platform/x86: hfi: Add online and offline callback support

JIRA: https://issues.redhat.com/browse/RHEL-107081

Conflicts: we don't have x86/msr: Rename 'wrmsrl_on_cpu()' to 'wrmsrq_on_cpu()' c895ecd

commit bb20421
Author: Perry Yuan <Perry.Yuan@amd.com>
Date:   Mon Jun 9 15:05:12 2025 -0500

    platform/x86: hfi: Add online and offline callback support

    There are some firmware parameters that need to be configured
    when a CPU core is brought online or offline.

    When a CPU is online, it will initialize the workload classification
    parameters to CPU firmware which will trigger the workload class ID
    updating function.

    Once the CPU is going offline, it will need to disable the workload
    classification function and clear the history.

    Signed-off-by: Perry Yuan <Perry.Yuan@amd.com>
    Co-developed-by: Mario Limonciello <mario.limonciello@amd.com>
    Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
    Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
    Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
    Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
    Link: https://lore.kernel.org/20250609200518.3616080-8-superm1@kernel.org

Signed-off-by: Steve Best <sbest@redhat.com>

Author: sfbest

drivers/platform/x86/amd/hfi/hfi.c

@@ -92,6 +92,7 @@ struct amd_hfi_classes {
  * struct amd_hfi_cpuinfo - HFI workload class info per CPU
  * @cpu:		CPU index
  * @apic_id:		APIC id of the current CPU
+ * @cpus:		mask of CPUs associated with amd_hfi_cpuinfo
  * @class_index:	workload class ID index
  * @nr_class:		max number of workload class supported
  * @ipcc_scores:	ipcc scores for each class
@@ -102,6 +103,7 @@ struct amd_hfi_classes {
 struct amd_hfi_cpuinfo {
 	int		cpu;
 	u32		apic_id;
+	cpumask_var_t	cpus;
 	s16		class_index;
 	u8		nr_class;
 	int		*ipcc_scores;
@@ -110,6 +112,8 @@ struct amd_hfi_cpuinfo {
 
 static DEFINE_PER_CPU(struct amd_hfi_cpuinfo, amd_hfi_cpuinfo) = {.class_index = -1};
 
+static DEFINE_MUTEX(hfi_cpuinfo_lock);
+
 static int find_cpu_index_by_apicid(unsigned int target_apicid)
 {
 	int cpu_index;
@@ -237,6 +241,81 @@ static int amd_set_hfi_ipcc_score(struct amd_hfi_cpuinfo *hfi_cpuinfo, int cpu)
 	return 0;
 }
 
+static int amd_hfi_set_state(unsigned int cpu, bool state)
+{
+	int ret;
+
+	ret = wrmsrl_on_cpu(cpu, MSR_AMD_WORKLOAD_CLASS_CONFIG, state ? 1 : 0);
+	if (ret)
+		return ret;
+
+	return wrmsrl_on_cpu(cpu, MSR_AMD_WORKLOAD_HRST, 0x1);
+}
+
+/**
+ * amd_hfi_online() - Enable workload classification on @cpu
+ * @cpu: CPU in which the workload classification will be enabled
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int amd_hfi_online(unsigned int cpu)
+{
+	struct amd_hfi_cpuinfo *hfi_info = per_cpu_ptr(&amd_hfi_cpuinfo, cpu);
+	struct amd_hfi_classes *hfi_classes;
+	int ret;
+
+	if (WARN_ON_ONCE(!hfi_info))
+		return -EINVAL;
+
+	/*
+	 * Check if @cpu as an associated, initialized and ranking data must
+	 * be filled.
+	 */
+	hfi_classes = hfi_info->amd_hfi_classes;
+	if (!hfi_classes)
+		return -EINVAL;
+
+	guard(mutex)(&hfi_cpuinfo_lock);
+
+	if (!zalloc_cpumask_var(&hfi_info->cpus, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_set_cpu(cpu, hfi_info->cpus);
+
+	ret = amd_hfi_set_state(cpu, true);
+	if (ret)
+		pr_err("WCT enable failed for CPU %u\n", cpu);
+
+	return ret;
+}
+
+/**
+ * amd_hfi_offline() - Disable workload classification on @cpu
+ * @cpu: CPU in which the workload classification will be disabled
+ *
+ * Remove @cpu from those covered by its HFI instance.
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int amd_hfi_offline(unsigned int cpu)
+{
+	struct amd_hfi_cpuinfo *hfi_info = &per_cpu(amd_hfi_cpuinfo, cpu);
+	int ret;
+
+	if (WARN_ON_ONCE(!hfi_info))
+		return -EINVAL;
+
+	guard(mutex)(&hfi_cpuinfo_lock);
+
+	ret = amd_hfi_set_state(cpu, false);
+	if (ret)
+		pr_err("WCT disable failed for CPU %u\n", cpu);
+
+	free_cpumask_var(hfi_info->cpus);
+
+	return ret;
+}
+
 static int update_hfi_ipcc_scores(void)
 {
 	int cpu;
@@ -339,6 +418,15 @@ static int amd_hfi_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	/*
+	 * Tasks will already be running at the time this happens. This is
+	 * OK because rankings will be adjusted by the callbacks.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/amd_hfi:online",
+				amd_hfi_online, amd_hfi_offline);
+	if (ret < 0)
+		return ret;
+
 	return 0;
 }