mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 21:57:43 +00:00
ecb23dc6f2
The pv_time_ops structure contains a function pointer for the "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 uses its own mechanism to account for the "stolen" time a thread wasn't able to run due to hypervisor scheduling. Add support in Xen arch independent time handling for this feature by moving it out of the arm arch into drivers/xen and remove the x86 Xen hack. Signed-off-by: Juergen Gross <jgross@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Reviewed-by: Stefano Stabellini <sstabellini@kernel.org> Signed-off-by: David Vrabel <david.vrabel@citrix.com>
108 lines
2.4 KiB
C
108 lines
2.4 KiB
C
/*
|
|
* Xen stolen ticks accounting.
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/math64.h>
|
|
#include <linux/gfp.h>
|
|
|
|
#include <asm/paravirt.h>
|
|
#include <asm/xen/hypervisor.h>
|
|
#include <asm/xen/hypercall.h>
|
|
|
|
#include <xen/events.h>
|
|
#include <xen/features.h>
|
|
#include <xen/interface/xen.h>
|
|
#include <xen/interface/vcpu.h>
|
|
#include <xen/xen-ops.h>
|
|
|
|
/* runstate info updated by Xen */
|
|
static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
|
|
|
|
/* return an consistent snapshot of 64-bit time/counter value */
|
|
static u64 get64(const u64 *p)
|
|
{
|
|
u64 ret;
|
|
|
|
if (BITS_PER_LONG < 64) {
|
|
u32 *p32 = (u32 *)p;
|
|
u32 h, l, h2;
|
|
|
|
/*
|
|
* Read high then low, and then make sure high is
|
|
* still the same; this will only loop if low wraps
|
|
* and carries into high.
|
|
* XXX some clean way to make this endian-proof?
|
|
*/
|
|
do {
|
|
h = READ_ONCE(p32[1]);
|
|
l = READ_ONCE(p32[0]);
|
|
h2 = READ_ONCE(p32[1]);
|
|
} while(h2 != h);
|
|
|
|
ret = (((u64)h) << 32) | l;
|
|
} else
|
|
ret = READ_ONCE(*p);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Runstate accounting
|
|
*/
|
|
void xen_get_runstate_snapshot(struct vcpu_runstate_info *res)
|
|
{
|
|
u64 state_time;
|
|
struct vcpu_runstate_info *state;
|
|
|
|
BUG_ON(preemptible());
|
|
|
|
state = this_cpu_ptr(&xen_runstate);
|
|
|
|
/*
|
|
* The runstate info is always updated by the hypervisor on
|
|
* the current CPU, so there's no need to use anything
|
|
* stronger than a compiler barrier when fetching it.
|
|
*/
|
|
do {
|
|
state_time = get64(&state->state_entry_time);
|
|
*res = READ_ONCE(*state);
|
|
} while (get64(&state->state_entry_time) != state_time);
|
|
}
|
|
|
|
/* return true when a vcpu could run but has no real cpu to run on */
|
|
bool xen_vcpu_stolen(int vcpu)
|
|
{
|
|
return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
|
|
}
|
|
|
|
static u64 xen_steal_clock(int cpu)
|
|
{
|
|
struct vcpu_runstate_info state;
|
|
|
|
BUG_ON(cpu != smp_processor_id());
|
|
xen_get_runstate_snapshot(&state);
|
|
return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
|
|
}
|
|
|
|
void xen_setup_runstate_info(int cpu)
|
|
{
|
|
struct vcpu_register_runstate_memory_area area;
|
|
|
|
area.addr.v = &per_cpu(xen_runstate, cpu);
|
|
|
|
if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
|
|
cpu, &area))
|
|
BUG();
|
|
}
|
|
|
|
void __init xen_time_setup_guest(void)
|
|
{
|
|
pv_time_ops.steal_clock = xen_steal_clock;
|
|
|
|
static_key_slow_inc(¶virt_steal_enabled);
|
|
/*
|
|
* We can't set paravirt_steal_rq_enabled as this would require the
|
|
* capability to read another cpu's runstate info.
|
|
*/
|
|
}
|