KVM: PPC: Only get pages when actually needed, not in prepare_memory_region()

This removes the code from kvmppc_core_prepare_memory_region() that
looked up the VMA for the region being added and called hva_to_page
to get the pfns for the memory.  We have no guarantee that there will
be anything mapped there at the time of the KVM_SET_USER_MEMORY_REGION
ioctl call; userspace can do that ioctl and then map memory into the
region later.

Instead we defer looking up the pfn for each memory page until it is
needed, which generally means when the guest does an H_ENTER hcall on
the page.  Since we can't call get_user_pages in real mode, if we don't
already have the pfn for the page, kvmppc_h_enter() will return
H_TOO_HARD and we then call kvmppc_virtmode_h_enter() once we get back
to kernel context.  That calls kvmppc_get_guest_page() to get the pfn
for the page, and then calls back to kvmppc_h_enter() to redo the HPTE
insertion.

When the first vcpu starts executing, we need to have the RMO or VRMA
region mapped so that the guest's real mode accesses will work.  Thus
we now have a check in kvmppc_vcpu_run() to see if the RMO/VRMA is set
up and if not, call kvmppc_hv_setup_rma().  It checks if the memslot
starting at guest physical 0 now has RMO memory mapped there; if so it
sets it up for the guest, otherwise on POWER7 it sets up the VRMA.
The function that does that, kvmppc_map_vrma, is now a bit simpler,
as it calls kvmppc_virtmode_h_enter instead of creating the HPTE itself.

Since we are now potentially updating entries in the slot_phys[]
arrays from multiple vcpu threads, we now have a spinlock protecting
those updates to ensure that we don't lose track of any references
to pages.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 27 insertions, 27 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index a28a6030ec90..047c5e1fd70f 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/hugetlb.h>
+#include <linux/module.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -56,56 +57,54 @@ static void *real_vmalloc_addr(void *x)
 long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 		    long pte_index, unsigned long pteh, unsigned long ptel)
 {
-	unsigned long porder;
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long i, gfn, lpn, pa;
+	unsigned long i, pa, gpa, gfn, psize;
+	unsigned long slot_fn;
 	unsigned long *hpte;
 	struct revmap_entry *rev;
 	unsigned long g_ptel = ptel;
 	struct kvm_memory_slot *memslot;
-	unsigned long *physp;
+	unsigned long *physp, pte_size;
+	bool realmode = vcpu->arch.vcore->vcore_state == VCORE_RUNNING;
 
-	/* only handle 4k, 64k and 16M pages for now */
-	porder = 12;
-	if (pteh & HPTE_V_LARGE) {
-		if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-		    (ptel & 0xf000) == 0x1000) {
-			/* 64k page */
-			porder = 16;
-		} else if ((ptel & 0xff000) == 0) {
-			/* 16M page */
-			porder = 24;
-			/* lowest AVA bit must be 0 for 16M pages */
-			if (pteh & 0x80)
-				return H_PARAMETER;
-		} else
-			return H_PARAMETER;
-	}
-	if (porder > kvm->arch.ram_porder)
+	psize = hpte_page_size(pteh, ptel);
+	if (!psize)
 		return H_PARAMETER;
 
-	gfn = ((ptel & HPTE_R_RPN) & ~((1ul << porder) - 1)) >> PAGE_SHIFT;
+	/* Find the memslot (if any) for this address */
+	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
+	gfn = gpa >> PAGE_SHIFT;
 	memslot = builtin_gfn_to_memslot(kvm, gfn);
 	if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)))
 		return H_PARAMETER;
+	slot_fn = gfn - memslot->base_gfn;
+
 	physp = kvm->arch.slot_phys[memslot->id];
 	if (!physp)
 		return H_PARAMETER;
-
-	lpn = (gfn - memslot->base_gfn) >> (kvm->arch.ram_porder - PAGE_SHIFT);
-	physp = real_vmalloc_addr(physp + lpn);
+	physp += slot_fn;
+	if (realmode)
+		physp = real_vmalloc_addr(physp);
 	pa = *physp;
 	if (!pa)
-		return H_PARAMETER;
+		return H_TOO_HARD;
 	pa &= PAGE_MASK;
 
+	pte_size = kvm->arch.ram_psize;
+	if (pte_size < psize)
+		return H_PARAMETER;
+	if (pa && pte_size > psize)
+		pa |= gpa & (pte_size - 1);
+
+	ptel &= ~(HPTE_R_PP0 - psize);
+	ptel |= pa;
+
 	/* Check WIMG */
 	if ((ptel & HPTE_R_WIMG) != HPTE_R_M &&
 	    (ptel & HPTE_R_WIMG) != (HPTE_R_W | HPTE_R_I | HPTE_R_M))
 		return H_PARAMETER;
 	pteh &= ~0x60UL;
-	ptel &= ~(HPTE_R_PP0 - kvm->arch.ram_psize);
-	ptel |= pa;
+	pteh |= HPTE_V_VALID;
 
 	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
@@ -162,6 +161,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	vcpu->arch.gpr[4] = pte_index;
 	return H_SUCCESS;
 }
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
 
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))