diff --git a/MAINTAINERS b/MAINTAINERS
index 380e43f585d3..da57abebaab3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2801,7 +2801,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
 Q:	https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
 S:	Supported
-F:	arch/x86/net/bpf_jit*
+F:	arch/*/net/*
 F:	Documentation/networking/filter.txt
 F:	Documentation/bpf/
 F:	include/linux/bpf*
@@ -2821,6 +2821,67 @@ F:	tools/bpf/
 F:	tools/lib/bpf/
 F:	tools/testing/selftests/bpf/
 
+BPF JIT for ARM
+M:	Shubham Bansal <illusionist.neo@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/arm/net/
+
+BPF JIT for ARM64
+M:	Daniel Borkmann <daniel@iogearbox.net>
+M:	Alexei Starovoitov <ast@kernel.org>
+M:	Zi Shen Lim <zlim.lnx@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	arch/arm64/net/
+
+BPF JIT for MIPS (32-BIT AND 64-BIT)
+M:	Paul Burton <paul.burton@mips.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/mips/net/
+
+BPF JIT for NFP NICs
+M:	Jakub Kicinski <jakub.kicinski@netronome.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/netronome/nfp/bpf/
+
+BPF JIT for POWERPC (32-BIT AND 64-BIT)
+M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+M:	Sandipan Das <sandipan@linux.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/powerpc/net/
+
+BPF JIT for S390
+M:	Martin Schwidefsky <schwidefsky@de.ibm.com>
+M:	Heiko Carstens <heiko.carstens@de.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/s390/net/
+X:	arch/s390/net/pnet.c
+
+BPF JIT for SPARC (32-BIT AND 64-BIT)
+M:	David S. Miller <davem@davemloft.net>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/sparc/net/
+
+BPF JIT for X86 32-BIT
+M:	Wang YanQing <udknight@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/x86/net/bpf_jit_comp32.c
+
+BPF JIT for X86 64-BIT
+M:	Alexei Starovoitov <ast@kernel.org>
+M:	Daniel Borkmann <daniel@iogearbox.net>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	arch/x86/net/
+X:	arch/x86/net/bpf_jit_comp32.c
+
 BROADCOM B44 10/100 ETHERNET DRIVER
 M:	Michael Chan <michael.chan@broadcom.com>
 L:	netdev@vger.kernel.org
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a6fdaea07c63..89198017e8e6 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -351,7 +351,8 @@ static void build_epilogue(struct jit_ctx *ctx)
  * >0 - successfully JITed a 16-byte eBPF instruction.
  * <0 - failed to JIT.
  */
-static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
+		      bool extra_pass)
 {
 	const u8 code = insn->code;
 	const u8 dst = bpf2a64[insn->dst_reg];
@@ -625,12 +626,19 @@ emit_cond_jmp:
 	case BPF_JMP | BPF_CALL:
 	{
 		const u8 r0 = bpf2a64[BPF_REG_0];
-		const u64 func = (u64)__bpf_call_base + imm;
+		bool func_addr_fixed;
+		u64 func_addr;
+		int ret;
 
-		if (ctx->prog->is_func)
-			emit_addr_mov_i64(tmp, func, ctx);
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
+					    &func_addr, &func_addr_fixed);
+		if (ret < 0)
+			return ret;
+		if (func_addr_fixed)
+			/* We can use optimized emission here. */
+			emit_a64_mov_i64(tmp, func_addr, ctx);
 		else
-			emit_a64_mov_i64(tmp, func, ctx);
+			emit_addr_mov_i64(tmp, func_addr, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -753,7 +761,7 @@ emit_cond_jmp:
 	return 0;
 }
 
-static int build_body(struct jit_ctx *ctx)
+static int build_body(struct jit_ctx *ctx, bool extra_pass)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
@@ -762,7 +770,7 @@ static int build_body(struct jit_ctx *ctx)
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
-		ret = build_insn(insn, ctx);
+		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
 			if (ctx->image == NULL)
@@ -858,7 +866,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 1. Initial fake pass to compute ctx->idx. */
 
 	/* Fake pass to fill in ctx->offset. */
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -888,7 +896,7 @@ skip_init_ctx:
 
 	build_prologue(&ctx, was_classic);
 
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		bpf_jit_binary_free(header);
 		prog = orig_prog;
 		goto out_off;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 50b129785aee..17482f5de3e2 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -166,7 +166,33 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	PPC_BLR();
 }
 
-static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
+static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
+				       u64 func)
+{
+#ifdef PPC64_ELF_ABI_v1
+	/* func points to the function descriptor */
+	PPC_LI64(b2p[TMP_REG_2], func);
+	/* Load actual entry point from function descriptor */
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
+	/* ... and move it to LR */
+	PPC_MTLR(b2p[TMP_REG_1]);
+	/*
+	 * Load TOC from function descriptor at offset 8.
+	 * We can clobber r2 since we get called through a
+	 * function pointer (so caller will save/restore r2)
+	 * and since we don't use a TOC ourself.
+	 */
+	PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
+#else
+	/* We can clobber r12 */
+	PPC_FUNC_ADDR(12, func);
+	PPC_MTLR(12);
+#endif
+	PPC_BLRL();
+}
+
+static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
+				       u64 func)
 {
 	unsigned int i, ctx_idx = ctx->idx;
 
@@ -273,7 +299,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
-	int i;
+	int i, ret;
 
 	/* Start of epilogue code - will only be valid 2nd pass onwards */
 	u32 exit_addr = addrs[flen];
@@ -284,8 +310,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		u32 src_reg = b2p[insn[i].src_reg];
 		s16 off = insn[i].off;
 		s32 imm = insn[i].imm;
+		bool func_addr_fixed;
+		u64 func_addr;
 		u64 imm64;
-		u8 *func;
 		u32 true_cond;
 		u32 tmp_idx;
 
@@ -711,23 +738,15 @@ emit_clear:
 		case BPF_JMP | BPF_CALL:
 			ctx->seen |= SEEN_FUNC;
 
-			/* bpf function call */
-			if (insn[i].src_reg == BPF_PSEUDO_CALL)
-				if (!extra_pass)
-					func = NULL;
-				else if (fp->aux->func && off < fp->aux->func_cnt)
-					/* use the subprog id from the off
-					 * field to lookup the callee address
-					 */
-					func = (u8 *) fp->aux->func[off]->bpf_func;
-				else
-					return -EINVAL;
-			/* kernel helper call */
+			ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
+						    &func_addr, &func_addr_fixed);
+			if (ret < 0)
+				return ret;
+
+			if (func_addr_fixed)
+				bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
 			else
-				func = (u8 *) __bpf_call_base + imm;
-
-			bpf_jit_emit_func_call(image, ctx, (u64)func);
-
+				bpf_jit_emit_func_call_rel(image, ctx, func_addr);
 			/* move return value from r3 to BPF_REG_0 */
 			PPC_MR(b2p[BPF_REG_0], 3);
 			break;
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 222785af550b..5fda4f7bf15d 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -791,7 +791,7 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
 }
 
 /* Just skip the save instruction and the ctx register move.  */
-#define BPF_TAILCALL_PROLOGUE_SKIP	16
+#define BPF_TAILCALL_PROLOGUE_SKIP	32
 #define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
 
 static void build_prologue(struct jit_ctx *ctx)
@@ -824,9 +824,15 @@ static void build_prologue(struct jit_ctx *ctx)
 		const u8 vfp = bpf2sparc[BPF_REG_FP];
 
 		emit(ADD | IMMED | RS1(FP) | S13(STACK_BIAS) | RD(vfp), ctx);
+	} else {
+		emit_nop(ctx);
 	}
 
 	emit_reg_move(I0, O0, ctx);
+	emit_reg_move(I1, O1, ctx);
+	emit_reg_move(I2, O2, ctx);
+	emit_reg_move(I3, O3, ctx);
+	emit_reg_move(I4, O4, ctx);
 	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
 }
 
@@ -1270,6 +1276,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		u32 opcode = 0, rs2;
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		ctx->tmp_2_used = true;
 		emit_loadimm(imm, tmp2, ctx);
 
@@ -1308,6 +1317,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 		u32 opcode = 0, rs2;
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		switch (BPF_SIZE(code)) {
 		case BPF_W:
 			opcode = ST32;
@@ -1340,6 +1352,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		ctx->tmp_1_used = true;
 		ctx->tmp_2_used = true;
 		ctx->tmp_3_used = true;
@@ -1360,6 +1375,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		ctx->tmp_1_used = true;
 		ctx->tmp_2_used = true;
 		ctx->tmp_3_used = true;
@@ -1425,12 +1443,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct sparc64_jit_data *jit_data;
 	struct bpf_binary_header *header;
+	u32 prev_image_size, image_size;
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
-	u32 image_size;
 	u8 *image_ptr;
-	int pass;
+	int pass, i;
 
 	if (!prog->jit_requested)
 		return orig_prog;
@@ -1461,27 +1479,52 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		header = jit_data->header;
 		extra_pass = true;
 		image_size = sizeof(u32) * ctx.idx;
+		prev_image_size = image_size;
+		pass = 1;
 		goto skip_init_ctx;
 	}
 
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
-	ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL);
+	ctx.offset = kmalloc_array(prog->len, sizeof(unsigned int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
 		goto out_off;
 	}
 
-	/* Fake pass to detect features used, and get an accurate assessment
-	 * of what the final image size will be.
+	/* Longest sequence emitted is for bswap32, 12 instructions.  Pre-cook
+	 * the offset array so that we converge faster.
 	 */
-	if (build_body(&ctx)) {
-		prog = orig_prog;
-		goto out_off;
+	for (i = 0; i < prog->len; i++)
+		ctx.offset[i] = i * (12 * 4);
+
+	prev_image_size = ~0U;
+	for (pass = 1; pass < 40; pass++) {
+		ctx.idx = 0;
+
+		build_prologue(&ctx);
+		if (build_body(&ctx)) {
+			prog = orig_prog;
+			goto out_off;
+		}
+		build_epilogue(&ctx);
+
+		if (bpf_jit_enable > 1)
+			pr_info("Pass %d: size = %u, seen = [%c%c%c%c%c%c]\n", pass,
+				ctx.idx * 4,
+				ctx.tmp_1_used ? '1' : ' ',
+				ctx.tmp_2_used ? '2' : ' ',
+				ctx.tmp_3_used ? '3' : ' ',
+				ctx.saw_frame_pointer ? 'F' : ' ',
+				ctx.saw_call ? 'C' : ' ',
+				ctx.saw_tail_call ? 'T' : ' ');
+
+		if (ctx.idx * 4 == prev_image_size)
+			break;
+		prev_image_size = ctx.idx * 4;
+		cond_resched();
 	}
-	build_prologue(&ctx);
-	build_epilogue(&ctx);
 
 	/* Now we know the actual image size. */
 	image_size = sizeof(u32) * ctx.idx;
@@ -1494,28 +1537,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	ctx.image = (u32 *)image_ptr;
 skip_init_ctx:
-	for (pass = 1; pass < 3; pass++) {
-		ctx.idx = 0;
+	ctx.idx = 0;
 
-		build_prologue(&ctx);
+	build_prologue(&ctx);
 
-		if (build_body(&ctx)) {
-			bpf_jit_binary_free(header);
-			prog = orig_prog;
-			goto out_off;
-		}
+	if (build_body(&ctx)) {
+		bpf_jit_binary_free(header);
+		prog = orig_prog;
+		goto out_off;
+	}
 
-		build_epilogue(&ctx);
+	build_epilogue(&ctx);
 
-		if (bpf_jit_enable > 1)
-			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass,
-				image_size - (ctx.idx * 4),
-				ctx.tmp_1_used ? '1' : ' ',
-				ctx.tmp_2_used ? '2' : ' ',
-				ctx.tmp_3_used ? '3' : ' ',
-				ctx.saw_frame_pointer ? 'F' : ' ',
-				ctx.saw_call ? 'C' : ' ',
-				ctx.saw_tail_call ? 'T' : ' ');
+	if (ctx.idx * 4 != prev_image_size) {
+		pr_err("bpf_jit: Failed to converge, prev_size=%u size=%d\n",
+		       prev_image_size, ctx.idx * 4);
+		bpf_jit_binary_free(header);
+		prog = orig_prog;
+		goto out_off;
 	}
 
 	if (bpf_jit_enable > 1)
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 4e46dc9e41ad..11e1663bdc4d 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -1410,7 +1410,7 @@ static int init_q(struct fs_dev *dev, struct queue *txq, int queue,
 
 	func_enter ();
 
-	fs_dprintk (FS_DEBUG_INIT, "Inititing queue at %x: %d entries:\n", 
+	fs_dprintk (FS_DEBUG_INIT, "Initializing queue at %x: %d entries:\n",
 		    queue, nentries);
 
 	p = aligned_kmalloc (sz, GFP_KERNEL, 0x10);
@@ -1443,7 +1443,7 @@ static int init_fp(struct fs_dev *dev, struct freepool *fp, int queue,
 {
 	func_enter ();
 
-	fs_dprintk (FS_DEBUG_INIT, "Inititing free pool at %x:\n", queue);
+	fs_dprintk (FS_DEBUG_INIT, "Initializing free pool at %x:\n", queue);
 
 	write_fs (dev, FP_CNF(queue), (bufsize * RBFP_RBS) | RBFP_RBSVAL | RBFP_CME);
 	write_fs (dev, FP_SA(queue),  0);
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 55af04fa03a7..6c8dcb65ff03 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -1441,6 +1441,9 @@ static void nic_remove(struct pci_dev *pdev)
 {
 	struct nicpf *nic = pci_get_drvdata(pdev);
 
+	if (!nic)
+		return;
+
 	if (nic->flags & NIC_SRIOV_ENABLED)
 		pci_disable_sriov(pdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index be268dcde8fa..f9a4e76c5a8b 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -915,10 +915,8 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	}
 
 	ret = register_netdev(ndev);
-	if (ret) {
-		free_netdev(ndev);
+	if (ret)
 		goto alloc_fail;
-	}
 
 	return 0;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 21c2688d6308..a3f45335437c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1413,7 +1413,7 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f)
 	}
 
 	vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
-	set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->state);
+	set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->back->state);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index add1e457886d..433c8e688c78 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -33,7 +33,7 @@ static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi)
 }
 
 /**
- * i40e_add_xsk_umem - Store an UMEM for a certain ring/qid
+ * i40e_add_xsk_umem - Store a UMEM for a certain ring/qid
  * @vsi: Current VSI
  * @umem: UMEM to store
  * @qid: Ring/qid to associate with the UMEM
@@ -56,7 +56,7 @@ static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem,
 }
 
 /**
- * i40e_remove_xsk_umem - Remove an UMEM for a certain ring/qid
+ * i40e_remove_xsk_umem - Remove a UMEM for a certain ring/qid
  * @vsi: Current VSI
  * @qid: Ring/qid associated with the UMEM
  **/
@@ -130,7 +130,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
 }
 
 /**
- * i40e_xsk_umem_enable - Enable/associate an UMEM to a certain ring/qid
+ * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
  * @vsi: Current VSI
  * @umem: UMEM
  * @qid: Rx ring to associate UMEM to
@@ -189,7 +189,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 }
 
 /**
- * i40e_xsk_umem_disable - Diassociate an UMEM from a certain ring/qid
+ * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid
  * @vsi: Current VSI
  * @qid: Rx ring to associate UMEM to
  *
@@ -255,12 +255,12 @@ int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
 }
 
 /**
- * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM
+ * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
  * @vsi: Current VSI
  * @umem: UMEM to enable/associate to a ring, or NULL to disable
  * @qid: Rx ring to (dis)associate UMEM (from)to
  *
- * This function enables or disables an UMEM to a certain ring.
+ * This function enables or disables a UMEM to a certain ring.
  *
  * Returns 0 on success, <0 on failure
  **/
@@ -276,7 +276,7 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
  *
- * This function enables or disables an UMEM to a certain ring.
+ * This function enables or disables a UMEM to a certain ring.
  *
  * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
  **/
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index c54ebedca6da..c393cb2c0f16 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -842,6 +842,7 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw)
 		nvm_word = E1000_INVM_DEFAULT_AL;
 	tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL;
 	igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, E1000_PHY_PLL_FREQ_PAGE);
+	phy_word = E1000_PHY_PLL_UNCONF;
 	for (i = 0; i < E1000_MAX_PLL_TRIES; i++) {
 		/* check current state directly from internal PHY */
 		igb_read_phy_reg_82580(hw, E1000_PHY_PLL_FREQ_REG, &phy_word);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 10dbaf4f6e80..9c42f741ed5e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -2262,7 +2262,9 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
 		*autoneg = false;
 
 		if (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
-		    hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) {
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 ||
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 ||
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1) {
 			*speed = IXGBE_LINK_SPEED_1GB_FULL;
 			return 0;
 		}
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 867cddba840f..e8ca98c070f6 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1672,7 +1672,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 		netif_wake_queue(adapter->netdev);
 	}
 
-	if (!napi_complete_done(napi, weight))
+	if (!napi_complete(napi))
 		goto done;
 
 	/* enable isr */
@@ -1681,7 +1681,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 	lan743x_csr_read(adapter, INT_STS);
 
 done:
-	return weight;
+	return 0;
 }
 
 static void lan743x_tx_ring_cleanup(struct lan743x_tx *tx)
@@ -1870,9 +1870,9 @@ static int lan743x_tx_open(struct lan743x_tx *tx)
 	tx->vector_flags = lan743x_intr_get_vector_flags(adapter,
 							 INT_BIT_DMA_TX_
 							 (tx->channel_number));
-	netif_napi_add(adapter->netdev,
-		       &tx->napi, lan743x_tx_napi_poll,
-		       tx->ring_size - 1);
+	netif_tx_napi_add(adapter->netdev,
+			  &tx->napi, lan743x_tx_napi_poll,
+			  tx->ring_size - 1);
 	napi_enable(&tx->napi);
 
 	data = 0;
@@ -3017,6 +3017,7 @@ static const struct dev_pm_ops lan743x_pm_ops = {
 
 static const struct pci_device_id lan743x_pcidev_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7431) },
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 0e82b6368798..2d6eea18973e 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -548,6 +548,7 @@ struct lan743x_adapter;
 /* SMSC acquired EFAR late 1990's, MCHP acquired SMSC 2012 */
 #define PCI_VENDOR_ID_SMSC		PCI_VENDOR_ID_EFAR
 #define PCI_DEVICE_ID_SMSC_LAN7430	(0x7430)
+#define PCI_DEVICE_ID_SMSC_LAN7431	(0x7431)
 
 #define PCI_CONFIG_LENGTH		(0x1000)
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 78a638ec7c0a..979f1e4bc18b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -6071,7 +6071,7 @@ static const char * const s_igu_fifo_error_strs[] = {
 	"no error",
 	"length error",
 	"function disabled",
-	"VF sent command to attnetion address",
+	"VF sent command to attention address",
 	"host sent prod update command",
 	"read of during interrupt register while in MIMD mode",
 	"access to PXP BAR reserved address",
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index ef9538ee53d0..82412691ee66 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -3605,7 +3605,7 @@ static const char velocity_gstrings[][ETH_GSTRING_LEN] = {
 	"tx_jumbo",
 	"rx_mac_control_frames",
 	"tx_mac_control_frames",
-	"rx_frame_alignement_errors",
+	"rx_frame_alignment_errors",
 	"rx_long_ok",
 	"rx_long_err",
 	"tx_sqe_errors",
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ab33d1777132..23ee3967c166 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2197,6 +2197,14 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner)
 	new_driver->mdiodrv.driver.remove = phy_remove;
 	new_driver->mdiodrv.driver.owner = owner;
 
+	/* The following works around an issue where the PHY driver doesn't bind
+	 * to the device, resulting in the genphy driver being used instead of
+	 * the dedicated driver. The root cause of the issue isn't known yet
+	 * and seems to be in the base driver core. Once this is fixed we may
+	 * remove this workaround.
+	 */
+	new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS;
+
 	retval = driver_register(&new_driver->mdiodrv.driver);
 	if (retval) {
 		pr_err("%s: Error %d in registering driver\n",
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index e9f101c9bae2..bfbb39f93554 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			 * it just report sending a packet to the target
 			 * (without actual packet transfer).
 			 */
-			dev_kfree_skb_any(skb);
 			ndev->stats.tx_packets++;
 			ndev->stats.tx_bytes += skb->len;
+			dev_kfree_skb_any(skb);
 		}
 	}
 
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 7275761a1177..3d8a70d3ea9b 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -140,7 +140,6 @@ struct ipheth_device {
 	struct usb_device *udev;
 	struct usb_interface *intf;
 	struct net_device *net;
-	struct sk_buff *tx_skb;
 	struct urb *tx_urb;
 	struct urb *rx_urb;
 	unsigned char *tx_buf;
@@ -230,6 +229,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
 	case -ENOENT:
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+	case -EPROTO:
 		return;
 	case 0:
 		break;
@@ -281,7 +281,6 @@ static void ipheth_sndbulk_callback(struct urb *urb)
 		dev_err(&dev->intf->dev, "%s: urb status: %d\n",
 		__func__, status);
 
-	dev_kfree_skb_irq(dev->tx_skb);
 	if (status == 0)
 		netif_wake_queue(dev->net);
 	else
@@ -423,7 +422,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 	if (skb->len > IPHETH_BUF_SIZE) {
 		WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len);
 		dev->net->stats.tx_dropped++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -443,12 +442,11 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 		dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n",
 			__func__, retval);
 		dev->net->stats.tx_errors++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 	} else {
-		dev->tx_skb = skb;
-
 		dev->net->stats.tx_packets++;
 		dev->net->stats.tx_bytes += skb->len;
+		dev_consume_skb_any(skb);
 		netif_stop_queue(net);
 	}
 
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 4bce5ae65a55..254065271867 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4518,8 +4518,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_arp_query_info *qinfo;
-	struct qeth_snmp_cmd *snmp;
 	unsigned char *data;
+	void *snmp_data;
 	__u16 data_len;
 
 	QETH_CARD_TEXT(card, 3, "snpcmdcb");
@@ -4527,7 +4527,6 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	cmd = (struct qeth_ipa_cmd *) sdata;
 	data = (unsigned char *)((char *)cmd - reply->offset);
 	qinfo = (struct qeth_arp_query_info *) reply->param;
-	snmp = &cmd->data.setadapterparms.data.snmp;
 
 	if (cmd->hdr.return_code) {
 		QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code);
@@ -4540,10 +4539,15 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 		return 0;
 	}
 	data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data));
-	if (cmd->data.setadapterparms.hdr.seq_no == 1)
-		data_len -= (__u16)((char *)&snmp->data - (char *)cmd);
-	else
-		data_len -= (__u16)((char *)&snmp->request - (char *)cmd);
+	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
+		snmp_data = &cmd->data.setadapterparms.data.snmp;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp);
+	} else {
+		snmp_data = &cmd->data.setadapterparms.data.snmp.request;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp.request);
+	}
 
 	/* check if there is enough room in userspace */
 	if ((qinfo->udata_len - qinfo->udata_offset) < data_len) {
@@ -4556,16 +4560,9 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	QETH_CARD_TEXT_(card, 4, "sseqn%i",
 		cmd->data.setadapterparms.hdr.seq_no);
 	/*copy entries to user buffer*/
-	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)snmp,
-		       data_len + offsetof(struct qeth_snmp_cmd, data));
-		qinfo->udata_offset += offsetof(struct qeth_snmp_cmd, data);
-	} else {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)&snmp->request, data_len);
-	}
+	memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len);
 	qinfo->udata_offset += data_len;
+
 	/* check if all replies received ... */
 		QETH_CARD_TEXT_(card, 4, "srtot%i",
 			       cmd->data.setadapterparms.hdr.used_total);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index de629b706d1d..448dcc448f1f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr);
 
 void bpf_jit_free(struct bpf_prog *fp);
 
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+			  const struct bpf_insn *insn, bool extra_pass,
+			  u64 *func_addr, bool *func_addr_fixed);
+
 struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
 void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
 
diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index b8d95564bd53..14edb795ab43 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -21,6 +21,19 @@ struct nf_ct_gre_keymap {
 	struct nf_conntrack_tuple tuple;
 };
 
+enum grep_conntrack {
+	GRE_CT_UNREPLIED,
+	GRE_CT_REPLIED,
+	GRE_CT_MAX
+};
+
+struct netns_proto_gre {
+	struct nf_proto_net	nf;
+	rwlock_t		keymap_lock;
+	struct list_head	keymap_list;
+	unsigned int		gre_timeouts[GRE_CT_MAX];
+};
+
 /* add new tuple->key_reply pair to keymap */
 int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 			 struct nf_conntrack_tuple *t);
diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h
index cd24be4c4a99..13d55206bb9f 100644
--- a/include/net/netfilter/ipv4/nf_nat_masquerade.h
+++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h
@@ -9,7 +9,7 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 		       const struct nf_nat_range2 *range,
 		       const struct net_device *out);
 
-void nf_nat_masquerade_ipv4_register_notifier(void);
+int nf_nat_masquerade_ipv4_register_notifier(void);
 void nf_nat_masquerade_ipv4_unregister_notifier(void);
 
 #endif /*_NF_NAT_MASQUERADE_IPV4_H_ */
diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
index 0c3b5ebf0bb8..2917bf95c437 100644
--- a/include/net/netfilter/ipv6/nf_nat_masquerade.h
+++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h
@@ -5,7 +5,7 @@
 unsigned int
 nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 		       const struct net_device *out);
-void nf_nat_masquerade_ipv6_register_notifier(void);
+int nf_nat_masquerade_ipv6_register_notifier(void);
 void nf_nat_masquerade_ipv6_unregister_notifier(void);
 
 #endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1a796e0799ec..b1a3545d0ec8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	bpf_prog_unlock_free(fp);
 }
 
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+			  const struct bpf_insn *insn, bool extra_pass,
+			  u64 *func_addr, bool *func_addr_fixed)
+{
+	s16 off = insn->off;
+	s32 imm = insn->imm;
+	u8 *addr;
+
+	*func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
+	if (!*func_addr_fixed) {
+		/* Place-holder address till the last pass has collected
+		 * all addresses for JITed subprograms in which case we
+		 * can pick them up from prog->aux.
+		 */
+		if (!extra_pass)
+			addr = NULL;
+		else if (prog->aux->func &&
+			 off >= 0 && off < prog->aux->func_cnt)
+			addr = (u8 *)prog->aux->func[off]->bpf_func;
+		else
+			return -EINVAL;
+	} else {
+		/* Address of a BPF helper call. Since part of the core
+		 * kernel, it's always at a fixed location. __bpf_call_base
+		 * and the helper with imm relative to it are both in core
+		 * kernel.
+		 */
+		addr = (u8 *)__bpf_call_base + imm;
+	}
+
+	*func_addr = (unsigned long)addr;
+	return 0;
+}
+
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
 			      const struct bpf_insn *aux,
 			      struct bpf_insn *to_buff)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c97a8f968638..bed9d48a7ae9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
 		return -ENOENT;
 
 	new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
-			   map->value_size, __GFP_ZERO | GFP_USER,
+			   map->value_size,
+			   __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
 			   map->numa_node);
 	if (!new)
 		return -ENOMEM;
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8bbd72d3a121..b384ea9f3254 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -7,6 +7,7 @@
 #include <linux/bpf.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/capability.h>
 #include "percpu_freelist.h"
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
@@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
 /* Called from syscall */
 static int queue_stack_map_alloc_check(union bpf_attr *attr)
 {
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 0 ||
+	    attr->value_size == 0 ||
 	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
 		return -EINVAL;
 
@@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
 {
 	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	struct bpf_queue_stack *qs;
-	u32 size, value_size;
-	u64 queue_size, cost;
+	u64 size, queue_size, cost;
 
-	size = attr->max_entries + 1;
-	value_size = attr->value_size;
-
-	queue_size = sizeof(*qs) + (u64) value_size * size;
-
-	cost = queue_size;
+	size = (u64) attr->max_entries + 1;
+	cost = queue_size = sizeof(*qs) + size * attr->value_size;
 	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1971ca325fb4..6dd419550aba 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5650,7 +5650,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 		return;
 	/* NOTE: fake 'exit' subprog should be updated as well. */
 	for (i = 0; i <= env->subprog_cnt; i++) {
-		if (env->subprog_info[i].start < off)
+		if (env->subprog_info[i].start <= off)
 			continue;
 		env->subprog_info[i].start += len - 1;
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 08fcfe440c63..9864a35c8bb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 			i++;
 		} else if (fmt[i] == 'p' || fmt[i] == 's') {
 			mod[fmt_cnt]++;
-			i++;
-			if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+			/* disallow any further format extensions */
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1]))
 				return -EINVAL;
 			fmt_cnt++;
-			if (fmt[i - 1] == 's') {
+			if (fmt[i] == 's') {
 				if (str_seen)
 					/* allow only one '%s' per fmt string */
 					return -EINVAL;
diff --git a/net/core/filter.c b/net/core/filter.c
index e521c5ebc7d1..9a1327eb25fa 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 	} else {
 		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
-		u16 hnum = ntohs(tuple->ipv6.dport);
 		int sdif = inet6_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
 			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
 					    src6, tuple->ipv6.sport,
-					    dst6, hnum,
+					    dst6, ntohs(tuple->ipv6.dport),
 					    dif, sdif, &refcounted);
 		else if (likely(ipv6_bpf_stub))
 			sk = ipv6_bpf_stub->udp6_lib_lookup(net,
 							    src6, tuple->ipv6.sport,
-							    dst6, hnum,
+							    dst6, tuple->ipv6.dport,
 							    dif, sdif,
 							    &udp_table, skb);
 #endif
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c09219e7f230..5dbec21856f4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -939,7 +939,7 @@ static int __ip_append_data(struct sock *sk,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			unsigned int pagedlen = 0;
+			unsigned int pagedlen;
 			struct sk_buff *skb_prev;
 alloc_new_skb:
 			skb_prev = skb;
@@ -956,6 +956,7 @@ alloc_new_skb:
 			if (datalen > mtu - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen;
 			fraglen = datalen + fragheaderlen;
+			pagedlen = 0;
 
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index ce1512b02cb2..fd3f9e8a74da 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -81,9 +81,12 @@ static int __init masquerade_tg_init(void)
 	int ret;
 
 	ret = xt_register_target(&masquerade_tg_reg);
+	if (ret)
+		return ret;
 
-	if (ret == 0)
-		nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret)
+		xt_unregister_target(&masquerade_tg_reg);
 
 	return ret;
 }
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index a9d5e013e555..41327bb99093 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -147,28 +147,50 @@ static struct notifier_block masq_inet_notifier = {
 	.notifier_call	= masq_inet_event,
 };
 
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
 
-void nf_nat_masquerade_ipv4_register_notifier(void)
+int nf_nat_masquerade_ipv4_register_notifier(void)
 {
+	int ret = 0;
+
+	mutex_lock(&masq_mutex);
 	/* check if the notifier was already set */
-	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return;
+	if (++masq_refcnt > 1)
+		goto out_unlock;
 
 	/* Register for device down reports */
-	register_netdevice_notifier(&masq_dev_notifier);
+	ret = register_netdevice_notifier(&masq_dev_notifier);
+	if (ret)
+		goto err_dec;
 	/* Register IP address change reports */
-	register_inetaddr_notifier(&masq_inet_notifier);
+	ret = register_inetaddr_notifier(&masq_inet_notifier);
+	if (ret)
+		goto err_unregister;
+
+	mutex_unlock(&masq_mutex);
+	return ret;
+
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+	masq_refcnt--;
+out_unlock:
+	mutex_unlock(&masq_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
 
 void nf_nat_masquerade_ipv4_unregister_notifier(void)
 {
+	mutex_lock(&masq_mutex);
 	/* check if the notifier still has clients */
-	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
-		return;
+	if (--masq_refcnt > 0)
+		goto out_unlock;
 
 	unregister_netdevice_notifier(&masq_dev_notifier);
 	unregister_inetaddr_notifier(&masq_inet_notifier);
+out_unlock:
+	mutex_unlock(&masq_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index f1193e1e928a..6847de1d1db8 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -69,7 +69,9 @@ static int __init nft_masq_ipv4_module_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret)
+		nft_unregister_expr(&nft_masq_ipv4_type);
 
 	return ret;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1e37c1388189..a9d9555a973f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 		u32 delta_us;
 
-		if (!delta)
-			delta = 1;
-		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
-		tcp_rcv_rtt_update(tp, delta_us, 0);
+		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			if (!delta)
+				delta = 1;
+			delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+			tcp_rcv_rtt_update(tp, delta_us, 0);
+		}
 	}
 }
 
@@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 	    flag & FLAG_ACKED) {
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
-		u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 
-		seq_rtt_us = ca_rtt_us = delta_us;
+		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+			ca_rtt_us = seq_rtt_us;
+		}
 	}
 	rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
 	if (seq_rtt_us < 0)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 5f8b6d3cd855..091c53925e4d 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 elapsed, start_ts;
+	s32 remaining;
 
 	start_ts = tcp_retransmit_stamp(sk);
 	if (!icsk->icsk_user_timeout || !start_ts)
 		return icsk->icsk_rto;
 	elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
-	if (elapsed >= icsk->icsk_user_timeout)
+	remaining = icsk->icsk_user_timeout - elapsed;
+	if (remaining <= 0)
 		return 1; /* user timeout has passed; fire ASAP */
-	else
-		return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed));
+
+	return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
 }
 
 /**
@@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk,
 				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 		timeout = jiffies_to_msecs(timeout);
 	}
-	return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout;
+	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
 
 /* A write timeout has occurred. Process the after effects. */
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 89e0d5118afe..827a3f5ff3bb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1354,7 +1354,7 @@ emsgsize:
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			unsigned int pagedlen = 0;
+			unsigned int pagedlen;
 alloc_new_skb:
 			/* There's no room in the current skb */
 			if (skb)
@@ -1378,6 +1378,7 @@ alloc_new_skb:
 			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			fraglen = datalen + fragheaderlen;
+			pagedlen = 0;
 
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 5ae8e1c51079..8b075f0bc351 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	struct flowi6 fl6 = {
-		.flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
+		.flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
+			rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
 		.flowi6_mark = skb->mark,
 		.flowi6_uid = sock_net_uid(net, sk),
 		.daddr = iph->daddr,
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 491f808e356a..29c7f1915a96 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void)
 	int err;
 
 	err = xt_register_target(&masquerade_tg6_reg);
-	if (err == 0)
-		nf_nat_masquerade_ipv6_register_notifier();
+	if (err)
+		return err;
+
+	err = nf_nat_masquerade_ipv6_register_notifier();
+	if (err)
+		xt_unregister_target(&masquerade_tg6_reg);
 
 	return err;
 }
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 3e4bf2286abe..0ad0da5a2600 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work)
  * of ipv6 addresses being deleted), we also need to add an upper
  * limit to the number of queued work items.
  */
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event, void *ptr)
+static int masq_inet6_event(struct notifier_block *this,
+			    unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *ifa = ptr;
 	const struct net_device *dev;
@@ -171,30 +171,53 @@ static int masq_inet_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
+static struct notifier_block masq_inet6_notifier = {
+	.notifier_call	= masq_inet6_event,
 };
 
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
 
-void nf_nat_masquerade_ipv6_register_notifier(void)
+int nf_nat_masquerade_ipv6_register_notifier(void)
 {
-	/* check if the notifier is already set */
-	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return;
+	int ret = 0;
 
-	register_netdevice_notifier(&masq_dev_notifier);
-	register_inet6addr_notifier(&masq_inet_notifier);
+	mutex_lock(&masq_mutex);
+	/* check if the notifier is already set */
+	if (++masq_refcnt > 1)
+		goto out_unlock;
+
+	ret = register_netdevice_notifier(&masq_dev_notifier);
+	if (ret)
+		goto err_dec;
+
+	ret = register_inet6addr_notifier(&masq_inet6_notifier);
+	if (ret)
+		goto err_unregister;
+
+	mutex_unlock(&masq_mutex);
+	return ret;
+
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+	masq_refcnt--;
+out_unlock:
+	mutex_unlock(&masq_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
 
 void nf_nat_masquerade_ipv6_unregister_notifier(void)
 {
+	mutex_lock(&masq_mutex);
 	/* check if the notifier still has clients */
-	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
-		return;
+	if (--masq_refcnt > 0)
+		goto out_unlock;
 
-	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_inet6addr_notifier(&masq_inet6_notifier);
 	unregister_netdevice_notifier(&masq_dev_notifier);
+out_unlock:
+	mutex_unlock(&masq_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index dd0122f3cffe..e06c82e9dfcd 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_nat_masquerade_ipv6_register_notifier();
+	ret = nf_nat_masquerade_ipv6_register_notifier();
+	if (ret)
+		nft_unregister_expr(&nft_masq_ipv6_type);
 
 	return ret;
 }
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 83395bf6dc35..432141f04af3 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3980,6 +3980,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
 
 static struct notifier_block ip_vs_dst_notifier = {
 	.notifier_call = ip_vs_dst_event,
+#ifdef CONFIG_IP_VS_IPV6
+	.priority = ADDRCONF_NOTIFY_PRIORITY + 5,
+#endif
 };
 
 int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 02ca7df793f5..b6d0f6deea86 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -49,6 +49,7 @@ struct nf_conncount_tuple {
 	struct nf_conntrack_zone	zone;
 	int				cpu;
 	u32				jiffies32;
+	bool				dead;
 	struct rcu_head			rcu_head;
 };
 
@@ -106,15 +107,16 @@ nf_conncount_add(struct nf_conncount_list *list,
 	conn->zone = *zone;
 	conn->cpu = raw_smp_processor_id();
 	conn->jiffies32 = (u32)jiffies;
-	spin_lock(&list->list_lock);
+	conn->dead = false;
+	spin_lock_bh(&list->list_lock);
 	if (list->dead == true) {
 		kmem_cache_free(conncount_conn_cachep, conn);
-		spin_unlock(&list->list_lock);
+		spin_unlock_bh(&list->list_lock);
 		return NF_CONNCOUNT_SKIP;
 	}
 	list_add_tail(&conn->node, &list->head);
 	list->count++;
-	spin_unlock(&list->list_lock);
+	spin_unlock_bh(&list->list_lock);
 	return NF_CONNCOUNT_ADDED;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
@@ -132,19 +134,22 @@ static bool conn_free(struct nf_conncount_list *list,
 {
 	bool free_entry = false;
 
-	spin_lock(&list->list_lock);
+	spin_lock_bh(&list->list_lock);
 
-	if (list->count == 0) {
-		spin_unlock(&list->list_lock);
-                return free_entry;
+	if (conn->dead) {
+		spin_unlock_bh(&list->list_lock);
+		return free_entry;
 	}
 
 	list->count--;
+	conn->dead = true;
 	list_del_rcu(&conn->node);
-	if (list->count == 0)
+	if (list->count == 0) {
+		list->dead = true;
 		free_entry = true;
+	}
 
-	spin_unlock(&list->list_lock);
+	spin_unlock_bh(&list->list_lock);
 	call_rcu(&conn->rcu_head, __conn_free);
 	return free_entry;
 }
@@ -245,7 +250,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list)
 {
 	spin_lock_init(&list->list_lock);
 	INIT_LIST_HEAD(&list->head);
-	list->count = 1;
+	list->count = 0;
 	list->dead = false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
@@ -259,6 +264,7 @@ bool nf_conncount_gc_list(struct net *net,
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
 	bool free_entry = false;
+	bool ret = false;
 
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
 		found = find_or_evict(net, list, conn, &free_entry);
@@ -288,7 +294,15 @@ bool nf_conncount_gc_list(struct net *net,
 		if (collected > CONNCOUNT_GC_MAX_NODES)
 			return false;
 	}
-	return false;
+
+	spin_lock_bh(&list->list_lock);
+	if (!list->count) {
+		list->dead = true;
+		ret = true;
+	}
+	spin_unlock_bh(&list->list_lock);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_gc_list);
 
@@ -309,11 +323,8 @@ static void tree_nodes_free(struct rb_root *root,
 	while (gc_count) {
 		rbconn = gc_nodes[--gc_count];
 		spin_lock(&rbconn->list.list_lock);
-		if (rbconn->list.count == 0 && rbconn->list.dead == false) {
-			rbconn->list.dead = true;
-			rb_erase(&rbconn->node, root);
-			call_rcu(&rbconn->rcu_head, __tree_nodes_free);
-		}
+		rb_erase(&rbconn->node, root);
+		call_rcu(&rbconn->rcu_head, __tree_nodes_free);
 		spin_unlock(&rbconn->list.list_lock);
 	}
 }
@@ -414,6 +425,7 @@ insert_tree(struct net *net,
 	nf_conncount_list_init(&rbconn->list);
 	list_add(&conn->node, &rbconn->list.head);
 	count = 1;
+	rbconn->list.count = count;
 
 	rb_link_node(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9b48dc8b4b88..2a5e56c6d8d9 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -43,24 +43,12 @@
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 
-enum grep_conntrack {
-	GRE_CT_UNREPLIED,
-	GRE_CT_REPLIED,
-	GRE_CT_MAX
-};
-
 static const unsigned int gre_timeouts[GRE_CT_MAX] = {
 	[GRE_CT_UNREPLIED]	= 30*HZ,
 	[GRE_CT_REPLIED]	= 180*HZ,
 };
 
 static unsigned int proto_gre_net_id __read_mostly;
-struct netns_proto_gre {
-	struct nf_proto_net	nf;
-	rwlock_t		keymap_lock;
-	struct list_head	keymap_list;
-	unsigned int		gre_timeouts[GRE_CT_MAX];
-};
 
 static inline struct netns_proto_gre *gre_pernet(struct net *net)
 {
@@ -402,6 +390,8 @@ static int __init nf_ct_proto_gre_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0);
+
 	ret = register_pernet_subsys(&proto_gre_net_ops);
 	if (ret < 0)
 		goto out_pernet;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 42487d01a3ed..2e61aab6ed73 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2457,7 +2457,7 @@ err:
 static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 				   struct nft_rule *rule)
 {
-	struct nft_expr *expr;
+	struct nft_expr *expr, *next;
 
 	/*
 	 * Careful: some expressions might not be initialized in case this
@@ -2465,8 +2465,9 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 */
 	expr = nft_expr_first(rule);
 	while (expr != nft_expr_last(rule) && expr->ops) {
+		next = nft_expr_next(expr);
 		nf_tables_expr_destroy(ctx, expr);
-		expr = nft_expr_next(expr);
+		expr = next;
 	}
 	kfree(rule);
 }
@@ -2589,17 +2590,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 
 		if (chain->use == UINT_MAX)
 			return -EOVERFLOW;
-	}
 
-	if (nla[NFTA_RULE_POSITION]) {
-		if (!(nlh->nlmsg_flags & NLM_F_CREATE))
-			return -EOPNOTSUPP;
-
-		pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
-		old_rule = __nft_rule_lookup(chain, pos_handle);
-		if (IS_ERR(old_rule)) {
-			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
-			return PTR_ERR(old_rule);
+		if (nla[NFTA_RULE_POSITION]) {
+			pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
+			old_rule = __nft_rule_lookup(chain, pos_handle);
+			if (IS_ERR(old_rule)) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
+				return PTR_ERR(old_rule);
+			}
 		}
 	}
 
@@ -2669,21 +2667,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
-		if (!nft_is_active_next(net, old_rule)) {
-			err = -ENOENT;
-			goto err2;
-		}
-		trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
-					   old_rule);
+		trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
 		if (trans == NULL) {
 			err = -ENOMEM;
 			goto err2;
 		}
-		nft_deactivate_next(net, old_rule);
-		chain->use--;
-
-		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
-			err = -ENOMEM;
+		err = nft_delrule(&ctx, old_rule);
+		if (err < 0) {
+			nft_trans_destroy(trans);
 			goto err2;
 		}
 
@@ -6324,7 +6315,7 @@ static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules)
 	call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old);
 }
 
-static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *chain)
+static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain)
 {
 	struct nft_rule **g0, **g1;
 	bool next_genbit;
@@ -6441,11 +6432,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	/* step 2.  Make rules_gen_X visible to packet path */
 	list_for_each_entry(table, &net->nft.tables, list) {
-		list_for_each_entry(chain, &table->chains, list) {
-			if (!nft_is_active_next(net, chain))
-				continue;
-			nf_tables_commit_chain_active(net, chain);
-		}
+		list_for_each_entry(chain, &table->chains, list)
+			nf_tables_commit_chain(net, chain);
 	}
 
 	/*
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index a518eb162344..109b0d27345a 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -455,7 +455,8 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 	case IPPROTO_TCP:
 		timeouts = nf_tcp_pernet(net)->timeouts;
 		break;
-	case IPPROTO_UDP:
+	case IPPROTO_UDP: /* fallthrough */
+	case IPPROTO_UDPLITE:
 		timeouts = nf_udp_pernet(net)->timeouts;
 		break;
 	case IPPROTO_DCCP:
@@ -469,13 +470,23 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 	case IPPROTO_SCTP:
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 		timeouts = nf_sctp_pernet(net)->timeouts;
+#endif
+		break;
+	case IPPROTO_GRE:
+#ifdef CONFIG_NF_CT_PROTO_GRE
+		if (l4proto->net_id) {
+			struct netns_proto_gre *net_gre;
+
+			net_gre = net_generic(net, *l4proto->net_id);
+			timeouts = net_gre->gre_timeouts;
+		}
 #endif
 		break;
 	case 255:
 		timeouts = &nf_generic_pernet(net)->timeout;
 		break;
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto);
 		break;
 	}
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 9d0ede474224..7334e0b80a5e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -520,6 +520,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		    void *info)
 {
 	struct xt_match *match = expr->ops->data;
+	struct module *me = match->me;
 	struct xt_mtdtor_param par;
 
 	par.net = ctx->net;
@@ -530,7 +531,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		par.match->destroy(&par);
 
 	if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
-		module_put(match->me);
+		module_put(me);
 }
 
 static void
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index e82d9a966c45..974525eb92df 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -214,7 +214,9 @@ static int __init nft_flow_offload_module_init(void)
 {
 	int err;
 
-	register_netdevice_notifier(&flow_offload_netdev_notifier);
+	err = register_netdevice_notifier(&flow_offload_netdev_notifier);
+	if (err)
+		goto err;
 
 	err = nft_register_expr(&nft_flow_offload_type);
 	if (err < 0)
@@ -224,6 +226,7 @@ static int __init nft_flow_offload_module_init(void)
 
 register_expr:
 	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+err:
 	return err;
 }
 
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index dec843cadf46..9e05c86ba5c4 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -201,18 +201,8 @@ static __net_init int xt_rateest_net_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit xt_rateest_net_exit(struct net *net)
-{
-	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(xn->hash); i++)
-		WARN_ON_ONCE(!hlist_empty(&xn->hash[i]));
-}
-
 static struct pernet_operations xt_rateest_net_ops = {
 	.init = xt_rateest_net_init,
-	.exit = xt_rateest_net_exit,
 	.id   = &xt_rateest_id,
 	.size = sizeof(struct xt_rateest_net),
 };
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 3e7d259e5d8d..1ad4017f9b73 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -295,9 +295,10 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 
 	/* copy match config into hashtable config */
 	ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3);
-
-	if (ret)
+	if (ret) {
+		vfree(hinfo);
 		return ret;
+	}
 
 	hinfo->cfg.size = size;
 	if (hinfo->cfg.max == 0)
@@ -814,7 +815,6 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	int ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
-
 	if (ret)
 		return ret;
 
@@ -830,7 +830,6 @@ hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	int ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 2);
-
 	if (ret)
 		return ret;
 
@@ -921,7 +920,6 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par)
 		return ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
-
 	if (ret)
 		return ret;
 
@@ -940,7 +938,6 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par)
 		return ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 2);
-
 	if (ret)
 		return ret;
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index b0e74a3e77ec..025f48e14a91 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -410,6 +410,7 @@ static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb)
 	head->truesize += skb->truesize;
 	head->data_len += skb->len;
 	head->len += skb->len;
+	refcount_add(skb->truesize, &head->sk->sk_wmem_alloc);
 
 	__skb_header_release(skb);
 }
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 2afc4f8c37a7..488019766433 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -584,12 +584,15 @@ static void  tipc_node_clear_links(struct tipc_node *node)
 /* tipc_node_cleanup - delete nodes that does not
  * have active links for NODE_CLEANUP_AFTER time
  */
-static int tipc_node_cleanup(struct tipc_node *peer)
+static bool tipc_node_cleanup(struct tipc_node *peer)
 {
 	struct tipc_net *tn = tipc_net(peer->net);
 	bool deleted = false;
 
-	spin_lock_bh(&tn->node_list_lock);
+	/* If lock held by tipc_node_stop() the node will be deleted anyway */
+	if (!spin_trylock_bh(&tn->node_list_lock))
+		return false;
+
 	tipc_node_write_lock(peer);
 
 	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index edbe81534c6d..d07ccf8a23f7 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -137,4 +137,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index f55a2daed59b..7bb787cfa971 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -171,4 +171,10 @@ The following three commands are equivalent:
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 408ec30d8872..ed87c9b619ad 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -136,4 +136,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
index e3eb0eab7641..f4c5e5538bb8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
@@ -78,4 +78,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ac4e904b10fb..ecf618807125 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -124,7 +124,8 @@ OPTIONS
 		  Generate human-readable JSON output. Implies **-j**.
 
 	-f, --bpffs
-		  Show file names of pinned programs.
+		  When showing BPF programs, show file names of pinned
+		  programs.
 
 EXAMPLES
 ========
@@ -206,4 +207,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-map**\ (8), **bpftool-cgroup**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 04cd4f92ab89..129b7a9c0f9b 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -63,5 +63,10 @@ OPTIONS
 
 SEE ALSO
 ========
-	**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
-        **bpftool-perf**\ (8), **bpftool-net**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 25af85304ebe..70fd48d79f61 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -130,16 +130,17 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 	return 0;
 }
 
-int open_obj_pinned(char *path)
+int open_obj_pinned(char *path, bool quiet)
 {
 	int fd;
 
 	fd = bpf_obj_get(path);
 	if (fd < 0) {
-		p_err("bpf obj get (%s): %s", path,
-		      errno == EACCES && !is_bpffs(dirname(path)) ?
-		    "directory not in bpf file system (bpffs)" :
-		    strerror(errno));
+		if (!quiet)
+			p_err("bpf obj get (%s): %s", path,
+			      errno == EACCES && !is_bpffs(dirname(path)) ?
+			    "directory not in bpf file system (bpffs)" :
+			    strerror(errno));
 		return -1;
 	}
 
@@ -151,7 +152,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 	enum bpf_obj_type type;
 	int fd;
 
-	fd = open_obj_pinned(path);
+	fd = open_obj_pinned(path, false);
 	if (fd < 0)
 		return -1;
 
@@ -304,7 +305,7 @@ char *get_fdinfo(int fd, const char *key)
 		return NULL;
 	}
 
-	while ((n = getline(&line, &line_n, fdi))) {
+	while ((n = getline(&line, &line_n, fdi)) > 0) {
 		char *value;
 		int len;
 
@@ -384,7 +385,7 @@ int build_pinned_obj_table(struct pinned_obj_table *tab,
 		while ((ftse = fts_read(fts))) {
 			if (!(ftse->fts_info & FTS_F))
 				continue;
-			fd = open_obj_pinned(ftse->fts_path);
+			fd = open_obj_pinned(ftse->fts_path, true);
 			if (fd < 0)
 				continue;
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28322ace2856..a8bf1e2d9818 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -127,7 +127,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv,
 int get_fd_type(int fd);
 const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
-int open_obj_pinned(char *path);
+int open_obj_pinned(char *path, bool quiet);
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
 int do_pin_fd(int fd, const char *name);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 5302ee282409..ccee180dfb76 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -357,10 +357,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (!hash_empty(prog_table.table)) {
 		struct pinned_obj *obj;
 
-		printf("\n");
 		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
 			if (obj->id == info->id)
-				printf("\tpinned %s\n", obj->path);
+				printf("\n\tpinned %s", obj->path);
 		}
 	}
 
@@ -845,6 +844,7 @@ static int do_load(int argc, char **argv)
 			}
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "map")) {
+			void *new_map_replace;
 			char *endptr, *name;
 			int fd;
 
@@ -878,12 +878,15 @@ static int do_load(int argc, char **argv)
 			if (fd < 0)
 				goto err_free_reuse_maps;
 
-			map_replace = reallocarray(map_replace, old_map_fds + 1,
-						   sizeof(*map_replace));
-			if (!map_replace) {
+			new_map_replace = reallocarray(map_replace,
+						       old_map_fds + 1,
+						       sizeof(*map_replace));
+			if (!new_map_replace) {
 				p_err("mem alloc failed");
 				goto err_free_reuse_maps;
 			}
+			map_replace = new_map_replace;
+
 			map_replace[old_map_fds].idx = idx;
 			map_replace[old_map_fds].name = name;
 			map_replace[old_map_fds].fd = fd;
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 000000000000..401d0c1e612d
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+	TCA_ACT_UNSPEC,
+	TCA_ACT_KIND,
+	TCA_ACT_OPTIONS,
+	TCA_ACT_INDEX,
+	TCA_ACT_STATS,
+	TCA_ACT_PAD,
+	TCA_ACT_COOKIE,
+	__TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND	1
+#define TCA_ACT_NOBIND	0
+#define TCA_ACT_UNBIND	1
+#define TCA_ACT_NOUNBIND	0
+#define TCA_ACT_REPLACE		1
+#define TCA_ACT_NOREPLACE	0
+
+#define TC_ACT_UNSPEC	(-1)
+#define TC_ACT_OK		0
+#define TC_ACT_RECLASSIFY	1
+#define TC_ACT_SHOT		2
+#define TC_ACT_PIPE		3
+#define TC_ACT_STOLEN		4
+#define TC_ACT_QUEUED		5
+#define TC_ACT_REPEAT		6
+#define TC_ACT_REDIRECT		7
+#define TC_ACT_TRAP		8 /* For hw path, this means "trap to cpu"
+				   * and don't further process the frame
+				   * in hardware. For sw path, this is
+				   * equivalent of TC_ACT_STOLEN - drop
+				   * the skb and act like everything
+				   * is alright.
+				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+	TCA_ID_UNSPEC=0,
+	TCA_ID_POLICE=1,
+	/* other actions go here */
+	__TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+	__u32			index;
+	int			action;
+#define TC_POLICE_UNSPEC	TC_ACT_UNSPEC
+#define TC_POLICE_OK		TC_ACT_OK
+#define TC_POLICE_RECLASSIFY	TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT		TC_ACT_SHOT
+#define TC_POLICE_PIPE		TC_ACT_PIPE
+
+	__u32			limit;
+	__u32			burst;
+	__u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+	int			refcnt;
+	int			bindcnt;
+	__u32			capab;
+};
+
+struct tcf_t {
+	__u64   install;
+	__u64   lastuse;
+	__u64   expires;
+	__u64   firstuse;
+};
+
+struct tc_cnt {
+	int                   refcnt;
+	int                   bindcnt;
+};
+
+#define tc_gen \
+	__u32                 index; \
+	__u32                 capab; \
+	int                   action; \
+	int                   refcnt; \
+	int                   bindcnt
+
+enum {
+	TCA_POLICE_UNSPEC,
+	TCA_POLICE_TBF,
+	TCA_POLICE_RATE,
+	TCA_POLICE_PEAKRATE,
+	TCA_POLICE_AVRATE,
+	TCA_POLICE_RESULT,
+	TCA_POLICE_TM,
+	TCA_POLICE_PAD,
+	__TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW	(1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW	(1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW	(1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE	(1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC	0
+#define TC_U32_ROOT	(0xFFF00000)
+
+enum {
+	TCA_U32_UNSPEC,
+	TCA_U32_CLASSID,
+	TCA_U32_HASH,
+	TCA_U32_LINK,
+	TCA_U32_DIVISOR,
+	TCA_U32_SEL,
+	TCA_U32_POLICE,
+	TCA_U32_ACT,
+	TCA_U32_INDEV,
+	TCA_U32_PCNT,
+	TCA_U32_MARK,
+	TCA_U32_FLAGS,
+	TCA_U32_PAD,
+	__TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+	__be32		mask;
+	__be32		val;
+	int		off;
+	int		offmask;
+};
+
+struct tc_u32_sel {
+	unsigned char		flags;
+	unsigned char		offshift;
+	unsigned char		nkeys;
+
+	__be16			offmask;
+	__u16			off;
+	short			offoff;
+
+	short			hoff;
+	__be32			hmask;
+	struct tc_u32_key	keys[0];
+};
+
+struct tc_u32_mark {
+	__u32		val;
+	__u32		mask;
+	__u32		success;
+};
+
+struct tc_u32_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+	__u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL		1
+#define TC_U32_OFFSET		2
+#define TC_U32_VAROFFSET	4
+#define TC_U32_EAT		8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
+/* ROUTE filter */
+
+enum {
+	TCA_ROUTE4_UNSPEC,
+	TCA_ROUTE4_CLASSID,
+	TCA_ROUTE4_TO,
+	TCA_ROUTE4_FROM,
+	TCA_ROUTE4_IIF,
+	TCA_ROUTE4_POLICE,
+	TCA_ROUTE4_ACT,
+	__TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+	TCA_FW_UNSPEC,
+	TCA_FW_CLASSID,
+	TCA_FW_POLICE,
+	TCA_FW_INDEV, /*  used by CONFIG_NET_CLS_IND */
+	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+	TCA_FW_MASK,
+	__TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+	FLOW_KEY_SRC,
+	FLOW_KEY_DST,
+	FLOW_KEY_PROTO,
+	FLOW_KEY_PROTO_SRC,
+	FLOW_KEY_PROTO_DST,
+	FLOW_KEY_IIF,
+	FLOW_KEY_PRIORITY,
+	FLOW_KEY_MARK,
+	FLOW_KEY_NFCT,
+	FLOW_KEY_NFCT_SRC,
+	FLOW_KEY_NFCT_DST,
+	FLOW_KEY_NFCT_PROTO_SRC,
+	FLOW_KEY_NFCT_PROTO_DST,
+	FLOW_KEY_RTCLASSID,
+	FLOW_KEY_SKUID,
+	FLOW_KEY_SKGID,
+	FLOW_KEY_VLAN_TAG,
+	FLOW_KEY_RXHASH,
+	__FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX	(__FLOW_KEY_MAX - 1)
+
+enum {
+	FLOW_MODE_MAP,
+	FLOW_MODE_HASH,
+};
+
+enum {
+	TCA_FLOW_UNSPEC,
+	TCA_FLOW_KEYS,
+	TCA_FLOW_MODE,
+	TCA_FLOW_BASECLASS,
+	TCA_FLOW_RSHIFT,
+	TCA_FLOW_ADDEND,
+	TCA_FLOW_MASK,
+	TCA_FLOW_XOR,
+	TCA_FLOW_DIVISOR,
+	TCA_FLOW_ACT,
+	TCA_FLOW_POLICE,
+	TCA_FLOW_EMATCHES,
+	TCA_FLOW_PERTURB,
+	__TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX	(__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+	TCA_BASIC_UNSPEC,
+	TCA_BASIC_CLASSID,
+	TCA_BASIC_EMATCHES,
+	TCA_BASIC_ACT,
+	TCA_BASIC_POLICE,
+	__TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+	TCA_CGROUP_UNSPEC,
+	TCA_CGROUP_ACT,
+	TCA_CGROUP_POLICE,
+	TCA_CGROUP_EMATCHES,
+	__TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT		(1 << 0)
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	TCA_BPF_FD,
+	TCA_BPF_NAME,
+	TCA_BPF_FLAGS,
+	TCA_BPF_FLAGS_GEN,
+	TCA_BPF_TAG,
+	TCA_BPF_ID,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+
+	TCA_FLOWER_FLAGS,
+	TCA_FLOWER_KEY_VLAN_ID,		/* be16 */
+	TCA_FLOWER_KEY_VLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_VLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+	TCA_FLOWER_KEY_TCP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_TCP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_SCTP_SRC,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_FLAGS,		/* be32 */
+	TCA_FLOWER_KEY_FLAGS_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ICMPV4_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+	TCA_FLOWER_KEY_ARP_SIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_SIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_OP,		/* u8 */
+	TCA_FLOWER_KEY_ARP_OP_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ARP_SHA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_SHA_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
+
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
+	TCA_FLOWER_KEY_TCP_FLAGS,	/* be16 */
+	TCA_FLOWER_KEY_TCP_FLAGS_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_IP_TOS,		/* u8 */
+	TCA_FLOWER_KEY_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
+	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+	TCA_FLOWER_IN_HW_COUNT,
+
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+	TCA_MATCHALL_UNSPEC,
+	TCA_MATCHALL_CLASSID,
+	TCA_MATCHALL_ACT,
+	TCA_MATCHALL_FLAGS,
+	__TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+	__u16		nmatches;
+	__u16		progid;
+};
+
+enum {
+	TCA_EMATCH_TREE_UNSPEC,
+	TCA_EMATCH_TREE_HDR,
+	TCA_EMATCH_TREE_LIST,
+	__TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+	__u16		matchid;
+	__u16		kind;
+	__u16		flags;
+	__u16		pad; /* currently unused */
+};
+
+/*  0                   1
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 
+ * +-----------------------+-+-+---+
+ * |         Unused        |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ *          where: 0 0 END (last ematch)
+ *                 0 1 AND
+ *                 1 0 OR
+ *                 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END	0
+#define TCF_EM_REL_AND	(1<<0)
+#define TCF_EM_REL_OR	(1<<1)
+#define TCF_EM_INVERT	(1<<2)
+#define TCF_EM_SIMPLE	(1<<3)
+
+#define TCF_EM_REL_MASK	3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+	TCF_LAYER_LINK,
+	TCF_LAYER_NETWORK,
+	TCF_LAYER_TRANSPORT,
+	__TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ *   1..32767		Reserved for ematches inside kernel tree
+ *   32768..65535	Free to use, not reliable
+ */
+#define	TCF_EM_CONTAINER	0
+#define	TCF_EM_CMP		1
+#define	TCF_EM_NBYTE		2
+#define	TCF_EM_U32		3
+#define	TCF_EM_META		4
+#define	TCF_EM_TEXT		5
+#define	TCF_EM_VLAN		6
+#define	TCF_EM_CANID		7
+#define	TCF_EM_IPSET		8
+#define	TCF_EM_IPT		9
+#define	TCF_EM_MAX		9
+
+enum {
+	TCF_EM_PROG_TC
+};
+
+enum {
+	TCF_EM_OPND_EQ,
+	TCF_EM_OPND_GT,
+	TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 000000000000..6e89a5df49a4
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	TCA_ACT_BPF_FD,
+	TCA_ACT_BPF_NAME,
+	TCA_ACT_BPF_PAD,
+	TCA_ACT_BPF_TAG,
+	TCA_ACT_BPF_ID,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f1fe492c8e17..f0017c831e57 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -24,6 +24,7 @@ TARGETS += memory-hotplug
 TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
+TARGETS += netfilter
 TARGETS += nsfs
 TARGETS += powerpc
 TARGETS += proc
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
index 7887df693399..44ed7f29f8ab 100644
--- a/tools/testing/selftests/bpf/test_netcnt.c
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -81,7 +81,10 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0);
+	if (system("which ping6 &>/dev/null") == 0)
+		assert(!system("ping6 localhost -c 10000 -f -q > /dev/null"));
+	else
+		assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null"));
 
 	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
 			   &prog_cnt)) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6f61df62f690..550b7e46bf4a 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -13896,6 +13896,25 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"calls: ctx read at start of subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			BPF_JMP_REG(BPF_JSGT, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
new file mode 100644
index 000000000000..47ed6cef93fb
--- /dev/null
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for netfilter selftests
+
+TEST_PROGS := nft_trans_stress.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
new file mode 100644
index 000000000000..1017313e41a8
--- /dev/null
+++ b/tools/testing/selftests/netfilter/config
@@ -0,0 +1,2 @@
+CONFIG_NET_NS=y
+NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh
new file mode 100755
index 000000000000..f1affd12c4b1
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh
@@ -0,0 +1,78 @@
+#!/bin/bash
+#
+# This test is for stress-testing the nf_tables config plane path vs.
+# packet path processing: Make sure we never release rules that are
+# still visible to other cpus.
+#
+# set -e
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+testns=testns1
+tables="foo bar baz quux"
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+tmp=$(mktemp)
+
+for table in $tables; do
+	echo add table inet "$table" >> "$tmp"
+	echo flush table inet "$table" >> "$tmp"
+
+	echo "add chain inet $table INPUT { type filter hook input priority 0; }" >> "$tmp"
+	echo "add chain inet $table OUTPUT { type filter hook output priority 0; }" >> "$tmp"
+	for c in $(seq 1 400); do
+		chain=$(printf "chain%03u" "$c")
+		echo "add chain inet $table $chain" >> "$tmp"
+	done
+
+	for c in $(seq 1 400); do
+		chain=$(printf "chain%03u" "$c")
+		for BASE in INPUT OUTPUT; do
+			echo "add rule inet $table $BASE counter jump $chain" >> "$tmp"
+		done
+		echo "add rule inet $table $chain counter return" >> "$tmp"
+	done
+done
+
+ip netns add "$testns"
+ip -netns "$testns" link set lo up
+
+lscpu | grep ^CPU\(s\): | ( read cpu cpunum ;
+cpunum=$((cpunum-1))
+for i in $(seq 0 $cpunum);do
+	mask=$(printf 0x%x $((1<<$i)))
+        ip netns exec "$testns" taskset $mask ping -4 127.0.0.1 -fq > /dev/null &
+        ip netns exec "$testns" taskset $mask ping -6 ::1 -fq > /dev/null &
+done)
+
+sleep 1
+
+for i in $(seq 1 10) ; do ip netns exec "$testns" nft -f "$tmp" & done
+
+for table in $tables;do
+	randsleep=$((RANDOM%10))
+	sleep $randsleep
+	ip netns exec "$testns" nft delete table inet $table 2>/dev/null
+done
+
+randsleep=$((RANDOM%10))
+sleep $randsleep
+
+pkill -9 ping
+
+wait
+
+rm -f "$tmp"
+ip netns del "$testns"