perf, x86: Fix callgraphs of 32-bit processes on 64-bit kernels

When profiling a 32-bit process on a 64-bit kernel, callgraph tracing
stopped after the first function, because it has seen a garbage memory
address (tried to interpret the frame pointer, and return address as a
64-bit pointer).

Fix this by using a struct stack_frame with 32-bit pointers when the
TIF_IA32 flag is set.

Note that TIF_IA32 flag must be used, and not is_compat_task(), because
the latter is only set when the 32-bit process is executing a syscall,
which may not always be the case (when tracing page fault events for
example).

Signed-off-by: Török Edwin <edwintorok@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
LKML-Reference: <1268820436-13145-1-git-send-email-edwintorok@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 39 insertions, 5 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index bd28cf9d8a82..53ea4cf1a878 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -28,6 +28,7 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
+#include <asm/compat.h>
 
 static u64 perf_event_mask __read_mostly;
 
@@ -1630,14 +1631,42 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
         return len;
 }
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+#ifdef CONFIG_COMPAT
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-        unsigned long bytes;
+        /* 32-bit process in 64-bit kernel. */
+        struct stack_frame_ia32 frame;
+        const void __user *fp;
+
+        if (!test_thread_flag(TIF_IA32))
+                return 0;
+
+        fp = compat_ptr(regs->bp);
+        while (entry->nr < PERF_MAX_STACK_DEPTH) {
+                unsigned long bytes;
+                frame.next_frame     = 0;
+                frame.return_address = 0;
 
-        bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
+                bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+                if (bytes != sizeof(frame))
+                        break;
+
+                if (fp < compat_ptr(regs->sp))
+                        break;
 
-        return bytes == sizeof(*frame);
+                callchain_store(entry, frame.return_address);
+                fp = compat_ptr(frame.next_frame);
+        }
+        return 1;
 }
+#else
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+    return 0;
+}
+#endif
 
 static void
 perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1653,11 +1682,16 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
         callchain_store(entry, PERF_CONTEXT_USER);
         callchain_store(entry, regs->ip);
 
+        if (perf_callchain_user32(regs, entry))
+                return;
+
         while (entry->nr < PERF_MAX_STACK_DEPTH) {
+                unsigned long bytes;
                 frame.next_frame             = NULL;
                 frame.return_address = 0;
 
-                if (!copy_stack_frame(fp, &frame))
+                bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+                if (bytes != sizeof(frame))
                         break;
 
                 if ((unsigned long)fp < regs->sp)