Merge branch 'hyperv-next' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git

8 files changed, 152 insertions, 40 deletions

diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 1e2fe398b66d..0b73a809e9e1 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -116,6 +116,9 @@
 /* Recommend using the newer ExProcessorMasks interface */
 #define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED		BIT(11)
 
+/* Indicates that the hypervisor is nested within a Hyper-V partition. */
+#define HV_X64_HYPERV_NESTED				BIT(12)
+
 /* Recommend using enlightened VMCS */
 #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED		BIT(14)
 
@@ -225,6 +228,17 @@ enum hv_isolation_type {
 #define HV_REGISTER_SINT15			0x4000009F
 
 /*
+ * Define synthetic interrupt controller model specific registers for
+ * nested hypervisor.
+ */
+#define HV_REGISTER_NESTED_SCONTROL            0x40001080
+#define HV_REGISTER_NESTED_SVERSION            0x40001081
+#define HV_REGISTER_NESTED_SIEFP               0x40001082
+#define HV_REGISTER_NESTED_SIMP                0x40001083
+#define HV_REGISTER_NESTED_EOM                 0x40001084
+#define HV_REGISTER_NESTED_SINT0               0x40001090
+
+/*
  * Synthetic Timer MSRs. Four timers per vcpu.
  */
 #define HV_REGISTER_STIMER0_CONFIG		0x400000B0
@@ -371,7 +385,8 @@ struct hv_nested_enlightenments_control {
 		__u32 reserved:31;
 	} features;
 	struct {
-		__u32 reserved;
+		__u32 inter_partition_comm:1;
+		__u32 reserved:31;
 	} hypercallControls;
 } __packed;
 
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 6d502f3efb0f..15ac2d03ac59 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -72,10 +72,16 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	return hv_status;
 }
 
+/* Hypercall to the L0 hypervisor */
+static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
+{
+	return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
+}
+
 /* Fast hypercall with 8 bytes of input and no output */
-static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
+static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
 {
-	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+	u64 hv_status;
 
 #ifdef CONFIG_X86_64
 	{
@@ -103,10 +109,24 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		return hv_status;
 }
 
+static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
+{
+	u64 control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+	return _hv_do_fast_hypercall8(control, input1);
+}
+
+static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
+{
+	u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
+
+	return _hv_do_fast_hypercall8(control, input1);
+}
+
 /* Fast hypercall with 16 bytes of input */
-static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 {
-	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+	u64 hv_status;
 
 #ifdef CONFIG_X86_64
 	{
@@ -137,6 +157,20 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 	return hv_status;
 }
 
+static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	u64 control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+	return _hv_do_fast_hypercall16(control, input1, input2);
+}
+
+static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
+
+	return _hv_do_fast_hypercall16(control, input1, input2);
+}
+
 extern struct hv_vp_assist_page **hv_vp_assist_page;
 
 static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -196,30 +230,10 @@ static inline bool hv_is_synic_reg(unsigned int reg)
 	return false;
 }
 
-static inline u64 hv_get_register(unsigned int reg)
-{
-	u64 value;
-
-	if (hv_is_synic_reg(reg) && hv_isolation_type_snp())
-		hv_ghcb_msr_read(reg, &value);
-	else
-		rdmsrl(reg, value);
-	return value;
-}
-
-static inline void hv_set_register(unsigned int reg, u64 value)
-{
-	if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) {
-		hv_ghcb_msr_write(reg, value);
-
-		/* Write proxy bit via wrmsl instruction */
-		if (reg >= HV_REGISTER_SINT0 &&
-		    reg <= HV_REGISTER_SINT15)
-			wrmsrl(reg, value | 1 << 20);
-	} else {
-		wrmsrl(reg, value);
-	}
-}
+u64 hv_get_register(unsigned int reg);
+void hv_set_register(unsigned int reg, u64 value);
+u64 hv_get_non_nested_register(unsigned int reg);
+void hv_set_non_nested_register(unsigned int reg, u64 value);
 
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
@@ -239,6 +253,8 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 }
 static inline void hv_set_register(unsigned int reg, u64 value) { }
 static inline u64 hv_get_register(unsigned int reg) { return 0; }
+static inline void hv_set_non_nested_register(unsigned int reg, u64 value) { }
+static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
 static inline int hv_set_mem_host_visibility(unsigned long addr, int numpages,
 					     bool visible)
 {
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index bfbdc072017d..b8bb13daacf7 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -37,9 +37,76 @@
 
 /* Is Linux running as the root partition? */
 bool hv_root_partition;
+/* Is Linux running on nested Microsoft Hypervisor */
+bool hv_nested;
 struct ms_hyperv_info ms_hyperv;
 
+static inline unsigned int hv_get_nested_reg(unsigned int reg)
+{
+	switch (reg) {
+	case HV_REGISTER_SIMP:
+		return HV_REGISTER_NESTED_SIMP;
+	case HV_REGISTER_SIEFP:
+		return HV_REGISTER_NESTED_SIEFP;
+	case HV_REGISTER_SVERSION:
+		return HV_REGISTER_NESTED_SVERSION;
+	case HV_REGISTER_SCONTROL:
+		return HV_REGISTER_NESTED_SCONTROL;
+	case HV_REGISTER_SINT0:
+		return HV_REGISTER_NESTED_SINT0;
+	case HV_REGISTER_EOM:
+		return HV_REGISTER_NESTED_EOM;
+	default:
+		return reg;
+	}
+}
+
 #if IS_ENABLED(CONFIG_HYPERV)
+u64 hv_get_non_nested_register(unsigned int reg)
+{
+	u64 value;
+
+	if (hv_is_synic_reg(reg) && hv_isolation_type_snp())
+		hv_ghcb_msr_read(reg, &value);
+	else
+		rdmsrl(reg, value);
+	return value;
+}
+EXPORT_SYMBOL_GPL(hv_get_non_nested_register);
+
+void hv_set_non_nested_register(unsigned int reg, u64 value)
+{
+	if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) {
+		hv_ghcb_msr_write(reg, value);
+
+		/* Write proxy bit via wrmsl instruction */
+		if (reg >= HV_REGISTER_SINT0 &&
+		    reg <= HV_REGISTER_SINT15)
+			wrmsrl(reg, value | 1 << 20);
+	} else {
+		wrmsrl(reg, value);
+	}
+}
+EXPORT_SYMBOL_GPL(hv_set_non_nested_register);
+
+u64 hv_get_register(unsigned int reg)
+{
+	if (hv_nested)
+		reg = hv_get_nested_reg(reg);
+
+	return hv_get_non_nested_register(reg);
+}
+EXPORT_SYMBOL_GPL(hv_get_register);
+
+void hv_set_register(unsigned int reg, u64 value)
+{
+	if (hv_nested)
+		reg = hv_get_nested_reg(reg);
+
+	hv_set_non_nested_register(reg, value);
+}
+EXPORT_SYMBOL_GPL(hv_set_register);
+
 static void (*vmbus_handler)(void);
 static void (*hv_stimer0_handler)(void);
 static void (*hv_kexec_handler)(void);
@@ -301,6 +368,11 @@ static void __init ms_hyperv_init_platform(void)
 		pr_info("Hyper-V: running as root partition\n");
 	}
 
+	if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) {
+		hv_nested = true;
+		pr_info("Hyper-V: running on a nested hypervisor\n");
+	}
+
 	/*
 	 * Extract host information.
 	 */
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 4d6480d57546..8b0dd8e5244d 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -147,7 +147,7 @@ int hv_synic_alloc(void)
 		 * Synic message and event pages are allocated by paravisor.
 		 * Skip these pages allocation here.
 		 */
-		if (!hv_isolation_type_snp()) {
+		if (!hv_isolation_type_snp() && !hv_root_partition) {
 			hv_cpu->synic_message_page =
 				(void *)get_zeroed_page(GFP_ATOMIC);
 			if (hv_cpu->synic_message_page == NULL) {
@@ -216,7 +216,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 1;
 
-	if (hv_isolation_type_snp()) {
+	if (hv_isolation_type_snp() || hv_root_partition) {
 		hv_cpu->synic_message_page
 			= memremap(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT,
 				   HV_HYP_PAGE_SIZE, MEMREMAP_WB);
@@ -233,7 +233,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 1;
 
-	if (hv_isolation_type_snp()) {
+	if (hv_isolation_type_snp() || hv_root_partition) {
 		hv_cpu->synic_event_page =
 			memremap(siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT,
 				 HV_HYP_PAGE_SIZE, MEMREMAP_WB);
@@ -315,20 +315,24 @@ void hv_synic_disable_regs(unsigned int cpu)
 	 * addresses.
 	 */
 	simp.simp_enabled = 0;
-	if (hv_isolation_type_snp())
+	if (hv_isolation_type_snp() || hv_root_partition) {
 		memunmap(hv_cpu->synic_message_page);
-	else
+		hv_cpu->synic_message_page = NULL;
+	} else {
 		simp.base_simp_gpa = 0;
+	}
 
 	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
 
 	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 0;
 
-	if (hv_isolation_type_snp())
+	if (hv_isolation_type_snp() || hv_root_partition) {
 		memunmap(hv_cpu->synic_event_page);
-	else
+		hv_cpu->synic_event_page = NULL;
+	} else {
 		siefp.base_siefp_gpa = 0;
+	}
 
 	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index ae68298c0dca..52a6f89ccdbd 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -25,17 +25,20 @@
 #include <asm/mshyperv.h>
 
 /*
- * hv_root_partition and ms_hyperv are defined here with other Hyper-V
- * specific globals so they are shared across all architectures and are
+ * hv_root_partition, ms_hyperv and hv_nested are defined here with other
+ * Hyper-V specific globals so they are shared across all architectures and are
  * built only when CONFIG_HYPERV is defined.  But on x86,
  * ms_hyperv_init_platform() is built even when CONFIG_HYPERV is not
- * defined, and it uses these two variables.  So mark them as __weak
+ * defined, and it uses these three variables.  So mark them as __weak
  * here, allowing for an overriding definition in the module containing
  * ms_hyperv_init_platform().
  */
 bool __weak hv_root_partition;
 EXPORT_SYMBOL_GPL(hv_root_partition);
 
+bool __weak hv_nested;
+EXPORT_SYMBOL_GPL(hv_nested);
+
 struct ms_hyperv_info __weak ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 3146710d4ac6..1901556efe79 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2744,7 +2744,7 @@ static int __init hv_acpi_init(void)
 	if (!hv_is_hyperv_initialized())
 		return -ENODEV;
 
-	if (hv_root_partition)
+	if (hv_root_partition && !hv_nested)
 		return 0;
 
 	/*
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
index e29ccabf2e09..b870983596b9 100644
--- a/include/asm-generic/hyperv-tlfs.h
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -194,6 +194,7 @@ enum HV_GENERIC_SET_FORMAT {
 #define HV_HYPERCALL_VARHEAD_OFFSET	17
 #define HV_HYPERCALL_VARHEAD_MASK	GENMASK_ULL(26, 17)
 #define HV_HYPERCALL_RSVD0_MASK		GENMASK_ULL(31, 27)
+#define HV_HYPERCALL_NESTED		BIT_ULL(31)
 #define HV_HYPERCALL_REP_COMP_OFFSET	32
 #define HV_HYPERCALL_REP_COMP_1		BIT_ULL(32)
 #define HV_HYPERCALL_REP_COMP_MASK	GENMASK_ULL(43, 32)
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index d55d2833a37b..8845a2eca339 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -48,6 +48,7 @@ struct ms_hyperv_info {
 	u64 shared_gpa_boundary;
 };
 extern struct ms_hyperv_info ms_hyperv;
+extern bool hv_nested;
 
 extern void * __percpu *hyperv_pcpu_input_arg;
 extern void * __percpu *hyperv_pcpu_output_arg;