powerpc: Separate out load/store emulation into its own function

This moves the parts of emulate_step() that deal with emulating
load and store instructions into a new function called
emulate_loadstore().  This is to make it possible to reuse this
code in the alignment handler.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

2 files changed, 154 insertions, 113 deletions

diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index 958c2c55bcfe..309d1c5de143 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -152,6 +152,15 @@ void emulate_update_regs(struct pt_regs *reg, struct instruction_op *op);
  */
 extern int emulate_step(struct pt_regs *regs, unsigned int instr);
 
+/*
+ * Emulate a load or store instruction by reading/writing the
+ * memory of the current process.  FP/VMX/VSX registers are assumed
+ * to hold live values if the appropriate enable bit in regs->msr is
+ * set; otherwise this will use the saved values in the thread struct
+ * for user-mode accesses.
+ */
+extern int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op);
+
 extern void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
 			     const void *mem, bool cross_endian);
 extern void emulate_vsx_store(struct instruction_op *op,
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 5d8284938898..423815599063 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -2667,76 +2667,35 @@ void emulate_update_regs(struct pt_regs *regs, struct instruction_op *op)
 }
 
 /*
- * Emulate instructions that cause a transfer of control,
- * loads and stores, and a few other instructions.
- * Returns 1 if the step was emulated, 0 if not,
- * or -1 if the instruction is one that should not be stepped,
- * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ * Emulate a previously-analysed load or store instruction.
+ * Return values are:
+ * 0 = instruction emulated successfully
+ * -EFAULT = address out of range or access faulted (regs->dar
+ *	     contains the faulting address)
+ * -EACCES = misaligned access, instruction requires alignment
+ * -EINVAL = unknown operation in *op
  */
-int emulate_step(struct pt_regs *regs, unsigned int instr)
+int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 {
-	struct instruction_op op;
-	int r, err, size, type;
-	unsigned long val;
-	unsigned int cr;
+	int err, size, type;
 	int i, rd, nb;
+	unsigned int cr;
+	unsigned long val;
 	unsigned long ea;
 	bool cross_endian;
 
-	r = analyse_instr(&op, regs, instr);
-	if (r < 0)
-		return r;
-	if (r > 0) {
-		emulate_update_regs(regs, &op);
-		return 1;
-	}
-
 	err = 0;
-	size = GETSIZE(op.type);
-	type = op.type & INSTR_TYPE_MASK;
+	size = GETSIZE(op->type);
+	type = op->type & INSTR_TYPE_MASK;
 	cross_endian = (regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
-
-	ea = op.ea;
-	if (OP_IS_LOAD_STORE(type) || type == CACHEOP)
-		ea = truncate_if_32bit(regs->msr, op.ea);
+	ea = truncate_if_32bit(regs->msr, op->ea);
 
 	switch (type) {
-	case CACHEOP:
-		if (!address_ok(regs, ea, 8))
-			return 0;
-		switch (op.type & CACHEOP_MASK) {
-		case DCBST:
-			__cacheop_user_asmx(ea, err, "dcbst");
-			break;
-		case DCBF:
-			__cacheop_user_asmx(ea, err, "dcbf");
-			break;
-		case DCBTST:
-			if (op.reg == 0)
-				prefetchw((void *) ea);
-			break;
-		case DCBT:
-			if (op.reg == 0)
-				prefetch((void *) ea);
-			break;
-		case ICBI:
-			__cacheop_user_asmx(ea, err, "icbi");
-			break;
-		case DCBZ:
-			err = emulate_dcbz(ea, regs);
-			break;
-		}
-		if (err) {
-			regs->dar = ea;
-			return 0;
-		}
-		goto instr_done;
-
 	case LARX:
 		if (ea & (size - 1))
-			break;		/* can't handle misaligned */
+			return -EACCES;		/* can't handle misaligned */
 		if (!address_ok(regs, ea, size))
-			return 0;
+			return -EFAULT;
 		err = 0;
 		switch (size) {
 #ifdef __powerpc64__
@@ -2755,49 +2714,49 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 			__get_user_asmx(val, ea, err, "ldarx");
 			break;
 		case 16:
-			err = do_lqarx(ea, &regs->gpr[op.reg]);
+			err = do_lqarx(ea, &regs->gpr[op->reg]);
 			break;
 #endif
 		default:
-			return 0;
+			return -EINVAL;
 		}
 		if (err) {
 			regs->dar = ea;
-			return 0;
+			break;
 		}
 		if (size < 16)
-			regs->gpr[op.reg] = val;
-		goto ldst_done;
+			regs->gpr[op->reg] = val;
+		break;
 
 	case STCX:
 		if (ea & (size - 1))
-			break;		/* can't handle misaligned */
+			return -EACCES;		/* can't handle misaligned */
 		if (!address_ok(regs, ea, size))
-			return 0;
+			return -EFAULT;
 		err = 0;
 		switch (size) {
 #ifdef __powerpc64__
 		case 1:
-			__put_user_asmx(op.val, ea, err, "stbcx.", cr);
+			__put_user_asmx(op->val, ea, err, "stbcx.", cr);
 			break;
 		case 2:
-			__put_user_asmx(op.val, ea, err, "stbcx.", cr);
+			__put_user_asmx(op->val, ea, err, "stbcx.", cr);
 			break;
 #endif
 		case 4:
-			__put_user_asmx(op.val, ea, err, "stwcx.", cr);
+			__put_user_asmx(op->val, ea, err, "stwcx.", cr);
 			break;
 #ifdef __powerpc64__
 		case 8:
-			__put_user_asmx(op.val, ea, err, "stdcx.", cr);
+			__put_user_asmx(op->val, ea, err, "stdcx.", cr);
 			break;
 		case 16:
-			err = do_stqcx(ea, regs->gpr[op.reg],
-				       regs->gpr[op.reg + 1], &cr);
+			err = do_stqcx(ea, regs->gpr[op->reg],
+				       regs->gpr[op->reg + 1], &cr);
 			break;
 #endif
 		default:
-			return 0;
+			return -EINVAL;
 		}
 		if (!err)
 			regs->ccr = (regs->ccr & 0x0fffffff) |
@@ -2805,23 +2764,23 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 				((regs->xer >> 3) & 0x10000000);
 		else
 			regs->dar = ea;
-		goto ldst_done;
+		break;
 
 	case LOAD:
 #ifdef __powerpc64__
 		if (size == 16) {
-			err = emulate_lq(regs, ea, op.reg, cross_endian);
-			goto ldst_done;
+			err = emulate_lq(regs, ea, op->reg, cross_endian);
+			break;
 		}
 #endif
-		err = read_mem(&regs->gpr[op.reg], ea, size, regs);
+		err = read_mem(&regs->gpr[op->reg], ea, size, regs);
 		if (!err) {
-			if (op.type & SIGNEXT)
-				do_signext(&regs->gpr[op.reg], size);
-			if ((op.type & BYTEREV) == (cross_endian ? 0 : BYTEREV))
-				do_byterev(&regs->gpr[op.reg], size);
+			if (op->type & SIGNEXT)
+				do_signext(&regs->gpr[op->reg], size);
+			if ((op->type & BYTEREV) == (cross_endian ? 0 : BYTEREV))
+				do_byterev(&regs->gpr[op->reg], size);
 		}
-		goto ldst_done;
+		break;
 
 #ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
@@ -2833,15 +2792,15 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 		 */
 		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
 			return 0;
-		err = do_fp_load(op.reg, ea, size, regs, cross_endian);
-		goto ldst_done;
+		err = do_fp_load(op->reg, ea, size, regs, cross_endian);
+		break;
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
 		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
 			return 0;
-		err = do_vec_load(op.reg, ea, size, regs, cross_endian);
-		goto ldst_done;
+		err = do_vec_load(op->reg, ea, size, regs, cross_endian);
+		break;
 #endif
 #ifdef CONFIG_VSX
 	case LOAD_VSX: {
@@ -2851,18 +2810,18 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 		 * Some VSX instructions check the MSR_VEC bit rather than MSR_VSX
 		 * when the target of the instruction is a vector register.
 		 */
-		if (op.reg >= 32 && (op.vsx_flags & VSX_CHECK_VEC))
+		if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
 			msrbit = MSR_VEC;
 		if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
 			return 0;
-		err = do_vsx_load(&op, ea, regs, cross_endian);
-		goto ldst_done;
+		err = do_vsx_load(op, ea, regs, cross_endian);
+		break;
 	}
 #endif
 	case LOAD_MULTI:
 		if (!address_ok(regs, ea, size))
 			return -EFAULT;
-		rd = op.reg;
+		rd = op->reg;
 		for (i = 0; i < size; i += 4) {
 			unsigned int v32 = 0;
 
@@ -2871,47 +2830,47 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 				nb = 4;
 			err = copy_mem_in((u8 *) &v32, ea, nb, regs);
 			if (err)
-				return 0;
+				break;
 			if (unlikely(cross_endian))
 				v32 = byterev_4(v32);
 			regs->gpr[rd] = v32;
 			ea += 4;
 			++rd;
 		}
-		goto instr_done;
+		break;
 
 	case STORE:
 #ifdef __powerpc64__
 		if (size == 16) {
-			err = emulate_stq(regs, ea, op.reg, cross_endian);
-			goto ldst_done;
+			err = emulate_stq(regs, ea, op->reg, cross_endian);
+			break;
 		}
 #endif
-		if ((op.type & UPDATE) && size == sizeof(long) &&
-		    op.reg == 1 && op.update_reg == 1 &&
+		if ((op->type & UPDATE) && size == sizeof(long) &&
+		    op->reg == 1 && op->update_reg == 1 &&
 		    !(regs->msr & MSR_PR) &&
 		    ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) {
 			err = handle_stack_update(ea, regs);
-			goto ldst_done;
+			break;
 		}
 		if (unlikely(cross_endian))
-			do_byterev(&op.val, size);
-		err = write_mem(op.val, ea, size, regs);
-		goto ldst_done;
+			do_byterev(&op->val, size);
+		err = write_mem(op->val, ea, size, regs);
+		break;
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
 		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
 			return 0;
-		err = do_fp_store(op.reg, ea, size, regs, cross_endian);
-		goto ldst_done;
+		err = do_fp_store(op->reg, ea, size, regs, cross_endian);
+		break;
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
 		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
 			return 0;
-		err = do_vec_store(op.reg, ea, size, regs, cross_endian);
-		goto ldst_done;
+		err = do_vec_store(op->reg, ea, size, regs, cross_endian);
+		break;
 #endif
 #ifdef CONFIG_VSX
 	case STORE_VSX: {
@@ -2921,18 +2880,18 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 		 * Some VSX instructions check the MSR_VEC bit rather than MSR_VSX
 		 * when the target of the instruction is a vector register.
 		 */
-		if (op.reg >= 32 && (op.vsx_flags & VSX_CHECK_VEC))
+		if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
 			msrbit = MSR_VEC;
 		if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
 			return 0;
-		err = do_vsx_store(&op, ea, regs, cross_endian);
-		goto ldst_done;
+		err = do_vsx_store(op, ea, regs, cross_endian);
+		break;
 	}
 #endif
 	case STORE_MULTI:
 		if (!address_ok(regs, ea, size))
 			return -EFAULT;
-		rd = op.reg;
+		rd = op->reg;
 		for (i = 0; i < size; i += 4) {
 			unsigned int v32 = regs->gpr[rd];
 
@@ -2943,10 +2902,89 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 				v32 = byterev_4(v32);
 			err = copy_mem_out((u8 *) &v32, ea, nb, regs);
 			if (err)
-				return 0;
+				break;
 			ea += 4;
 			++rd;
 		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (err)
+		return err;
+
+	if (op->type & UPDATE)
+		regs->gpr[op->update_reg] = op->ea;
+
+	return 0;
+}
+NOKPROBE_SYMBOL(emulate_loadstore);
+
+/*
+ * Emulate instructions that cause a transfer of control,
+ * loads and stores, and a few other instructions.
+ * Returns 1 if the step was emulated, 0 if not,
+ * or -1 if the instruction is one that should not be stepped,
+ * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ */
+int emulate_step(struct pt_regs *regs, unsigned int instr)
+{
+	struct instruction_op op;
+	int r, err, type;
+	unsigned long val;
+	unsigned long ea;
+
+	r = analyse_instr(&op, regs, instr);
+	if (r < 0)
+		return r;
+	if (r > 0) {
+		emulate_update_regs(regs, &op);
+		return 1;
+	}
+
+	err = 0;
+	type = op.type & INSTR_TYPE_MASK;
+
+	if (OP_IS_LOAD_STORE(type)) {
+		err = emulate_loadstore(regs, &op);
+		if (err)
+			return 0;
+		goto instr_done;
+	}
+
+	switch (type) {
+	case CACHEOP:
+		ea = truncate_if_32bit(regs->msr, op.ea);
+		if (!address_ok(regs, ea, 8))
+			return 0;
+		switch (op.type & CACHEOP_MASK) {
+		case DCBST:
+			__cacheop_user_asmx(ea, err, "dcbst");
+			break;
+		case DCBF:
+			__cacheop_user_asmx(ea, err, "dcbf");
+			break;
+		case DCBTST:
+			if (op.reg == 0)
+				prefetchw((void *) ea);
+			break;
+		case DCBT:
+			if (op.reg == 0)
+				prefetch((void *) ea);
+			break;
+		case ICBI:
+			__cacheop_user_asmx(ea, err, "icbi");
+			break;
+		case DCBZ:
+			err = emulate_dcbz(ea, regs);
+			break;
+		}
+		if (err) {
+			regs->dar = ea;
+			return 0;
+		}
 		goto instr_done;
 
 	case MFMSR:
@@ -2989,12 +3027,6 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 	}
 	return 0;
 
- ldst_done:
-	if (err)
-		return 0;
-	if (op.type & UPDATE)
-		regs->gpr[op.update_reg] = op.ea;
-
  instr_done:
 	regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
 	return 1;