X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=arch%2Fpowerpc%2Fkvm%2Fbook3s_hv_rm_mmu.c;h=c086eb0fa992504be49d22d15f74978d0edd26c5;hb=da9d1d7f2875cc8c1ffbce8f3501d0b33f4e7a4d;hp=bacb0cfa3602023ec28755766899d5433a20bf5c;hpb=7e95e365d5399647a41e10059e4b09826b82d78b;p=pandora-kernel.git

diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index bacb0cfa3602..c086eb0fa992 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>
@@ -20,95 +21,151 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER	24
-#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
-#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+/*
+ * Since this file is built in even if KVM is a module, we need
+ * a local copy of this function for the case where kvm_main.c is
+ * modular.
+ */
+static struct kvm_memory_slot *builtin_gfn_to_memslot(struct kvm *kvm,
+						gfn_t gfn)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
 
-#define HPTE_V_HVLOCK	0x40UL
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		if (gfn >= memslot->base_gfn &&
+		      gfn < memslot->base_gfn + memslot->npages)
+			return memslot;
+	return NULL;
+}
 
-static inline long lock_hpte(unsigned long *hpte, unsigned long bits)
+/* Translate address of a vmalloc'd thing to a linear map address */
+static void *real_vmalloc_addr(void *x)
 {
-	unsigned long tmp, old;
+	unsigned long addr = (unsigned long) x;
+	pte_t *p;
 
-	asm volatile("	ldarx	%0,0,%2\n"
-		     "	and.	%1,%0,%3\n"
-		     "	bne	2f\n"
-		     "	ori	%0,%0,%4\n"
-		     "  stdcx.	%0,0,%2\n"
-		     "	beq+	2f\n"
-		     "	li	%1,%3\n"
-		     "2:	isync"
-		     : "=&r" (tmp), "=&r" (old)
-		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
-		     : "cc", "memory");
-	return old == 0;
+	p = find_linux_pte(swapper_pg_dir, addr);
+	if (!p || !pte_present(*p))
+		return NULL;
+	/* assume we don't have huge pages in vmalloc space... */
+	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
+	return __va(addr);
 }
 
 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, 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, 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;
-	}
-	lpn = (ptel & HPTE_R_RPN) >> kvm->arch.ram_porder;
-	if (lpn >= kvm->arch.ram_npages || porder > kvm->arch.ram_porder)
+	psize = hpte_page_size(pteh, ptel);
+	if (!psize)
+		return H_PARAMETER;
+
+	/* 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;
+
+	/* Check if the requested page fits entirely in the memslot. */
+	if (!slot_is_aligned(memslot, psize))
+		return H_PARAMETER;
+	slot_fn = gfn - memslot->base_gfn;
+
+	physp = kvm->arch.slot_phys[memslot->id];
+	if (!physp)
 		return H_PARAMETER;
-	pa = kvm->arch.ram_pginfo[lpn].pfn << PAGE_SHIFT;
+	physp += slot_fn;
+	if (realmode)
+		physp = real_vmalloc_addr(physp);
+	pa = *physp;
 	if (!pa)
+		return H_TOO_HARD;
+	pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
+	pa &= PAGE_MASK;
+
+	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;
-	if (pte_index >= (HPT_NPTEG << 3))
+	pteh |= HPTE_V_VALID;
+
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	if (likely((flags & H_EXACT) == 0)) {
 		pte_index &= ~7UL;
 		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-		for (i = 0; ; ++i) {
-			if (i == 8)
-				return H_PTEG_FULL;
+		for (i = 0; i < 8; ++i) {
 			if ((*hpte & HPTE_V_VALID) == 0 &&
-			    lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
+			    try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
 				break;
 			hpte += 2;
 		}
+		if (i == 8) {
+			/*
+			 * Since try_lock_hpte doesn't retry (not even stdcx.
+			 * failures), it could be that there is a free slot
+			 * but we transiently failed to lock it.  Try again,
+			 * actually locking each slot and checking it.
+			 */
+			hpte -= 16;
+			for (i = 0; i < 8; ++i) {
+				while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+					cpu_relax();
+				if ((*hpte & HPTE_V_VALID) == 0)
+					break;
+				*hpte &= ~HPTE_V_HVLOCK;
+				hpte += 2;
+			}
+			if (i == 8)
+				return H_PTEG_FULL;
+		}
+		pte_index += i;
 	} else {
-		i = 0;
 		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-		if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
-			return H_PTEG_FULL;
+		if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID)) {
+			/* Lock the slot and check again */
+			while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+				cpu_relax();
+			if (*hpte & HPTE_V_VALID) {
+				*hpte &= ~HPTE_V_HVLOCK;
+				return H_PTEG_FULL;
+			}
+		}
 	}
+
+	/* Save away the guest's idea of the second HPTE dword */
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+	if (rev)
+		rev->guest_rpte = g_ptel;
 	hpte[1] = ptel;
 	eieio();
 	hpte[0] = pteh;
 	asm volatile("ptesync" : : : "memory");
-	atomic_inc(&kvm->arch.ram_pginfo[lpn].refcnt);
-	vcpu->arch.gpr[4] = pte_index + i;
+	vcpu->arch.gpr[4] = pte_index;
 	return H_SUCCESS;
 }
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
 
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
 
@@ -138,10 +195,10 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 	unsigned long *hpte;
 	unsigned long v, r, rb;
 
-	if (pte_index >= (HPT_NPTEG << 3))
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-	while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 		cpu_relax();
 	if ((hpte[0] & HPTE_V_VALID) == 0 ||
 	    ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) ||
@@ -193,14 +250,14 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 		if (req == 3)
 			break;
 		if (req != 1 || flags == 3 ||
-		    pte_index >= (HPT_NPTEG << 3)) {
+		    pte_index >= HPT_NPTE) {
 			/* parameter error */
 			args[i * 2] = ((0xa0 | flags) << 56) + pte_index;
 			ret = H_PARAMETER;
 			break;
 		}
 		hp = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-		while (!lock_hpte(hp, HPTE_V_HVLOCK))
+		while (!try_lock_hpte(hp, HPTE_V_HVLOCK))
 			cpu_relax();
 		found = 0;
 		if (hp[0] & HPTE_V_VALID) {
@@ -256,12 +313,13 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 {
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hpte;
-	unsigned long v, r, rb;
+	struct revmap_entry *rev;
+	unsigned long v, r, rb, mask, bits;
 
-	if (pte_index >= (HPT_NPTEG << 3))
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-	while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 		cpu_relax();
 	if ((hpte[0] & HPTE_V_VALID) == 0 ||
 	    ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) {
@@ -271,11 +329,21 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (atomic_read(&kvm->online_vcpus) == 1)
 		flags |= H_LOCAL;
 	v = hpte[0];
-	r = hpte[1] & ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
-			HPTE_R_KEY_HI | HPTE_R_KEY_LO);
-	r |= (flags << 55) & HPTE_R_PP0;
-	r |= (flags << 48) & HPTE_R_KEY_HI;
-	r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+	bits = (flags << 55) & HPTE_R_PP0;
+	bits |= (flags << 48) & HPTE_R_KEY_HI;
+	bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+
+	/* Update guest view of 2nd HPTE dword */
+	mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
+		HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+	if (rev) {
+		r = (rev->guest_rpte & ~mask) | bits;
+		rev->guest_rpte = r;
+	}
+	r = (hpte[1] & ~mask) | bits;
+
+	/* Update HPTE */
 	rb = compute_tlbie_rb(v, r, pte_index);
 	hpte[0] = v & ~HPTE_V_VALID;
 	if (!(flags & H_LOCAL)) {
@@ -298,38 +366,31 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	return H_SUCCESS;
 }
 
-static unsigned long reverse_xlate(struct kvm *kvm, unsigned long realaddr)
-{
-	long int i;
-	unsigned long offset, rpn;
-
-	offset = realaddr & (kvm->arch.ram_psize - 1);
-	rpn = (realaddr - offset) >> PAGE_SHIFT;
-	for (i = 0; i < kvm->arch.ram_npages; ++i)
-		if (rpn == kvm->arch.ram_pginfo[i].pfn)
-			return (i << PAGE_SHIFT) + offset;
-	return HPTE_R_RPN;	/* all 1s in the RPN field */
-}
-
 long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 		   unsigned long pte_index)
 {
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hpte, r;
 	int i, n = 1;
+	struct revmap_entry *rev = NULL;
 
-	if (pte_index >= (HPT_NPTEG << 3))
+	if (pte_index >= HPT_NPTE)
 		return H_PARAMETER;
 	if (flags & H_READ_4) {
 		pte_index &= ~3;
 		n = 4;
 	}
+	if (flags & H_R_XLATE)
+		rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
 	for (i = 0; i < n; ++i, ++pte_index) {
 		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
 		r = hpte[1];
-		if ((flags & H_R_XLATE) && (hpte[0] & HPTE_V_VALID))
-			r = reverse_xlate(kvm, r & HPTE_R_RPN) |
-				(r & ~HPTE_R_RPN);
+		if (hpte[0] & HPTE_V_VALID) {
+			if (rev)
+				r = rev[i].guest_rpte;
+			else
+				r = hpte[1] | HPTE_R_RPN;
+		}
 		vcpu->arch.gpr[4 + i * 2] = hpte[0];
 		vcpu->arch.gpr[5 + i * 2] = r;
 	}