[PATCH 3.19.y-ckt 185/196] s390/perf_event: fix address range for asynchronous stack

From: Kamal Mostafa
Date: Tue Mar 08 2016 - 19:41:35 EST

3.19.8-ckt16 -stable review patch. If anyone has any objections, please let me know.


From: Heiko Carstens <heiko.carstens@xxxxxxxxxx>

commit 1f8cbb9c8365061d8b866e9b4f4403e029d57989 upstream.

git commit dc7ee00d4771 ("s390: lowcore stack pointer offsets")
introduced a regression in regard to perf_callchain_kernel(). The
stack pointer for the asynchronous stack in the lowcore now has an
additional offset applied. This offset needs to be taken into account
in the calculation for the low and high address for the stack.

This bug was already partially fixed with 9cc5c206d9b4
("s390/dumpstack: fix address ranges for asynchronous and panic
stack"). This patch fixes it also for the perf_event code.

Fixes: dc7ee00d4771 ("s390: lowcore stack pointer offsets")
Signed-off-by: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Signed-off-by: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Signed-off-by: Kamal Mostafa <kamal@xxxxxxxxxxxxx>
arch/s390/kernel/perf_event.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 61595c1..f4307f6 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -262,12 +262,13 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry,
void perf_callchain_kernel(struct perf_callchain_entry *entry,
struct pt_regs *regs)
- unsigned long head;
+ unsigned long head, frame_size;
struct stack_frame *head_sf;

if (user_mode(regs))

+ frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
head = regs->gprs[15];
head_sf = (struct stack_frame *) head;

@@ -275,8 +276,9 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,

head = head_sf->back_chain;
- head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE,
- S390_lowcore.async_stack);
+ head = __store_trace(entry, head,
+ S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
+ S390_lowcore.async_stack + frame_size);

__store_trace(entry, head, S390_lowcore.thread_info,
S390_lowcore.thread_info + THREAD_SIZE);