[PATCH v2 03/11] 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. Actual implmentation will be introduced
in the following commits.

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
---
 docs/misc/xen-command-line.pandoc    |  8 +++-
 xen/arch/x86/acpi/cpufreq/Makefile   |  1 +
 xen/arch/x86/acpi/cpufreq/amd-cppc.c | 64 ++++++++++++++++++++++++++++
 xen/arch/x86/acpi/cpufreq/cpufreq.c  | 32 +++++++++++++-
 xen/arch/x86/platform_hypercall.c    |  6 +++
 xen/drivers/cpufreq/cpufreq.c        | 13 +++++-
 xen/include/acpi/cpufreq/cpufreq.h   |  4 ++
 xen/include/public/platform.h        |  1 +
 xen/include/public/sysctl.h          |  1 +
 9 files changed, 125 insertions(+), 5 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 9bbd00baef..78cfb8a02e 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 +534,10 @@ 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. If `amd-cppc` is selected, but hardware support
+  is not available, Xen will fallback to cpufreq=xen.
 
 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/amd-cppc.c 
b/xen/arch/x86/acpi/cpufreq/amd-cppc.c
new file mode 100644
index 0000000000..2dca4a00f3
--- /dev/null
+++ b/xen/arch/x86/acpi/cpufreq/amd-cppc.c
@@ -0,0 +1,64 @@
+/* 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/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 : end;
+    } 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)
+{
+    if ( !cpu_has_cppc )
+        return -ENODEV;
+
+    return cpufreq_register_driver(&amd_cppc_cpufreq_driver);
+}
diff --git a/xen/arch/x86/acpi/cpufreq/cpufreq.c 
b/xen/arch/x86/acpi/cpufreq/cpufreq.c
index 61e98b67bd..4bcaca1a01 100644
--- a/xen/arch/x86/acpi/cpufreq/cpufreq.c
+++ b/xen/arch/x86/acpi/cpufreq/cpufreq.c
@@ -148,6 +148,9 @@ 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 +160,34 @@ 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\n");
+                    break;
+                }
+
+                if ( ret != -ENODEV )
+                    break;
+            }
             break;
         }
     }
diff --git a/xen/arch/x86/platform_hypercall.c 
b/xen/arch/x86/platform_hypercall.c
index 735c71b0e7..3d10827930 100644
--- a/xen/arch/x86/platform_hypercall.c
+++ b/xen/arch/x86/platform_hypercall.c
@@ -573,6 +573,12 @@ ret_t do_platform_op(
         }
 
         case XEN_PM_CPPC:
+            if ( !(xen_processor_pmbits & XEN_PROCESSOR_PM_CPPC) )
+            {
+                ret = -EOPNOTSUPP;
+                break;
+            }
+
             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 f5e8bfa09e..c0c6dc4c42 100644
--- a/xen/drivers/cpufreq/cpufreq.c
+++ b/xen/drivers/cpufreq/cpufreq.c
@@ -85,7 +85,7 @@ static int __init cf_check setup_cpufreq_option(const char 
*str)
 
     if ( choice < 0 && !cmdline_strcmp(str, "dom0-kernel") )
     {
-        xen_processor_pmbits &= ~XEN_PROCESSOR_PM_PX;
+        xen_processor_pmbits &= ~(XEN_PROCESSOR_PM_PX | XEN_PROCESSOR_PM_CPPC);
         cpufreq_controller = FREQCTL_dom0_kernel;
         opt_dom0_vcpus_pin = 1;
         return 0;
@@ -93,7 +93,7 @@ static int __init cf_check setup_cpufreq_option(const char 
*str)
 
     if ( choice == 0 || !cmdline_strcmp(str, "none") )
     {
-        xen_processor_pmbits &= ~XEN_PROCESSOR_PM_PX;
+        xen_processor_pmbits &= ~(XEN_PROCESSOR_PM_PX | XEN_PROCESSOR_PM_CPPC);
         cpufreq_controller = FREQCTL_none;
         return 0;
     }
@@ -131,6 +131,15 @@ 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 ( choice < 0 && !cmdline_strcmp(str, "amd-cppc") )
+        {
+            xen_processor_pmbits |= XEN_PROCESSOR_PM_CPPC;
+            cpufreq_controller = FREQCTL_xen;
+            cpufreq_xen_opts[cpufreq_xen_cnt++] = CPUFREQ_amd_cppc;
+            ret = 0;
+            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 3f1b05a02e..a6fb10ea27 100644
--- a/xen/include/acpi/cpufreq/cpufreq.h
+++ b/xen/include/acpi/cpufreq/cpufreq.h
@@ -28,6 +28,7 @@ enum cpufreq_xen_opt {
     CPUFREQ_none,
     CPUFREQ_xen,
     CPUFREQ_hwp,
+    CPUFREQ_amd_cppc,
 };
 extern enum cpufreq_xen_opt cpufreq_xen_opts[2];
 extern unsigned int cpufreq_xen_cnt;
@@ -267,4 +268,7 @@ 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/public/platform.h b/xen/include/public/platform.h
index b8daa8fc42..11d30c894e 100644
--- a/xen/include/public/platform.h
+++ b/xen/include/public/platform.h
@@ -357,6 +357,7 @@ DEFINE_XEN_GUEST_HANDLE(xenpf_getidletime_t);
 #define XEN_PROCESSOR_PM_CX    1
 #define XEN_PROCESSOR_PM_PX    2
 #define XEN_PROCESSOR_PM_TX    4
+#define XEN_PROCESSOR_PM_CPPC  8
 
 /* cmd type */
 #define XEN_PM_CX   0
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