KVM: PPC: Book3S HV: Make the guest hash table size configurable

This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.

There must be no vcpus running at the time of this ioctl.  To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.

If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out.  We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.

If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point.  We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.

When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool.  If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator.  Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB).  Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>

3 files changed, 8 insertions, 6 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index b0c08b142770..0dd1d86d3e31 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -36,11 +36,8 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 #define SPAPR_TCE_SHIFT		12
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER	24
-#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
-#define HPT_NPTE	(HPT_NPTEG << 3)		/* 8 PTEs per PTEG */
-#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+#define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
+extern int kvm_hpt_order;		/* order of preallocated HPTs */
 #endif
 
 #define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d848cdc49715..dd783beb88b3 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -237,6 +237,10 @@ struct kvm_arch {
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
+	u32 hpt_order;
+	atomic_t vcpus_running;
+	unsigned long hpt_npte;
+	unsigned long hpt_mask;
 	spinlock_t slot_phys_lock;
 	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
 	int slot_npages[KVM_MEM_SLOTS_NUM];
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f68c22fa2fce..0124937a23b9 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,7 +119,8 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
 extern void kvmppc_map_magic(struct kvm_vcpu *vcpu);
 
-extern long kvmppc_alloc_hpt(struct kvm *kvm);
+extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp);
+extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp);
 extern void kvmppc_free_hpt(struct kvm *kvm);
 extern long kvmppc_prepare_vrma(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);