KVM: PPC: Book3S PR: Allow guest to use 1TB segments

With this, the guest can use 1TB segments as well as 256MB segments.
Since we now have the situation where a single emulated guest segment
could correspond to multiple shadow segments (as the shadow segments
are still 256MB segments), this adds a new kvmppc_mmu_flush_segment()
to scan for all shadow segments that need to be removed.

This restructures the guest HPT (hashed page table) lookup code to
use the correct hashing and matching functions for HPTEs within a
1TB segment.  We use the standard hpt_hash() function instead of
open-coding the hash calculation, and we use HPTE_V_COMPARE() with
an AVPN value that has the B (segment size) field included.  The
calculation of avpn is done a little earlier since it doesn't change
in the loop starting at the do_second label.

The computation in kvmppc_mmu_book3s_64_esid_to_vsid() changes so that
it returns a 256MB VSID even if the guest SLB entry is a 1TB entry.
This is because the users of this function are creating 256MB SLB
entries.  We set a new VSID_1T flag so that entries created from 1T
segments don't collide with entries from 256MB segments.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s.h

@@ -107,8 +107,9 @@ struct kvmppc_vcpu_book3s {
 #define CONTEXT_GUEST		1
 #define CONTEXT_GUEST_END	2
 
-#define VSID_REAL	0x1fffffffffc00000ULL
-#define VSID_BAT	0x1fffffffffb00000ULL
+#define VSID_REAL	0x0fffffffffc00000ULL
+#define VSID_BAT	0x0fffffffffb00000ULL
+#define VSID_1T		0x1000000000000000ULL
 #define VSID_REAL_DR	0x2000000000000000ULL
 #define VSID_REAL_IR	0x4000000000000000ULL
 #define VSID_PR		0x8000000000000000ULL
@@ -123,6 +124,7 @@ extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
+extern void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong eaddr, ulong seg_size);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
 extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run,
 			struct kvm_vcpu *vcpu, unsigned long addr,

arch/powerpc/kvm/book3s_64_mmu.c

@@ -26,6 +26,7 @@
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
+#include <asm/mmu-hash64.h>
 
 /* #define DEBUG_MMU */
 
@@ -76,6 +77,24 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
 	return NULL;
 }
 
+static int kvmppc_slb_sid_shift(struct kvmppc_slb *slbe)
+{
+	return slbe->tb ? SID_SHIFT_1T : SID_SHIFT;
+}
+
+static u64 kvmppc_slb_offset_mask(struct kvmppc_slb *slbe)
+{
+	return (1ul << kvmppc_slb_sid_shift(slbe)) - 1;
+}
+
+static u64 kvmppc_slb_calc_vpn(struct kvmppc_slb *slb, gva_t eaddr)
+{
+	eaddr &= kvmppc_slb_offset_mask(slb);
+
+	return (eaddr >> VPN_SHIFT) |
+		((slb->vsid) << (kvmppc_slb_sid_shift(slb) - VPN_SHIFT));
+}
+
 static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 					 bool data)
 {
@@ -85,11 +104,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	if (!slb)
 		return 0;
 
-	if (slb->tb)
-		return (((u64)eaddr >> 12) & 0xfffffff) |
-		       (((u64)slb->vsid) << 28);
-
-	return (((u64)eaddr >> 12) & 0xffff) | (((u64)slb->vsid) << 16);
+	return kvmppc_slb_calc_vpn(slb, eaddr);
 }
 
 static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe)
@@ -100,7 +115,8 @@ static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe)
 static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
 {
 	int p = kvmppc_mmu_book3s_64_get_pagesize(slbe);
-	return ((eaddr & 0xfffffff) >> p);
+
+	return ((eaddr & kvmppc_slb_offset_mask(slbe)) >> p);
 }
 
 static hva_t kvmppc_mmu_book3s_64_get_pteg(
@@ -109,13 +125,15 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg(
 				bool second)
 {
 	u64 hash, pteg, htabsize;
-	u32 page;
+	u32 ssize;
 	hva_t r;
+	u64 vpn;
 
-	page = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
 	htabsize = ((1 << ((vcpu_book3s->sdr1 & 0x1f) + 11)) - 1);
 
-	hash = slbe->vsid ^ page;
+	vpn = kvmppc_slb_calc_vpn(slbe, eaddr);
+	ssize = slbe->tb ? MMU_SEGSIZE_1T : MMU_SEGSIZE_256M;
+	hash = hpt_hash(vpn, kvmppc_mmu_book3s_64_get_pagesize(slbe), ssize);
 	if (second)
 		hash = ~hash;
 	hash &= ((1ULL << 39ULL) - 1ULL);
@@ -146,7 +164,7 @@ static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr)
 	u64 avpn;
 
 	avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
-	avpn |= slbe->vsid << (28 - p);
+	avpn |= slbe->vsid << (kvmppc_slb_sid_shift(slbe) - p);
 
 	if (p < 24)
 		avpn >>= ((80 - p) - 56) - 8;
@@ -189,13 +207,15 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	if (!slbe)
 		goto no_seg_found;
 
+	avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr);
+	if (slbe->tb)
+		avpn |= SLB_VSID_B_1T;
+
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
 	if (kvm_is_error_hva(ptegp))
 		goto no_page_found;
 
-	avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr);
-
 	if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) {
 		printk(KERN_ERR "KVM can't copy data from 0x%lx!\n", ptegp);
 		goto no_page_found;
@@ -218,7 +238,7 @@ do_second:
 			continue;
 
 		/* AVPN compare */
-		if (HPTE_V_AVPN_VAL(avpn) == HPTE_V_AVPN_VAL(v)) {
+		if (HPTE_V_COMPARE(avpn, v)) {
 			u8 pp = (r & HPTE_R_PP) | key;
 			int eaddr_mask = 0xFFF;
 
@@ -324,7 +344,7 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	slbe->large = (rs & SLB_VSID_L) ? 1 : 0;
 	slbe->tb    = (rs & SLB_VSID_B_1T) ? 1 : 0;
 	slbe->esid  = slbe->tb ? esid_1t : esid;
-	slbe->vsid  = rs >> 12;
+	slbe->vsid  = (rs & ~SLB_VSID_B) >> (kvmppc_slb_sid_shift(slbe) - 16);
 	slbe->valid = (rb & SLB_ESID_V) ? 1 : 0;
 	slbe->Ks    = (rs & SLB_VSID_KS) ? 1 : 0;
 	slbe->Kp    = (rs & SLB_VSID_KP) ? 1 : 0;
@@ -365,6 +385,7 @@ static u64 kvmppc_mmu_book3s_64_slbmfev(struct kvm_vcpu *vcpu, u64 slb_nr)
 static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea)
 {
 	struct kvmppc_slb *slbe;
+	u64 seg_size;
 
 	dprintk("KVM MMU: slbie(0x%llx)\n", ea);
 
@@ -377,7 +398,8 @@ static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea)
 
 	slbe->valid = false;
 
-	kvmppc_mmu_map_segment(vcpu, ea);
+	seg_size = 1ull << kvmppc_slb_sid_shift(slbe);
+	kvmppc_mmu_flush_segment(vcpu, ea & ~(seg_size - 1), seg_size);
 }
 
 static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu)
@@ -457,8 +479,14 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
-		if (slb)
+		if (slb) {
 			gvsid = slb->vsid;
+			if (slb->tb) {
+				gvsid <<= SID_SHIFT_1T - SID_SHIFT;
+				gvsid |= esid & ((1ul << (SID_SHIFT_1T - SID_SHIFT)) - 1);
+				gvsid |= VSID_1T;
+			}
+		}
 	}
 
 	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -301,6 +301,23 @@ out:
 	return r;
 }
 
+void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong ea, ulong seg_size)
+{
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong seg_mask = -seg_size;
+	int i;
+
+	for (i = 1; i < svcpu->slb_max; i++) {
+		if ((svcpu->slb[i].esid & SLB_ESID_V) &&
+		    (svcpu->slb[i].esid & seg_mask) == ea) {
+			/* Invalidate this entry */
+			svcpu->slb[i].esid = 0;
+		}
+	}
+
+	svcpu_put(svcpu);
+}
+
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);

arch/powerpc/kvm/book3s_pr.c

@@ -1239,8 +1239,7 @@ out:
 #ifdef CONFIG_PPC64
 int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 {
-	/* No flags */
-	info->flags = 0;
+	info->flags = KVM_PPC_1T_SEGMENTS;
 
 	/* SLB is always 64 entries */
 	info->slb_size = 64;