4 files changed, 41 insertions, 40 deletions

diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index dd223b3eb333..17e5b2364312 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -20,7 +20,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 
-	err = __put_user(instr, addr);
+	__put_user_size(instr, addr, 4, err);
 	if (err)
 		return err;
 	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index f9ede7c6606e..0d24ff15f5f6 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -288,7 +288,7 @@ err1;	stb	r0,0(r3)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	bl	.enter_vmx_usercopy
-	cmpwi	r3,0
+	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
 	ld	r3,STACKFRAMESIZE+48(r1)
 	ld	r4,STACKFRAMESIZE+56(r1)
@@ -326,38 +326,7 @@ err1;	stb	r0,0(r3)
 	dcbt	r0,r8,0b01010	/* GO */
 .machine pop
 
-	/*
-	 * We prefetch both the source and destination using enhanced touch
-	 * instructions. We use a stream ID of 0 for the load side and
-	 * 1 for the store side.
-	 */
-	clrrdi	r6,r4,7
-	clrrdi	r9,r3,7
-	ori	r9,r9,1		/* stream=1 */
-
-	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
-	cmpldi	cr1,r7,0x3FF
-	ble	cr1,1f
-	li	r7,0x3FF
-1:	lis	r0,0x0E00	/* depth=7 */
-	sldi	r7,r7,7
-	or	r7,r7,r0
-	ori	r10,r7,1	/* stream=1 */
-
-	lis	r8,0x8000	/* GO=1 */
-	clrldi	r8,r8,32
-
-.machine push
-.machine "power4"
-	dcbt	r0,r6,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
-	eieio
-	dcbt	r0,r8,0b01010	/* GO */
-.machine pop
-
-	beq	.Lunwind_stack_nonvmx_copy
+	beq	cr1,.Lunwind_stack_nonvmx_copy
 
 	/*
 	 * If source and destination are not relatively aligned we use a
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 0efdc51bc716..0663630baf3b 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -222,7 +222,7 @@ _GLOBAL(memcpy_power7)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	bl	.enter_vmx_copy
-	cmpwi	r3,0
+	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
 	ld	r3,STACKFRAMESIZE+48(r1)
 	ld	r4,STACKFRAMESIZE+56(r1)
@@ -239,8 +239,8 @@ _GLOBAL(memcpy_power7)
 	ori	r9,r9,1		/* stream=1 */
 
 	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
-	cmpldi	cr1,r7,0x3FF
-	ble	cr1,1f
+	cmpldi	r7,0x3FF
+	ble	1f
 	li	r7,0x3FF
 1:	lis	r0,0x0E00	/* depth=7 */
 	sldi	r7,r7,7
@@ -260,7 +260,7 @@ _GLOBAL(memcpy_power7)
 	dcbt	r0,r8,0b01010	/* GO */
 .machine pop
 
-	beq	.Lunwind_stack_nonvmx_copy
+	beq	cr1,.Lunwind_stack_nonvmx_copy
 
 	/*
 	 * If source and destination are not relatively aligned we use a
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 9a52349874ee..e15c521846ca 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -566,7 +566,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 	unsigned long int ea;
 	unsigned int cr, mb, me, sh;
 	int err;
-	unsigned long old_ra;
+	unsigned long old_ra, val3;
 	long ival;
 
 	opcode = instr >> 26;
@@ -1486,11 +1486,43 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case 36:	/* stw */
-	case 37:	/* stwu */
 		val = regs->gpr[rd];
 		err = write_mem(val, dform_ea(instr, regs), 4, regs);
 		goto ldst_done;
 
+	case 37:	/* stwu */
+		val = regs->gpr[rd];
+		val3 = dform_ea(instr, regs);
+		/*
+		 * For PPC32 we always use stwu to change stack point with r1. So
+		 * this emulated store may corrupt the exception frame, now we
+		 * have to provide the exception frame trampoline, which is pushed
+		 * below the kprobed function stack. So we only update gpr[1] but
+		 * don't emulate the real store operation. We will do real store
+		 * operation safely in exception return code by checking this flag.
+		 */
+		if ((ra == 1) && !(regs->msr & MSR_PR) \
+			&& (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
+			/*
+			 * Check if we will touch kernel sack overflow
+			 */
+			if (val3 - STACK_INT_FRAME_SIZE <= current->thread.ksp_limit) {
+				printk(KERN_CRIT "Can't kprobe this since Kernel stack overflow.\n");
+				err = -EINVAL;
+				break;
+			}
+
+			/*
+			 * Check if we already set since that means we'll
+			 * lose the previous value.
+			 */
+			WARN_ON(test_thread_flag(TIF_EMULATE_STACK_STORE));
+			set_thread_flag(TIF_EMULATE_STACK_STORE);
+			err = 0;
+		} else
+			err = write_mem(val, val3, 4, regs);
+		goto ldst_done;
+
 	case 38:	/* stb */
 	case 39:	/* stbu */
 		val = regs->gpr[rd];