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

Pull networking updates from David Miller:
 "Here is what we have this merge window:

   1) Support SW steering for mlx5 Connect-X6Dx, from Yevgeny Kliteynik.

   2) Add RSS multi group support to octeontx2-pf driver, from Geetha
      Sowjanya.

   3) Add support for KS8851 PHY. From Marek Vasut.

   4) Add support for GarfieldPeak bluetooth controller from Kiran K.

   5) Add support for half-duplex tcan4x5x can controllers.

   6) Add batch skb rx processing to bcrm63xx_enet, from Sieng Piaw
      Liew.

   7) Rework RX port offload infrastructure, particularly wrt, UDP
      tunneling, from Jakub Kicinski.

   8) Add BCM72116 PHY support, from Florian Fainelli.

   9) Remove Dsa specific notifiers, they are unnecessary. From Vladimir
      Oltean.

  10) Add support for picosecond rx delay in dwmac-meson8b chips. From
      Martin Blumenstingl.

  11) Support TSO on xfrm interfaces from Eyal Birger.

  12) Add support for MP_PRIO to mptcp stack, from Geliang Tang.

  13) Support BCM4908 integrated switch, from Rafał Miłecki.

  14) Support for directly accessing kernel module variables via module
      BTF info, from Andrii Naryiko.

  15) Add DASH (esktop and mobile Architecture for System Hardware)
      support to r8169 driver, from Heiner Kallweit.

  16) Add rx vlan filtering to dpaa2-eth, from Ionut-robert Aron.

  17) Add support for 100 base0x SFP devices, from Bjarni Jonasson.

  18) Support link aggregation in DSA, from Tobias Waldekranz.

  19) Support for bitwidse atomics in bpf, from Brendan Jackman.

  20) SmartEEE support in at803x driver, from Russell King.

  21) Add support for flow based tunneling to GTP, from Pravin B Shelar.

  22) Allow arbitrary number of interconnrcts in ipa, from Alex Elder.

  23) TLS RX offload for bonding, from Tariq Toukan.

  24) RX decap offklload support in mac80211, from Felix Fietkou.

  25) devlink health saupport in octeontx2-af, from George Cherian.

  26) Add TTL attr to SCM_TIMESTAMP_OPT_STATS, from Yousuk Seung

  27) Delegated actionss support in mptcp, from Paolo Abeni.

  28) Support receive timestamping when doin zerocopy tcp receive. From
      Arjun Ray.

  29) HTB offload support for mlx5, from Maxim Mikityanskiy.

  30) UDP GRO forwarding, from Maxim Mikityanskiy.

  31) TAPRIO offloading in dsa hellcreek driver, from Kurt Kanzenbach.

  32) Weighted random twos choice algorithm for ipvs, from Darby Payne.

  33) Fix netdev registration deadlock, from Johannes Berg.

  34) Various conversions to new tasklet api, from EmilRenner Berthing.

  35) Bulk skb allocations in veth, from Lorenzo Bianconi.

  36) New ethtool interface for lane setting, from Danielle Ratson.

  37) Offload failiure notifications for routes, from Amit Cohen.

  38) BCM4908 support, from Rafał Miłecki.

  39) Support several new iwlwifi chips, from Ihab Zhaika.

  40) Flow drector support for ipv6 in i40e, from Przemyslaw Patynowski.

  41) Support for mhi prrotocols, from Loic Poulain.

  42) Optimize bpf program stats.

  43) Implement RFC6056, for better port randomization, from Eric
      Dumazet.

  44) hsr tag offloading support from George McCollister.

  45) Netpoll support in qede, from Bhaskar Upadhaya.

  46) 2005/400g speed support in bonding 3ad mode, from Nikolay
      Aleksandrov.

  47) Netlink event support in mptcp, from Florian Westphal.

  48) Better skbuff caching, from Alexander Lobakin.

  49) MRP (Media Redundancy Protocol) offloading in DSA and a few
      drivers, from Horatiu Vultur.

  50) mqprio saupport in mvneta, from Maxime Chevallier.

  51) Remove of_phy_attach, no longer needed, from Florian Fainelli"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1766 commits)
  octeontx2-pf: Fix otx2_get_fecparam()
  cteontx2-pf: cn10k: Prevent harmless double shift bugs
  net: stmmac: Add PCI bus info to ethtool driver query output
  ptp: ptp_clockmatrix: clean-up - parenthesis around a == b are unnecessary
  ptp: ptp_clockmatrix: Simplify code - remove unnecessary `err` variable.
  ptp: ptp_clockmatrix: Coding style - tighten vertical spacing.
  ptp: ptp_clockmatrix: Clean-up dev_*() messages.
  ptp: ptp_clockmatrix: Remove unused header declarations.
  ptp: ptp_clockmatrix: Add alignment of 1 PPS to idtcm_perout_enable.
  ptp: ptp_clockmatrix: Add wait_for_sys_apll_dpll_lock.
  net: stmmac: dwmac-sun8i: Add a shutdown callback
  net: stmmac: dwmac-sun8i: Minor probe function cleanup
  net: stmmac: dwmac-sun8i: Use reset_control_reset
  net: stmmac: dwmac-sun8i: Remove unnecessary PHY power check
  net: stmmac: dwmac-sun8i: Return void from PHY unpower
  r8169: use macro pm_ptr
  net: mdio: Remove of_phy_attach()
  net: mscc: ocelot: select PACKING in the Kconfig
  net: re-solve some conflicts after net -> net-next merge
  net: dsa: tag_rtl4_a: Support also egress tags
  ...

15 files changed, 460 insertions, 156 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 0207b6ea6e8a..897634d0a67c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1620,10 +1620,9 @@ exit:
 		}
 		emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code));
 		break;
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W:
-	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	/* Atomic ops */
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
 		goto notyet;
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_W:
diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
index 994a2fce449a..7c329e173a6d 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
@@ -59,7 +59,7 @@
 
 		CP11X_LABEL(ethernet): ethernet@0 {
 			compatible = "marvell,armada-7k-pp22";
-			reg = <0x0 0x100000>, <0x129000 0xb000>;
+			reg = <0x0 0x100000>, <0x129000 0xb000>, <0x220000 0x800>;
 			clocks = <&CP11X_LABEL(clk) 1 3>, <&CP11X_LABEL(clk) 1 9>,
 				 <&CP11X_LABEL(clk) 1 5>, <&CP11X_LABEL(clk) 1 6>,
 				 <&CP11X_LABEL(clk) 1 18>;
diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
index 22b832fc62e3..003309f0d3e1 100644
--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
@@ -1434,8 +1434,6 @@
 			qcom,smem-state-names = "ipa-clock-enabled-valid",
 						"ipa-clock-enabled";
 
-			modem-remoteproc = <&remoteproc_mpss>;
-
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index bcf888381f14..04b2490eec9f 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -2366,8 +2366,6 @@
 			qcom,smem-state-names = "ipa-clock-enabled-valid",
 						"ipa-clock-enabled";
 
-			modem-remoteproc = <&mss_pil>;
-
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/toshiba/tmpv7708-rm-mbrc.dts b/arch/arm64/boot/dts/toshiba/tmpv7708-rm-mbrc.dts
index ed0bf7f13f54..48fa8776e36f 100644
--- a/arch/arm64/boot/dts/toshiba/tmpv7708-rm-mbrc.dts
+++ b/arch/arm64/boot/dts/toshiba/tmpv7708-rm-mbrc.dts
@@ -41,3 +41,21 @@
 	clocks = <&uart_clk>;
 	clock-names = "apb_pclk";
 };
+
+&piether {
+	status = "okay";
+	phy-handle = <&phy0>;
+	phy-mode = "rgmii-id";
+	clocks = <&clk300mhz>, <&clk125mhz>;
+	clock-names = "stmmaceth", "phy_ref_clk";
+
+	mdio0 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "snps,dwmac-mdio";
+		phy0: ethernet-phy@1 {
+			device_type = "ethernet-phy";
+			reg = <0x1>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/toshiba/tmpv7708.dtsi b/arch/arm64/boot/dts/toshiba/tmpv7708.dtsi
index 242f25f4e12a..3366786699fc 100644
--- a/arch/arm64/boot/dts/toshiba/tmpv7708.dtsi
+++ b/arch/arm64/boot/dts/toshiba/tmpv7708.dtsi
@@ -134,6 +134,20 @@
 		#clock-cells = <0>;
 	};
 
+	clk125mhz: clk125mhz {
+		compatible = "fixed-clock";
+		clock-frequency = <125000000>;
+		#clock-cells = <0>;
+		clock-output-names = "clk125mhz";
+	};
+
+	clk300mhz: clk300mhz {
+		compatible = "fixed-clock";
+		clock-frequency = <300000000>;
+		#clock-cells = <0>;
+		clock-output-names = "clk300mhz";
+	};
+
 	soc {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -384,6 +398,17 @@
 			#size-cells = <0>;
 			status = "disabled";
 		};
+
+		piether: ethernet@28000000 {
+			compatible = "toshiba,visconti-dwmac", "snps,dwmac-4.20a";
+			reg = <0 0x28000000 0 0x10000>;
+			interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			snps,txpbl = <4>;
+			snps,rxpbl = <4>;
+			snps,tso;
+			status = "disabled";
+		};
 	};
 };
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ef9f1d5e989d..f7b194878a99 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -875,10 +875,18 @@ emit_cond_jmp:
 		}
 		break;
 
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W:
-	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (insn->imm != BPF_ADD) {
+			pr_err_once("unknown atomic op code %02x\n", insn->imm);
+			return -EINVAL;
+		}
+
+		/* STX XADD: lock *(u32 *)(dst + off) += src
+		 * and
+		 * STX XADD: lock *(u64 *)(dst + off) += src
+		 */
+
 		if (!off) {
 			reg = dst;
 		} else {
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 561154cbcc40..939dd06764bc 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1423,8 +1423,8 @@ jeq_common:
 	case BPF_STX | BPF_H | BPF_MEM:
 	case BPF_STX | BPF_W | BPF_MEM:
 	case BPF_STX | BPF_DW | BPF_MEM:
-	case BPF_STX | BPF_W | BPF_XADD:
-	case BPF_STX | BPF_DW | BPF_XADD:
+	case BPF_STX | BPF_W | BPF_ATOMIC:
+	case BPF_STX | BPF_DW | BPF_ATOMIC:
 		if (insn->dst_reg == BPF_REG_10) {
 			ctx->flags |= EBPF_SEEN_FP;
 			dst = MIPS_R_SP;
@@ -1438,7 +1438,12 @@ jeq_common:
 		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
 		if (src < 0)
 			return src;
-		if (BPF_MODE(insn->code) == BPF_XADD) {
+		if (BPF_MODE(insn->code) == BPF_ATOMIC) {
+			if (insn->imm != BPF_ADD) {
+				pr_err("ATOMIC OP %02x NOT HANDLED\n", insn->imm);
+				return -EINVAL;
+			}
+
 			/*
 			 * If mem_off does not fit within the 9 bit ll/sc
 			 * instruction immediate field, use a temp reg.
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 022103c6a201..aaf1a887f653 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -683,10 +683,18 @@ emit_clear:
 			break;
 
 		/*
-		 * BPF_STX XADD (atomic_add)
+		 * BPF_STX ATOMIC (atomic ops)
 		 */
-		/* *(u32 *)(dst + off) += src */
-		case BPF_STX | BPF_XADD | BPF_W:
+		case BPF_STX | BPF_ATOMIC | BPF_W:
+			if (insn->imm != BPF_ADD) {
+				pr_err_ratelimited(
+					"eBPF filter atomic op code %02x (@%d) unsupported\n",
+					code, i);
+				return -ENOTSUPP;
+			}
+
+			/* *(u32 *)(dst + off) += src */
+
 			/* Get EA into TMP_REG_1 */
 			EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off));
 			tmp_idx = ctx->idx * 4;
@@ -699,8 +707,15 @@ emit_clear:
 			/* we're done if this succeeded */
 			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
-		/* *(u64 *)(dst + off) += src */
-		case BPF_STX | BPF_XADD | BPF_DW:
+		case BPF_STX | BPF_ATOMIC | BPF_DW:
+			if (insn->imm != BPF_ADD) {
+				pr_err_ratelimited(
+					"eBPF filter atomic op code %02x (@%d) unsupported\n",
+					code, i);
+				return -ENOTSUPP;
+			}
+			/* *(u64 *)(dst + off) += src */
+
 			EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off));
 			tmp_idx = ctx->idx * 4;
 			EMIT(PPC_RAW_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0));
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
index 579575f9cdae..81de865f4c7c 100644
--- a/arch/riscv/net/bpf_jit_comp32.c
+++ b/arch/riscv/net/bpf_jit_comp32.c
@@ -881,7 +881,7 @@ static int emit_store_r64(const s8 *dst, const s8 *src, s16 off,
 	const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
 	const s8 *rs = bpf_get_reg64(src, tmp2, ctx);
 
-	if (mode == BPF_XADD && size != BPF_W)
+	if (mode == BPF_ATOMIC && size != BPF_W)
 		return -1;
 
 	emit_imm(RV_REG_T0, off, ctx);
@@ -899,7 +899,7 @@ static int emit_store_r64(const s8 *dst, const s8 *src, s16 off,
 		case BPF_MEM:
 			emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx);
 			break;
-		case BPF_XADD:
+		case BPF_ATOMIC: /* Only BPF_ADD supported */
 			emit(rv_amoadd_w(RV_REG_ZERO, lo(rs), RV_REG_T0, 0, 0),
 			     ctx);
 			break;
@@ -1260,7 +1260,6 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_STX | BPF_MEM | BPF_H:
 	case BPF_STX | BPF_MEM | BPF_W:
 	case BPF_STX | BPF_MEM | BPF_DW:
-	case BPF_STX | BPF_XADD | BPF_W:
 		if (BPF_CLASS(code) == BPF_ST) {
 			emit_imm32(tmp2, imm, ctx);
 			src = tmp2;
@@ -1271,8 +1270,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			return -1;
 		break;
 
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+		if (insn->imm != BPF_ADD) {
+			pr_info_once(
+				"bpf-jit: not supported: atomic operation %02x ***\n",
+				insn->imm);
+			return -EFAULT;
+		}
+
+		if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code),
+				   BPF_MODE(code)))
+			return -1;
+		break;
+
 	/* No hardware support for 8-byte atomics in RV32. */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
 		/* Fallthrough. */
 
 notsupported:
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 8a56b5293117..b44ff52f84a6 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1027,10 +1027,18 @@ out_be:
 		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
 		emit_sd(RV_REG_T1, 0, rs, ctx);
 		break;
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W:
-	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (insn->imm != BPF_ADD) {
+			pr_err("bpf-jit: not supported: atomic operation %02x ***\n",
+			       insn->imm);
+			return -EINVAL;
+		}
+
+		/* atomic_add: lock *(u32 *)(dst + off) += src
+		 * atomic_add: lock *(u64 *)(dst + off) += src
+		 */
+
 		if (off) {
 			if (is_12b_int(off)) {
 				emit_addi(RV_REG_T1, rd, off, ctx);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 0a4182792876..f973e2ead197 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1205,18 +1205,23 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		jit->seen |= SEEN_MEM;
 		break;
 	/*
-	 * BPF_STX XADD (atomic_add)
+	 * BPF_ATOMIC
 	 */
-	case BPF_STX | BPF_XADD | BPF_W: /* *(u32 *)(dst + off) += src */
-		/* laal %w0,%src,off(%dst) */
-		EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W0, src_reg,
-			      dst_reg, off);
-		jit->seen |= SEEN_MEM;
-		break;
-	case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */
-		/* laalg %w0,%src,off(%dst) */
-		EMIT6_DISP_LH(0xeb000000, 0x00ea, REG_W0, src_reg,
-			      dst_reg, off);
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+		if (insn->imm != BPF_ADD) {
+			pr_err("Unknown atomic operation %02x\n", insn->imm);
+			return -1;
+		}
+
+		/* *(u32/u64 *)(dst + off) += src
+		 *
+		 * BFW_W:  laal  %w0,%src,off(%dst)
+		 * BPF_DW: laalg %w0,%src,off(%dst)
+		 */
+		EMIT6_DISP_LH(0xeb000000,
+			      BPF_SIZE(insn->code) == BPF_W ? 0x00fa : 0x00ea,
+			      REG_W0, src_reg, dst_reg, off);
 		jit->seen |= SEEN_MEM;
 		break;
 	/*
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 3364e2a00989..4b8d3c65d266 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1366,12 +1366,18 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	}
 
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W: {
+	case BPF_STX | BPF_ATOMIC | BPF_W: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->imm != BPF_ADD) {
+			pr_err_once("unknown atomic op %02x\n", insn->imm);
+			return -EINVAL;
+		}
+
+		/* lock *(u32 *)(dst + off) += src */
+
 		if (insn->dst_reg == BPF_REG_FP)
 			ctx->saw_frame_pointer = true;
 
@@ -1390,11 +1396,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	}
 	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW: {
+	case BPF_STX | BPF_ATOMIC | BPF_DW: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->imm != BPF_ADD) {
+			pr_err_once("unknown atomic op %02x\n", insn->imm);
+			return -EINVAL;
+		}
+
 		if (insn->dst_reg == BPF_REG_FP)
 			ctx->saw_frame_pointer = true;
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 796506dcfc42..79e7a0ec1da5 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -205,6 +205,18 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
 }
 
+/* Some 1-byte opcodes for binary ALU operations */
+static u8 simple_alu_opcodes[] = {
+	[BPF_ADD] = 0x01,
+	[BPF_SUB] = 0x29,
+	[BPF_AND] = 0x21,
+	[BPF_OR] = 0x09,
+	[BPF_XOR] = 0x31,
+	[BPF_LSH] = 0xE0,
+	[BPF_RSH] = 0xE8,
+	[BPF_ARSH] = 0xF8,
+};
+
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	/* Fill whole space with INT3 instructions */
@@ -681,6 +693,42 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
 	*pprog = prog;
 }
 
+/* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */
+static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (is_imm8(off)) {
+		/* 1-byte signed displacement.
+		 *
+		 * If off == 0 we could skip this and save one extra byte, but
+		 * special case of x86 R13 which always needs an offset is not
+		 * worth the hassle
+		 */
+		EMIT2(add_2reg(0x40, ptr_reg, val_reg), off);
+	} else {
+		/* 4-byte signed displacement */
+		EMIT1_off32(add_2reg(0x80, ptr_reg, val_reg), off);
+	}
+	*pprog = prog;
+}
+
+/*
+ * Emit a REX byte if it will be necessary to address these registers
+ */
+static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (is64)
+		EMIT1(add_2mod(0x48, dst_reg, src_reg));
+	else if (is_ereg(dst_reg) || is_ereg(src_reg))
+		EMIT1(add_2mod(0x40, dst_reg, src_reg));
+	*pprog = prog;
+}
+
 /* LDX: dst_reg = *(u8*)(src_reg + off) */
 static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 {
@@ -708,15 +756,7 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 		EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
 		break;
 	}
-	/*
-	 * If insn->off == 0 we can save one extra byte, but
-	 * special case of x86 R13 which always needs an offset
-	 * is not worth the hassle
-	 */
-	if (is_imm8(off))
-		EMIT2(add_2reg(0x40, src_reg, dst_reg), off);
-	else
-		EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off);
+	emit_insn_suffix(&prog, src_reg, dst_reg, off);
 	*pprog = prog;
 }
 
@@ -751,11 +791,51 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 		EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
 		break;
 	}
-	if (is_imm8(off))
-		EMIT2(add_2reg(0x40, dst_reg, src_reg), off);
-	else
-		EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off);
+	emit_insn_suffix(&prog, dst_reg, src_reg, off);
+	*pprog = prog;
+}
+
+static int emit_atomic(u8 **pprog, u8 atomic_op,
+		       u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	EMIT1(0xF0); /* lock prefix */
+
+	maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW);
+
+	/* emit opcode */
+	switch (atomic_op) {
+	case BPF_ADD:
+	case BPF_SUB:
+	case BPF_AND:
+	case BPF_OR:
+	case BPF_XOR:
+		/* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */
+		EMIT1(simple_alu_opcodes[atomic_op]);
+		break;
+	case BPF_ADD | BPF_FETCH:
+		/* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */
+		EMIT2(0x0F, 0xC1);
+		break;
+	case BPF_XCHG:
+		/* src_reg = atomic_xchg(dst_reg + off, src_reg); */
+		EMIT1(0x87);
+		break;
+	case BPF_CMPXCHG:
+		/* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
+		EMIT2(0x0F, 0xB1);
+		break;
+	default:
+		pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
+		return -EFAULT;
+	}
+
+	emit_insn_suffix(&prog, dst_reg, src_reg, off);
+
 	*pprog = prog;
+	return 0;
 }
 
 static bool ex_handler_bpf(const struct exception_table_entry *x,
@@ -789,8 +869,31 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
 	}
 }
 
+static int emit_nops(u8 **pprog, int len)
+{
+	u8 *prog = *pprog;
+	int i, noplen, cnt = 0;
+
+	while (len > 0) {
+		noplen = len;
+
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+
+		for (i = 0; i < noplen; i++)
+			EMIT1(ideal_nops[noplen][i]);
+		len -= noplen;
+	}
+
+	*pprog = prog;
+
+	return cnt;
+}
+
+#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
-		  int oldproglen, struct jit_context *ctx)
+		  int oldproglen, struct jit_context *ctx, bool jmp_padding)
 {
 	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
 	struct bpf_insn *insn = bpf_prog->insnsi;
@@ -800,8 +903,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i, cnt = 0, excnt = 0;
-	int proglen = 0;
+	int ilen, proglen = 0;
 	u8 *prog = temp;
+	int err;
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used,
 			 &tail_call_seen);
@@ -813,17 +917,24 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
 		      bpf_prog->aux->func_idx != 0);
 	push_callee_regs(&prog, callee_regs_used);
-	addrs[0] = prog - temp;
+
+	ilen = prog - temp;
+	if (image)
+		memcpy(image + proglen, temp, ilen);
+	proglen += ilen;
+	addrs[0] = proglen;
+	prog = temp;
 
 	for (i = 1; i <= insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
 		u32 dst_reg = insn->dst_reg;
 		u32 src_reg = insn->src_reg;
 		u8 b2 = 0, b3 = 0;
+		u8 *start_of_ldx;
 		s64 jmp_offset;
 		u8 jmp_cond;
-		int ilen;
 		u8 *func;
+		int nops;
 
 		switch (insn->code) {
 			/* ALU */
@@ -837,17 +948,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_AND | BPF_X:
 		case BPF_ALU64 | BPF_OR | BPF_X:
 		case BPF_ALU64 | BPF_XOR | BPF_X:
-			switch (BPF_OP(insn->code)) {
-			case BPF_ADD: b2 = 0x01; break;
-			case BPF_SUB: b2 = 0x29; break;
-			case BPF_AND: b2 = 0x21; break;
-			case BPF_OR: b2 = 0x09; break;
-			case BPF_XOR: b2 = 0x31; break;
-			}
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				EMIT1(add_2mod(0x48, dst_reg, src_reg));
-			else if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			maybe_emit_mod(&prog, dst_reg, src_reg,
+				       BPF_CLASS(insn->code) == BPF_ALU64);
+			b2 = simple_alu_opcodes[BPF_OP(insn->code)];
 			EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
 			break;
 
@@ -1027,12 +1130,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
-			switch (BPF_OP(insn->code)) {
-			case BPF_LSH: b3 = 0xE0; break;
-			case BPF_RSH: b3 = 0xE8; break;
-			case BPF_ARSH: b3 = 0xF8; break;
-			}
-
+			b3 = simple_alu_opcodes[BPF_OP(insn->code)];
 			if (imm32 == 1)
 				EMIT2(0xD1, add_1reg(b3, dst_reg));
 			else
@@ -1066,11 +1164,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
-			switch (BPF_OP(insn->code)) {
-			case BPF_LSH: b3 = 0xE0; break;
-			case BPF_RSH: b3 = 0xE8; break;
-			case BPF_ARSH: b3 = 0xF8; break;
-			}
+			b3 = simple_alu_opcodes[BPF_OP(insn->code)];
 			EMIT2(0xD3, add_1reg(b3, dst_reg));
 
 			if (src_reg != BPF_REG_4)
@@ -1185,12 +1279,30 @@ st:			if (is_imm8(insn->off))
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+				/* test src_reg, src_reg */
+				maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */
+				EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));
+				/* jne start_of_ldx */
+				EMIT2(X86_JNE, 0);
+				/* xor dst_reg, dst_reg */
+				emit_mov_imm32(&prog, false, dst_reg, 0);
+				/* jmp byte_after_ldx */
+				EMIT2(0xEB, 0);
+
+				/* populate jmp_offset for JNE above */
+				temp[4] = prog - temp - 5 /* sizeof(test + jne) */;
+				start_of_ldx = prog;
+			}
 			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
 				struct exception_table_entry *ex;
 				u8 *_insn = image + proglen;
 				s64 delta;
 
+				/* populate jmp_offset for JMP above */
+				start_of_ldx[-1] = prog - start_of_ldx;
+
 				if (!bpf_prog->aux->extable)
 					break;
 
@@ -1230,21 +1342,56 @@ st:			if (is_imm8(insn->off))
 			}
 			break;
 
-			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
-		case BPF_STX | BPF_XADD | BPF_W:
-			/* Emit 'lock add dword ptr [rax + off], eax' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
-			else
-				EMIT2(0xF0, 0x01);
-			goto xadd;
-		case BPF_STX | BPF_XADD | BPF_DW:
-			EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
-xadd:			if (is_imm8(insn->off))
-				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
-			else
-				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
-					    insn->off);
+		case BPF_STX | BPF_ATOMIC | BPF_W:
+		case BPF_STX | BPF_ATOMIC | BPF_DW:
+			if (insn->imm == (BPF_AND | BPF_FETCH) ||
+			    insn->imm == (BPF_OR | BPF_FETCH) ||
+			    insn->imm == (BPF_XOR | BPF_FETCH)) {
+				u8 *branch_target;
+				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+
+				/*
+				 * Can't be implemented with a single x86 insn.
+				 * Need to do a CMPXCHG loop.
+				 */
+
+				/* Will need RAX as a CMPXCHG operand so save R0 */
+				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+				branch_target = prog;
+				/* Load old value */
+				emit_ldx(&prog, BPF_SIZE(insn->code),
+					 BPF_REG_0, dst_reg, insn->off);
+				/*
+				 * Perform the (commutative) operation locally,
+				 * put the result in the AUX_REG.
+				 */
+				emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
+				maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+				EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
+				      add_2reg(0xC0, AUX_REG, src_reg));
+				/* Attempt to swap in new value */
+				err = emit_atomic(&prog, BPF_CMPXCHG,
+						  dst_reg, AUX_REG, insn->off,
+						  BPF_SIZE(insn->code));
+				if (WARN_ON(err))
+					return err;
+				/*
+				 * ZF tells us whether we won the race. If it's
+				 * cleared we need to try again.
+				 */
+				EMIT2(X86_JNE, -(prog - branch_target) - 2);
+				/* Return the pre-modification value */
+				emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+				/* Restore R0 after clobbering RAX */
+				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
+				break;
+
+			}
+
+			err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
+						  insn->off, BPF_SIZE(insn->code));
+			if (err)
+				return err;
 			break;
 
 			/* call */
@@ -1295,20 +1442,16 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSGE | BPF_X:
 		case BPF_JMP32 | BPF_JSLE | BPF_X:
 			/* cmp dst_reg, src_reg */
-			if (BPF_CLASS(insn->code) == BPF_JMP)
-				EMIT1(add_2mod(0x48, dst_reg, src_reg));
-			else if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			maybe_emit_mod(&prog, dst_reg, src_reg,
+				       BPF_CLASS(insn->code) == BPF_JMP);
 			EMIT2(0x39, add_2reg(0xC0, dst_reg, src_reg));
 			goto emit_cond_jmp;
 
 		case BPF_JMP | BPF_JSET | BPF_X:
 		case BPF_JMP32 | BPF_JSET | BPF_X:
 			/* test dst_reg, src_reg */
-			if (BPF_CLASS(insn->code) == BPF_JMP)
-				EMIT1(add_2mod(0x48, dst_reg, src_reg));
-			else if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			maybe_emit_mod(&prog, dst_reg, src_reg,
+				       BPF_CLASS(insn->code) == BPF_JMP);
 			EMIT2(0x85, add_2reg(0xC0, dst_reg, src_reg));
 			goto emit_cond_jmp;
 
@@ -1344,10 +1487,8 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSLE | BPF_K:
 			/* test dst_reg, dst_reg to save one extra byte */
 			if (imm32 == 0) {
-				if (BPF_CLASS(insn->code) == BPF_JMP)
-					EMIT1(add_2mod(0x48, dst_reg, dst_reg));
-				else if (is_ereg(dst_reg))
-					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+				maybe_emit_mod(&prog, dst_reg, dst_reg,
+					       BPF_CLASS(insn->code) == BPF_JMP);
 				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
 				goto emit_cond_jmp;
 			}
@@ -1409,6 +1550,30 @@ emit_cond_jmp:		/* Convert BPF opcode to x86 */
 			}
 			jmp_offset = addrs[i + insn->off] - addrs[i];
 			if (is_imm8(jmp_offset)) {
+				if (jmp_padding) {
+					/* To keep the jmp_offset valid, the extra bytes are
+					 * padded before the jump insn, so we substract the
+					 * 2 bytes of jmp_cond insn from INSN_SZ_DIFF.
+					 *
+					 * If the previous pass already emits an imm8
+					 * jmp_cond, then this BPF insn won't shrink, so
+					 * "nops" is 0.
+					 *
+					 * On the other hand, if the previous pass emits an
+					 * imm32 jmp_cond, the extra 4 bytes(*) is padded to
+					 * keep the image from shrinking further.
+					 *
+					 * (*) imm32 jmp_cond is 6 bytes, and imm8 jmp_cond
+					 *     is 2 bytes, so the size difference is 4 bytes.
+					 */
+					nops = INSN_SZ_DIFF - 2;
+					if (nops != 0 && nops != 4) {
+						pr_err("unexpected jmp_cond padding: %d bytes\n",
+						       nops);
+						return -EFAULT;
+					}
+					cnt += emit_nops(&prog, nops);
+				}
 				EMIT2(jmp_cond, jmp_offset);
 			} else if (is_simm32(jmp_offset)) {
 				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
@@ -1431,11 +1596,55 @@ emit_cond_jmp:		/* Convert BPF opcode to x86 */
 			else
 				jmp_offset = addrs[i + insn->off] - addrs[i];
 
-			if (!jmp_offset)
-				/* Optimize out nop jumps */
+			if (!jmp_offset) {
+				/*
+				 * If jmp_padding is enabled, the extra nops will
+				 * be inserted. Otherwise, optimize out nop jumps.
+				 */
+				if (jmp_padding) {
+					/* There are 3 possible conditions.
+					 * (1) This BPF_JA is already optimized out in
+					 *     the previous run, so there is no need
+					 *     to pad any extra byte (0 byte).
+					 * (2) The previous pass emits an imm8 jmp,
+					 *     so we pad 2 bytes to match the previous
+					 *     insn size.
+					 * (3) Similarly, the previous pass emits an
+					 *     imm32 jmp, and 5 bytes is padded.
+					 */
+					nops = INSN_SZ_DIFF;
+					if (nops != 0 && nops != 2 && nops != 5) {
+						pr_err("unexpected nop jump padding: %d bytes\n",
+						       nops);
+						return -EFAULT;
+					}
+					cnt += emit_nops(&prog, nops);
+				}
 				break;
+			}
 emit_jmp:
 			if (is_imm8(jmp_offset)) {
+				if (jmp_padding) {
+					/* To avoid breaking jmp_offset, the extra bytes
+					 * are padded before the actual jmp insn, so
+					 * 2 bytes is substracted from INSN_SZ_DIFF.
+					 *
+					 * If the previous pass already emits an imm8
+					 * jmp, there is nothing to pad (0 byte).
+					 *
+					 * If it emits an imm32 jmp (5 bytes) previously
+					 * and now an imm8 jmp (2 bytes), then we pad
+					 * (5 - 2 = 3) bytes to stop the image from
+					 * shrinking further.
+					 */
+					nops = INSN_SZ_DIFF - 2;
+					if (nops != 0 && nops != 3) {
+						pr_err("unexpected jump padding: %d bytes\n",
+						       nops);
+						return -EFAULT;
+					}
+					cnt += emit_nops(&prog, INSN_SZ_DIFF - 2);
+				}
 				EMIT2(0xEB, jmp_offset);
 			} else if (is_simm32(jmp_offset)) {
 				EMIT1_off32(0xE9, jmp_offset);
@@ -1531,17 +1740,25 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_prog *p, int stack_size, bool mod_ret)
 {
 	u8 *prog = *pprog;
+	u8 *jmp_insn;
 	int cnt = 0;
 
-	if (p->aux->sleepable) {
-		if (emit_call(&prog, __bpf_prog_enter_sleepable, prog))
-			return -EINVAL;
-	} else {
-		if (emit_call(&prog, __bpf_prog_enter, prog))
+	/* arg1: mov rdi, progs[i] */
+	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
+	if (emit_call(&prog,
+		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
+		      __bpf_prog_enter, prog))
 			return -EINVAL;
-		/* remember prog start time returned by __bpf_prog_enter */
-		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
-	}
+	/* remember prog start time returned by __bpf_prog_enter */
+	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+
+	/* if (__bpf_prog_enter*(prog) == 0)
+	 *	goto skip_exec_of_prog;
+	 */
+	EMIT3(0x48, 0x85, 0xC0);  /* test rax,rax */
+	/* emit 2 nops that will be replaced with JE insn */
+	jmp_insn = prog;
+	emit_nops(&prog, 2);
 
 	/* arg1: lea rdi, [rbp - stack_size] */
 	EMIT4(0x48, 0x8D, 0x7D, -stack_size);
@@ -1561,43 +1778,23 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (mod_ret)
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 
-	if (p->aux->sleepable) {
-		if (emit_call(&prog, __bpf_prog_exit_sleepable, prog))
+	/* replace 2 nops with JE insn, since jmp target is known */
+	jmp_insn[0] = X86_JE;
+	jmp_insn[1] = prog - jmp_insn - 2;
+
+	/* arg1: mov rdi, progs[i] */
+	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
+	/* arg2: mov rsi, rbx <- start time in nsec */
+	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+	if (emit_call(&prog,
+		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
+		      __bpf_prog_exit, prog))
 			return -EINVAL;
-	} else {
-		/* arg1: mov rdi, progs[i] */
-		emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
-			       (u32) (long) p);
-		/* arg2: mov rsi, rbx <- start time in nsec */
-		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
-		if (emit_call(&prog, __bpf_prog_exit, prog))
-			return -EINVAL;
-	}
 
 	*pprog = prog;
 	return 0;
 }
 
-static void emit_nops(u8 **pprog, unsigned int len)
-{
-	unsigned int i, noplen;
-	u8 *prog = *pprog;
-	int cnt = 0;
-
-	while (len > 0) {
-		noplen = len;
-
-		if (noplen > ASM_NOP_MAX)
-			noplen = ASM_NOP_MAX;
-
-		for (i = 0; i < noplen; i++)
-			EMIT1(ideal_nops[noplen][i]);
-		len -= noplen;
-	}
-
-	*pprog = prog;
-}
-
 static void emit_align(u8 **pprog, u32 align)
 {
 	u8 *target, *prog = *pprog;
@@ -1972,6 +2169,9 @@ struct x64_jit_data {
 	struct jit_context ctx;
 };
 
+#define MAX_PASSES 20
+#define PADDING_PASSES (MAX_PASSES - 5)
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;
@@ -1981,6 +2181,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	struct jit_context ctx = {};
 	bool tmp_blinded = false;
 	bool extra_pass = false;
+	bool padding = false;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
@@ -2017,6 +2218,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		image = jit_data->image;
 		header = jit_data->header;
 		extra_pass = true;
+		padding = true;
 		goto skip_init_addrs;
 	}
 	addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
@@ -2042,8 +2244,10 @@ skip_init_addrs:
 	 * may converge on the last pass. In such case do one more
 	 * pass to emit the final image.
 	 */
-	for (pass = 0; pass < 20 || image; pass++) {
-		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
+	for (pass = 0; pass < MAX_PASSES || image; pass++) {
+		if (!padding && pass >= PADDING_PASSES)
+			padding = true;
+		proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding);
 		if (proglen <= 0) {
 out_image:
 			image = NULL;
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 96fde03aa987..d17b67c69f89 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2243,10 +2243,8 @@ emit_jmp:
 				return -EFAULT;
 			}
 			break;
-		/* STX XADD: lock *(u32 *)(dst + off) += src */
-		case BPF_STX | BPF_XADD | BPF_W:
-		/* STX XADD: lock *(u64 *)(dst + off) += src */
-		case BPF_STX | BPF_XADD | BPF_DW:
+		case BPF_STX | BPF_ATOMIC | BPF_W:
+		case BPF_STX | BPF_ATOMIC | BPF_DW:
 			goto notyet;
 		case BPF_JMP | BPF_EXIT:
 			if (seen_exit) {