[PATCH v3 6/8] pstore: Add ftrace timestamp counter

[Kees Cook <keescook@chromium.org>]

From: Joel Fernandes <joelaf@google.com>

In preparation for merging the per CPU buffers into one buffer when
we retrieve the pstore ftrace data, we store the timestamp as a
counter in the ftrace pstore record.  We store the CPU number as well
if !PSTORE_CPU_IN_IP, in this case we shift the counter and may lose
ordering there but we preserve the same record size. The timestamp counter
is also racy, and not doing any locking or synchronization here results
in the benefit of lower overhead. Since we don't care much here for exact
ordering of function traces across CPUs, we don't synchronize and may lose
some counter updates but I'm ok with that.

Using trace_clock() results in much lower performance so avoid using it
since we don't want accuracy in timestamp and need a rough ordering to
perform merge.

Signed-off-by: Joel Fernandes <joelaf@google.com>
[kees: updated commit message, added comments]
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/pstore/ftrace.c     |  4 +++
 fs/pstore/inode.c      |  8 ++++--
 fs/pstore/internal.h   | 34 ----------------------
 include/linux/pstore.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 85 insertions(+), 37 deletions(-)

diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
index d4887705bb61..31548cc09e7b 100644
--- a/fs/pstore/ftrace.c
+++ b/fs/pstore/ftrace.c
@@ -27,6 +27,9 @@
 #include <asm/barrier.h>
 #include "internal.h"
 
+/* This doesn't need to be atomic: speed is chosen over correctness here. */
+static u64 pstore_ftrace_stamp;
+
 static void notrace pstore_ftrace_call(unsigned long ip,
 				       unsigned long parent_ip,
 				       struct ftrace_ops *op,
@@ -42,6 +45,7 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 
 	rec.ip = ip;
 	rec.parent_ip = parent_ip;
+	pstore_ftrace_write_timestamp(&rec, pstore_ftrace_stamp++);
 	pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id());
 	psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec,
 			  0, sizeof(rec), psinfo);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 1781dc50762e..0d6bbcf47d52 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -107,9 +107,11 @@ static int pstore_ftrace_seq_show(struct seq_file *s, void *v)
 	struct pstore_ftrace_seq_data *data = v;
 	struct pstore_ftrace_record *rec = (void *)(ps->data + data->off);
 
-	seq_printf(s, "%d %08lx  %08lx  %pf <- %pF\n",
-		pstore_ftrace_decode_cpu(rec), rec->ip, rec->parent_ip,
-		(void *)rec->ip, (void *)rec->parent_ip);
+	seq_printf(s, "CPU:%d ts:%llu %08lx  %08lx  %pf <- %pF\n",
+		   pstore_ftrace_decode_cpu(rec),
+		   pstore_ftrace_read_timestamp(rec),
+		   rec->ip, rec->parent_ip, (void *)rec->ip,
+		   (void *)rec->parent_ip);
 
 	return 0;
 }
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index e38a22b31282..da416e6591c9 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -5,40 +5,6 @@
 #include <linux/time.h>
 #include <linux/pstore.h>
 
-#if NR_CPUS <= 2 && defined(CONFIG_ARM_THUMB)
-#define PSTORE_CPU_IN_IP 0x1
-#elif NR_CPUS <= 4 && defined(CONFIG_ARM)
-#define PSTORE_CPU_IN_IP 0x3
-#endif
-
-struct pstore_ftrace_record {
-	unsigned long ip;
-	unsigned long parent_ip;
-#ifndef PSTORE_CPU_IN_IP
-	unsigned int cpu;
-#endif
-};
-
-static inline void
-pstore_ftrace_encode_cpu(struct pstore_ftrace_record *rec, unsigned int cpu)
-{
-#ifndef PSTORE_CPU_IN_IP
-	rec->cpu = cpu;
-#else
-	rec->ip |= cpu;
-#endif
-}
-
-static inline unsigned int
-pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec)
-{
-#ifndef PSTORE_CPU_IN_IP
-	return rec->cpu;
-#else
-	return rec->ip & PSTORE_CPU_IN_IP;
-#endif
-}
-
 #ifdef CONFIG_PSTORE_FTRACE
 extern void pstore_register_ftrace(void);
 extern void pstore_unregister_ftrace(void);
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index 92013cc9cc8c..0da29cae009b 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -89,4 +89,80 @@ extern int pstore_register(struct pstore_info *);
 extern void pstore_unregister(struct pstore_info *);
 extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason);
 
+struct pstore_ftrace_record {
+	unsigned long ip;
+	unsigned long parent_ip;
+	u64 ts;
+};
+
+/*
+ * ftrace related stuff: Both backends and frontends need these so expose
+ * them here.
+ */
+
+#if NR_CPUS <= 2 && defined(CONFIG_ARM_THUMB)
+#define PSTORE_CPU_IN_IP 0x1
+#elif NR_CPUS <= 4 && defined(CONFIG_ARM)
+#define PSTORE_CPU_IN_IP 0x3
+#endif
+
+#define TS_CPU_SHIFT 8
+#define TS_CPU_MASK (BIT(TS_CPU_SHIFT) - 1)
+
+/*
+ * If CPU number can be stored in IP, store it there, otherwise store it in
+ * the time stamp. This means more timestamp resolution is available when
+ * the CPU can be stored in the IP.
+ */
+#ifdef PSTORE_CPU_IN_IP
+static inline void
+pstore_ftrace_encode_cpu(struct pstore_ftrace_record *rec, unsigned int cpu)
+{
+	rec->ip |= cpu;
+}
+
+static inline unsigned int
+pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec)
+{
+	return rec->ip & PSTORE_CPU_IN_IP;
+}
+
+static inline u64
+pstore_ftrace_read_timestamp(struct pstore_ftrace_record *rec)
+{
+	return rec->ts;
+}
+
+static inline void
+pstore_ftrace_write_timestamp(struct pstore_ftrace_record *rec, u64 val)
+{
+	rec->ts = val;
+}
+#else
+static inline void
+pstore_ftrace_encode_cpu(struct pstore_ftrace_record *rec, unsigned int cpu)
+{
+	rec->ts &= ~(TS_CPU_MASK);
+	rec->ts |= cpu;
+}
+
+static inline unsigned int
+pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec)
+{
+	return rec->ts & TS_CPU_MASK;
+}
+
+static inline u64
+pstore_ftrace_read_timestamp(struct pstore_ftrace_record *rec)
+{
+	return rec->ts >> TS_CPU_SHIFT;
+}
+
+static inline void
+pstore_ftrace_write_timestamp(struct pstore_ftrace_record *rec, u64 val)
+{
+	rec->ts = (rec->ts & TS_CPU_MASK) | (val << TS_CPU_SHIFT);
+}
+#endif
+
 #endif /*_LINUX_PSTORE_H*/
-- 
2.7.4