KVM: PPC: Book3S PR: Allow guest to use 64k pages

This adds the code to interpret 64k HPTEs in the guest hashed page
table (HPT), 64k SLB entries, and to tell the guest about 64k pages
in kvm_vm_ioctl_get_smmu_info().  Guest 64k pages are still shadowed
by 4k pages.

This also adds another hash table to the four we have already in
book3s_mmu_hpte.c to allow us to find all the PTEs that we have
instantiated that match a given 64k guest page.

The tlbie instruction changed starting with POWER6 to use a bit in
the RB operand to indicate large page invalidations, and to use other
RB bits to indicate the base and actual page sizes and the segment
size.  64k pages came in slightly earlier, with POWER5++.
We use one bit in vcpu->arch.hflags to indicate that the emulated
cpu supports 64k pages, and another to indicate that it has the new
tlbie definition.

The KVM_PPC_GET_SMMU_INFO ioctl presents a bit of a problem, because
the MMU capabilities depend on which CPU model we're emulating, but it
is a VM ioctl not a VCPU ioctl and therefore doesn't get passed a VCPU
fd.  In addition, commonly-used userspace (QEMU) calls it before
setting the PVR for any VCPU.  Therefore, as a best effort we look at
the first vcpu in the VM and return 64k pages or not depending on its
capabilities.  We also make the PVR default to the host PVR on recent
CPUs that support 1TB segments (and therefore multiple page sizes as
well) so that KVM_PPC_GET_SMMU_INFO will include 64k page and 1TB
segment support on those CPUs.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_asm.h

@@ -123,6 +123,8 @@
 #define BOOK3S_HFLAG_SLB			0x2
 #define BOOK3S_HFLAG_PAIRED_SINGLE		0x4
 #define BOOK3S_HFLAG_NATIVE_PS			0x8
+#define BOOK3S_HFLAG_MULTI_PGSIZE		0x10
+#define BOOK3S_HFLAG_NEW_TLBIE			0x20
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */

arch/powerpc/include/asm/kvm_book3s.h

@@ -58,6 +58,9 @@ struct hpte_cache {
 	struct hlist_node list_pte_long;
 	struct hlist_node list_vpte;
 	struct hlist_node list_vpte_long;
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct hlist_node list_vpte_64k;
+#endif
 	struct rcu_head rcu_head;
 	u64 host_vpn;
 	u64 pfn;
@@ -99,6 +102,9 @@ struct kvmppc_vcpu_book3s {
 	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
 	struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct hlist_head hpte_hash_vpte_64k[HPTEG_HASH_NUM_VPTE_64K];
+#endif
 	int hpte_cache_count;
 	spinlock_t mmu_lock;
 };

arch/powerpc/include/asm/kvm_host.h

@@ -68,10 +68,12 @@ extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 #define HPTEG_HASH_BITS_PTE_LONG	12
 #define HPTEG_HASH_BITS_VPTE		13
 #define HPTEG_HASH_BITS_VPTE_LONG	5
+#define HPTEG_HASH_BITS_VPTE_64K	11
 #define HPTEG_HASH_NUM_PTE		(1 << HPTEG_HASH_BITS_PTE)
 #define HPTEG_HASH_NUM_PTE_LONG		(1 << HPTEG_HASH_BITS_PTE_LONG)
 #define HPTEG_HASH_NUM_VPTE		(1 << HPTEG_HASH_BITS_VPTE)
 #define HPTEG_HASH_NUM_VPTE_LONG	(1 << HPTEG_HASH_BITS_VPTE_LONG)
+#define HPTEG_HASH_NUM_VPTE_64K		(1 << HPTEG_HASH_BITS_VPTE_64K)
 
 /* Physical Address Mask - allowed range of real mode RAM access */
 #define KVM_PAM			0x0fffffffffffffffULL
@@ -327,6 +329,7 @@ struct kvmppc_pte {
 	bool may_read		: 1;
 	bool may_write		: 1;
 	bool may_execute	: 1;
+	u8 page_size;		/* MMU_PAGE_xxx */
 };
 
 struct kvmppc_mmu {
@@ -359,6 +362,7 @@ struct kvmppc_slb {
 	bool large	: 1;	/* PTEs are 16MB */
 	bool tb		: 1;	/* 1TB segment */
 	bool class	: 1;
+	u8 base_page_size;	/* MMU_PAGE_xxx */
 };
 
 # ifdef CONFIG_PPC_FSL_BOOK3E

arch/powerpc/kvm/book3s_64_mmu.c

@@ -107,9 +107,20 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	return kvmppc_slb_calc_vpn(slb, eaddr);
 }
 
+static int mmu_pagesize(int mmu_pg)
+{
+	switch (mmu_pg) {
+	case MMU_PAGE_64K:
+		return 16;
+	case MMU_PAGE_16M:
+		return 24;
+	}
+	return 12;
+}
+
 static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe)
 {
-	return slbe->large ? 24 : 12;
+	return mmu_pagesize(slbe->base_page_size);
 }
 
 static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
@@ -166,14 +177,34 @@ static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr)
 	avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
 	avpn |= slbe->vsid << (kvmppc_slb_sid_shift(slbe) - p);
 
-	if (p < 24)
-		avpn >>= ((80 - p) - 56) - 8;
+	if (p < 16)
+		avpn >>= ((80 - p) - 56) - 8;	/* 16 - p */
 	else
-		avpn <<= 8;
+		avpn <<= p - 16;
 
 	return avpn;
 }
 
+/*
+ * Return page size encoded in the second word of a HPTE, or
+ * -1 for an invalid encoding for the base page size indicated by
+ * the SLB entry.  This doesn't handle mixed pagesize segments yet.
+ */
+static int decode_pagesize(struct kvmppc_slb *slbe, u64 r)
+{
+	switch (slbe->base_page_size) {
+	case MMU_PAGE_64K:
+		if ((r & 0xf000) == 0x1000)
+			return MMU_PAGE_64K;
+		break;
+	case MMU_PAGE_16M:
+		if ((r & 0xff000) == 0)
+			return MMU_PAGE_16M;
+		break;
+	}
+	return -1;
+}
+
 static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 				struct kvmppc_pte *gpte, bool data)
 {
@@ -189,6 +220,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u8 pp, key = 0;
 	bool found = false;
 	bool second = false;
+	int pgsize;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	/* Magic page override */
@@ -202,6 +234,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		gpte->may_execute = true;
 		gpte->may_read = true;
 		gpte->may_write = true;
+		gpte->page_size = MMU_PAGE_4K;
 
 		return 0;
 	}
@@ -222,6 +255,8 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID |
 		HPTE_V_SECONDARY;
 
+	pgsize = slbe->large ? MMU_PAGE_16M : MMU_PAGE_4K;
+
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
 	if (kvm_is_error_hva(ptegp))
@@ -240,6 +275,13 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	for (i=0; i<16; i+=2) {
 		/* Check all relevant fields of 1st dword */
 		if ((pteg[i] & v_mask) == v_val) {
+			/* If large page bit is set, check pgsize encoding */
+			if (slbe->large &&
+			    (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) {
+				pgsize = decode_pagesize(slbe, pteg[i+1]);
+				if (pgsize < 0)
+					continue;
+			}
 			found = true;
 			break;
 		}
@@ -256,13 +298,13 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	v = pteg[i];
 	r = pteg[i+1];
 	pp = (r & HPTE_R_PP) | key;
-	eaddr_mask = 0xFFF;
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
-	if (slbe->large)
-		eaddr_mask = 0xFFFFFF;
+
+	eaddr_mask = (1ull << mmu_pagesize(pgsize)) - 1;
 	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
+	gpte->page_size = pgsize;
 	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
 	gpte->may_read = false;
 	gpte->may_write = false;
@@ -345,6 +387,21 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	slbe->nx    = (rs & SLB_VSID_N) ? 1 : 0;
 	slbe->class = (rs & SLB_VSID_C) ? 1 : 0;
 
+	slbe->base_page_size = MMU_PAGE_4K;
+	if (slbe->large) {
+		if (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE) {
+			switch (rs & SLB_VSID_LP) {
+			case SLB_VSID_LP_00:
+				slbe->base_page_size = MMU_PAGE_16M;
+				break;
+			case SLB_VSID_LP_01:
+				slbe->base_page_size = MMU_PAGE_64K;
+				break;
+			}
+		} else
+			slbe->base_page_size = MMU_PAGE_16M;
+	}
+
 	slbe->orige = rb & (ESID_MASK | SLB_ESID_V);
 	slbe->origv = rs;
 
@@ -463,8 +520,25 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 
 	dprintk("KVM MMU: tlbie(0x%lx)\n", va);
 
-	if (large)
-		mask = 0xFFFFFF000ULL;
+	/*
+	 * The tlbie instruction changed behaviour starting with
+	 * POWER6.  POWER6 and later don't have the large page flag
+	 * in the instruction but in the RB value, along with bits
+	 * indicating page and segment sizes.
+	 */
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_NEW_TLBIE) {
+		/* POWER6 or later */
+		if (va & 1) {		/* L bit */
+			if ((va & 0xf000) == 0x1000)
+				mask = 0xFFFFFFFF0ULL;	/* 64k page */
+			else
+				mask = 0xFFFFFF000ULL;	/* 16M page */
+		}
+	} else {
+		/* older processors, e.g. PPC970 */
+		if (large)
+			mask = 0xFFFFFF000ULL;
+	}
 	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
 }
 

arch/powerpc/kvm/book3s_mmu_hpte.c

@@ -56,6 +56,14 @@ static inline u64 kvmppc_mmu_hash_vpte_long(u64 vpage)
 		       HPTEG_HASH_BITS_VPTE_LONG);
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline u64 kvmppc_mmu_hash_vpte_64k(u64 vpage)
+{
+	return hash_64((vpage & 0xffffffff0ULL) >> 4,
+		       HPTEG_HASH_BITS_VPTE_64K);
+}
+#endif
+
 void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	u64 index;
@@ -83,6 +91,13 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_add_head_rcu(&pte->list_vpte_long,
 			   &vcpu3s->hpte_hash_vpte_long[index]);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Add to vPTE_64k list */
+	index = kvmppc_mmu_hash_vpte_64k(pte->pte.vpage);
+	hlist_add_head_rcu(&pte->list_vpte_64k,
+			   &vcpu3s->hpte_hash_vpte_64k[index]);
+#endif
+
 	spin_unlock(&vcpu3s->mmu_lock);
 }
 
@@ -113,6 +128,9 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_del_init_rcu(&pte->list_pte_long);
 	hlist_del_init_rcu(&pte->list_vpte);
 	hlist_del_init_rcu(&pte->list_vpte_long);
+#ifdef CONFIG_PPC_BOOK3S_64
+	hlist_del_init_rcu(&pte->list_vpte_64k);
+#endif
 
 	spin_unlock(&vcpu3s->mmu_lock);
 
@@ -219,6 +237,29 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Flush with mask 0xffffffff0 */
+static void kvmppc_mmu_pte_vflush_64k(struct kvm_vcpu *vcpu, u64 guest_vp)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	struct hlist_head *list;
+	struct hpte_cache *pte;
+	u64 vp_mask = 0xffffffff0ULL;
+
+	list = &vcpu3s->hpte_hash_vpte_64k[
+		kvmppc_mmu_hash_vpte_64k(guest_vp)];
+
+	rcu_read_lock();
+
+	/* Check the list for matching entries and invalidate */
+	hlist_for_each_entry_rcu(pte, list, list_vpte_64k)
+		if ((pte->pte.vpage & vp_mask) == guest_vp)
+			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
+}
+#endif
+
 /* Flush with mask 0xffffff000 */
 static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
@@ -249,6 +290,11 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 	case 0xfffffffffULL:
 		kvmppc_mmu_pte_vflush_short(vcpu, guest_vp);
 		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case 0xffffffff0ULL:
+		kvmppc_mmu_pte_vflush_64k(vcpu, guest_vp);
+		break;
+#endif
 	case 0xffffff000ULL:
 		kvmppc_mmu_pte_vflush_long(vcpu, guest_vp);
 		break;
@@ -320,6 +366,10 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
 				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte));
 	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_long,
 				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_long));
+#ifdef CONFIG_PPC_BOOK3S_64
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_64k,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_64k));
+#endif
 
 	spin_lock_init(&vcpu3s->mmu_lock);
 

arch/powerpc/kvm/book3s_pr.c

@@ -306,6 +306,23 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
 		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);
 
+	/*
+	 * If they're asking for POWER6 or later, set the flag
+	 * indicating that we can do multiple large page sizes
+	 * and 1TB segments.
+	 * Also set the flag that indicates that tlbie has the large
+	 * page bit in the RB operand instead of the instruction.
+	 */
+	switch (PVR_VER(pvr)) {
+	case PVR_POWER6:
+	case PVR_POWER7:
+	case PVR_POWER7p:
+	case PVR_POWER8:
+		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
+			BOOK3S_HFLAG_NEW_TLBIE;
+		break;
+	}
+
 #ifdef CONFIG_PPC_BOOK3S_32
 	/* 32 bit Book3S always has 32 byte dcbz */
 	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
@@ -1130,8 +1147,14 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* default to book3s_64 (970fx) */
+	/*
+	 * Default to the same as the host if we're on sufficiently
+	 * recent machine that we have 1TB segments;
+	 * otherwise default to PPC970FX.
+	 */
 	vcpu->arch.pvr = 0x3C0301;
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		vcpu->arch.pvr = mfspr(SPRN_PVR);
 #else
 	/* default to book3s_32 (750) */
 	vcpu->arch.pvr = 0x84202;
@@ -1317,7 +1340,10 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 #ifdef CONFIG_PPC64
 int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 {
-	info->flags = KVM_PPC_1T_SEGMENTS;
+	long int i;
+	struct kvm_vcpu *vcpu;
+
+	info->flags = 0;
 
 	/* SLB is always 64 entries */
 	info->slb_size = 64;
@@ -1328,11 +1354,31 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 	info->sps[0].enc[0].page_shift = 12;
 	info->sps[0].enc[0].pte_enc = 0;
 
+	/*
+	 * 64k large page size.
+	 * We only want to put this in if the CPUs we're emulating
+	 * support it, but unfortunately we don't have a vcpu easily
+	 * to hand here to test.  Just pick the first vcpu, and if
+	 * that doesn't exist yet, report the minimum capability,
+	 * i.e., no 64k pages.
+	 * 1T segment support goes along with 64k pages.
+	 */
+	i = 1;
+	vcpu = kvm_get_vcpu(kvm, 0);
+	if (vcpu && (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) {
+		info->flags = KVM_PPC_1T_SEGMENTS;
+		info->sps[i].page_shift = 16;
+		info->sps[i].slb_enc = SLB_VSID_L | SLB_VSID_LP_01;
+		info->sps[i].enc[0].page_shift = 16;
+		info->sps[i].enc[0].pte_enc = 1;
+		++i;
+	}
+
 	/* Standard 16M large page size segment */
-	info->sps[1].page_shift = 24;
-	info->sps[1].slb_enc = SLB_VSID_L;
-	info->sps[1].enc[0].page_shift = 24;
-	info->sps[1].enc[0].pte_enc = 0;
+	info->sps[i].page_shift = 24;
+	info->sps[i].slb_enc = SLB_VSID_L;
+	info->sps[i].enc[0].page_shift = 24;
+	info->sps[i].enc[0].pte_enc = 0;
 
 	return 0;
 }