Merge tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Remove socket skb caches

   - Add a SO_RESERVE_MEM socket op to forward allocate buffer space and
     avoid memory accounting overhead on each message sent

   - Introduce managed neighbor entries - added by control plane and
     resolved by the kernel for use in acceleration paths (BPF / XDP
     right now, HW offload users will benefit as well)

   - Make neighbor eviction on link down controllable by userspace to
     work around WiFi networks with bad roaming implementations

   - vrf: Rework interaction with netfilter/conntrack

   - fq_codel: implement L4S style ce_threshold_ect1 marking

   - sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()

  BPF:

   - Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
     as implemented in LLVM14

   - Introduce bpf_get_branch_snapshot() to capture Last Branch Records

   - Implement variadic trace_printk helper

   - Add a new Bloomfilter map type

   - Track <8-byte scalar spill and refill

   - Access hw timestamp through BPF's __sk_buff

   - Disallow unprivileged BPF by default

   - Document BPF licensing

  Netfilter:

   - Introduce egress hook for looking at raw outgoing packets

   - Allow matching on and modifying inner headers / payload data

   - Add NFT_META_IFTYPE to match on the interface type either from
     ingress or egress

  Protocols:

   - Multi-Path TCP:
      - increase default max additional subflows to 2
      - rework forward memory allocation
      - add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS

   - MCTP flow support allowing lower layer drivers to configure msg
     muxing as needed

   - Automatic Multicast Tunneling (AMT) driver based on RFC7450

   - HSR support the redbox supervision frames (IEC-62439-3:2018)

   - Support for the ip6ip6 encapsulation of IOAM

   - Netlink interface for CAN-FD's Transmitter Delay Compensation

   - Support SMC-Rv2 eliminating the current same-subnet restriction, by
     exploiting the UDP encapsulation feature of RoCE adapters

   - TLS: add SM4 GCM/CCM crypto support

   - Bluetooth: initial support for link quality and audio/codec offload

  Driver APIs:

   - Add a batched interface for RX buffer allocation in AF_XDP buffer
     pool

   - ethtool: Add ability to control transceiver modules' power mode

   - phy: Introduce supported interfaces bitmap to express MAC
     capabilities and simplify PHY code

   - Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks

  New drivers:

   - WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)

   - Ethernet driver for ASIX AX88796C SPI device (x88796c)

  Drivers:

   - Broadcom PHYs
      - support 72165, 7712 16nm PHYs
      - support IDDQ-SR for additional power savings

   - PHY support for QCA8081, QCA9561 PHYs

   - NXP DPAA2: support for IRQ coalescing

   - NXP Ethernet (enetc): support for software TCP segmentation

   - Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
     Gigabit-capable IP found on RZ/G2L SoC

   - Intel 100G Ethernet
      - support for eswitch offload of TC/OvS flow API, including
        offload of GRE, VxLAN, Geneve tunneling
      - support application device queues - ability to assign Rx and Tx
        queues to application threads
      - PTP and PPS (pulse-per-second) extensions

   - Broadcom Ethernet (bnxt)
      - devlink health reporting and device reload extensions

   - Mellanox Ethernet (mlx5)
      - offload macvlan interfaces
      - support HW offload of TC rules involving OVS internal ports
      - support HW-GRO and header/data split
      - support application device queues

   - Marvell OcteonTx2:
      - add XDP support for PF
      - add PTP support for VF

   - Qualcomm Ethernet switch (qca8k): support for QCA8328

   - Realtek Ethernet DSA switch (rtl8366rb)
      - support bridge offload
      - support STP, fast aging, disabling address learning
      - support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch

   - Mellanox Ethernet/IB switch (mlxsw)
      - multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
      - offload root TBF qdisc as port shaper
      - support multiple routing interface MAC address prefixes
      - support for IP-in-IP with IPv6 underlay

   - MediaTek WiFi (mt76)
      - mt7921 - ASPM, 6GHz, SDIO and testmode support
      - mt7915 - LED and TWT support

   - Qualcomm WiFi (ath11k)
      - include channel rx and tx time in survey dump statistics
      - support for 80P80 and 160 MHz bandwidths
      - support channel 2 in 6 GHz band
      - spectral scan support for QCN9074
      - support for rx decapsulation offload (data frames in 802.3
        format)

   - Qualcomm phone SoC WiFi (wcn36xx)
      - enable Idle Mode Power Save (IMPS) to reduce power consumption
        during idle

   - Bluetooth driver support for MediaTek MT7922 and MT7921

   - Enable support for AOSP Bluetooth extension in Qualcomm WCN399x and
     Realtek 8822C/8852A

   - Microsoft vNIC driver (mana)
      - support hibernation and kexec

   - Google vNIC driver (gve)
      - support for jumbo frames
      - implement Rx page reuse

  Refactor:

   - Make all writes to netdev->dev_addr go thru helpers, so that we can
     add this address to the address rbtree and handle the updates

   - Various TCP cleanups and optimizations including improvements to
     CPU cache use

   - Simplify the gnet_stats, Qdisc stats' handling and remove
     qdisc->running sequence counter

   - Driver changes and API updates to address devlink locking
     deficiencies"

* tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2122 commits)
  Revert "net: avoid double accounting for pure zerocopy skbs"
  selftests: net: add arp_ndisc_evict_nocarrier
  net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter
  net: arp: introduce arp_evict_nocarrier sysctl parameter
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  net: vmxnet3: remove multiple false checks in vmxnet3_ethtool.c
  net: avoid double accounting for pure zerocopy skbs
  tcp: rename sk_wmem_free_skb
  netdevsim: fix uninit value in nsim_drv_configure_vfs()
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  ...

5 files changed, 166 insertions, 101 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index aa3f5b527dc0..603964408d2d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2145,19 +2145,19 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * However, there are some cases which may change PEBS status, e.g. PMI
  * throttle. The PEBS_ENABLE should be updated where the status changes.
  */
-static void __intel_pmu_disable_all(void)
+static __always_inline void __intel_pmu_disable_all(bool bts)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
-	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+	if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
 }
 
-static void intel_pmu_disable_all(void)
+static __always_inline void intel_pmu_disable_all(void)
 {
-	__intel_pmu_disable_all();
+	__intel_pmu_disable_all(true);
 	intel_pmu_pebs_disable_all();
 	intel_pmu_lbr_disable_all();
 }
@@ -2188,6 +2188,49 @@ static void intel_pmu_enable_all(int added)
 	__intel_pmu_enable_all(added, false);
 }
 
+static noinline int
+__intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries,
+				  unsigned int cnt, unsigned long flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	intel_pmu_lbr_read();
+	cnt = min_t(unsigned int, cnt, x86_pmu.lbr_nr);
+
+	memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt);
+	intel_pmu_enable_all(0);
+	local_irq_restore(flags);
+	return cnt;
+}
+
+static int
+intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+
+	/* must not have branches... */
+	local_irq_save(flags);
+	__intel_pmu_disable_all(false); /* we don't care about BTS */
+	__intel_pmu_pebs_disable_all();
+	__intel_pmu_lbr_disable();
+	/*            ... until here */
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+}
+
+static int
+intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+
+	/* must not have branches... */
+	local_irq_save(flags);
+	__intel_pmu_disable_all(false); /* we don't care about BTS */
+	__intel_pmu_pebs_disable_all();
+	__intel_pmu_arch_lbr_disable();
+	/*            ... until here */
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+}
+
 /*
  * Workaround for:
  *   Intel Errata AAK100 (model 26)
@@ -2937,7 +2980,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	intel_bts_disable_local();
 	cpuc->enabled = 0;
-	__intel_pmu_disable_all();
+	__intel_pmu_disable_all(true);
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
 	status = intel_pmu_get_status();
@@ -6299,9 +6342,21 @@ __init int intel_pmu_init(void)
 			x86_pmu.lbr_nr = 0;
 	}
 
-	if (x86_pmu.lbr_nr)
+	if (x86_pmu.lbr_nr) {
 		pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
 
+		/* only support branch_stack snapshot for perfmon >= v2 */
+		if (x86_pmu.disable_all == intel_pmu_disable_all) {
+			if (boot_cpu_has(X86_FEATURE_ARCH_LBR)) {
+				static_call_update(perf_snapshot_branch_stack,
+						   intel_pmu_snapshot_arch_branch_stack);
+			} else {
+				static_call_update(perf_snapshot_branch_stack,
+						   intel_pmu_snapshot_branch_stack);
+			}
+		}
+	}
+
 	intel_pmu_check_extra_regs(x86_pmu.extra_regs);
 
 	/* Support full width counters using alternative MSR range */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4dbb55a43dad..2e215369df4a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1302,7 +1302,7 @@ void intel_pmu_pebs_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
-		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+		__intel_pmu_pebs_disable_all();
 }
 
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 9e6d6eaeb4cb..6b72e9b55c69 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -228,20 +228,6 @@ static void __intel_pmu_lbr_enable(bool pmi)
 		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
 }
 
-static void __intel_pmu_lbr_disable(void)
-{
-	u64 debugctl;
-
-	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
-		wrmsrl(MSR_ARCH_LBR_CTL, 0);
-		return;
-	}
-
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-}
-
 void intel_pmu_lbr_reset_32(void)
 {
 	int i;
@@ -779,8 +765,12 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users && !vlbr_exclude_host())
+	if (cpuc->lbr_users && !vlbr_exclude_host()) {
+		if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+			return __intel_pmu_arch_lbr_disable();
+
 		__intel_pmu_lbr_disable();
+	}
 }
 
 void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7b5167db3e78..5480db242083 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1242,6 +1242,25 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
+static __always_inline void __intel_pmu_pebs_disable_all(void)
+{
+	wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+}
+
+static __always_inline void __intel_pmu_arch_lbr_disable(void)
+{
+	wrmsrl(MSR_ARCH_LBR_CTL, 0);
+}
+
+static __always_inline void __intel_pmu_lbr_disable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
 int intel_pmu_save_and_restart(struct perf_event *event);
 
 struct event_constraint *
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8796559f62a4..726700fabca6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -697,6 +697,20 @@ static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64)
 	*pprog = prog;
 }
 
+/*
+ * Similar version of maybe_emit_mod() for a single register
+ */
+static void maybe_emit_1mod(u8 **pprog, u32 reg, bool is64)
+{
+	u8 *prog = *pprog;
+
+	if (is64)
+		EMIT1(add_1mod(0x48, reg));
+	else if (is_ereg(reg))
+		EMIT1(add_1mod(0x40, 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)
 {
@@ -925,10 +939,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* neg dst */
 		case BPF_ALU | BPF_NEG:
 		case BPF_ALU64 | BPF_NEG:
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				EMIT1(add_1mod(0x48, dst_reg));
-			else if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
+			maybe_emit_1mod(&prog, dst_reg,
+					BPF_CLASS(insn->code) == BPF_ALU64);
 			EMIT2(0xF7, add_1reg(0xD8, dst_reg));
 			break;
 
@@ -942,10 +954,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_AND | BPF_K:
 		case BPF_ALU64 | BPF_OR | BPF_K:
 		case BPF_ALU64 | BPF_XOR | BPF_K:
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				EMIT1(add_1mod(0x48, dst_reg));
-			else if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
+			maybe_emit_1mod(&prog, dst_reg,
+					BPF_CLASS(insn->code) == BPF_ALU64);
 
 			/*
 			 * b3 holds 'normal' opcode, b2 short form only valid
@@ -1002,19 +1012,30 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_MOD | BPF_X:
 		case BPF_ALU64 | BPF_DIV | BPF_X:
 		case BPF_ALU64 | BPF_MOD | BPF_K:
-		case BPF_ALU64 | BPF_DIV | BPF_K:
-			EMIT1(0x50); /* push rax */
-			EMIT1(0x52); /* push rdx */
+		case BPF_ALU64 | BPF_DIV | BPF_K: {
+			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
 
-			if (BPF_SRC(insn->code) == BPF_X)
-				/* mov r11, src_reg */
-				EMIT_mov(AUX_REG, src_reg);
-			else
+			if (dst_reg != BPF_REG_0)
+				EMIT1(0x50); /* push rax */
+			if (dst_reg != BPF_REG_3)
+				EMIT1(0x52); /* push rdx */
+
+			if (BPF_SRC(insn->code) == BPF_X) {
+				if (src_reg == BPF_REG_0 ||
+				    src_reg == BPF_REG_3) {
+					/* mov r11, src_reg */
+					EMIT_mov(AUX_REG, src_reg);
+					src_reg = AUX_REG;
+				}
+			} else {
 				/* mov r11, imm32 */
 				EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
+				src_reg = AUX_REG;
+			}
 
-			/* mov rax, dst_reg */
-			EMIT_mov(BPF_REG_0, dst_reg);
+			if (dst_reg != BPF_REG_0)
+				/* mov rax, dst_reg */
+				emit_mov_reg(&prog, is64, BPF_REG_0, dst_reg);
 
 			/*
 			 * xor edx, edx
@@ -1022,63 +1043,51 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			 */
 			EMIT2(0x31, 0xd2);
 
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				/* div r11 */
-				EMIT3(0x49, 0xF7, 0xF3);
-			else
-				/* div r11d */
-				EMIT3(0x41, 0xF7, 0xF3);
-
-			if (BPF_OP(insn->code) == BPF_MOD)
-				/* mov r11, rdx */
-				EMIT3(0x49, 0x89, 0xD3);
-			else
-				/* mov r11, rax */
-				EMIT3(0x49, 0x89, 0xC3);
+			/* div src_reg */
+			maybe_emit_1mod(&prog, src_reg, is64);
+			EMIT2(0xF7, add_1reg(0xF0, src_reg));
 
-			EMIT1(0x5A); /* pop rdx */
-			EMIT1(0x58); /* pop rax */
+			if (BPF_OP(insn->code) == BPF_MOD &&
+			    dst_reg != BPF_REG_3)
+				/* mov dst_reg, rdx */
+				emit_mov_reg(&prog, is64, dst_reg, BPF_REG_3);
+			else if (BPF_OP(insn->code) == BPF_DIV &&
+				 dst_reg != BPF_REG_0)
+				/* mov dst_reg, rax */
+				emit_mov_reg(&prog, is64, dst_reg, BPF_REG_0);
 
-			/* mov dst_reg, r11 */
-			EMIT_mov(dst_reg, AUX_REG);
+			if (dst_reg != BPF_REG_3)
+				EMIT1(0x5A); /* pop rdx */
+			if (dst_reg != BPF_REG_0)
+				EMIT1(0x58); /* pop rax */
 			break;
+		}
 
 		case BPF_ALU | BPF_MUL | BPF_K:
-		case BPF_ALU | BPF_MUL | BPF_X:
 		case BPF_ALU64 | BPF_MUL | BPF_K:
-		case BPF_ALU64 | BPF_MUL | BPF_X:
-		{
-			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
-
-			if (dst_reg != BPF_REG_0)
-				EMIT1(0x50); /* push rax */
-			if (dst_reg != BPF_REG_3)
-				EMIT1(0x52); /* push rdx */
-
-			/* mov r11, dst_reg */
-			EMIT_mov(AUX_REG, dst_reg);
+			maybe_emit_mod(&prog, dst_reg, dst_reg,
+				       BPF_CLASS(insn->code) == BPF_ALU64);
 
-			if (BPF_SRC(insn->code) == BPF_X)
-				emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
+			if (is_imm8(imm32))
+				/* imul dst_reg, dst_reg, imm8 */
+				EMIT3(0x6B, add_2reg(0xC0, dst_reg, dst_reg),
+				      imm32);
 			else
-				emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);
+				/* imul dst_reg, dst_reg, imm32 */
+				EMIT2_off32(0x69,
+					    add_2reg(0xC0, dst_reg, dst_reg),
+					    imm32);
+			break;
 
-			if (is64)
-				EMIT1(add_1mod(0x48, AUX_REG));
-			else if (is_ereg(AUX_REG))
-				EMIT1(add_1mod(0x40, AUX_REG));
-			/* mul(q) r11 */
-			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU64 | BPF_MUL | BPF_X:
+			maybe_emit_mod(&prog, src_reg, dst_reg,
+				       BPF_CLASS(insn->code) == BPF_ALU64);
 
-			if (dst_reg != BPF_REG_3)
-				EMIT1(0x5A); /* pop rdx */
-			if (dst_reg != BPF_REG_0) {
-				/* mov dst_reg, rax */
-				EMIT_mov(dst_reg, BPF_REG_0);
-				EMIT1(0x58); /* pop rax */
-			}
+			/* imul dst_reg, src_reg */
+			EMIT3(0x0F, 0xAF, add_2reg(0xC0, src_reg, dst_reg));
 			break;
-		}
+
 			/* Shifts */
 		case BPF_ALU | BPF_LSH | BPF_K:
 		case BPF_ALU | BPF_RSH | BPF_K:
@@ -1086,10 +1095,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_LSH | BPF_K:
 		case BPF_ALU64 | BPF_RSH | BPF_K:
 		case BPF_ALU64 | BPF_ARSH | BPF_K:
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				EMIT1(add_1mod(0x48, dst_reg));
-			else if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
+			maybe_emit_1mod(&prog, dst_reg,
+					BPF_CLASS(insn->code) == BPF_ALU64);
 
 			b3 = simple_alu_opcodes[BPF_OP(insn->code)];
 			if (imm32 == 1)
@@ -1120,10 +1127,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			}
 
 			/* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				EMIT1(add_1mod(0x48, dst_reg));
-			else if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
+			maybe_emit_1mod(&prog, dst_reg,
+					BPF_CLASS(insn->code) == BPF_ALU64);
 
 			b3 = simple_alu_opcodes[BPF_OP(insn->code)];
 			EMIT2(0xD3, add_1reg(b3, dst_reg));
@@ -1430,10 +1435,8 @@ st:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP32 | BPF_JSET | BPF_K:
 			/* test dst_reg, imm32 */
-			if (BPF_CLASS(insn->code) == BPF_JMP)
-				EMIT1(add_1mod(0x48, dst_reg));
-			else if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
+			maybe_emit_1mod(&prog, dst_reg,
+					BPF_CLASS(insn->code) == BPF_JMP);
 			EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
 			goto emit_cond_jmp;
 
@@ -1466,10 +1469,8 @@ st:			if (is_imm8(insn->off))
 			}
 
 			/* cmp dst_reg, imm8/32 */
-			if (BPF_CLASS(insn->code) == BPF_JMP)
-				EMIT1(add_1mod(0x48, dst_reg));
-			else if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
+			maybe_emit_1mod(&prog, dst_reg,
+					BPF_CLASS(insn->code) == BPF_JMP);
 
 			if (is_imm8(imm32))
 				EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);