated rxq is present,
+			 * - slave is not in collecting state,
+			 * - bonding interface is not in promiscuous mode and
+			 *   packet is not multicast and address does not match,
+			 */
+			if (unlikely(
+				(!dedicated_rxq &&
+				 is_lacp_packets(hdr->ether_type, subtype,
+						 bufs[j])) ||
 				!collecting || (!promisc &&
 					!is_multicast_ether_addr(&hdr->d_addr) &&
 					!is_same_ether_addr(&bond_mac, &hdr->d_addr)))) {
@@ -500,6 +460,20 @@ bond_ethdev_rx_burst_8023ad(void *queue, struct rte_mbuf **bufs,
 	return num_rx_total;
 }
 
+static uint16_t
+bond_ethdev_rx_burst_8023ad(void *queue, struct rte_mbuf **bufs,
+		uint16_t nb_pkts)
+{
+	return rx_burst_8023ad(queue, bufs, nb_pkts, false);
+}
+
+static uint16_t
+bond_ethdev_rx_burst_8023ad_fast_queue(void *queue, struct rte_mbuf **bufs,
+		uint16_t nb_pkts)
+{
+	return rx_burst_8023ad(queue, bufs, nb_pkts, true);
+}
+
 #if defined(RTE_LIBRTE_BOND_DEBUG_ALB) || defined(RTE_LIBRTE_BOND_DEBUG_ALB_L1)
 uint32_t burstnumberRX;
 uint32_t burstnumberTX;
@@ -2352,8 +2326,8 @@ bond_ethdev_link_update(struct rte_eth_dev *ethdev, int wait_to_complete)
 		 * packet loss will occur on this slave if transmission at rates
 		 * greater than this are attempted
 		 */
-		for (idx = 1; idx < bond_ctx->active_slave_count; idx++) {
-			link_update(bond_ctx->active_slaves[0],	&slave_link);
+		for (idx = 0; idx < bond_ctx->active_slave_count; idx++) {
+			link_update(bond_ctx->active_slaves[idx], &slave_link);
 
 			if (slave_link.link_speed <
 					ethdev->data->dev_link.link_speed)
diff --git a/drivers/net/cxgbe/cxgbe_ethdev.c b/drivers/net/cxgbe/cxgbe_ethdev.c
index dc153c7..8b5b9b4 100644
--- a/drivers/net/cxgbe/cxgbe_ethdev.c
+++ b/drivers/net/cxgbe/cxgbe_ethdev.c
@@ -91,6 +91,7 @@ static uint16_t cxgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 	struct sge_eth_txq *txq = (struct sge_eth_txq *)tx_queue;
 	uint16_t pkts_sent, pkts_remain;
 	uint16_t total_sent = 0;
+	uint16_t idx = 0;
 	int ret = 0;
 
 	CXGBE_DEBUG_TX(adapter, "%s: txq = %p; tx_pkts = %p; nb_pkts = %d\n",
@@ -99,12 +100,16 @@ static uint16_t cxgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 	t4_os_lock(&txq->txq_lock);
 	/* free up desc from already completed tx */
 	reclaim_completed_tx(&txq->q);
+	rte_prefetch0(rte_pktmbuf_mtod(tx_pkts[0], volatile void *));
 	while (total_sent < nb_pkts) {
 		pkts_remain = nb_pkts - total_sent;
 
 		for (pkts_sent = 0; pkts_sent < pkts_remain; pkts_sent++) {
-			ret = t4_eth_xmit(txq, tx_pkts[total_sent + pkts_sent],
-					  nb_pkts);
+			idx = total_sent + pkts_sent;
+			if ((idx + 1) < nb_pkts)
+				rte_prefetch0(rte_pktmbuf_mtod(tx_pkts[idx + 1],
+							volatile void *));
+			ret = t4_eth_xmit(txq, tx_pkts[idx], nb_pkts);
 			if (ret < 0)
 				break;
 		}
diff --git a/drivers/net/cxgbe/sge.c b/drivers/net/cxgbe/sge.c
index babff0b..9dddea5 100644
--- a/drivers/net/cxgbe/sge.c
+++ b/drivers/net/cxgbe/sge.c
@@ -1130,7 +1130,6 @@ out_free:
 				txq->stats.mapping_err++;
 				goto out_free;
 			}
-			rte_prefetch0((volatile void *)addr);
 			return tx_do_packet_coalesce(txq, mbuf, cflits, adap,
 						     pi, addr, nb_pkts);
 		} else {
diff --git a/drivers/net/dpaa2/dpaa2_rxtx.c b/drivers/net/dpaa2/dpaa2_rxtx.c
index 8ecd238..4459424 100644
--- a/drivers/net/dpaa2/dpaa2_rxtx.c
+++ b/drivers/net/dpaa2/dpaa2_rxtx.c
@@ -132,7 +132,8 @@ dpaa2_dev_rx_offload(uint64_t hw_annot_addr, struct rte_mbuf *mbuf)
 }
 
 static inline struct rte_mbuf *__attribute__((hot))
-eth_sg_fd_to_mbuf(const struct qbman_fd *fd)
+eth_sg_fd_to_mbuf(const struct qbman_fd *fd,
+		  int port_id)
 {
 	struct qbman_sge *sgt, *sge;
 	dma_addr_t sg_addr;
@@ -159,6 +160,7 @@ eth_sg_fd_to_mbuf(const struct qbman_fd *fd)
 	first_seg->pkt_len = DPAA2_GET_FD_LEN(fd);
 	first_seg->nb_segs = 1;
 	first_seg->next = NULL;
+	first_seg->port = port_id;
 
 	first_seg->packet_type = dpaa2_dev_rx_parse(
 			 (uint64_t)DPAA2_IOVA_TO_VADDR(DPAA2_GET_FD_ADDR(fd))
@@ -192,7 +194,8 @@ eth_sg_fd_to_mbuf(const struct qbman_fd *fd)
 }
 
 static inline struct rte_mbuf *__attribute__((hot))
-eth_fd_to_mbuf(const struct qbman_fd *fd)
+eth_fd_to_mbuf(const struct qbman_fd *fd,
+	       int port_id)
 {
 	struct rte_mbuf *mbuf = DPAA2_INLINE_MBUF_FROM_BUF(
 		DPAA2_IOVA_TO_VADDR(DPAA2_GET_FD_ADDR(fd)),
@@ -206,6 +209,7 @@ eth_fd_to_mbuf(const struct qbman_fd *fd)
 	mbuf->data_off = DPAA2_GET_FD_OFFSET(fd);
 	mbuf->data_len = DPAA2_GET_FD_LEN(fd);
 	mbuf->pkt_len = mbuf->data_len;
+	mbuf->port = port_id;
 
 	/* Parse the packet */
 	/* parse results are after the private - sw annotation area */
@@ -470,10 +474,9 @@ dpaa2_dev_prefetch_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 				+ DPAA2_FD_PTA_SIZE + 16));
 
 		if (unlikely(DPAA2_FD_GET_FORMAT(fd[num_rx]) == qbman_fd_sg))
-			bufs[num_rx] = eth_sg_fd_to_mbuf(fd[num_rx]);
+			bufs[num_rx] = eth_sg_fd_to_mbuf(fd[num_rx], eth_data->port_id);
 		else
-			bufs[num_rx] = eth_fd_to_mbuf(fd[num_rx]);
-		bufs[num_rx]->port = dev->data->port_id;
+			bufs[num_rx] = eth_fd_to_mbuf(fd[num_rx], eth_data->port_id);
 
 		if (dev->data->dev_conf.rxmode.hw_vlan_strip)
 			rte_vlan_strip(bufs[num_rx]);
@@ -521,7 +524,7 @@ dpaa2_dev_process_parallel_event(struct qbman_swp *swp,
 				 struct dpaa2_queue *rxq,
 				 struct rte_event *ev)
 {
-	ev->mbuf = eth_fd_to_mbuf(fd);
+	ev->mbuf = eth_fd_to_mbuf(fd, rxq->eth_data->port_id);
 
 	ev->flow_id = rxq->ev.flow_id;
 	ev->sub_event_type = rxq->ev.sub_event_type;
@@ -633,15 +636,28 @@ dpaa2_dev_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 			}
 			bufs++;
 		}
+
 		loop = 0;
+		retry_count = 0;
 		while (loop < frames_to_send) {
-			loop += qbman_swp_enqueue_multiple(swp, &eqdesc,
+			ret = qbman_swp_enqueue_multiple(swp, &eqdesc,
 					&fd_arr[loop], frames_to_send - loop);
+			if (unlikely(ret < 0)) {
+				retry_count++;
+				if (retry_count > DPAA2_MAX_TX_RETRY_COUNT) {
+					num_tx += loop;
+					nb_pkts -= loop;
+					goto send_n_return;
+				}
+			} else {
+				loop += ret;
+				retry_count = 0;
+			}
 		}
 
-		num_tx += frames_to_send;
-		dpaa2_q->tx_pkts += frames_to_send;
-		nb_pkts -= frames_to_send;
+		num_tx += loop;
+		dpaa2_q->tx_pkts += loop;
+		nb_pkts -= loop;
 	}
 	return num_tx;
 
@@ -650,12 +666,21 @@ send_n_return:
 	if (loop) {
 		unsigned int i = 0;
 
+		retry_count = 0;
 		while (i < loop) {
-			i += qbman_swp_enqueue_multiple(swp, &eqdesc,
+			ret = qbman_swp_enqueue_multiple(swp, &eqdesc,
 							&fd_arr[i], loop - i);
+			if (unlikely(ret < 0)) {
+				retry_count++;
+				if (retry_count > DPAA2_MAX_TX_RETRY_COUNT)
+					break;
+			} else {
+				i += ret;
+				retry_count = 0;
+			}
 		}
-		num_tx += loop;
-		dpaa2_q->tx_pkts += loop;
+		num_tx += i;
+		dpaa2_q->tx_pkts += i;
 	}
 skip_tx:
 	return num_tx;
diff --git a/drivers/net/dpaa2/mc/dpkg.c b/drivers/net/dpaa2/mc/dpkg.c
index 3f98907..34d37bf 100644
--- a/drivers/net/dpaa2/mc/dpkg.c
+++ b/drivers/net/dpaa2/mc/dpkg.c
@@ -96,7 +96,10 @@ dpkg_prepare_key_cfg(const struct dpkg_profile_cfg *cfg, uint8_t *key_cfg_buf)
 		dpkg_set_field(extr->extract_type, EXTRACT_TYPE,
 			       cfg->extracts[i].type);
 
-		for (j = 0; j < DPKG_NUM_OF_MASKS; j++) {
+		if (extr->num_of_byte_masks > DPKG_NUM_OF_MASKS)
+			return -EINVAL;
+
+		for (j = 0; j < extr->num_of_byte_masks; j++) {
 			extr->masks[j].mask = cfg->extracts[i].masks[j].mask;
 			extr->masks[j].offset =
 				cfg->extracts[i].masks[j].offset;
diff --git a/drivers/net/e1000/e1000_ethdev.h b/drivers/net/e1000/e1000_ethdev.h
index 5668910..70a4798 100644
--- a/drivers/net/e1000/e1000_ethdev.h
+++ b/drivers/net/e1000/e1000_ethdev.h
@@ -350,15 +350,15 @@ struct igb_flow_mem {
 };
 
 TAILQ_HEAD(igb_ntuple_filter_list, igb_ntuple_filter_ele);
-struct igb_ntuple_filter_list igb_filter_ntuple_list;
+extern struct igb_ntuple_filter_list igb_filter_ntuple_list;
 TAILQ_HEAD(igb_ethertype_filter_list, igb_ethertype_filter_ele);
-struct igb_ethertype_filter_list igb_filter_ethertype_list;
+extern struct igb_ethertype_filter_list igb_filter_ethertype_list;
 TAILQ_HEAD(igb_syn_filter_list, igb_eth_syn_filter_ele);
-struct igb_syn_filter_list igb_filter_syn_list;
+extern struct igb_syn_filter_list igb_filter_syn_list;
 TAILQ_HEAD(igb_flex_filter_list, igb_flex_filter_ele);
-struct igb_flex_filter_list igb_filter_flex_list;
+extern struct igb_flex_filter_list igb_filter_flex_list;
 TAILQ_HEAD(igb_flow_mem_list, igb_flow_mem);
-struct igb_flow_mem_list igb_flow_list;
+extern struct igb_flow_mem_list igb_flow_list;
 
 extern const struct rte_flow_ops igb_flow_ops;
 
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_ethdev.c
index 4378f08..daf9d2f 100644
--- a/drivers/net/e1000/igb_ethdev.c
+++ b/drivers/net/e1000/igb_ethdev.c
@@ -956,6 +956,8 @@ eth_igb_dev_init(struct rte_eth_dev *eth_dev)
 	/* enable support intr */
 	igb_intr_enable(eth_dev);
 
+	eth_igb_dev_set_link_down(eth_dev);
+
 	/* initialize filter info */
 	memset(filter_info, 0,
 	       sizeof(struct e1000_filter_info));
@@ -1557,8 +1559,9 @@ eth_igb_stop(struct rte_eth_dev *dev)
 	igb_pf_reset_hw(hw);
 	E1000_WRITE_REG(hw, E1000_WUC, 0);
 
-	/* Set bit for Go Link disconnect */
-	if (hw->mac.type >= e1000_82580) {
+	/* Set bit for Go Link disconnect if PHY reset is not blocked */
+	if (hw->mac.type >= e1000_82580 &&
+	    (e1000_check_reset_block(hw) != E1000_BLK_PHY_RESET)) {
 		uint32_t phpm_reg;
 
 		phpm_reg = E1000_READ_REG(hw, E1000_82580_PHY_POWER_MGMT);
@@ -1632,8 +1635,9 @@ eth_igb_close(struct rte_eth_dev *dev)
 	igb_release_manageability(hw);
 	igb_hw_control_release(hw);
 
-	/* Clear bit for Go Link disconnect */
-	if (hw->mac.type >= e1000_82580) {
+	/* Clear bit for Go Link disconnect if PHY reset is not blocked */
+	if (hw->mac.type >= e1000_82580 &&
+	    (e1000_check_reset_block(hw) != E1000_BLK_PHY_RESET)) {
 		uint32_t phpm_reg;
 
 		phpm_reg = E1000_READ_REG(hw, E1000_82580_PHY_POWER_MGMT);
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index 057579b..894f8a1 100644
--- a/drivers/net/e1000/igb_flow.c
+++ b/drivers/net/e1000/igb_flow.c
@@ -78,6 +78,12 @@
 
 #define	IGB_FLEX_RAW_NUM	12
 
+struct igb_flow_mem_list igb_flow_list;
+struct igb_ntuple_filter_list igb_filter_ntuple_list;
+struct igb_ethertype_filter_list igb_filter_ethertype_list;
+struct igb_syn_filter_list igb_filter_syn_list;
+struct igb_flex_filter_list igb_filter_flex_list;
+
 /**
  * Please aware there's an asumption for all the parsers.
  * rte_flow_item is using big endian, rte_flow_attr and
diff --git a/drivers/net/fm10k/base/fm10k_api.c b/drivers/net/fm10k/base/fm10k_api.c
index c49d20d..e7b2fe7 100644
--- a/drivers/net/fm10k/base/fm10k_api.c
+++ b/drivers/net/fm10k/base/fm10k_api.c
@@ -234,8 +234,14 @@ s32 fm10k_read_mac_addr(struct fm10k_hw *hw)
  * */
 void fm10k_update_hw_stats(struct fm10k_hw *hw, struct fm10k_hw_stats *stats)
 {
-	if (hw->mac.ops.update_hw_stats)
-		hw->mac.ops.update_hw_stats(hw, stats);
+	switch (hw->mac.type) {
+	case fm10k_mac_pf:
+		return fm10k_update_hw_stats_pf(hw, stats);
+	case fm10k_mac_vf:
+		return fm10k_update_hw_stats_vf(hw, stats);
+	default:
+		break;
+	}
 }
 
 /**
@@ -246,8 +252,14 @@ void fm10k_update_hw_stats(struct fm10k_hw *hw, struct fm10k_hw_stats *stats)
  * */
 void fm10k_rebind_hw_stats(struct fm10k_hw *hw, struct fm10k_hw_stats *stats)
 {
-	if (hw->mac.ops.rebind_hw_stats)
-		hw->mac.ops.rebind_hw_stats(hw, stats);
+	switch (hw->mac.type) {
+	case fm10k_mac_pf:
+		return fm10k_rebind_hw_stats_pf(hw, stats);
+	case fm10k_mac_vf:
+		return fm10k_rebind_hw_stats_vf(hw, stats);
+	default:
+		break;
+	}
 }
 
 /**
diff --git a/drivers/net/fm10k/base/fm10k_pf.c b/drivers/net/fm10k/base/fm10k_pf.c
index db5f491..f5b6a9e 100644
--- a/drivers/net/fm10k/base/fm10k_pf.c
+++ b/drivers/net/fm10k/base/fm10k_pf.c
@@ -1511,7 +1511,7 @@ const struct fm10k_msg_data fm10k_iov_msg_data_pf[] = {
  *  This function collects and aggregates global and per queue hardware
  *  statistics.
  **/
-STATIC void fm10k_update_hw_stats_pf(struct fm10k_hw *hw,
+void fm10k_update_hw_stats_pf(struct fm10k_hw *hw,
 				     struct fm10k_hw_stats *stats)
 {
 	u32 timeout, ur, ca, um, xec, vlan_drop, loopback_drop, nodesc_drop;
@@ -1584,7 +1584,7 @@ STATIC void fm10k_update_hw_stats_pf(struct fm10k_hw *hw,
  *  This function resets the base for global and per queue hardware
  *  statistics.
  **/
-STATIC void fm10k_rebind_hw_stats_pf(struct fm10k_hw *hw,
+void fm10k_rebind_hw_stats_pf(struct fm10k_hw *hw,
 				     struct fm10k_hw_stats *stats)
 {
 	DEBUGFUNC("fm10k_rebind_hw_stats_pf");
diff --git a/drivers/net/fm10k/base/fm10k_pf.h b/drivers/net/fm10k/base/fm10k_pf.h
index ca125c2..2c22bdd 100644
--- a/drivers/net/fm10k/base/fm10k_pf.h
+++ b/drivers/net/fm10k/base/fm10k_pf.h
@@ -184,4 +184,10 @@ extern const struct fm10k_msg_data fm10k_iov_msg_data_pf[];
 #endif
 
 s32 fm10k_init_ops_pf(struct fm10k_hw *hw);
+
+void fm10k_update_hw_stats_pf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats);
+
+void fm10k_rebind_hw_stats_pf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats);
 #endif /* _FM10K_PF_H */
diff --git a/drivers/net/fm10k/base/fm10k_vf.c b/drivers/net/fm10k/base/fm10k_vf.c
index bd44977..2f4b5f5 100644
--- a/drivers/net/fm10k/base/fm10k_vf.c
+++ b/drivers/net/fm10k/base/fm10k_vf.c
@@ -526,7 +526,7 @@ const struct fm10k_tlv_attr fm10k_1588_msg_attr[] = {
  *
  *  This function collects and aggregates per queue hardware statistics.
  **/
-STATIC void fm10k_update_hw_stats_vf(struct fm10k_hw *hw,
+void fm10k_update_hw_stats_vf(struct fm10k_hw *hw,
 				     struct fm10k_hw_stats *stats)
 {
 	DEBUGFUNC("fm10k_update_hw_stats_vf");
@@ -541,7 +541,7 @@ STATIC void fm10k_update_hw_stats_vf(struct fm10k_hw *hw,
  *
  *  This function resets the base for queue hardware statistics.
  **/
-STATIC void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw,
+void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw,
 				     struct fm10k_hw_stats *stats)
 {
 	DEBUGFUNC("fm10k_rebind_hw_stats_vf");
diff --git a/drivers/net/fm10k/base/fm10k_vf.h b/drivers/net/fm10k/base/fm10k_vf.h
index 116c56f..d4edd33 100644
--- a/drivers/net/fm10k/base/fm10k_vf.h
+++ b/drivers/net/fm10k/base/fm10k_vf.h
@@ -89,4 +89,9 @@ extern const struct fm10k_tlv_attr fm10k_1588_msg_attr[];
 	FM10K_MSG_HANDLER(FM10K_VF_MSG_ID_1588, fm10k_1588_msg_attr, func)
 
 s32 fm10k_init_ops_vf(struct fm10k_hw *hw);
+
+void fm10k_update_hw_stats_vf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats);
+void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats);
 #endif /* _FM10K_VF_H */
diff --git a/drivers/net/fm10k/fm10k_rxtx_vec.c b/drivers/net/fm10k/fm10k_rxtx_vec.c
index 1a66dc3..9e86c28 100644
--- a/drivers/net/fm10k/fm10k_rxtx_vec.c
+++ b/drivers/net/fm10k/fm10k_rxtx_vec.c
@@ -388,8 +388,15 @@ fm10k_rx_queue_release_mbufs_vec(struct fm10k_rx_queue *rxq)
 		return;
 
 	/* free all mbufs that are valid in the ring */
-	for (i = rxq->next_dd; i != rxq->rxrearm_start; i = (i + 1) & mask)
-		rte_pktmbuf_free_seg(rxq->sw_ring[i]);
+	if (rxq->rxrearm_nb == 0) {
+		for (i = 0; i < rxq->nb_desc; i++)
+			if (rxq->sw_ring[i] != NULL)
+				rte_pktmbuf_free_seg(rxq->sw_ring[i]);
+	} else {
+		for (i = rxq->next_dd; i != rxq->rxrearm_start;
+				i = (i + 1) & mask)
+			rte_pktmbuf_free_seg(rxq->sw_ring[i]);
+	}
 	rxq->rxrearm_nb = rxq->nb_desc;
 
 	/* set all entries to NULL */
diff --git a/drivers/net/i40e/i40e_ethdev_vf.c b/drivers/net/i40e/i40e_ethdev_vf.c
index b36ba9f..2830ffe 100644
--- a/drivers/net/i40e/i40e_ethdev_vf.c
+++ b/drivers/net/i40e/i40e_ethdev_vf.c
@@ -1384,7 +1384,7 @@ i40evf_handle_aq_msg(struct rte_eth_dev *dev)
 			}
 			break;
 		default:
-			PMD_DRV_LOG(ERR, "Request %u is not supported yet",
+			PMD_DRV_LOG(DEBUG, "Request %u is not supported yet",
 				    aq_opc);
 			break;
 		}
diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index b5685e2..4b77e8c 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -314,7 +314,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load 4 pkts desc */
 		descs[3] =  vld1q_u64((uint64_t *)(rxdp + 3));
-		rte_rmb();
 
 		/* B.2 copy 2 mbuf point into rx_pkts  */
 		vst1q_u64((uint64_t *)&rx_pkts[pos], mbp1);
@@ -337,9 +336,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 			rte_mbuf_prefetch_part2(rx_pkts[pos + 3]);
 		}
 
-		/* avoid compiler reorder optimization */
-		rte_compiler_barrier();
-
 		/* pkt 3,4 shift the pktlen field to be 16-bit aligned*/
 		uint32x4_t len3 = vshlq_u32(vreinterpretq_u32_u64(descs[3]),
 					    len_shl);
@@ -507,6 +503,7 @@ i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			i++;
 		if (i == nb_bufs)
 			return nb_bufs;
+		rxq->pkt_first_seg = rx_pkts[i];
 	}
 	return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
 		&split_flags[i]);
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c
index c186ed6..0532bf6 100644
--- a/drivers/net/ixgbe/ixgbe_ethdev.c
+++ b/drivers/net/ixgbe/ixgbe_ethdev.c
@@ -1232,6 +1232,7 @@ eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev)
 	diag = ixgbe_bypass_init_hw(hw);
 #else
 	diag = ixgbe_init_hw(hw);
+	hw->mac.autotry_restart = false;
 #endif /* RTE_LIBRTE_IXGBE_BYPASS */
 
 	/*
@@ -1337,6 +1338,8 @@ eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev)
 	/* enable support intr */
 	ixgbe_enable_intr(eth_dev);
 
+	ixgbe_dev_set_link_down(eth_dev);
+
 	/* initialize filter info */
 	memset(filter_info, 0,
 	       sizeof(struct ixgbe_filter_info));
@@ -2852,6 +2855,7 @@ ixgbe_dev_set_link_up(struct rte_eth_dev *dev)
 	} else {
 		/* Turn on the laser */
 		ixgbe_enable_tx_laser(hw);
+		ixgbe_dev_link_update(dev, 0);
 	}
 
 	return 0;
@@ -2882,6 +2886,7 @@ ixgbe_dev_set_link_down(struct rte_eth_dev *dev)
 	} else {
 		/* Turn off the laser */
 		ixgbe_disable_tx_laser(hw);
+		ixgbe_dev_link_update(dev, 0);
 	}
 
 	return 0;
@@ -3774,6 +3779,11 @@ ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 	dev_info->flow_type_rss_offloads = IXGBE_RSS_OFFLOAD_ALL;
 
 	dev_info->speed_capa = ETH_LINK_SPEED_1G | ETH_LINK_SPEED_10G;
+	if (hw->device_id == IXGBE_DEV_ID_X550EM_A_1G_T ||
+			hw->device_id == IXGBE_DEV_ID_X550EM_A_1G_T_L)
+		dev_info->speed_capa = ETH_LINK_SPEED_10M |
+			ETH_LINK_SPEED_100M | ETH_LINK_SPEED_1G;
+
 	if (hw->mac.type == ixgbe_mac_X540 ||
 	    hw->mac.type == ixgbe_mac_X540_vf ||
 	    hw->mac.type == ixgbe_mac_X550 ||
@@ -3817,7 +3827,7 @@ ixgbe_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 	    dev->rx_pkt_burst == ixgbe_recv_pkts_bulk_alloc)
 		return ptypes;
 
-#if defined(RTE_ARCH_X86)
+#if defined(RTE_ARCH_X86) || defined(RTE_MACHINE_CPUFLAG_NEON)
 	if (dev->rx_pkt_burst == ixgbe_recv_pkts_vec ||
 	    dev->rx_pkt_burst == ixgbe_recv_scattered_pkts_vec)
 		return ptypes;
@@ -3854,6 +3864,7 @@ ixgbevf_dev_info_get(struct rte_eth_dev *dev,
 				DEV_TX_OFFLOAD_TCP_CKSUM   |
 				DEV_TX_OFFLOAD_SCTP_CKSUM  |
 				DEV_TX_OFFLOAD_TCP_TSO;
+	dev_info->flow_type_rss_offloads = IXGBE_RSS_OFFLOAD_ALL;
 
 	dev_info->default_rxconf = (struct rte_eth_rxconf) {
 		.rx_thresh = {
@@ -4006,6 +4017,7 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
 	int link_up;
 	int diag;
 	int wait = 1;
+	u32 esdp_reg;
 
 	link.link_status = ETH_LINK_DOWN;
 	link.link_speed = 0;
@@ -4041,6 +4053,10 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
 		return 0;
 	}
 
+	esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP);
+	if ((esdp_reg & IXGBE_ESDP_SDP3))
+		link_up = 0;
+
 	if (link_up == 0) {
 		rte_ixgbe_dev_atomic_write_link_status(dev, &link);
 		if (ixgbe_get_media_type(hw) == ixgbe_media_type_fiber) {
@@ -4059,7 +4075,6 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
 	switch (link_speed) {
 	default:
 	case IXGBE_LINK_SPEED_UNKNOWN:
-		link.link_duplex = ETH_LINK_FULL_DUPLEX;
 		link.link_speed = ETH_SPEED_NUM_100M;
 		break;
 
@@ -5796,7 +5811,8 @@ ixgbe_set_ivar_map(struct ixgbe_hw *hw, int8_t direction,
 		IXGBE_WRITE_REG(hw, IXGBE_IVAR(idx), tmp);
 	} else if ((hw->mac.type == ixgbe_mac_82599EB) ||
 			(hw->mac.type == ixgbe_mac_X540) ||
-			(hw->mac.type == ixgbe_mac_X550)) {
+			(hw->mac.type == ixgbe_mac_X550) ||
+			(hw->mac.type == ixgbe_mac_X550EM_x)) {
 		if (direction == -1) {
 			/* other causes */
 			idx = ((queue & 1) * 8);
@@ -5919,6 +5935,7 @@ ixgbe_configure_msix(struct rte_eth_dev *dev)
 		case ixgbe_mac_82599EB:
 		case ixgbe_mac_X540:
 		case ixgbe_mac_X550:
+		case ixgbe_mac_X550EM_x:
 			ixgbe_set_ivar_map(hw, -1, 1, IXGBE_MISC_VEC_ID);
 			break;
 		default:
diff --git a/drivers/net/ixgbe/ixgbe_pf.c b/drivers/net/ixgbe/ixgbe_pf.c
index 22ecbad..29a6f3b 100644
--- a/drivers/net/ixgbe/ixgbe_pf.c
+++ b/drivers/net/ixgbe/ixgbe_pf.c
@@ -655,6 +655,7 @@ ixgbe_get_vf_queues(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
 	case ixgbe_mbox_api_20:
 	case ixgbe_mbox_api_11:
 	case ixgbe_mbox_api_12:
+	case ixgbe_mbox_api_13:
 		break;
 	default:
 		return -1;
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index 2e87ffa..fd01d97 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -174,6 +174,68 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
 #define IXGBE_VPMD_DESC_DD_MASK		0x01010101
 #define IXGBE_VPMD_DESC_EOP_MASK	0x02020202
 
+static inline uint32_t
+get_packet_type(uint32_t pkt_info,
+		uint32_t etqf_check,
+		uint32_t tunnel_check)
+{
+	if (etqf_check)
+		return RTE_PTYPE_UNKNOWN;
+
+	if (tunnel_check) {
+		pkt_info &= IXGBE_PACKET_TYPE_MASK_TUNNEL;
+		return ptype_table_tn[pkt_info];
+	}
+
+	pkt_info &= IXGBE_PACKET_TYPE_MASK_82599;
+	return ptype_table[pkt_info];
+}
+
+static inline void
+desc_to_ptype_v(uint64x2_t descs[4], uint16_t pkt_type_mask,
+		struct rte_mbuf **rx_pkts)
+{
+	uint32x4_t etqf_check, tunnel_check;
+	uint32x4_t etqf_mask = vdupq_n_u32(0x8000);
+	uint32x4_t tunnel_mask = vdupq_n_u32(0x10000);
+	uint32x4_t ptype_mask = vdupq_n_u32((uint32_t)pkt_type_mask);
+	uint32x4_t ptype0 = vzipq_u32(vreinterpretq_u32_u64(descs[0]),
+				vreinterpretq_u32_u64(descs[2])).val[0];
+	uint32x4_t ptype1 = vzipq_u32(vreinterpretq_u32_u64(descs[1]),
+				vreinterpretq_u32_u64(descs[3])).val[0];
+
+	/* interleave low 32 bits,
+	 * now we have 4 ptypes in a NEON register
+	 */
+	ptype0 = vzipq_u32(ptype0, ptype1).val[0];
+
+	/* mask etqf bits */
+	etqf_check = vandq_u32(ptype0, etqf_mask);
+	/* mask tunnel bits */
+	tunnel_check = vandq_u32(ptype0, tunnel_mask);
+
+	/* shift right by IXGBE_PACKET_TYPE_SHIFT, and apply ptype mask */
+	ptype0 = vandq_u32(vshrq_n_u32(ptype0, IXGBE_PACKET_TYPE_SHIFT),
+			ptype_mask);
+
+	rx_pkts[0]->packet_type =
+		get_packet_type(vgetq_lane_u32(ptype0, 0),
+				vgetq_lane_u32(etqf_check, 0),
+				vgetq_lane_u32(tunnel_check, 0));
+	rx_pkts[1]->packet_type =
+		get_packet_type(vgetq_lane_u32(ptype0, 1),
+				vgetq_lane_u32(etqf_check, 1),
+				vgetq_lane_u32(tunnel_check, 1));
+	rx_pkts[2]->packet_type =
+		get_packet_type(vgetq_lane_u32(ptype0, 2),
+				vgetq_lane_u32(etqf_check, 2),
+				vgetq_lane_u32(tunnel_check, 2));
+	rx_pkts[3]->packet_type =
+		get_packet_type(vgetq_lane_u32(ptype0, 3),
+				vgetq_lane_u32(etqf_check, 3),
+				vgetq_lane_u32(tunnel_check, 3));
+}
+
 static inline uint16_t
 _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		   uint16_t nb_pkts, uint8_t *split_packet)
@@ -243,13 +305,13 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		uint32_t var = 0;
 		uint32_t stat;
 
-		/* B.1 load 1 mbuf point */
+		/* B.1 load 2 mbuf point */
 		mbp1 = vld1q_u64((uint64_t *)&sw_ring[pos]);
 
 		/* B.2 copy 2 mbuf point into rx_pkts  */
 		vst1q_u64((uint64_t *)&rx_pkts[pos], mbp1);
 
-		/* B.1 load 1 mbuf point */
+		/* B.1 load 2 mbuf point */
 		mbp2 = vld1q_u64((uint64_t *)&sw_ring[pos + 2]);
 
 		/* A. load 4 pkts descs */
@@ -257,7 +319,6 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		descs[1] =  vld1q_u64((uint64_t *)(rxdp + 1));
 		descs[2] =  vld1q_u64((uint64_t *)(rxdp + 2));
 		descs[3] =  vld1q_u64((uint64_t *)(rxdp + 3));
-		rte_smp_rmb();
 
 		/* B.2 copy 2 mbuf point into rx_pkts  */
 		vst1q_u64((uint64_t *)&rx_pkts[pos + 2], mbp2);
@@ -326,6 +387,8 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		vst1q_u8((uint8_t *)&rx_pkts[pos]->rx_descriptor_fields1,
 			 pkt_mb1);
 
+		desc_to_ptype_v(descs, rxq->pkt_type_mask, &rx_pkts[pos]);
+
 		stat &= IXGBE_VPMD_DESC_DD_MASK;
 
 		/* C.4 calc avaialbe number of desc */
@@ -404,6 +467,7 @@ ixgbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			i++;
 		if (i == nb_bufs)
 			return nb_bufs;
+		rxq->pkt_first_seg = rx_pkts[i];
 	}
 	return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
 		&split_flags[i]);
diff --git a/drivers/net/mlx4/Makefile b/drivers/net/mlx4/Makefile
index 1f95e0d..0bde672 100644
--- a/drivers/net/mlx4/Makefile
+++ b/drivers/net/mlx4/Makefile
@@ -73,7 +73,11 @@ endif
 
 # User-defined CFLAGS.
 ifeq ($(CONFIG_RTE_LIBRTE_MLX4_DEBUG),y)
-CFLAGS += -pedantic -UNDEBUG -DPEDANTIC
+CFLAGS += -pedantic -UNDEBUG
+ifneq ($(CONFIG_RTE_TOOLCHAIN_ICC),y)
+CFLAGS += -DPEDANTIC
+endif
+AUTO_CONFIG_CFLAGS += -Wno-pedantic
 else
 CFLAGS += -DNDEBUG -UPEDANTIC
 endif
@@ -87,7 +91,7 @@ include $(RTE_SDK)/mk/rte.lib.mk
 # Generate and clean-up mlx4_autoconf.h.
 
 export CC CFLAGS CPPFLAGS EXTRA_CFLAGS EXTRA_CPPFLAGS
-export AUTO_CONFIG_CFLAGS = -Wno-error
+export AUTO_CONFIG_CFLAGS += -Wno-error
 
 ifndef V
 AUTOCONF_OUTPUT := >/dev/null
diff --git a/drivers/net/mlx4/mlx4_utils.h b/drivers/net/mlx4/mlx4_utils.h
index 4f11405..02e6b7b 100644
--- a/drivers/net/mlx4/mlx4_utils.h
+++ b/drivers/net/mlx4/mlx4_utils.h
@@ -43,6 +43,16 @@
 
 #include "mlx4.h"
 
+/*
+ * Compilation workaround for PPC64 when AltiVec is fully enabled, e.g. std=c11.
+ * Otherwise there would be a type conflict between stdbool and altivec.
+ */
+#if defined(__PPC64__) && !defined(__APPLE_ALTIVEC__)
+#undef bool
+/* redefine as in stdbool.h */
+#define bool _Bool
+#endif
+
 #ifndef NDEBUG
 
 /*
diff --git a/drivers/net/mlx5/Makefile b/drivers/net/mlx5/Makefile
index c62ad11..e6fe1c6 100644
--- a/drivers/net/mlx5/Makefile
+++ b/drivers/net/mlx5/Makefile
@@ -83,7 +83,11 @@ endif
 
 # User-defined CFLAGS.
 ifeq ($(CONFIG_RTE_LIBRTE_MLX5_DEBUG),y)
-CFLAGS += -pedantic -UNDEBUG -DPEDANTIC
+CFLAGS += -pedantic -UNDEBUG
+ifneq ($(CONFIG_RTE_TOOLCHAIN_ICC),y)
+CFLAGS += -DPEDANTIC
+endif
+AUTO_CONFIG_CFLAGS += -Wno-pedantic
 else
 CFLAGS += -DNDEBUG -UPEDANTIC
 endif
@@ -97,7 +101,7 @@ include $(RTE_SDK)/mk/rte.lib.mk
 # Generate and clean-up mlx5_autoconf.h.
 
 export CC CFLAGS CPPFLAGS EXTRA_CFLAGS EXTRA_CPPFLAGS
-export AUTO_CONFIG_CFLAGS = -Wno-error
+export AUTO_CONFIG_CFLAGS += -Wno-error
 
 ifndef V
 AUTOCONF_OUTPUT := >/dev/null
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index ae37c2b..950d27d 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -1032,7 +1032,7 @@ rxq_burst_v(struct mlx5_rxq_data *rxq, struct rte_mbuf **pkts, uint16_t pkts_n,
 			rcvd_pkt += n;
 		}
 	}
-	rte_compiler_barrier();
+	rte_cio_wmb();
 	*rxq->cq_db = rte_cpu_to_be_32(rxq->cq_ci);
 	return rcvd_pkt;
 }
diff --git a/drivers/net/qede/qede_ethdev.c b/drivers/net/qede/qede_ethdev.c
index 43403e6..1fa64e1 100644
--- a/drivers/net/qede/qede_ethdev.c
+++ b/drivers/net/qede/qede_ethdev.c
@@ -970,6 +970,8 @@ static int qede_vlan_stripping(struct rte_eth_dev *eth_dev, bool flg)
 		}
 	}
 
+	qdev->vlan_strip_flg = flg;
+
 	DP_INFO(edev, "VLAN stripping %s\n", flg ? "enabled" : "disabled");
 	return 0;
 }
@@ -1178,9 +1180,11 @@ static int qede_dev_start(struct rte_eth_dev *eth_dev)
 	PMD_INIT_FUNC_TRACE(edev);
 
 	/* Update MTU only if it has changed */
-	if (eth_dev->data->mtu != qdev->mtu) {
-		if (qede_update_mtu(eth_dev, qdev->mtu))
+	if (qdev->new_mtu && qdev->new_mtu != qdev->mtu) {
+		if (qede_update_mtu(eth_dev, qdev->new_mtu))
 			goto err;
+		qdev->mtu = qdev->new_mtu;
+		qdev->new_mtu = 0;
 	}
 
 	/* Configure TPA parameters */
@@ -2408,7 +2412,7 @@ static int qede_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 		restart = true;
 	}
 	rte_delay_ms(1000);
-	qdev->mtu = mtu;
+	qdev->new_mtu = mtu;
 
 	/* Fix up RX buf size for all queues of the port */
 	for_each_rss(i) {
diff --git a/drivers/net/qede/qede_ethdev.h b/drivers/net/qede/qede_ethdev.h
index cc1a409..39d5822 100644
--- a/drivers/net/qede/qede_ethdev.h
+++ b/drivers/net/qede/qede_ethdev.h
@@ -185,6 +185,7 @@ struct qede_dev {
 	struct ecore_sb_info *sb_array;
 	struct qede_fastpath *fp_array;
 	uint16_t mtu;
+	uint16_t new_mtu;
 	bool enable_tx_switching;
 	bool rss_enable;
 	struct rte_eth_rss_conf rss_conf;
diff --git a/drivers/net/qede/qede_rxtx.c b/drivers/net/qede/qede_rxtx.c
index 358a8ef..dd88c50 100644
--- a/drivers/net/qede/qede_rxtx.c
+++ b/drivers/net/qede/qede_rxtx.c
@@ -48,8 +48,6 @@ static inline int qede_alloc_rx_bulk_mbufs(struct qede_rx_queue *rxq, int count)
 	int i, ret = 0;
 	uint16_t idx;
 
-	idx = rxq->sw_rx_prod & NUM_RX_BDS(rxq);
-
 	if (count > QEDE_MAX_BULK_ALLOC_COUNT)
 		count = QEDE_MAX_BULK_ALLOC_COUNT;
 
@@ -58,7 +56,9 @@ static inline int qede_alloc_rx_bulk_mbufs(struct qede_rx_queue *rxq, int count)
 		PMD_RX_LOG(ERR, rxq,
 			   "Failed to allocate %d rx buffers "
 			    "sw_rx_prod %u sw_rx_cons %u mp entries %u free %u",
-			    count, idx, rxq->sw_rx_cons & NUM_RX_BDS(rxq),
+			    count,
+			    rxq->sw_rx_prod & NUM_RX_BDS(rxq),
+			    rxq->sw_rx_cons & NUM_RX_BDS(rxq),
 			    rte_mempool_avail_count(rxq->mb_pool),
 			    rte_mempool_in_use_count(rxq->mb_pool));
 		return -ENOMEM;
diff --git a/drivers/net/sfc/sfc_flow.c b/drivers/net/sfc/sfc_flow.c
index 90ef5bf..9d46abe 100644
--- a/drivers/net/sfc/sfc_flow.c
+++ b/drivers/net/sfc/sfc_flow.c
@@ -1185,10 +1185,10 @@ sfc_flow_create(struct rte_eth_dev *dev,
 	if (rc != 0)
 		goto fail_bad_value;
 
-	TAILQ_INSERT_TAIL(&sa->filter.flow_list, flow, entries);
-
 	sfc_adapter_lock(sa);
 
+	TAILQ_INSERT_TAIL(&sa->filter.flow_list, flow, entries);
+
 	if (sa->state == SFC_ADAPTER_STARTED) {
 		rc = sfc_flow_filter_insert(sa, flow);
 		if (rc != 0) {
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 2204216..341a5e0 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -308,9 +308,7 @@ pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 
 	if (trigger == rxq->trigger_seen)
 		return 0;
-	if (trigger)
-		rxq->trigger_seen = trigger;
-	rte_compiler_barrier();
+
 	for (num_rx = 0; num_rx < nb_pkts; ) {
 		struct rte_mbuf *mbuf = rxq->pool;
 		struct rte_mbuf *seg = NULL;
@@ -386,6 +384,9 @@ end:
 	rxq->stats.ipackets += num_rx;
 	rxq->stats.ibytes += num_rx_bytes;
 
+	if (trigger && num_rx < nb_pkts)
+		rxq->trigger_seen = trigger;
+
 	return num_rx;
 }
 
diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
index 7b7780c..1f3b271 100644
--- a/drivers/net/vhost/rte_eth_vhost.c
+++ b/drivers/net/vhost/rte_eth_vhost.c
@@ -705,6 +705,10 @@ vring_state_changed(int vid, uint16_t vring, int enable)
 	/* won't be NULL */
 	state = vring_states[eth_dev->data->port_id];
 	rte_spinlock_lock(&state->lock);
+	if (state->cur[vring] == enable) {
+		rte_spinlock_unlock(&state->lock);
+		return 0;
+	}
 	state->cur[vring] = enable;
 	state->max_vring = RTE_MAX(vring, state->max_vring);
 	rte_spinlock_unlock(&state->lock);
diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c
index 1bdf37e..a4089f7 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/drivers/net/virtio/virtio_ethdev.c
@@ -1502,6 +1502,8 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
 	} else {
 		PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=1");
 		hw->max_queue_pairs = 1;
+		hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN -
+			VLAN_TAG_LEN - hw->vtnet_hdr_size;
 	}
 
 	ret = virtio_alloc_queues(eth_dev);
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index b37a186..cea097a 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -36,6 +36,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <stdbool.h>
 
 #include <rte_cycles.h>
 #include <rte_memory.h>
@@ -282,9 +283,10 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 	struct vring_desc *start_dp;
 	uint16_t seg_num = cookie->nb_segs;
 	uint16_t head_idx, idx;
-	uint16_t head_size = vq->hw->vtnet_hdr_size;
+	int16_t head_size = vq->hw->vtnet_hdr_size;
 	struct virtio_net_hdr *hdr;
 	int offload;
+	bool prepend_header = false;
 
 	offload = tx_offload_enabled(vq->hw);
 	head_idx = vq->vq_desc_head_idx;
@@ -297,12 +299,9 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 
 	if (can_push) {
 		/* prepend cannot fail, checked by caller */
-		hdr = (struct virtio_net_hdr *)
-			rte_pktmbuf_prepend(cookie, head_size);
-		/* rte_pktmbuf_prepend() counts the hdr size to the pkt length,
-		 * which is wrong. Below subtract restores correct pkt size.
-		 */
-		cookie->pkt_len -= head_size;
+		hdr = rte_pktmbuf_mtod_offset(cookie, struct virtio_net_hdr *,
+									  -head_size);
+		prepend_header = true;
 		/* if offload disabled, it is not zeroed below, do it now */
 		if (offload == 0) {
 			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
@@ -388,6 +387,11 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
 	do {
 		start_dp[idx].addr  = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq);
 		start_dp[idx].len   = cookie->data_len;
+		if (prepend_header) {
+			start_dp[idx].addr -= head_size;
+			start_dp[idx].len += head_size;
+			prepend_header = false;
+		}
 		start_dp[idx].flags = cookie->next ? VRING_DESC_F_NEXT : 0;
 		idx = start_dp[idx].next;
 	} while ((cookie = cookie->next) != NULL);
@@ -417,7 +421,7 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 			uint16_t queue_idx,
 			uint16_t nb_desc,
 			unsigned int socket_id __rte_unused,
-			__rte_unused const struct rte_eth_rxconf *rx_conf,
+			const struct rte_eth_rxconf *rx_conf,
 			struct rte_mempool *mp)
 {
 	uint16_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_RQ_QUEUE_IDX;
@@ -427,6 +431,11 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev,
 
 	PMD_INIT_FUNC_TRACE();
 
+	if (rx_conf->rx_deferred_start) {
+		PMD_INIT_LOG(ERR, "Rx deferred start is not supported");
+		return -EINVAL;
+	}
+
 	if (nb_desc == 0 || nb_desc > vq->vq_nentries)
 		nb_desc = vq->vq_nentries;
 	vq->vq_free_cnt = RTE_MIN(vq->vq_free_cnt, nb_desc);
@@ -529,6 +538,11 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev,
 
 	PMD_INIT_FUNC_TRACE();
 
+	if (tx_conf->tx_deferred_start) {
+		PMD_INIT_LOG(ERR, "Tx deferred start is not supported");
+		return -EINVAL;
+	}
+
 	/* cannot use simple rxtx funcs with multisegs or offloads */
 	if ((tx_conf->txq_flags & VIRTIO_SIMPLE_FLAGS) != VIRTIO_SIMPLE_FLAGS)
 		hw->use_simple_tx = 0;
diff --git a/drivers/net/virtio/virtio_rxtx_simple_neon.c b/drivers/net/virtio/virtio_rxtx_simple_neon.c
index b8b9355..a9d5cb6 100644
--- a/drivers/net/virtio/virtio_rxtx_simple_neon.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_neon.c
@@ -72,7 +72,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	struct virtnet_rx *rxvq = rx_queue;
 	struct virtqueue *vq = rxvq->vq;
 	struct virtio_hw *hw = vq->hw;
-	uint16_t nb_used;
+	uint16_t nb_used, nb_total;
 	uint16_t desc_idx;
 	struct vring_used_elem *rused;
 	struct rte_mbuf **sw_ring;
@@ -135,8 +135,9 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			virtqueue_notify(vq);
 	}
 
+	nb_total = nb_used;
 	for (nb_pkts_received = 0;
-		nb_pkts_received < nb_used;) {
+		nb_pkts_received < nb_total;) {
 		uint64x2_t desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
 		uint64x2_t mbp[RTE_VIRTIO_DESC_PER_LOOP / 2];
 		uint64x2_t pkt_mb[RTE_VIRTIO_DESC_PER_LOOP];
diff --git a/drivers/net/virtio/virtio_rxtx_simple_sse.c b/drivers/net/virtio/virtio_rxtx_simple_sse.c
index 94f6514..74ca28d 100644
--- a/drivers/net/virtio/virtio_rxtx_simple_sse.c
+++ b/drivers/net/virtio/virtio_rxtx_simple_sse.c
@@ -74,7 +74,7 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 	struct virtnet_rx *rxvq = rx_queue;
 	struct virtqueue *vq = rxvq->vq;
 	struct virtio_hw *hw = vq->hw;
-	uint16_t nb_used;
+	uint16_t nb_used, nb_total;
 	uint16_t desc_idx;
 	struct vring_used_elem *rused;
 	struct rte_mbuf **sw_ring;
@@ -138,8 +138,9 @@ virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			virtqueue_notify(vq);
 	}
 
+	nb_total = nb_used;
 	for (nb_pkts_received = 0;
-		nb_pkts_received < nb_used;) {
+		nb_pkts_received < nb_total;) {
 		__m128i desc[RTE_VIRTIO_DESC_PER_LOOP / 2];
 		__m128i mbp[RTE_VIRTIO_DESC_PER_LOOP / 2];
 		__m128i pkt_mb[RTE_VIRTIO_DESC_PER_LOOP];
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c b/drivers/net/virtio/virtio_user/virtio_user_dev.c
index 23510a9..95433f7 100644
--- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
@@ -484,6 +484,10 @@ virtio_user_handle_ctrl_msg(struct virtio_user_dev *dev, struct vring *vring,
 
 		queues = *(uint16_t *)(uintptr_t)vring->desc[idx_data].addr;
 		status = virtio_user_handle_mq(dev, queues);
+	} else if (hdr->class == VIRTIO_NET_CTRL_RX  ||
+		   hdr->class == VIRTIO_NET_CTRL_MAC ||
+		   hdr->class == VIRTIO_NET_CTRL_VLAN) {
+		status = 0;
 	}
 
 	/* Update status */
diff --git a/examples/ethtool/lib/rte_ethtool.c b/examples/ethtool/lib/rte_ethtool.c
index c70c547..ebdaed4 100644
--- a/examples/ethtool/lib/rte_ethtool.c
+++ b/examples/ethtool/lib/rte_ethtool.c
@@ -67,7 +67,6 @@ rte_ethtool_get_drvinfo(uint16_t port_id, struct ethtool_drvinfo *drvinfo)
 		printf("Insufficient fw version buffer size, "
 		       "the minimum size should be %d\n", ret);
 
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(port_id, &dev_info);
 
 	snprintf(drvinfo->driver, sizeof(drvinfo->driver), "%s",
@@ -367,7 +366,6 @@ rte_ethtool_net_set_rx_mode(uint16_t port_id)
 	struct rte_eth_dev_info dev_info;
 	uint16_t vf;
 
-	memset(&dev_info, 0, sizeof(dev_info));
 	rte_eth_dev_info_get(port_id, &dev_info);
 	num_vfs = dev_info.max_vfs;
 
diff --git a/examples/ipsec-secgw/ep0.cfg b/examples/ipsec-secgw/ep0.cfg
index 299aa9e..dfd4aca 100644
--- a/examples/ipsec-secgw/ep0.cfg
+++ b/examples/ipsec-secgw/ep0.cfg
@@ -49,14 +49,14 @@ sport 0:65535 dport 0:65535
 sp ipv6 out esp protect 26 pri 1 dst 0000:0000:0000:0000:bbbb:bbbb:0000:0000/96 \
 sport 0:65535 dport 0:65535
 
-sp ipv6 in esp protect 15 pri 1 dst ffff:0000:0000:0000:5555:5555:0000:0000/96 \
-sport 0:65535 dport 0:65535
-sp ipv6 in esp protect 16 pri 1 dst ffff:0000:0000:0000:6666:6666:0000:0000/96 \
-sport 0:65535 dport 0:65535
 sp ipv6 in esp protect 110 pri 1 dst ffff:0000:1111:1111:0000:0000:0000:0000/96 \
 sport 0:65535 dport 0:65535
 sp ipv6 in esp protect 111 pri 1 dst ffff:0000:1111:1111:1111:1111:0000:0000/96 \
 sport 0:65535 dport 0:65535
+sp ipv6 in esp protect 115 pri 1 dst ffff:0000:0000:0000:5555:5555:0000:0000/96 \
+sport 0:65535 dport 0:65535
+sp ipv6 in esp protect 116 pri 1 dst ffff:0000:0000:0000:6666:6666:0000:0000/96 \
+sport 0:65535 dport 0:65535
 sp ipv6 in esp protect 125 pri 1 dst ffff:0000:0000:0000:aaaa:aaaa:0000:0000/96 \
 sport 0:65535 dport 0:65535
 sp ipv6 in esp protect 126 pri 1 dst ffff:0000:0000:0000:bbbb:bbbb:0000:0000/96 \
diff --git a/examples/ipsec-secgw/ep1.cfg b/examples/ipsec-secgw/ep1.cfg
index 3f6ff81..19bdc68 100644
--- a/examples/ipsec-secgw/ep1.cfg
+++ b/examples/ipsec-secgw/ep1.cfg
@@ -19,8 +19,8 @@ sp ipv4 in esp protect 15 pri 1 dst 192.168.200.0/24 sport 0:65535 dport 0:65535
 sp ipv4 in esp protect 16 pri 1 dst 192.168.201.0/24 sport 0:65535 dport 0:65535
 sp ipv4 in esp protect 25 pri 1 dst 192.168.55.0/24 sport 0:65535 dport 0:65535
 sp ipv4 in esp protect 26 pri 1 dst 192.168.56.0/24 sport 0:65535 dport 0:65535
-sp ipv4 in esp bypass dst 192.168.240.0/24 sport 0:65535 dport 0:65535
-sp ipv4 in esp bypass dst 192.168.241.0/24 sport 0:65535 dport 0:65535
+sp ipv4 in esp bypass pri 1 dst 192.168.240.0/24 sport 0:65535 dport 0:65535
+sp ipv4 in esp bypass pri 1 dst 192.168.241.0/24 sport 0:65535 dport 0:65535
 
 sp ipv4 out esp protect 105 pri 1 dst 192.168.115.0/24 sport 0:65535 dport 0:65535
 sp ipv4 out esp protect 106 pri 1 dst 192.168.116.0/24 sport 0:65535 dport 0:65535
@@ -49,14 +49,14 @@ sport 0:65535 dport 0:65535
 sp ipv6 in esp protect 26 pri 1 dst 0000:0000:0000:0000:bbbb:bbbb:0000:0000/96 \
 sport 0:65535 dport 0:65535
 
-sp ipv6 out esp protect 15 pri 1 dst ffff:0000:0000:0000:5555:5555:0000:0000/96 \
-sport 0:65535 dport 0:65535
-sp ipv6 out esp protect 16 pri 1 dst ffff:0000:0000:0000:6666:6666:0000:0000/96 \
-sport 0:65535 dport 0:65535
 sp ipv6 out esp protect 110 pri 1 dst ffff:0000:1111:1111:0000:0000:0000:0000/96 \
 sport 0:65535 dport 0:65535
 sp ipv6 out esp protect 111 pri 1 dst ffff:0000:1111:1111:1111:1111:0000:0000/96 \
 sport 0:65535 dport 0:65535
+sp ipv6 out esp protect 115 pri 1 dst ffff:0000:0000:0000:5555:5555:0000:0000/96 \
+sport 0:65535 dport 0:65535
+sp ipv6 out esp protect 116 pri 1 dst ffff:0000:0000:0000:6666:6666:0000:0000/96 \
+sport 0:65535 dport 0:65535
 sp ipv6 out esp protect 125 pri 1 dst ffff:0000:0000:0000:aaaa:aaaa:0000:0000/96 \
 sport 0:65535 dport 0:65535
 sp ipv6 out esp protect 126 pri 1 dst ffff:0000:0000:0000:bbbb:bbbb:0000:0000/96 \
diff --git a/examples/ipsec-secgw/sa.c b/examples/ipsec-secgw/sa.c
index eb83d94..f01a531 100644
--- a/examples/ipsec-secgw/sa.c
+++ b/examples/ipsec-secgw/sa.c
@@ -123,7 +123,7 @@ const struct supported_auth_algo auth_algos[] = {
 	{
 		.keyword = "sha256-hmac",
 		.algo = RTE_CRYPTO_AUTH_SHA256_HMAC,
-		.digest_len = 12,
+		.digest_len = 16,
 		.key_len = 32
 	}
 };
@@ -822,7 +822,7 @@ sa_add_rules(struct sa_ctx *sa_ctx, const struct ipsec_sa entries[],
 		}
 
 		if (sa->aead_algo == RTE_CRYPTO_AEAD_AES_GCM) {
-			iv_length = 16;
+			iv_length = 12;
 
 			sa_ctx->xf[idx].a.type = RTE_CRYPTO_SYM_XFORM_AEAD;
 			sa_ctx->xf[idx].a.aead.algo = sa->aead_algo;
diff --git a/examples/kni/main.c b/examples/kni/main.c
index 3f17385..e272e84 100644
--- a/examples/kni/main.c
+++ b/examples/kni/main.c
@@ -802,7 +802,6 @@ kni_alloc(uint16_t port_id)
 			struct rte_kni_ops ops;
 			struct rte_eth_dev_info dev_info;
 
-			memset(&dev_info, 0, sizeof(dev_info));
 			rte_eth_dev_info_get(port_id, &dev_info);
 
 			if (dev_info.pci_dev) {
diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c
index 50c3702..c669f6a 100644
--- a/examples/l3fwd-power/main.c
+++ b/examples/l3fwd-power/main.c
@@ -813,7 +813,9 @@ sleep_until_rx_interrupt(int num)
 		port_id = ((uintptr_t)data) >> CHAR_BIT;
 		queue_id = ((uintptr_t)data) &
 			RTE_LEN2MASK(CHAR_BIT, uint8_t);
+		rte_spinlock_lock(&(locks[port_id]));
 		rte_eth_dev_rx_intr_disable(port_id, queue_id);
+		rte_spinlock_unlock(&(locks[port_id]));
 		RTE_LOG(INFO, L3FWD_POWER,
 			"lcore %u is waked up from rx interrupt on"
 			" port %d queue %d\n",
diff --git a/examples/multi_process/client_server_mp/mp_client/client.c b/examples/multi_process/client_server_mp/mp_client/client.c
index 30ce4b3..a9076d1 100644
--- a/examples/multi_process/client_server_mp/mp_client/client.c
+++ b/examples/multi_process/client_server_mp/mp_client/client.c
@@ -275,19 +275,19 @@ main(int argc, char *argv[])
 
 	for (;;) {
 		uint16_t i, rx_pkts;
-		uint16_t port;
 
 		rx_pkts = rte_ring_dequeue_burst(rx_ring, pkts,
 				PKT_READ_SIZE, NULL);
 
-		if (unlikely(rx_pkts == 0)){
-			if (need_flush)
-				for (port = 0; port < ports->num_ports; port++) {
-					sent = rte_eth_tx_buffer_flush(ports->id[port], client_id,
-							tx_buffer[port]);
-					if (unlikely(sent))
-						tx_stats->tx[port] += sent;
-				}
+		if (rx_pkts == 0 && need_flush) {
+			for (i = 0; i < ports->num_ports; i++) {
+				uint16_t port = ports->id[i];
+
+				sent = rte_eth_tx_buffer_flush(port,
+							       client_id,
+							       tx_buffer[port]);
+				tx_stats->tx[port] += sent;
+			}
 			need_flush = 0;
 			continue;
 		}
diff --git a/examples/vm_power_manager/channel_monitor.c b/examples/vm_power_manager/channel_monitor.c
index 37e71ed..6e73d54 100644
--- a/examples/vm_power_manager/channel_monitor.c
+++ b/examples/vm_power_manager/channel_monitor.c
@@ -49,7 +49,9 @@
 #include <rte_atomic.h>
 #include <rte_cycles.h>
 #include <rte_ethdev.h>
+#ifdef RTE_LIBRTE_I40E_PMD
 #include <rte_pmd_i40e.h>
+#endif
 
 #include <libvirt/libvirt.h>
 #include "channel_monitor.h"
@@ -145,8 +147,12 @@ get_pfid(struct policy *pol)
 	for (i = 0; i < pol->pkt.nb_mac_to_monitor; i++) {
 
 		for (x = 0; x < nb_ports; x++) {
+#ifdef RTE_LIBRTE_I40E_PMD
 			ret = rte_pmd_i40e_query_vfid_by_mac(x,
 				(struct ether_addr *)&(pol->pkt.vfid[i]));
+#else
+			ret = -ENOTSUP;
+#endif
 			if (ret != -EINVAL) {
 				pol->port[i] = x;
 				break;
@@ -209,15 +215,21 @@ get_pkt_diff(struct policy *pol)
 		vsi_pkt_count_prev_total = 0;
 	double rdtsc_curr, rdtsc_diff, diff;
 	int x;
+#ifdef RTE_LIBRTE_I40E_PMD
 	struct rte_eth_stats vf_stats;
+#endif
 
 	for (x = 0; x < pol->pkt.nb_mac_to_monitor; x++) {
 
+#ifdef RTE_LIBRTE_I40E_PMD
 		/*Read vsi stats*/
 		if (rte_pmd_i40e_get_vf_stats(x, pol->pfid[x], &vf_stats) == 0)
 			vsi_pkt_count = vf_stats.ipackets;
 		else
 			vsi_pkt_count = -1;
+#else
+		vsi_pkt_count = -1;
+#endif
 
 		vsi_pkt_total += vsi_pkt_count;
 
diff --git a/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c b/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c
index 63f711e..61a3dd6 100644
--- a/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c
+++ b/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c
@@ -121,7 +121,7 @@ cmd_set_cpu_freq_parsed(void *parsed_result, struct cmdline *cl,
 cmdline_parse_token_string_t cmd_set_cpu_freq =
 	TOKEN_STRING_INITIALIZER(struct cmd_set_cpu_freq_result,
 			set_cpu_freq, "set_cpu_freq");
-cmdline_parse_token_string_t cmd_set_cpu_freq_core_num =
+cmdline_parse_token_num_t cmd_set_cpu_freq_core_num =
 	TOKEN_NUM_INITIALIZER(struct cmd_set_cpu_freq_result,
 			lcore_id, UINT8);
 cmdline_parse_token_string_t cmd_set_cpu_freq_cmd_cmd =
diff --git a/lib/librte_compat/rte_compat.h b/lib/librte_compat/rte_compat.h
index 41e8032..f45b434 100644
--- a/lib/librte_compat/rte_compat.h
+++ b/lib/librte_compat/rte_compat.h
@@ -63,14 +63,14 @@
 /*
  * VERSION_SYMBOL
  * Creates a symbol version table entry binding symbol <b>@DPDK_<n> to the internal
- * function name <b>_<e>
+ * function name <b><e>
  */
 #define VERSION_SYMBOL(b, e, n) __asm__(".symver " RTE_STR(b) RTE_STR(e) ", " RTE_STR(b) "@DPDK_" RTE_STR(n))
 
 /*
  * BIND_DEFAULT_SYMBOL
  * Creates a symbol version entry instructing the linker to bind references to
- * symbol <b> to the internal symbol <b>_<e>
+ * symbol <b> to the internal symbol <b><e>
  */
 #define BIND_DEFAULT_SYMBOL(b, e, n) __asm__(".symver " RTE_STR(b) RTE_STR(e) ", " RTE_STR(b) "@@DPDK_" RTE_STR(n))
 #define __vsym __attribute__((used))
diff --git a/lib/librte_cryptodev/rte_cryptodev.c b/lib/librte_cryptodev/rte_cryptodev.c
index c9f2b62..150ef9a 100644
--- a/lib/librte_cryptodev/rte_cryptodev.c
+++ b/lib/librte_cryptodev/rte_cryptodev.c
@@ -78,8 +78,7 @@ struct rte_cryptodev *rte_cryptodevs = &rte_crypto_devices[0];
 static struct rte_cryptodev_global cryptodev_globals = {
 		.devs			= &rte_crypto_devices[0],
 		.data			= { NULL },
-		.nb_devs		= 0,
-		.max_devs		= RTE_CRYPTO_MAX_DEVS
+		.nb_devs		= 0
 };
 
 struct rte_cryptodev_global *rte_cryptodev_globals = &cryptodev_globals;
@@ -415,7 +414,7 @@ rte_cryptodev_pmd_get_named_dev(const char *name)
 	if (name == NULL)
 		return NULL;
 
-	for (i = 0; i < rte_cryptodev_globals->max_devs; i++) {
+	for (i = 0; i < RTE_CRYPTO_MAX_DEVS; i++) {
 		dev = &rte_cryptodev_globals->devs[i];
 
 		if ((dev->attached == RTE_CRYPTODEV_ATTACHED) &&
@@ -426,12 +425,22 @@ rte_cryptodev_pmd_get_named_dev(const char *name)
 	return NULL;
 }
 
+static inline uint8_t
+rte_cryptodev_is_valid_device_data(uint8_t dev_id)
+{
+	if (dev_id >= RTE_CRYPTO_MAX_DEVS ||
+			rte_crypto_devices[dev_id].data == NULL)
+		return 0;
+
+	return 1;
+}
+
 unsigned int
 rte_cryptodev_pmd_is_valid_dev(uint8_t dev_id)
 {
 	struct rte_cryptodev *dev = NULL;
 
-	if (dev_id >= rte_cryptodev_globals->nb_devs)
+	if (!rte_cryptodev_is_valid_device_data(dev_id))
 		return 0;
 
 	dev = rte_cryptodev_pmd_get_dev(dev_id);
@@ -450,12 +459,15 @@ rte_cryptodev_get_dev_id(const char *name)
 	if (name == NULL)
 		return -1;
 
-	for (i = 0; i < rte_cryptodev_globals->nb_devs; i++)
+	for (i = 0; i < RTE_CRYPTO_MAX_DEVS; i++) {
+		if (!rte_cryptodev_is_valid_device_data(i))
+			continue;
 		if ((strcmp(rte_cryptodev_globals->devs[i].data->name, name)
 				== 0) &&
 				(rte_cryptodev_globals->devs[i].attached ==
 						RTE_CRYPTODEV_ATTACHED))
 			return i;
+	}
 
 	return -1;
 }
@@ -471,7 +483,7 @@ rte_cryptodev_device_count_by_driver(uint8_t driver_id)
 {
 	uint8_t i, dev_count = 0;
 
-	for (i = 0; i < rte_cryptodev_globals->max_devs; i++)
+	for (i = 0; i < RTE_CRYPTO_MAX_DEVS; i++)
 		if (rte_cryptodev_globals->devs[i].driver_id == driver_id &&
 			rte_cryptodev_globals->devs[i].attached ==
 					RTE_CRYPTODEV_ATTACHED)
@@ -486,9 +498,10 @@ rte_cryptodev_devices_get(const char *driver_name, uint8_t *devices,
 {
 	uint8_t i, count = 0;
 	struct rte_cryptodev *devs = rte_cryptodev_globals->devs;
-	uint8_t max_devs = rte_cryptodev_globals->max_devs;
 
-	for (i = 0; i < max_devs && count < nb_devices;	i++) {
+	for (i = 0; i < RTE_CRYPTO_MAX_DEVS && count < nb_devices; i++) {
+		if (!rte_cryptodev_is_valid_device_data(i))
+			continue;
 
 		if (devs[i].attached == RTE_CRYPTODEV_ATTACHED) {
 			int cmp;
@@ -508,8 +521,9 @@ rte_cryptodev_devices_get(const char *driver_name, uint8_t *devices,
 void *
 rte_cryptodev_get_sec_ctx(uint8_t dev_id)
 {
-	if (rte_crypto_devices[dev_id].feature_flags &
-			RTE_CRYPTODEV_FF_SECURITY)
+	if (dev_id < RTE_CRYPTO_MAX_DEVS &&
+			(rte_crypto_devices[dev_id].feature_flags &
+			RTE_CRYPTODEV_FF_SECURITY))
 		return rte_crypto_devices[dev_id].security_ctx;
 
 	return NULL;
@@ -603,12 +617,14 @@ rte_cryptodev_pmd_allocate(const char *name, int socket_id)
 
 		cryptodev->data = cryptodev_data;
 
-		snprintf(cryptodev->data->name, RTE_CRYPTODEV_NAME_MAX_LEN,
-				"%s", name);
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+			snprintf(cryptodev->data->name, RTE_CRYPTODEV_NAME_MAX_LEN,
+					"%s", name);
 
-		cryptodev->data->dev_id = dev_id;
-		cryptodev->data->socket_id = socket_id;
-		cryptodev->data->dev_started = 0;
+			cryptodev->data->dev_id = dev_id;
+			cryptodev->data->socket_id = socket_id;
+			cryptodev->data->dev_started = 0;
+		}
 
 		/* init user callbacks */
 		TAILQ_INIT(&(cryptodev->link_intr_cbs));
@@ -646,6 +662,11 @@ rte_cryptodev_queue_pair_count(uint8_t dev_id)
 {
 	struct rte_cryptodev *dev;
 
+	if (!rte_cryptodev_is_valid_device_data(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%" PRIu8, dev_id);
+		return 0;
+	}
+
 	dev = &rte_crypto_devices[dev_id];
 	return dev->data->nb_queue_pairs;
 }
@@ -979,7 +1000,7 @@ rte_cryptodev_info_get(uint8_t dev_id, struct rte_cryptodev_info *dev_info)
 {
 	struct rte_cryptodev *dev;
 
-	if (dev_id >= cryptodev_globals.nb_devs) {
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
 		CDEV_LOG_ERR("Invalid dev_id=%d", dev_id);
 		return;
 	}
@@ -1117,6 +1138,11 @@ rte_cryptodev_sym_session_init(uint8_t dev_id,
 	uint8_t index;
 	int ret;
 
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%" PRIu8, dev_id);
+		return -EINVAL;
+	}
+
 	dev = rte_cryptodev_pmd_get_dev(dev_id);
 
 	if (sess == NULL || xforms == NULL || dev == NULL)
@@ -1214,6 +1240,11 @@ rte_cryptodev_sym_session_clear(uint8_t dev_id,
 {
 	struct rte_cryptodev *dev;
 
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%" PRIu8, dev_id);
+		return -EINVAL;
+	}
+
 	dev = rte_cryptodev_pmd_get_dev(dev_id);
 
 	if (dev == NULL || sess == NULL)
@@ -1414,8 +1445,14 @@ rte_cryptodev_driver_id_get(const char *name)
 const char *
 rte_cryptodev_name_get(uint8_t dev_id)
 {
-	struct rte_cryptodev *dev = rte_cryptodev_pmd_get_dev(dev_id);
+	struct rte_cryptodev *dev;
+
+	if (!rte_cryptodev_is_valid_device_data(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%" PRIu8, dev_id);
+		return NULL;
+	}
 
+	dev = rte_cryptodev_pmd_get_dev(dev_id);
 	if (dev == NULL)
 		return NULL;
 
diff --git a/lib/librte_cryptodev/rte_cryptodev_pmd.h b/lib/librte_cryptodev/rte_cryptodev_pmd.h
index 089848e..2b40717 100644
--- a/lib/librte_cryptodev/rte_cryptodev_pmd.h
+++ b/lib/librte_cryptodev/rte_cryptodev_pmd.h
@@ -92,7 +92,6 @@ struct rte_cryptodev_global {
 	struct rte_cryptodev_data *data[RTE_CRYPTO_MAX_DEVS];
 	/**< Device private data */
 	uint8_t nb_devs;		/**< Number of devices found */
-	uint8_t max_devs;		/**< Max number of devices */
 };
 
 /* Cryptodev driver, containing the driver ID */
diff --git a/lib/librte_distributor/rte_distributor.c b/lib/librte_distributor/rte_distributor.c
index 6ad2301..00fc003 100644
--- a/lib/librte_distributor/rte_distributor.c
+++ b/lib/librte_distributor/rte_distributor.c
@@ -76,8 +76,11 @@ rte_distributor_request_pkt_v1705(struct rte_distributor *d,
 	}
 
 	retptr64 = &(buf->retptr64[0]);
-	/* Spin while handshake bits are set (scheduler clears it) */
-	while (unlikely(*retptr64 & RTE_DISTRIB_GET_BUF)) {
+	/* Spin while handshake bits are set (scheduler clears it).
+	 * Sync with worker on GET_BUF flag.
+	 */
+	while (unlikely(__atomic_load_n(retptr64, __ATOMIC_ACQUIRE)
+			& RTE_DISTRIB_GET_BUF)) {
 		rte_pause();
 		uint64_t t = rte_rdtsc()+100;
 
@@ -102,8 +105,10 @@ rte_distributor_request_pkt_v1705(struct rte_distributor *d,
 	/*
 	 * Finally, set the GET_BUF  to signal to distributor that cache
 	 * line is ready for processing
+	 * Sync with distributor to release retptrs
 	 */
-	*retptr64 |= RTE_DISTRIB_GET_BUF;
+	__atomic_store_n(retptr64, *retptr64 | RTE_DISTRIB_GET_BUF,
+			__ATOMIC_RELEASE);
 }
 BIND_DEFAULT_SYMBOL(rte_distributor_request_pkt, _v1705, 17.05);
 MAP_STATIC_SYMBOL(void rte_distributor_request_pkt(struct rte_distributor *d,
@@ -125,8 +130,11 @@ rte_distributor_poll_pkt_v1705(struct rte_distributor *d,
 		return (pkts[0]) ? 1 : 0;
 	}
 
-	/* If bit is set, return */
-	if (buf->bufptr64[0] & RTE_DISTRIB_GET_BUF)
+	/* If bit is set, return
+	 * Sync with distributor to acquire bufptrs
+	 */
+	if (__atomic_load_n(&(buf->bufptr64[0]), __ATOMIC_ACQUIRE)
+		& RTE_DISTRIB_GET_BUF)
 		return -1;
 
 	/* since bufptr64 is signed, this should be an arithmetic shift */
@@ -141,8 +149,10 @@ rte_distributor_poll_pkt_v1705(struct rte_distributor *d,
 	 * so now we've got the contents of the cacheline into an  array of
 	 * mbuf pointers, so toggle the bit so scheduler can start working
 	 * on the next cacheline while we're working.
+	 * Sync with distributor on GET_BUF flag. Release bufptrs.
 	 */
-	buf->bufptr64[0] |= RTE_DISTRIB_GET_BUF;
+	__atomic_store_n(&(buf->bufptr64[0]),
+		buf->bufptr64[0] | RTE_DISTRIB_GET_BUF, __ATOMIC_RELEASE);
 
 	return count;
 }
@@ -201,6 +211,8 @@ rte_distributor_return_pkt_v1705(struct rte_distributor *d,
 			return -EINVAL;
 	}
 
+	/* Sync with distributor to acquire retptrs */
+	__atomic_thread_fence(__ATOMIC_ACQUIRE);
 	for (i = 0; i < RTE_DIST_BURST_SIZE; i++)
 		/* Switch off the return bit first */
 		buf->retptr64[i] &= ~RTE_DISTRIB_RETURN_BUF;
@@ -209,8 +221,11 @@ rte_distributor_return_pkt_v1705(struct rte_distributor *d,
 		buf->retptr64[i] = (((int64_t)(uintptr_t)oldpkt[i]) <<
 			RTE_DISTRIB_FLAG_BITS) | RTE_DISTRIB_RETURN_BUF;
 
-	/* set the GET_BUF but even if we got no returns */
-	buf->retptr64[0] |= RTE_DISTRIB_GET_BUF;
+	/* set the GET_BUF but even if we got no returns.
+	 * Sync with distributor on GET_BUF flag. Release retptrs.
+	 */
+	__atomic_store_n(&(buf->retptr64[0]),
+		buf->retptr64[0] | RTE_DISTRIB_GET_BUF, __ATOMIC_RELEASE);
 
 	return 0;
 }
@@ -300,7 +315,9 @@ handle_returns(struct rte_distributor *d, unsigned int wkr)
 	unsigned int count = 0;
 	unsigned int i;
 
-	if (buf->retptr64[0] & RTE_DISTRIB_GET_BUF) {
+	/* Sync on GET_BUF flag. Acquire retptrs. */
+	if (__atomic_load_n(&(buf->retptr64[0]), __ATOMIC_ACQUIRE)
+		& RTE_DISTRIB_GET_BUF) {
 		for (i = 0; i < RTE_DIST_BURST_SIZE; i++) {
 			if (buf->retptr64[i] & RTE_DISTRIB_RETURN_BUF) {
 				oldbuf = ((uintptr_t)(buf->retptr64[i] >>
@@ -313,8 +330,10 @@ handle_returns(struct rte_distributor *d, unsigned int wkr)
 		}
 		d->returns.start = ret_start;
 		d->returns.count = ret_count;
-		/* Clear for the worker to populate with more returns */
-		buf->retptr64[0] = 0;
+		/* Clear for the worker to populate with more returns.
+		 * Sync with distributor on GET_BUF flag. Release retptrs.
+		 */
+		__atomic_store_n(&(buf->retptr64[0]), 0, __ATOMIC_RELEASE);
 	}
 	return count;
 }
@@ -334,7 +353,9 @@ release(struct rte_distributor *d, unsigned int wkr)
 	struct rte_distributor_buffer *buf = &(d->bufs[wkr]);
 	unsigned int i;
 
-	while (!(d->bufs[wkr].bufptr64[0] & RTE_DISTRIB_GET_BUF))
+	/* Sync with worker on GET_BUF flag */
+	while (!(__atomic_load_n(&(d->bufs[wkr].bufptr64[0]), __ATOMIC_ACQUIRE)
+		& RTE_DISTRIB_GET_BUF))
 		rte_pause();
 
 	handle_returns(d, wkr);
@@ -354,8 +375,11 @@ release(struct rte_distributor *d, unsigned int wkr)
 
 	d->backlog[wkr].count = 0;
 
-	/* Clear the GET bit */
-	buf->bufptr64[0] &= ~RTE_DISTRIB_GET_BUF;
+	/* Clear the GET bit.
+	 * Sync with worker on GET_BUF flag. Release bufptrs.
+	 */
+	__atomic_store_n(&(buf->bufptr64[0]),
+		buf->bufptr64[0] & ~RTE_DISTRIB_GET_BUF, __ATOMIC_RELEASE);
 	return  buf->count;
 
 }
@@ -382,7 +406,9 @@ rte_distributor_process_v1705(struct rte_distributor *d,
 	if (unlikely(num_mbufs == 0)) {
 		/* Flush out all non-full cache-lines to workers. */
 		for (wid = 0 ; wid < d->num_workers; wid++) {
-			if ((d->bufs[wid].bufptr64[0] & RTE_DISTRIB_GET_BUF)) {
+			/* Sync with worker on GET_BUF flag. */
+			if (__atomic_load_n(&(d->bufs[wid].bufptr64[0]),
+				__ATOMIC_ACQUIRE) & RTE_DISTRIB_GET_BUF) {
 				release(d, wid);
 				handle_returns(d, wid);
 			}
@@ -394,7 +420,9 @@ rte_distributor_process_v1705(struct rte_distributor *d,
 		uint16_t matches[RTE_DIST_BURST_SIZE];
 		unsigned int pkts;
 
-		if (d->bufs[wkr].bufptr64[0] & RTE_DISTRIB_GET_BUF)
+		/* Sync with worker on GET_BUF flag. */
+		if (__atomic_load_n(&(d->bufs[wkr].bufptr64[0]),
+			__ATOMIC_ACQUIRE) & RTE_DISTRIB_GET_BUF)
 			d->bufs[wkr].count = 0;
 
 		if ((num_mbufs - next_idx) < RTE_DIST_BURST_SIZE)
@@ -492,7 +520,9 @@ rte_distributor_process_v1705(struct rte_distributor *d,
 
 	/* Flush out all non-full cache-lines to workers. */
 	for (wid = 0 ; wid < d->num_workers; wid++)
-		if ((d->bufs[wid].bufptr64[0] & RTE_DISTRIB_GET_BUF))
+		/* Sync with worker on GET_BUF flag. */
+		if ((__atomic_load_n(&(d->bufs[wid].bufptr64[0]),
+			__ATOMIC_ACQUIRE) & RTE_DISTRIB_GET_BUF))
 			release(d, wid);
 
 	return num_mbufs;
@@ -598,7 +628,9 @@ rte_distributor_clear_returns_v1705(struct rte_distributor *d)
 
 	/* throw away returns, so workers can exit */
 	for (wkr = 0; wkr < d->num_workers; wkr++)
-		d->bufs[wkr].retptr64[0] = 0;
+		/* Sync with worker. Release retptrs. */
+		__atomic_store_n(&(d->bufs[wkr].retptr64[0]), 0,
+				__ATOMIC_RELEASE);
 }
 BIND_DEFAULT_SYMBOL(rte_distributor_clear_returns, _v1705, 17.05);
 MAP_STATIC_SYMBOL(void rte_distributor_clear_returns(struct rte_distributor *d),
diff --git a/lib/librte_distributor/rte_distributor_v20.c b/lib/librte_distributor/rte_distributor_v20.c
index 5be6efd..6fede5c 100644
--- a/lib/librte_distributor/rte_distributor_v20.c
+++ b/lib/librte_distributor/rte_distributor_v20.c
@@ -62,9 +62,12 @@ rte_distributor_request_pkt_v20(struct rte_distributor_v20 *d,
 	union rte_distributor_buffer_v20 *buf = &d->bufs[worker_id];
 	int64_t req = (((int64_t)(uintptr_t)oldpkt) << RTE_DISTRIB_FLAG_BITS)
 			| RTE_DISTRIB_GET_BUF;
-	while (unlikely(buf->bufptr64 & RTE_DISTRIB_FLAGS_MASK))
+	while (unlikely(__atomic_load_n(&buf->bufptr64, __ATOMIC_RELAXED)
+			& RTE_DISTRIB_FLAGS_MASK))
 		rte_pause();
-	buf->bufptr64 = req;
+
+	/* Sync with distributor on GET_BUF flag. */
+	__atomic_store_n(&(buf->bufptr64), req, __ATOMIC_RELEASE);
 }
 VERSION_SYMBOL(rte_distributor_request_pkt, _v20, 2.0);
 
@@ -73,7 +76,9 @@ rte_distributor_poll_pkt_v20(struct rte_distributor_v20 *d,
 		unsigned worker_id)
 {
 	union rte_distributor_buffer_v20 *buf = &d->bufs[worker_id];
-	if (buf->bufptr64 & RTE_DISTRIB_GET_BUF)
+	/* Sync with distributor. Acquire bufptr64. */
+	if (__atomic_load_n(&buf->bufptr64, __ATOMIC_ACQUIRE)
+		& RTE_DISTRIB_GET_BUF)
 		return NULL;
 
 	/* since bufptr64 is signed, this should be an arithmetic shift */
@@ -101,7 +106,8 @@ rte_distributor_return_pkt_v20(struct rte_distributor_v20 *d,
 	union rte_distributor_buffer_v20 *buf = &d->bufs[worker_id];
 	uint64_t req = (((int64_t)(uintptr_t)oldpkt) << RTE_DISTRIB_FLAG_BITS)
 			| RTE_DISTRIB_RETURN_BUF;
-	buf->bufptr64 = req;
+	/* Sync with distributor on RETURN_BUF flag. */
+	__atomic_store_n(&(buf->bufptr64), req, __ATOMIC_RELEASE);
 	return 0;
 }
 VERSION_SYMBOL(rte_distributor_return_pkt, _v20, 2.0);
@@ -145,7 +151,8 @@ handle_worker_shutdown(struct rte_distributor_v20 *d, unsigned int wkr)
 {
 	d->in_flight_tags[wkr] = 0;
 	d->in_flight_bitmask &= ~(1UL << wkr);
-	d->bufs[wkr].bufptr64 = 0;
+	/* Sync with worker. Release bufptr64. */
+	__atomic_store_n(&(d->bufs[wkr].bufptr64), 0, __ATOMIC_RELEASE);
 	if (unlikely(d->backlog[wkr].count != 0)) {
 		/* On return of a packet, we need to move the
 		 * queued packets for this core elsewhere.
@@ -189,17 +196,23 @@ process_returns(struct rte_distributor_v20 *d)
 			ret_count = d->returns.count;
 
 	for (wkr = 0; wkr < d->num_workers; wkr++) {
-
-		const int64_t data = d->bufs[wkr].bufptr64;
 		uintptr_t oldbuf = 0;
+		/* Sync with worker. Acquire bufptr64. */
+		const int64_t data = __atomic_load_n(&(d->bufs[wkr].bufptr64),
+							__ATOMIC_ACQUIRE);
 
 		if (data & RTE_DISTRIB_GET_BUF) {
 			flushed++;
 			if (d->backlog[wkr].count)
-				d->bufs[wkr].bufptr64 =
-						backlog_pop(&d->backlog[wkr]);
+				/* Sync with worker. Release bufptr64. */
+				__atomic_store_n(&(d->bufs[wkr].bufptr64),
+					backlog_pop(&d->backlog[wkr]),
+					__ATOMIC_RELEASE);
 			else {
-				d->bufs[wkr].bufptr64 = RTE_DISTRIB_GET_BUF;
+				/* Sync with worker on GET_BUF flag. */
+				__atomic_store_n(&(d->bufs[wkr].bufptr64),
+					RTE_DISTRIB_GET_BUF,
+					__ATOMIC_RELEASE);
 				d->in_flight_tags[wkr] = 0;
 				d->in_flight_bitmask &= ~(1UL << wkr);
 			}
@@ -235,9 +248,10 @@ rte_distributor_process_v20(struct rte_distributor_v20 *d,
 		return process_returns(d);
 
 	while (next_idx < num_mbufs || next_mb != NULL) {
-
-		int64_t data = d->bufs[wkr].bufptr64;
 		uintptr_t oldbuf = 0;
+		/* Sync with worker. Acquire bufptr64. */
+		int64_t data = __atomic_load_n(&(d->bufs[wkr].bufptr64),
+						__ATOMIC_ACQUIRE);
 
 		if (!next_mb) {
 			next_mb = mbufs[next_idx++];
@@ -283,11 +297,16 @@ rte_distributor_process_v20(struct rte_distributor_v20 *d,
 				(d->backlog[wkr].count || next_mb)) {
 
 			if (d->backlog[wkr].count)
-				d->bufs[wkr].bufptr64 =
-						backlog_pop(&d->backlog[wkr]);
+				/* Sync with worker. Release bufptr64. */
+				__atomic_store_n(&(d->bufs[wkr].bufptr64),
+						backlog_pop(&d->backlog[wkr]),
+						__ATOMIC_RELEASE);
 
 			else {
-				d->bufs[wkr].bufptr64 = next_value;
+				/* Sync with worker. Release bufptr64.  */
+				__atomic_store_n(&(d->bufs[wkr].bufptr64),
+						next_value,
+						__ATOMIC_RELEASE);
 				d->in_flight_tags[wkr] = new_tag;
 				d->in_flight_bitmask |= (1UL << wkr);
 				next_mb = NULL;
@@ -308,13 +327,19 @@ rte_distributor_process_v20(struct rte_distributor_v20 *d,
 	 * if they are ready */
 	for (wkr = 0; wkr < d->num_workers; wkr++)
 		if (d->backlog[wkr].count &&
-				(d->bufs[wkr].bufptr64 & RTE_DISTRIB_GET_BUF)) {
+				/* Sync with worker. Acquire bufptr64. */
+				(__atomic_load_n(&(d->bufs[wkr].bufptr64),
+				__ATOMIC_ACQUIRE) & RTE_DISTRIB_GET_BUF)) {
 
 			int64_t oldbuf = d->bufs[wkr].bufptr64 >>
 					RTE_DISTRIB_FLAG_BITS;
+
 			store_return(oldbuf, d, &ret_start, &ret_count);
 
-			d->bufs[wkr].bufptr64 = backlog_pop(&d->backlog[wkr]);
+			/* Sync with worker. Release bufptr64. */
+			__atomic_store_n(&(d->bufs[wkr].bufptr64),
+				backlog_pop(&d->backlog[wkr]),
+				__ATOMIC_RELEASE);
 		}
 
 	d->returns.start = ret_start;
diff --git a/lib/librte_eal/common/eal_common_lcore.c b/lib/librte_eal/common/eal_common_lcore.c
index 0db1555..723f2b2 100644
--- a/lib/librte_eal/common/eal_common_lcore.c
+++ b/lib/librte_eal/common/eal_common_lcore.c
@@ -84,17 +84,6 @@ rte_eal_cpu_init(void)
 		lcore_config[lcore_id].core_role = ROLE_RTE;
 		lcore_config[lcore_id].core_id = eal_cpu_core_id(lcore_id);
 		lcore_config[lcore_id].socket_id = eal_cpu_socket_id(lcore_id);
-		if (lcore_config[lcore_id].socket_id >= RTE_MAX_NUMA_NODES) {
-#ifdef RTE_EAL_ALLOW_INV_SOCKET_ID
-			lcore_config[lcore_id].socket_id = 0;
-#else
-			RTE_LOG(ERR, EAL, "Socket ID (%u) is greater than "
-				"RTE_MAX_NUMA_NODES (%d)\n",
-				lcore_config[lcore_id].socket_id,
-				RTE_MAX_NUMA_NODES);
-			return -1;
-#endif
-		}
 		RTE_LOG(DEBUG, EAL, "Detected lcore %u as "
 				"core %u on socket %u\n",
 				lcore_id, lcore_config[lcore_id].core_id,
diff --git a/lib/librte_eal/common/eal_common_log.c b/lib/librte_eal/common/eal_common_log.c
index 4b2409a..88a3e10 100644
--- a/lib/librte_eal/common/eal_common_log.c
+++ b/lib/librte_eal/common/eal_common_log.c
@@ -56,7 +56,7 @@ struct rte_logs rte_logs = {
 static FILE *default_log_stream;
 
 /**
- * This global structure stores some informations about the message
+ * This global structure stores some information about the message
  * that is currently being processed by one lcore
  */
 struct log_cur_msg {
diff --git a/lib/librte_eal/common/eal_hugepages.h b/lib/librte_eal/common/eal_hugepages.h
index 68369f2..31d745d 100644
--- a/lib/librte_eal/common/eal_hugepages.h
+++ b/lib/librte_eal/common/eal_hugepages.h
@@ -41,7 +41,7 @@
 #define MAX_HUGEPAGE_PATH PATH_MAX
 
 /**
- * Structure used to store informations about hugepages that we mapped
+ * Structure used to store information about hugepages that we mapped
  * through the files in hugetlbfs.
  */
 struct hugepage_file {
diff --git a/lib/librte_eal/common/include/rte_dev.h b/lib/librte_eal/common/include/rte_dev.h
index bc6e592..6f21fde 100644
--- a/lib/librte_eal/common/include/rte_dev.h
+++ b/lib/librte_eal/common/include/rte_dev.h
@@ -281,7 +281,7 @@ __attribute__((used)) = str
  *   "pci:v8086:d*:sv*:sd*"  all PCI devices supported by this driver
  *                           whose vendor id is 0x8086.
  *
- * The format of the kernel modules list is a parenthesed expression
+ * The format of the kernel modules list is a parenthesized expression
  * containing logical-and (&) and logical-or (|).
  *
  * The device pattern and the kmod expression are separated by a space.
diff --git a/lib/librte_eal/common/include/rte_version.h b/lib/librte_eal/common/include/rte_version.h
index 27137a0..c3242e0 100644
--- a/lib/librte_eal/common/include/rte_version.h
+++ b/lib/librte_eal/common/include/rte_version.h
@@ -66,7 +66,7 @@ extern "C" {
 /**
  * Patch level number i.e. the z in yy.mm.z
  */
-#define RTE_VER_MINOR 9
+#define RTE_VER_MINOR 10
 
 /**
  * Extra string to be appended to version number
diff --git a/lib/librte_eal/common/malloc_elem.c b/lib/librte_eal/common/malloc_elem.c
index f6cbc42..02bd958 100644
--- a/lib/librte_eal/common/malloc_elem.c
+++ b/lib/librte_eal/common/malloc_elem.c
@@ -136,6 +136,11 @@ split_elem(struct malloc_elem *elem, struct malloc_elem *split_pt)
 	next_elem->prev = split_pt;
 	elem->size = old_elem_size;
 	set_trailer(elem);
+	if (elem->pad) {
+		/* Update inner padding inner element size. */
+		elem = RTE_PTR_ADD(elem, elem->pad);
+		elem->size = old_elem_size - elem->pad;
+	}
 }
 
 /*
@@ -298,6 +303,8 @@ malloc_elem_free(struct malloc_elem *elem)
 	}
 	malloc_elem_free_list_insert(elem);
 
+	elem->pad = 0;
+
 	/* decrease heap's count of allocated elements */
 	elem->heap->alloc_count--;
 
diff --git a/lib/librte_eal/common/rte_malloc.c b/lib/librte_eal/common/rte_malloc.c
index fe2278b..1d3ab5a 100644
--- a/lib/librte_eal/common/rte_malloc.c
+++ b/lib/librte_eal/common/rte_malloc.c
@@ -177,7 +177,8 @@ rte_realloc(void *ptr, size_t size, unsigned align)
 	void *new_ptr = rte_malloc(NULL, size, align);
 	if (new_ptr == NULL)
 		return NULL;
-	const unsigned old_size = elem->size - MALLOC_ELEM_OVERHEAD;
+	/* elem: |pad|data_elem|data|trailer| */
+	const size_t old_size = elem->size - elem->pad - MALLOC_ELEM_OVERHEAD;
 	rte_memcpy(new_ptr, ptr, old_size < size ? old_size : size);
 	rte_free(ptr);
 
diff --git a/lib/librte_eal/common/rte_service.c b/lib/librte_eal/common/rte_service.c
index 1f92294..71a07dd 100644
--- a/lib/librte_eal/common/rte_service.c
+++ b/lib/librte_eal/common/rte_service.c
@@ -98,10 +98,12 @@ static struct rte_service_spec_impl *rte_services;
 static struct core_state *lcore_states;
 static uint32_t rte_service_library_initialized;
 
-int32_t rte_service_init(void)
+int32_t
+rte_service_init(void)
 {
 	if (rte_service_library_initialized) {
-		printf("service library init() called, init flag %d\n",
+		RTE_LOG(NOTICE, EAL,
+			"service library init() called, init flag %d\n",
 			rte_service_library_initialized);
 		return -EALREADY;
 	}
@@ -110,14 +112,14 @@ int32_t rte_service_init(void)
 			sizeof(struct rte_service_spec_impl),
 			RTE_CACHE_LINE_SIZE);
 	if (!rte_services) {
-		printf("error allocating rte services array\n");
+		RTE_LOG(ERR, EAL, "error allocating rte services array\n");
 		goto fail_mem;
 	}
 
 	lcore_states = rte_calloc("rte_service_core_states", RTE_MAX_LCORE,
 			sizeof(struct core_state), RTE_CACHE_LINE_SIZE);
 	if (!lcore_states) {
-		printf("error allocating core states array\n");
+		RTE_LOG(ERR, EAL, "error allocating core states array\n");
 		goto fail_mem;
 	}
 
@@ -136,10 +138,8 @@ int32_t rte_service_init(void)
 	rte_service_library_initialized = 1;
 	return 0;
 fail_mem:
-	if (rte_services)
-		rte_free(rte_services);
-	if (lcore_states)
-		rte_free(lcore_states);
+	rte_free(rte_services);
+	rte_free(lcore_states);
 	return -ENOMEM;
 }
 
@@ -384,8 +384,8 @@ service_run(uint32_t i, struct core_state *cs, uint64_t service_mask)
 	return 0;
 }
 
-int32_t rte_service_run_iter_on_app_lcore(uint32_t id,
-		uint32_t serialize_mt_unsafe)
+int32_t
+rte_service_run_iter_on_app_lcore(uint32_t id, uint32_t serialize_mt_unsafe)
 {
 	/* run service on calling core, using all-ones as the service mask */
 	if (!service_valid(id))
diff --git a/lib/librte_eal/linuxapp/kni/kni_net.c b/lib/librte_eal/linuxapp/kni/kni_net.c
index db9f489..1802f9d 100644
--- a/lib/librte_eal/linuxapp/kni/kni_net.c
+++ b/lib/librte_eal/linuxapp/kni/kni_net.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 
 #include <exec-env/rte_kni_common.h>
-#include <kni_fifo.h>
+#include "kni_fifo.h"
 
 #include "compat.h"
 #include "kni_dev.h"
diff --git a/lib/librte_efd/rte_efd.c b/lib/librte_efd/rte_efd.c
index 34e0920..f449180 100644
--- a/lib/librte_efd/rte_efd.c
+++ b/lib/librte_efd/rte_efd.c
@@ -208,7 +208,7 @@ struct efd_offline_group_rules {
 	/**< Array with all values of the keys of the group. */
 
 	uint8_t bin_id[EFD_MAX_GROUP_NUM_RULES];
-	/**< Stores the bin for each correspending key to
+	/**< Stores the bin for each corresponding key to
 	 * avoid having to recompute it
 	 */
 };
diff --git a/lib/librte_ether/rte_eth_ctrl.h b/lib/librte_ether/rte_eth_ctrl.h
index 8386904..c1c97bd 100644
--- a/lib/librte_ether/rte_eth_ctrl.h
+++ b/lib/librte_ether/rte_eth_ctrl.h
@@ -36,7 +36,7 @@
 
 #include <stdint.h>
 #include <rte_common.h>
-#include "rte_ether.h"
+#include <rte_ether.h>
 
 /**
  * @file
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index 7998a3a..f116707 100644
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -63,8 +63,8 @@
 #include <rte_errno.h>
 #include <rte_spinlock.h>
 #include <rte_string_fns.h>
+#include <rte_ether.h>
 
-#include "rte_ether.h"
 #include "rte_ethdev.h"
 #include "ethdev_profile.h"
 
@@ -2051,6 +2051,12 @@ rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info)
 	dev_info->rx_desc_lim = lim;
 	dev_info->tx_desc_lim = lim;
 
+	/* Maximum number of queues should be <= RTE_MAX_QUEUES_PER_PORT */
+	dev_info->max_rx_queues = RTE_MIN(dev_info->max_rx_queues,
+			RTE_MAX_QUEUES_PER_PORT);
+	dev_info->max_tx_queues = RTE_MIN(dev_info->max_tx_queues,
+			RTE_MAX_QUEUES_PER_PORT);
+
 	RTE_FUNC_PTR_OR_RET(*dev->dev_ops->dev_infos_get);
 	(*dev->dev_ops->dev_infos_get)(dev, dev_info);
 	dev_info->driver_name = dev->device->driver->name;
diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h
index 1a730d3..16a1508 100644
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -182,8 +182,8 @@ extern "C" {
 #include <rte_errno.h>
 #include <rte_common.h>
 #include <rte_config.h>
+#include <rte_ether.h>
 
-#include "rte_ether.h"
 #include "rte_eth_ctrl.h"
 #include "rte_dev_info.h"
 
@@ -2696,7 +2696,7 @@ int rte_eth_dev_set_mtu(uint16_t port_id, uint16_t mtu);
  *   Otherwise, disable VLAN filtering of VLAN packets tagged with *vlan_id*.
  * @return
  *   - (0) if successful.
- *   - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
+ *   - (-ENOTSUP) if hardware-assisted VLAN filtering not configured.
  *   - (-ENODEV) if *port_id* invalid.
  *   - (-ENOSYS) if VLAN filtering on *port_id* disabled.
  *   - (-EINVAL) if *vlan_id* > 4095.
@@ -2718,7 +2718,7 @@ int rte_eth_dev_vlan_filter(uint16_t port_id, uint16_t vlan_id, int on);
  *   If 0, Disable VLAN Stripping of the receive queue of the Ethernet port.
  * @return
  *   - (0) if successful.
- *   - (-ENOSUP) if hardware-assisted VLAN stripping not configured.
+ *   - (-ENOTSUP) if hardware-assisted VLAN stripping not configured.
  *   - (-ENODEV) if *port_id* invalid.
  *   - (-EINVAL) if *rx_queue_id* invalid.
  */
@@ -2738,7 +2738,7 @@ int rte_eth_dev_set_vlan_strip_on_queue(uint16_t port_id, uint16_t rx_queue_id,
  *   The Tag Protocol ID
  * @return
  *   - (0) if successful.
- *   - (-ENOSUP) if hardware-assisted VLAN TPID setup is not supported.
+ *   - (-ENOTSUP) if hardware-assisted VLAN TPID setup is not supported.
  *   - (-ENODEV) if *port_id* invalid.
  */
 int rte_eth_dev_set_vlan_ether_type(uint16_t port_id,
@@ -2762,7 +2762,7 @@ int rte_eth_dev_set_vlan_ether_type(uint16_t port_id,
  *       ETH_VLAN_EXTEND_OFFLOAD
  * @return
  *   - (0) if successful.
- *   - (-ENOSUP) if hardware-assisted VLAN filtering not configured.
+ *   - (-ENOTSUP) if hardware-assisted VLAN filtering not configured.
  *   - (-ENODEV) if *port_id* invalid.
  */
 int rte_eth_dev_set_vlan_offload(uint16_t port_id, int offload_mask);
diff --git a/lib/librte_ether/rte_flow.h b/lib/librte_ether/rte_flow.h
index 47c88ea..8cbf38d 100644
--- a/lib/librte_ether/rte_flow.h
+++ b/lib/librte_ether/rte_flow.h
@@ -807,7 +807,7 @@ struct rte_flow_item_esp {
 #ifndef __cplusplus
 static const struct rte_flow_item_esp rte_flow_item_esp_mask = {
 	.hdr = {
-		.spi = 0xffffffff,
+		.spi = RTE_BE32(0xffffffff),
 	},
 };
 #endif
diff --git a/lib/librte_power/guest_channel.c b/lib/librte_power/guest_channel.c
index fa5de0f..2c3ee7d 100644
--- a/lib/librte_power/guest_channel.c
+++ b/lib/librte_power/guest_channel.c
@@ -48,7 +48,7 @@
 
 #define RTE_LOGTYPE_GUEST_CHANNEL RTE_LOGTYPE_USER1
 
-static int global_fds[RTE_MAX_LCORE];
+static int global_fds[RTE_MAX_LCORE] = { [0 ... RTE_MAX_LCORE-1] = -1 };
 
 int
 guest_channel_host_connect(const char *path, unsigned lcore_id)
@@ -64,7 +64,7 @@ guest_channel_host_connect(const char *path, unsigned lcore_id)
 		return -1;
 	}
 	/* check if path is already open */
-	if (global_fds[lcore_id] != 0) {
+	if (global_fds[lcore_id] != -1) {
 		RTE_LOG(ERR, GUEST_CHANNEL, "Channel(%u) is already open with fd %d\n",
 				lcore_id, global_fds[lcore_id]);
 		return -1;
@@ -113,7 +113,7 @@ guest_channel_host_connect(const char *path, unsigned lcore_id)
 	return 0;
 error:
 	close(fd);
-	global_fds[lcore_id] = 0;
+	global_fds[lcore_id] = -1;
 	return -1;
 }
 
@@ -129,7 +129,7 @@ guest_channel_send_msg(struct channel_packet *pkt, unsigned lcore_id)
 		return -1;
 	}
 
-	if (global_fds[lcore_id] == 0) {
+	if (global_fds[lcore_id] < 0) {
 		RTE_LOG(ERR, GUEST_CHANNEL, "Channel is not connected\n");
 		return -1;
 	}
@@ -163,8 +163,8 @@ guest_channel_host_disconnect(unsigned lcore_id)
 				lcore_id, RTE_MAX_LCORE-1);
 		return;
 	}
-	if (global_fds[lcore_id] == 0)
+	if (global_fds[lcore_id] < 0)
 		return;
 	close(global_fds[lcore_id]);
-	global_fds[lcore_id] = 0;
+	global_fds[lcore_id] = -1;
 }
diff --git a/lib/librte_power/rte_power_acpi_cpufreq.c b/lib/librte_power/rte_power_acpi_cpufreq.c
index 9a2fa81..63ad029 100644
--- a/lib/librte_power/rte_power_acpi_cpufreq.c
+++ b/lib/librte_power/rte_power_acpi_cpufreq.c
@@ -57,7 +57,7 @@
 
 #define FOPEN_OR_ERR_RET(f, retval) do { \
 		if ((f) == NULL) { \
-			RTE_LOG(ERR, POWER, "File not openned\n"); \
+			RTE_LOG(ERR, POWER, "File not opened\n"); \
 			return retval; \
 		} \
 } while (0)
@@ -136,7 +136,7 @@ set_freq_internal(struct rte_power_info *pi, uint32_t idx)
 	if (idx == pi->curr_idx)
 		return 0;
 
-	POWER_DEBUG_TRACE("Freqency[%u] %u to be set for lcore %u\n",
+	POWER_DEBUG_TRACE("Frequency[%u] %u to be set for lcore %u\n",
 			idx, pi->freqs[idx], pi->lcore_id);
 	if (fseek(pi->f, 0, SEEK_SET) < 0) {
 		RTE_LOG(ERR, POWER, "Fail to set file position indicator to 0 "
@@ -531,7 +531,8 @@ rte_power_acpi_cpufreq_freq_up(unsigned lcore_id)
 	}
 
 	pi = &lcore_power_info[lcore_id];
-	if (pi->curr_idx == 0)
+	if (pi->curr_idx == 0 ||
+	    (pi->curr_idx == 1 && pi->turbo_available && !pi->turbo_enable))
 		return 0;
 
 	/* Frequencies in the array are from high to low. */
diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h
index 935bfac..11e26c5 100644
--- a/lib/librte_ring/rte_ring.h
+++ b/lib/librte_ring/rte_ring.h
@@ -543,11 +543,14 @@ __rte_ring_move_cons_head(struct rte_ring *r, unsigned int is_sc,
 			return 0;
 
 		*new_head = *old_head + n;
-		if (is_sc)
-			r->cons.head = *new_head, success = 1;
-		else
+		if (is_sc) {
+			r->cons.head = *new_head;
+			rte_smp_rmb();
+			success = 1;
+		} else {
 			success = rte_atomic32_cmpset(&r->cons.head, *old_head,
 					*new_head);
+		}
 	} while (unlikely(success == 0));
 	return n;
 }
diff --git a/lib/librte_security/rte_security.h b/lib/librte_security/rte_security.h
index 2b609cb..2c8cf6b 100644
--- a/lib/librte_security/rte_security.h
+++ b/lib/librte_security/rte_security.h
@@ -143,14 +143,14 @@ struct rte_security_ipsec_tunnel_param {
  * IPsec Security Association option flags
  */
 struct rte_security_ipsec_sa_options {
-	/**< Extended Sequence Numbers (ESN)
+	/** Extended Sequence Numbers (ESN)
 	 *
 	 * * 1: Use extended (64 bit) sequence numbers
 	 * * 0: Use normal sequence numbers
 	 */
 	uint32_t esn : 1;
 
-	/**< UDP encapsulation
+	/** UDP encapsulation
 	 *
 	 * * 1: Do UDP encapsulation/decapsulation so that IPSEC packets can
 	 *      traverse through NAT boxes.
@@ -158,7 +158,7 @@ struct rte_security_ipsec_sa_options {
 	 */
 	uint32_t udp_encap : 1;
 
-	/**< Copy DSCP bits
+	/** Copy DSCP bits
 	 *
 	 * * 1: Copy IPv4 or IPv6 DSCP bits from inner IP header to
 	 *      the outer IP header in encapsulation, and vice versa in
@@ -167,7 +167,7 @@ struct rte_security_ipsec_sa_options {
 	 */
 	uint32_t copy_dscp : 1;
 
-	/**< Copy IPv6 Flow Label
+	/** Copy IPv6 Flow Label
 	 *
 	 * * 1: Copy IPv6 flow label from inner IPv6 header to the
 	 *      outer IPv6 header.
@@ -175,7 +175,7 @@ struct rte_security_ipsec_sa_options {
 	 */
 	uint32_t copy_flabel : 1;
 
-	/**< Copy IPv4 Don't Fragment bit
+	/** Copy IPv4 Don't Fragment bit
 	 *
 	 * * 1: Copy the DF bit from the inner IPv4 header to the outer
 	 *      IPv4 header.
@@ -183,7 +183,7 @@ struct rte_security_ipsec_sa_options {
 	 */
 	uint32_t copy_df : 1;
 
-	/**< Decrement inner packet Time To Live (TTL) field
+	/** Decrement inner packet Time To Live (TTL) field
 	 *
 	 * * 1: In tunnel mode, decrement inner packet IPv4 TTL or
 	 *      IPv6 Hop Limit after tunnel decapsulation, or before tunnel
diff --git a/lib/librte_vhost/rte_vhost.h b/lib/librte_vhost/rte_vhost.h
index 3fc6034..eccaa3e 100644
--- a/lib/librte_vhost/rte_vhost.h
+++ b/lib/librte_vhost/rte_vhost.h
@@ -204,7 +204,7 @@ rte_vhost_va_from_guest_pa(struct rte_vhost_memory *mem,
  * @param vid
  *  vhost device ID
  * @param addr
- *  the starting address for write
+ *  the starting address for write (in guest physical address space)
  * @param len
  *  the length to write
  */
diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c
index 2fa7ea0..1933f47 100644
--- a/lib/librte_vhost/socket.c
+++ b/lib/librte_vhost/socket.c
@@ -150,7 +150,7 @@ read_fd_message(int sockfd, char *buf, int buflen, int *fds, int max_fds,
 	}
 
 	if (msgh.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
-		RTE_LOG(ERR, VHOST_CONFIG, "truncted msg\n");
+		RTE_LOG(ERR, VHOST_CONFIG, "truncated msg\n");
 		return -1;
 	}
 
@@ -675,6 +675,14 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	}
 	vsocket->dequeue_zero_copy = flags & RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
 
+	if (vsocket->dequeue_zero_copy &&
+	    (flags & RTE_VHOST_USER_IOMMU_SUPPORT)) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"error: enabling dequeue zero copy and IOMMU features "
+			"simultaneously is not supported\n");
+		goto out_mutex;
+	}
+
 	/*
 	 * Set the supported features correctly for the builtin vhost-user
 	 * net driver.
diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
index a8ed40b..6a8f54f 100644
--- a/lib/librte_vhost/vhost.c
+++ b/lib/librte_vhost/vhost.c
@@ -110,6 +110,180 @@ get_device(int vid)
 	return dev;
 }
 
+#define VHOST_LOG_PAGE	4096
+
+/*
+ * Atomically set a bit in memory.
+ */
+static __rte_always_inline void
+vhost_set_bit(unsigned int nr, volatile uint8_t *addr)
+{
+#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION < 70100)
+	/*
+	 * __sync_ built-ins are deprecated, but __atomic_ ones
+	 * are sub-optimized in older GCC versions.
+	 */
+	__sync_fetch_and_or_1(addr, (1U << nr));
+#else
+	__atomic_fetch_or(addr, (1U << nr), __ATOMIC_RELAXED);
+#endif
+}
+
+static __rte_always_inline void
+vhost_log_page(uint8_t *log_base, uint64_t page)
+{
+	vhost_set_bit(page % 8, &log_base[page / 8]);
+}
+
+void
+__vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
+{
+	uint64_t page;
+
+	if (unlikely(!dev->log_base || !len))
+		return;
+
+	if (unlikely(dev->log_size <= ((addr + len - 1) / VHOST_LOG_PAGE / 8)))
+		return;
+
+	/* To make sure guest memory updates are committed before logging */
+	rte_smp_wmb();
+
+	page = addr / VHOST_LOG_PAGE;
+	while (page * VHOST_LOG_PAGE < addr + len) {
+		vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
+		page += 1;
+	}
+}
+
+void
+__vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
+			     uint64_t iova, uint64_t len)
+{
+	uint64_t hva, gpa, map_len;
+	map_len = len;
+
+	hva = __vhost_iova_to_vva(dev, vq, iova, &map_len, VHOST_ACCESS_RW);
+	if (map_len != len) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Failed to write log for IOVA 0x%" PRIx64 ". No IOTLB entry found\n",
+			iova);
+		return;
+	}
+
+	gpa = hva_to_gpa(dev, hva, len);
+	if (gpa)
+		__vhost_log_write(dev, gpa, len);
+}
+
+void
+__vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+	unsigned long *log_base;
+	int i;
+
+	if (unlikely(!dev->log_base))
+		return;
+
+	log_base = (unsigned long *)(uintptr_t)dev->log_base;
+
+	/*
+	 * It is expected a write memory barrier has been issued
+	 * before this function is called.
+	 */
+
+	for (i = 0; i < vq->log_cache_nb_elem; i++) {
+		struct log_cache_entry *elem = vq->log_cache + i;
+
+#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION < 70100)
+		/*
+		 * '__sync' builtins are deprecated, but '__atomic' ones
+		 * are sub-optimized in older GCC versions.
+		 */
+		__sync_fetch_and_or(log_base + elem->offset, elem->val);
+#else
+		__atomic_fetch_or(log_base + elem->offset, elem->val,
+				__ATOMIC_RELAXED);
+#endif
+	}
+
+	rte_smp_wmb();
+
+	vq->log_cache_nb_elem = 0;
+}
+
+static __rte_always_inline void
+vhost_log_cache_page(struct virtio_net *dev, struct vhost_virtqueue *vq,
+			uint64_t page)
+{
+	uint32_t bit_nr = page % (sizeof(unsigned long) << 3);
+	uint32_t offset = page / (sizeof(unsigned long) << 3);
+	int i;