lib/vdso: Prepare for time namespace support

To support time namespaces in the vdso with a minimal impact on regular non
time namespace affected tasks, the namespace handling needs to be hidden in
a slow path.

The most obvious place is vdso_seq_begin(). If a task belongs to a time
namespace then the VVAR page which contains the system wide vdso data is
replaced with a namespace specific page which has the same layout as the
VVAR page. That page has vdso_data->seq set to 1 to enforce the slow path
and vdso_data->clock_mode set to VCLOCK_TIMENS to enforce the time
namespace handling path.

The extra check in the case that vdso_data->seq is odd, e.g. a concurrent
update of the vdso data is in progress, is not really affecting regular
tasks which are not part of a time namespace as the task is spin waiting
for the update to finish and vdso_data->seq to become even again.

If a time namespace task hits that code path, it invokes the corresponding
time getter function which retrieves the real VVAR page, reads host time
and then adds the offset for the requested clock which is stored in the
special VVAR page.

If VDSO time namespace support is disabled the whole magic is compiled out.

Initial testing shows that the disabled case is almost identical to the
host case which does not take the slow timens path. With the special timens
page installed the performance hit is constant time and in the range of
5-7%.

For the vdso functions which are not using the sequence count an
unconditional check for vdso_data->clock_mode is added which switches to
the real vdso when the clock_mode is VCLOCK_TIMENS.

[avagin: Make do_hres_timens() work with raw clocks too: choose vdso_data
 pointer by CS_RAW offset.]

Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20191112012724.250792-21-dima@arista.com

2 files changed, 24 insertions, 1 deletions

diff --git a/include/linux/time.h b/include/linux/time.h
index 8e10b9dbd8c2..8ef5e5cc9f57 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -110,4 +110,10 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its)
  * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)).
  */
 #define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l))
+
+struct timens_offset {
+	s64	sec;
+	u64	nsec;
+};
+
 #endif
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 2e302c0f41f7..c5f347cc5e55 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -21,6 +21,8 @@
 #define CS_RAW		1
 #define CS_BASES	(CS_RAW + 1)
 
+#define VCLOCK_TIMENS	UINT_MAX
+
 /**
  * struct vdso_timestamp - basetime per clock_id
  * @sec:	seconds
@@ -48,6 +50,7 @@ struct vdso_timestamp {
  * @mult:		clocksource multiplier
  * @shift:		clocksource shift
  * @basetime[clock_id]:	basetime per clock_id
+ * @offset[clock_id]:	time namespace offset per clock_id
  * @tz_minuteswest:	minutes west of Greenwich
  * @tz_dsttime:		type of DST correction
  * @hrtimer_res:	hrtimer resolution
@@ -55,6 +58,17 @@ struct vdso_timestamp {
  *
  * vdso_data will be accessed by 64 bit and compat code at the same time
  * so we should be careful before modifying this structure.
+ *
+ * @basetime is used to store the base time for the system wide time getter
+ * VVAR page.
+ *
+ * @offset is used by the special time namespace VVAR pages which are
+ * installed instead of the real VVAR page. These namespace pages must set
+ * @seq to 1 and @clock_mode to VLOCK_TIMENS to force the code into the
+ * time namespace slow path. The namespace aware functions retrieve the
+ * real system wide VVAR page, read host time and add the per clock offset.
+ * For clocks which are not affected by time namespace adjustment the
+ * offset must be zero.
  */
 struct vdso_data {
 	u32			seq;
@@ -65,7 +79,10 @@ struct vdso_data {
 	u32			mult;
 	u32			shift;
 
-	struct vdso_timestamp	basetime[VDSO_BASES];
+	union {
+		struct vdso_timestamp	basetime[VDSO_BASES];
+		struct timens_offset	offset[VDSO_BASES];
+	};
 
 	s32			tz_minuteswest;
 	s32			tz_dsttime;