KVM: PPC: Book3S HV: XIVE: Add support for automatic save-restore

On P10, the feature doing an automatic "save & restore" of a VCPU
interrupt context is set by default in OPAL. When a VP context is
pulled out, the state of the interrupt registers are saved by the XIVE
interrupt controller under the internal NVP structure representing the
VP. This saves a costly store/load in guest entries and exits.

If OPAL advertises the "save & restore" feature in the device tree,
it should also have set the 'H' bit in the CAM line. Check that when
vCPUs are connected to their ICP in KVM before going any further.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210720134209.256133-3-clg@kaod.org

6 files changed, 57 insertions, 2 deletions

diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
index 8b211faa0e42..cf8bb6ac4463 100644
--- a/arch/powerpc/include/asm/xive-regs.h
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -80,10 +80,13 @@
 #define   TM_QW0W2_VU		PPC_BIT32(0)
 #define   TM_QW0W2_LOGIC_SERV	PPC_BITMASK32(1,31) // XX 2,31 ?
 #define   TM_QW1W2_VO		PPC_BIT32(0)
+#define   TM_QW1W2_HO           PPC_BIT32(1) /* P10 XIVE2 */
 #define   TM_QW1W2_OS_CAM	PPC_BITMASK32(8,31)
 #define   TM_QW2W2_VP		PPC_BIT32(0)
+#define   TM_QW2W2_HP           PPC_BIT32(1) /* P10 XIVE2 */
 #define   TM_QW2W2_POOL_CAM	PPC_BITMASK32(8,31)
 #define   TM_QW3W2_VT		PPC_BIT32(0)
+#define   TM_QW3W2_HT           PPC_BIT32(1) /* P10 XIVE2 */
 #define   TM_QW3W2_LP		PPC_BIT32(6)
 #define   TM_QW3W2_LE		PPC_BIT32(7)
 #define   TM_QW3W2_T		PPC_BIT32(31)
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index 20ae50ab083c..92930b0b5d0e 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -126,6 +126,7 @@ int xive_native_enable_vp(u32 vp_id, bool single_escalation);
 int xive_native_disable_vp(u32 vp_id);
 int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
 bool xive_native_has_single_escalation(void);
+bool xive_native_has_save_restore(void);
 
 int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
 			       u64 *out_qpage,
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 555cc610e7ab..912c1e9eef6b 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -59,6 +59,25 @@
  */
 #define XIVE_Q_GAP	2
 
+static bool kvmppc_xive_vcpu_has_save_restore(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+	/* Check enablement at VP level */
+	return xc->vp_cam & TM_QW1W2_HO;
+}
+
+bool kvmppc_xive_check_save_restore(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct kvmppc_xive *xive = xc->xive;
+
+	if (xive->flags & KVMPPC_XIVE_FLAG_SAVE_RESTORE)
+		return kvmppc_xive_vcpu_has_save_restore(vcpu);
+
+	return true;
+}
+
 /*
  * Push a vcpu's context to the XIVE on guest entry.
  * This assumes we are in virtual mode (MMU on)
@@ -77,7 +96,8 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu)
 		return;
 
 	eieio();
-	__raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS);
+	if (!kvmppc_xive_vcpu_has_save_restore(vcpu))
+		__raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS);
 	__raw_writel(vcpu->arch.xive_cam_word, tima + TM_QW1_OS + TM_WORD2);
 	vcpu->arch.xive_pushed = 1;
 	eieio();
@@ -149,7 +169,8 @@ void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu)
 	/* First load to pull the context, we ignore the value */
 	__raw_readl(tima + TM_SPC_PULL_OS_CTX);
 	/* Second load to recover the context state (Words 0 and 1) */
-	vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS);
+	if (!kvmppc_xive_vcpu_has_save_restore(vcpu))
+		vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS);
 
 	/* Fixup some of the state for the next load */
 	vcpu->arch.xive_saved_state.lsmfb = 0;
@@ -1319,6 +1340,12 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	if (r)
 		goto bail;
 
+	if (!kvmppc_xive_check_save_restore(vcpu)) {
+		pr_err("inconsistent save-restore setup for VCPU %d\n", cpu);
+		r = -EIO;
+		goto bail;
+	}
+
 	/* Configure VCPU fields for use by assembly push/pull */
 	vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
 	vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
@@ -2138,6 +2165,9 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	if (xive_native_has_single_escalation())
 		xive->flags |= KVMPPC_XIVE_FLAG_SINGLE_ESCALATION;
 
+	if (xive_native_has_save_restore())
+		xive->flags |= KVMPPC_XIVE_FLAG_SAVE_RESTORE;
+
 	kvm->arch.xive = xive;
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 73c3cd25093c..e6a9651c6f1e 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -98,6 +98,7 @@ struct kvmppc_xive_ops {
 };
 
 #define KVMPPC_XIVE_FLAG_SINGLE_ESCALATION 0x1
+#define KVMPPC_XIVE_FLAG_SAVE_RESTORE 0x2
 
 struct kvmppc_xive {
 	struct kvm *kvm;
@@ -309,6 +310,7 @@ void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
 				    struct kvmppc_xive_vcpu *xc, int irq);
 int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp);
 int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr);
+bool kvmppc_xive_check_save_restore(struct kvm_vcpu *vcpu);
 
 static inline bool kvmppc_xive_has_single_escalation(struct kvmppc_xive *xive)
 {
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 2abb1358a268..af65ea21bde7 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -168,6 +168,12 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 		goto bail;
 	}
 
+	if (!kvmppc_xive_check_save_restore(vcpu)) {
+		pr_err("inconsistent save-restore setup for VCPU %d\n", server_num);
+		rc = -EIO;
+		goto bail;
+	}
+
 	/*
 	 * Enable the VP first as the single escalation mode will
 	 * affect escalation interrupts numbering
@@ -1114,6 +1120,9 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	if (xive_native_has_single_escalation())
 		xive->flags |= KVMPPC_XIVE_FLAG_SINGLE_ESCALATION;
 
+	if (xive_native_has_save_restore())
+		xive->flags |= KVMPPC_XIVE_FLAG_SAVE_RESTORE;
+
 	xive->ops = &kvmppc_xive_native_ops;
 
 	kvm->arch.xive = xive;
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 57e3f1540435..1aec282cd650 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -41,6 +41,7 @@ static u32 xive_queue_shift;
 static u32 xive_pool_vps = XIVE_INVALID_VP;
 static struct kmem_cache *xive_provision_cache;
 static bool xive_has_single_esc;
+static bool xive_has_save_restore;
 
 int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
 {
@@ -588,6 +589,9 @@ bool __init xive_native_init(void)
 	if (of_get_property(np, "single-escalation-support", NULL) != NULL)
 		xive_has_single_esc = true;
 
+	if (of_get_property(np, "vp-save-restore", NULL))
+		xive_has_save_restore = true;
+
 	/* Configure Thread Management areas for KVM */
 	for_each_possible_cpu(cpu)
 		kvmppc_set_xive_tima(cpu, r.start, tima);
@@ -752,6 +756,12 @@ bool xive_native_has_single_escalation(void)
 }
 EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
 
+bool xive_native_has_save_restore(void)
+{
+	return xive_has_save_restore;
+}
+EXPORT_SYMBOL_GPL(xive_native_has_save_restore);
+
 int xive_native_get_queue_info(u32 vp_id, u32 prio,
 			       u64 *out_qpage,
 			       u64 *out_qsize,