x86/asm: Don't use RBP as a temporary register in csum_partial_copy_g…

…eneric()

Andrey Konovalov reported the following warning while fuzzing the kernel
with syzkaller:

  WARNING: kernel stack regs at ffff8800686869f8 in a.out:4933 has bad 'bp' value c3fc855a10167ec0

The unwinder dump revealed that RBP had a bad value when an interrupt
occurred in csum_partial_copy_generic().

That function saves RBP on the stack and then overwrites it, using it as
a scratch register.  That's problematic because it breaks stack traces
if an interrupt occurs in the middle of the function.

Replace the usage of RBP with another callee-saved register (R15) so
stack traces are no longer affected.

Reported-by: Andrey Konovalov <[email protected]>
Tested-by: Andrey Konovalov <[email protected]>
Signed-off-by: Josh Poimboeuf <[email protected]>
Cc: Cong Wang <[email protected]>
Cc: David S . Miller <[email protected]>
Cc: Dmitry Vyukov <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: Kostya Serebryany <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Marcelo Ricardo Leitner <[email protected]>
Cc: Neil Horman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vlad Yasevich <[email protected]>
Cc: [email protected]
Cc: netdev <[email protected]>
Cc: syzkaller <[email protected]>
Link: http://lkml.kernel.org/r/4b03a961efda5ec9bfe46b7b9c9ad72d1efad343.1493909486.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <[email protected]>

arch/x86/lib/csum-copy_64.S

@@ -55,7 +55,7 @@ ENTRY(csum_partial_copy_generic)
 	movq  %r12, 3*8(%rsp)
 	movq  %r14, 4*8(%rsp)
 	movq  %r13, 5*8(%rsp)
-	movq  %rbp, 6*8(%rsp)
+	movq  %r15, 6*8(%rsp)
 
 	movq  %r8, (%rsp)
 	movq  %r9, 1*8(%rsp)
@@ -74,7 +74,7 @@ ENTRY(csum_partial_copy_generic)
 	/* main loop. clear in 64 byte blocks */
 	/* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
 	/* r11:	temp3, rdx: temp4, r12 loopcnt */
-	/* r10:	temp5, rbp: temp6, r14 temp7, r13 temp8 */
+	/* r10:	temp5, r15: temp6, r14 temp7, r13 temp8 */
 	.p2align 4
 .Lloop:
 	source
@@ -89,7 +89,7 @@ ENTRY(csum_partial_copy_generic)
 	source
 	movq  32(%rdi), %r10
 	source
-	movq  40(%rdi), %rbp
+	movq  40(%rdi), %r15
 	source
 	movq  48(%rdi), %r14
 	source
@@ -103,7 +103,7 @@ ENTRY(csum_partial_copy_generic)
 	adcq  %r11, %rax
 	adcq  %rdx, %rax
 	adcq  %r10, %rax
-	adcq  %rbp, %rax
+	adcq  %r15, %rax
 	adcq  %r14, %rax
 	adcq  %r13, %rax
 
@@ -121,7 +121,7 @@ ENTRY(csum_partial_copy_generic)
 	dest
 	movq %r10, 32(%rsi)
 	dest
-	movq %rbp, 40(%rsi)
+	movq %r15, 40(%rsi)
 	dest
 	movq %r14, 48(%rsi)
 	dest
@@ -203,7 +203,7 @@ ENTRY(csum_partial_copy_generic)
 	movq 3*8(%rsp), %r12
 	movq 4*8(%rsp), %r14
 	movq 5*8(%rsp), %r13
-	movq 6*8(%rsp), %rbp
+	movq 6*8(%rsp), %r15
 	addq $7*8, %rsp
 	ret