diff --git a/MAINTAINERS b/MAINTAINERS
index 03c46f4..bfaa411 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2801,7 +2801,7 @@
 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/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 a6fdaea..89198017 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 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	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 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	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 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	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 50b1297..17482f5 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 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		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 222785a..5fda4f7 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/include/linux/filter.h b/include/linux/filter.h
index de629b7..448dcc4 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/kernel/bpf/core.c b/kernel/bpf/core.c
index 1a796e0..b1a3545 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)