[PATCH 3/4] x86: Add trace point for MSR accesses

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

For debugging low level code interacting with the CPU
it is often useful to trace the MSR read/writes. This gives
a concise summary of PMU and other operations.

perf has an ad-hoc way to do this using trace_printk,
but it's somewhat limited (and also now spews ugly boot
messages when enabled)

Instead define real trace points for all MSR accesses.

This adds three new trace points: read_msr and write_msr
and rdpmc.

They also report if the access faulted (if *_safe is used)

This allows filtering and triggering on specific
MSR values, which allows various more advanced
debugging techniques.

All the values are well defined in the CPU documentation.

The trace can be post processed with
Documentation/trace/postprocess/decode_msr.py
to add symbolic MSR names to the trace.

I only added it to native MSR accesses in C, not paravirtualized
or in entry*.S (which is not too interesting)

Originally the patch kit moved the MSRs out of line.
This uses an alternative approach recommended by Steven Rostedt
of only moving the trace calls out of line, but open coding the
access to the jump label.

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 Documentation/trace/events-msr.txt            | 37 +++++++++++++++++++
 Documentation/trace/postprocess/decode_msr.py | 37 +++++++++++++++++++
 arch/x86/include/asm/msr.h                    | 31 ++++++++++++++++
 arch/x86/lib/msr.c                            | 26 ++++++++++++++
 include/trace/events/msr.h                    | 51 +++++++++++++++++++++++++++
 5 files changed, 182 insertions(+)
 create mode 100644 Documentation/trace/events-msr.txt
 create mode 100755 Documentation/trace/postprocess/decode_msr.py
 create mode 100644 include/trace/events/msr.h

diff --git a/Documentation/trace/events-msr.txt b/Documentation/trace/events-msr.txt
new file mode 100644
index 0000000..78c383b
--- /dev/null
+++ b/Documentation/trace/events-msr.txt
@@ -0,0 +1,37 @@
+
+The x86 kernel supports tracing most MSR (Model Specific Register) accesses.
+To see the definition of the MSRs on Intel systems please see the SDM
+at http://www.intel.com/sdm (Volume 3)
+
+Available trace points:
+
+/sys/kernel/debug/tracing/events/msr/
+
+Trace MSR reads
+
+read_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace MSR writes
+
+write_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace RDPMC in kernel
+
+rdpmc
+
+The trace data can be post processed with the postprocess/decode_msr.py script
+
+cat /sys/kernel/debug/tracing/trace | decode_msr.py /usr/src/linux/include/asm/msr-index.h
+
+to add symbolic MSR names.
+
diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py
new file mode 100755
index 0000000..0ab40e0
--- /dev/null
+++ b/Documentation/trace/postprocess/decode_msr.py
@@ -0,0 +1,37 @@
+#!/usr/bin/python
+# add symbolic names to read_msr / write_msr in trace
+# decode_msr msr-index.h < trace
+import sys
+import re
+
+msrs = dict()
+
+with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f:
+	for j in f:
+		m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j)
+		if m:
+			msrs[int(m.group(2), 16)] = m.group(1)
+
+extra_ranges = (
+	( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ),
+	( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ),
+	( "LBR_INFO_%d", 0xdc0, 0xddf ),
+)
+
+for j in sys.stdin:
+	m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j)
+	if m:
+		r = None
+		num = int(m.group(2), 16)
+		if num in msrs:
+			r = msrs[num]
+		else:
+			for er in extra_ranges:
+				if er[1] <= num <= er[2]:
+					r = er[0] % (num - er[1],)
+					break
+		if r:
+			j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")")
+	print j,
+
+
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 77d8b28..fedd6e6 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -57,11 +57,34 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 #define EAX_EDX_RET(val, low, high)	"=A" (val)
 #endif
 
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Be very careful with includes. This header is prone to include loops.
+ */
+#include <asm/atomic.h>
+#include <linux/tracepoint-defs.h>
+
+extern struct tracepoint __tracepoint_read_msr;
+extern struct tracepoint __tracepoint_write_msr;
+extern struct tracepoint __tracepoint_rdpmc;
+#define msr_tracepoint_active(t) static_key_false(&(t).key)
+extern void do_trace_write_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_read_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_rdpmc(unsigned msr, u64 val, int failed);
+#else
+#define msr_tracepoint_active(t) false
+static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {}
+#endif
+
 static inline unsigned long long native_read_msr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
 	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -78,6 +101,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 		     _ASM_EXTABLE(2b, 3b)
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
 		     : "c" (msr), [fault] "i" (-EIO));
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -85,6 +110,8 @@ static inline void native_write_msr(unsigned int msr,
 				    unsigned low, unsigned high)
 {
 	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
 
 /* Can be uninlined because referenced by paravirt */
@@ -102,6 +129,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 		     : "c" (msr), "0" (low), "d" (high),
 		       [fault] "i" (-EIO)
 		     : "memory");
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
 	return err;
 }
 
@@ -160,6 +189,8 @@ static inline unsigned long long native_read_pmc(int counter)
 	DECLARE_ARGS(val, low, high);
 
 	asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
+	if (msr_tracepoint_active(__tracepoint_rdpmc))
+		do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
 }
 
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4362373..47248ee 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,6 +1,8 @@
 #include <linux/module.h>
 #include <linux/preempt.h>
 #include <asm/msr.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/msr.h>
 
 struct msr *msrs_alloc(void)
 {
@@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit)
 {
 	return __flip_bit(msr, bit, false);
 }
+
+#ifdef CONFIG_TRACEPOINTS
+void do_trace_write_msr(unsigned msr, u64 val, int failed)
+{
+	trace_write_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_write_msr);
+EXPORT_TRACEPOINT_SYMBOL(write_msr);
+
+void do_trace_read_msr(unsigned msr, u64 val, int failed)
+{
+	trace_read_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_read_msr);
+EXPORT_TRACEPOINT_SYMBOL(read_msr);
+
+void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+{
+	trace_rdpmc(counter, val, failed);
+}
+EXPORT_SYMBOL(do_trace_rdpmc);
+EXPORT_TRACEPOINT_SYMBOL(rdpmc);
+
+#endif
diff --git a/include/trace/events/msr.h b/include/trace/events/msr.h
new file mode 100644
index 0000000..b2232b5
--- /dev/null
+++ b/include/trace/events/msr.h
@@ -0,0 +1,51 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM msr
+
+#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MSR_H
+
+#include <linux/tracepoint.h>
+
+/*
+ * Tracing for x86 model specific registers. Directly maps to the
+ * RDMSR/WRMSR instructions.
+ */
+
+DECLARE_EVENT_CLASS(msr_trace_class,
+	    TP_PROTO(unsigned msr, u64 val, int failed),
+	    TP_ARGS(msr, val, failed),
+	    TP_STRUCT__entry(
+		    __field(	unsigned,	msr )
+		    __field(    u64,		val )
+		    __field(    int,		failed )
+	    ),
+	    TP_fast_assign(
+		    __entry->msr = msr;
+		    __entry->val = val;
+		    __entry->failed = failed;
+	    ),
+	    TP_printk("%x, value %llx%s",
+		      __entry->msr,
+		      __entry->val,
+		      __entry->failed ? " #GP" : "")
+);
+
+DEFINE_EVENT(msr_trace_class, read_msr,
+	     TP_PROTO(unsigned msr, u64 val, int failed),
+	     TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, write_msr,
+	     TP_PROTO(unsigned msr, u64 val, int failed),
+	     TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, rdpmc,
+	     TP_PROTO(unsigned msr, u64 val, int failed),
+	     TP_ARGS(msr, val, failed)
+);
+
+#endif /* _TRACE_MSR_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
2.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/