x86/hyperv: Add support for detecting nested hypervisor

Detect if Linux is running as a nested hypervisor in the root partition for Microsoft Hypervisor, using flags provided by MSHV. Expose a new variable hv_nested that is used later for decisions specific to the nested use case.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/hyperv-tlfs.h | 3 +++
 arch/x86/kernel/cpu/mshyperv.c     | 7 +++++++
 drivers/hv/hv_common.c             | 9 ++++++---
 include/asm-generic/mshyperv.h     | 1 +
 4 files changed, 17 insertions(+), 3 deletions(-)

arch/x86/include/asm/hyperv-tlfs.h +3 -0

index 6d9368ea3701..58c03d18c235 100644
@@ -114,6 +114,9 @@
 /* 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)
 

arch/x86/kernel/cpu/mshyperv.c +7 -0

index 46668e255421..f9b78d4829e3 100644
@@ -37,6 +37,8 @@
 
 /* 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;
 
 #if IS_ENABLED(CONFIG_HYPERV)

@@ -301,6 +303,11 @@ 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.
 	 */

drivers/hv/hv_common.c +6 -3

index ae68298c0dca..52a6f89ccdbd 100644
@@ -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);
 

include/asm-generic/mshyperv.h +1 -1

index bfb9eb9d7215..f131027830c3 100644
@@ -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;
--

2.25.1

Child partitions are free to allocate SynIC message and event page but in case of root partition it must use the pages allocated by Microsoft Hypervisor (MSHV). Base address for these pages can be found using synthetic MSRs exposed by MSHV. There is a slight difference in those MSRs for nested vs non-nested root partition.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/hyperv-tlfs.h | 11 +++++
 arch/x86/include/asm/mshyperv.h    | 30 +++-----------
 arch/x86/kernel/cpu/mshyperv.c     | 65 ++++++++++++++++++++++++++++++
 drivers/hv/hv.c                    | 18 +++++----
 4 files changed, 93 insertions(+), 31 deletions(-)

arch/x86/include/asm/hyperv-tlfs.h +11 -0

index 58c03d18c235..b5019becb618 100644
@@ -225,6 +225,17 @@ enum hv_isolation_type {
 #define HV_REGISTER_SINT14			0x4000009E
 #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.
  */

arch/x86/include/asm/mshyperv.h +6 -24

index 61f0c206bff0..c38e4c66a3ac 100644
@@ -198,30 +198,10 @@ 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) {}

@@ -241,6 +221,8 @@ 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)
 {

arch/x86/kernel/cpu/mshyperv.c +65 -0

index f9b78d4829e3..938fc82edf05 100644
@@ -41,7 +41,72 @@ bool hv_root_partition;
 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);

drivers/hv/hv.c +11 -8

index 4d6480d57546..8b0dd8e5244d 100644
@@ -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);
 
--

2.25.1

Child partitions are free to allocate SynIC message and event page but in case of root partition it must use the pages allocated by Microsoft Hypervisor (MSHV). Base address for these pages can be found using synthetic MSRs exposed by MSHV. There is a slight difference in those MSRs for nested vs non-nested root partition.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/hyperv-tlfs.h | 11 +++++
 arch/x86/include/asm/mshyperv.h    | 30 +++-----------
 arch/x86/kernel/cpu/mshyperv.c     | 65 ++++++++++++++++++++++++++++++
 drivers/hv/hv.c                    | 18 +++++----
 4 files changed, 93 insertions(+), 31 deletions(-)

arch/x86/include/asm/hyperv-tlfs.h +11 -0

index 58c03d18c235..b5019becb618 100644
@@ -225,6 +225,17 @@ enum hv_isolation_type {
 #define HV_REGISTER_SINT14			0x4000009E
 #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.
  */

arch/x86/include/asm/mshyperv.h +6 -24

index 61f0c206bff0..c38e4c66a3ac 100644
@@ -198,30 +198,10 @@ 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) {}

@@ -241,6 +221,8 @@ 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)
 {

arch/x86/kernel/cpu/mshyperv.c +65 -0

index f9b78d4829e3..938fc82edf05 100644
@@ -41,7 +41,72 @@ bool hv_root_partition;
 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);

drivers/hv/hv.c +7 -6

index 4d6480d57546..8b0dd8e5244d 100644
@@ -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())

According to TLFS, in order to communicate to L0 hypervisor there needs to be an additional bit set in the control register. This communication is required to perform privileged instructions which can only be performed by L0 hypervisor. An example of that could be setting up the VMBus infrastructure.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/hyperv-tlfs.h |  3 ++-
 arch/x86/include/asm/mshyperv.h    | 42 +++++++++++++++++++++++++++---
 include/asm-generic/hyperv-tlfs.h  |  1 +
 3 files changed, 41 insertions(+), 5 deletions(-)

arch/x86/include/asm/hyperv-tlfs.h +2 -1

index b5019becb618..7758c495541d 100644
@@ -380,7 +380,8 @@ struct hv_nested_enlightenments_control {
 		__u32 reserved:31;
 	} features;
 	struct {
-		__u32 reserved;
+		__u32 inter_partition_comm:1;
+		__u32 reserved:31;
 	} hypercallControls;
 } __packed;
 

arch/x86/include/asm/mshyperv.h +8 -2

index c38e4c66a3ac..9e5535044ed0 100644
@@ -74,10 +74,16 @@ 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

arch/x86/include/asm/mshyperv.h +16 -2

 	{

@@ -105,10 +111,24 @@ 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

arch/x86/include/asm/mshyperv.h +14 -0

 	{

@@ -139,6 +159,20 @@ 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)

include/asm-generic/hyperv-tlfs.h +1 -1

index b17c6eeb9afa..e61ee461c4fc 100644
@@ -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)
--

2.25.1

Currently VMBus driver is not initialized for root partition but we need to enable the VMBus driver for nested root partition. This is required, so that L2 root can use the VMBus devices.

Signed-off-by Jinank Jain <[email protected]>

---
 drivers/hv/vmbus_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/hv/vmbus_drv.c +1 -2

index 0f00d57b7c25..6324e01d5eec 100644
@@ -2745,7 +2745,7 @@ 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;
 
 	/*
--

2.25.1

Traditionally we have been using the HYPERVISOR_CALLBACK_VECTOR to relay the VMBus interrupt. But this does not work in case of nested hypervisor. Microsoft Hypervisor reserves 0x31 to 0x34 as the interrupt vector range for VMBus and thus we have to use one of the vectors from that range and setup the IDT accordingly.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/idtentry.h    |  2 ++
 arch/x86/include/asm/irq_vectors.h |  6 ++++++
 arch/x86/kernel/cpu/mshyperv.c     | 15 +++++++++++++++
 arch/x86/kernel/idt.c              | 10 ++++++++++
 drivers/hv/vmbus_drv.c             |  3 ++-
 5 files changed, 35 insertions(+), 1 deletion(-)

arch/x86/include/asm/idtentry.h +0 -0

index 72184b0b2219..c0648e3e4d4a 100644
@@ -686,6 +686,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,
 	sysvec_kvm_posted_intr_nested
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,
 	sysvec_hyperv_callback);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,
 	sysvec_hyperv_reenlightenment);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,

	sysvec_hyperv_stimer0);

arch/x86/include/asm/idtentry.h +2 -0

+DECLARE_IDTENTRY_SYSVEC(HYPERV_INTR_NESTED_VMBUS_VECTOR,
+			sysvec_hyperv_nested_vmbus_intr);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)

arch/x86/include/asm/irq_vectors.h +6 -0

index 43dcb9284208..729d19eab7f5 100644
@@ -102,6 +102,12 @@
 #if IS_ENABLED(CONFIG_HYPERV)
 #define HYPERV_REENLIGHTENMENT_VECTOR	0xee
 #define HYPERV_STIMER0_VECTOR		0xed
+/*
+ * FIXME: Change this, once Microsoft Hypervisor changes its assumption
+ * around VMBus interrupt vector allocation for nested root partition.
+ * Or provides a better interface to detect this instead of hardcoding.
+ */
+#define HYPERV_INTR_NESTED_VMBUS_VECTOR	0x31
 #endif
 
 #define LOCAL_TIMER_VECTOR		0xec

arch/x86/kernel/cpu/mshyperv.c +15 -0

index 938fc82edf05..4dfe0f9d7be3 100644
@@ -126,6 +126,21 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	set_irq_regs(old_regs);
 }
 
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_nested_vmbus_intr)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	inc_irq_stat(irq_hv_callback_count);
+
+	if (vmbus_handler)
+		vmbus_handler();
+
+	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
+		ack_APIC_irq();
+
+	set_irq_regs(old_regs);
+}
+
 void hv_setup_vmbus_handler(void (*handler)(void))
 {
 	vmbus_handler = handler;

arch/x86/kernel/idt.c +10 -0

index a58c6bc1cd68..3536935cea39 100644
@@ -160,6 +160,16 @@ static const __initconst struct idt_data apic_idts[] = {
 # endif
 	INTG(SPURIOUS_APIC_VECTOR,
 	asm_sysvec_spurious_apic_interrupt),
 	INTG(ERROR_APIC_VECTOR,			asm_sysvec_error_interrupt),
+#ifdef CONFIG_HYPERV
+	/*
+	 * This is a hack because we cannot install this interrupt handler
+	 * via alloc_intr_gate as it does not allow interrupt vector less
+	 * than FIRST_SYSTEM_VECTORS. And hyperv does not want anything other
+	 * than 0x31-0x34 as the interrupt vector for vmbus interrupt in case
+	 * of nested setup.
+	 */
+	INTG(HYPERV_INTR_NESTED_VMBUS_VECTOR,
 asm_sysvec_hyperv_nested_vmbus_intr),
+#endif
 #endif

};

drivers/hv/vmbus_drv.c +2 -2

index 6324e01d5eec..740878367426 100644
@@ -2768,7 +2768,8 @@ static int __init hv_acpi_init(void)
 	 * normal Linux IRQ mechanism is not used in this case.
 	 */
 #ifdef HYPERVISOR_CALLBACK_VECTOR
-	vmbus_interrupt = HYPERVISOR_CALLBACK_VECTOR;
+	vmbus_interrupt = hv_nested ? HYPERV_INTR_NESTED_VMBUS_VECTOR :
+				      HYPERVISOR_CALLBACK_VECTOR;
 	vmbus_irq = -1;
 #endif
 
--

2.25.1

Traditionally we have been using the HYPERVISOR_CALLBACK_VECTOR to relay the VMBus interrupt. But this does not work in case of nested hypervisor. Microsoft Hypervisor reserves 0x31 to 0x34 as the interrupt vector range for VMBus and thus we have to use one of the vectors from that range and setup the IDT accordingly.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/idtentry.h    |  2 ++
 arch/x86/include/asm/irq_vectors.h |  6 ++++++
 arch/x86/kernel/cpu/mshyperv.c     | 15 +++++++++++++++
 arch/x86/kernel/idt.c              | 10 ++++++++++
 drivers/hv/vmbus_drv.c             |  3 ++-
 5 files changed, 35 insertions(+), 1 deletion(-)

arch/x86/include/asm/idtentry.h +2 -0

index 72184b0b2219..c0648e3e4d4a 100644
@@ -686,6 +686,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_INTR_NESTED_VMBUS_VECTOR,
+			sysvec_hyperv_nested_vmbus_intr);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)

arch/x86/include/asm/irq_vectors.h +6 -0

index 43dcb9284208..729d19eab7f5 100644
@@ -102,6 +102,12 @@
 #if IS_ENABLED(CONFIG_HYPERV)
 #define HYPERV_REENLIGHTENMENT_VECTOR	0xee
 #define HYPERV_STIMER0_VECTOR		0xed
+/*
+ * FIXME: Change this, once Microsoft Hypervisor changes its assumption
+ * around VMBus interrupt vector allocation for nested root partition.
+ * Or provides a better interface to detect this instead of hardcoding.
+ */
+#define HYPERV_INTR_NESTED_VMBUS_VECTOR	0x31
 #endif
 
 #define LOCAL_TIMER_VECTOR		0xec

arch/x86/kernel/cpu/mshyperv.c +15 -0

index 938fc82edf05..4dfe0f9d7be3 100644
@@ -126,6 +126,21 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	set_irq_regs(old_regs);
 }
 
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_nested_vmbus_intr)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	inc_irq_stat(irq_hv_callback_count);
+
+	if (vmbus_handler)
+		vmbus_handler();
+
+	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
+		ack_APIC_irq();
+
+	set_irq_regs(old_regs);
+}
+
 void hv_setup_vmbus_handler(void (*handler)(void))
 {
 	vmbus_handler = handler;

arch/x86/kernel/idt.c +10 -0

index a58c6bc1cd68..3536935cea39 100644
@@ -160,6 +160,16 @@ static const __initconst struct idt_data apic_idts[] = {
 # endif
 	INTG(SPURIOUS_APIC_VECTOR,		asm_sysvec_spurious_apic_interrupt),
 	INTG(ERROR_APIC_VECTOR,			asm_sysvec_error_interrupt),
+#ifdef CONFIG_HYPERV
+	/*
+	 * This is a hack because we cannot install this interrupt handler
+	 * via alloc_intr_gate as it does not allow interrupt vector less
+	 * than FIRST_SYSTEM_VECTORS. And hyperv does not want anything other
+	 * than 0x31-0x34 as the interrupt vector for vmbus interrupt in case
+	 * of nested setup.
+	 */
+	INTG(HYPERV_INTR_NESTED_VMBUS_VECTOR, asm_sysvec_hyperv_nested_vmbus_intr),
+#endif
 #endif
 };
 

drivers/hv/vmbus_drv.c +2 -1

index 6324e01d5eec..740878367426 100644
@@ -2768,7 +2768,8 @@ static int __init hv_acpi_init(void)
 	 * normal Linux IRQ mechanism is not used in this case.
 	 */
 #ifdef HYPERVISOR_CALLBACK_VECTOR
-	vmbus_interrupt = HYPERVISOR_CALLBACK_VECTOR;
+	vmbus_interrupt = hv_nested ? HYPERV_INTR_NESTED_VMBUS_VECTOR :
+				      HYPERVISOR_CALLBACK_VECTOR;
 	vmbus_irq = -1;
 #endif
 

Signature · 1 line

2.25.1

Traditionally we have been using the HYPERVISOR_CALLBACK_VECTOR to relay

the VMBus interrupt. But this does not work in case of nested hypervisor. Microsoft Hypervisor reserves 0x31 to 0x34 as the interrupt vector range for VMBus and thus we have to use one of the vectors from that range and setup the IDT accordingly.

Signed-off-by Jinank Jain <[email protected]>

---
 arch/x86/include/asm/idtentry.h    |  2 ++
 arch/x86/include/asm/irq_vectors.h |  6 ++++++
 arch/x86/kernel/cpu/mshyperv.c     | 15 +++++++++++++++
 arch/x86/kernel/idt.c              | 10 ++++++++++
 drivers/hv/vmbus_drv.c             |  3 ++-
 5 files changed, 35 insertions(+), 1 deletion(-)

arch/x86/include/asm/idtentry.h +2 -0

index 72184b0b2219..c0648e3e4d4a 100644
@@ -686,6 +686,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_INTR_NESTED_VMBUS_VECTOR,
+			sysvec_hyperv_nested_vmbus_intr);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)

arch/x86/include/asm/irq_vectors.h +0 -0

index 43dcb9284208..729d19eab7f5 100644

arch/x86/include/asm/irq_vectors.h +3 -0

+ * Or provides a better interface to detect this instead of hardcoding.
+ */
+#define HYPERV_INTR_NESTED_VMBUS_VECTOR	0x31
 #endif
 
 #define LOCAL_TIMER_VECTOR		0xec

arch/x86/kernel/cpu/mshyperv.c +15 -0

index 938fc82edf05..4dfe0f9d7be3 100644
@@ -126,6 +126,21 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	set_irq_regs(old_regs);
 }
 
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_nested_vmbus_intr)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	inc_irq_stat(irq_hv_callback_count);
+
+	if (vmbus_handler)
+		vmbus_handler();
+
+	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
+		ack_APIC_irq();
+
+	set_irq_regs(old_regs);
+}
+
 void hv_setup_vmbus_handler(void (*handler)(void))
 {
 	vmbus_handler = handler;

arch/x86/kernel/idt.c +0 -0

index a58c6bc1cd68..3536935cea39 100644

+DECLARE_IDTENTRY_SYSVEC(HYPERV_INTR_NESTED_VMBUS_VECTOR, sysvec_hyperv_nested_vmbus_intr);