Merge branch 'kvm-ppc-next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into next

PPC KVM updates for 4.9.

- Fix for the bug that Thomas Huth found which caused guests to falsely
  report soft lockups,
- other minor fixes from Thomas Huth and Dan Carpenter,
- and a small optimization from Balbir Singh.

11 files changed, 34 insertions, 143 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index cef2b892245c..5cf306ae0ac3 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -101,6 +101,7 @@ struct kvmppc_vcore {
 	u32 arch_compat;
 	ulong pcr;
 	ulong dpdes;		/* doorbell state (POWER8) */
+	ulong vtb;		/* virtual timebase */
 	ulong conferring_threads;
 	unsigned int halt_poll_ns;
 };
@@ -119,6 +120,7 @@ struct kvmppc_vcpu_book3s {
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
+	u64 vtb;
 #ifdef CONFIG_PPC_BOOK3S_32
 	u32 vsid_pool[VSID_POOL_SIZE];
 	u32 vsid_next;
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 4ffd5a1e788d..848292176908 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -125,7 +125,6 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	/* This covers 14..54 bits of va*/
 	rb = (v & ~0x7fUL) << 16;		/* AVA field */
 
-	rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8;	/*  B field */
 	/*
 	 * AVA in v had cleared lower 23 bits. We need to derive
 	 * that from pteg index
@@ -177,7 +176,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 		break;
 	}
 	}
-	rb |= (v >> 54) & 0x300;		/* B field */
+	rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8;	/* B field */
 	return rb;
 }
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ed30d2ea21b7..28350a294b1e 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -475,7 +475,6 @@ struct kvm_vcpu_arch {
 	ulong purr;
 	ulong spurr;
 	ulong ic;
-	ulong vtb;
 	ulong dscr;
 	ulong amr;
 	ulong uamor;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f69f40f1519a..978dada662ae 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -737,6 +737,7 @@
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
 #define SPRN_MMCR2	785
+#define SPRN_UMMCR2	769
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b89d14c0352c..a51ae9b165e0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -506,7 +506,6 @@ int main(void)
 	DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
 	DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
 	DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic));
-	DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb));
 	DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
 	DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
 	DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
@@ -557,6 +556,7 @@ int main(void)
 	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
 	DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
 	DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes));
+	DEFINE(VCORE_VTB, offsetof(struct kvmppc_vcore, vtb));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
 	DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
 	DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index ba231a1d43d4..b6952dd23152 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -599,9 +599,6 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 		case KVM_REG_PPC_BESCR:
 			*val = get_reg_val(id, vcpu->arch.bescr);
 			break;
-		case KVM_REG_PPC_VTB:
-			*val = get_reg_val(id, vcpu->arch.vtb);
-			break;
 		case KVM_REG_PPC_IC:
 			*val = get_reg_val(id, vcpu->arch.ic);
 			break;
@@ -673,9 +670,6 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 		case KVM_REG_PPC_BESCR:
 			vcpu->arch.bescr = set_reg_val(id, *val);
 			break;
-		case KVM_REG_PPC_VTB:
-			vcpu->arch.vtb = set_reg_val(id, *val);
-			break;
 		case KVM_REG_PPC_IC:
 			vcpu->arch.ic = set_reg_val(id, *val);
 			break;
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 2afdb9c0937d..8359752b3efc 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -498,6 +498,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_MMCR0:
 	case SPRN_MMCR1:
 	case SPRN_MMCR2:
+	case SPRN_UMMCR2:
 #endif
 		break;
 unprivileged:
@@ -579,7 +580,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
 		*spr_val = vcpu->arch.spurr;
 		break;
 	case SPRN_VTB:
-		*spr_val = vcpu->arch.vtb;
+		*spr_val = to_book3s(vcpu)->vtb;
 		break;
 	case SPRN_IC:
 		*spr_val = vcpu->arch.ic;
@@ -640,6 +641,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
 	case SPRN_MMCR0:
 	case SPRN_MMCR1:
 	case SPRN_MMCR2:
+	case SPRN_UMMCR2:
 	case SPRN_TIR:
 #endif
 		*spr_val = 0;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9b3bba643b43..3686471be32b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1199,6 +1199,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_DPDES:
 		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
 		break;
+	case KVM_REG_PPC_VTB:
+		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
+		break;
 	case KVM_REG_PPC_DAWR:
 		*val = get_reg_val(id, vcpu->arch.dawr);
 		break;
@@ -1391,6 +1394,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_DPDES:
 		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_VTB:
+		vcpu->arch.vcore->vtb = set_reg_val(id, *val);
+		break;
 	case KVM_REG_PPC_DAWR:
 		vcpu->arch.dawr = set_reg_val(id, *val);
 		break;
@@ -2097,66 +2103,6 @@ static void init_master_vcore(struct kvmppc_vcore *vc)
 	vc->conferring_threads = 0;
 }
 
-/*
- * See if the existing subcores can be split into 3 (or fewer) subcores
- * of at most two threads each, so we can fit in another vcore.  This
- * assumes there are at most two subcores and at most 6 threads in total.
- */
-static bool can_split_piggybacked_subcores(struct core_info *cip)
-{
-	int sub, new_sub;
-	int large_sub = -1;
-	int thr;
-	int n_subcores = cip->n_subcores;
-	struct kvmppc_vcore *vc, *vcnext;
-	struct kvmppc_vcore *master_vc = NULL;
-
-	for (sub = 0; sub < cip->n_subcores; ++sub) {
-		if (cip->subcore_threads[sub] <= 2)
-			continue;
-		if (large_sub >= 0)
-			return false;
-		large_sub = sub;
-		vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore,
-				      preempt_list);
-		if (vc->num_threads > 2)
-			return false;
-		n_subcores += (cip->subcore_threads[sub] - 1) >> 1;
-	}
-	if (large_sub < 0 || !subcore_config_ok(n_subcores + 1, 2))
-		return false;
-
-	/*
-	 * Seems feasible, so go through and move vcores to new subcores.
-	 * Note that when we have two or more vcores in one subcore,
-	 * all those vcores must have only one thread each.
-	 */
-	new_sub = cip->n_subcores;
-	thr = 0;
-	sub = large_sub;
-	list_for_each_entry_safe(vc, vcnext, &cip->vcs[sub], preempt_list) {
-		if (thr >= 2) {
-			list_del(&vc->preempt_list);
-			list_add_tail(&vc->preempt_list, &cip->vcs[new_sub]);
-			/* vc->num_threads must be 1 */
-			if (++cip->subcore_threads[new_sub] == 1) {
-				cip->subcore_vm[new_sub] = vc->kvm;
-				init_master_vcore(vc);
-				master_vc = vc;
-				++cip->n_subcores;
-			} else {
-				vc->master_vcore = master_vc;
-				++new_sub;
-			}
-		}
-		thr += vc->num_threads;
-	}
-	cip->subcore_threads[large_sub] = 2;
-	cip->max_subcore_threads = 2;
-
-	return true;
-}
-
 static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
 {
 	int n_threads = vc->num_threads;
@@ -2167,23 +2113,9 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
 
 	if (n_threads < cip->max_subcore_threads)
 		n_threads = cip->max_subcore_threads;
-	if (subcore_config_ok(cip->n_subcores + 1, n_threads)) {
-		cip->max_subcore_threads = n_threads;
-	} else if (cip->n_subcores <= 2 && cip->total_threads <= 6 &&
-		   vc->num_threads <= 2) {
-		/*
-		 * We may be able to fit another subcore in by
-		 * splitting an existing subcore with 3 or 4
-		 * threads into two 2-thread subcores, or one
-		 * with 5 or 6 threads into three subcores.
-		 * We can only do this if those subcores have
-		 * piggybacked virtual cores.
-		 */
-		if (!can_split_piggybacked_subcores(cip))
-			return false;
-	} else {
+	if (!subcore_config_ok(cip->n_subcores + 1, n_threads))
 		return false;
-	}
+	cip->max_subcore_threads = n_threads;
 
 	sub = cip->n_subcores;
 	++cip->n_subcores;
@@ -2197,43 +2129,6 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
 	return true;
 }
 
-static bool can_piggyback_subcore(struct kvmppc_vcore *pvc,
-				  struct core_info *cip, int sub)
-{
-	struct kvmppc_vcore *vc;
-	int n_thr;
-
-	vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore,
-			      preempt_list);
-
-	/* require same VM and same per-core reg values */
-	if (pvc->kvm != vc->kvm ||
-	    pvc->tb_offset != vc->tb_offset ||
-	    pvc->pcr != vc->pcr ||
-	    pvc->lpcr != vc->lpcr)
-		return false;
-
-	/* P8 guest with > 1 thread per core would see wrong TIR value */
-	if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
-	    (vc->num_threads > 1 || pvc->num_threads > 1))
-		return false;
-
-	n_thr = cip->subcore_threads[sub] + pvc->num_threads;
-	if (n_thr > cip->max_subcore_threads) {
-		if (!subcore_config_ok(cip->n_subcores, n_thr))
-			return false;
-		cip->max_subcore_threads = n_thr;
-	}
-
-	cip->total_threads += pvc->num_threads;
-	cip->subcore_threads[sub] = n_thr;
-	pvc->master_vcore = vc;
-	list_del(&pvc->preempt_list);
-	list_add_tail(&pvc->preempt_list, &cip->vcs[sub]);
-
-	return true;
-}
-
 /*
  * Work out whether it is possible to piggyback the execution of
  * vcore *pvc onto the execution of the other vcores described in *cip.
@@ -2241,19 +2136,10 @@ static bool can_piggyback_subcore(struct kvmppc_vcore *pvc,
 static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
 			  int target_threads)
 {
-	int sub;
-
 	if (cip->total_threads + pvc->num_threads > target_threads)
 		return false;
-	for (sub = 0; sub < cip->n_subcores; ++sub)
-		if (cip->subcore_threads[sub] &&
-		    can_piggyback_subcore(pvc, cip, sub))
-			return true;
 
-	if (can_dynamic_split(pvc, cip))
-		return true;
-
-	return false;
+	return can_dynamic_split(pvc, cip);
 }
 
 static void prepare_threads(struct kvmppc_vcore *vc)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7cc924b5eea2..c3c1d1bcfc67 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -644,9 +644,11 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
 38:
 
 BEGIN_FTR_SECTION
-	/* DPDES is shared between threads */
+	/* DPDES and VTB are shared between threads */
 	ld	r8, VCORE_DPDES(r5)
+	ld	r7, VCORE_VTB(r5)
 	mtspr	SPRN_DPDES, r8
+	mtspr	SPRN_VTB, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* Mark the subcore state as inside guest */
@@ -806,10 +808,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_CIABR, r7
 	mtspr	SPRN_TAR, r8
 	ld	r5, VCPU_IC(r4)
-	ld	r6, VCPU_VTB(r4)
-	mtspr	SPRN_IC, r5
-	mtspr	SPRN_VTB, r6
 	ld	r8, VCPU_EBBHR(r4)
+	mtspr	SPRN_IC, r5
 	mtspr	SPRN_EBBHR, r8
 	ld	r5, VCPU_EBBRR(r4)
 	ld	r6, VCPU_BESCR(r4)
@@ -1334,10 +1334,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	stw	r6, VCPU_PSPB(r9)
 	std	r7, VCPU_FSCR(r9)
 	mfspr	r5, SPRN_IC
-	mfspr	r6, SPRN_VTB
 	mfspr	r7, SPRN_TAR
 	std	r5, VCPU_IC(r9)
-	std	r6, VCPU_VTB(r9)
 	std	r7, VCPU_TAR(r9)
 	mfspr	r8, SPRN_EBBHR
 	std	r8, VCPU_EBBHR(r9)
@@ -1564,9 +1562,11 @@ kvmhv_switch_to_host:
 	isync
 
 BEGIN_FTR_SECTION
-	/* DPDES is shared between threads */
+	/* DPDES and VTB are shared between threads */
 	mfspr	r7, SPRN_DPDES
+	mfspr	r8, SPRN_VTB
 	std	r7, VCORE_DPDES(r5)
+	std	r8, VCORE_VTB(r5)
 	/* clear DPDES so we don't get guest doorbells in the host */
 	li	r8, 0
 	mtspr	SPRN_DPDES, r8
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index e76f79a45988..826c541a12af 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -226,7 +226,7 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 	 */
 	vcpu->arch.purr += get_tb() - vcpu->arch.entry_tb;
 	vcpu->arch.spurr += get_tb() - vcpu->arch.entry_tb;
-	vcpu->arch.vtb += get_vtb() - vcpu->arch.entry_vtb;
+	to_book3s(vcpu)->vtb += get_vtb() - vcpu->arch.entry_vtb;
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		vcpu->arch.ic += mfspr(SPRN_IC) - vcpu->arch.entry_ic;
 	svcpu->in_use = false;
@@ -448,6 +448,8 @@ void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 	case PVR_POWER7:
 	case PVR_POWER7p:
 	case PVR_POWER8:
+	case PVR_POWER8E:
+	case PVR_POWER8NVL:
 		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
 			BOOK3S_HFLAG_NEW_TLBIE;
 		break;
@@ -1361,6 +1363,9 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_HIOR:
 		*val = get_reg_val(id, to_book3s(vcpu)->hior);
 		break;
+	case KVM_REG_PPC_VTB:
+		*val = get_reg_val(id, to_book3s(vcpu)->vtb);
+		break;
 	case KVM_REG_PPC_LPCR:
 	case KVM_REG_PPC_LPCR_64:
 		/*
@@ -1397,6 +1402,9 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 		to_book3s(vcpu)->hior = set_reg_val(id, *val);
 		to_book3s(vcpu)->hior_explicit = true;
 		break;
+	case KVM_REG_PPC_VTB:
+		to_book3s(vcpu)->vtb = set_reg_val(id, *val);
+		break;
 	case KVM_REG_PPC_LPCR:
 	case KVM_REG_PPC_LPCR_64:
 		kvmppc_set_lpcr_pr(vcpu, set_reg_val(id, *val));
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 02b4672f7347..df3f2706d3e5 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -2038,7 +2038,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 		if (type == KVMPPC_DEBUG_NONE)
 			continue;
 
-		if (type & !(KVMPPC_DEBUG_WATCH_READ |
+		if (type & ~(KVMPPC_DEBUG_WATCH_READ |
 			     KVMPPC_DEBUG_WATCH_WRITE |
 			     KVMPPC_DEBUG_BREAKPOINT))
 			return -EINVAL;