Commit 6cb9a835 authored by Zachary Amsden's avatar Zachary Amsden Committed by Linus Torvalds
Browse files

[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: default avatarZachary Amsden <zach@vmware.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 7507ba34

arch/i386/kernel/paravirt.c

+2 −0
Original line number Diff line number Diff line
@@ -32,6 +32,7 @@ 
#include <asm/fixmap.h>

#include <asm/apic.h>

#include <asm/tlbflush.h>

#include <asm/timer.h>



/* 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,

arch/i386/kernel/tsc.c

+2 −4
Original line number Diff line number Diff line
@@ -14,6 +14,7 @@ 
#include <asm/delay.h>

#include <asm/tsc.h>

#include <asm/io.h>

#include <asm/timer.h>



#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);

arch/i386/kernel/vmi.c

+1 −1
Original line number Diff line number Diff line
@@ -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);

arch/i386/kernel/vmitime.c

+1 −1
Original line number Diff line number Diff line
@@ -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();

}

include/asm-i386/paravirt.h

+3 −0
Original line number Diff line number Diff line
@@ -94,6 +94,7 @@ struct paravirt_ops 


	u64 (*read_tsc)(void);

	u64 (*read_pmc)(void);

 	u64 (*get_scheduled_cycles)(void);



	void (*load_tr_desc)(void);

	void (*load_gdt)(const struct Xgt_desc_struct *);
@@ -273,6 +274,8 @@ static inline void halt(void) 


#define rdtscll(val) (val = paravirt_ops.read_tsc())



#define get_scheduled_cycles(val) (val = paravirt_ops.get_scheduled_cycles())



#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)



#define rdpmc(counter,low,high) do {				\

CRA Git | Maintained and supported by SUSTech CRA and CCSE