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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2018-05-24

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

The main changes are:

1) Björn Töpel cleans up AF_XDP (removes rebind, explicit cache alignment from uapi, etc).

2) David Ahern adds mtu checks to bpf_ipv{4,6}_fib_lookup() helpers.

3) Jesper Dangaard Brouer adds bulking support to ndo_xdp_xmit.

4) Jiong Wang adds support for indirect and arithmetic shifts to NFP

5) Martin KaFai Lau cleans up BTF uapi and makes the btf_header extensible.

6) Mathieu Xhonneux adds an End.BPF action to seg6local with BPF helpers allowing
   to edit/grow/shrink a SRH and apply on a packet generic SRv6 actions.

7) Sandipan Das adds support for bpf2bpf function calls in ppc64 JIT.

8) Yonghong Song adds BPF_TASK_FD_QUERY command for introspection of tracing events.

9) other misc fixes from Gustavo A. R. Silva, Sirio Balmelli, John Fastabend, and Magnus Karlsson
====================

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

8 files changed, 470 insertions, 45 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5efa68de935b..9b698c5acd05 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3664,14 +3664,19 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
  * @dev: netdev
  * @xdp: XDP buffer
  *
- * Returns Zero if sent, else an error code
+ * Returns number of frames successfully sent. Frames that fail are
+ * free'ed via XDP return API.
+ *
+ * For error cases, a negative errno code is returned and no-frames
+ * are transmitted (caller must handle freeing frames).
  **/
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
+int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	unsigned int queue_index = smp_processor_id();
 	struct i40e_vsi *vsi = np->vsi;
-	int err;
+	int drops = 0;
+	int i;
 
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
@@ -3679,11 +3684,18 @@ int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
 	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
 		return -ENXIO;
 
-	err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]);
-	if (err != I40E_XDP_TX)
-		return -ENOSPC;
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		int err;
 
-	return 0;
+		err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]);
+		if (err != I40E_XDP_TX) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	return n - drops;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index fdd2c55f03a6..eb8804b3d7b6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -487,7 +487,7 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
 void i40e_detect_recover_hung(struct i40e_vsi *vsi);
 int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf);
+int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames);
 void i40e_xdp_flush(struct net_device *dev);
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a52d92e182ee..031d65c4178d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10022,11 +10022,13 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
-static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
+static int ixgbe_xdp_xmit(struct net_device *dev, int n,
+			  struct xdp_frame **frames)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_ring *ring;
-	int err;
+	int drops = 0;
+	int i;
 
 	if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
 		return -ENETDOWN;
@@ -10038,11 +10040,18 @@ static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
 	if (unlikely(!ring))
 		return -ENXIO;
 
-	err = ixgbe_xmit_xdp_ring(adapter, xdpf);
-	if (err != IXGBE_XDP_TX)
-		return -ENOSPC;
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		int err;
 
-	return 0;
+		err = ixgbe_xmit_xdp_ring(adapter, xdpf);
+		if (err != IXGBE_XDP_TX) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	return n - drops;
 }
 
 static void ixgbe_xdp_flush(struct net_device *dev)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index a4d3da215863..8a92088df0d7 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -212,6 +212,60 @@ emit_br(struct nfp_prog *nfp_prog, enum br_mask mask, u16 addr, u8 defer)
 }
 
 static void
+__emit_br_bit(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 addr, u8 defer,
+	      bool set, bool src_lmextn)
+{
+	u16 addr_lo, addr_hi;
+	u64 insn;
+
+	addr_lo = addr & (OP_BR_BIT_ADDR_LO >> __bf_shf(OP_BR_BIT_ADDR_LO));
+	addr_hi = addr != addr_lo;
+
+	insn = OP_BR_BIT_BASE |
+		FIELD_PREP(OP_BR_BIT_A_SRC, areg) |
+		FIELD_PREP(OP_BR_BIT_B_SRC, breg) |
+		FIELD_PREP(OP_BR_BIT_BV, set) |
+		FIELD_PREP(OP_BR_BIT_DEFBR, defer) |
+		FIELD_PREP(OP_BR_BIT_ADDR_LO, addr_lo) |
+		FIELD_PREP(OP_BR_BIT_ADDR_HI, addr_hi) |
+		FIELD_PREP(OP_BR_BIT_SRC_LMEXTN, src_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void
+emit_br_bit_relo(struct nfp_prog *nfp_prog, swreg src, u8 bit, u16 addr,
+		 u8 defer, bool set, enum nfp_relo_type relo)
+{
+	struct nfp_insn_re_regs reg;
+	int err;
+
+	/* NOTE: The bit to test is specified as an rotation amount, such that
+	 *	 the bit to test will be placed on the MSB of the result when
+	 *	 doing a rotate right. For bit X, we need right rotate X + 1.
+	 */
+	bit += 1;
+
+	err = swreg_to_restricted(reg_none(), src, reg_imm(bit), &reg, false);
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_br_bit(nfp_prog, reg.areg, reg.breg, addr, defer, set,
+		      reg.src_lmextn);
+
+	nfp_prog->prog[nfp_prog->prog_len - 1] |=
+		FIELD_PREP(OP_RELO_TYPE, relo);
+}
+
+static void
+emit_br_bset(struct nfp_prog *nfp_prog, swreg src, u8 bit, u16 addr, u8 defer)
+{
+	emit_br_bit_relo(nfp_prog, src, bit, addr, defer, true, RELO_BR_REL);
+}
+
+static void
 __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi,
 	     enum immed_width width, bool invert,
 	     enum immed_shift shift, bool wr_both,
@@ -310,6 +364,19 @@ emit_shf(struct nfp_prog *nfp_prog, swreg dst,
 }
 
 static void
+emit_shf_indir(struct nfp_prog *nfp_prog, swreg dst,
+	       swreg lreg, enum shf_op op, swreg rreg, enum shf_sc sc)
+{
+	if (sc == SHF_SC_R_ROT) {
+		pr_err("indirect shift is not allowed on rotation\n");
+		nfp_prog->error = -EFAULT;
+		return;
+	}
+
+	emit_shf(nfp_prog, dst, lreg, op, rreg, sc, 0);
+}
+
+static void
 __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab,
 	   u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both,
 	   bool dst_lmextn, bool src_lmextn)
@@ -1629,26 +1696,142 @@ static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+/* Pseudo code:
+ *   if shift_amt >= 32
+ *     dst_high = dst_low << shift_amt[4:0]
+ *     dst_low = 0;
+ *   else
+ *     dst_high = (dst_high, dst_low) >> (32 - shift_amt)
+ *     dst_low = dst_low << shift_amt
+ *
+ * The indirect shift will use the same logic at runtime.
+ */
+static int __shl_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	if (shift_amt < 32) {
+		emit_shf(nfp_prog, reg_both(dst + 1), reg_a(dst + 1),
+			 SHF_OP_NONE, reg_b(dst), SHF_SC_R_DSHF,
+			 32 - shift_amt);
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_L_SHF, shift_amt);
+	} else if (shift_amt == 32) {
+		wrp_reg_mov(nfp_prog, dst + 1, dst);
+		wrp_immed(nfp_prog, reg_both(dst), 0);
+	} else if (shift_amt > 32) {
+		emit_shf(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_L_SHF, shift_amt - 32);
+		wrp_immed(nfp_prog, reg_both(dst), 0);
+	}
+
+	return 0;
+}
+
 static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u8 dst = insn->dst_reg * 2;
 
-	if (insn->imm < 32) {
-		emit_shf(nfp_prog, reg_both(dst + 1),
-			 reg_a(dst + 1), SHF_OP_NONE, reg_b(dst),
-			 SHF_SC_R_DSHF, 32 - insn->imm);
-		emit_shf(nfp_prog, reg_both(dst),
-			 reg_none(), SHF_OP_NONE, reg_b(dst),
-			 SHF_SC_L_SHF, insn->imm);
-	} else if (insn->imm == 32) {
-		wrp_reg_mov(nfp_prog, dst + 1, dst);
-		wrp_immed(nfp_prog, reg_both(dst), 0);
-	} else if (insn->imm > 32) {
-		emit_shf(nfp_prog, reg_both(dst + 1),
-			 reg_none(), SHF_OP_NONE, reg_b(dst),
-			 SHF_SC_L_SHF, insn->imm - 32);
-		wrp_immed(nfp_prog, reg_both(dst), 0);
+	return __shl_imm64(nfp_prog, dst, insn->imm);
+}
+
+static void shl_reg64_lt32_high(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, imm_both(nfp_prog), reg_imm(32), ALU_OP_SUB,
+		 reg_b(src));
+	emit_alu(nfp_prog, reg_none(), imm_a(nfp_prog), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst + 1), reg_a(dst + 1), SHF_OP_NONE,
+		       reg_b(dst), SHF_SC_R_DSHF);
+}
+
+/* NOTE: for indirect left shift, HIGH part should be calculated first. */
+static void shl_reg64_lt32_low(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+		       reg_b(dst), SHF_SC_L_SHF);
+}
+
+static void shl_reg64_lt32(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	shl_reg64_lt32_high(nfp_prog, dst, src);
+	shl_reg64_lt32_low(nfp_prog, dst, src);
+}
+
+static void shl_reg64_ge32(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_NONE,
+		       reg_b(dst), SHF_SC_L_SHF);
+	wrp_immed(nfp_prog, reg_both(dst), 0);
+}
+
+static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin;
+	umax = meta->umax;
+	if (umin == umax)
+		return __shl_imm64(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	if (umax < 32) {
+		shl_reg64_lt32(nfp_prog, dst, src);
+	} else if (umin >= 32) {
+		shl_reg64_ge32(nfp_prog, dst, src);
+	} else {
+		/* Generate different instruction sequences depending on runtime
+		 * value of shift amount.
+		 */
+		u16 label_ge32, label_end;
+
+		label_ge32 = nfp_prog_current_offset(nfp_prog) + 7;
+		emit_br_bset(nfp_prog, reg_a(src), 5, label_ge32, 0);
+
+		shl_reg64_lt32_high(nfp_prog, dst, src);
+		label_end = nfp_prog_current_offset(nfp_prog) + 6;
+		emit_br(nfp_prog, BR_UNC, label_end, 2);
+		/* shl_reg64_lt32_low packed in delay slot. */
+		shl_reg64_lt32_low(nfp_prog, dst, src);
+
+		if (!nfp_prog_confirm_current_offset(nfp_prog, label_ge32))
+			return -EINVAL;
+		shl_reg64_ge32(nfp_prog, dst, src);
+
+		if (!nfp_prog_confirm_current_offset(nfp_prog, label_end))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Pseudo code:
+ *   if shift_amt >= 32
+ *     dst_high = 0;
+ *     dst_low = dst_high >> shift_amt[4:0]
+ *   else
+ *     dst_high = dst_high >> shift_amt
+ *     dst_low = (dst_high, dst_low) >> shift_amt
+ *
+ * The indirect shift will use the same logic at runtime.
+ */
+static int __shr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	if (shift_amt < 32) {
+		emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_R_DSHF, shift_amt);
+		emit_shf(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_NONE,
+			 reg_b(dst + 1), SHF_SC_R_SHF, shift_amt);
+	} else if (shift_amt == 32) {
+		wrp_reg_mov(nfp_prog, dst, dst + 1);
+		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	} else if (shift_amt > 32) {
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+			 reg_b(dst + 1), SHF_SC_R_SHF, shift_amt - 32);
+		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
 	}
 
 	return 0;
@@ -1659,21 +1842,186 @@ static int shr_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	const struct bpf_insn *insn = &meta->insn;
 	u8 dst = insn->dst_reg * 2;
 
-	if (insn->imm < 32) {
-		emit_shf(nfp_prog, reg_both(dst),
-			 reg_a(dst + 1), SHF_OP_NONE, reg_b(dst),
-			 SHF_SC_R_DSHF, insn->imm);
-		emit_shf(nfp_prog, reg_both(dst + 1),
-			 reg_none(), SHF_OP_NONE, reg_b(dst + 1),
-			 SHF_SC_R_SHF, insn->imm);
-	} else if (insn->imm == 32) {
+	return __shr_imm64(nfp_prog, dst, insn->imm);
+}
+
+/* NOTE: for indirect right shift, LOW part should be calculated first. */
+static void shr_reg64_lt32_high(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_NONE,
+		       reg_b(dst + 1), SHF_SC_R_SHF);
+}
+
+static void shr_reg64_lt32_low(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
+		       reg_b(dst), SHF_SC_R_DSHF);
+}
+
+static void shr_reg64_lt32(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	shr_reg64_lt32_low(nfp_prog, dst, src);
+	shr_reg64_lt32_high(nfp_prog, dst, src);
+}
+
+static void shr_reg64_ge32(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+		       reg_b(dst + 1), SHF_SC_R_SHF);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+}
+
+static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin;
+	umax = meta->umax;
+	if (umin == umax)
+		return __shr_imm64(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	if (umax < 32) {
+		shr_reg64_lt32(nfp_prog, dst, src);
+	} else if (umin >= 32) {
+		shr_reg64_ge32(nfp_prog, dst, src);
+	} else {
+		/* Generate different instruction sequences depending on runtime
+		 * value of shift amount.
+		 */
+		u16 label_ge32, label_end;
+
+		label_ge32 = nfp_prog_current_offset(nfp_prog) + 6;
+		emit_br_bset(nfp_prog, reg_a(src), 5, label_ge32, 0);
+		shr_reg64_lt32_low(nfp_prog, dst, src);
+		label_end = nfp_prog_current_offset(nfp_prog) + 6;
+		emit_br(nfp_prog, BR_UNC, label_end, 2);
+		/* shr_reg64_lt32_high packed in delay slot. */
+		shr_reg64_lt32_high(nfp_prog, dst, src);
+
+		if (!nfp_prog_confirm_current_offset(nfp_prog, label_ge32))
+			return -EINVAL;
+		shr_reg64_ge32(nfp_prog, dst, src);
+
+		if (!nfp_prog_confirm_current_offset(nfp_prog, label_end))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Code logic is the same as __shr_imm64 except ashr requires signedness bit
+ * told through PREV_ALU result.
+ */
+static int __ashr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	if (shift_amt < 32) {
+		emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_R_DSHF, shift_amt);
+		/* Set signedness bit. */
+		emit_alu(nfp_prog, reg_none(), reg_a(dst + 1), ALU_OP_OR,
+			 reg_imm(0));
+		emit_shf(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_ASHR,
+			 reg_b(dst + 1), SHF_SC_R_SHF, shift_amt);
+	} else if (shift_amt == 32) {
+		/* NOTE: this also helps setting signedness bit. */
 		wrp_reg_mov(nfp_prog, dst, dst + 1);
-		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
-	} else if (insn->imm > 32) {
-		emit_shf(nfp_prog, reg_both(dst),
-			 reg_none(), SHF_OP_NONE, reg_b(dst + 1),
-			 SHF_SC_R_SHF, insn->imm - 32);
-		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+		emit_shf(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_ASHR,
+			 reg_b(dst + 1), SHF_SC_R_SHF, 31);
+	} else if (shift_amt > 32) {
+		emit_alu(nfp_prog, reg_none(), reg_a(dst + 1), ALU_OP_OR,
+			 reg_imm(0));
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+			 reg_b(dst + 1), SHF_SC_R_SHF, shift_amt - 32);
+		emit_shf(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_ASHR,
+			 reg_b(dst + 1), SHF_SC_R_SHF, 31);
+	}
+
+	return 0;
+}
+
+static int ashr_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	return __ashr_imm64(nfp_prog, dst, insn->imm);
+}
+
+static void ashr_reg64_lt32_high(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	/* NOTE: the first insn will set both indirect shift amount (source A)
+	 * and signedness bit (MSB of result).
+	 */
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_b(dst + 1));
+	emit_shf_indir(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_ASHR,
+		       reg_b(dst + 1), SHF_SC_R_SHF);
+}
+
+static void ashr_reg64_lt32_low(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	/* NOTE: it is the same as logic shift because we don't need to shift in
+	 * signedness bit when the shift amount is less than 32.
+	 */
+	return shr_reg64_lt32_low(nfp_prog, dst, src);
+}
+
+static void ashr_reg64_lt32(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	ashr_reg64_lt32_low(nfp_prog, dst, src);
+	ashr_reg64_lt32_high(nfp_prog, dst, src);
+}
+
+static void ashr_reg64_ge32(struct nfp_prog *nfp_prog, u8 dst, u8 src)
+{
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_b(dst + 1));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+		       reg_b(dst + 1), SHF_SC_R_SHF);
+	emit_shf(nfp_prog, reg_both(dst + 1), reg_none(), SHF_OP_ASHR,
+		 reg_b(dst + 1), SHF_SC_R_SHF, 31);
+}
+
+/* Like ashr_imm64, but need to use indirect shift. */
+static int ashr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin;
+	umax = meta->umax;
+	if (umin == umax)
+		return __ashr_imm64(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	if (umax < 32) {
+		ashr_reg64_lt32(nfp_prog, dst, src);
+	} else if (umin >= 32) {
+		ashr_reg64_ge32(nfp_prog, dst, src);
+	} else {
+		u16 label_ge32, label_end;
+
+		label_ge32 = nfp_prog_current_offset(nfp_prog) + 6;
+		emit_br_bset(nfp_prog, reg_a(src), 5, label_ge32, 0);
+		ashr_reg64_lt32_low(nfp_prog, dst, src);
+		label_end = nfp_prog_current_offset(nfp_prog) + 6;
+		emit_br(nfp_prog, BR_UNC, label_end, 2);
+		/* ashr_reg64_lt32_high packed in delay slot. */
+		ashr_reg64_lt32_high(nfp_prog, dst, src);
+
+		if (!nfp_prog_confirm_current_offset(nfp_prog, label_ge32))
+			return -EINVAL;
+		ashr_reg64_ge32(nfp_prog, dst, src);
+
+		if (!nfp_prog_confirm_current_offset(nfp_prog, label_end))
+			return -EINVAL;
 	}
 
 	return 0;
@@ -2501,8 +2849,12 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_SUB | BPF_X] =	sub_reg64,
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
 	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
+	[BPF_ALU64 | BPF_LSH | BPF_X] =	shl_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
+	[BPF_ALU64 | BPF_RSH | BPF_X] =	shr_reg64,
 	[BPF_ALU64 | BPF_RSH | BPF_K] =	shr_imm64,
+	[BPF_ALU64 | BPF_ARSH | BPF_X] = ashr_reg64,
+	[BPF_ALU64 | BPF_ARSH | BPF_K] = ashr_imm64,
 	[BPF_ALU | BPF_MOV | BPF_X] =	mov_reg,
 	[BPF_ALU | BPF_MOV | BPF_K] =	mov_imm,
 	[BPF_ALU | BPF_XOR | BPF_X] =	xor_reg,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 8b143546ae85..654fe7823e5e 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -263,6 +263,8 @@ 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.
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
@@ -298,6 +300,13 @@ 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.
+		 */
+		struct {
+			u64 umin;
+			u64 umax;
+		};
 	};
 	unsigned int off;
 	unsigned short n;
@@ -375,6 +384,25 @@ 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)
+{
+	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 BPF_SRC(code) == BPF_X;
+}
+
 /**
  * struct nfp_prog - nfp BPF program
  * @bpf: backpointer to the bpf app priv structure
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 4db0ac1e42a8..7eae4c0266f8 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -190,6 +190,8 @@ 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;
 
 		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 844a9be6e55a..4bfeba7b21b2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -551,6 +551,14 @@ 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);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index faa4e131c136..f6677bc9875a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -72,8 +72,21 @@
 #define OP_BR_ADDR_LO		0x007ffc00000ULL
 #define OP_BR_ADDR_HI		0x10000000000ULL
 
-#define nfp_is_br(_insn)				\
-	(((_insn) & OP_BR_BASE_MASK) == OP_BR_BASE)
+#define OP_BR_BIT_BASE		0x0d000000000ULL
+#define OP_BR_BIT_BASE_MASK	0x0f800080300ULL
+#define OP_BR_BIT_A_SRC		0x000000000ffULL
+#define OP_BR_BIT_B_SRC		0x0000003fc00ULL
+#define OP_BR_BIT_BV		0x00000040000ULL
+#define OP_BR_BIT_SRC_LMEXTN	0x40000000000ULL
+#define OP_BR_BIT_DEFBR		OP_BR_DEFBR
+#define OP_BR_BIT_ADDR_LO	OP_BR_ADDR_LO
+#define OP_BR_BIT_ADDR_HI	OP_BR_ADDR_HI
+
+static inline bool nfp_is_br(u64 insn)
+{
+	return (insn & OP_BR_BASE_MASK) == OP_BR_BASE ||
+	       (insn & OP_BR_BIT_BASE_MASK) == OP_BR_BIT_BASE;
+}
 
 enum br_mask {
 	BR_BEQ = 0x00,
@@ -161,6 +174,7 @@ enum shf_op {
 	SHF_OP_NONE = 0,
 	SHF_OP_AND = 2,
 	SHF_OP_OR = 5,
+	SHF_OP_ASHR = 6,
 };
 
 enum shf_sc {