@@ -168,6 +168,7 @@ config X86
select GENERIC_TIME_VSYSCALL
select GENERIC_GETTIMEOFDAY
select GENERIC_VDSO_TIME_NS
+ select GENERIC_VDSO_OVERFLOW_PROTECT
select GUP_GET_PXX_LOW_HIGH if X86_PAE
select HARDIRQS_SW_RESEND
select HARDLOCKUP_CHECK_TIMESTAMP if X86_64
@@ -319,18 +319,31 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
*/
static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
{
+ u64 delta = cycles - vd->cycle_last;
+
/*
+ * Negative motion and deltas which can cause multiplication
+ * overflow require special treatment. This check covers both as
+ * negative motion is guaranteed to be greater than @vd::max_cycles
+ * due to unsigned comparison.
+ *
* Due to the MSB/Sign-bit being used as invalid marker (see
- * arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
+ * arch_vdso_cycles_valid() above), the effective mask is S64_MAX,
+ * but that case is also unlikely and will also take the unlikely path
+ * here.
*/
- u64 delta = (cycles - vd->cycle_last) & S64_MAX;
+ if (unlikely(delta > vd->max_cycles)) {
+ /*
+ * Due to the above mentioned TSC wobbles, filter out
+ * negative motion. Per the above masking, the effective
+ * sign bit is now bit 62.
+ */
+ if (delta & (1ULL << 62))
+ return base >> vd->shift;
- /*
- * Due to the above mentioned TSC wobbles, filter out negative motion.
- * Per the above masking, the effective sign bit is now bit 62.
- */
- if (unlikely(delta & (1ULL << 62)))
- return base >> vd->shift;
+ /* Handle multiplication overflow gracefully */
+ return mul_u64_u32_add_u64_shr(delta & S64_MAX, vd->mult, base, vd->shift);
+ }
return ((delta * vd->mult) + base) >> vd->shift;
}
Kernel timekeeping is designed to keep the change in cycles (since the last timer interrupt) below max_cycles, which prevents multiplication overflow when converting cycles to nanoseconds. However, if timer interrupts stop, the calculation will eventually overflow. Add protection against that. Select GENERIC_VDSO_OVERFLOW_PROTECT so that max_cycles is made available in the VDSO data page. Check against max_cycles, falling back to a slower higher precision calculation. Take advantage of the opportunity to move masking and negative motion check into the slow path. The result is a calculation that has similar performance as before. Newer machines showed performance benefit, whereas older Skylake-based hardware such as Intel Kaby Lake was seen <1% worse. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- arch/x86/Kconfig | 1 + arch/x86/include/asm/vdso/gettimeofday.h | 29 +++++++++++++++++------- 2 files changed, 22 insertions(+), 8 deletions(-)