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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

9 files changed, 1805 insertions, 61 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index ed96869c4101..58243b0d21c0 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -31,7 +31,8 @@ config SPARC
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_PCI_IOMAP
 	select HAVE_NMI_WATCHDOG if SPARC64
-	select HAVE_CBPF_JIT
+	select HAVE_CBPF_JIT if SPARC32
+	select HAVE_EBPF_JIT if SPARC64
 	select HAVE_DEBUG_BUGVERBOSE
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index a25dc32f5d6a..3f4ad19d9ec7 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -88,6 +88,12 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	0x0038
 
+#define SO_MEMINFO		0x0039
+
+#define SO_INCOMING_NAPI_ID	0x003a
+
+#define SO_COOKIE		0x003b
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/sparc/net/Makefile b/arch/sparc/net/Makefile
index 1306a58ac541..76fa8e95b721 100644
--- a/arch/sparc/net/Makefile
+++ b/arch/sparc/net/Makefile
@@ -1,4 +1,4 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o
diff --git a/arch/sparc/net/bpf_jit.h b/arch/sparc/net/bpf_jit_32.h
index 33d6b375ff12..d5c069bff5f9 100644
--- a/arch/sparc/net/bpf_jit.h
+++ b/arch/sparc/net/bpf_jit_32.h
@@ -39,7 +39,7 @@
 #define r_TMP2		G2
 #define r_OFF		G3
 
-/* assembly code in arch/sparc/net/bpf_jit_asm.S */
+/* assembly code in arch/sparc/net/bpf_jit_asm_32.S */
 extern u32 bpf_jit_load_word[];
 extern u32 bpf_jit_load_half[];
 extern u32 bpf_jit_load_byte[];
diff --git a/arch/sparc/net/bpf_jit_64.h b/arch/sparc/net/bpf_jit_64.h
new file mode 100644
index 000000000000..74abd45796ea
--- /dev/null
+++ b/arch/sparc/net/bpf_jit_64.h
@@ -0,0 +1,66 @@
+#ifndef _BPF_JIT_H
+#define _BPF_JIT_H
+
+#ifndef __ASSEMBLER__
+#define G0		0x00
+#define G1		0x01
+#define G2		0x02
+#define G3		0x03
+#define G6		0x06
+#define G7		0x07
+#define O0		0x08
+#define O1		0x09
+#define O2		0x0a
+#define O3		0x0b
+#define O4		0x0c
+#define O5		0x0d
+#define SP		0x0e
+#define O7		0x0f
+#define L0		0x10
+#define L1		0x11
+#define L2		0x12
+#define L3		0x13
+#define L4		0x14
+#define L5		0x15
+#define L6		0x16
+#define L7		0x17
+#define I0		0x18
+#define I1		0x19
+#define I2		0x1a
+#define I3		0x1b
+#define I4		0x1c
+#define I5		0x1d
+#define FP		0x1e
+#define I7		0x1f
+
+#define r_SKB		L0
+#define r_HEADLEN	L4
+#define r_SKB_DATA	L5
+#define r_TMP		G1
+#define r_TMP2		G3
+
+/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */
+extern u32 bpf_jit_load_word[];
+extern u32 bpf_jit_load_half[];
+extern u32 bpf_jit_load_byte[];
+extern u32 bpf_jit_load_byte_msh[];
+extern u32 bpf_jit_load_word_positive_offset[];
+extern u32 bpf_jit_load_half_positive_offset[];
+extern u32 bpf_jit_load_byte_positive_offset[];
+extern u32 bpf_jit_load_byte_msh_positive_offset[];
+extern u32 bpf_jit_load_word_negative_offset[];
+extern u32 bpf_jit_load_half_negative_offset[];
+extern u32 bpf_jit_load_byte_negative_offset[];
+extern u32 bpf_jit_load_byte_msh_negative_offset[];
+
+#else
+#define r_RESULT	%o0
+#define r_SKB		%o0
+#define r_OFF		%o1
+#define r_HEADLEN	%l4
+#define r_SKB_DATA	%l5
+#define r_TMP		%g1
+#define r_TMP2		%g3
+#endif
+
+#endif /* _BPF_JIT_H */
diff --git a/arch/sparc/net/bpf_jit_asm.S b/arch/sparc/net/bpf_jit_asm_32.S
index 8c83f4b8eb15..dcc402f5738a 100644
--- a/arch/sparc/net/bpf_jit_asm.S
+++ b/arch/sparc/net/bpf_jit_asm_32.S
@@ -1,18 +1,11 @@
 #include <asm/ptrace.h>
 
-#include "bpf_jit.h"
+#include "bpf_jit_32.h"
 
-#ifdef CONFIG_SPARC64
-#define SAVE_SZ		176
-#define SCRATCH_OFF	STACK_BIAS + 128
-#define BE_PTR(label)	be,pn %xcc, label
-#define SIGN_EXTEND(reg)	sra reg, 0, reg
-#else
 #define SAVE_SZ		96
 #define SCRATCH_OFF	72
 #define BE_PTR(label)	be label
 #define SIGN_EXTEND(reg)
-#endif
 
 #define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
 
diff --git a/arch/sparc/net/bpf_jit_asm_64.S b/arch/sparc/net/bpf_jit_asm_64.S
new file mode 100644
index 000000000000..3b3f14655f81
--- /dev/null
+++ b/arch/sparc/net/bpf_jit_asm_64.S
@@ -0,0 +1,161 @@
+#include <asm/ptrace.h>
+
+#include "bpf_jit_64.h"
+
+#define SAVE_SZ		176
+#define SCRATCH_OFF	STACK_BIAS + 128
+#define BE_PTR(label)	be,pn %xcc, label
+#define SIGN_EXTEND(reg)	sra reg, 0, reg
+
+#define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
+
+	.text
+	.globl	bpf_jit_load_word
+bpf_jit_load_word:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_word_neg
+	 nop
+	.globl	bpf_jit_load_word_positive_offset
+bpf_jit_load_word_positive_offset:
+	sub	r_HEADLEN, r_OFF, r_TMP
+	cmp	r_TMP, 3
+	ble	bpf_slow_path_word
+	 add	r_SKB_DATA, r_OFF, r_TMP
+	andcc	r_TMP, 3, %g0
+	bne	load_word_unaligned
+	 nop
+	retl
+	 ld	[r_TMP], r_RESULT
+load_word_unaligned:
+	ldub	[r_TMP + 0x0], r_OFF
+	ldub	[r_TMP + 0x1], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	or	r_OFF, r_TMP2, r_OFF
+	ldub	[r_TMP + 0x2], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	or	r_OFF, r_TMP2, r_OFF
+	ldub	[r_TMP + 0x3], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	retl
+	 or	r_OFF, r_TMP2, r_RESULT
+
+	.globl	bpf_jit_load_half
+bpf_jit_load_half:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_half_neg
+	 nop
+	.globl	bpf_jit_load_half_positive_offset
+bpf_jit_load_half_positive_offset:
+	sub	r_HEADLEN, r_OFF, r_TMP
+	cmp	r_TMP, 1
+	ble	bpf_slow_path_half
+	 add	r_SKB_DATA, r_OFF, r_TMP
+	andcc	r_TMP, 1, %g0
+	bne	load_half_unaligned
+	 nop
+	retl
+	 lduh	[r_TMP], r_RESULT
+load_half_unaligned:
+	ldub	[r_TMP + 0x0], r_OFF
+	ldub	[r_TMP + 0x1], r_TMP2
+	sll	r_OFF, 8, r_OFF
+	retl
+	 or	r_OFF, r_TMP2, r_RESULT
+
+	.globl	bpf_jit_load_byte
+bpf_jit_load_byte:
+	cmp	r_OFF, 0
+	bl	bpf_slow_path_byte_neg
+	 nop
+	.globl	bpf_jit_load_byte_positive_offset
+bpf_jit_load_byte_positive_offset:
+	cmp	r_OFF, r_HEADLEN
+	bge	bpf_slow_path_byte
+	 nop
+	retl
+	 ldub	[r_SKB_DATA + r_OFF], r_RESULT
+
+#define bpf_slow_path_common(LEN)	\
+	save	%sp, -SAVE_SZ, %sp;	\
+	mov	%i0, %o0;		\
+	mov	%i1, %o1;		\
+	add	%fp, SCRATCH_OFF, %o2;	\
+	call	skb_copy_bits;		\
+	 mov	(LEN), %o3;		\
+	cmp	%o0, 0;			\
+	restore;
+
+bpf_slow_path_word:
+	bpf_slow_path_common(4)
+	bl	bpf_error
+	 ld	[%sp + SCRATCH_OFF], r_RESULT
+	retl
+	 nop
+bpf_slow_path_half:
+	bpf_slow_path_common(2)
+	bl	bpf_error
+	 lduh	[%sp + SCRATCH_OFF], r_RESULT
+	retl
+	 nop
+bpf_slow_path_byte:
+	bpf_slow_path_common(1)
+	bl	bpf_error
+	 ldub	[%sp + SCRATCH_OFF], r_RESULT
+	retl
+	 nop
+
+#define bpf_negative_common(LEN)			\
+	save	%sp, -SAVE_SZ, %sp;			\
+	mov	%i0, %o0;				\
+	mov	%i1, %o1;				\
+	SIGN_EXTEND(%o1);				\
+	call	bpf_internal_load_pointer_neg_helper;	\
+	 mov	(LEN), %o2;				\
+	mov	%o0, r_TMP;				\
+	cmp	%o0, 0;					\
+	BE_PTR(bpf_error);				\
+	 restore;
+
+bpf_slow_path_word_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_word_negative_offset
+bpf_jit_load_word_negative_offset:
+	bpf_negative_common(4)
+	andcc	r_TMP, 3, %g0
+	bne	load_word_unaligned
+	 nop
+	retl
+	 ld	[r_TMP], r_RESULT
+
+bpf_slow_path_half_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_half_negative_offset
+bpf_jit_load_half_negative_offset:
+	bpf_negative_common(2)
+	andcc	r_TMP, 1, %g0
+	bne	load_half_unaligned
+	 nop
+	retl
+	 lduh	[r_TMP], r_RESULT
+
+bpf_slow_path_byte_neg:
+	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
+	cmp	r_OFF, r_TMP
+	bl	bpf_error
+	 nop
+	.globl	bpf_jit_load_byte_negative_offset
+bpf_jit_load_byte_negative_offset:
+	bpf_negative_common(1)
+	retl
+	 ldub	[r_TMP], r_RESULT
+
+bpf_error:
+	/* Make the JIT program itself return zero. */
+	ret
+	restore	%g0, %g0, %o0
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp_32.c
index a6d9204a6a0b..d193748548e2 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -8,7 +8,7 @@
 #include <asm/cacheflush.h>
 #include <asm/ptrace.h>
 
-#include "bpf_jit.h"
+#include "bpf_jit_32.h"
 
 int bpf_jit_enable __read_mostly;
 
@@ -17,24 +17,6 @@ static inline bool is_simm13(unsigned int value)
 	return value + 0x1000 < 0x2000;
 }
 
-static void bpf_flush_icache(void *start_, void *end_)
-{
-#ifdef CONFIG_SPARC64
-	/* Cheetah's I-cache is fully coherent.  */
-	if (tlb_type == spitfire) {
-		unsigned long start = (unsigned long) start_;
-		unsigned long end = (unsigned long) end_;
-
-		start &= ~7UL;
-		end = (end + 7UL) & ~7UL;
-		while (start < end) {
-			flushi(start);
-			start += 32;
-		}
-	}
-#endif
-}
-
 #define SEEN_DATAREF 1 /* might call external helpers */
 #define SEEN_XREG    2 /* ebx is used */
 #define SEEN_MEM     4 /* use mem[] for temporary storage */
@@ -82,11 +64,7 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define BE		(F2(0, 2) | CONDE)
 #define BNE		(F2(0, 2) | CONDNE)
 
-#ifdef CONFIG_SPARC64
-#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
-#else
 #define BE_PTR		BE
-#endif
 
 #define SETHI(K, REG)	\
 	(F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff))
@@ -116,13 +94,8 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define LD64		F3(3, 0x0b)
 #define ST32		F3(3, 0x04)
 
-#ifdef CONFIG_SPARC64
-#define LDPTR		LD64
-#define BASE_STACKFRAME	176
-#else
 #define LDPTR		LD32
 #define BASE_STACKFRAME	96
-#endif
 
 #define LD32I		(LD32 | IMMED)
 #define LD8I		(LD8 | IMMED)
@@ -234,11 +207,7 @@ do {	BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u8));	\
 	__emit_load8(BASE, STRUCT, FIELD, DEST);			\
 } while (0)
 
-#ifdef CONFIG_SPARC64
-#define BIAS (STACK_BIAS - 4)
-#else
 #define BIAS (-4)
-#endif
 
 #define emit_ldmem(OFF, DEST)						\
 do {	*prog++ = LD32I | RS1(SP) | S13(BIAS - (OFF)) | RD(DEST);	\
@@ -249,13 +218,8 @@ do {	*prog++ = ST32I | RS1(SP) | S13(BIAS - (OFF)) | RD(SRC);	\
 } while (0)
 
 #ifdef CONFIG_SMP
-#ifdef CONFIG_SPARC64
-#define emit_load_cpu(REG)						\
-	emit_load16(G6, struct thread_info, cpu, REG)
-#else
 #define emit_load_cpu(REG)						\
 	emit_load32(G6, struct thread_info, cpu, REG)
-#endif
 #else
 #define emit_load_cpu(REG)	emit_clear(REG)
 #endif
@@ -486,7 +450,6 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				if (K == 1)
 					break;
 				emit_write_y(G0);
-#ifdef CONFIG_SPARC32
 				/* The Sparc v8 architecture requires
 				 * three instructions between a %y
 				 * register write and the first use.
@@ -494,31 +457,21 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				emit_nop();
 				emit_nop();
 				emit_nop();
-#endif
 				emit_alu_K(DIV, K);
 				break;
 			case BPF_ALU | BPF_DIV | BPF_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
 				if (pc_ret0 > 0) {
 					t_offset = addrs[pc_ret0 - 1];
-#ifdef CONFIG_SPARC32
 					emit_branch(BE, t_offset + 20);
-#else
-					emit_branch(BE, t_offset + 8);
-#endif
 					emit_nop(); /* delay slot */
 				} else {
 					emit_branch_off(BNE, 16);
 					emit_nop();
-#ifdef CONFIG_SPARC32
 					emit_jump(cleanup_addr + 20);
-#else
-					emit_jump(cleanup_addr + 8);
-#endif
 					emit_clear(r_A);
 				}
 				emit_write_y(G0);
-#ifdef CONFIG_SPARC32
 				/* The Sparc v8 architecture requires
 				 * three instructions between a %y
 				 * register write and the first use.
@@ -526,7 +479,6 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				emit_nop();
 				emit_nop();
 				emit_nop();
-#endif
 				emit_alu_X(DIV);
 				break;
 			case BPF_ALU | BPF_NEG:
@@ -797,7 +749,6 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 		bpf_jit_dump(flen, proglen, pass + 1, image);
 
 	if (image) {
-		bpf_flush_icache(image, image + proglen);
 		fp->bpf_func = (void *)image;
 		fp->jited = 1;
 	}
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
new file mode 100644
index 000000000000..21de77419f48
--- /dev/null
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -0,0 +1,1566 @@
+#include <linux/moduleloader.h>
+#include <linux/workqueue.h>
+#include <linux/netdevice.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/cache.h>
+#include <linux/if_vlan.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ptrace.h>
+
+#include "bpf_jit_64.h"
+
+int bpf_jit_enable __read_mostly;
+
+static inline bool is_simm13(unsigned int value)
+{
+	return value + 0x1000 < 0x2000;
+}
+
+static inline bool is_simm10(unsigned int value)
+{
+	return value + 0x200 < 0x400;
+}
+
+static inline bool is_simm5(unsigned int value)
+{
+	return value + 0x10 < 0x20;
+}
+
+static inline bool is_sethi(unsigned int value)
+{
+	return (value & ~0x3fffff) == 0;
+}
+
+static void bpf_flush_icache(void *start_, void *end_)
+{
+	/* Cheetah's I-cache is fully coherent.  */
+	if (tlb_type == spitfire) {
+		unsigned long start = (unsigned long) start_;
+		unsigned long end = (unsigned long) end_;
+
+		start &= ~7UL;
+		end = (end + 7UL) & ~7UL;
+		while (start < end) {
+			flushi(start);
+			start += 32;
+		}
+	}
+}
+
+#define SEEN_DATAREF 1 /* might call external helpers */
+#define SEEN_XREG    2 /* ebx is used */
+#define SEEN_MEM     4 /* use mem[] for temporary storage */
+
+#define S13(X)		((X) & 0x1fff)
+#define S5(X)		((X) & 0x1f)
+#define IMMED		0x00002000
+#define RD(X)		((X) << 25)
+#define RS1(X)		((X) << 14)
+#define RS2(X)		((X))
+#define OP(X)		((X) << 30)
+#define OP2(X)		((X) << 22)
+#define OP3(X)		((X) << 19)
+#define COND(X)		(((X) & 0xf) << 25)
+#define CBCOND(X)	(((X) & 0x1f) << 25)
+#define F1(X)		OP(X)
+#define F2(X, Y)	(OP(X) | OP2(Y))
+#define F3(X, Y)	(OP(X) | OP3(Y))
+#define ASI(X)		(((X) & 0xff) << 5)
+
+#define CONDN		COND(0x0)
+#define CONDE		COND(0x1)
+#define CONDLE		COND(0x2)
+#define CONDL		COND(0x3)
+#define CONDLEU		COND(0x4)
+#define CONDCS		COND(0x5)
+#define CONDNEG		COND(0x6)
+#define CONDVC		COND(0x7)
+#define CONDA		COND(0x8)
+#define CONDNE		COND(0x9)
+#define CONDG		COND(0xa)
+#define CONDGE		COND(0xb)
+#define CONDGU		COND(0xc)
+#define CONDCC		COND(0xd)
+#define CONDPOS		COND(0xe)
+#define CONDVS		COND(0xf)
+
+#define CONDGEU		CONDCC
+#define CONDLU		CONDCS
+
+#define WDISP22(X)	(((X) >> 2) & 0x3fffff)
+#define WDISP19(X)	(((X) >> 2) & 0x7ffff)
+
+/* The 10-bit branch displacement for CBCOND is split into two fields */
+static u32 WDISP10(u32 off)
+{
+	u32 ret = ((off >> 2) & 0xff) << 5;
+
+	ret |= ((off >> (2 + 8)) & 0x03) << 19;
+
+	return ret;
+}
+
+#define CBCONDE		CBCOND(0x09)
+#define CBCONDLE	CBCOND(0x0a)
+#define CBCONDL		CBCOND(0x0b)
+#define CBCONDLEU	CBCOND(0x0c)
+#define CBCONDCS	CBCOND(0x0d)
+#define CBCONDN		CBCOND(0x0e)
+#define CBCONDVS	CBCOND(0x0f)
+#define CBCONDNE	CBCOND(0x19)
+#define CBCONDG		CBCOND(0x1a)
+#define CBCONDGE	CBCOND(0x1b)
+#define CBCONDGU	CBCOND(0x1c)
+#define CBCONDCC	CBCOND(0x1d)
+#define CBCONDPOS	CBCOND(0x1e)
+#define CBCONDVC	CBCOND(0x1f)
+
+#define CBCONDGEU	CBCONDCC
+#define CBCONDLU	CBCONDCS
+
+#define ANNUL		(1 << 29)
+#define XCC		(1 << 21)
+
+#define BRANCH		(F2(0, 1) | XCC)
+#define CBCOND_OP	(F2(0, 3) | XCC)
+
+#define BA		(BRANCH | CONDA)
+#define BG		(BRANCH | CONDG)
+#define BGU		(BRANCH | CONDGU)
+#define BLEU		(BRANCH | CONDLEU)
+#define BGE		(BRANCH | CONDGE)
+#define BGEU		(BRANCH | CONDGEU)
+#define BLU		(BRANCH | CONDLU)
+#define BE		(BRANCH | CONDE)
+#define BNE		(BRANCH | CONDNE)
+
+#define SETHI(K, REG)	\
+	(F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff))
+#define OR_LO(K, REG)	\
+	(F3(2, 0x02) | IMMED | RS1(REG) | ((K) & 0x3ff) | RD(REG))
+
+#define ADD		F3(2, 0x00)
+#define AND		F3(2, 0x01)
+#define ANDCC		F3(2, 0x11)
+#define OR		F3(2, 0x02)
+#define XOR		F3(2, 0x03)
+#define SUB		F3(2, 0x04)
+#define SUBCC		F3(2, 0x14)
+#define MUL		F3(2, 0x0a)
+#define MULX		F3(2, 0x09)
+#define UDIVX		F3(2, 0x0d)
+#define DIV		F3(2, 0x0e)
+#define SLL		F3(2, 0x25)
+#define SLLX		(F3(2, 0x25)|(1<<12))
+#define SRA		F3(2, 0x27)
+#define SRAX		(F3(2, 0x27)|(1<<12))
+#define SRL		F3(2, 0x26)
+#define SRLX		(F3(2, 0x26)|(1<<12))
+#define JMPL		F3(2, 0x38)
+#define SAVE		F3(2, 0x3c)
+#define RESTORE		F3(2, 0x3d)
+#define CALL		F1(1)
+#define BR		F2(0, 0x01)
+#define RD_Y		F3(2, 0x28)
+#define WR_Y		F3(2, 0x30)
+
+#define LD32		F3(3, 0x00)
+#define LD8		F3(3, 0x01)
+#define LD16		F3(3, 0x02)
+#define LD64		F3(3, 0x0b)
+#define LD64A		F3(3, 0x1b)
+#define ST8		F3(3, 0x05)
+#define ST16		F3(3, 0x06)
+#define ST32		F3(3, 0x04)
+#define ST64		F3(3, 0x0e)
+
+#define CAS		F3(3, 0x3c)
+#define CASX		F3(3, 0x3e)
+
+#define LDPTR		LD64
+#define BASE_STACKFRAME	176
+
+#define LD32I		(LD32 | IMMED)
+#define LD8I		(LD8 | IMMED)
+#define LD16I		(LD16 | IMMED)
+#define LD64I		(LD64 | IMMED)
+#define LDPTRI		(LDPTR | IMMED)
+#define ST32I		(ST32 | IMMED)
+
+struct jit_ctx {
+	struct bpf_prog		*prog;
+	unsigned int		*offset;
+	int			idx;
+	int			epilogue_offset;
+	bool 			tmp_1_used;
+	bool 			tmp_2_used;
+	bool 			tmp_3_used;
+	bool			saw_ld_abs_ind;
+	bool			saw_frame_pointer;
+	bool			saw_call;
+	bool			saw_tail_call;
+	u32			*image;
+};
+
+#define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
+#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 2)
+#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 3)
+#define TMP_REG_3	(MAX_BPF_JIT_REG + 4)
+
+/* Map BPF registers to SPARC registers */
+static const int bpf2sparc[] = {
+	/* return value from in-kernel function, and exit value from eBPF */
+	[BPF_REG_0] = O5,
+
+	/* arguments from eBPF program to in-kernel function */
+	[BPF_REG_1] = O0,
+	[BPF_REG_2] = O1,
+	[BPF_REG_3] = O2,
+	[BPF_REG_4] = O3,
+	[BPF_REG_5] = O4,
+
+	/* callee saved registers that in-kernel function will preserve */
+	[BPF_REG_6] = L0,
+	[BPF_REG_7] = L1,
+	[BPF_REG_8] = L2,
+	[BPF_REG_9] = L3,
+
+	/* read-only frame pointer to access stack */
+	[BPF_REG_FP] = L6,
+
+	[BPF_REG_AX] = G7,
+
+	/* temporary register for internal BPF JIT */
+	[TMP_REG_1] = G1,
+	[TMP_REG_2] = G2,
+	[TMP_REG_3] = G3,
+
+	[SKB_HLEN_REG] = L4,
+	[SKB_DATA_REG] = L5,
+};
+
+static void emit(const u32 insn, struct jit_ctx *ctx)
+{
+	if (ctx->image != NULL)
+		ctx->image[ctx->idx] = insn;
+
+	ctx->idx++;
+}
+
+static void emit_call(u32 *func, struct jit_ctx *ctx)
+{
+	if (ctx->image != NULL) {
+		void *here = &ctx->image[ctx->idx];
+		unsigned int off;
+
+		off = (void *)func - here;
+		ctx->image[ctx->idx] = CALL | ((off >> 2) & 0x3fffffff);
+	}
+	ctx->idx++;
+}
+
+static void emit_nop(struct jit_ctx *ctx)
+{
+	emit(SETHI(0, G0), ctx);
+}
+
+static void emit_reg_move(u32 from, u32 to, struct jit_ctx *ctx)
+{
+	emit(OR | RS1(G0) | RS2(from) | RD(to), ctx);
+}
+
+/* Emit 32-bit constant, zero extended. */
+static void emit_set_const(s32 K, u32 reg, struct jit_ctx *ctx)
+{
+	emit(SETHI(K, reg), ctx);
+	emit(OR_LO(K, reg), ctx);
+}
+
+/* Emit 32-bit constant, sign extended. */
+static void emit_set_const_sext(s32 K, u32 reg, struct jit_ctx *ctx)
+{
+	if (K >= 0) {
+		emit(SETHI(K, reg), ctx);
+		emit(OR_LO(K, reg), ctx);
+	} else {
+		u32 hbits = ~(u32) K;
+		u32 lbits = -0x400 | (u32) K;
+
+		emit(SETHI(hbits, reg), ctx);
+		emit(XOR | IMMED | RS1(reg) | S13(lbits) | RD(reg), ctx);
+	}
+}
+
+static void emit_alu(u32 opcode, u32 src, u32 dst, struct jit_ctx *ctx)
+{
+	emit(opcode | RS1(dst) | RS2(src) | RD(dst), ctx);
+}
+
+static void emit_alu3(u32 opcode, u32 a, u32 b, u32 c, struct jit_ctx *ctx)
+{
+	emit(opcode | RS1(a) | RS2(b) | RD(c), ctx);
+}
+
+static void emit_alu_K(unsigned int opcode, unsigned int dst, unsigned int imm,
+		       struct jit_ctx *ctx)
+{
+	bool small_immed = is_simm13(imm);
+	unsigned int insn = opcode;
+
+	insn |= RS1(dst) | RD(dst);
+	if (small_immed) {
+		emit(insn | IMMED | S13(imm), ctx);
+	} else {
+		unsigned int tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_set_const_sext(imm, tmp, ctx);
+		emit(insn | RS2(tmp), ctx);
+	}
+}
+
+static void emit_alu3_K(unsigned int opcode, unsigned int src, unsigned int imm,
+			unsigned int dst, struct jit_ctx *ctx)
+{
+	bool small_immed = is_simm13(imm);
+	unsigned int insn = opcode;
+
+	insn |= RS1(src) | RD(dst);
+	if (small_immed) {
+		emit(insn | IMMED | S13(imm), ctx);
+	} else {
+		unsigned int tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_set_const_sext(imm, tmp, ctx);
+		emit(insn | RS2(tmp), ctx);
+	}
+}
+
+static void emit_loadimm32(s32 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	if (K >= 0 && is_simm13(K)) {
+		/* or %g0, K, DEST */
+		emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx);
+	} else {
+		emit_set_const(K, dest, ctx);
+	}
+}
+
+static void emit_loadimm(s32 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	if (is_simm13(K)) {
+		/* or %g0, K, DEST */
+		emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx);
+	} else {
+		emit_set_const(K, dest, ctx);
+	}
+}
+
+static void emit_loadimm_sext(s32 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	if (is_simm13(K)) {
+		/* or %g0, K, DEST */
+		emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx);
+	} else {
+		emit_set_const_sext(K, dest, ctx);
+	}
+}
+
+static void analyze_64bit_constant(u32 high_bits, u32 low_bits,
+				   int *hbsp, int *lbsp, int *abbasp)
+{
+	int lowest_bit_set, highest_bit_set, all_bits_between_are_set;
+	int i;
+
+	lowest_bit_set = highest_bit_set = -1;
+	i = 0;
+	do {
+		if ((lowest_bit_set == -1) && ((low_bits >> i) & 1))
+			lowest_bit_set = i;
+		if ((highest_bit_set == -1) && ((high_bits >> (32 - i - 1)) & 1))
+			highest_bit_set = (64 - i - 1);
+	}  while (++i < 32 && (highest_bit_set == -1 ||
+			       lowest_bit_set == -1));
+	if (i == 32) {
+		i = 0;
+		do {
+			if (lowest_bit_set == -1 && ((high_bits >> i) & 1))
+				lowest_bit_set = i + 32;
+			if (highest_bit_set == -1 &&
+			    ((low_bits >> (32 - i - 1)) & 1))
+				highest_bit_set = 32 - i - 1;
+		} while (++i < 32 && (highest_bit_set == -1 ||
+				      lowest_bit_set == -1));
+	}
+
+	all_bits_between_are_set = 1;
+	for (i = lowest_bit_set; i <= highest_bit_set; i++) {
+		if (i < 32) {
+			if ((low_bits & (1 << i)) != 0)
+				continue;
+		} else {
+			if ((high_bits & (1 << (i - 32))) != 0)
+				continue;
+		}
+		all_bits_between_are_set = 0;
+		break;
+	}
+	*hbsp = highest_bit_set;
+	*lbsp = lowest_bit_set;
+	*abbasp = all_bits_between_are_set;
+}
+
+static unsigned long create_simple_focus_bits(unsigned long high_bits,
+					      unsigned long low_bits,
+					      int lowest_bit_set, int shift)
+{
+	long hi, lo;
+
+	if (lowest_bit_set < 32) {
+		lo = (low_bits >> lowest_bit_set) << shift;
+		hi = ((high_bits << (32 - lowest_bit_set)) << shift);
+	} else {
+		lo = 0;
+		hi = ((high_bits >> (lowest_bit_set - 32)) << shift);
+	}
+	return hi | lo;
+}
+
+static bool const64_is_2insns(unsigned long high_bits,
+			      unsigned long low_bits)
+{
+	int highest_bit_set, lowest_bit_set, all_bits_between_are_set;
+
+	if (high_bits == 0 || high_bits == 0xffffffff)
+		return true;
+
+	analyze_64bit_constant(high_bits, low_bits,
+			       &highest_bit_set, &lowest_bit_set,
+			       &all_bits_between_are_set);
+
+	if ((highest_bit_set == 63 || lowest_bit_set == 0) &&
+	    all_bits_between_are_set != 0)
+		return true;
+
+	if (highest_bit_set - lowest_bit_set < 21)
+		return true;
+
+	return false;
+}
+
+static void sparc_emit_set_const64_quick2(unsigned long high_bits,
+					  unsigned long low_imm,
+					  unsigned int dest,
+					  int shift_count, struct jit_ctx *ctx)
+{
+	emit_loadimm32(high_bits, dest, ctx);
+
+	/* Now shift it up into place.  */
+	emit_alu_K(SLLX, dest, shift_count, ctx);
+
+	/* If there is a low immediate part piece, finish up by
+	 * putting that in as well.
+	 */
+	if (low_imm != 0)
+		emit(OR | IMMED | RS1(dest) | S13(low_imm) | RD(dest), ctx);
+}
+
+static void emit_loadimm64(u64 K, unsigned int dest, struct jit_ctx *ctx)
+{
+	int all_bits_between_are_set, lowest_bit_set, highest_bit_set;
+	unsigned int tmp = bpf2sparc[TMP_REG_1];
+	u32 low_bits = (K & 0xffffffff);
+	u32 high_bits = (K >> 32);
+
+	/* These two tests also take care of all of the one
+	 * instruction cases.
+	 */
+	if (high_bits == 0xffffffff && (low_bits & 0x80000000))
+		return emit_loadimm_sext(K, dest, ctx);
+	if (high_bits == 0x00000000)
+		return emit_loadimm32(K, dest, ctx);
+
+	analyze_64bit_constant(high_bits, low_bits, &highest_bit_set,
+			       &lowest_bit_set, &all_bits_between_are_set);
+
+	/* 1) mov	-1, %reg
+	 *    sllx	%reg, shift, %reg
+	 * 2) mov	-1, %reg
+	 *    srlx	%reg, shift, %reg
+	 * 3) mov	some_small_const, %reg
+	 *    sllx	%reg, shift, %reg
+	 */
+	if (((highest_bit_set == 63 || lowest_bit_set == 0) &&
+	     all_bits_between_are_set != 0) ||
+	    ((highest_bit_set - lowest_bit_set) < 12)) {
+		int shift = lowest_bit_set;
+		long the_const = -1;
+
+		if ((highest_bit_set != 63 && lowest_bit_set != 0) ||
+		    all_bits_between_are_set == 0) {
+			the_const =
+				create_simple_focus_bits(high_bits, low_bits,
+							 lowest_bit_set, 0);
+		} else if (lowest_bit_set == 0)
+			shift = -(63 - highest_bit_set);
+
+		emit(OR | IMMED | RS1(G0) | S13(the_const) | RD(dest), ctx);
+		if (shift > 0)
+			emit_alu_K(SLLX, dest, shift, ctx);
+		else if (shift < 0)
+			emit_alu_K(SRLX, dest, -shift, ctx);
+
+		return;
+	}
+
+	/* Now a range of 22 or less bits set somewhere.
+	 * 1) sethi	%hi(focus_bits), %reg
+	 *    sllx	%reg, shift, %reg
+	 * 2) sethi	%hi(focus_bits), %reg
+	 *    srlx	%reg, shift, %reg
+	 */
+	if ((highest_bit_set - lowest_bit_set) < 21) {
+		unsigned long focus_bits =
+			create_simple_focus_bits(high_bits, low_bits,
+						 lowest_bit_set, 10);
+
+		emit(SETHI(focus_bits, dest), ctx);
+
+		/* If lowest_bit_set == 10 then a sethi alone could
+		 * have done it.
+		 */
+		if (lowest_bit_set < 10)
+			emit_alu_K(SRLX, dest, 10 - lowest_bit_set, ctx);
+		else if (lowest_bit_set > 10)
+			emit_alu_K(SLLX, dest, lowest_bit_set - 10, ctx);
+		return;
+	}
+
+	/* Ok, now 3 instruction sequences.  */
+	if (low_bits == 0) {
+		emit_loadimm32(high_bits, dest, ctx);
+		emit_alu_K(SLLX, dest, 32, ctx);
+		return;
+	}
+
+	/* We may be able to do something quick
+	 * when the constant is negated, so try that.
+	 */
+	if (const64_is_2insns((~high_bits) & 0xffffffff,
+			      (~low_bits) & 0xfffffc00)) {
+		/* NOTE: The trailing bits get XOR'd so we need the
+		 * non-negated bits, not the negated ones.
+		 */
+		unsigned long trailing_bits = low_bits & 0x3ff;
+
+		if ((((~high_bits) & 0xffffffff) == 0 &&
+		     ((~low_bits) & 0x80000000) == 0) ||
+		    (((~high_bits) & 0xffffffff) == 0xffffffff &&
+		     ((~low_bits) & 0x80000000) != 0)) {
+			unsigned long fast_int = (~low_bits & 0xffffffff);
+
+			if ((is_sethi(fast_int) &&
+			     (~high_bits & 0xffffffff) == 0)) {
+				emit(SETHI(fast_int, dest), ctx);
+			} else if (is_simm13(fast_int)) {
+				emit(OR | IMMED | RS1(G0) | S13(fast_int) | RD(dest), ctx);
+			} else {
+				emit_loadimm64(fast_int, dest, ctx);
+			}
+		} else {
+			u64 n = ((~low_bits) & 0xfffffc00) |
+				(((unsigned long)((~high_bits) & 0xffffffff))<<32);
+			emit_loadimm64(n, dest, ctx);
+		}
+
+		low_bits = -0x400 | trailing_bits;
+
+		emit(XOR | IMMED | RS1(dest) | S13(low_bits) | RD(dest), ctx);
+		return;
+	}
+
+	/* 1) sethi	%hi(xxx), %reg
+	 *    or	%reg, %lo(xxx), %reg
+	 *    sllx	%reg, yyy, %reg
+	 */
+	if ((highest_bit_set - lowest_bit_set) < 32) {
+		unsigned long focus_bits =
+			create_simple_focus_bits(high_bits, low_bits,
+						 lowest_bit_set, 0);
+
+		/* So what we know is that the set bits straddle the
+		 * middle of the 64-bit word.
+		 */
+		sparc_emit_set_const64_quick2(focus_bits, 0, dest,
+					      lowest_bit_set, ctx);
+		return;
+	}
+
+	/* 1) sethi	%hi(high_bits), %reg
+	 *    or	%reg, %lo(high_bits), %reg
+	 *    sllx	%reg, 32, %reg
+	 *    or	%reg, low_bits, %reg
+	 */
+	if (is_simm13(low_bits) && ((int)low_bits > 0)) {
+		sparc_emit_set_const64_quick2(high_bits, low_bits,
+					      dest, 32, ctx);
+		return;
+	}
+
+	/* Oh well, we tried... Do a full 64-bit decomposition.  */
+	ctx->tmp_1_used = true;
+
+	emit_loadimm32(high_bits, tmp, ctx);
+	emit_loadimm32(low_bits, dest, ctx);
+	emit_alu_K(SLLX, tmp, 32, ctx);
+	emit(OR | RS1(dest) | RS2(tmp) | RD(dest), ctx);
+}
+
+static void emit_branch(unsigned int br_opc, unsigned int from_idx, unsigned int to_idx,
+			struct jit_ctx *ctx)
+{
+	unsigned int off = to_idx - from_idx;
+
+	if (br_opc & XCC)
+		emit(br_opc | WDISP19(off << 2), ctx);
+	else
+		emit(br_opc | WDISP22(off << 2), ctx);
+}
+
+static void emit_cbcond(unsigned int cb_opc, unsigned int from_idx, unsigned int to_idx,
+			const u8 dst, const u8 src, struct jit_ctx *ctx)
+{
+	unsigned int off = to_idx - from_idx;
+
+	emit(cb_opc | WDISP10(off << 2) | RS1(dst) | RS2(src), ctx);
+}
+
+static void emit_cbcondi(unsigned int cb_opc, unsigned int from_idx, unsigned int to_idx,
+			 const u8 dst, s32 imm, struct jit_ctx *ctx)
+{
+	unsigned int off = to_idx - from_idx;
+
+	emit(cb_opc | IMMED | WDISP10(off << 2) | RS1(dst) | S5(imm), ctx);
+}
+
+#define emit_read_y(REG, CTX)	emit(RD_Y | RD(REG), CTX)
+#define emit_write_y(REG, CTX)	emit(WR_Y | IMMED | RS1(REG) | S13(0), CTX)
+
+#define emit_cmp(R1, R2, CTX)				\
+	emit(SUBCC | RS1(R1) | RS2(R2) | RD(G0), CTX)
+
+#define emit_cmpi(R1, IMM, CTX)				\
+	emit(SUBCC | IMMED | RS1(R1) | S13(IMM) | RD(G0), CTX)
+
+#define emit_btst(R1, R2, CTX)				\
+	emit(ANDCC | RS1(R1) | RS2(R2) | RD(G0), CTX)
+
+#define emit_btsti(R1, IMM, CTX)			\
+	emit(ANDCC | IMMED | RS1(R1) | S13(IMM) | RD(G0), CTX)
+
+static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
+				   const s32 imm, bool is_imm, int branch_dst,
+				   struct jit_ctx *ctx)
+{
+	bool use_cbcond = (sparc64_elf_hwcap & AV_SPARC_CBCOND) != 0;
+	const u8 tmp = bpf2sparc[TMP_REG_1];
+
+	branch_dst = ctx->offset[branch_dst];
+
+	if (!is_simm10(branch_dst - ctx->idx) ||
+	    BPF_OP(code) == BPF_JSET)
+		use_cbcond = false;
+
+	if (is_imm) {
+		bool fits = true;
+
+		if (use_cbcond) {
+			if (!is_simm5(imm))
+				fits = false;
+		} else if (!is_simm13(imm)) {
+			fits = false;
+		}
+		if (!fits) {
+			ctx->tmp_1_used = true;
+			emit_loadimm_sext(imm, tmp, ctx);
+			src = tmp;
+			is_imm = false;
+		}
+	}
+
+	if (!use_cbcond) {
+		u32 br_opcode;
+
+		if (BPF_OP(code) == BPF_JSET) {
+			if (is_imm)
+				emit_btsti(dst, imm, ctx);
+			else
+				emit_btst(dst, src, ctx);
+		} else {
+			if (is_imm)
+				emit_cmpi(dst, imm, ctx);
+			else
+				emit_cmp(dst, src, ctx);
+		}
+		switch (BPF_OP(code)) {
+		case BPF_JEQ:
+			br_opcode = BE;
+			break;
+		case BPF_JGT:
+			br_opcode = BGU;
+			break;
+		case BPF_JGE:
+			br_opcode = BGEU;
+			break;
+		case BPF_JSET:
+		case BPF_JNE:
+			br_opcode = BNE;
+			break;
+		case BPF_JSGT:
+			br_opcode = BG;
+			break;
+		case BPF_JSGE:
+			br_opcode = BGE;
+			break;
+		default:
+			/* Make sure we dont leak kernel information to the
+			 * user.
+			 */
+			return -EFAULT;
+		}
+		emit_branch(br_opcode, ctx->idx, branch_dst, ctx);
+		emit_nop(ctx);
+	} else {
+		u32 cbcond_opcode;
+
+		switch (BPF_OP(code)) {
+		case BPF_JEQ:
+			cbcond_opcode = CBCONDE;
+			break;
+		case BPF_JGT:
+			cbcond_opcode = CBCONDGU;
+			break;
+		case BPF_JGE:
+			cbcond_opcode = CBCONDGEU;
+			break;
+		case BPF_JNE:
+			cbcond_opcode = CBCONDNE;
+			break;
+		case BPF_JSGT:
+			cbcond_opcode = CBCONDG;
+			break;
+		case BPF_JSGE:
+			cbcond_opcode = CBCONDGE;
+			break;
+		default:
+			/* Make sure we dont leak kernel information to the
+			 * user.
+			 */
+			return -EFAULT;
+		}
+		cbcond_opcode |= CBCOND_OP;
+		if (is_imm)
+			emit_cbcondi(cbcond_opcode, ctx->idx, branch_dst,
+				     dst, imm, ctx);
+		else
+			emit_cbcond(cbcond_opcode, ctx->idx, branch_dst,
+				    dst, src, ctx);
+	}
+	return 0;
+}
+
+static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb)
+{
+	const u8 r_headlen = bpf2sparc[SKB_HLEN_REG];
+	const u8 r_data = bpf2sparc[SKB_DATA_REG];
+	const u8 r_tmp = bpf2sparc[TMP_REG_1];
+	unsigned int off;
+
+	off = offsetof(struct sk_buff, len);
+	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx);
+
+	off = offsetof(struct sk_buff, data_len);
+	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx);
+
+	emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx);
+
+	off = offsetof(struct sk_buff, data);
+	emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx);
+}
+
+/* Just skip the save instruction and the ctx register move.  */
+#define BPF_TAILCALL_PROLOGUE_SKIP	16
+#define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	s32 stack_needed = BASE_STACKFRAME;
+
+	if (ctx->saw_frame_pointer || ctx->saw_tail_call)
+		stack_needed += MAX_BPF_STACK;
+
+	if (ctx->saw_tail_call)
+		stack_needed += 8;
+
+	/* save %sp, -176, %sp */
+	emit(SAVE | IMMED | RS1(SP) | S13(-stack_needed) | RD(SP), ctx);
+
+	/* tail_call_cnt = 0 */
+	if (ctx->saw_tail_call) {
+		u32 off = BPF_TAILCALL_CNT_SP_OFF;
+
+		emit(ST32 | IMMED | RS1(SP) | S13(off) | RD(G0), ctx);
+	} else {
+		emit_nop(ctx);
+	}
+	if (ctx->saw_frame_pointer) {
+		const u8 vfp = bpf2sparc[BPF_REG_FP];
+
+		emit(ADD | IMMED | RS1(FP) | S13(STACK_BIAS) | RD(vfp), ctx);
+	}
+
+	emit_reg_move(I0, O0, ctx);
+	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
+
+	if (ctx->saw_ld_abs_ind)
+		load_skb_regs(ctx, bpf2sparc[BPF_REG_1]);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	ctx->epilogue_offset = ctx->idx;
+
+	/* ret (jmpl %i7 + 8, %g0) */
+	emit(JMPL | IMMED | RS1(I7) | S13(8) | RD(G0), ctx);
+
+	/* restore %i5, %g0, %o0 */
+	emit(RESTORE | RS1(bpf2sparc[BPF_REG_0]) | RS2(G0) | RD(O0), ctx);
+}
+
+static void emit_tail_call(struct jit_ctx *ctx)
+{
+	const u8 bpf_array = bpf2sparc[BPF_REG_2];
+	const u8 bpf_index = bpf2sparc[BPF_REG_3];
+	const u8 tmp = bpf2sparc[TMP_REG_1];
+	u32 off;
+
+	ctx->saw_tail_call = true;
+
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit(LD32 | IMMED | RS1(bpf_array) | S13(off) | RD(tmp), ctx);
+	emit_cmp(bpf_index, tmp, ctx);
+#define OFFSET1 17
+	emit_branch(BGEU, ctx->idx, ctx->idx + OFFSET1, ctx);
+	emit_nop(ctx);
+
+	off = BPF_TAILCALL_CNT_SP_OFF;
+	emit(LD32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx);
+	emit_cmpi(tmp, MAX_TAIL_CALL_CNT, ctx);
+#define OFFSET2 13
+	emit_branch(BGU, ctx->idx, ctx->idx + OFFSET2, ctx);
+	emit_nop(ctx);
+
+	emit_alu_K(ADD, tmp, 1, ctx);
+	off = BPF_TAILCALL_CNT_SP_OFF;
+	emit(ST32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx);
+
+	emit_alu3_K(SLL, bpf_index, 3, tmp, ctx);
+	emit_alu(ADD, bpf_array, tmp, ctx);
+	off = offsetof(struct bpf_array, ptrs);
+	emit(LD64 | IMMED | RS1(tmp) | S13(off) | RD(tmp), ctx);
+
+	emit_cmpi(tmp, 0, ctx);
+#define OFFSET3 5
+	emit_branch(BE, ctx->idx, ctx->idx + OFFSET3, ctx);
+	emit_nop(ctx);
+
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit(LD64 | IMMED | RS1(tmp) | S13(off) | RD(tmp), ctx);
+
+	off = BPF_TAILCALL_PROLOGUE_SKIP;
+	emit(JMPL | IMMED | RS1(tmp) | S13(off) | RD(G0), ctx);
+	emit_nop(ctx);
+}
+
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const u8 code = insn->code;
+	const u8 dst = bpf2sparc[insn->dst_reg];
+	const u8 src = bpf2sparc[insn->src_reg];
+	const int i = insn - ctx->prog->insnsi;
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	u32 *func;
+
+	if (insn->src_reg == BPF_REG_FP)
+		ctx->saw_frame_pointer = true;
+
+	switch (code) {
+	/* dst = src */
+	case BPF_ALU | BPF_MOV | BPF_X:
+		emit_alu3_K(SRL, src, 0, dst, ctx);
+		break;
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		emit_reg_move(src, dst, ctx);
+		break;
+	/* dst = dst OP src */
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		emit_alu(ADD, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		emit_alu(SUB, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		emit_alu(AND, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		emit_alu(OR, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_XOR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		emit_alu(XOR, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_MUL | BPF_X:
+		emit_alu(MUL, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		emit_alu(MULX, src, dst, ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_X:
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_write_y(G0, ctx);
+		emit_alu(DIV, src, dst, ctx);
+		break;
+
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_alu(UDIVX, src, dst, ctx);
+		break;
+
+	case BPF_ALU | BPF_MOD | BPF_X: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_write_y(G0, ctx);
+		emit_alu3(DIV, dst, src, tmp, ctx);
+		emit_alu3(MULX, tmp, src, tmp, ctx);
+		emit_alu3(SUB, dst, tmp, dst, ctx);
+		goto do_alu32_trunc;
+	}
+	case BPF_ALU64 | BPF_MOD | BPF_X: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+
+		ctx->tmp_1_used = true;
+
+		emit_cmp(src, G0, ctx);
+		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
+
+		emit_alu3(UDIVX, dst, src, tmp, ctx);
+		emit_alu3(MULX, tmp, src, tmp, ctx);
+		emit_alu3(SUB, dst, tmp, dst, ctx);
+		break;
+	}
+	case BPF_ALU | BPF_LSH | BPF_X:
+		emit_alu(SLL, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+		emit_alu(SLLX, src, dst, ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_X:
+		emit_alu(SRL, src, dst, ctx);
+		break;
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+		emit_alu(SRLX, src, dst, ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_X:
+		emit_alu(SRA, src, dst, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		emit_alu(SRAX, src, dst, ctx);
+		break;
+
+	/* dst = -dst */
+	case BPF_ALU | BPF_NEG:
+	case BPF_ALU64 | BPF_NEG:
+		emit(SUB | RS1(0) | RS2(dst) | RD(dst), ctx);
+		goto do_alu32_trunc;
+
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+		switch (imm) {
+		case 16:
+			emit_alu_K(SLL, dst, 16, ctx);
+			emit_alu_K(SRL, dst, 16, ctx);
+			break;
+		case 32:
+			emit_alu_K(SRL, dst, 0, ctx);
+			break;
+		case 64:
+			/* nop */
+			break;
+
+		}
+		break;
+
+	/* dst = BSWAP##imm(dst) */
+	case BPF_ALU | BPF_END | BPF_FROM_LE: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+
+		ctx->tmp_1_used = true;
+		switch (imm) {
+		case 16:
+			emit_alu3_K(AND, dst, 0xff, tmp, ctx);
+			emit_alu3_K(SRL, dst, 8, dst, ctx);
+			emit_alu3_K(AND, dst, 0xff, dst, ctx);
+			emit_alu3_K(SLL, tmp, 8, tmp, ctx);
+			emit_alu(OR, tmp, dst, ctx);
+			break;
+
+		case 32:
+			ctx->tmp_2_used = true;
+			emit_alu3_K(SRL, dst, 24, tmp, ctx);	/* tmp  = dst >> 24 */
+			emit_alu3_K(SRL, dst, 16, tmp2, ctx);	/* tmp2 = dst >> 16 */
+			emit_alu3_K(AND, tmp2, 0xff, tmp2, ctx);/* tmp2 = tmp2 & 0xff */
+			emit_alu3_K(SLL, tmp2, 8, tmp2, ctx);	/* tmp2 = tmp2 << 8 */
+			emit_alu(OR, tmp2, tmp, ctx);		/* tmp  = tmp | tmp2 */
+			emit_alu3_K(SRL, dst, 8, tmp2, ctx);	/* tmp2 = dst >> 8 */
+			emit_alu3_K(AND, tmp2, 0xff, tmp2, ctx);/* tmp2 = tmp2 & 0xff */
+			emit_alu3_K(SLL, tmp2, 16, tmp2, ctx);	/* tmp2 = tmp2 << 16 */
+			emit_alu(OR, tmp2, tmp, ctx);		/* tmp  = tmp | tmp2 */
+			emit_alu3_K(AND, dst, 0xff, dst, ctx);	/* dst	= dst & 0xff */
+			emit_alu3_K(SLL, dst, 24, dst, ctx);	/* dst  = dst << 24 */
+			emit_alu(OR, tmp, dst, ctx);		/* dst  = dst | tmp */
+			break;
+
+		case 64:
+			emit_alu3_K(ADD, SP, STACK_BIAS + 128, tmp, ctx);
+			emit(ST64 | RS1(tmp) | RS2(G0) | RD(dst), ctx);
+			emit(LD64A | ASI(ASI_PL) | RS1(tmp) | RS2(G0) | RD(dst), ctx);
+			break;
+		}
+		break;
+	}
+	/* dst = imm */
+	case BPF_ALU | BPF_MOV | BPF_K:
+		emit_loadimm32(imm, dst, ctx);
+		break;
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		emit_loadimm_sext(imm, dst, ctx);
+		break;
+	/* dst = dst OP imm */
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		emit_alu_K(ADD, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		emit_alu_K(SUB, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		emit_alu_K(AND, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		emit_alu_K(OR, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		emit_alu_K(XOR, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU | BPF_MUL | BPF_K:
+		emit_alu_K(MUL, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		emit_alu_K(MULX, dst, imm, ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_K:
+		if (imm == 0)
+			return -EINVAL;
+
+		emit_write_y(G0, ctx);
+		emit_alu_K(DIV, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+		if (imm == 0)
+			return -EINVAL;
+
+		emit_alu_K(UDIVX, dst, imm, ctx);
+		break;
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+	case BPF_ALU | BPF_MOD | BPF_K: {
+		const u8 tmp = bpf2sparc[TMP_REG_2];
+		unsigned int div;
+
+		if (imm == 0)
+			return -EINVAL;
+
+		div = (BPF_CLASS(code) == BPF_ALU64) ? UDIVX : DIV;
+
+		ctx->tmp_2_used = true;
+
+		if (BPF_CLASS(code) != BPF_ALU64)
+			emit_write_y(G0, ctx);
+		if (is_simm13(imm)) {
+			emit(div | IMMED | RS1(dst) | S13(imm) | RD(tmp), ctx);
+			emit(MULX | IMMED | RS1(tmp) | S13(imm) | RD(tmp), ctx);
+			emit(SUB | RS1(dst) | RS2(tmp) | RD(dst), ctx);
+		} else {
+			const u8 tmp1 = bpf2sparc[TMP_REG_1];
+
+			ctx->tmp_1_used = true;
+
+			emit_set_const_sext(imm, tmp1, ctx);
+			emit(div | RS1(dst) | RS2(tmp1) | RD(tmp), ctx);
+			emit(MULX | RS1(tmp) | RS2(tmp1) | RD(tmp), ctx);
+			emit(SUB | RS1(dst) | RS2(tmp) | RD(dst), ctx);
+		}
+		goto do_alu32_trunc;
+	}
+	case BPF_ALU | BPF_LSH | BPF_K:
+		emit_alu_K(SLL, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		emit_alu_K(SLLX, dst, imm, ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_K:
+		emit_alu_K(SRL, dst, imm, ctx);
+		break;
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		emit_alu_K(SRLX, dst, imm, ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_K:
+		emit_alu_K(SRA, dst, imm, ctx);
+		goto do_alu32_trunc;
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		emit_alu_K(SRAX, dst, imm, ctx);
+		break;
+
+	do_alu32_trunc:
+		if (BPF_CLASS(code) == BPF_ALU)
+			emit_alu_K(SRL, dst, 0, ctx);
+		break;
+
+	/* JUMP off */
+	case BPF_JMP | BPF_JA:
+		emit_branch(BA, ctx->idx, ctx->offset[i + off], ctx);
+		emit_nop(ctx);
+		break;
+	/* IF (dst COND src) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JSET | BPF_X: {
+		int err;
+
+		err = emit_compare_and_branch(code, dst, src, 0, false, i + off, ctx);
+		if (err)
+			return err;
+		break;
+	}
+	/* IF (dst COND imm) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP | BPF_JSET | BPF_K: {
+		int err;
+
+		err = emit_compare_and_branch(code, dst, 0, imm, true, i + off, ctx);
+		if (err)
+			return err;
+		break;
+	}
+
+	/* function call */
+	case BPF_JMP | BPF_CALL:
+	{
+		u8 *func = ((u8 *)__bpf_call_base) + imm;
+
+		ctx->saw_call = true;
+
+		emit_call((u32 *)func, ctx);
+		emit_nop(ctx);
+
+		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
+
+		if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind)
+			load_skb_regs(ctx, bpf2sparc[BPF_REG_6]);
+		break;
+	}
+
+	/* tail call */
+	case BPF_JMP | BPF_CALL |BPF_X:
+		emit_tail_call(ctx);
+		break;
+
+	/* function return */
+	case BPF_JMP | BPF_EXIT:
+		/* Optimization: when last instruction is EXIT,
+		   simply fallthrough to epilogue. */
+		if (i == ctx->prog->len - 1)
+			break;
+		emit_branch(BA, ctx->idx, ctx->epilogue_offset, ctx);
+		emit_nop(ctx);
+		break;
+
+	/* dst = imm64 */
+	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		const struct bpf_insn insn1 = insn[1];
+		u64 imm64;
+
+		imm64 = (u64)insn1.imm << 32 | (u32)imm;
+		emit_loadimm64(imm64, dst, ctx);
+
+		return 1;
+	}
+
+	/* LDX: dst = *(size *)(src + off) */
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		u32 opcode = 0, rs2;
+
+		ctx->tmp_1_used = true;
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			opcode = LD32;
+			break;
+		case BPF_H:
+			opcode = LD16;
+			break;
+		case BPF_B:
+			opcode = LD8;
+			break;
+		case BPF_DW:
+			opcode = LD64;
+			break;
+		}
+
+		if (is_simm13(off)) {
+			opcode |= IMMED;
+			rs2 = S13(off);
+		} else {
+			emit_loadimm(off, tmp, ctx);
+			rs2 = RS2(tmp);
+		}
+		emit(opcode | RS1(src) | rs2 | RD(dst), ctx);
+		break;
+	}
+	/* ST: *(size *)(dst + off) = imm */
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_B:
+	case BPF_ST | BPF_MEM | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+		u32 opcode = 0, rs2;
+
+		ctx->tmp_2_used = true;
+		emit_loadimm(imm, tmp2, ctx);
+
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			opcode = ST32;
+			break;
+		case BPF_H:
+			opcode = ST16;
+			break;
+		case BPF_B:
+			opcode = ST8;
+			break;
+		case BPF_DW:
+			opcode = ST64;
+			break;
+		}
+
+		if (is_simm13(off)) {
+			opcode |= IMMED;
+			rs2 = S13(off);
+		} else {
+			ctx->tmp_1_used = true;
+			emit_loadimm(off, tmp, ctx);
+			rs2 = RS2(tmp);
+		}
+		emit(opcode | RS1(dst) | rs2 | RD(tmp2), ctx);
+		break;
+	}
+
+	/* STX: *(size *)(dst + off) = src */
+	case BPF_STX | BPF_MEM | BPF_W:
+	case BPF_STX | BPF_MEM | BPF_H:
+	case BPF_STX | BPF_MEM | BPF_B:
+	case BPF_STX | BPF_MEM | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		u32 opcode = 0, rs2;
+
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			opcode = ST32;
+			break;
+		case BPF_H:
+			opcode = ST16;
+			break;
+		case BPF_B:
+			opcode = ST8;
+			break;
+		case BPF_DW:
+			opcode = ST64;
+			break;
+		}
+		if (is_simm13(off)) {
+			opcode |= IMMED;
+			rs2 = S13(off);
+		} else {
+			ctx->tmp_1_used = true;
+			emit_loadimm(off, tmp, ctx);
+			rs2 = RS2(tmp);
+		}
+		emit(opcode | RS1(dst) | rs2 | RD(src), ctx);
+		break;
+	}
+
+	/* STX XADD: lock *(u32 *)(dst + off) += src */
+	case BPF_STX | BPF_XADD | BPF_W: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+		const u8 tmp3 = bpf2sparc[TMP_REG_3];
+
+		ctx->tmp_1_used = true;
+		ctx->tmp_2_used = true;
+		ctx->tmp_3_used = true;
+		emit_loadimm(off, tmp, ctx);
+		emit_alu3(ADD, dst, tmp, tmp, ctx);
+
+		emit(LD32 | RS1(tmp) | RS2(G0) | RD(tmp2), ctx);
+		emit_alu3(ADD, tmp2, src, tmp3, ctx);
+		emit(CAS | ASI(ASI_P) | RS1(tmp) | RS2(tmp2) | RD(tmp3), ctx);
+		emit_cmp(tmp2, tmp3, ctx);
+		emit_branch(BNE, 4, 0, ctx);
+		emit_nop(ctx);
+		break;
+	}
+	/* STX XADD: lock *(u64 *)(dst + off) += src */
+	case BPF_STX | BPF_XADD | BPF_DW: {
+		const u8 tmp = bpf2sparc[TMP_REG_1];
+		const u8 tmp2 = bpf2sparc[TMP_REG_2];
+		const u8 tmp3 = bpf2sparc[TMP_REG_3];
+
+		ctx->tmp_1_used = true;
+		ctx->tmp_2_used = true;
+		ctx->tmp_3_used = true;
+		emit_loadimm(off, tmp, ctx);
+		emit_alu3(ADD, dst, tmp, tmp, ctx);
+
+		emit(LD64 | RS1(tmp) | RS2(G0) | RD(tmp2), ctx);
+		emit_alu3(ADD, tmp2, src, tmp3, ctx);
+		emit(CASX | ASI(ASI_P) | RS1(tmp) | RS2(tmp2) | RD(tmp3), ctx);
+		emit_cmp(tmp2, tmp3, ctx);
+		emit_branch(BNE, 4, 0, ctx);
+		emit_nop(ctx);
+		break;
+	}
+#define CHOOSE_LOAD_FUNC(K, func) \
+		((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
+
+	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
+	case BPF_LD | BPF_ABS | BPF_W:
+		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word);
+		goto common_load;
+	case BPF_LD | BPF_ABS | BPF_H:
+		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half);
+		goto common_load;
+	case BPF_LD | BPF_ABS | BPF_B:
+		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte);
+		goto common_load;
+	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
+	case BPF_LD | BPF_IND | BPF_W:
+		func = bpf_jit_load_word;
+		goto common_load;
+	case BPF_LD | BPF_IND | BPF_H:
+		func = bpf_jit_load_half;
+		goto common_load;
+
+	case BPF_LD | BPF_IND | BPF_B:
+		func = bpf_jit_load_byte;
+	common_load:
+		ctx->saw_ld_abs_ind = true;
+
+		emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx);
+		emit_loadimm(imm, O1, ctx);
+
+		if (BPF_MODE(code) == BPF_IND)
+			emit_alu(ADD, src, O1, ctx);
+
+		emit_call(func, ctx);
+		emit_alu_K(SRA, O1, 0, ctx);
+
+		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
+		break;
+
+	default:
+		pr_err_once("unknown opcode %02x\n", code);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	const struct bpf_prog *prog = ctx->prog;
+	int i;
+
+	for (i = 0; i < prog->len; i++) {
+		const struct bpf_insn *insn = &prog->insnsi[i];
+		int ret;
+
+		ret = build_insn(insn, ctx);
+
+		if (ret > 0) {
+			i++;
+			ctx->offset[i] = ctx->idx;
+			continue;
+		}
+		ctx->offset[i] = ctx->idx;
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	u32 *ptr;
+	/* We are guaranteed to have aligned memory. */
+	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
+		*ptr++ = 0x91d02005; /* ta 5 */
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	struct bpf_prog *tmp, *orig_prog = prog;
+	struct bpf_binary_header *header;
+	bool tmp_blinded = false;
+	struct jit_ctx ctx;
+	u32 image_size;
+	u8 *image_ptr;
+	int pass;
+
+	if (!bpf_jit_enable)
+		return orig_prog;
+
+	tmp = bpf_jit_blind_constants(prog);
+	/* If blinding was requested and we failed during blinding,
+	 * we must fall back to the interpreter.
+	 */
+	if (IS_ERR(tmp))
+		return orig_prog;
+	if (tmp != prog) {
+		tmp_blinded = true;
+		prog = tmp;
+	}
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.prog = prog;
+
+	ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL);
+	if (ctx.offset == NULL) {
+		prog = orig_prog;
+		goto out;
+	}
+
+	/* Fake pass to detect features used, and get an accurate assessment
+	 * of what the final image size will be.
+	 */
+	if (build_body(&ctx)) {
+		prog = orig_prog;
+		goto out_off;
+	}
+	build_prologue(&ctx);
+	build_epilogue(&ctx);
+
+	/* Now we know the actual image size. */
+	image_size = sizeof(u32) * ctx.idx;
+	header = bpf_jit_binary_alloc(image_size, &image_ptr,
+				      sizeof(u32), jit_fill_hole);
+	if (header == NULL) {
+		prog = orig_prog;
+		goto out_off;
+	}
+
+	ctx.image = (u32 *)image_ptr;
+
+	for (pass = 1; pass < 3; pass++) {
+		ctx.idx = 0;
+
+		build_prologue(&ctx);
+
+		if (build_body(&ctx)) {
+			bpf_jit_binary_free(header);
+			prog = orig_prog;
+			goto out_off;
+		}
+
+		build_epilogue(&ctx);
+
+		if (bpf_jit_enable > 1)
+			pr_info("Pass %d: shrink = %d, seen = [%c%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_ld_abs_ind ? 'L' : ' ',
+				ctx.saw_frame_pointer ? 'F' : ' ',
+				ctx.saw_call ? 'C' : ' ',
+				ctx.saw_tail_call ? 'T' : ' ');
+	}
+
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(prog->len, image_size, pass, ctx.image);
+
+	bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE));
+
+	bpf_jit_binary_lock_ro(header);
+
+	prog->bpf_func = (void *)ctx.image;
+	prog->jited = 1;
+
+out_off:
+	kfree(ctx.offset);
+out:
+	if (tmp_blinded)
+		bpf_jit_prog_release_other(prog, prog == orig_prog ?
+					   tmp : orig_prog);
+	return prog;
+}