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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-07-15

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

The main changes are:

1) Various different arm32 JIT improvements in order to optimize code emission
   and make the JIT code itself more robust, from Russell.

2) Support simultaneous driver and offloaded XDP in order to allow for advanced
   use-cases where some work is offloaded to the NIC and some to the host. Also
   add ability for bpftool to load programs and maps beyond just the cgroup case,
   from Jakub.

3) Add BPF JIT support in nfp for multiplication as well as division. For the
   latter in particular, it uses the reciprocal algorithm to emulate it, from Jiong.

4) Add BTF pretty print functionality to bpftool in plain and JSON output
   format, from Okash.

5) Add build and installation to the BPF helper man page into bpftool, from Quentin.

6) Add a TCP BPF callback for listening sockets which is triggered right after
   the socket transitions to TCP_LISTEN state, from Andrey.

7) Add a new cgroup tree command to bpftool which iterates over the whole cgroup
   tree and prints all attached programs, from Roman.

8) Improve xdp_redirect_cpu sample to support parsing of double VLAN tagged
   packets, from Jesper.
====================

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

16 files changed, 403 insertions, 95 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 1f0e872d0667..0584d07c8c33 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -219,7 +219,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		rc = bnxt_xdp_set(bp, xdp->prog);
 		break;
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!bp->xdp_prog;
 		xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
 		rc = 0;
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 135766c4296b..768f584f8392 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1848,7 +1848,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nic->xdp_prog;
 		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 426b0ccb1fc6..51762428b40e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11841,7 +11841,6 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = i40e_enabled_xdp_vsi(vsi);
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bd6d9ea27b4b..5a6600f7b382 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9992,7 +9992,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 59416eddd840..d86446d202d5 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4462,7 +4462,6 @@ static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbevf_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			       adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 65eb06e017e4..6785661d1a72 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2926,7 +2926,6 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx4_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx4_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c7791d036e9f..712b9766485f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4196,7 +4196,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx5e_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx5e_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 33111739b210..1d9e36835404 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -34,10 +34,11 @@
 #define pr_fmt(fmt)	"NFP net bpf: " fmt
 
 #include <linux/bug.h>
-#include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/pkt_cls.h>
+#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 
 #include "main.h"
@@ -416,6 +417,60 @@ emit_alu(struct nfp_prog *nfp_prog, swreg dst,
 }
 
 static void
+__emit_mul(struct nfp_prog *nfp_prog, enum alu_dst_ab dst_ab, u16 areg,
+	   enum mul_type type, enum mul_step step, u16 breg, bool swap,
+	   bool wr_both, bool dst_lmextn, bool src_lmextn)
+{
+	u64 insn;
+
+	insn = OP_MUL_BASE |
+		FIELD_PREP(OP_MUL_A_SRC, areg) |
+		FIELD_PREP(OP_MUL_B_SRC, breg) |
+		FIELD_PREP(OP_MUL_STEP, step) |
+		FIELD_PREP(OP_MUL_DST_AB, dst_ab) |
+		FIELD_PREP(OP_MUL_SW, swap) |
+		FIELD_PREP(OP_MUL_TYPE, type) |
+		FIELD_PREP(OP_MUL_WR_AB, wr_both) |
+		FIELD_PREP(OP_MUL_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_MUL_DST_LMEXTN, dst_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void
+emit_mul(struct nfp_prog *nfp_prog, swreg lreg, enum mul_type type,
+	 enum mul_step step, swreg rreg)
+{
+	struct nfp_insn_ur_regs reg;
+	u16 areg;
+	int err;
+
+	if (type == MUL_TYPE_START && step != MUL_STEP_NONE) {
+		nfp_prog->error = -EINVAL;
+		return;
+	}
+
+	if (step == MUL_LAST || step == MUL_LAST_2) {
+		/* When type is step and step Number is LAST or LAST2, left
+		 * source is used as destination.
+		 */
+		err = swreg_to_unrestricted(lreg, reg_none(), rreg, &reg);
+		areg = reg.dst;
+	} else {
+		err = swreg_to_unrestricted(reg_none(), lreg, rreg, &reg);
+		areg = reg.areg;
+	}
+
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_mul(nfp_prog, reg.dst_ab, areg, type, step, reg.breg, reg.swap,
+		   reg.wr_both, reg.dst_lmextn, reg.src_lmextn);
+}
+
+static void
 __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
 		u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8,
 		bool zero, bool swap, bool wr_both,
@@ -1380,6 +1435,133 @@ static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out)
 		      SHF_SC_R_ROT, 16);
 }
 
+static void
+wrp_mul_u32(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg, bool gen_high_half)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_3, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_4, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_32x32, MUL_LAST, reg_none());
+	if (gen_high_half)
+		emit_mul(nfp_prog, dst_hi, MUL_TYPE_STEP_32x32, MUL_LAST_2,
+			 reg_none());
+	else
+		wrp_immed(nfp_prog, dst_hi, 0);
+}
+
+static void
+wrp_mul_u16(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_16x16, MUL_LAST, reg_none());
+}
+
+static int
+wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	bool gen_high_half, bool ropnd_from_reg)
+{
+	swreg multiplier, multiplicand, dst_hi, dst_lo;
+	const struct bpf_insn *insn = &meta->insn;
+	u32 lopnd_max, ropnd_max;
+	u8 dst_reg;
+
+	dst_reg = insn->dst_reg;
+	multiplicand = reg_a(dst_reg * 2);
+	dst_hi = reg_both(dst_reg * 2 + 1);
+	dst_lo = reg_both(dst_reg * 2);
+	lopnd_max = meta->umax_dst;
+	if (ropnd_from_reg) {
+		multiplier = reg_b(insn->src_reg * 2);
+		ropnd_max = meta->umax_src;
+	} else {
+		u32 imm = insn->imm;
+
+		multiplier = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+		ropnd_max = imm;
+	}
+	if (lopnd_max > U16_MAX || ropnd_max > U16_MAX)
+		wrp_mul_u32(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier,
+			    gen_high_half);
+	else
+		wrp_mul_u16(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier);
+
+	return 0;
+}
+
+static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
+{
+	swreg dst_both = reg_both(dst), dst_a = reg_a(dst), dst_b = reg_a(dst);
+	struct reciprocal_value_adv rvalue;
+	u8 pre_shift, exp;
+	swreg magic;
+
+	if (imm > U32_MAX) {
+		wrp_immed(nfp_prog, dst_both, 0);
+		return 0;
+	}
+
+	/* NOTE: because we are using "reciprocal_value_adv" which doesn't
+	 * support "divisor > (1u << 31)", we need to JIT separate NFP sequence
+	 * to handle such case which actually equals to the result of unsigned
+	 * comparison "dst >= imm" which could be calculated using the following
+	 * NFP sequence:
+	 *
+	 *  alu[--, dst, -, imm]
+	 *  immed[imm, 0]
+	 *  alu[dst, imm, +carry, 0]
+	 *
+	 */
+	if (imm > 1U << 31) {
+		swreg tmp_b = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+
+		emit_alu(nfp_prog, reg_none(), dst_a, ALU_OP_SUB, tmp_b);
+		wrp_immed(nfp_prog, imm_a(nfp_prog), 0);
+		emit_alu(nfp_prog, dst_both, imm_a(nfp_prog), ALU_OP_ADD_C,
+			 reg_imm(0));
+		return 0;
+	}
+
+	rvalue = reciprocal_value_adv(imm, 32);
+	exp = rvalue.exp;
+	if (rvalue.is_wide_m && !(imm & 1)) {
+		pre_shift = fls(imm & -imm) - 1;
+		rvalue = reciprocal_value_adv(imm >> pre_shift, 32 - pre_shift);
+	} else {
+		pre_shift = 0;
+	}
+	magic = ur_load_imm_any(nfp_prog, rvalue.m, imm_b(nfp_prog));
+	if (imm == 1U << exp) {
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, exp);
+	} else if (rvalue.is_wide_m) {
+		wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a,
+			    magic, true);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, 1);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, rvalue.sh - 1);
+	} else {
+		if (pre_shift)
+			emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+				 dst_b, SHF_SC_R_SHF, pre_shift);
+		wrp_mul_u32(nfp_prog, dst_both, reg_none(), dst_a, magic, true);
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+			 dst_b, SHF_SC_R_SHF, rvalue.sh);
+	}
+
+	return 0;
+}
+
 static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	swreg tmp = imm_a(nfp_prog), tmp_len = imm_b(nfp_prog);
@@ -1684,6 +1866,31 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int mul_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, true);
+}
+
+static int mul_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, false);
+}
+
+static int div_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+
+	return wrp_div_imm(nfp_prog, insn->dst_reg * 2, insn->imm);
+}
+
+static int div_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	/* NOTE: verifier hook has rejected cases for which verifier doesn't
+	 * know whether the source operand is constant or not.
+	 */
+	return wrp_div_imm(nfp_prog, meta->insn.dst_reg * 2, meta->umin_src);
+}
+
 static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -1772,8 +1979,8 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shl_imm64(nfp_prog, dst, umin);
 
@@ -1881,8 +2088,8 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shr_imm64(nfp_prog, dst, umin);
 
@@ -1995,8 +2202,8 @@ static int ashr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __ashr_imm64(nfp_prog, dst, umin);
 
@@ -2097,6 +2304,26 @@ static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
 }
 
+static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, true);
+}
+
+static int mul_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, false);
+}
+
+static int div_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_reg64(nfp_prog, meta);
+}
+
+static int div_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_imm64(nfp_prog, meta);
+}
+
 static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	u8 dst = meta->insn.dst_reg * 2;
@@ -2848,6 +3075,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_ADD | BPF_K] =	add_imm64,
 	[BPF_ALU64 | BPF_SUB | BPF_X] =	sub_reg64,
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
+	[BPF_ALU64 | BPF_MUL | BPF_X] =	mul_reg64,
+	[BPF_ALU64 | BPF_MUL | BPF_K] =	mul_imm64,
+	[BPF_ALU64 | BPF_DIV | BPF_X] =	div_reg64,
+	[BPF_ALU64 | BPF_DIV | BPF_K] =	div_imm64,
 	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_X] =	shl_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
@@ -2867,6 +3098,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_ADD | BPF_K] =	add_imm,
 	[BPF_ALU | BPF_SUB | BPF_X] =	sub_reg,
 	[BPF_ALU | BPF_SUB | BPF_K] =	sub_imm,
+	[BPF_ALU | BPF_MUL | BPF_X] =	mul_reg,
+	[BPF_ALU | BPF_MUL | BPF_K] =	mul_imm,
+	[BPF_ALU | BPF_DIV | BPF_X] =	div_reg,
+	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 4dbf7cba6377..b95b94d008cf 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -66,26 +66,19 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 		    struct bpf_prog *prog, struct netlink_ext_ack *extack)
 {
 	bool running, xdp_running;
-	int ret;
 
 	if (!nfp_net_ebpf_capable(nn))
 		return -EINVAL;
 
 	running = nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF;
-	xdp_running = running && nn->dp.bpf_offload_xdp;
+	xdp_running = running && nn->xdp_hw.prog;
 
 	if (!prog && !xdp_running)
 		return 0;
 	if (prog && running && !xdp_running)
 		return -EBUSY;
 
-	ret = nfp_net_bpf_offload(nn, prog, running, extack);
-	/* Stop offload if replace not possible */
-	if (ret)
-		return ret;
-
-	nn->dp.bpf_offload_xdp = !!prog;
-	return ret;
+	return nfp_net_bpf_offload(nn, prog, running, extack);
 }
 
 static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 654fe7823e5e..9845c1a2d4c2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -263,8 +263,10 @@ struct nfp_bpf_reg_state {
  * @func_id: function id for call instructions
  * @arg1: arg1 for call instructions
  * @arg2: arg2 for call instructions
- * @umin: copy of core verifier umin_value.
- * @umax: copy of core verifier umax_value.
+ * @umin_src: copy of core verifier umin_value for src opearnd.
+ * @umax_src: copy of core verifier umax_value for src operand.
+ * @umin_dst: copy of core verifier umin_value for dst opearnd.
+ * @umax_dst: copy of core verifier umax_value for dst operand.
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
@@ -300,12 +302,15 @@ struct nfp_insn_meta {
 			struct bpf_reg_state arg1;
 			struct nfp_bpf_reg_state arg2;
 		};
-		/* We are interested in range info for some operands,
-		 * for example, the shift amount.
+		/* We are interested in range info for operands of ALU
+		 * operations. For example, shift amount, multiplicand and
+		 * multiplier etc.
 		 */
 		struct {
-			u64 umin;
-			u64 umax;
+			u64 umin_src;
+			u64 umax_src;
+			u64 umin_dst;
+			u64 umax_dst;
 		};
 	};
 	unsigned int off;
@@ -339,6 +344,11 @@ static inline u8 mbpf_mode(const struct nfp_insn_meta *meta)
 	return BPF_MODE(meta->insn.code);
 }
 
+static inline bool is_mbpf_alu(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_ALU64 || mbpf_class(meta) == BPF_ALU;
+}
+
 static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
@@ -384,23 +394,14 @@ static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD);
 }
 
-static inline bool is_mbpf_indir_shift(const struct nfp_insn_meta *meta)
+static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta)
 {
-	u8 code = meta->insn.code;
-	bool is_alu, is_shift;
-	u8 opclass, opcode;
-
-	opclass = BPF_CLASS(code);
-	is_alu = opclass == BPF_ALU64 || opclass == BPF_ALU;
-	if (!is_alu)
-		return false;
-
-	opcode = BPF_OP(code);
-	is_shift = opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH;
-	if (!is_shift)
-		return false;
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_MUL;
+}
 
-	return BPF_SRC(code) == BPF_X;
+static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 7eae4c0266f8..78f44c4d95b4 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -190,8 +190,10 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		meta->insn = prog[i];
 		meta->n = i;
-		if (is_mbpf_indir_shift(meta))
-			meta->umin = U64_MAX;
+		if (is_mbpf_alu(meta)) {
+			meta->umin_src = U64_MAX;
+			meta->umin_dst = U64_MAX;
+		}
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 4bfeba7b21b2..49ba0d645d36 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -517,6 +517,82 @@ nfp_bpf_check_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 }
 
 static int
+nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  struct bpf_verifier_env *env)
+{
+	const struct bpf_reg_state *sreg =
+		cur_regs(env) + meta->insn.src_reg;
+	const struct bpf_reg_state *dreg =
+		cur_regs(env) + meta->insn.dst_reg;
+
+	meta->umin_src = min(meta->umin_src, sreg->umin_value);
+	meta->umax_src = max(meta->umax_src, sreg->umax_value);
+	meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
+	meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
+
+	/* NFP supports u16 and u32 multiplication.
+	 *
+	 * For ALU64, if either operand is beyond u32's value range, we reject
+	 * it. One thing to note, if the source operand is BPF_K, then we need
+	 * to check "imm" field directly, and we'd reject it if it is negative.
+	 * Because for ALU64, "imm" (with s32 type) is expected to be sign
+	 * extended to s64 which NFP mul doesn't support.
+	 *
+	 * For ALU32, it is fine for "imm" be negative though, because the
+	 * result is 32-bits and there is no difference on the low halve of
+	 * the result for signed/unsigned mul, so we will get correct result.
+	 */
+	if (is_mbpf_mul(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "multiplier is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X && meta->umax_src > U32_MAX) {
+			pr_vlog(env, "multiplicand is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_class(meta) == BPF_ALU64 &&
+		    mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "sign extended multiplicand won't be within u32 value range\n");
+			return -EINVAL;
+		}
+	}
+
+	/* NFP doesn't have divide instructions, we support divide by constant
+	 * through reciprocal multiplication. Given NFP support multiplication
+	 * no bigger than u32, we'd require divisor and dividend no bigger than
+	 * that as well.
+	 *
+	 * Also eBPF doesn't support signed divide and has enforced this on C
+	 * language level by failing compilation. However LLVM assembler hasn't
+	 * enforced this, so it is possible for negative constant to leak in as
+	 * a BPF_K operand through assembly code, we reject such cases as well.
+	 */
+	if (is_mbpf_div(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "dividend is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X) {
+			if (meta->umin_src != meta->umax_src) {
+				pr_vlog(env, "divisor is not constant\n");
+				return -EINVAL;
+			}
+			if (meta->umax_src > U32_MAX) {
+				pr_vlog(env, "divisor is not within u32 value range\n");
+				return -EINVAL;
+			}
+		}
+		if (mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "divide by negative constant is not supported\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int
 nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 {
 	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
@@ -551,13 +627,8 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	if (is_mbpf_xadd(meta))
 		return nfp_bpf_check_xadd(nfp_prog, meta, env);
 
-	if (is_mbpf_indir_shift(meta)) {
-		const struct bpf_reg_state *sreg =
-			cur_regs(env) + meta->insn.src_reg;
-
-		meta->umin = min(meta->umin, sreg->umin_value);
-		meta->umax = max(meta->umax, sreg->umax_value);
-	}
+	if (is_mbpf_alu(meta))
+		return nfp_bpf_check_alu(nfp_prog, meta, env);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index f6677bc9875a..cdc4e065f6f5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -426,4 +426,32 @@ static inline u32 nfp_get_ind_csr_ctx_ptr_offs(u32 read_offset)
 	return (read_offset & ~NFP_IND_ME_CTX_PTR_BASE_MASK) | NFP_CSR_CTX_PTR;
 }
 
+enum mul_type {
+	MUL_TYPE_START		= 0x00,
+	MUL_TYPE_STEP_24x8	= 0x01,
+	MUL_TYPE_STEP_16x16	= 0x02,
+	MUL_TYPE_STEP_32x32	= 0x03,
+};
+
+enum mul_step {
+	MUL_STEP_1		= 0x00,
+	MUL_STEP_NONE		= MUL_STEP_1,
+	MUL_STEP_2		= 0x01,
+	MUL_STEP_3		= 0x02,
+	MUL_STEP_4		= 0x03,
+	MUL_LAST		= 0x04,
+	MUL_LAST_2		= 0x05,
+};
+
+#define OP_MUL_BASE		0x0f800000000ULL
+#define OP_MUL_A_SRC		0x000000003ffULL
+#define OP_MUL_B_SRC		0x000000ffc00ULL
+#define OP_MUL_STEP		0x00000700000ULL
+#define OP_MUL_DST_AB		0x00000800000ULL
+#define OP_MUL_SW		0x00040000000ULL
+#define OP_MUL_TYPE		0x00180000000ULL
+#define OP_MUL_WR_AB		0x20000000000ULL
+#define OP_MUL_SRC_LMEXTN	0x40000000000ULL
+#define OP_MUL_DST_LMEXTN	0x80000000000ULL
+
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 2a71a9ffd095..8970ec981e11 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -485,7 +485,6 @@ struct nfp_stat_pair {
  * @dev:		Backpointer to struct device
  * @netdev:		Backpointer to net_device structure
  * @is_vf:		Is the driver attached to a VF?
- * @bpf_offload_xdp:	Offloaded BPF program is XDP
  * @chained_metadata_format:  Firemware will use new metadata format
  * @rx_dma_dir:		Mapping direction for RX buffers
  * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
@@ -510,7 +509,6 @@ struct nfp_net_dp {
 	struct net_device *netdev;
 
 	u8 is_vf:1;
-	u8 bpf_offload_xdp:1;
 	u8 chained_metadata_format:1;
 
 	u8 rx_dma_dir;
@@ -553,8 +551,8 @@ struct nfp_net_dp {
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
- * @xdp_flags:		Flags with which XDP prog was loaded
- * @xdp_prog:		XDP prog (for ctrl path, both DRV and HW modes)
+ * @xdp:		Information about the driver XDP program
+ * @xdp_hw:		Information about the HW XDP program
  * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
@@ -610,8 +608,8 @@ struct nfp_net {
 	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
 
-	u32 xdp_flags;
-	struct bpf_prog *xdp_prog;
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 7df5ca37bfb8..a712e83c3f0f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1710,8 +1710,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			}
 		}
 
-		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
-				  dp->bpf_offload_xdp) && !meta.portid) {
+		if (xdp_prog && !meta.portid) {
 			void *orig_data = rxbuf->frag + pkt_off;
 			unsigned int dma_off;
 			int act;
@@ -3393,14 +3392,18 @@ static void nfp_net_del_vxlan_port(struct net_device *netdev,
 		nfp_net_set_vxlan_port(nn, idx, 0);
 }
 
-static int
-nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
-		      struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
+	struct bpf_prog *prog = bpf->prog;
 	struct nfp_net_dp *dp;
+	int err;
+
+	if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
+		return -EBUSY;
 
 	if (!prog == !nn->dp.xdp_prog) {
 		WRITE_ONCE(nn->dp.xdp_prog, prog);
+		xdp_attachment_setup(&nn->xdp, bpf);
 		return 0;
 	}
 
@@ -3414,38 +3417,26 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
 	dp->rx_dma_off = prog ? XDP_PACKET_HEADROOM - nn->dp.rx_offset : 0;
 
 	/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
-	return nfp_net_ring_reconfig(nn, dp, extack);
+	err = nfp_net_ring_reconfig(nn, dp, bpf->extack);
+	if (err)
+		return err;
+
+	xdp_attachment_setup(&nn->xdp, bpf);
+	return 0;
 }
 
-static int
-nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags,
-		  struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
-	struct bpf_prog *drv_prog, *offload_prog;
 	int err;
 
-	if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES)
+	if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf))
 		return -EBUSY;
 
-	/* Load both when no flags set to allow easy activation of driver path
-	 * when program is replaced by one which can't be offloaded.
-	 */
-	drv_prog     = flags & XDP_FLAGS_HW_MODE  ? NULL : prog;
-	offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog;
-
-	err = nfp_net_xdp_setup_drv(nn, drv_prog, extack);
+	err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack);
 	if (err)
 		return err;
 
-	err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack);
-	if (err && flags & XDP_FLAGS_HW_MODE)
-		return err;
-
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-	nn->xdp_prog = prog;
-	nn->xdp_flags = flags;
-
+	xdp_attachment_setup(&nn->xdp_hw, bpf);
 	return 0;
 }
 
@@ -3455,16 +3446,13 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
+		return nfp_net_xdp_setup_drv(nn, xdp);
 	case XDP_SETUP_PROG_HW:
-		return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags,
-					 xdp->extack);
+		return nfp_net_xdp_setup_hw(nn, xdp);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nn->xdp_prog;
-		if (nn->dp.bpf_offload_xdp)
-			xdp->prog_attached = XDP_ATTACHED_HW;
-		xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
-		xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&nn->xdp, xdp);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&nn->xdp_hw, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b823bfe2ea4d..f9a327c821eb 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1116,7 +1116,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!edev->xdp_prog;
 		xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
 		return 0;
 	default: