mirror of
https://github.com/torvalds/linux.git
synced 2024-11-13 23:51:39 +00:00
9e343b467c
{READ,WRITE}_ONCE() cannot guarantee atomicity for arbitrary data sizes. This can be surprising to callers that might incorrectly be expecting atomicity for accesses to aggregate structures, although there are other callers where tearing is actually permissable (e.g. if they are using something akin to sequence locking to protect the access). Linus sayeth: | We could also look at being stricter for the normal READ/WRITE_ONCE(), | and require that they are | | (a) regular integer types | | (b) fit in an atomic word | | We actually did (b) for a while, until we noticed that we do it on | loff_t's etc and relaxed the rules. But maybe we could have a | "non-atomic" version of READ/WRITE_ONCE() that is used for the | questionable cases? The slight snag is that we also have to support 64-bit accesses on 32-bit architectures, as these appear to be widespread and tend to work out ok if either the architecture supports atomic 64-bit accesses (x86, armv7) or if the variable being accesses represents a virtual address and therefore only requires 32-bit atomicity in practice. Take a step in that direction by introducing a variant of 'compiletime_assert_atomic_type()' and use it to check the pointer argument to {READ,WRITE}_ONCE(). Expose __{READ,WRITE}_ONCE() variants which are allowed to tear and convert the one broken caller over to the new macros. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Will Deacon <will@kernel.org>
184 lines
4.1 KiB
C
184 lines
4.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Xen stolen ticks accounting.
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/math64.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/slab.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);
|
|
|
|
static DEFINE_PER_CPU(u64[4], old_runstate_time);
|
|
|
|
/* 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;
|
|
}
|
|
|
|
static void xen_get_runstate_snapshot_cpu_delta(
|
|
struct vcpu_runstate_info *res, unsigned int cpu)
|
|
{
|
|
u64 state_time;
|
|
struct vcpu_runstate_info *state;
|
|
|
|
BUG_ON(preemptible());
|
|
|
|
state = per_cpu_ptr(&xen_runstate, cpu);
|
|
|
|
do {
|
|
state_time = get64(&state->state_entry_time);
|
|
rmb(); /* Hypervisor might update data. */
|
|
*res = __READ_ONCE(*state);
|
|
rmb(); /* Hypervisor might update data. */
|
|
} while (get64(&state->state_entry_time) != state_time ||
|
|
(state_time & XEN_RUNSTATE_UPDATE));
|
|
}
|
|
|
|
static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
|
|
unsigned int cpu)
|
|
{
|
|
int i;
|
|
|
|
xen_get_runstate_snapshot_cpu_delta(res, cpu);
|
|
|
|
for (i = 0; i < 4; i++)
|
|
res->time[i] += per_cpu(old_runstate_time, cpu)[i];
|
|
}
|
|
|
|
void xen_manage_runstate_time(int action)
|
|
{
|
|
static struct vcpu_runstate_info *runstate_delta;
|
|
struct vcpu_runstate_info state;
|
|
int cpu, i;
|
|
|
|
switch (action) {
|
|
case -1: /* backup runstate time before suspend */
|
|
if (unlikely(runstate_delta))
|
|
pr_warn_once("%s: memory leak as runstate_delta is not NULL\n",
|
|
__func__);
|
|
|
|
runstate_delta = kmalloc_array(num_possible_cpus(),
|
|
sizeof(*runstate_delta),
|
|
GFP_ATOMIC);
|
|
if (unlikely(!runstate_delta)) {
|
|
pr_warn("%s: failed to allocate runstate_delta\n",
|
|
__func__);
|
|
return;
|
|
}
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
xen_get_runstate_snapshot_cpu_delta(&state, cpu);
|
|
memcpy(runstate_delta[cpu].time, state.time,
|
|
sizeof(runstate_delta[cpu].time));
|
|
}
|
|
|
|
break;
|
|
|
|
case 0: /* backup runstate time after resume */
|
|
if (unlikely(!runstate_delta)) {
|
|
pr_warn("%s: cannot accumulate runstate time as runstate_delta is NULL\n",
|
|
__func__);
|
|
return;
|
|
}
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
for (i = 0; i < 4; i++)
|
|
per_cpu(old_runstate_time, cpu)[i] +=
|
|
runstate_delta[cpu].time[i];
|
|
}
|
|
|
|
break;
|
|
|
|
default: /* do not accumulate runstate time for checkpointing */
|
|
break;
|
|
}
|
|
|
|
if (action != -1 && runstate_delta) {
|
|
kfree(runstate_delta);
|
|
runstate_delta = NULL;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Runstate accounting
|
|
*/
|
|
void xen_get_runstate_snapshot(struct vcpu_runstate_info *res)
|
|
{
|
|
xen_get_runstate_snapshot_cpu(res, smp_processor_id());
|
|
}
|
|
|
|
/* 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;
|
|
}
|
|
|
|
u64 xen_steal_clock(int cpu)
|
|
{
|
|
struct vcpu_runstate_info state;
|
|
|
|
xen_get_runstate_snapshot_cpu(&state, cpu);
|
|
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,
|
|
xen_vcpu_nr(cpu), &area))
|
|
BUG();
|
|
}
|
|
|
|
void __init xen_time_setup_guest(void)
|
|
{
|
|
bool xen_runstate_remote;
|
|
|
|
xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
|
|
VMASST_TYPE_runstate_update_flag);
|
|
|
|
pv_ops.time.steal_clock = xen_steal_clock;
|
|
|
|
static_key_slow_inc(¶virt_steal_enabled);
|
|
if (xen_runstate_remote)
|
|
static_key_slow_inc(¶virt_steal_rq_enabled);
|
|
}
|