powerpc64/bpf: Implement PROBE_MEM32 pseudo instructions

Add support for [LDX | STX | ST], PROBE_MEM32, [B | H | W | DW]
instructions. They are similar to PROBE_MEM instructions with the
following differences:
- PROBE_MEM32 supports store.
- PROBE_MEM32 relies on the verifier to clear upper 32-bit of the
src/dst register
- PROBE_MEM32 adds 64-bit kern_vm_start address (which is stored in _R26
in the prologue). Due to bpf_arena constructions such _R26 + reg +
off16 access is guaranteed to be within arena virtual range, so no
address check at run-time.
- PROBE_MEM32 allows STX and ST. If they fault the store is a nop. When
LDX faults the destination register is zeroed.

To support these on powerpc, we do tmp1 = _R26 + src/dst reg and then use
tmp1 as the new src/dst register. This allows us to reuse most of the
code for normal [LDX | STX | ST].

Additionally, bpf_jit_emit_probe_mem_store() is introduced to emit
instructions for storing memory values depending on the size (byte,
halfword, word, doubleword).

Stack layout is adjusted to introduce a new NVR (_R26) and to make
BPF_PPC_STACKFRAME quadword aligned (local_tmp_var is increased by
8 bytes).

Reviewed-by: Hari Bathini <[e-mail]>
Tested-by: Venkat Rao Bagalkote <[e-mail]>
Signed-off-by: Saket Kumar Bhaskar <[e-mail]>
Signed-off-by: Madhavan Srinivasan <[e-mail]>
Link: https://patch.msgid.link/[e-mail]

arch/powerpc/net/bpf_jit.h

···
 	unsigned int seen;
 	unsigned int idx;
 	unsigned int stack_size;
-	int b2p[MAX_BPF_JIT_REG + 2];
+	int b2p[MAX_BPF_JIT_REG + 3];
 	unsigned int exentry_idx;
 	unsigned int alt_exit_addr;
+	u64 arena_vm_start;
 };
 
 #define bpf_to_ppc(r)	(ctx->b2p[r])
···
 
 int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
 			  struct codegen_context *ctx, int insn_idx,
-			  int jmp_off, int dst_reg);
+			  int jmp_off, int dst_reg, u32 code);
 
 #endif
 

arch/powerpc/net/bpf_jit_comp.c

···
 
 	/* Make sure that the stack is quadword aligned. */
 	cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
+	cgctx.arena_vm_start = bpf_arena_get_kern_vm_start(fp->aux->arena);
 
 	/* Scouting faux-generate pass 0 */
 	if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
···
  */
 int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
 			  struct codegen_context *ctx, int insn_idx, int jmp_off,
-			  int dst_reg)
+			  int dst_reg, u32 code)
 {
 	off_t offset;
 	unsigned long pc;
···
 		(ctx->exentry_idx * BPF_FIXUP_LEN * 4);
 
 	fixup[0] = PPC_RAW_LI(dst_reg, 0);
+	if (BPF_CLASS(code) == BPF_ST || BPF_CLASS(code) == BPF_STX)
+		fixup[0] = PPC_RAW_NOP();
+
 	if (IS_ENABLED(CONFIG_PPC32))
 		fixup[1] = PPC_RAW_LI(dst_reg - 1, 0); /* clear higher 32-bit register too */
 
···
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
 		/* See bpf_jit_stack_tailcallcnt() */
-		int tailcallcnt_offset = 6 * 8;
+		int tailcallcnt_offset = 7 * 8;
 
 		EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
 		EMIT(PPC_RAW_STL(_R3, _R1, -tailcallcnt_offset));
···
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
 		/* See bpf_jit_stack_tailcallcnt() */
-		int tailcallcnt_offset = 6 * 8;
+		int tailcallcnt_offset = 7 * 8;
 
 		EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset));
 		EMIT(PPC_RAW_STL(_R3, _R1, func_frame_offset - tailcallcnt_offset));

arch/powerpc/net/bpf_jit_comp32.c

···
 				}
 
 				ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, insn_idx,
-							    jmp_off, dst_reg);
+							    jmp_off, dst_reg, code);
 				if (ret)
 					return ret;
 			}

arch/powerpc/net/bpf_jit_comp64.c

···
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 5*8		|
+ *		[   nv gpr save area	] 6*8		|
  *		[    tail_call_cnt	] 8		|
- *		[    local_tmp_var	] 16		|
+ *		[    local_tmp_var	] 24		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
  *		[     frame header	] 32/112	|
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
 /* for gpr non volatile registers BPG_REG_6 to 10 */
-#define BPF_PPC_STACK_SAVE	(5*8)
+#define BPF_PPC_STACK_SAVE	(6*8)
 /* for bpf JIT code internal usage */
-#define BPF_PPC_STACK_LOCALS	24
+#define BPF_PPC_STACK_LOCALS	32
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
 #define BPF_PPC_STACKFRAME	(STACK_FRAME_MIN_SIZE + \
 				 BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
···
 /* BPF register usage */
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
+#define ARENA_VM_START  (MAX_BPF_JIT_REG + 2)
 
 /* BPF to ppc register mappings */
 void bpf_jit_init_reg_mapping(struct codegen_context *ctx)
···
 	ctx->b2p[BPF_REG_AX] = _R12;
 	ctx->b2p[TMP_REG_1] = _R9;
 	ctx->b2p[TMP_REG_2] = _R10;
+	/* non volatile register for kern_vm_start address */
+	ctx->b2p[ARENA_VM_START] = _R26;
 }
 
-/* PPC NVR range -- update this if we ever use NVRs below r27 */
-#define BPF_PPC_NVR_MIN		_R27
+/* PPC NVR range -- update this if we ever use NVRs below r26 */
+#define BPF_PPC_NVR_MIN		_R26
 
 static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
 {
···
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 5*8
+ *		[   nv gpr save area	] 6*8
  *		[    tail_call_cnt	] 8
- *		[    local_tmp_var	] 16
+ *		[    local_tmp_var	] 24
  *		[   unused red zone	] 224
  */
 static int bpf_jit_stack_local(struct codegen_context *ctx)
···
 	if (bpf_has_stack_frame(ctx))
 		return STACK_FRAME_MIN_SIZE + ctx->stack_size;
 	else
-		return -(BPF_PPC_STACK_SAVE + 24);
+		return -(BPF_PPC_STACK_SAVE + 32);
 }
 
 static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
 {
-	return bpf_jit_stack_local(ctx) + 16;
+	return bpf_jit_stack_local(ctx) + 24;
 }
 
 static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
···
 		if (bpf_is_seen_register(ctx, bpf_to_ppc(i)))
 			EMIT(PPC_RAW_STD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i))));
 
+	if (ctx->arena_vm_start)
+		EMIT(PPC_RAW_STD(bpf_to_ppc(ARENA_VM_START), _R1,
+				 bpf_jit_stack_offsetof(ctx, bpf_to_ppc(ARENA_VM_START))));
+
 	/* Setup frame pointer to point to the bpf stack area */
 	if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP)))
 		EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1,
 				STACK_FRAME_MIN_SIZE + ctx->stack_size));
+
+	if (ctx->arena_vm_start)
+		PPC_LI64(bpf_to_ppc(ARENA_VM_START), ctx->arena_vm_start);
 }
 
 static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx)
···
 	for (i = BPF_REG_6; i <= BPF_REG_10; i++)
 		if (bpf_is_seen_register(ctx, bpf_to_ppc(i)))
 			EMIT(PPC_RAW_LD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i))));
+
+	if (ctx->arena_vm_start)
+		EMIT(PPC_RAW_LD(bpf_to_ppc(ARENA_VM_START), _R1,
+				bpf_jit_stack_offsetof(ctx, bpf_to_ppc(ARENA_VM_START))));
 
 	/* Tear down our stack frame */
 	if (bpf_has_stack_frame(ctx)) {
···
 asm (
 "		.global bpf_stf_barrier		;"
 "	bpf_stf_barrier:			;"
-"		std	21,-64(1)		;"
-"		std	22,-56(1)		;"
+"		std	21,-80(1)		;"
+"		std	22,-72(1)		;"
 "		sync				;"
-"		ld	21,-64(1)		;"
-"		ld	22,-56(1)		;"
+"		ld	21,-80(1)		;"
+"		ld	22,-72(1)		;"
 "		ori	31,31,0			;"
 "		.rept 14			;"
 "		b	1f			;"
···
 "		.endr				;"
 "		blr				;"
 );
+
+static int bpf_jit_emit_probe_mem_store(struct codegen_context *ctx, u32 src_reg, s16 off,
+					u32 code, u32 *image)
+{
+	u32 tmp1_reg = bpf_to_ppc(TMP_REG_1);
+	u32 tmp2_reg = bpf_to_ppc(TMP_REG_2);
+
+	switch (BPF_SIZE(code)) {
+	case BPF_B:
+		EMIT(PPC_RAW_STB(src_reg, tmp1_reg, off));
+		break;
+	case BPF_H:
+		EMIT(PPC_RAW_STH(src_reg, tmp1_reg, off));
+		break;
+	case BPF_W:
+		EMIT(PPC_RAW_STW(src_reg, tmp1_reg, off));
+		break;
+	case BPF_DW:
+		if (off % 4) {
+			EMIT(PPC_RAW_LI(tmp2_reg, off));
+			EMIT(PPC_RAW_STDX(src_reg, tmp1_reg, tmp2_reg));
+		} else {
+			EMIT(PPC_RAW_STD(src_reg, tmp1_reg, off));
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
 
 static int emit_atomic_ld_st(const struct bpf_insn insn, struct codegen_context *ctx, u32 *image)
 {
···
 			}
 			break;
 
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
+
+			EMIT(PPC_RAW_ADD(tmp1_reg, dst_reg, bpf_to_ppc(ARENA_VM_START)));
+
+			ret = bpf_jit_emit_probe_mem_store(ctx, src_reg, off, code, image);
+			if (ret)
+				return ret;
+
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    ctx->idx - 1, 4, -1, code);
+			if (ret)
+				return ret;
+
+			break;
+
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+
+			EMIT(PPC_RAW_ADD(tmp1_reg, dst_reg, bpf_to_ppc(ARENA_VM_START)));
+
+			if (BPF_SIZE(code) == BPF_W || BPF_SIZE(code) == BPF_DW) {
+				PPC_LI32(tmp2_reg, imm);
+				src_reg = tmp2_reg;
+			} else {
+				EMIT(PPC_RAW_LI(tmp2_reg, imm));
+				src_reg = tmp2_reg;
+			}
+
+			ret = bpf_jit_emit_probe_mem_store(ctx, src_reg, off, code, image);
+			if (ret)
+				return ret;
+
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    ctx->idx - 1, 4, -1, code);
+			if (ret)
+				return ret;
+
+			break;
+
 		/*
 		 * BPF_STX ATOMIC (atomic ops)
 		 */
···
 				 * Check if 'off' is word aligned for BPF_DW, because
 				 * we might generate two instructions.
 				 */
-				if ((BPF_SIZE(code) == BPF_DW ||
-				    (BPF_SIZE(code) == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX)) &&
-						(off & 3))
+				if ((BPF_SIZE(code) == BPF_DW && (off & 3)) ||
+				    (BPF_SIZE(code) == BPF_B &&
+				     BPF_MODE(code) == BPF_PROBE_MEMSX) ||
+				    (BPF_SIZE(code) == BPF_B && BPF_MODE(code) == BPF_MEMSX))
 					PPC_JMP((ctx->idx + 3) * 4);
 				else
 					PPC_JMP((ctx->idx + 2) * 4);
···
 
 			if (BPF_MODE(code) == BPF_PROBE_MEM) {
 				ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
-							    ctx->idx - 1, 4, dst_reg);
+							    ctx->idx - 1, 4, dst_reg, code);
 				if (ret)
 					return ret;
 			}
+			break;
+
+		/* dst = *(u64 *)(ul) (src + ARENA_VM_START + off) */
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
+
+			EMIT(PPC_RAW_ADD(tmp1_reg, src_reg, bpf_to_ppc(ARENA_VM_START)));
+
+			switch (size) {
+			case BPF_B:
+				EMIT(PPC_RAW_LBZ(dst_reg, tmp1_reg, off));
+				break;
+			case BPF_H:
+				EMIT(PPC_RAW_LHZ(dst_reg, tmp1_reg, off));
+				break;
+			case BPF_W:
+				EMIT(PPC_RAW_LWZ(dst_reg, tmp1_reg, off));
+				break;
+			case BPF_DW:
+				if (off % 4) {
+					EMIT(PPC_RAW_LI(tmp2_reg, off));
+					EMIT(PPC_RAW_LDX(dst_reg, tmp1_reg, tmp2_reg));
+				} else {
+					EMIT(PPC_RAW_LD(dst_reg, tmp1_reg, off));
+				}
+				break;
+			}
+
+			if (size != BPF_DW && insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
+
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    ctx->idx - 1, 4, dst_reg, code);
+			if (ret)
+				return ret;
 			break;
 
 		/*