From 6cb9a8350aee789100a365794272ed20cc8f2401 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Mon, 5 Mar 2007 00:30:35 -0800 Subject: [PATCH] vmi: sched clock paravirt op fix The custom_sched_clock hook is broken. The result from sched_clock needs to be in nanoseconds, not in CPU cycles. The TSC is insufficient for this purpose, because TSC is poorly defined in a virtual environment, and mostly represents real world time instead of scheduled process time (which can be interrupted without notice when a virtual machine is descheduled). To make the scheduler consistent, we must expose a different nature of time, that is scheduled time. So deprecate this custom_sched_clock hack and turn it into a paravirt-op, as it should have been all along. This allows the tsc.c code which converts cycles to nanoseconds to be shared by all paravirt-ops backends. It is unfortunate to add a new paravirt-op, but this is a very distinct abstraction which is clearly different for all virtual machine implementations, and it gets rid of an ugly indirect function which I ashamedly admit I hacked in to try to get this to work earlier, and then even got in the wrong units. Signed-off-by: Zachary Amsden Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/paravirt.c | 2 ++ arch/i386/kernel/tsc.c | 6 ++---- arch/i386/kernel/vmi.c | 2 +- arch/i386/kernel/vmitime.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/i386') diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c index c156ecf..31bbe70 100644 --- a/arch/i386/kernel/paravirt.c +++ b/arch/i386/kernel/paravirt.c @@ -32,6 +32,7 @@ #include #include #include +#include /* nop stub */ static void native_nop(void) @@ -520,6 +521,7 @@ struct paravirt_ops paravirt_ops = { .write_msr = native_write_msr, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, + .get_scheduled_cycles = native_read_tsc, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c index 3082a41..c9c9d54 100644 --- a/arch/i386/kernel/tsc.c +++ b/arch/i386/kernel/tsc.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "mach_timer.h" @@ -102,9 +103,6 @@ unsigned long long sched_clock(void) { unsigned long long this_offset; - if (unlikely(custom_sched_clock)) - return (*custom_sched_clock)(); - /* * Fall back to jiffies if there's no TSC available: */ @@ -113,7 +111,7 @@ unsigned long long sched_clock(void) return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); /* read the Time Stamp Counter: */ - rdtscll(this_offset); + get_scheduled_cycles(this_offset); /* return the value in ns */ return cycles_2_ns(this_offset); diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c index 8417f74..556b9a6 100644 --- a/arch/i386/kernel/vmi.c +++ b/arch/i386/kernel/vmi.c @@ -873,7 +873,7 @@ static inline int __init activate_vmi(void) paravirt_ops.setup_boot_clock = vmi_timer_setup_boot_alarm; paravirt_ops.setup_secondary_clock = vmi_timer_setup_secondary_alarm; #endif - custom_sched_clock = vmi_sched_clock; + paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles; } if (!disable_noidle) para_fill(safe_halt, Halt); diff --git a/arch/i386/kernel/vmitime.c b/arch/i386/kernel/vmitime.c index 694aa85..f2aa8fa 100644 --- a/arch/i386/kernel/vmitime.c +++ b/arch/i386/kernel/vmitime.c @@ -172,7 +172,7 @@ int vmi_set_wallclock(unsigned long now) return -1; } -unsigned long long vmi_sched_clock(void) +unsigned long long vmi_get_sched_cycles(void) { return read_available_cycles(); } -- cgit v1.1