Hi,
>>> (1) Use this patch (with alignment issue fixed of course).
>>> (2) Do a full kvmclock implementation. Feels a bit like overkill.
>>> (3) SeaBIOS can fallback to the PIT for timing on machines which
>>> have no TSC. We could do that too in case we detect kvm ...
>>
>> What sort of timeouts are these? If seconds, maybe the rtc would be best.
>
> I vote for 3 so nobody has to maintain kvmclock code in SeaBIOS and Gerd
> can fix the in-kernel PIT issues with GRUB (see Michaels message) while testing.
(2) turned out to be not too bad when taking a shortcut: Go through an
enable/disable cycle each time we read the clock, then just grab
system_time. Not that efficient, but should be ok for seabios. Usually
it checks the clock when sitting around idle, waiting for something to
happen. And it simplifies the implementation alot as we can just skip
all the tsc frequency & delta calculations.
Draft patch attached. Comments?
cheers,
Gerd
>From e42d62e90ae4b8a00413a0665d4022069154a516 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@xxxxxxxxxx>
Date: Thu, 9 Aug 2012 13:26:18 +0200
Subject: [PATCH] kvmclock clocksource
Signed-off-by: Gerd Hoffmann <kraxel@xxxxxxxxxx>
---
Makefile | 4 +-
src/clock.c | 13 +++++++++++
src/paravirt.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
src/paravirt.h | 3 ++
4 files changed, 83 insertions(+), 2 deletions(-)
diff --git a/Makefile b/Makefile
index 72ee152..b692a96 100644
--- a/Makefile
+++ b/Makefile
@@ -13,11 +13,11 @@ SRCBOTH=misc.c stacks.c pmm.c output.c util.c block.c floppy.c ata.c mouse.c \
pnpbios.c pirtable.c vgahooks.c ramdisk.c pcibios.c blockcmd.c \
usb.c usb-uhci.c usb-ohci.c usb-ehci.c usb-hid.c usb-msc.c \
virtio-ring.c virtio-pci.c virtio-blk.c virtio-scsi.c apm.c ahci.c \
- usb-uas.c lsi-scsi.c esp-scsi.c
+ usb-uas.c lsi-scsi.c esp-scsi.c paravirt.c
SRC16=$(SRCBOTH) system.c disk.c font.c
SRC32FLAT=$(SRCBOTH) post.c shadow.c memmap.c coreboot.c boot.c \
acpi.c smm.c mptable.c smbios.c pciinit.c optionroms.c mtrr.c \
- lzmadecode.c bootsplash.c jpeg.c usb-hub.c paravirt.c \
+ lzmadecode.c bootsplash.c jpeg.c usb-hub.c \
biostables.c xen.c bmp.c romfile.c
SRC32SEG=util.c output.c pci.c pcibios.c apm.c stacks.c
diff --git a/src/clock.c b/src/clock.c
index 69e9f17..15921fa 100644
--- a/src/clock.c
+++ b/src/clock.c
@@ -13,6 +13,7 @@
#include "bregs.h" // struct bregs
#include "biosvar.h" // GET_GLOBAL
#include "usb-hid.h" // usb_check_event
+#include "paravirt.h" // kvm clock
// RTC register flags
#define RTC_A_UIP 0x80
@@ -64,6 +65,7 @@
u32 cpu_khz VAR16VISIBLE;
u8 no_tsc VAR16VISIBLE;
+u8 use_kvmclock VAR16VISIBLE;
static void
calibrate_tsc(void)
@@ -80,6 +82,15 @@ calibrate_tsc(void)
return;
}
+ if (kvm_para_available()) {
+ u32 hz = kvmclock_init();
+ if (hz != 0) {
+ SET_GLOBAL(use_kvmclock, 1);
+ SET_GLOBAL(cpu_khz, hz / 1000);
+ return;
+ }
+ }
+
// Setup "timer2"
u8 orig = inb(PORT_PS2_CTRLB);
outb((orig & ~PPCB_SPKR) | PPCB_T2GATE, PORT_PS2_CTRLB);
@@ -134,6 +145,8 @@ get_tsc(void)
{
if (unlikely(GET_GLOBAL(no_tsc)))
return emulate_tsc();
+ if (unlikely(GET_GLOBAL(use_kvmclock)))
+ return kvmclock_get();
return rdtscll();
}
diff --git a/src/paravirt.c b/src/paravirt.c
index 2a98d53..07aa926 100644
--- a/src/paravirt.c
+++ b/src/paravirt.c
@@ -12,6 +12,7 @@
#include "ioport.h" // outw
#include "paravirt.h" // qemu_cfg_port_probe
#include "smbios.h" // struct smbios_structure_header
+#include "biosvar.h" // GET_GLOBAL
int qemu_cfg_present;
@@ -346,3 +347,67 @@ void qemu_cfg_romfile_setup(void)
dprintf(3, "Found fw_cfg file: %s (size=%d)\n", file->name, file->size);
}
}
+
+#define KVM_CPUID_SIGNATURE 0x40000000
+#define KVM_CPUID_FEATURES 0x40000001
+#define KVM_FEATURE_CLOCKSOURCE 0
+#define KVM_FEATURE_CLOCKSOURCE2 3
+#define MSR_KVM_SYSTEM_TIME 0x12
+#define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
+
+struct pvclock_vcpu_time_info {
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 flags;
+ u8 pad[2];
+} PACKED;
+
+/* kvmclock system time runs with nanoseconds */
+#define KVM_SYSTIME_HZ 1000000000
+
+u32 kvm_systime_msr VAR16VISIBLE;
+
+static void kvmclock_fetch(struct pvclock_vcpu_time_info *time)
+{
+ u32 addr = (u32)MAKE_FLATPTR(GET_SEG(SS), time);
+ u32 msr = GET_GLOBAL(kvm_systime_msr);
+
+ memset(time, 0, sizeof(*time));
+ wrmsr(msr, addr | 1);
+ wrmsr(msr, 0);
+}
+
+u64 kvmclock_get(void)
+{
+ struct pvclock_vcpu_time_info time;
+
+ kvmclock_fetch(&time);
+ return time.system_time;
+}
+
+u32 kvmclock_init(void)
+{
+ u32 eax, ebx, ecx, edx;
+ struct pvclock_vcpu_time_info time;
+
+ cpuid(KVM_CPUID_FEATURES, &eax, &ebx, &ecx, &edx);
+ if (eax & KVM_FEATURE_CLOCKSOURCE2) {
+ SET_GLOBAL(kvm_systime_msr, MSR_KVM_SYSTEM_TIME_NEW);
+ } else if (eax & KVM_FEATURE_CLOCKSOURCE) {
+ SET_GLOBAL(kvm_systime_msr, MSR_KVM_SYSTEM_TIME);
+ } else {
+ return 0;
+ }
+
+ kvmclock_fetch(&time);
+ if (time.version < 2 || time.tsc_to_system_mul == 0)
+ return 0;
+
+ dprintf(1, "Using kvmclock, msr 0x%x\n",
+ GET_GLOBAL(kvm_systime_msr));
+ return KVM_SYSTIME_HZ;
+}
diff --git a/src/paravirt.h b/src/paravirt.h
index a284c41..64ed3d8 100644
--- a/src/paravirt.h
+++ b/src/paravirt.h
@@ -28,6 +28,9 @@ static inline int kvm_para_available(void)
return 0;
}
+extern u64 kvmclock_get(void);
+extern u32 kvmclock_init(void);
+
#define QEMU_CFG_SIGNATURE 0x00
#define QEMU_CFG_ID 0x01
#define QEMU_CFG_UUID 0x02
--
1.7.1
