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, 263 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 8d26f2537586..b3ee44a40c2f 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -6,6 +6,7 @@
 
 #include <linux/string.h>
 #include <linux/irqflags.h>
+#include <linux/delay.h>
 
 #include <asm/hvcall.h>
 #include <asm/paca.h>
@@ -343,6 +344,212 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
 	return rc;
 }
 
+static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	unsigned long token;
+	long rc;
+
+	token = -1UL;
+	do {
+		rc = plpar_hcall(H_GUEST_CREATE, retbuf, flags, token);
+		if (rc == H_SUCCESS)
+			*guest_id = retbuf[0];
+
+		if (rc == H_BUSY) {
+			token = retbuf[0];
+			cond_resched();
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			token = retbuf[0];
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_create_vcpu(unsigned long flags,
+					   unsigned long guest_id,
+					   unsigned long vcpu_id)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_GUEST_CREATE_VCPU, 0, guest_id, vcpu_id);
+
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_set_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	while (true) {
+		rc = plpar_hcall(H_GUEST_SET_STATE, retbuf, flags, guest_id,
+				 vcpu_id, data_buffer, data_size);
+
+		if (rc == H_BUSY) {
+			cpu_relax();
+			continue;
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			mdelay(get_longbusy_msecs(rc));
+			continue;
+		}
+
+		if (rc == H_INVALID_ELEMENT_ID)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			*failed_index = retbuf[0];
+
+		break;
+	}
+
+	return rc;
+}
+
+static inline long plpar_guest_get_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	while (true) {
+		rc = plpar_hcall(H_GUEST_GET_STATE, retbuf, flags, guest_id,
+				 vcpu_id, data_buffer, data_size);
+
+		if (rc == H_BUSY) {
+			cpu_relax();
+			continue;
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			mdelay(get_longbusy_msecs(rc));
+			continue;
+		}
+
+		if (rc == H_INVALID_ELEMENT_ID)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			*failed_index = retbuf[0];
+
+		break;
+	}
+
+	return rc;
+}
+
+static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id,
+					unsigned long vcpu_id, int *trap,
+					unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GUEST_RUN_VCPU, retbuf, flags, guest_id, vcpu_id);
+	if (rc == H_SUCCESS)
+		*trap = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_ID)
+		*failed_index = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_SIZE)
+		*failed_index = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_VALUE)
+		*failed_index = retbuf[0];
+
+	return rc;
+}
+
+static inline long plpar_guest_delete(unsigned long flags, u64 guest_id)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_GUEST_DELETE, flags, guest_id);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_set_capabilities(unsigned long flags,
+						unsigned long capabilities)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_GUEST_SET_CAPABILITIES, retbuf, flags, capabilities);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_get_capabilities(unsigned long flags,
+						unsigned long *capabilities)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_GUEST_GET_CAPABILITIES, retbuf, flags);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+	} while (rc == H_BUSY);
+
+	if (rc == H_SUCCESS)
+		*capabilities = retbuf[0];
+
+	return rc;
+}
+
 /*
  * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately
  *
@@ -407,6 +614,62 @@ static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type,
 	return 0;
 }
 
+static inline long plpar_guest_create_vcpu(unsigned long flags,
+					   unsigned long guest_id,
+					   unsigned long vcpu_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_get_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_set_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id,
+					unsigned long vcpu_id, int *trap,
+					unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_delete(unsigned long flags, u64 guest_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_get_capabilities(unsigned long flags,
+						unsigned long *capabilities)
+{
+	return 0;
+}
+
+static inline long plpar_guest_set_capabilities(unsigned long flags,
+						unsigned long capabilities)
+{
+	return 0;
+}
+
 #endif /* CONFIG_PPC_PSERIES */
 
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */