OpenCloudOS-Kernel/arch/x86/kernel/pvclock.c

157 lines
3.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* paravirtual clock -- common code used by kvm/xen
*/
#include <linux/clocksource.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/gfp.h>
mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include <linux/memblock.h> @@ @@ - #include <linux/bootmem.h> + #include <linux/memblock.h> [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:09:49 +08:00
#include <linux/memblock.h>
#include <linux/nmi.h>
#include <asm/fixmap.h>
#include <asm/pvclock.h>
#include <asm/vgtod.h>
static u8 valid_flags __read_mostly = 0;
static struct pvclock_vsyscall_time_info *pvti_cpu0_va __read_mostly;
void pvclock_set_flags(u8 flags)
{
valid_flags = flags;
}
unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
{
u64 pv_tsc_khz = 1000000ULL << 32;
do_div(pv_tsc_khz, src->tsc_to_system_mul);
if (src->tsc_shift < 0)
pv_tsc_khz <<= -src->tsc_shift;
else
pv_tsc_khz >>= src->tsc_shift;
return pv_tsc_khz;
}
void pvclock_touch_watchdogs(void)
{
touch_softlockup_watchdog_sync();
clocksource_touch_watchdog();
rcu_cpu_stall_reset();
reset_hung_task_detector();
}
x86, paravirt: Add a global synchronization point for pvclock In recent stress tests, it was found that pvclock-based systems could seriously warp in smp systems. Using ingo's time-warp-test.c, I could trigger a scenario as bad as 1.5mi warps a minute in some systems. (to be fair, it wasn't that bad in most of them). Investigating further, I found out that such warps were caused by the very offset-based calculation pvclock is based on. This happens even on some machines that report constant_tsc in its tsc flags, specially on multi-socket ones. Two reads of the same kernel timestamp at approx the same time, will likely have tsc timestamped in different occasions too. This means the delta we calculate is unpredictable at best, and can probably be smaller in a cpu that is legitimately reading clock in a forward ocasion. Some adjustments on the host could make this window less likely to happen, but still, it pretty much poses as an intrinsic problem of the mechanism. A while ago, I though about using a shared variable anyway, to hold clock last state, but gave up due to the high contention locking was likely to introduce, possibly rendering the thing useless on big machines. I argue, however, that locking is not necessary. We do a read-and-return sequence in pvclock, and between read and return, the global value can have changed. However, it can only have changed by means of an addition of a positive value. So if we detected that our clock timestamp is less than the current global, we know that we need to return a higher one, even though it is not exactly the one we compared to. OTOH, if we detect we're greater than the current time source, we atomically replace the value with our new readings. This do causes contention on big boxes (but big here means *BIG*), but it seems like a good trade off, since it provide us with a time source guaranteed to be stable wrt time warps. After this patch is applied, I don't see a single warp in time during 5 days of execution, in any of the machines I saw them before. Signed-off-by: Glauber Costa <glommer@redhat.com> Acked-by: Zachary Amsden <zamsden@redhat.com> CC: Jeremy Fitzhardinge <jeremy@goop.org> CC: Avi Kivity <avi@redhat.com> CC: Marcelo Tosatti <mtosatti@redhat.com> CC: Zachary Amsden <zamsden@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-05-12 00:17:40 +08:00
static atomic64_t last_value = ATOMIC64_INIT(0);
void pvclock_resume(void)
{
atomic64_set(&last_value, 0);
}
u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
{
unsigned version;
u8 flags;
do {
version = pvclock_read_begin(src);
flags = src->flags;
} while (pvclock_read_retry(src, version));
return flags & valid_flags;
}
u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
{
unsigned version;
u64 ret;
x86, paravirt: Add a global synchronization point for pvclock In recent stress tests, it was found that pvclock-based systems could seriously warp in smp systems. Using ingo's time-warp-test.c, I could trigger a scenario as bad as 1.5mi warps a minute in some systems. (to be fair, it wasn't that bad in most of them). Investigating further, I found out that such warps were caused by the very offset-based calculation pvclock is based on. This happens even on some machines that report constant_tsc in its tsc flags, specially on multi-socket ones. Two reads of the same kernel timestamp at approx the same time, will likely have tsc timestamped in different occasions too. This means the delta we calculate is unpredictable at best, and can probably be smaller in a cpu that is legitimately reading clock in a forward ocasion. Some adjustments on the host could make this window less likely to happen, but still, it pretty much poses as an intrinsic problem of the mechanism. A while ago, I though about using a shared variable anyway, to hold clock last state, but gave up due to the high contention locking was likely to introduce, possibly rendering the thing useless on big machines. I argue, however, that locking is not necessary. We do a read-and-return sequence in pvclock, and between read and return, the global value can have changed. However, it can only have changed by means of an addition of a positive value. So if we detected that our clock timestamp is less than the current global, we know that we need to return a higher one, even though it is not exactly the one we compared to. OTOH, if we detect we're greater than the current time source, we atomically replace the value with our new readings. This do causes contention on big boxes (but big here means *BIG*), but it seems like a good trade off, since it provide us with a time source guaranteed to be stable wrt time warps. After this patch is applied, I don't see a single warp in time during 5 days of execution, in any of the machines I saw them before. Signed-off-by: Glauber Costa <glommer@redhat.com> Acked-by: Zachary Amsden <zamsden@redhat.com> CC: Jeremy Fitzhardinge <jeremy@goop.org> CC: Avi Kivity <avi@redhat.com> CC: Marcelo Tosatti <mtosatti@redhat.com> CC: Zachary Amsden <zamsden@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-05-12 00:17:40 +08:00
u64 last;
u8 flags;
do {
version = pvclock_read_begin(src);
ret = __pvclock_read_cycles(src, rdtsc_ordered());
flags = src->flags;
} while (pvclock_read_retry(src, version));
if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
src->flags &= ~PVCLOCK_GUEST_STOPPED;
pvclock_touch_watchdogs();
}
if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
(flags & PVCLOCK_TSC_STABLE_BIT))
return ret;
x86, paravirt: Add a global synchronization point for pvclock In recent stress tests, it was found that pvclock-based systems could seriously warp in smp systems. Using ingo's time-warp-test.c, I could trigger a scenario as bad as 1.5mi warps a minute in some systems. (to be fair, it wasn't that bad in most of them). Investigating further, I found out that such warps were caused by the very offset-based calculation pvclock is based on. This happens even on some machines that report constant_tsc in its tsc flags, specially on multi-socket ones. Two reads of the same kernel timestamp at approx the same time, will likely have tsc timestamped in different occasions too. This means the delta we calculate is unpredictable at best, and can probably be smaller in a cpu that is legitimately reading clock in a forward ocasion. Some adjustments on the host could make this window less likely to happen, but still, it pretty much poses as an intrinsic problem of the mechanism. A while ago, I though about using a shared variable anyway, to hold clock last state, but gave up due to the high contention locking was likely to introduce, possibly rendering the thing useless on big machines. I argue, however, that locking is not necessary. We do a read-and-return sequence in pvclock, and between read and return, the global value can have changed. However, it can only have changed by means of an addition of a positive value. So if we detected that our clock timestamp is less than the current global, we know that we need to return a higher one, even though it is not exactly the one we compared to. OTOH, if we detect we're greater than the current time source, we atomically replace the value with our new readings. This do causes contention on big boxes (but big here means *BIG*), but it seems like a good trade off, since it provide us with a time source guaranteed to be stable wrt time warps. After this patch is applied, I don't see a single warp in time during 5 days of execution, in any of the machines I saw them before. Signed-off-by: Glauber Costa <glommer@redhat.com> Acked-by: Zachary Amsden <zamsden@redhat.com> CC: Jeremy Fitzhardinge <jeremy@goop.org> CC: Avi Kivity <avi@redhat.com> CC: Marcelo Tosatti <mtosatti@redhat.com> CC: Zachary Amsden <zamsden@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-05-12 00:17:40 +08:00
/*
* Assumption here is that last_value, a global accumulator, always goes
* forward. If we are less than that, we should not be much smaller.
* We assume there is an error marging we're inside, and then the correction
* does not sacrifice accuracy.
*
* For reads: global may have changed between test and return,
* but this means someone else updated poked the clock at a later time.
* We just need to make sure we are not seeing a backwards event.
*
* For updates: last_value = ret is not enough, since two vcpus could be
* updating at the same time, and one of them could be slightly behind,
* making the assumption that last_value always go forward fail to hold.
*/
last = atomic64_read(&last_value);
do {
if (ret < last)
return last;
last = atomic64_cmpxchg(&last_value, last, ret);
} while (unlikely(last != ret));
return ret;
}
void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
struct pvclock_vcpu_time_info *vcpu_time,
struct timespec64 *ts)
{
u32 version;
u64 delta;
struct timespec64 now;
/* get wallclock at system boot */
do {
version = wall_clock->version;
rmb(); /* fetch version before time */
/*
* Note: wall_clock->sec is a u32 value, so it can
* only store dates between 1970 and 2106. To allow
* times beyond that, we need to create a new hypercall
* interface with an extended pvclock_wall_clock structure
* like ARM has.
*/
now.tv_sec = wall_clock->sec;
now.tv_nsec = wall_clock->nsec;
rmb(); /* fetch time before checking version */
} while ((wall_clock->version & 1) || (version != wall_clock->version));
delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */
delta += now.tv_sec * NSEC_PER_SEC + now.tv_nsec;
now.tv_nsec = do_div(delta, NSEC_PER_SEC);
now.tv_sec = delta;
set_normalized_timespec64(ts, now.tv_sec, now.tv_nsec);
}
void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti)
{
WARN_ON(vclock_was_used(VDSO_CLOCKMODE_PVCLOCK));
pvti_cpu0_va = pvti;
}
struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void)
{
return pvti_cpu0_va;
}
EXPORT_SYMBOL_GPL(pvclock_get_pvti_cpu0_va);