perf: Fix race in callchains

Now that software events don't have interrupt disabled anymore in
the event path, callchains can nest on any context. So seperating
nmi and others contexts in two buffers has become racy.

Fix this by providing one buffer per nesting level. Given the size
of the callchain entries (2040 bytes * 4), we now need to allocate
them dynamically.

v2: Fixed put_callchain_entry call after recursion.
    Fix the type of the recursion, it must be an array.

v3: Use a manual pr cpu allocation (temporary solution until NMIs
    can safely access vmalloc'ed memory).
    Do a better separation between callchain reference tracking and
    allocation. Make the "put" path lockless for non-release cases.

v4: Protect the callchain buffers with rcu.

v5: Do the cpu buffers allocations node affine.

Signed-off-by: Frederic Weisbecker <[email protected]>
Tested-by: Will Deacon <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Paul Mundt <[email protected]>
Cc: David Miller <[email protected]>
Cc: Borislav Petkov <[email protected]>

arch/x86/kernel/cpu/perf_event.c

@@ -1608,6 +1608,11 @@ static const struct stacktrace_ops backtrace_ops = {
 void
 perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return NULL;
+	}
+
 	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
@@ -1656,6 +1661,10 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	struct stack_frame frame;
 	const void __user *fp;
 
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return NULL;
+	}
 
 	fp = (void __user *)regs->bp;
 
@@ -1681,19 +1690,6 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	}
 }
 
-struct perf_callchain_entry *perf_callchain_buffer(void)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* TODO: We don't support guest os callchain now */
-		return NULL;
-	}
-
-	if (in_nmi())
-		return &__get_cpu_var(perf_callchain_entry_nmi);
-
-	return &__get_cpu_var(perf_callchain_entry);
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;

include/linux/perf_event.h

@@ -983,7 +983,6 @@ extern void perf_callchain_user(struct perf_callchain_entry *entry,
 				struct pt_regs *regs);
 extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
 				  struct pt_regs *regs);
-extern struct perf_callchain_entry *perf_callchain_buffer(void);
 
 
 static inline void