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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

4 files changed, 99 insertions, 337 deletions

diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile
index 02d369ca6a53..809f019d3cba 100644
--- a/arch/powerpc/net/Makefile
+++ b/arch/powerpc/net/Makefile
@@ -3,7 +3,7 @@
 # Arch-specific network modules
 #
 ifeq ($(CONFIG_PPC64),y)
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm64.o bpf_jit_comp64.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o
 else
 obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
 endif
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 8bdef7ed28a8..3609be4692b3 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -20,7 +20,7 @@
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 8*8		|
+ *		[   nv gpr save area	] 6*8		|
  *		[    tail_call_cnt	] 8		|
  *		[    local_tmp_var	] 8		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
@@ -28,8 +28,8 @@
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
-/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */
-#define BPF_PPC_STACK_SAVE	(8*8)
+/* for gpr non volatile registers BPG_REG_6 to 10 */
+#define BPF_PPC_STACK_SAVE	(6*8)
 /* for bpf JIT code internal usage */
 #define BPF_PPC_STACK_LOCALS	16
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
@@ -39,10 +39,8 @@
 #ifndef __ASSEMBLY__
 
 /* BPF register usage */
-#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 0)
-#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 1)
-#define TMP_REG_1	(MAX_BPF_JIT_REG + 2)
-#define TMP_REG_2	(MAX_BPF_JIT_REG + 3)
+#define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
 
 /* BPF to ppc register mappings */
 static const int b2p[] = {
@@ -63,40 +61,23 @@ static const int b2p[] = {
 	[BPF_REG_FP] = 31,
 	/* eBPF jit internal registers */
 	[BPF_REG_AX] = 2,
-	[SKB_HLEN_REG] = 25,
-	[SKB_DATA_REG] = 26,
 	[TMP_REG_1] = 9,
 	[TMP_REG_2] = 10
 };
 
-/* PPC NVR range -- update this if we ever use NVRs below r24 */
-#define BPF_PPC_NVR_MIN		24
-
-/* Assembly helpers */
-#define DECLARE_LOAD_FUNC(func)	u64 func(u64 r3, u64 r4);			\
-				u64 func##_negative_offset(u64 r3, u64 r4);	\
-				u64 func##_positive_offset(u64 r3, u64 r4);
-
-DECLARE_LOAD_FUNC(sk_load_word);
-DECLARE_LOAD_FUNC(sk_load_half);
-DECLARE_LOAD_FUNC(sk_load_byte);
-
-#define CHOOSE_LOAD_FUNC(imm, func)						\
-			(imm < 0 ?						\
-			(imm >= SKF_LL_OFF ? func##_negative_offset : func) :	\
-			func##_positive_offset)
+/* PPC NVR range -- update this if we ever use NVRs below r27 */
+#define BPF_PPC_NVR_MIN		27
 
 #define SEEN_FUNC	0x1000 /* might call external helpers */
 #define SEEN_STACK	0x2000 /* uses BPF stack */
-#define SEEN_SKB	0x4000 /* uses sk_buff */
-#define SEEN_TAILCALL	0x8000 /* uses tail calls */
+#define SEEN_TAILCALL	0x4000 /* uses tail calls */
 
 struct codegen_context {
 	/*
 	 * This is used to track register usage as well
 	 * as calls to external helpers.
 	 * - register usage is tracked with corresponding
-	 *   bits (r3-r10 and r25-r31)
+	 *   bits (r3-r10 and r27-r31)
 	 * - rest of the bits can be used to track other
 	 *   things -- for now, we use bits 16 to 23
 	 *   encoded in SEEN_* macros above
diff --git a/arch/powerpc/net/bpf_jit_asm64.S b/arch/powerpc/net/bpf_jit_asm64.S
deleted file mode 100644
index 7e4c51430b84..000000000000
--- a/arch/powerpc/net/bpf_jit_asm64.S
+++ /dev/null
@@ -1,180 +0,0 @@
-/*
- * bpf_jit_asm64.S: Packet/header access helper functions
- * for PPC64 BPF compiler.
- *
- * Copyright 2016, Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
- * 		   IBM Corporation
- *
- * Based on bpf_jit_asm.S by Matt Evans
- *
- * 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; version 2
- * of the License.
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/ptrace.h>
-#include "bpf_jit64.h"
-
-/*
- * All of these routines are called directly from generated code,
- * with the below register usage:
- * r27		skb pointer (ctx)
- * r25		skb header length
- * r26		skb->data pointer
- * r4		offset
- *
- * Result is passed back in:
- * r8		data read in host endian format (accumulator)
- *
- * r9 is used as a temporary register
- */
-
-#define r_skb	r27
-#define r_hlen	r25
-#define r_data	r26
-#define r_off	r4
-#define r_val	r8
-#define r_tmp	r9
-
-_GLOBAL_TOC(sk_load_word)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_word_neg
-	b	sk_load_word_positive_offset
-
-_GLOBAL_TOC(sk_load_word_positive_offset)
-	/* Are we accessing past headlen? */
-	subi	r_tmp, r_hlen, 4
-	cmpd	r_tmp, r_off
-	blt	bpf_slow_path_word
-	/* Nope, just hitting the header.  cr0 here is eq or gt! */
-	LWZX_BE	r_val, r_data, r_off
-	blr	/* Return success, cr0 != LT */
-
-_GLOBAL_TOC(sk_load_half)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_half_neg
-	b	sk_load_half_positive_offset
-
-_GLOBAL_TOC(sk_load_half_positive_offset)
-	subi	r_tmp, r_hlen, 2
-	cmpd	r_tmp, r_off
-	blt	bpf_slow_path_half
-	LHZX_BE	r_val, r_data, r_off
-	blr
-
-_GLOBAL_TOC(sk_load_byte)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_byte_neg
-	b	sk_load_byte_positive_offset
-
-_GLOBAL_TOC(sk_load_byte_positive_offset)
-	cmpd	r_hlen, r_off
-	ble	bpf_slow_path_byte
-	lbzx	r_val, r_data, r_off
-	blr
-
-/*
- * Call out to skb_copy_bits:
- * Allocate a new stack frame here to remain ABI-compliant in
- * stashing LR.
- */
-#define bpf_slow_path_common(SIZE)					\
-	mflr	r0;							\
-	std	r0, PPC_LR_STKOFF(r1);					\
-	stdu	r1, -(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS)(r1);	\
-	mr	r3, r_skb;						\
-	/* r4 = r_off as passed */					\
-	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
-	li	r6, SIZE;						\
-	bl	skb_copy_bits;						\
-	nop;								\
-	/* save r5 */							\
-	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
-	/* r3 = 0 on success */						\
-	addi	r1, r1, STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS;	\
-	ld	r0, PPC_LR_STKOFF(r1);					\
-	mtlr	r0;							\
-	cmpdi	r3, 0;							\
-	blt	bpf_error;	/* cr0 = LT */
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	/* Data value is on stack, and cr0 != LT */
-	LWZX_BE	r_val, 0, r5
-	blr
-
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	LHZX_BE	r_val, 0, r5
-	blr
-
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	lbzx	r_val, 0, r5
-	blr
-
-/*
- * Call out to bpf_internal_load_pointer_neg_helper
- */
-#define sk_negative_common(SIZE)				\
-	mflr	r0;						\
-	std	r0, PPC_LR_STKOFF(r1);				\
-	stdu	r1, -STACK_FRAME_MIN_SIZE(r1);			\
-	mr	r3, r_skb;					\
-	/* r4 = r_off, as passed */				\
-	li	r5, SIZE;					\
-	bl	bpf_internal_load_pointer_neg_helper;		\
-	nop;							\
-	addi	r1, r1, STACK_FRAME_MIN_SIZE;			\
-	ld	r0, PPC_LR_STKOFF(r1);				\
-	mtlr	r0;						\
-	/* R3 != 0 on success */				\
-	cmpldi	r3, 0;						\
-	beq	bpf_error_slow;	/* cr0 = EQ */
-
-bpf_slow_path_word_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_word_negative_offset
-
-_GLOBAL_TOC(sk_load_word_negative_offset)
-	sk_negative_common(4)
-	LWZX_BE	r_val, 0, r3
-	blr
-
-bpf_slow_path_half_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_half_negative_offset
-
-_GLOBAL_TOC(sk_load_half_negative_offset)
-	sk_negative_common(2)
-	LHZX_BE	r_val, 0, r3
-	blr
-
-bpf_slow_path_byte_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_byte_negative_offset
-
-_GLOBAL_TOC(sk_load_byte_negative_offset)
-	sk_negative_common(1)
-	lbzx	r_val, 0, r3
-	blr
-
-bpf_error_slow:
-	/* fabricate a cr0 = lt */
-	li	r_tmp, -1
-	cmpdi	r_tmp, 0
-bpf_error:
-	/*
-	 * Entered with cr0 = lt
-	 * Generated code will 'blt epilogue', returning 0.
-	 */
-	li	r_val, 0
-	blr
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0ef3d9580e98..f1c95779843b 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -59,7 +59,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 8*8
+ *		[   nv gpr save area	] 6*8
  *		[    tail_call_cnt	] 8
  *		[    local_tmp_var	] 8
  *		[   unused red zone	] 208 bytes protected
@@ -88,21 +88,6 @@ static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
 	BUG();
 }
 
-static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx)
-{
-	/*
-	 * Load skb->len and skb->data_len
-	 * r3 points to skb
-	 */
-	PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len));
-	PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len));
-	/* header_len = len - data_len */
-	PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]);
-
-	/* skb->data pointer */
-	PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data));
-}
-
 static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
@@ -145,18 +130,6 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		if (bpf_is_seen_register(ctx, i))
 			PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
 
-	/*
-	 * Save additional non-volatile regs if we cache skb
-	 * Also, setup skb data
-	 */
-	if (ctx->seen & SEEN_SKB) {
-		PPC_BPF_STL(b2p[SKB_HLEN_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
-		PPC_BPF_STL(b2p[SKB_DATA_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
-		bpf_jit_emit_skb_loads(image, ctx);
-	}
-
 	/* Setup frame pointer to point to the bpf stack area */
 	if (bpf_is_seen_register(ctx, BPF_REG_FP))
 		PPC_ADDI(b2p[BPF_REG_FP], 1,
@@ -172,14 +145,6 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 		if (bpf_is_seen_register(ctx, i))
 			PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
 
-	/* Restore non-volatile registers used for skb cache */
-	if (ctx->seen & SEEN_SKB) {
-		PPC_BPF_LL(b2p[SKB_HLEN_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
-		PPC_BPF_LL(b2p[SKB_DATA_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
-	}
-
 	/* Tear down our stack frame */
 	if (bpf_has_stack_frame(ctx)) {
 		PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
@@ -202,25 +167,37 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
 {
+	unsigned int i, ctx_idx = ctx->idx;
+
+	/* Load function address into r12 */
+	PPC_LI64(12, func);
+
+	/* For bpf-to-bpf function calls, the callee's address is unknown
+	 * until the last extra pass. As seen above, we use PPC_LI64() to
+	 * load the callee's address, but this may optimize the number of
+	 * instructions required based on the nature of the address.
+	 *
+	 * Since we don't want the number of instructions emitted to change,
+	 * we pad the optimized PPC_LI64() call with NOPs to guarantee that
+	 * we always have a five-instruction sequence, which is the maximum
+	 * that PPC_LI64() can emit.
+	 */
+	for (i = ctx->idx - ctx_idx; i < 5; i++)
+		PPC_NOP();
+
 #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);
+	PPC_BPF_LL(2, 12, 8);
+	/* Load actual entry point from function descriptor */
+	PPC_BPF_LL(12, 12, 0);
 #endif
+
+	PPC_MTLR(12);
 	PPC_BLRL();
 }
 
@@ -291,7 +268,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 /* Assemble the body code between the prologue & epilogue */
 static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			      struct codegen_context *ctx,
-			      u32 *addrs)
+			      u32 *addrs, bool extra_pass)
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
@@ -747,29 +724,30 @@ emit_clear:
 			break;
 
 		/*
-		 * Call kernel helper
+		 * Call kernel helper or bpf function
 		 */
 		case BPF_JMP | BPF_CALL:
 			ctx->seen |= SEEN_FUNC;
-			func = (u8 *) __bpf_call_base + imm;
 
-			/* Save skb pointer if we need to re-cache skb data */
-			if ((ctx->seen & SEEN_SKB) &&
-			    bpf_helper_changes_pkt_data(func))
-				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
+			/* 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 */
+			else
+				func = (u8 *) __bpf_call_base + imm;
 
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
 
 			/* move return value from r3 to BPF_REG_0 */
 			PPC_MR(b2p[BPF_REG_0], 3);
-
-			/* refresh skb cache */
-			if ((ctx->seen & SEEN_SKB) &&
-			    bpf_helper_changes_pkt_data(func)) {
-				/* reload skb pointer to r3 */
-				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
-				bpf_jit_emit_skb_loads(image, ctx);
-			}
 			break;
 
 		/*
@@ -887,65 +865,6 @@ cond_branch:
 			break;
 
 		/*
-		 * Loads from packet header/data
-		 * Assume 32-bit input value in imm and X (src_reg)
-		 */
-
-		/* Absolute loads */
-		case BPF_LD | BPF_W | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word);
-			goto common_load_abs;
-		case BPF_LD | BPF_H | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half);
-			goto common_load_abs;
-		case BPF_LD | BPF_B | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte);
-common_load_abs:
-			/*
-			 * Load from [imm]
-			 * Load into r4, which can just be passed onto
-			 *  skb load helpers as the second parameter
-			 */
-			PPC_LI32(4, imm);
-			goto common_load;
-
-		/* Indirect loads */
-		case BPF_LD | BPF_W | BPF_IND:
-			func = (u8 *)sk_load_word;
-			goto common_load_ind;
-		case BPF_LD | BPF_H | BPF_IND:
-			func = (u8 *)sk_load_half;
-			goto common_load_ind;
-		case BPF_LD | BPF_B | BPF_IND:
-			func = (u8 *)sk_load_byte;
-common_load_ind:
-			/*
-			 * Load from [src_reg + imm]
-			 * Treat src_reg as a 32-bit value
-			 */
-			PPC_EXTSW(4, src_reg);
-			if (imm) {
-				if (imm >= -32768 && imm < 32768)
-					PPC_ADDI(4, 4, IMM_L(imm));
-				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_ADD(4, 4, b2p[TMP_REG_1]);
-				}
-			}
-
-common_load:
-			ctx->seen |= SEEN_SKB;
-			ctx->seen |= SEEN_FUNC;
-			bpf_jit_emit_func_call(image, ctx, (u64)func);
-
-			/*
-			 * Helper returns 'lt' condition on error, and an
-			 * appropriate return value in BPF_REG_0
-			 */
-			PPC_BCC(COND_LT, exit_addr);
-			break;
-
-		/*
 		 * Tail call
 		 */
 		case BPF_JMP | BPF_TAIL_CALL:
@@ -971,6 +890,14 @@ common_load:
 	return 0;
 }
 
+struct powerpc64_jit_data {
+	struct bpf_binary_header *header;
+	u32 *addrs;
+	u8 *image;
+	u32 proglen;
+	struct codegen_context ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
 	u32 proglen;
@@ -978,6 +905,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	u8 *image = NULL;
 	u32 *code_base;
 	u32 *addrs;
+	struct powerpc64_jit_data *jit_data;
 	struct codegen_context cgctx;
 	int pass;
 	int flen;
@@ -985,6 +913,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_prog *org_fp = fp;
 	struct bpf_prog *tmp_fp;
 	bool bpf_blinded = false;
+	bool extra_pass = false;
 
 	if (!fp->jit_requested)
 		return org_fp;
@@ -998,11 +927,32 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		fp = tmp_fp;
 	}
 
+	jit_data = fp->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			fp = org_fp;
+			goto out;
+		}
+		fp->aux->jit_data = jit_data;
+	}
+
 	flen = fp->len;
+	addrs = jit_data->addrs;
+	if (addrs) {
+		cgctx = jit_data->ctx;
+		image = jit_data->image;
+		bpf_hdr = jit_data->header;
+		proglen = jit_data->proglen;
+		alloclen = proglen + FUNCTION_DESCR_SIZE;
+		extra_pass = true;
+		goto skip_init_ctx;
+	}
+
 	addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL);
 	if (addrs == NULL) {
 		fp = org_fp;
-		goto out;
+		goto out_addrs;
 	}
 
 	memset(&cgctx, 0, sizeof(struct codegen_context));
@@ -1011,10 +961,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
 
 	/* Scouting faux-generate pass 0 */
-	if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) {
+	if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
 		/* We hit something illegal or unsupported. */
 		fp = org_fp;
-		goto out;
+		goto out_addrs;
 	}
 
 	/*
@@ -1032,9 +982,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 			bpf_jit_fill_ill_insns);
 	if (!bpf_hdr) {
 		fp = org_fp;
-		goto out;
+		goto out_addrs;
 	}
 
+skip_init_ctx:
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
 
 	/* Code generation passes 1-2 */
@@ -1042,7 +993,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		/* Now build the prologue, body code & epilogue for real. */
 		cgctx.idx = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
-		bpf_jit_build_body(fp, code_base, &cgctx, addrs);
+		bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass);
 		bpf_jit_build_epilogue(code_base, &cgctx);
 
 		if (bpf_jit_enable > 1)
@@ -1068,10 +1019,20 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	fp->jited_len = alloclen;
 
 	bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
+	if (!fp->is_func || extra_pass) {
+out_addrs:
+		kfree(addrs);
+		kfree(jit_data);
+		fp->aux->jit_data = NULL;
+	} else {
+		jit_data->addrs = addrs;
+		jit_data->ctx = cgctx;
+		jit_data->proglen = proglen;
+		jit_data->image = image;
+		jit_data->header = bpf_hdr;
+	}
 
 out:
-	kfree(addrs);
-
 	if (bpf_blinded)
 		bpf_jit_prog_release_other(fp, fp == org_fp ? tmp_fp : org_fp);