KVM: PPC: Accelerate H_PUT_TCE by implementing it in real mode

This improves I/O performance for guests using the PAPR
paravirtualization interface by making the H_PUT_TCE hcall faster, by
implementing it in real mode.  H_PUT_TCE is used for updating virtual
IOMMU tables, and is used both for virtual I/O and for real I/O in the
PAPR interface.

Since this moves the IOMMU tables into the kernel, we define a new
KVM_CREATE_SPAPR_TCE ioctl to allow qemu to create the tables.  The
ioctl returns a file descriptor which can be used to mmap the newly
created table.  The qemu driver models use them in the same way as
userspace managed tables, but they can be updated directly by the
guest with a real-mode H_PUT_TCE implementation, reducing the number
of host/guest context switches during guest IO.

There are certain circumstances where it is useful for userland qemu
to write to the TCE table even if the kernel H_PUT_TCE path is used
most of the time.  Specifically, allowing this will avoid awkwardness
when we need to reset the table.  More importantly, we will in the
future need to write the table in order to restore its state after a
checkpoint resume or migration.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

4 files changed, 22 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index d2ca5ed3877b..c3ec990daf45 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -22,6 +22,9 @@
 
 #include <linux/types.h>
 
+/* Select powerpc specific features in <linux/kvm.h> */
+#define __KVM_HAVE_SPAPR_TCE
+
 struct kvm_regs {
 	__u64 pc;
 	__u64 cr;
@@ -272,4 +275,10 @@ struct kvm_guest_debug_arch {
 #define KVM_INTERRUPT_UNSET	-2U
 #define KVM_INTERRUPT_SET_LEVEL	-3U
 
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+	__u64 liobn;
+	__u32 window_size;
+};
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 5f73388ea0af..e43fe42b9875 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -27,4 +27,6 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
 }
 #endif
 
+#define SPAPR_TCE_SHIFT		12
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 6ebf1721680a..5616e39a7fa4 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -144,6 +144,14 @@ struct kvmppc_pginfo {
 	atomic_t refcnt;
 };
 
+struct kvmppc_spapr_tce_table {
+	struct list_head list;
+	struct kvm *kvm;
+	u64 liobn;
+	u32 window_size;
+	struct page *pages[0];
+};
+
 struct kvm_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long hpt_virt;
@@ -157,6 +165,7 @@ struct kvm_arch {
 	unsigned long sdr1;
 	unsigned long host_sdr1;
 	int tlbie_lock;
+	struct list_head spapr_tce_tables;
 	unsigned short last_vcpu[NR_CPUS];
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2afe92e6f625..99f6fcf4cf88 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,6 +119,8 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 extern void kvmppc_map_vrma(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
+				struct kvm_create_spapr_tce *args);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,