x86: Skip verification by the watchdog for TSC clocksource.

Impact: Changes timekeeping on Vmware (or with tsc=reliable).

This is achieved by resetting the CLOCKSOURCE_MUST_VERIFY flag.

We add a tsc=reliable commandline option to enable this.
This enables legacy hardware without HPET, LAPIC, or ACPI timers
to enter high-resolution timer mode.

Along with that have extended this to be used in virtualization environement
too. Now we also set this flag if the X86_FEATURE_TSC_RELIABLE bit is set.

This is important since there is a wrap-around problem with the acpi_pm timer.
The acpi_pm counter is just 24bits and this can overflow in ~4 seconds. With
the NO_HZ kernels in virtualized environment, there can be situations when
the guest is descheduled for longer duration, as a result we may miss the wrap
of the acpi counter. When TSC is used as a clocksource and acpi_pm timer is
being used as the watchdog clocksource this error in acpi_pm results in TSC
being marked as unstable, and essentially results in time dropping in chunks
of 4 seconds whenever this wrap is missed. Since the virtualized TSC is
reliable on VMware, we should always use the TSCs clocksource on VMware, so
we skip the verfication at runtime, by checking for the feature bit.

Since we reset the flag for mgeode systems too, i have combined
the mgeode case with the feature bit check.

Signed-off-by: Jeff Hansen <jhansen@cardaccess-inc.com>
Signed-off-by: Alok N Kataria <akataria@vmware.com>
Signed-off-by: Dan Hecht <dhecht@vmware.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1bbcaa8982b6c2445fcfdd852f9e33702129cd8b..dc6b06f67fca46c78d11eff60bfc18b844320fdc 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2267,6 +2267,13 @@ and is between 256 and 4096 characters. It is defined in the file
                        Format:
                        <io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
 
+       tsc=            Disable clocksource-must-verify flag for TSC.
+                       Format: <string>
+                       [x86] reliable: mark tsc clocksource as reliable, this
+                       disables clocksource verification at runtime.
+                       Used to enable high-resolution timer mode on older
+                       hardware, and in virtualized environment.
+
        turbografx.map[2|3]=    [HW,JOY]
                        TurboGraFX parallel port interface
                        Format:

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6dbf0bcb44a8bc2d56b6778aa12a22484e7f691b..ee01cd96b5e12e6b94a7f5d7c20f6f839b4a8d10 100644 (file)
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -32,6 +32,7 @@ static int tsc_unstable;
    erroneous rdtsc usage on !cpu_has_tsc processors */
 static int tsc_disabled = -1;
 
+static int tsc_clocksource_reliable;
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -99,6 +100,15 @@ int __init notsc_setup(char *str)
 
 __setup("notsc", notsc_setup);
 
+static int __init tsc_setup(char *str)
+{
+       if (!strcmp(str, "reliable"))
+               tsc_clocksource_reliable = 1;
+       return 1;
+}
+
+__setup("tsc=", tsc_setup);
+
 #define MAX_RETRIES     5
 #define SMI_TRESHOLD    50000
 
@@ -738,24 +748,21 @@ static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
        {}
 };
 
-/*
- * Geode_LX - the OLPC CPU has a possibly a very reliable TSC
- */
+static void __init check_system_tsc_reliable(void)
+{
 #ifdef CONFIG_MGEODE_LX
-/* RTSC counts during suspend */
+       /* RTSC counts during suspend */
 #define RTSC_SUSP 0x100
-
-static void __init check_geode_tsc_reliable(void)
-{
        unsigned long res_low, res_high;
 
        rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+       /* Geode_LX - the OLPC CPU has a possibly a very reliable TSC */
        if (res_low & RTSC_SUSP)
-               clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-}
-#else
-static inline void check_geode_tsc_reliable(void) { }
+               tsc_clocksource_reliable = 1;
 #endif
+       if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
+               tsc_clocksource_reliable = 1;
+}
 
 /*
  * Make an educated guess if the TSC is trustworthy and synchronized
@@ -790,6 +797,8 @@ static void __init init_tsc_clocksource(void)
 {
        clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
                        clocksource_tsc.shift);
+       if (tsc_clocksource_reliable)
+               clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
        /* lower the rating if we already know its unstable: */
        if (check_tsc_unstable()) {
                clocksource_tsc.rating = 0;
@@ -850,7 +859,7 @@ void __init tsc_init(void)
        if (unsynchronized_tsc())
                mark_tsc_unstable("TSCs unsynchronized");
 
-       check_geode_tsc_reliable();
+       check_system_tsc_reliable();
        init_tsc_clocksource();
 }