bpf, ppc64: 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 ppc64 JIT.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Sandipan Das <sandipan@linux.vnet.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

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

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

arch/powerpc/net/bpf_jit_asm64.S

@@ -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

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);
@@ -753,23 +718,10 @@ emit_clear:
 			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_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;
 
 		/*
@@ -886,65 +838,6 @@ cond_branch:
 			PPC_BCC(true_cond, addrs[i + 1 + off]);
 			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
 		 */