x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic()

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 <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: linux-sctp@vger.kernel.org
Cc: netdev <netdev@vger.kernel.org>
Cc: syzkaller <syzkaller@googlegroups.com>
Link: http://lkml.kernel.org/r/4b03a961efda5ec9bfe46b7b9c9ad72d1efad343.1493909486.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 7e48807b2fa198c4e2b8e7022df2218308a41b7c..45a53dfe1859b1955fa91bad9bf1543903f1c1a8 100644 (file)
--- a/arch/x86/lib/csum-copy_64.S
+++ b/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