On Tuesday 11 April 2006 04:25 am, Keir Fraser wrote:
> On 11 Apr 2006, at 01:05, Matt T. Yourst wrote:
> > Note that I only implemented this for powernow-k8 right now, since
> > that's the
> > only hardware I could test it on. It's very obvious how to adapt it to
> > the
> > other cpufreq drivers, by just replacing rdmsr and wrmsr with the Xen
> > wrapper
> > versions I provided, and adding in the setcpufreq hypercall at the end.
>
> All this stuff should be done by emulating the MSR writes in
> emulate_privileged_op() in arch/x86/traps.c. This will avoid any
> modification of Linux at all. Currently there's only simple filtering
> of MSR write attempts, but picking up on cpu-freq MSR accesses on e.g.,
> AMD systems and also resync'ing the local clock would not be difficult.
>
Here's a patch that does just that, without modifying the guest kernel.
It seems to work correctly on my machine, and doesn't freeze up or lose
interrupts like before (at least no log messages or visible latency issues).
There was one case where the keyboard response got extremely slow, but
everything else seemed to continue working (i.e. video played in the
background without stalls). Restarting powersaved (the SuSE daemon that
drives cpufreq) seemed to restore normal performance, so maybe it just needed
to be kicked between frequencies to resync the keyboard timing.
Could you please look over the code and make sure there's nothing I missed
that could cause it to be unstable in corner cases? Locking may need to be
added since I haven't tested this on an SMP system and I don't know how Xen
would cope with frequency changes here.
I can add support from the Intel cpufreq drivers (speedstep and centrino), but
someone else with the appropriate hardware will have to test it if I do.
- Matt
diff -r 886594fa3aef xen/arch/x86/time.c
--- a/xen/arch/x86/time.c Sat Apr 8 12:10:04 2006 +0100
+++ b/xen/arch/x86/time.c Tue Apr 11 22:38:41 2006 -0400
@@ -914,6 +915,144 @@ void __init early_time_init(void)
setup_irq(0, &irq0);
}
+/*
+ * Frequency Scaling Support
+ *
+ * These functions are called from emulate_privileged_op
+ * in response to the MSR writes that control core frequency
+ * and voltage on various CPU types.
+ *
+ * We identify only those writes that alter the frequency
+ * itself (i.e. between raising or lowering the voltage
+ * appropriately) and make sure that the requested frequency
+ * is different from the current frequency. In this case
+ * we read the appropriate status MSR until the frequency
+ * stabilizes, then recalibrate all hypervisor timing
+ * variables to the new frequency as indicated in the MSR.
+ *
+ * The frequency change is effective on the CPU this code
+ * is called on: it's the responsibility of the guest OS
+ * to only write the virtual MSR on the target CPU context.
+ *
+ * No modifications to the guest OS cpufreq drivers are
+ * needed as long as support is provided below for the
+ * corresponding CPU type.
+ */
+
+/*
+ * AMD Athlon 64 / Opteron Support (from powernow-k8 driver):
+ */
+
+/*
+ * According to the AMD manuals, the following formula
+ * always converts an FID to the actual frequency,
+ * based on increments of 100 MHz (200 MHz steps):
+ *
+ * mhz = 800 + 100*fid
+ *
+ * Technically the BIOS is supposed to provide this
+ * table (so matching voltages can be found), but
+ * the frequency part is fixed for all K8 cores,
+ * so we just hard code the following formula:
+ */
+static inline int k8_fid_to_mhz(int fid) {
+ return 800 + 100*fid;
+}
+
+int handle_k8_fidvid_status_msr_read(u32* lo, u32* hi) {
+ /* This will return -1 if the processor isn't a K8: */
+ return rdmsr_safe(MSR_FIDVID_STATUS, *lo, *hi);
+}
+
+static int k8_fidvid_wait(void) {
+ u32 lo, hi;
+ u32 i = 0;
+
+ DPRINTK("k8_fidvid_wait: waiting for frequency and voltage to
stabilize...");
+
+ do {
+ if (i++ > 10000) {
+ printk("k8_vidfid_wait: Excessive wait time for vid/fid to
stabilize\n");
+ return -1;
+ }
+ rdmsr_safe(MSR_FIDVID_STATUS, lo, hi);
+ } while (lo & MSR_S_LO_CHANGE_PENDING);
+
+ DPRINTK("OK: new fid %d\n", lo & MSR_S_LO_CHANGE_PENDING);
+
+ return lo & MSR_S_LO_CURRENT_FID;
+}
+
+#if 0
+#undef DPRINTK
+#define DPRINTK printk
+#endif
+
+int handle_k8_fidvid_ctl_msr_write(u32 lo, u32 hi) {
+ int rc;
+ u32 oldlo, oldhi;
+ int oldfid, newfid;
+ int mhz;
+ unsigned int cpu = smp_processor_id();
+ // unsigned long flags;
+ s_time_t now;
+
+ DPRINTK("fidvid_ctl: requested msr write 0x%08x:0x%08x\n", hi, lo);
+
+ rc = rdmsr_safe(MSR_FIDVID_STATUS, oldlo, oldhi);
+ /* This will return -1 if the processor isn't a K8: */
+ if (rc) return rc;
+
+ oldfid = (oldlo & MSR_S_LO_CURRENT_FID);
+ newfid = (lo & MSR_C_LO_NEW_FID);
+
+ if (oldfid != newfid) {
+ DPRINTK("fidvid_ctl: moving from old fid %d to new fid %d\n", oldfid,
newfid);
+ } else {
+ DPRINTK("fidvid_ctl: same fid %d\n", oldfid);
+ }
+
+ DPRINTK("fidvid_ctl: writing MSR 0x%08x with 0x%08x:0x%08x...\n",
MSR_FIDVID_CTL, hi, lo);
+
+ rc = wrmsr_safe(MSR_FIDVID_CTL, lo, hi);
+ if (rc) return rc;
+
+ if (oldfid == newfid) return 0;
+
+ /* Only do the stabilization wait if we're changing the frequency */
+ /* For voltage changes, the OS will do this itself */
+
+ newfid = k8_fidvid_wait();
+ /* excessive wait? abort the change and let guest kernel figure it out */
+ if (newfid < 0) return 0;
+
+ DPRINTK("fidvid_ctl: recalibrating TSC...");
+
+ mhz = k8_fid_to_mhz(newfid);
+ DPRINTK("%d MHz\n", mhz);
+
+ cpu_khz = mhz * 1000;
+ set_time_scale(&cpu_time[smp_processor_id()].tsc_scale, mhz * 1000000);
+
+ DPRINTK("fidvid_ctl: resetting timestamps...");
+
+ rdtscll(cpu_time[cpu].local_tsc_stamp);
+ now = read_platform_stime();
+
+ cpu_time[cpu].stime_master_stamp = now;
+ cpu_time[cpu].stime_local_stamp = now;
+
+ DPRINTK("OK\n");
+
+ DPRINTK("fidvid_ctl: recalibrating timers...");
+
+ local_time_calibration(NULL);
+ __update_vcpu_system_time(current);
+ DPRINTK("OK\n");
+
+ return 0;
+}
+
void send_timer_event(struct vcpu *v)
{
send_guest_vcpu_virq(v, VIRQ_TIMER);
diff -r 886594fa3aef xen/arch/x86/traps.c
--- a/xen/arch/x86/traps.c Sat Apr 8 12:10:04 2006 +0100
+++ b/xen/arch/x86/traps.c Tue Apr 11 22:38:41 2006 -0400
@@ -1131,6 +1131,16 @@ static int emulate_privileged_op(struct
((u64)regs->edx << 32) | regs->eax;
break;
#endif
+ case MSR_FIDVID_CTL: {
+ extern int handle_k8_fidvid_ctl_msr_write(u32 lo, u32 hi);
+ /* domU is never allowed to mess with core frequencies and
voltages */
+ if (!IS_PRIV(current->domain))
+ break;
+ if (handle_k8_fidvid_ctl_msr_write(regs->eax, regs->edx))
+ goto fail;
+ break;
+ }
+
default:
if ( (rdmsr_safe(regs->ecx, l, h) != 0) ||
(regs->eax != l) || (regs->edx != h) )
@@ -1162,6 +1172,14 @@ static int emulate_privileged_op(struct
if ( rdmsr_safe(regs->ecx, regs->eax, regs->edx) )
goto fail;
break;
+
+ case MSR_FIDVID_STATUS: {
+ extern int handle_k8_fidvid_status_msr_read(u32* lo, u32* hi);
+ if (handle_k8_fidvid_status_msr_read((u32*)®s->eax,
(u32*)®s->edx))
+ goto fail;
+ break;
+ }
+
default:
/* Everyone can read the MSR space. */
/*DPRINTK("Domain attempted RDMSR %p.\n", _p(regs->ecx));*/
diff -r 886594fa3aef xen/include/asm-x86/msr.h
--- a/xen/include/asm-x86/msr.h Sat Apr 8 12:10:04 2006 +0100
+++ b/xen/include/asm-x86/msr.h Tue Apr 11 22:38:41 2006 -0400
@@ -137,6 +137,37 @@ static inline void wrmsrl(unsigned int m
#define EFER_LMA (1<<_EFER_LMA)
#define EFER_NX (1<<_EFER_NX)
#define EFER_SVME (1<<_EFER_SVME)
+
+/* Model Specific Registers for K8 p-state transitions. MSRs are 64-bit. For
*/
+/* writes (wrmsr - opcode 0f 30), the register number is placed in ecx, and
*/
+/* the value to write is placed in edx:eax. For reads (rdmsr - opcode 0f 32),
*/
+/* the register number is placed in ecx, and the data is returned in edx:eax.
*/
+
+#define MSR_FIDVID_CTL 0xc0010041
+#define MSR_FIDVID_STATUS 0xc0010042
+
+/* Field definitions within the FID VID Low Control MSR : */
+#define MSR_C_LO_INIT_FID_VID 0x00010000
+#define MSR_C_LO_NEW_VID 0x00003f00
+#define MSR_C_LO_NEW_FID 0x0000003f
+#define MSR_C_LO_VID_SHIFT 8
+
+/* Field definitions within the FID VID High Control MSR : */
+#define MSR_C_HI_STP_GNT_TO 0x000fffff
+
+/* Field definitions within the FID VID Low Status MSR : */
+#define MSR_S_LO_CHANGE_PENDING 0x80000000 /* cleared when completed */
+#define MSR_S_LO_MAX_RAMP_VID 0x3f000000
+#define MSR_S_LO_MAX_FID 0x003f0000
+#define MSR_S_LO_START_FID 0x00003f00
+#define MSR_S_LO_CURRENT_FID 0x0000003f
+
+/* Field definitions within the FID VID High Status MSR : */
+#define MSR_S_HI_MIN_WORKING_VID 0x3f000000
+#define MSR_S_HI_MAX_WORKING_VID 0x003f0000
+#define MSR_S_HI_START_VID 0x00003f00
+#define MSR_S_HI_CURRENT_VID 0x0000003f
+#define MSR_C_HI_STP_GNT_BENIGN 0x00000001
/* Intel MSRs. Some also available on other CPUs */
#define MSR_IA32_PLATFORM_ID 0x17
-------------------------------------------------------
Matt T. Yourst yourst@xxxxxxxxxxxxxxxxx
Binghamton University, Department of Computer Science
-------------------------------------------------------
xen-cpufreq-amd-powernow-k8.diff
Description: Text Data
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home