Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2017-12-03

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Addition of a software model for BPF offloads in order to ease
   testing code changes in that area and make semantics more clear.
   This is implemented in a new driver called netdevsim, which can
   later also be extended for other offloads. SR-IOV support is added
   as well to netdevsim. BPF kernel selftests for offloading are
   added so we can track basic functionality as well as exercising
   all corner cases around BPF offloading, from Jakub.

2) Today drivers have to drop the reference on BPF progs they hold
   due to XDP on device teardown themselves. Change this in order
   to make XDP handling inside the drivers less error prone, and
   move disabling XDP to the core instead, also from Jakub.

3) Misc set of BPF verifier improvements and cleanups as preparatory
   work for upcoming BPF-to-BPF calls. Among others, this set also
   improves liveness marking such that pruning can be slightly more
   effective. Register and stack liveness information is now included
   in the verifier log as well, from Alexei.

4) nfp JIT improvements in order to identify load/store sequences in
   the BPF prog e.g. coming from memcpy lowering and optimizing them
   through the NPU's command push pull (CPP) instruction, from Jiong.

5) Cleanups to test_cgrp2_attach2.c BPF sample code in oder to remove
   bpf_prog_attach() magic values and replacing them with actual proper
   attach flag instead, from David.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

31 files changed, 2362 insertions, 443 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 77d819b458a9..010e46a38373 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9599,6 +9599,11 @@ NETWORKING [WIRELESS]
 L:	linux-wireless@vger.kernel.org
 Q:	http://patchwork.kernel.org/project/linux-wireless/list/
 
+NETDEVSIM
+M:	Jakub Kicinski <jakub.kicinski@netronome.com>
+S:	Maintained
+F:	drivers/net/netdevsim/*
+
 NETXEN (1/10) GbE SUPPORT
 M:	Manish Chopra <manish.chopra@cavium.com>
 M:	Rahul Verma <rahul.verma@cavium.com>
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 0936da592e12..944ec3c9282c 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -497,4 +497,15 @@ config THUNDERBOLT_NET
 
 source "drivers/net/hyperv/Kconfig"
 
+config NETDEVSIM
+	tristate "Simulated networking device"
+	depends on DEBUG_FS
+	help
+	  This driver is a developer testing tool and software model that can
+	  be used to test various control path networking APIs, especially
+	  HW-offload related.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called netdevsim.
+
 endif # NETDEVICES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 766f62d02a0b..04c3b747812c 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -78,3 +78,4 @@ obj-$(CONFIG_FUJITSU_ES) += fjes/
 
 thunderbolt-net-y += thunderbolt.o
 obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
+obj-$(CONFIG_NETDEVSIM) += netdevsim/
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 58483af80bdb..30b1c8512049 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -42,48 +42,7 @@
 #define DRV_NAME	"dummy"
 #define DRV_VERSION	"1.0"
 
-#undef pr_fmt
-#define pr_fmt(fmt) DRV_NAME ": " fmt
-
 static int numdummies = 1;
-static int num_vfs;
-
-struct vf_data_storage {
-	u8	vf_mac[ETH_ALEN];
-	u16	pf_vlan; /* When set, guest VLAN config not allowed. */
-	u16	pf_qos;
-	__be16	vlan_proto;
-	u16	min_tx_rate;
-	u16	max_tx_rate;
-	u8	spoofchk_enabled;
-	bool	rss_query_enabled;
-	u8	trusted;
-	int	link_state;
-};
-
-struct dummy_priv {
-	struct vf_data_storage	*vfinfo;
-};
-
-static int dummy_num_vf(struct device *dev)
-{
-	return num_vfs;
-}
-
-static struct bus_type dummy_bus = {
-	.name	= "dummy",
-	.num_vf	= dummy_num_vf,
-};
-
-static void release_dummy_parent(struct device *dev)
-{
-}
-
-static struct device dummy_parent = {
-	.init_name	= "dummy",
-	.bus		= &dummy_bus,
-	.release	= release_dummy_parent,
-};
 
 /* fake multicast ability */
 static void set_multicast_list(struct net_device *dev)
@@ -133,25 +92,10 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int dummy_dev_init(struct net_device *dev)
 {
-	struct dummy_priv *priv = netdev_priv(dev);
-
 	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
 	if (!dev->dstats)
 		return -ENOMEM;
 
-	priv->vfinfo = NULL;
-
-	if (!num_vfs)
-		return 0;
-
-	dev->dev.parent = &dummy_parent;
-	priv->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage),
-			       GFP_KERNEL);
-	if (!priv->vfinfo) {
-		free_percpu(dev->dstats);
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -169,117 +113,6 @@ static int dummy_change_carrier(struct net_device *dev, bool new_carrier)
 	return 0;
 }
 
-static int dummy_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (!is_valid_ether_addr(mac) || (vf >= num_vfs))
-		return -EINVAL;
-
-	memcpy(priv->vfinfo[vf].vf_mac, mac, ETH_ALEN);
-
-	return 0;
-}
-
-static int dummy_set_vf_vlan(struct net_device *dev, int vf,
-			     u16 vlan, u8 qos, __be16 vlan_proto)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if ((vf >= num_vfs) || (vlan > 4095) || (qos > 7))
-		return -EINVAL;
-
-	priv->vfinfo[vf].pf_vlan = vlan;
-	priv->vfinfo[vf].pf_qos = qos;
-	priv->vfinfo[vf].vlan_proto = vlan_proto;
-
-	return 0;
-}
-
-static int dummy_set_vf_rate(struct net_device *dev, int vf, int min, int max)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].min_tx_rate = min;
-	priv->vfinfo[vf].max_tx_rate = max;
-
-	return 0;
-}
-
-static int dummy_set_vf_spoofchk(struct net_device *dev, int vf, bool val)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].spoofchk_enabled = val;
-
-	return 0;
-}
-
-static int dummy_set_vf_rss_query_en(struct net_device *dev, int vf, bool val)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].rss_query_enabled = val;
-
-	return 0;
-}
-
-static int dummy_set_vf_trust(struct net_device *dev, int vf, bool val)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].trusted = val;
-
-	return 0;
-}
-
-static int dummy_get_vf_config(struct net_device *dev,
-			       int vf, struct ifla_vf_info *ivi)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	ivi->vf = vf;
-	memcpy(&ivi->mac, priv->vfinfo[vf].vf_mac, ETH_ALEN);
-	ivi->vlan = priv->vfinfo[vf].pf_vlan;
-	ivi->qos = priv->vfinfo[vf].pf_qos;
-	ivi->spoofchk = priv->vfinfo[vf].spoofchk_enabled;
-	ivi->linkstate = priv->vfinfo[vf].link_state;
-	ivi->min_tx_rate = priv->vfinfo[vf].min_tx_rate;
-	ivi->max_tx_rate = priv->vfinfo[vf].max_tx_rate;
-	ivi->rss_query_en = priv->vfinfo[vf].rss_query_enabled;
-	ivi->trusted = priv->vfinfo[vf].trusted;
-	ivi->vlan_proto = priv->vfinfo[vf].vlan_proto;
-
-	return 0;
-}
-
-static int dummy_set_vf_link_state(struct net_device *dev, int vf, int state)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	if (vf >= num_vfs)
-		return -EINVAL;
-
-	priv->vfinfo[vf].link_state = state;
-
-	return 0;
-}
-
 static const struct net_device_ops dummy_netdev_ops = {
 	.ndo_init		= dummy_dev_init,
 	.ndo_uninit		= dummy_dev_uninit,
@@ -289,14 +122,6 @@ static const struct net_device_ops dummy_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_get_stats64	= dummy_get_stats64,
 	.ndo_change_carrier	= dummy_change_carrier,
-	.ndo_set_vf_mac		= dummy_set_vf_mac,
-	.ndo_set_vf_vlan	= dummy_set_vf_vlan,
-	.ndo_set_vf_rate	= dummy_set_vf_rate,
-	.ndo_set_vf_spoofchk	= dummy_set_vf_spoofchk,
-	.ndo_set_vf_trust	= dummy_set_vf_trust,
-	.ndo_get_vf_config	= dummy_get_vf_config,
-	.ndo_set_vf_link_state	= dummy_set_vf_link_state,
-	.ndo_set_vf_rss_query_en = dummy_set_vf_rss_query_en,
 };
 
 static void dummy_get_drvinfo(struct net_device *dev,
@@ -323,13 +148,6 @@ static const struct ethtool_ops dummy_ethtool_ops = {
 	.get_ts_info		= dummy_get_ts_info,
 };
 
-static void dummy_free_netdev(struct net_device *dev)
-{
-	struct dummy_priv *priv = netdev_priv(dev);
-
-	kfree(priv->vfinfo);
-}
-
 static void dummy_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -338,7 +156,6 @@ static void dummy_setup(struct net_device *dev)
 	dev->netdev_ops = &dummy_netdev_ops;
 	dev->ethtool_ops = &dummy_ethtool_ops;
 	dev->needs_free_netdev = true;
-	dev->priv_destructor = dummy_free_netdev;
 
 	/* Fill in device structure with ethernet-generic values. */
 	dev->flags |= IFF_NOARP;
@@ -370,7 +187,6 @@ static int dummy_validate(struct nlattr *tb[], struct nlattr *data[],
 
 static struct rtnl_link_ops dummy_link_ops __read_mostly = {
 	.kind		= DRV_NAME,
-	.priv_size	= sizeof(struct dummy_priv),
 	.setup		= dummy_setup,
 	.validate	= dummy_validate,
 };
@@ -379,16 +195,12 @@ static struct rtnl_link_ops dummy_link_ops __read_mostly = {
 module_param(numdummies, int, 0);
 MODULE_PARM_DESC(numdummies, "Number of dummy pseudo devices");
 
-module_param(num_vfs, int, 0);
-MODULE_PARM_DESC(num_vfs, "Number of dummy VFs per dummy device");
-
 static int __init dummy_init_one(void)
 {
 	struct net_device *dev_dummy;
 	int err;
 
-	dev_dummy = alloc_netdev(sizeof(struct dummy_priv),
-				 "dummy%d", NET_NAME_ENUM, dummy_setup);
+	dev_dummy = alloc_netdev(0, "dummy%d", NET_NAME_ENUM, dummy_setup);
 	if (!dev_dummy)
 		return -ENOMEM;
 
@@ -407,21 +219,6 @@ static int __init dummy_init_module(void)
 {
 	int i, err = 0;
 
-	if (num_vfs) {
-		err = bus_register(&dummy_bus);
-		if (err < 0) {
-			pr_err("registering dummy bus failed\n");
-			return err;
-		}
-
-		err = device_register(&dummy_parent);
-		if (err < 0) {
-			pr_err("registering dummy parent device failed\n");
-			bus_unregister(&dummy_bus);
-			return err;
-		}
-	}
-
 	rtnl_lock();
 	err = __rtnl_link_register(&dummy_link_ops);
 	if (err < 0)
@@ -437,22 +234,12 @@ static int __init dummy_init_module(void)
 out:
 	rtnl_unlock();
 
-	if (err && num_vfs) {
-		device_unregister(&dummy_parent);
-		bus_unregister(&dummy_bus);
-	}
-
 	return err;
 }
 
 static void __exit dummy_cleanup_module(void)
 {
 	rtnl_link_unregister(&dummy_link_ops);
-
-	if (num_vfs) {
-		device_unregister(&dummy_parent);
-		bus_unregister(&dummy_bus);
-	}
 }
 
 module_init(dummy_init_module);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c5c38d4b7d1c..8c1dd60eab6f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7800,8 +7800,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
-	if (bp->xdp_prog)
-		bpf_prog_put(bp->xdp_prog);
 	bnxt_cleanup_pci(bp);
 	free_netdev(dev);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d2b057a3e512..0f5c012de52e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4308,9 +4308,6 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_ipsec_cleanup(priv);
 	mlx5e_vxlan_cleanup(priv);
-
-	if (priv->channels.params.xdp_prog)
-		bpf_prog_put(priv->channels.params.xdp_prog);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 995e95410b11..3419ad495962 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2016 Netronome Systems, Inc.
+ * Copyright (C) 2016-2017 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -66,12 +66,6 @@
 	     next2 = nfp_meta_next(next))
 
 static bool
-nfp_meta_has_next(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
-	return meta->l.next != &nfp_prog->insns;
-}
-
-static bool
 nfp_meta_has_prev(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	return meta->l.prev != &nfp_prog->insns;
@@ -102,7 +96,7 @@ nfp_prog_offset_to_index(struct nfp_prog *nfp_prog, unsigned int offset)
 /* --- Emitters --- */
 static void
 __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
-	   u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, bool sync)
+	   u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, bool sync, bool indir)
 {
 	enum cmd_ctx_swap ctx;
 	u64 insn;
@@ -120,14 +114,15 @@ __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
 		FIELD_PREP(OP_CMD_CNT, size) |
 		FIELD_PREP(OP_CMD_SIG, sync) |
 		FIELD_PREP(OP_CMD_TGT_CMD, cmd_tgt_act[op].tgt_cmd) |
+		FIELD_PREP(OP_CMD_INDIR, indir) |
 		FIELD_PREP(OP_CMD_MODE, mode);
 
 	nfp_prog_push(nfp_prog, insn);
 }
 
 static void
-emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
-	 u8 mode, u8 xfer, swreg lreg, swreg rreg, u8 size, bool sync)
+emit_cmd_any(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer,
+	     swreg lreg, swreg rreg, u8 size, bool sync, bool indir)
 {
 	struct nfp_insn_re_regs reg;
 	int err;
@@ -148,7 +143,22 @@ emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
 		return;
 	}
 
-	__emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, sync);
+	__emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, sync,
+		   indir);
+}
+
+static void
+emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer,
+	 swreg lreg, swreg rreg, u8 size, bool sync)
+{
+	emit_cmd_any(nfp_prog, op, mode, xfer, lreg, rreg, size, sync, false);
+}
+
+static void
+emit_cmd_indir(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer,
+	       swreg lreg, swreg rreg, u8 size, bool sync)
+{
+	emit_cmd_any(nfp_prog, op, mode, xfer, lreg, rreg, size, sync, true);
 }
 
 static void
@@ -230,9 +240,11 @@ emit_immed(struct nfp_prog *nfp_prog, swreg dst, u16 imm,
 		return;
 	}
 
-	__emit_immed(nfp_prog, reg.areg, reg.breg, imm >> 8, width,
-		     invert, shift, reg.wr_both,
-		     reg.dst_lmextn, reg.src_lmextn);
+	/* Use reg.dst when destination is No-Dest. */
+	__emit_immed(nfp_prog,
+		     swreg_type(dst) == NN_REG_NONE ? reg.dst : reg.areg,
+		     reg.breg, imm >> 8, width, invert, shift,
+		     reg.wr_both, reg.dst_lmextn, reg.src_lmextn);
 }
 
 static void
@@ -510,6 +522,147 @@ static void wrp_reg_mov(struct nfp_prog *nfp_prog, u16 dst, u16 src)
 	wrp_mov(nfp_prog, reg_both(dst), reg_b(src));
 }
 
+/* wrp_reg_subpart() - load @field_len bytes from @offset of @src, write the
+ * result to @dst from low end.
+ */
+static void
+wrp_reg_subpart(struct nfp_prog *nfp_prog, swreg dst, swreg src, u8 field_len,
+		u8 offset)
+{
+	enum shf_sc sc = offset ? SHF_SC_R_SHF : SHF_SC_NONE;
+	u8 mask = (1 << field_len) - 1;
+
+	emit_ld_field_any(nfp_prog, dst, mask, src, sc, offset * 8, true);
+}
+
+/* NFP has Command Push Pull bus which supports bluk memory operations. */
+static int nfp_cpp_memcpy(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	bool descending_seq = meta->ldst_gather_len < 0;
+	s16 len = abs(meta->ldst_gather_len);
+	swreg src_base, off;
+	unsigned int i;
+	u8 xfer_num;
+
+	off = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog));
+	src_base = reg_a(meta->insn.src_reg * 2);
+	xfer_num = round_up(len, 4) / 4;
+
+	/* Setup PREV_ALU fields to override memory read length. */
+	if (len > 32)
+		wrp_immed(nfp_prog, reg_none(),
+			  CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, xfer_num - 1));
+
+	/* Memory read from source addr into transfer-in registers. */
+	emit_cmd_any(nfp_prog, CMD_TGT_READ32_SWAP, CMD_MODE_32b, 0, src_base,
+		     off, xfer_num - 1, true, len > 32);
+
+	/* Move from transfer-in to transfer-out. */
+	for (i = 0; i < xfer_num; i++)
+		wrp_mov(nfp_prog, reg_xfer(i), reg_xfer(i));
+
+	off = re_load_imm_any(nfp_prog, meta->paired_st->off, imm_b(nfp_prog));
+
+	if (len <= 8) {
+		/* Use single direct_ref write8. */
+		emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
+			 reg_a(meta->paired_st->dst_reg * 2), off, len - 1,
+			 true);
+	} else if (len <= 32 && IS_ALIGNED(len, 4)) {
+		/* Use single direct_ref write32. */
+		emit_cmd(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
+			 reg_a(meta->paired_st->dst_reg * 2), off, xfer_num - 1,
+			 true);
+	} else if (len <= 32) {
+		/* Use single indirect_ref write8. */
+		wrp_immed(nfp_prog, reg_none(),
+			  CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, len - 1));
+		emit_cmd_indir(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
+			       reg_a(meta->paired_st->dst_reg * 2), off,
+			       len - 1, true);
+	} else if (IS_ALIGNED(len, 4)) {
+		/* Use single indirect_ref write32. */
+		wrp_immed(nfp_prog, reg_none(),
+			  CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, xfer_num - 1));
+		emit_cmd_indir(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
+			       reg_a(meta->paired_st->dst_reg * 2), off,
+			       xfer_num - 1, true);
+	} else if (len <= 40) {
+		/* Use one direct_ref write32 to write the first 32-bytes, then
+		 * another direct_ref write8 to write the remaining bytes.
+		 */
+		emit_cmd(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
+			 reg_a(meta->paired_st->dst_reg * 2), off, 7,
+			 true);
+
+		off = re_load_imm_any(nfp_prog, meta->paired_st->off + 32,
+				      imm_b(nfp_prog));
+		emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 8,
+			 reg_a(meta->paired_st->dst_reg * 2), off, len - 33,
+			 true);
+	} else {
+		/* Use one indirect_ref write32 to write 4-bytes aligned length,
+		 * then another direct_ref write8 to write the remaining bytes.
+		 */
+		u8 new_off;
+
+		wrp_immed(nfp_prog, reg_none(),
+			  CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, xfer_num - 2));
+		emit_cmd_indir(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
+			       reg_a(meta->paired_st->dst_reg * 2), off,
+			       xfer_num - 2, true);
+		new_off = meta->paired_st->off + (xfer_num - 1) * 4;
+		off = re_load_imm_any(nfp_prog, new_off, imm_b(nfp_prog));
+		emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b,
+			 xfer_num - 1, reg_a(meta->paired_st->dst_reg * 2), off,
+			 (len & 0x3) - 1, true);
+	}
+
+	/* TODO: The following extra load is to make sure data flow be identical
+	 *  before and after we do memory copy optimization.
+	 *
+	 *  The load destination register is not guaranteed to be dead, so we
+	 *  need to make sure it is loaded with the value the same as before
+	 *  this transformation.
+	 *
+	 *  These extra loads could be removed once we have accurate register
+	 *  usage information.
+	 */
+	if (descending_seq)
+		xfer_num = 0;
+	else if (BPF_SIZE(meta->insn.code) != BPF_DW)
+		xfer_num = xfer_num - 1;
+	else
+		xfer_num = xfer_num - 2;
+
+	switch (BPF_SIZE(meta->insn.code)) {
+	case BPF_B:
+		wrp_reg_subpart(nfp_prog, reg_both(meta->insn.dst_reg * 2),
+				reg_xfer(xfer_num), 1,
+				IS_ALIGNED(len, 4) ? 3 : (len & 3) - 1);
+		break;
+	case BPF_H:
+		wrp_reg_subpart(nfp_prog, reg_both(meta->insn.dst_reg * 2),
+				reg_xfer(xfer_num), 2, (len & 3) ^ 2);
+		break;
+	case BPF_W:
+		wrp_mov(nfp_prog, reg_both(meta->insn.dst_reg * 2),
+			reg_xfer(0));
+		break;
+	case BPF_DW:
+		wrp_mov(nfp_prog, reg_both(meta->insn.dst_reg * 2),
+			reg_xfer(xfer_num));
+		wrp_mov(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1),
+			reg_xfer(xfer_num + 1));
+		break;
+	}
+
+	if (BPF_SIZE(meta->insn.code) != BPF_DW)
+		wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+
+	return 0;
+}
+
 static int
 data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size)
 {
@@ -975,9 +1128,6 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 {
 	const struct bpf_insn *insn = &meta->insn;
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2, alu_op,
 			 insn->src_reg * 2, br_mask, insn->off);
 	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
@@ -995,9 +1145,6 @@ wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u8 reg = insn->dst_reg * 2;
 	swreg tmp_reg;
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
 	if (!swap)
 		emit_alu(nfp_prog, reg_none(), reg_a(reg), ALU_OP_SUB, tmp_reg);
@@ -1027,9 +1174,6 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	areg = insn->dst_reg * 2;
 	breg = insn->src_reg * 2;
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	if (swap) {
 		areg ^= breg;
 		breg ^= areg;
@@ -1494,6 +1638,9 @@ static int
 mem_ldx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	unsigned int size)
 {
+	if (meta->ldst_gather_len)
+		return nfp_cpp_memcpy(nfp_prog, meta);
+
 	if (meta->ptr.type == PTR_TO_CTX) {
 		if (nfp_prog->type == BPF_PROG_TYPE_XDP)
 			return mem_ldx_xdp(nfp_prog, meta, size);
@@ -1630,8 +1777,6 @@ static int mem_stx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int jump(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	if (meta->insn.off < 0) /* TODO */
-		return -EOPNOTSUPP;
 	emit_br(nfp_prog, BR_UNC, meta->insn.off, 0);
 
 	return 0;
@@ -1646,9 +1791,6 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	or1 = reg_a(insn->dst_reg * 2);
 	or2 = reg_b(insn->dst_reg * 2 + 1);
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	if (imm & ~0U) {
 		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
 		emit_alu(nfp_prog, imm_a(nfp_prog),
@@ -1695,9 +1837,6 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u64 imm = insn->imm; /* sign extend */
 	swreg tmp_reg;
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	if (!imm) {
 		meta->skip = true;
 		return 0;
@@ -1726,9 +1865,6 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u64 imm = insn->imm; /* sign extend */
 	swreg tmp_reg;
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	if (!imm) {
 		emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
 			 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
@@ -1753,9 +1889,6 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 
-	if (insn->off < 0) /* TODO */
-		return -EOPNOTSUPP;
-
 	emit_alu(nfp_prog, imm_a(nfp_prog), reg_a(insn->dst_reg * 2),
 		 ALU_OP_XOR, reg_b(insn->src_reg * 2));
 	emit_alu(nfp_prog, imm_b(nfp_prog), reg_a(insn->dst_reg * 2 + 1),
@@ -1887,17 +2020,22 @@ static void br_set_offset(u64 *instr, u16 offset)
 /* --- Assembler logic --- */
 static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 {
-	struct nfp_insn_meta *meta, *next;
-	u32 off, br_idx;
-	u32 idx;
+	struct nfp_insn_meta *meta, *jmp_dst;
+	u32 idx, br_idx;
 
-	nfp_for_each_insn_walk2(nfp_prog, meta, next) {
+	list_for_each_entry(meta, &nfp_prog->insns, l) {
 		if (meta->skip)
 			continue;
 		if (BPF_CLASS(meta->insn.code) != BPF_JMP)
 			continue;
 
-		br_idx = nfp_prog_offset_to_index(nfp_prog, next->off) - 1;
+		if (list_is_last(&meta->l, &nfp_prog->insns))
+			idx = nfp_prog->last_bpf_off;
+		else
+			idx = list_next_entry(meta, l)->off - 1;
+
+		br_idx = nfp_prog_offset_to_index(nfp_prog, idx);
+
 		if (!nfp_is_br(nfp_prog->prog[br_idx])) {
 			pr_err("Fixup found block not ending in branch %d %02x %016llx!!\n",
 			       br_idx, meta->insn.code, nfp_prog->prog[br_idx]);
@@ -1907,23 +2045,14 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 		if (FIELD_GET(OP_BR_SPECIAL, nfp_prog->prog[br_idx]))
 			continue;
 
-		/* Find the target offset in assembler realm */
-		off = meta->insn.off;
-		if (!off) {
-			pr_err("Fixup found zero offset!!\n");
+		if (!meta->jmp_dst) {
+			pr_err("Non-exit jump doesn't have destination info recorded!!\n");
 			return -ELOOP;
 		}
 
-		while (off && nfp_meta_has_next(nfp_prog, next)) {
-			next = nfp_meta_next(next);
-			off--;
-		}
-		if (off) {
-			pr_err("Fixup found too large jump!! %d\n", off);
-			return -ELOOP;
-		}
+		jmp_dst = meta->jmp_dst;
 
-		if (next->skip) {
+		if (jmp_dst->skip) {
 			pr_err("Branch landing on removed instruction!!\n");
 			return -ELOOP;
 		}
@@ -1932,7 +2061,7 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 		     idx <= br_idx; idx++) {
 			if (!nfp_is_br(nfp_prog->prog[idx]))
 				continue;
-			br_set_offset(&nfp_prog->prog[idx], next->off);
+			br_set_offset(&nfp_prog->prog[idx], jmp_dst->off);
 		}
 	}
 
@@ -2105,6 +2234,8 @@ static int nfp_translate(struct nfp_prog *nfp_prog)
 		nfp_prog->n_translated++;
 	}
 
+	nfp_prog->last_bpf_off = nfp_prog_current_offset(nfp_prog) - 1;
+
 	nfp_outro(nfp_prog);
 	if (nfp_prog->error)
 		return nfp_prog->error;
@@ -2173,6 +2304,9 @@ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
 		if (next.src_reg || next.dst_reg)
 			continue;
 
+		if (meta2->flags & FLAG_INSN_IS_JUMP_DST)
+			continue;
+
 		meta2->skip = true;
 	}
 }
@@ -2209,17 +2343,258 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog)
 		if (next1.imm != 0x20 || next2.imm != 0x20)
 			continue;
 
+		if (meta2->flags & FLAG_INSN_IS_JUMP_DST ||
+		    meta3->flags & FLAG_INSN_IS_JUMP_DST)
+			continue;
+
 		meta2->skip = true;
 		meta3->skip = true;
 	}
 }
 
+/* load/store pair that forms memory copy sould look like the following:
+ *
+ *   ld_width R, [addr_src + offset_src]
+ *   st_width [addr_dest + offset_dest], R
+ *
+ * The destination register of load and source register of store should
+ * be the same, load and store should also perform at the same width.
+ * If either of addr_src or addr_dest is stack pointer, we don't do the
+ * CPP optimization as stack is modelled by registers on NFP.
+ */
+static bool
+curr_pair_is_memcpy(struct nfp_insn_meta *ld_meta,
+		    struct nfp_insn_meta *st_meta)
+{
+	struct bpf_insn *ld = &ld_meta->insn;
+	struct bpf_insn *st = &st_meta->insn;
+
+	if (!is_mbpf_load(ld_meta) || !is_mbpf_store(st_meta))
+		return false;
+
+	if (ld_meta->ptr.type != PTR_TO_PACKET)
+		return false;
+
+	if (st_meta->ptr.type != PTR_TO_PACKET)
+		return false;
+
+	if (BPF_SIZE(ld->code) != BPF_SIZE(st->code))
+		return false;
+
+	if (ld->dst_reg != st->src_reg)
+		return false;