x86/Hyper-V: Support for free page reporting

Linux has support for free page reporting now (36e66c554b5c) for
virtualized environment. On Hyper-V when virtually backed VMs are
configured, Hyper-V will advertise cold memory discard capability,
when supported. This patch adds the support to hook into the free
page reporting infrastructure and leverage the Hyper-V cold memory
discard hint hypercall to report/free these pages back to the host.

Signed-off-by: Sunil Muthuswamy <sunilmut@microsoft.com>
Tested-by: Matheus Castello <matheus@castello.eng.br>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/SN4PR2101MB0880121FA4E2FEC67F35C1DCC0649@SN4PR2101MB0880.namprd21.prod.outlook.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>

2 files changed, 55 insertions, 5 deletions

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 9d100257b3af..7c9da3f65afa 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -498,6 +498,8 @@ void __init hyperv_init(void)
 		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
 #endif
 
+	/* Query the VMs extended capability once, so that it can be cached. */
+	hv_query_ext_cap(0);
 	return;
 
 remove_cpuhp_state:
@@ -601,7 +603,7 @@ EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
 
 enum hv_isolation_type hv_get_isolation_type(void)
 {
-	if (!(ms_hyperv.features_b & HV_ISOLATION))
+	if (!(ms_hyperv.priv_high & HV_ISOLATION))
 		return HV_ISOLATION_TYPE_NONE;
 	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
 }
@@ -612,3 +614,50 @@ bool hv_is_isolation_supported(void)
 	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
 }
 EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
+
+/* Bit mask of the extended capability to query: see HV_EXT_CAPABILITY_xxx */
+bool hv_query_ext_cap(u64 cap_query)
+{
+	/*
+	 * The address of the 'hv_extended_cap' variable will be used as an
+	 * output parameter to the hypercall below and so it should be
+	 * compatible with 'virt_to_phys'. Which means, it's address should be
+	 * directly mapped. Use 'static' to keep it compatible; stack variables
+	 * can be virtually mapped, making them imcompatible with
+	 * 'virt_to_phys'.
+	 * Hypercall input/output addresses should also be 8-byte aligned.
+	 */
+	static u64 hv_extended_cap __aligned(8);
+	static bool hv_extended_cap_queried;
+	u64 status;
+
+	/*
+	 * Querying extended capabilities is an extended hypercall. Check if the
+	 * partition supports extended hypercall, first.
+	 */
+	if (!(ms_hyperv.priv_high & HV_ENABLE_EXTENDED_HYPERCALLS))
+		return false;
+
+	/* Extended capabilities do not change at runtime. */
+	if (hv_extended_cap_queried)
+		return hv_extended_cap & cap_query;
+
+	status = hv_do_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, NULL,
+				 &hv_extended_cap);
+
+	/*
+	 * The query extended capabilities hypercall should not fail under
+	 * any normal circumstances. Avoid repeatedly making the hypercall, on
+	 * error.
+	 */
+	hv_extended_cap_queried = true;
+	status &= HV_HYPERCALL_RESULT_MASK;
+	if (status != HV_STATUS_SUCCESS) {
+		pr_err("Hyper-V: Extended query capabilities hypercall failed 0x%llx\n",
+		       status);
+		return false;
+	}
+
+	return hv_extended_cap & cap_query;
+}
+EXPORT_SYMBOL_GPL(hv_query_ext_cap);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index cebed535ec56..3546d3e21787 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -265,12 +265,13 @@ static void __init ms_hyperv_init_platform(void)
 	 * Extract the features and hints
 	 */
 	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
-	ms_hyperv.features_b = cpuid_ebx(HYPERV_CPUID_FEATURES);
+	ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
+	pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
+		ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -316,7 +317,7 @@ static void __init ms_hyperv_init_platform(void)
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
 	}
 
-	if (ms_hyperv.features_b & HV_ISOLATION) {
+	if (ms_hyperv.priv_high & HV_ISOLATION) {
 		ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG);
 		ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG);