KVM: PPC: Add support for nestedv2 guests

A series of hcalls have been added to the PAPR which allow a regular
guest partition to create and manage guest partitions of its own. KVM
already had an interface that allowed this on powernv platforms. This
existing interface will now be called "nestedv1". The newly added PAPR
interface will be called "nestedv2".  PHYP will support the nestedv2
interface. At this time the host side of the nestedv2 interface has not
been implemented on powernv but there is no technical reason why it
could not be added.

The nestedv1 interface is still supported.

Add support to KVM to utilize these hcalls to enable running nested
guests as a pseries guest on PHYP.

Overview of the new hcall usage:

- L1 and L0 negotiate capabilities with
  H_GUEST_{G,S}ET_CAPABILITIES()

- L1 requests the L0 create a L2 with
  H_GUEST_CREATE() and receives a handle to use in future hcalls

- L1 requests the L0 create a L2 vCPU with
  H_GUEST_CREATE_VCPU()

- L1 sets up the L2 using H_GUEST_SET and the
  H_GUEST_VCPU_RUN input buffer

- L1 requests the L0 runs the L2 vCPU using H_GUEST_VCPU_RUN()

- L2 returns to L1 with an exit reason and L1 reads the
  H_GUEST_VCPU_RUN output buffer populated by the L0

- L1 handles the exit using H_GET_STATE if necessary

- L1 reruns L2 vCPU with H_GUEST_VCPU_RUN

- L1 frees the L2 in the L0 with H_GUEST_DELETE()

Support for the new API is determined by trying
H_GUEST_GET_CAPABILITIES. On a successful return, use the nestedv2
interface.

Use the vcpu register state setters for tracking modified guest state
elements and copy the thread wide values into the H_GUEST_VCPU_RUN input
buffer immediately before running a L2. The guest wide
elements can not be added to the input buffer so send them with a
separate H_GUEST_SET call if necessary.

Make the vcpu register getter load the corresponding value from the real
host with H_GUEST_GET. To avoid unnecessarily calling H_GUEST_GET, track
which values have already been loaded between H_GUEST_VCPU_RUN calls. If
an element is present in the H_GUEST_VCPU_RUN output buffer it also does
not need to be loaded again.

Tested-by: Sachin Sant <sachinp@linux.ibm.com>
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Gautam Menghani <gautam@linux.ibm.com>
Signed-off-by: Kautuk Consul <kconsul@linux.vnet.ibm.com>
Signed-off-by: Amit Machhiwal <amachhiw@linux.vnet.ibm.com>
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20230914030600.16993-11-jniethe5@gmail.com

1 files changed, 116 insertions, 21 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 831c23e4f121..4f527d09c92b 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_book3s_asm.h>
+#include <asm/guest-state-buffer.h>
 
 struct kvmppc_bat {
 	u64 raw;
@@ -295,6 +296,7 @@ static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {}
 static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {}
 #endif
 
+extern unsigned long nested_capabilities;
 long kvmhv_nested_init(void);
 void kvmhv_nested_exit(void);
 void kvmhv_vm_nested_init(struct kvm *kvm);
@@ -316,6 +318,69 @@ long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu);
 
 void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+
+extern struct static_key_false __kvmhv_is_nestedv2;
+
+static inline bool kvmhv_is_nestedv2(void)
+{
+	return static_branch_unlikely(&__kvmhv_is_nestedv2);
+}
+
+static inline bool kvmhv_is_nestedv1(void)
+{
+	return !static_branch_likely(&__kvmhv_is_nestedv2);
+}
+
+#else
+
+static inline bool kvmhv_is_nestedv2(void)
+{
+	return false;
+}
+
+static inline bool kvmhv_is_nestedv1(void)
+{
+	return false;
+}
+
+#endif
+
+int __kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs);
+int __kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs);
+int __kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden);
+int __kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden);
+
+static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu,
+					       struct pt_regs *regs)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_reload_ptregs(vcpu, regs);
+	return 0;
+}
+static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu,
+						   struct pt_regs *regs)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_mark_dirty_ptregs(vcpu, regs);
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_mark_dirty(vcpu, iden);
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_cached_reload(vcpu, iden);
+	return 0;
+}
+
 extern int kvm_irq_bypass;
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
@@ -335,60 +400,72 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
 	vcpu->arch.regs.gpr[num] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_GPR(num));
 }
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_GPR(num)) < 0);
 	return vcpu->arch.regs.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
 	vcpu->arch.regs.ccr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CR);
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CR) < 0);
 	return vcpu->arch.regs.ccr;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.xer = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_XER);
 }
 
 static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_XER) < 0);
 	return vcpu->arch.regs.xer;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.ctr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CTR);
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CTR) < 0);
 	return vcpu->arch.regs.ctr;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.link = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LR);
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_LR) < 0);
 	return vcpu->arch.regs.link;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.nip = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_NIA);
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_NIA) < 0);
 	return vcpu->arch.regs.nip;
 }
 
@@ -405,27 +482,32 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 
 static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0);
 	return vcpu->arch.fp.fpr[i][TS_FPROFFSET];
 }
 
 static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val)
 {
 	vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i));
 }
 
 static inline u64 kvmppc_get_fpscr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_FPSCR) < 0);
 	return vcpu->arch.fp.fpscr;
 }
 
 static inline void kvmppc_set_fpscr(struct kvm_vcpu *vcpu, u64 val)
 {
 	vcpu->arch.fp.fpscr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_FPSCR);
 }
 
 
 static inline u64 kvmppc_get_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0);
 	return vcpu->arch.fp.fpr[i][j];
 }
 
@@ -433,11 +515,13 @@ static inline void kvmppc_set_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j,
 				      u64 val)
 {
 	vcpu->arch.fp.fpr[i][j] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i));
 }
 
 #ifdef CONFIG_ALTIVEC
 static inline void kvmppc_get_vsx_vr(struct kvm_vcpu *vcpu, int i, vector128 *v)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(32 + i)) < 0);
 	*v =  vcpu->arch.vr.vr[i];
 }
 
@@ -445,75 +529,86 @@ static inline void kvmppc_set_vsx_vr(struct kvm_vcpu *vcpu, int i,
 				     vector128 *val)
 {
 	vcpu->arch.vr.vr[i] = *val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(32 + i));
 }
 
 static inline u32 kvmppc_get_vscr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSCR) < 0);
 	return vcpu->arch.vr.vscr.u[3];
 }
 
 static inline void kvmppc_set_vscr(struct kvm_vcpu *vcpu, u32 val)
 {
 	vcpu->arch.vr.vscr.u[3] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSCR);
 }
 #endif
 
-#define KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size)			\
+#define KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden)		\
 static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
 {									\
 									\
 	vcpu->arch.reg = val;						\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden);				\
 }
 
-#define KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size)			\
+#define KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden)		\
 static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 {									\
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0);		\
 	return vcpu->arch.reg;						\
 }
 
-#define KVMPPC_BOOK3S_VCPU_ACCESSOR(reg, size)				\
-	KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size)			\
-	KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size)			\
+#define KVMPPC_BOOK3S_VCPU_ACCESSOR(reg, size, iden)			\
+	KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden)		\
+	KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden)		\
 
-KVMPPC_BOOK3S_VCPU_ACCESSOR(pid, 32)
-KVMPPC_BOOK3S_VCPU_ACCESSOR(tar, 64)
-KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbhr, 64)
-KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbrr, 64)
-KVMPPC_BOOK3S_VCPU_ACCESSOR(bescr, 64)
-KVMPPC_BOOK3S_VCPU_ACCESSOR(ic, 64)
-KVMPPC_BOOK3S_VCPU_ACCESSOR(vrsave, 64)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(pid, 32, KVMPPC_GSID_PIDR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(tar, 64, KVMPPC_GSID_TAR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbhr, 64, KVMPPC_GSID_EBBHR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbrr, 64, KVMPPC_GSID_EBBRR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(bescr, 64, KVMPPC_GSID_BESCR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(ic, 64, KVMPPC_GSID_IC)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(vrsave, 64, KVMPPC_GSID_VRSAVE)
 
 
-#define KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size)			\
+#define KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden)		\
 static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
 {									\
 	vcpu->arch.vcore->reg = val;					\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden);				\
 }
 
-#define KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size)			\
+#define KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden)		\
 static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 {									\
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0);		\
 	return vcpu->arch.vcore->reg;					\
 }
 
-#define KVMPPC_BOOK3S_VCORE_ACCESSOR(reg, size)				\
-	KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size)			\
-	KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size)			\
+#define KVMPPC_BOOK3S_VCORE_ACCESSOR(reg, size, iden)			\
+	KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden)		\
+	KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden)		\
 
 
-KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64)
-KVMPPC_BOOK3S_VCORE_ACCESSOR(tb_offset, 64)
-KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32)
-KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64)
+KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
+KVMPPC_BOOK3S_VCORE_ACCESSOR(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
 
 static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB) < 0);
 	return vcpu->arch.dec_expires;
 }
 
 static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val)
 {
 	vcpu->arch.dec_expires = val;
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB);
 }
 
 /* Expiry time of vcpu DEC relative to host TB */