summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2010-01-19 00:26:13 -0800
committerDavid S. Miller <davem@davemloft.net>2010-01-20 16:23:02 -0800
commit4f6dbe4ac01d2664231d3f3eceadd33a44cde993 (patch)
tree029201f8597df383c5fac18b2693227570b1693e /arch
parent0299b1371d8f1b074c8284a19beb9094ada9405f (diff)
downloadlinux-4f6dbe4ac01d2664231d3f3eceadd33a44cde993.tar.gz
linux-4f6dbe4ac01d2664231d3f3eceadd33a44cde993.tar.bz2
linux-4f6dbe4ac01d2664231d3f3eceadd33a44cde993.zip
sparc64: Add perf callchain support.
Pretty straightforward, and it should be easy to add accurate walk through of signal stack frames in userspace. Signed-off-by: David S. Miller <davem@davemloft.net> Tested-by: Jens Axboe <jens.axboe@oracle.com>
Diffstat (limited to 'arch')
-rw-r--r--arch/sparc/kernel/perf_event.c120
1 files changed, 119 insertions, 1 deletions
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 198fb4e79ba2..2386ac6ec956 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1,6 +1,6 @@
/* Performance event support for sparc64.
*
- * Copyright (C) 2009 David S. Miller <davem@davemloft.net>
+ * Copyright (C) 2009, 2010 David S. Miller <davem@davemloft.net>
*
* This code is based almost entirely upon the x86 perf event
* code, which is:
@@ -18,11 +18,15 @@
#include <linux/kdebug.h>
#include <linux/mutex.h>
+#include <asm/stacktrace.h>
#include <asm/cpudata.h>
+#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <asm/nmi.h>
#include <asm/pcr.h>
+#include "kstack.h"
+
/* Sparc64 chips have two performance counters, 32-bits each, with
* overflow interrupts generated on transition from 0xffffffff to 0.
* The counters are accessed in one go using a 64-bit register.
@@ -1062,3 +1066,117 @@ void __init init_hw_perf_events(void)
register_die_notifier(&perf_event_nmi_notifier);
}
+
+static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+ if (entry->nr < PERF_MAX_STACK_DEPTH)
+ entry->ip[entry->nr++] = ip;
+}
+
+static void perf_callchain_kernel(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+ unsigned long ksp, fp;
+
+ callchain_store(entry, PERF_CONTEXT_KERNEL);
+ callchain_store(entry, regs->tpc);
+
+ ksp = regs->u_regs[UREG_I6];
+ fp = ksp + STACK_BIAS;
+ do {
+ struct sparc_stackf *sf;
+ struct pt_regs *regs;
+ unsigned long pc;
+
+ if (!kstack_valid(current_thread_info(), fp))
+ break;
+
+ sf = (struct sparc_stackf *) fp;
+ regs = (struct pt_regs *) (sf + 1);
+
+ if (kstack_is_trap_frame(current_thread_info(), regs)) {
+ if (user_mode(regs))
+ break;
+ pc = regs->tpc;
+ fp = regs->u_regs[UREG_I6] + STACK_BIAS;
+ } else {
+ pc = sf->callers_pc;
+ fp = (unsigned long)sf->fp + STACK_BIAS;
+ }
+ callchain_store(entry, pc);
+ } while (entry->nr < PERF_MAX_STACK_DEPTH);
+}
+
+static void perf_callchain_user_64(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+ unsigned long ufp;
+
+ callchain_store(entry, PERF_CONTEXT_USER);
+ callchain_store(entry, regs->tpc);
+
+ ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
+ do {
+ struct sparc_stackf *usf, sf;
+ unsigned long pc;
+
+ usf = (struct sparc_stackf *) ufp;
+ if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
+ break;
+
+ pc = sf.callers_pc;
+ ufp = (unsigned long)sf.fp + STACK_BIAS;
+ callchain_store(entry, pc);
+ } while (entry->nr < PERF_MAX_STACK_DEPTH);
+}
+
+static void perf_callchain_user_32(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+ unsigned long ufp;
+
+ callchain_store(entry, PERF_CONTEXT_USER);
+ callchain_store(entry, regs->tpc);
+
+ ufp = regs->u_regs[UREG_I6];
+ do {
+ struct sparc_stackf32 *usf, sf;
+ unsigned long pc;
+
+ usf = (struct sparc_stackf32 *) ufp;
+ if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
+ break;
+
+ pc = sf.callers_pc;
+ ufp = (unsigned long)sf.fp;
+ callchain_store(entry, pc);
+ } while (entry->nr < PERF_MAX_STACK_DEPTH);
+}
+
+/* Like powerpc we can't get PMU interrupts within the PMU handler,
+ * so no need for seperate NMI and IRQ chains as on x86.
+ */
+static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+ struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+
+ entry->nr = 0;
+ if (!user_mode(regs)) {
+ stack_trace_flush();
+ perf_callchain_kernel(regs, entry);
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+ if (regs) {
+ flushw_user();
+ if (test_thread_flag(TIF_32BIT))
+ perf_callchain_user_32(regs, entry);
+ else
+ perf_callchain_user_64(regs, entry);
+ }
+ return entry;
+}