[Xen-devel] [PATCH 2/5] x86/time: implement tsc as clocksource

[Joao Martins <joao.m.martins@xxxxxxxxxx>]

Introduce support for using TSC as platform time which is the highest
resolution time and most performant to get (~20 nsecs).  Though there
are also several problems associated with its usage, and there isn't a
complete (and architecturally defined) guarantee that all machines
will provide reliable and monotonic TSC across all CPUs, on different
sockets and different P/C states.  I believe Intel to be the only that
can guarantee that. For this reason it's set with less priority when
compared to HPET unless adminstrator changes "clocksource" boot option
to "tsc". Upon initializing it, we also check for time warps and
appropriate CPU features i.e.  TSC_RELIABLE, CONSTANT_TSC and
NONSTOP_TSC. And in case none of these conditions are met, we fail in
order to fallback to the next available clocksource.

It is also worth noting that with clocksource=tsc there isn't any
need to synchronise with another clocksource, and I could verify that
great portion the time skew was eliminated and seeing much less time
warps happening. With HPET I observed ~500 warps in the period
of 1h of around 27 us, and with TSC down to 50 warps in the same
period having each warp < 100 ns. The warps still exist though but
are only related to cross CPU calibration (being how much it takes to
rendezvous with master), in which a later patch in this series aims to
solve.

Signed-off-by: Joao Martins <joao.m.martins@xxxxxxxxxx>
---
Cc: Keir Fraser <keir@xxxxxxx>
Cc: Jan Beulich <jbeulich@xxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>

Changes since RFC:
 - Spelling fixes in the commit message.
 - Remove unused clocksource_is_tsc variable and introduce it instead
 on the patch that uses it.
 - Move plt_tsc from second to last in the available clocksources.
---
 xen/arch/x86/time.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 60 insertions(+), 2 deletions(-)

diff --git a/xen/arch/x86/time.c b/xen/arch/x86/time.c
index 687e39b..1311c58 100644
--- a/xen/arch/x86/time.c
+++ b/xen/arch/x86/time.c
@@ -432,6 +432,63 @@ uint64_t ns_to_acpi_pm_tick(uint64_t ns)
 }
 
 /************************************************************
+ * PLATFORM TIMER 4: TSC
+ */
+static u64 tsc_freq;
+static unsigned long tsc_max_warp;
+static void tsc_check_reliability(void);
+
+static int __init init_tsctimer(struct platform_timesource *pts)
+{
+    bool_t tsc_reliable = 0;
+
+    tsc_check_reliability();
+
+    if ( tsc_max_warp > 0 )
+    {
+        tsc_reliable = 0;
+        printk("TSC: didn't passed warp test\n");
+    }
+    else if ( boot_cpu_has(X86_FEATURE_TSC_RELIABLE) ||
+              ( boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+                boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ) )
+    {
+        tsc_reliable = 1;
+    }
+    else if ( boot_cpu_has(X86_FEATURE_CONSTANT_TSC) )
+    {
+        tsc_reliable = (max_cstate <= 2);
+
+        if (tsc_reliable)
+            printk("TSC: no deep Cstates, deemed reliable\n");
+        else
+            printk("TSC: deep Cstates possible, so not reliable\n");
+    }
+
+    pts->frequency = tsc_freq;
+    return tsc_reliable;
+}
+
+static u64 read_tsc(void)
+{
+    return rdtsc();
+}
+
+static void resume_tsctimer(struct platform_timesource *pts)
+{
+}
+
+static struct platform_timesource __initdata plt_tsc =
+{
+    .id = "tsc",
+    .name = "TSC",
+    .read_counter = read_tsc,
+    .counter_bits = 64,
+    .init = init_tsctimer,
+    .resume = resume_tsctimer,
+};
+
+/************************************************************
  * GENERIC PLATFORM TIMER INFRASTRUCTURE
  */
 
@@ -536,7 +593,7 @@ static void resume_platform_timer(void)
 static void __init init_platform_timer(void)
 {
     static struct platform_timesource * __initdata plt_timers[] = {
-        &plt_hpet, &plt_pmtimer, &plt_pit
+        &plt_hpet, &plt_pmtimer, &plt_pit, &plt_tsc
     };
 
     struct platform_timesource *pts = NULL;
@@ -1181,7 +1238,7 @@ static void check_tsc_warp(unsigned long tsc_khz, 
unsigned long *max_warp)
     }
 }
 
-static unsigned long tsc_max_warp, tsc_check_count;
+static unsigned long tsc_check_count;
 static cpumask_t tsc_check_cpumask;
 
 static void tsc_check_slave(void *unused)
@@ -1465,6 +1522,7 @@ void __init early_time_init(void)
     struct cpu_time *t = &this_cpu(cpu_time);
     u64 tmp = init_pit_and_calibrate_tsc();
 
+    tsc_freq = tmp;
     set_time_scale(&t->tsc_scale, tmp);
     t->local_tsc_stamp = boot_tsc_stamp;
 
-- 
2.1.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel