xen/cpufreq: introduce new sub-hypercall to propagate CPPC data

In order to provide backward compatibility with existing governors
that represent performance as frequency, like ondemand, the _CPC
table can optionally provide processor frequency range values, Lowest
frequency and Nominal frequency, to let OS use Lowest Frequency/
Performance and Nominal Frequency/Performance as anchor points to
create linear mapping of CPPC performance to CPU frequency.

As Xen is uncapable of parsing the ACPI dynamic table, we'd like to
introduce a new sub-hypercall "XEN_PM_CPPC" to propagate required CPPC
data from dom0 kernel to Xen.
In the according handler set_cppc_pminfo(), we do _CPC and _PSD
sanitization check, as both _PSD and _CPC info are necessary for correctly
initializing cpufreq cores in CPPC mode.
Users shall be warned that if we failed at this point,
no fallback scheme, like legacy P-state could be switched to.

A new flag "XEN_CPPC_INIT" is also introduced for cpufreq core initialised in
CPPC mode. Then all .init flag checking shall be updated to
consider "XEN_CPPC_INIT" too.

We want to bypass construction of px statistic info in cpufreq_statistic_init()
for CPPC mode, while not bypassing cpufreq_statistic_lock initialization for a
good reason. The same check is unnecessary for cpufreq_statistic_exit(),
since it has already been covered by px statistic variable
"cpufreq_statistic_data" check

Signed-off-by: Penny Zheng <Penny.Zheng@amd.com>
Acked-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/platform_hypercall.c

@@ -577,6 +577,11 @@ ret_t do_platform_op(
             break;
         }
 
+        case XEN_PM_CPPC:
+            ret = set_cppc_pminfo(op->u.set_pminfo.id,
+                                  &op->u.set_pminfo.u.cppc_data);
+            break;
+
         default:
             ret = -EINVAL;
             break;

xen/arch/x86/x86_64/cpufreq.c

@@ -54,3 +54,22 @@ int compat_set_px_pminfo(uint32_t acpi_id,
 
     return set_px_pminfo(acpi_id, xen_perf);
 }
+
+int compat_set_cppc_pminfo(unsigned int acpi_id,
+                           const struct compat_processor_cppc *cppc_data)
+
+{
+    struct xen_processor_cppc *xen_cppc;
+    unsigned long xlat_page_current;
+
+    xlat_malloc_init(xlat_page_current);
+
+    xen_cppc = xlat_malloc_array(xlat_page_current,
+                                 struct xen_processor_cppc, 1);
+    if ( unlikely(xen_cppc == NULL) )
+        return -ENOMEM;
+
+    XLAT_processor_cppc(xen_cppc, cppc_data);
+
+    return set_cppc_pminfo(acpi_id, xen_cppc);
+}

xen/arch/x86/x86_64/platform_hypercall.c

@@ -14,6 +14,9 @@ EMIT_FILE;
 #define efi_get_info        efi_compat_get_info
 #define efi_runtime_call(x) efi_compat_runtime_call(x)
 
+#define xen_processor_cppc  compat_processor_cppc
+#define set_cppc_pminfo     compat_set_cppc_pminfo
+
 #define xen_processor_performance compat_processor_performance
 #define set_px_pminfo       compat_set_px_pminfo
 

xen/drivers/acpi/pm-op.c

@@ -91,7 +91,10 @@ static int get_cpufreq_para(struct xen_sysctl_pm_op *op)
     pmpt = processor_pminfo[op->cpuid];
     policy = per_cpu(cpufreq_cpu_policy, op->cpuid);
 
-    if ( !pmpt || !pmpt->perf.states ||
+    if ( !pmpt ||
+         ((pmpt->init & XEN_PX_INIT) && !pmpt->perf.states) ||
+         /* Avoid NULL deref of pmpt->perf.states[] */
+         ((pmpt->init & XEN_CPPC_INIT) && pmpt->perf.state_count) ||
          !policy || !policy->governor )
         return -EINVAL;
 
@@ -351,7 +354,7 @@ int do_pm_op(struct xen_sysctl_pm_op *op)
     case CPUFREQ_PARA:
         if ( !(xen_processor_pmbits & XEN_PROCESSOR_PM_PX) )
             return -ENODEV;
-        if ( !pmpt || !(pmpt->init & XEN_PX_INIT) )
+        if ( !pmpt || !(pmpt->init & (XEN_PX_INIT | XEN_CPPC_INIT)) )
             return -EINVAL;
         break;
     }

xen/drivers/acpi/pmstat.c

@@ -108,6 +108,10 @@ int cpufreq_statistic_init(unsigned int cpu)
     if ( !pmpt )
         return -EINVAL;
 
+    /* Only need to initialize in Px mode */
+    if ( !(pmpt->init & XEN_PX_INIT) )
+        return 0;
+
     spin_lock(cpufreq_statistic_lock);
 
     pxpt = per_cpu(cpufreq_statistic_data, cpu);

xen/drivers/cpufreq/cpufreq.c

@@ -40,6 +40,7 @@
 #include <xen/domain.h>
 #include <xen/cpu.h>
 #include <xen/pmstat.h>
+#include <xen/xvmalloc.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 
@@ -234,6 +235,11 @@ static int get_psd_info(unsigned int cpu, unsigned int *shared_type,
         *domain_info = &processor_pminfo[cpu]->perf.domain_info;
         break;
 
+    case XEN_CPPC_INIT:
+        *shared_type = processor_pminfo[cpu]->cppc_data.shared_type;
+        *domain_info = &processor_pminfo[cpu]->cppc_data.domain_info;
+        break;
+
     default:
         ret = -EINVAL;
         break;
@@ -259,7 +265,7 @@ int cpufreq_add_cpu(unsigned int cpu)
     if ( !processor_pminfo[cpu] || !cpu_online(cpu) )
         return -EINVAL;
 
-    if ( !(processor_pminfo[cpu]->init & XEN_PX_INIT) )
+    if ( !(processor_pminfo[cpu]->init & (XEN_PX_INIT | XEN_CPPC_INIT)) )
         return -EINVAL;
 
     if (!cpufreq_driver.init)
@@ -434,7 +440,7 @@ int cpufreq_del_cpu(unsigned int cpu)
     if ( !processor_pminfo[cpu] || !cpu_online(cpu) )
         return -EINVAL;
 
-    if ( !(processor_pminfo[cpu]->init & XEN_PX_INIT) )
+    if ( !(processor_pminfo[cpu]->init & (XEN_PX_INIT | XEN_CPPC_INIT)) )
         return -EINVAL;
 
     if (!per_cpu(cpufreq_cpu_policy, cpu))
@@ -693,6 +699,120 @@ int acpi_set_pdc_bits(unsigned int acpi_id, XEN_GUEST_HANDLE(uint32) pdc)
     return ret;
 }
 
+static void print_CPPC(const struct xen_processor_cppc *cppc_data)
+{
+    printk("\t_CPC: highest_perf=%u, lowest_perf=%u, "
+           "nominal_perf=%u, lowest_nonlinear_perf=%u, "
+           "nominal_mhz=%uMHz, lowest_mhz=%uMHz\n",
+           cppc_data->cpc.highest_perf, cppc_data->cpc.lowest_perf,
+           cppc_data->cpc.nominal_perf, cppc_data->cpc.lowest_nonlinear_perf,
+           cppc_data->cpc.nominal_mhz, cppc_data->cpc.lowest_mhz);
+}
+
+int set_cppc_pminfo(unsigned int acpi_id,
+                    const struct xen_processor_cppc *cppc_data)
+{
+    int ret = 0, cpu_id;
+    struct processor_pminfo *pm_info;
+
+    cpu_id = get_cpu_id(acpi_id);
+    if ( cpu_id < 0 )
+    {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    if ( cppc_data->pad[0] || cppc_data->pad[1] || cppc_data->pad[2] )
+    {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    if ( cpufreq_verbose )
+        printk("Set CPU%d (ACPI ID %u) CPPC state info:\n",
+               cpu_id, acpi_id);
+
+    pm_info = processor_pminfo[cpu_id];
+    if ( !pm_info )
+    {
+        pm_info = xvzalloc(struct processor_pminfo);
+        if ( !pm_info )
+        {
+            ret = -ENOMEM;
+            goto out;
+        }
+        processor_pminfo[cpu_id] = pm_info;
+    }
+    pm_info->acpi_id = acpi_id;
+    pm_info->id = cpu_id;
+    pm_info->cppc_data = *cppc_data;
+
+    if ( (cppc_data->flags & XEN_CPPC_PSD) &&
+         !check_psd_pminfo(cppc_data->shared_type) )
+    {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    if ( cppc_data->flags & XEN_CPPC_CPC )
+    {
+        if ( cppc_data->cpc.highest_perf == 0 ||
+             cppc_data->cpc.highest_perf > UINT8_MAX ||
+             cppc_data->cpc.nominal_perf == 0 ||
+             cppc_data->cpc.lowest_nonlinear_perf == 0 ||
+             cppc_data->cpc.lowest_perf == 0 ||
+             cppc_data->cpc.lowest_perf >
+                 cppc_data->cpc.lowest_nonlinear_perf ||
+             cppc_data->cpc.lowest_nonlinear_perf >
+                 cppc_data->cpc.nominal_perf ||
+             cppc_data->cpc.nominal_perf > cppc_data->cpc.highest_perf )
+            /*
+             * Right now, Xen doesn't actually use highest_perf/nominal_perf/
+             * lowest_nonlinear_perf/lowest_perf values read from ACPI _CPC
+             * table. Xen reads CPPC capability MSR to get these four values.
+             * So warning is enough.
+             */
+            printk_once(XENLOG_WARNING
+                        "Broken CPPC perf values: lowest(%u), nonlinear_lowest(%u), nominal(%u), highest(%u)\n",
+                        cppc_data->cpc.lowest_perf,
+                        cppc_data->cpc.lowest_nonlinear_perf,
+                        cppc_data->cpc.nominal_perf,
+                        cppc_data->cpc.highest_perf);
+
+        /* lowest_mhz and nominal_mhz are optional value */
+        if ( cppc_data->cpc.nominal_mhz &&
+             cppc_data->cpc.lowest_mhz > cppc_data->cpc.nominal_mhz )
+        {
+            printk_once(XENLOG_WARNING
+                        "Broken CPPC freq values: lowest(%u), nominal(%u)\n",
+                        cppc_data->cpc.lowest_mhz,
+                        cppc_data->cpc.nominal_mhz);
+            /* Re-set with zero values, instead of keeping invalid values */
+            pm_info->cppc_data.cpc.nominal_mhz = 0;
+            pm_info->cppc_data.cpc.lowest_mhz = 0;
+        }
+    }
+
+    if ( cppc_data->flags == (XEN_CPPC_PSD | XEN_CPPC_CPC) )
+    {
+        if ( cpufreq_verbose )
+        {
+            print_PSD(&pm_info->cppc_data.domain_info);
+            print_CPPC(&pm_info->cppc_data);
+        }
+
+        pm_info->init = XEN_CPPC_INIT;
+        ret = cpufreq_cpu_init(cpu_id);
+        if ( ret )
+            printk_once(XENLOG_WARNING
+                        "CPU%d failed amd-cppc mode init; use \"cpufreq=xen\" instead",
+                        cpu_id);
+    }
+
+ out:
+    return ret;
+}
+
 static void cpufreq_cmdline_common_para(struct cpufreq_policy *new_policy)
 {
     if (usr_max_freq)

xen/include/acpi/cpufreq/processor_perf.h

@@ -5,7 +5,8 @@
 #include <public/sysctl.h>
 #include <xen/acpi.h>
 
-#define XEN_PX_INIT 0x80000000U
+#define XEN_CPPC_INIT 0x40000000U
+#define XEN_PX_INIT   0x80000000U
 
 unsigned int powernow_register_driver(void);
 unsigned int get_measured_perf(unsigned int cpu, unsigned int flag);
@@ -43,6 +44,7 @@ struct processor_pminfo {
     uint32_t acpi_id;
     uint32_t id;
     struct processor_performance    perf;
+    struct xen_processor_cppc cppc_data;
 
     uint32_t init;
 };

xen/include/public/platform.h

@@ -363,6 +363,7 @@ DEFINE_XEN_GUEST_HANDLE(xenpf_getidletime_t);
 #define XEN_PM_PX   1
 #define XEN_PM_TX   2
 #define XEN_PM_PDC  3
+#define XEN_PM_CPPC 4
 
 /* Px sub info type */
 #define XEN_PX_PCT   1
@@ -370,6 +371,10 @@ DEFINE_XEN_GUEST_HANDLE(xenpf_getidletime_t);
 #define XEN_PX_PPC   4
 #define XEN_PX_PSD   8
 
+/* CPPC sub info type */
+#define XEN_CPPC_PSD   (1U << 0)
+#define XEN_CPPC_CPC   (1U << 1)
+
 struct xen_power_register {
     uint32_t     space_id;
     uint32_t     bit_width;
@@ -457,6 +462,26 @@ struct xen_processor_performance {
 typedef struct xen_processor_performance xen_processor_performance_t;
 DEFINE_XEN_GUEST_HANDLE(xen_processor_performance_t);
 
+struct xen_processor_cppc {
+    uint8_t flags; /* IN: XEN_CPPC_xxx */
+    uint8_t pad[3];
+    /*
+     * IN: Subset _CPC fields useful for CPPC-compatible cpufreq
+     * driver's initialization
+     */
+    struct {
+        uint32_t highest_perf;
+        uint32_t nominal_perf;
+        uint32_t lowest_nonlinear_perf;
+        uint32_t lowest_perf;
+        uint32_t lowest_mhz;
+        uint32_t nominal_mhz;
+    } cpc;
+    uint32_t shared_type; /* IN: XEN_CPUPERF_SHARED_TYPE_xxx */
+    struct xen_psd_package domain_info; /* IN: _PSD */
+};
+typedef struct xen_processor_cppc xen_processor_cppc_t;
+
 struct xenpf_set_processor_pminfo {
     /* IN variables */
     uint32_t id;    /* ACPI CPU ID */
@@ -465,6 +490,7 @@ struct xenpf_set_processor_pminfo {
         struct xen_processor_power          power;/* Cx: _CST/_CSD */
         struct xen_processor_performance    perf; /* Px: _PPC/_PCT/_PSS/_PSD */
         XEN_GUEST_HANDLE(uint32)            pdc;  /* _PDC */
+        xen_processor_cppc_t                cppc_data; /* CPPC: _CPC and _PSD */
     } u;
 };
 typedef struct xenpf_set_processor_pminfo xenpf_set_processor_pminfo_t;

xen/include/xen/pmstat.h

@@ -7,12 +7,17 @@
 
 int set_px_pminfo(uint32_t acpi_id, struct xen_processor_performance *perf);
 long set_cx_pminfo(uint32_t acpi_id, struct xen_processor_power *power);
+int set_cppc_pminfo(unsigned int acpi_id,
+                    const struct xen_processor_cppc *cppc_data);
 
 #ifdef CONFIG_COMPAT
 struct compat_processor_performance;
 int compat_set_px_pminfo(uint32_t acpi_id, struct compat_processor_performance *perf);
 struct compat_processor_power;
 long compat_set_cx_pminfo(uint32_t acpi_id, struct compat_processor_power *power);
+struct compat_processor_cppc;
+int compat_set_cppc_pminfo(unsigned int acpi_id,
+                           const struct compat_processor_cppc *cppc_data);
 #endif
 
 uint32_t pmstat_get_cx_nr(unsigned int cpu);

xen/include/xlat.lst

@@ -160,6 +160,7 @@
 
 !	pct_register			platform.h
 !	power_register			platform.h
+!	processor_cppc			platform.h
 ?	processor_csd			platform.h
 !	processor_cx			platform.h
 !	processor_flags			platform.h