[PATCH v4 03/15] xen/x86: introduce new sub-hypercall to propagate CPPC data

[Penny Zheng <Penny.Zheng@xxxxxxx>]

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 Norminal frequency, to let OS use Lowest Frequency/
Performance and Nominal Frequency/Performance as anchor points to
create linear mapping of CPPC abstract 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 to differentiate cpufreq core
initialised in Px mode.

Signed-off-by: Penny Zheng <Penny.Zheng@xxxxxxx>
---
v1 -> v2:
- Remove unnecessary figure braces
- Pointer-to-const for print_CPPC and set_cppc_pminfo
- Structure allocation shall use xvzalloc()
- Unnecessary memcpy(), and change it to a (type safe) structure assignment
- Add comment for struct xen_processor_cppc, and keep the chosen fields
in the order _CPC has them
- Obey to alphabetic sorting, and prefix compat structures with ? instead
of !
---
v2 -> v3:
- Trim too long line
- Re-place set_cppc_pminfo() past set_px_pminfo()
- Fix Misra violations: Declaration and definition ought to agree
in parameter names
- Introduce a new flag XEN_PM_CPPC to reflect processor initialised in CPPC
mode
---
v3 -> v4:
- Refactor commit message
- make "acpi_id" unsigned int
- Add warning message when cpufreq_cpu_init() failed only under debug mode
- Expand "struct xen_processor_cppc" to include _PSD and shared type
- add sanity check for ACPI CPPC data
---
 xen/arch/x86/platform_hypercall.c         |   5 +
 xen/drivers/cpufreq/cpufreq.c             | 131 ++++++++++++++++++++--
 xen/include/acpi/cpufreq/processor_perf.h |   4 +-
 xen/include/public/platform.h             |  26 +++++
 xen/include/xen/pmstat.h                  |   2 +
 xen/include/xlat.lst                      |   1 +
 6 files changed, 161 insertions(+), 8 deletions(-)

diff --git a/xen/arch/x86/platform_hypercall.c 
b/xen/arch/x86/platform_hypercall.c
index 90abd3197f..49717e9ca9 100644
--- a/xen/arch/x86/platform_hypercall.c
+++ b/xen/arch/x86/platform_hypercall.c
@@ -572,6 +572,11 @@ 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;
diff --git a/xen/drivers/cpufreq/cpufreq.c b/xen/drivers/cpufreq/cpufreq.c
index b020ccbcf7..e01acc0c2d 100644
--- a/xen/drivers/cpufreq/cpufreq.c
+++ b/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>
 
@@ -205,6 +206,12 @@ static int get_psd_info(uint32_t init, unsigned int cpu,
         if ( domain_info )
             *domain_info = processor_pminfo[cpu]->perf.domain_info;
         break;
+    case XEN_CPPC_INIT:
+        if ( shared_type )
+            *shared_type = processor_pminfo[cpu]->cppc_data.shared_type;
+        if ( domain_info )
+            *domain_info = processor_pminfo[cpu]->cppc_data.domain_info;
+        break;
     default:
         ret = -EINVAL;
         break;
@@ -230,7 +237,7 @@ 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)
@@ -401,7 +408,7 @@ 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))
@@ -497,12 +504,19 @@ static void print_PPC(unsigned int platform_limit)
     printk("\t_PPC: %d\n", platform_limit);
 }
 
-static int check_psd_pminfo(const struct xen_processor_performance *perf)
+static int check_psd_pminfo(const struct xen_processor_performance *perf,
+                            const struct xen_processor_cppc *cppc_data)
 {
+    uint32_t shared_type;
+
+    if ( !perf && !cppc_data )
+        return -EINVAL;
+
+    shared_type = perf ? perf->shared_type : cppc_data->shared_type;
     /* check domain coordination */
-    if ( perf->shared_type != CPUFREQ_SHARED_TYPE_ALL &&
-         perf->shared_type != CPUFREQ_SHARED_TYPE_ANY &&
-         perf->shared_type != CPUFREQ_SHARED_TYPE_HW )
+    if ( shared_type != CPUFREQ_SHARED_TYPE_ALL &&
+         shared_type != CPUFREQ_SHARED_TYPE_ANY &&
+         shared_type != CPUFREQ_SHARED_TYPE_HW )
         return -EINVAL;
 
     return 0;
@@ -589,7 +603,7 @@ int set_px_pminfo(uint32_t acpi_id, struct 
xen_processor_performance *perf)
 
     if ( perf->flags & XEN_PX_PSD )
     {
-        ret = check_psd_pminfo(perf);
+        ret = check_psd_pminfo(perf, NULL);
         if ( ret )
             goto out;
 
@@ -627,6 +641,109 @@ out:
     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, cpuid;
+    struct processor_pminfo *pm_info;
+
+    cpuid = get_cpu_id(acpi_id);
+    if ( cpuid < 0 || !cppc_data )
+    {
+        ret = -EINVAL;
+        goto out;
+    }
+    if ( cpufreq_verbose )
+        printk("Set CPU acpi_id(%u) cpuid(%d) CPPC State info:\n",
+               acpi_id, cpuid);
+
+    pm_info = processor_pminfo[cpuid];
+    if ( !pm_info )
+    {
+        pm_info = xvzalloc(struct processor_pminfo);
+        if ( !pm_info )
+        {
+            ret = -ENOMEM;
+            goto out;
+        }
+        processor_pminfo[cpuid] = pm_info;
+    }
+    pm_info->acpi_id = acpi_id;
+    pm_info->id = cpuid;
+
+    if ( cppc_data->flags & XEN_CPPC_PSD )
+    {
+        ret = check_psd_pminfo(NULL, cppc_data);
+        if ( ret )
+            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.nominal_perf > UINT8_MAX ||
+             cppc_data->cpc.lowest_nonlinear_perf == 0 ||
+             cppc_data->cpc.lowest_nonlinear_perf > UINT8_MAX ||
+             cppc_data->cpc.lowest_perf == 0 ||
+             cppc_data->cpc.lowest_perf > UINT8_MAX ||
+             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 perf values
+             * in ACPI _CPC table, warning is enough.
+             */
+            printk(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.lowest_mhz && cppc_data->cpc.nominal_mhz) &&
+             cppc_data->cpc.lowest_mhz > cppc_data->cpc.nominal_mhz )
+            printk(XENLOG_WARNING
+                   "Broken CPPC freq values: lowest(%u), nominal(%u)\n",
+                   cppc_data->cpc.lowest_mhz,
+                   cppc_data->cpc.nominal_mhz);
+    }
+
+    if ( cppc_data->flags == (XEN_CPPC_PSD | XEN_CPPC_CPC) )
+    {
+        pm_info->cppc_data = *cppc_data;
+        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(cpuid);
+#ifndef NDEBUG
+        if ( ret )
+            printk(XENLOG_WARNING "No fallback scheme could be replaced now");
+#endif
+    }
+
+ out:
+    return ret;
+}
+
 static void cpufreq_cmdline_common_para(struct cpufreq_policy *new_policy)
 {
     if (usr_max_freq)
diff --git a/xen/include/acpi/cpufreq/processor_perf.h 
b/xen/include/acpi/cpufreq/processor_perf.h
index 5f2612b15a..f1f4f3138d 100644
--- a/xen/include/acpi/cpufreq/processor_perf.h
+++ b/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);
@@ -35,6 +36,7 @@ struct processor_pminfo {
     uint32_t acpi_id;
     uint32_t id;
     struct processor_performance    perf;
+    struct xen_processor_cppc cppc_data;
 
     uint32_t init;
 };
diff --git a/xen/include/public/platform.h b/xen/include/public/platform.h
index 67cf5eeabd..0e18a86ab4 100644
--- a/xen/include/public/platform.h
+++ b/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   1
+#define XEN_CPPC_CPC   2
+
 struct xen_power_register {
     uint32_t     space_id;
     uint32_t     bit_width;
@@ -459,6 +464,26 @@ 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; /* flag for CPPC sub info type */
+    /*
+     * 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;
+    struct xen_psd_package domain_info; /* _PSD */
+    /* Coordination type of this processor */
+    uint32_t shared_type;
+};
+typedef struct xen_processor_cppc xen_processor_cppc_t;
+
 struct xenpf_set_processor_pminfo {
     /* IN variables */
     uint32_t id;    /* ACPI CPU ID */
@@ -467,6 +492,7 @@ 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; /* _CPC and _PSD */
     } u;
 };
 typedef struct xenpf_set_processor_pminfo xenpf_set_processor_pminfo_t;
diff --git a/xen/include/xen/pmstat.h b/xen/include/xen/pmstat.h
index 8350403e95..f30286d48e 100644
--- a/xen/include/xen/pmstat.h
+++ b/xen/include/xen/pmstat.h
@@ -7,6 +7,8 @@
 
 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;
diff --git a/xen/include/xlat.lst b/xen/include/xlat.lst
index 3c7b6c6830..d3f87c7cc2 100644
--- a/xen/include/xlat.lst
+++ b/xen/include/xlat.lst
@@ -168,6 +168,7 @@
 !      processor_performance           platform.h
 !      processor_power                 platform.h
 ?      processor_px                    platform.h
+?      processor_cppc                  platform.h
 !      psd_package                     platform.h
 ?      xenpf_enter_acpi_sleep          platform.h
 ?      xenpf_pcpu_version              platform.h
-- 
2.34.1