[PATCH v4 05/15] xen/x86: introduce "cpufreq=amd-cppc" xen cmdline

[Penny Zheng <Penny.Zheng@xxxxxxx>]

Users need to set "cpufreq=amd-cppc" in xen cmdline to enable
amd-cppc driver, which selects ACPI Collaborative Performance
and Power Control (CPPC) on supported AMD hardware to provide a
finer grained frequency control mechanism.
`verbose` option can also be included to support verbose print.

When users setting "cpufreq=amd-cppc", a new amd-cppc driver
shall be registered and used. All hooks for amd-cppc driver are missing
until commit "xen/x86: introduce a new amd cppc driver for cpufreq scaling"

Xen is not expected to support both or mixed mode (CPPC & legacy PSS, _PCT,
_PPC) operations, so only one cpufreq driver gets registerd, either amd-cppc
or legacy P-states driver, which is reflected and asserted by the incompatible
flags XEN_PROCESSOR_PM_PX and XEN_PROCESSOR_PM_CPPC.

Signed-off-by: Penny Zheng <Penny.Zheng@xxxxxxx>
---
v1 -> v2:
- Obey to alphabetic sorting and also strict it with CONFIG_AMD
- Remove unnecessary empty comment line
- Use __initconst_cf_clobber for pre-filled structure cpufreq_driver
- Make new switch-case code apply to Hygon CPUs too
- Change ENOSYS with EOPNOTSUPP
- Blanks around binary operator
- Change all amd_/-pstate defined values to amd_/-cppc
---
v2 -> v3
- refactor too long lines
- Make sure XEN_PROCESSOR_PM_PX and XEN_PROCESSOR_PM_CPPC incompatible flags
after cpufreq register registrantion
---
v3 -> v4:
- introduce XEN_PROCESSOR_PM_CPPC in xen internal header
- complement "Hygon" in log message
- remove unnecessary if()
- grow cpufreq_xen_opts[] array
---
 docs/misc/xen-command-line.pandoc         |  7 +-
 xen/arch/x86/acpi/cpufreq/Makefile        |  1 +
 xen/arch/x86/acpi/cpufreq/acpi.c          | 14 +++-
 xen/arch/x86/acpi/cpufreq/amd-cppc.c      | 81 +++++++++++++++++++++++
 xen/arch/x86/acpi/cpufreq/cpufreq.c       | 34 +++++++++-
 xen/arch/x86/platform_hypercall.c         | 11 +++
 xen/drivers/cpufreq/cpufreq.c             | 15 ++++-
 xen/include/acpi/cpufreq/cpufreq.h        |  6 +-
 xen/include/acpi/cpufreq/processor_perf.h |  3 +
 xen/include/public/sysctl.h               |  1 +
 10 files changed, 166 insertions(+), 7 deletions(-)
 create mode 100644 xen/arch/x86/acpi/cpufreq/amd-cppc.c

diff --git a/docs/misc/xen-command-line.pandoc 
b/docs/misc/xen-command-line.pandoc
index 89db6e83be..9ef847a336 100644
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -515,7 +515,7 @@ If set, force use of the performance counters for oprofile, 
rather than detectin
 available support.
 
 ### cpufreq
-> `= none | {{ <boolean> | xen } { 
[:[powersave|performance|ondemand|userspace][,[<maxfreq>]][,[<minfreq>]]] } 
[,verbose]} | dom0-kernel | hwp[:[<hdc>][,verbose]]`
+> `= none | {{ <boolean> | xen } { 
[:[powersave|performance|ondemand|userspace][,[<maxfreq>]][,[<minfreq>]]] } 
[,verbose]} | dom0-kernel | hwp[:[<hdc>][,verbose]] | amd-cppc[:[verbose]]`
 
 > Default: `xen`
 
@@ -526,7 +526,7 @@ choice of `dom0-kernel` is deprecated and not supported by 
all Dom0 kernels.
 * `<maxfreq>` and `<minfreq>` are integers which represent max and min 
processor frequencies
   respectively.
 * `verbose` option can be included as a string or also as `verbose=<integer>`
-  for `xen`.  It is a boolean for `hwp`.
+  for `xen`.  It is a boolean for `hwp` and `amd-cppc`.
 * `hwp` selects Hardware-Controlled Performance States (HWP) on supported Intel
   hardware.  HWP is a Skylake+ feature which provides better CPU power
   management.  The default is disabled.  If `hwp` is selected, but hardware
@@ -534,6 +534,9 @@ choice of `dom0-kernel` is deprecated and not supported by 
all Dom0 kernels.
 * `<hdc>` is a boolean to enable Hardware Duty Cycling (HDC).  HDC enables the
   processor to autonomously force physical package components into idle state.
   The default is enabled, but the option only applies when `hwp` is enabled.
+* `amd-cppc` selects ACPI Collaborative Performance and Power Control (CPPC)
+  on supported AMD hardware to provide finer grained frequency control
+  mechanism. The default is disabled.
 
 There is also support for `;`-separated fallback options:
 `cpufreq=hwp;xen,verbose`.  This first tries `hwp` and falls back to `xen` if
diff --git a/xen/arch/x86/acpi/cpufreq/Makefile 
b/xen/arch/x86/acpi/cpufreq/Makefile
index e7dbe434a8..a2ba34bda0 100644
--- a/xen/arch/x86/acpi/cpufreq/Makefile
+++ b/xen/arch/x86/acpi/cpufreq/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_INTEL) += acpi.o
+obj-$(CONFIG_AMD) += amd-cppc.o
 obj-y += cpufreq.o
 obj-$(CONFIG_INTEL) += hwp.o
 obj-$(CONFIG_AMD) += powernow.o
diff --git a/xen/arch/x86/acpi/cpufreq/acpi.c b/xen/arch/x86/acpi/cpufreq/acpi.c
index 0c25376406..e0cea9425f 100644
--- a/xen/arch/x86/acpi/cpufreq/acpi.c
+++ b/xen/arch/x86/acpi/cpufreq/acpi.c
@@ -13,6 +13,7 @@
 
 #include <xen/errno.h>
 #include <xen/delay.h>
+#include <xen/domain.h>
 #include <xen/param.h>
 #include <xen/types.h>
 
@@ -514,5 +515,16 @@ acpi_cpufreq_driver = {
 
 int __init acpi_cpufreq_register(void)
 {
-    return cpufreq_register_driver(&acpi_cpufreq_driver);
+    int ret;
+
+    ret = cpufreq_register_driver(&acpi_cpufreq_driver);
+    if ( ret )
+        return ret;
+    /*
+     * After cpufreq driver registeration, XEN_PROCESSOR_PM_CPPC
+     * and XEN_PROCESSOR_PM_PX shall become exclusive flags
+     */
+    xen_processor_pmbits &= ~XEN_PROCESSOR_PM_CPPC;
+
+    return ret;
 }
diff --git a/xen/arch/x86/acpi/cpufreq/amd-cppc.c 
b/xen/arch/x86/acpi/cpufreq/amd-cppc.c
new file mode 100644
index 0000000000..8a081e5523
--- /dev/null
+++ b/xen/arch/x86/acpi/cpufreq/amd-cppc.c
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * amd-cppc.c - AMD Processor CPPC Frequency Driver
+ *
+ * Copyright (C) 2025 Advanced Micro Devices, Inc. All Rights Reserved.
+ *
+ * Author: Penny Zheng <penny.zheng@xxxxxxx>
+ *
+ * AMD CPPC cpufreq driver introduces a new CPU performance scaling design
+ * for AMD processors using the ACPI Collaborative Performance and Power
+ * Control (CPPC) feature which provides finer grained frequency control range.
+ */
+
+#include <xen/domain.h>
+#include <xen/init.h>
+#include <xen/param.h>
+#include <acpi/cpufreq/cpufreq.h>
+
+static bool __init amd_cppc_handle_option(const char *s, const char *end)
+{
+    int ret;
+
+    ret = parse_boolean("verbose", s, end);
+    if ( ret >= 0 )
+    {
+        cpufreq_verbose = ret;
+        return true;
+    }
+
+    return false;
+}
+
+int __init amd_cppc_cmdline_parse(const char *s, const char *e)
+{
+    do
+    {
+        const char *end = strpbrk(s, ",;");
+
+        if ( !amd_cppc_handle_option(s, end) )
+        {
+            printk(XENLOG_WARNING
+                   "cpufreq/amd-cppc: option '%.*s' not recognized\n",
+                   (int)((end ?: e) - s), s);
+
+            return -EINVAL;
+        }
+
+        s = end ? end + 1 : NULL;
+    } while ( s && s < e );
+
+    return 0;
+}
+
+static const struct cpufreq_driver __initconst_cf_clobber
+amd_cppc_cpufreq_driver =
+{
+    .name   = XEN_AMD_CPPC_DRIVER_NAME,
+};
+
+int __init amd_cppc_register_driver(void)
+{
+    int ret;
+
+    if ( !cpu_has_cppc )
+    {
+        xen_processor_pmbits &= ~XEN_PROCESSOR_PM_CPPC;
+        return -ENODEV;
+    }
+
+    ret = cpufreq_register_driver(&amd_cppc_cpufreq_driver);
+    if ( ret )
+        return ret;
+
+    /*
+     * After cpufreq driver registeration, XEN_PROCESSOR_PM_CPPC
+     * and XEN_PROCESSOR_PM_PX shall become exclusive flags
+     */
+    xen_processor_pmbits &= ~XEN_PROCESSOR_PM_PX;
+
+    return ret;
+}
diff --git a/xen/arch/x86/acpi/cpufreq/cpufreq.c 
b/xen/arch/x86/acpi/cpufreq/cpufreq.c
index 61e98b67bd..eac1c125a3 100644
--- a/xen/arch/x86/acpi/cpufreq/cpufreq.c
+++ b/xen/arch/x86/acpi/cpufreq/cpufreq.c
@@ -148,6 +148,10 @@ static int __init cf_check cpufreq_driver_init(void)
                 case CPUFREQ_none:
                     ret = 0;
                     break;
+                default:
+                    printk(XENLOG_WARNING
+                           "Unsupported cpufreq driver for vendor Intel\n");
+                    break;
                 }
 
                 if ( ret != -ENODEV )
@@ -157,7 +161,35 @@ static int __init cf_check cpufreq_driver_init(void)
 
         case X86_VENDOR_AMD:
         case X86_VENDOR_HYGON:
-            ret = IS_ENABLED(CONFIG_AMD) ? powernow_register_driver() : 
-ENODEV;
+            if ( !IS_ENABLED(CONFIG_AMD) )
+            {
+                ret = -ENODEV;
+                break;
+            }
+            ret = -ENOENT;
+
+            for ( unsigned int i = 0; i < cpufreq_xen_cnt; i++ )
+            {
+                switch ( cpufreq_xen_opts[i] )
+                {
+                case CPUFREQ_xen:
+                    ret = powernow_register_driver();
+                    break;
+                case CPUFREQ_amd_cppc:
+                    ret = amd_cppc_register_driver();
+                    break;
+                case CPUFREQ_none:
+                    ret = 0;
+                    break;
+                default:
+                    printk(XENLOG_WARNING
+                           "Unsupported cpufreq driver for vendor AMD or 
Hygon\n");
+                    break;
+                }
+
+                if ( ret != -ENODEV )
+                    break;
+            }
             break;
         }
     }
diff --git a/xen/arch/x86/platform_hypercall.c 
b/xen/arch/x86/platform_hypercall.c
index 49717e9ca9..82663011ad 100644
--- a/xen/arch/x86/platform_hypercall.c
+++ b/xen/arch/x86/platform_hypercall.c
@@ -542,6 +542,9 @@ ret_t do_platform_op(
                 ret = -ENOSYS;
                 break;
             }
+            /* Xen doesn't support mixed mode */
+            ASSERT((xen_processor_pmbits & XEN_PROCESSOR_PM_CPPC) == 0);
+
             ret = set_px_pminfo(op->u.set_pminfo.id, &op->u.set_pminfo.u.perf);
             break;
  
@@ -573,6 +576,14 @@ ret_t do_platform_op(
         }
 
         case XEN_PM_CPPC:
+            if ( !(xen_processor_pmbits & XEN_PROCESSOR_PM_CPPC) )
+            {
+                ret = -EOPNOTSUPP;
+                break;
+            }
+            /* Xen doesn't support mixed mode */
+            ASSERT((xen_processor_pmbits & XEN_PROCESSOR_PM_PX) == 0);
+
             ret = set_cppc_pminfo(op->u.set_pminfo.id,
                                   &op->u.set_pminfo.u.cppc_data);
             break;
diff --git a/xen/drivers/cpufreq/cpufreq.c b/xen/drivers/cpufreq/cpufreq.c
index 79c6444116..818668c99c 100644
--- a/xen/drivers/cpufreq/cpufreq.c
+++ b/xen/drivers/cpufreq/cpufreq.c
@@ -65,7 +65,7 @@ LIST_HEAD_READ_MOSTLY(cpufreq_governor_list);
 /* set xen as default cpufreq */
 enum cpufreq_controller cpufreq_controller = FREQCTL_xen;
 
-enum cpufreq_xen_opt __initdata cpufreq_xen_opts[2] = { CPUFREQ_xen,
+enum cpufreq_xen_opt __initdata cpufreq_xen_opts[3] = { CPUFREQ_xen,
                                                         CPUFREQ_none };
 unsigned int __initdata cpufreq_xen_cnt = 1;
 
@@ -90,7 +90,8 @@ static int __init handle_cpufreq_cmdline(enum cpufreq_xen_opt 
option)
 
     if ( cpufreq_opts_contain(option) )
     {
-        const char *cpufreq_opts_str[] = { "CPUFREQ_xen", "CPUFREQ_hwp" };
+        const char *cpufreq_opts_str[] = { "CPUFREQ_xen", "CPUFREQ_hwp",
+                                           "CPUFREQ_amd_cppc" };
 
         printk(XENLOG_WARNING
                "Duplicate cpufreq driver option: %s",
@@ -102,6 +103,9 @@ static int __init handle_cpufreq_cmdline(enum 
cpufreq_xen_opt option)
     cpufreq_xen_opts[cpufreq_xen_cnt++] = option;
     switch ( option )
     {
+    case CPUFREQ_amd_cppc:
+        xen_processor_pmbits |= XEN_PROCESSOR_PM_CPPC;
+        break;
     case CPUFREQ_hwp:
     case CPUFREQ_xen:
         xen_processor_pmbits |= XEN_PROCESSOR_PM_PX;
@@ -168,6 +172,13 @@ static int __init cf_check setup_cpufreq_option(const char 
*str)
             if ( arg[0] && arg[1] )
                 ret = hwp_cmdline_parse(arg + 1, end);
         }
+        else if ( IS_ENABLED(CONFIG_AMD) && choice < 0 &&
+                  !cmdline_strcmp(str, "amd-cppc") )
+        {
+            ret = handle_cpufreq_cmdline(CPUFREQ_amd_cppc);
+            if ( arg[0] && arg[1] )
+                ret = amd_cppc_cmdline_parse(arg + 1, end);
+        }
         else
             ret = -EINVAL;
 
diff --git a/xen/include/acpi/cpufreq/cpufreq.h 
b/xen/include/acpi/cpufreq/cpufreq.h
index a3c84143af..83050c58b2 100644
--- a/xen/include/acpi/cpufreq/cpufreq.h
+++ b/xen/include/acpi/cpufreq/cpufreq.h
@@ -28,8 +28,9 @@ enum cpufreq_xen_opt {
     CPUFREQ_none,
     CPUFREQ_xen,
     CPUFREQ_hwp,
+    CPUFREQ_amd_cppc,
 };
-extern enum cpufreq_xen_opt cpufreq_xen_opts[2];
+extern enum cpufreq_xen_opt cpufreq_xen_opts[3];
 extern unsigned int cpufreq_xen_cnt;
 struct cpufreq_governor;
 
@@ -277,4 +278,7 @@ int set_hwp_para(struct cpufreq_policy *policy,
 
 int acpi_cpufreq_register(void);
 
+int amd_cppc_cmdline_parse(const char *s, const char *e);
+int amd_cppc_register_driver(void);
+
 #endif /* __XEN_CPUFREQ_PM_H__ */
diff --git a/xen/include/acpi/cpufreq/processor_perf.h 
b/xen/include/acpi/cpufreq/processor_perf.h
index f1f4f3138d..1a6591d612 100644
--- a/xen/include/acpi/cpufreq/processor_perf.h
+++ b/xen/include/acpi/cpufreq/processor_perf.h
@@ -5,6 +5,9 @@
 #include <public/sysctl.h>
 #include <xen/acpi.h>
 
+/* ability bits */
+#define XEN_PROCESSOR_PM_CPPC   8
+
 #define XEN_CPPC_INIT 0x40000000U
 #define XEN_PX_INIT   0x80000000U
 
diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
index b0fec271d3..42997252ef 100644
--- a/xen/include/public/sysctl.h
+++ b/xen/include/public/sysctl.h
@@ -423,6 +423,7 @@ struct xen_set_cppc_para {
     uint32_t activity_window;
 };
 
+#define XEN_AMD_CPPC_DRIVER_NAME "amd-cppc"
 #define XEN_HWP_DRIVER_NAME "hwp"
 
 /*
-- 
2.34.1