bpf, s390x: remove ld_abs/ld_ind

Since LD_ABS/LD_IND instructions are now removed from the core and
reimplemented through a combination of inlined BPF instructions and
a slow-path helper, we can get rid of the complexity from s390x JIT.
Tested on s390x instance on LinuxONE.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/s390/net/Makefile

@@ -2,4 +2,4 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o

arch/s390/net/bpf_jit.S

-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * BPF Jit compiler for s390, help functions.
- *
- * Copyright IBM Corp. 2012,2015
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
- */
-
-#include <linux/linkage.h>
-#include "bpf_jit.h"
-
-/*
- * Calling convention:
- * registers %r7-%r10, %r11,%r13, and %r15 are call saved
- *
- * Input (64 bit):
- *   %r3 (%b2) = offset into skb data
- *   %r6 (%b5) = return address
- *   %r7 (%b6) = skb pointer
- *   %r12      = skb data pointer
- *
- * Output:
- *   %r14= %b0 = return value (read skb value)
- *
- * Work registers: %r2,%r4,%r5,%r14
- *
- * skb_copy_bits takes 4 parameters:
- *   %r2 = skb pointer
- *   %r3 = offset into skb data
- *   %r4 = pointer to temp buffer
- *   %r5 = length to copy
- *   Return value in %r2: 0 = ok
- *
- * bpf_internal_load_pointer_neg_helper takes 3 parameters:
- *   %r2 = skb pointer
- *   %r3 = offset into data
- *   %r4 = length to copy
- *   Return value in %r2: Pointer to data
- */
-
-#define SKF_MAX_NEG_OFF	-0x200000	/* SKF_LL_OFF from filter.h */
-
-/*
- * Load SIZE bytes from SKB
- */
-#define sk_load_common(NAME, SIZE, LOAD)				\
-ENTRY(sk_load_##NAME);							\
-	ltgr	%r3,%r3;		/* Is offset negative? */	\
-	jl	sk_load_##NAME##_slow_neg;				\
-ENTRY(sk_load_##NAME##_pos);						\
-	aghi	%r3,SIZE;		/* Offset + SIZE */		\
-	clg	%r3,STK_OFF_HLEN(%r15);	/* Offset + SIZE > hlen? */	\
-	jh	sk_load_##NAME##_slow;					\
-	LOAD	%r14,-SIZE(%r3,%r12);	/* Get data from skb */		\
-	b	OFF_OK(%r6);		/* Return */			\
-									\
-sk_load_##NAME##_slow:;							\
-	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
-	aghi	%r3,-SIZE;		/* Arg2 = offset */		\
-	la	%r4,STK_OFF_TMP(%r15);	/* Arg3 = temp bufffer */	\
-	lghi	%r5,SIZE;		/* Arg4 = size */		\
-	brasl	%r14,skb_copy_bits;	/* Get data from skb */		\
-	LOAD	%r14,STK_OFF_TMP(%r15);	/* Load from temp bufffer */	\
-	ltgr	%r2,%r2;		/* Set cc to (%r2 != 0) */	\
-	br	%r6;			/* Return */
-
-sk_load_common(word, 4, llgf)	/* r14 = *(u32 *) (skb->data+offset) */
-sk_load_common(half, 2, llgh)	/* r14 = *(u16 *) (skb->data+offset) */
-
-/*
- * Load 1 byte from SKB (optimized version)
- */
-	/* r14 = *(u8 *) (skb->data+offset) */
-ENTRY(sk_load_byte)
-	ltgr	%r3,%r3			# Is offset negative?
-	jl	sk_load_byte_slow_neg
-ENTRY(sk_load_byte_pos)
-	clg	%r3,STK_OFF_HLEN(%r15)	# Offset >= hlen?
-	jnl	sk_load_byte_slow
-	llgc	%r14,0(%r3,%r12)	# Get byte from skb
-	b	OFF_OK(%r6)		# Return OK
-
-sk_load_byte_slow:
-	lgr	%r2,%r7			# Arg1 = skb pointer
-					# Arg2 = offset
-	la	%r4,STK_OFF_TMP(%r15)	# Arg3 = pointer to temp buffer
-	lghi	%r5,1			# Arg4 = size (1 byte)
-	brasl	%r14,skb_copy_bits	# Get data from skb
-	llgc	%r14,STK_OFF_TMP(%r15)	# Load result from temp buffer
-	ltgr	%r2,%r2			# Set cc to (%r2 != 0)
-	br	%r6			# Return cc
-
-#define sk_negative_common(NAME, SIZE, LOAD)				\
-sk_load_##NAME##_slow_neg:;						\
-	cgfi	%r3,SKF_MAX_NEG_OFF;					\
-	jl	bpf_error;						\
-	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
-					/* Arg2 = offset */		\
-	lghi	%r4,SIZE;		/* Arg3 = size */		\
-	brasl	%r14,bpf_internal_load_pointer_neg_helper;		\
-	ltgr	%r2,%r2;						\
-	jz	bpf_error;						\
-	LOAD	%r14,0(%r2);		/* Get data from pointer */	\
-	xr	%r3,%r3;		/* Set cc to zero */		\
-	br	%r6;			/* Return cc */
-
-sk_negative_common(word, 4, llgf)
-sk_negative_common(half, 2, llgh)
-sk_negative_common(byte, 1, llgc)
-
-bpf_error:
-# force a return 0 from jit handler
-	ltgr	%r15,%r15	# Set condition code
-	br	%r6

arch/s390/net/bpf_jit.h

@@ -16,9 +16,6 @@
 #include <linux/filter.h>
 #include <linux/types.h>
 
-extern u8 sk_load_word_pos[], sk_load_half_pos[], sk_load_byte_pos[];
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-
 #endif /* __ASSEMBLY__ */
 
 /*
@@ -36,15 +33,6 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |		      |     |
  *	      |   BPF stack   |     |
  *	      |		      |     |
- *	      +---------------+     |
- *	      | 8 byte skbp   |     |
- * R15+176 -> +---------------+     |
- *	      | 8 byte hlen   |     |
- * R15+168 -> +---------------+     |
- *	      | 4 byte align  |     |
- *	      +---------------+     |
- *	      | 4 byte temp   |     |
- *	      | for bpf_jit.S |     |
  * R15+160 -> +---------------+     |
  *	      | new backchain |     |
  * R15+152 -> +---------------+     |
@@ -57,17 +45,11 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * The stack size used by the BPF program ("BPF stack" above) is passed
  * via "aux->stack_depth".
  */
-#define STK_SPACE_ADD (8 + 8 + 4 + 4 + 160)
+#define STK_SPACE_ADD	(160)
 #define STK_160_UNUSED	(160 - 12 * 8)
 #define STK_OFF		(STK_SPACE_ADD - STK_160_UNUSED)
-#define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
-#define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
-#define STK_OFF_SKBP	176	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
 
-/* Offset to skip condition code check */
-#define OFF_OK		4
-
 #endif /* __ARCH_S390_NET_BPF_JIT_H */

arch/s390/net/bpf_jit_comp.c

@@ -47,23 +47,21 @@ struct bpf_jit {
 
 #define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
 
-#define SEEN_SKB	1	/* skb access */
-#define SEEN_MEM	2	/* use mem[] for temporary storage */
-#define SEEN_RET0	4	/* ret0_ip points to a valid return 0 */
-#define SEEN_LITERAL	8	/* code uses literals */
-#define SEEN_FUNC	16	/* calls C functions */
-#define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_REG_AX	64	/* code uses constant blinding */
-#define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
+#define SEEN_MEM	(1 << 0)	/* use mem[] for temporary storage */
+#define SEEN_RET0	(1 << 1)	/* ret0_ip points to a valid return 0 */
+#define SEEN_LITERAL	(1 << 2)	/* code uses literals */
+#define SEEN_FUNC	(1 << 3)	/* calls C functions */
+#define SEEN_TAIL_CALL	(1 << 4)	/* code uses tail calls */
+#define SEEN_REG_AX	(1 << 5)	/* code uses constant blinding */
+#define SEEN_STACK	(SEEN_FUNC | SEEN_MEM)
 
 /*
  * s390 registers
  */
 #define REG_W0		(MAX_BPF_JIT_REG + 0)	/* Work register 1 (even) */
 #define REG_W1		(MAX_BPF_JIT_REG + 1)	/* Work register 2 (odd) */
-#define REG_SKB_DATA	(MAX_BPF_JIT_REG + 2)	/* SKB data register */
-#define REG_L		(MAX_BPF_JIT_REG + 3)	/* Literal pool register */
-#define REG_15		(MAX_BPF_JIT_REG + 4)	/* Register 15 */
+#define REG_L		(MAX_BPF_JIT_REG + 2)	/* Literal pool register */
+#define REG_15		(MAX_BPF_JIT_REG + 3)	/* Register 15 */
 #define REG_0		REG_W0			/* Register 0 */
 #define REG_1		REG_W1			/* Register 1 */
 #define REG_2		BPF_REG_1		/* Register 2 */
@@ -88,10 +86,8 @@ static const int reg2hex[] = {
 	[BPF_REG_9]	= 10,
 	/* BPF stack pointer */
 	[BPF_REG_FP]	= 13,
-	/* Register for blinding (shared with REG_SKB_DATA) */
+	/* Register for blinding */
 	[BPF_REG_AX]	= 12,
-	/* SKB data pointer */
-	[REG_SKB_DATA]	= 12,
 	/* Work registers for s390x backend */
 	[REG_W0]	= 0,
 	[REG_W1]	= 1,
@@ -384,27 +380,6 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 	} while (re <= 15);
 }
 
-/*
- * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
- * we store the SKB header length on the stack and the SKB data
- * pointer in REG_SKB_DATA if BPF_REG_AX is not used.
- */
-static void emit_load_skb_data_hlen(struct bpf_jit *jit)
-{
-	/* Header length: llgf %w1,<len>(%b1) */
-	EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
-		      offsetof(struct sk_buff, len));
-	/* s %w1,<data_len>(%b1) */
-	EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
-		   offsetof(struct sk_buff, data_len));
-	/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
-	EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
-	if (!(jit->seen & SEEN_REG_AX))
-		/* lg %skb_data,data_off(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-			      BPF_REG_1, offsetof(struct sk_buff, data));
-}
-
 /*
  * Emit function prologue
  *
@@ -445,12 +420,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB) {
-		emit_load_skb_data_hlen(jit);
-		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
-		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
-			      STK_OFF_SKBP);
-	}
 }
 
 /*
@@ -483,12 +452,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
 	int jmp_off, last, insn_count = 1;
-	unsigned int func_addr, mask;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
 	u32 *addrs = jit->addrs;
 	s32 imm = insn->imm;
 	s16 off = insn->off;
+	unsigned int mask;
 
 	if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
 		jit->seen |= SEEN_REG_AX;
@@ -970,13 +939,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if ((jit->seen & SEEN_SKB) &&
-		    bpf_helper_changes_pkt_data((void *)func)) {
-			/* lg %b1,ST_OFF_SKBP(%r15) */
-			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
-				      REG_15, STK_OFF_SKBP);
-			emit_load_skb_data_hlen(jit);
-		}
 		break;
 	}
 	case BPF_JMP | BPF_TAIL_CALL:
@@ -1176,73 +1138,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
 		EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
 		break;
-	/*
-	 * BPF_LD
-	 */
-	case BPF_LD | BPF_ABS | BPF_B: /* b0 = *(u8 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_B: /* b0 = *(u8 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_byte_pos);
-		else
-			func_addr = __pa(sk_load_byte);
-		goto call_fn;
-	case BPF_LD | BPF_ABS | BPF_H: /* b0 = *(u16 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_H: /* b0 = *(u16 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_half_pos);
-		else
-			func_addr = __pa(sk_load_half);
-		goto call_fn;
-	case BPF_LD | BPF_ABS | BPF_W: /* b0 = *(u32 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_W: /* b0 = *(u32 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_word_pos);
-		else
-			func_addr = __pa(sk_load_word);
-		goto call_fn;
-call_fn:
-		jit->seen |= SEEN_SKB | SEEN_RET0 | SEEN_FUNC;
-		REG_SET_SEEN(REG_14); /* Return address of possible func call */
-
-		/*
-		 * Implicit input:
-		 *  BPF_REG_6	 (R7) : skb pointer
-		 *  REG_SKB_DATA (R12): skb data pointer (if no BPF_REG_AX)
-		 *
-		 * Calculated input:
-		 *  BPF_REG_2	 (R3) : offset of byte(s) to fetch in skb
-		 *  BPF_REG_5	 (R6) : return address
-		 *
-		 * Output:
-		 *  BPF_REG_0	 (R14): data read from skb
-		 *
-		 * Scratch registers (BPF_REG_1-5)
-		 */
-
-		/* Call function: llilf %w1,func_addr  */
-		EMIT6_IMM(0xc00f0000, REG_W1, func_addr);
-
-		/* Offset: lgfi %b2,imm */
-		EMIT6_IMM(0xc0010000, BPF_REG_2, imm);
-		if (BPF_MODE(insn->code) == BPF_IND)
-			/* agfr %b2,%src (%src is s32 here) */
-			EMIT4(0xb9180000, BPF_REG_2, src_reg);
-
-		/* Reload REG_SKB_DATA if BPF_REG_AX is used */
-		if (jit->seen & SEEN_REG_AX)
-			/* lg %skb_data,data_off(%b6) */
-			EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-				      BPF_REG_6, offsetof(struct sk_buff, data));
-		/* basr %b5,%w1 (%b5 is call saved) */
-		EMIT2(0x0d00, BPF_REG_5, REG_W1);
-
-		/*
-		 * Note: For fast access we jump directly after the
-		 * jnz instruction from bpf_jit.S
-		 */
-		/* jnz <ret0> */
-		EMIT4_PCREL(0xa7740000, jit->ret0_ip - jit->prg);
-		break;
 	default: /* too complex, give up */
 		pr_err("Unknown opcode %02x\n", insn->code);
 		return -1;