[PATCH 0/12] Sundry fixes for Book3S HV

[PATCH 0/12] Sundry fixes for Book3S HV

[Paul Mackerras]

This set of 12 patches contains various fixes collected during the
process of getting reboot of Book3S HV guests to work correctly, plus
some needed for Ben H's forthcoming series to implement in-kernel XICS
(interrupt controller) emulation, plus two patches around handling
memslots properly.  This doesn't include the patch to implement
kvm_arch_flush_shadow_memslot since that depends on Marcelo's patch
series.  These patches are against Alex Graf's kvm-ppc-next branch.

As part of getting reboot to work, we have relaxed the previous policy
where, on POWER7, a virtual core would only run when all of the vcpus
in it were ready to run (or were idle).  Now a virtual core will run
as soon as any one of its vcpus are ready.  This avoids the problem
where the guest wouldn't run after reboot because userspace (qemu) had
stopped all except cpu 0.

Paul.

[PATCH 01/12] KVM: PPC: Move kvm->arch.slot_phys into memslot.arch

[Paul Mackerras]

Now that we have an architecture-specific field in the kvm_memory_slot
structure, we can use it to store the array of page physical addresses
that we need for Book3S HV KVM on PPC970 processors.  This reduces the
size of struct kvm_arch for Book3S HV, and also reduces the size of
struct kvm_arch_memory_slot for other PPC KVM variants since the fields
in it are now only compiled in for Book3S HV.

This necessitates making the kvm_arch_create_memslot and
kvm_arch_free_memslot operations specific to each PPC KVM variant.
That in turn means that we now don't allocate the rmap arrays on
Book3S PR and Book E.

Since we now unpin pages and free the slot_phys array in
kvmppc_core_free_memslot, we no longer need to do it in
kvmppc_core_destroy_vm, since the generic code takes care to free
all the memslots when destroying a VM.

We now need the new memslot to be passed in to
kvmppc_core_prepare_memory_region, since we need to initialize its
arch.slot_phys member on Book3S HV.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_host.h |    9 +--
 arch/powerpc/include/asm/kvm_ppc.h  |    5 ++
 arch/powerpc/kvm/book3s_64_mmu_hv.c |    6 +-
 arch/powerpc/kvm/book3s_hv.c        |  104 ++++++++++++++++++++---------------
 arch/powerpc/kvm/book3s_hv_rm_mmu.c |    2 +-
 arch/powerpc/kvm/book3s_pr.c        |   12 ++++
 arch/powerpc/kvm/booke.c            |   12 ++++
 arch/powerpc/kvm/powerpc.c          |   13 +----
 8 files changed, 102 insertions(+), 61 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f20a5ef..68f5a30 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -204,7 +204,7 @@ struct revmap_entry {
 };
 
 /*
- * We use the top bit of each memslot->rmap entry as a lock bit,
+ * We use the top bit of each memslot->arch.rmap entry as a lock bit,
  * and bit 32 as a present flag.  The bottom 32 bits are the
  * index in the guest HPT of a HPTE that points to the page.
  */
@@ -215,14 +215,17 @@ struct revmap_entry {
 #define KVMPPC_RMAP_PRESENT	0x100000000ul
 #define KVMPPC_RMAP_INDEX	0xfffffffful
 
-/* Low-order bits in kvm->arch.slot_phys[][] */
+/* Low-order bits in memslot->arch.slot_phys[] */
 #define KVMPPC_PAGE_ORDER_MASK	0x1f
 #define KVMPPC_PAGE_NO_CACHE	HPTE_R_I	/* 0x20 */
 #define KVMPPC_PAGE_WRITETHRU	HPTE_R_W	/* 0x40 */
 #define KVMPPC_GOT_PAGE		0x80
 
 struct kvm_arch_memory_slot {
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long *rmap;
+	unsigned long *slot_phys;
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
 struct kvm_arch {
@@ -246,8 +249,6 @@ struct kvm_arch {
 	unsigned long hpt_npte;
 	unsigned long hpt_mask;
 	spinlock_t slot_phys_lock;
-	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
-	int slot_npages[KVM_MEM_SLOTS_NUM];
 	unsigned short last_vcpu[NR_CPUS];
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	struct kvmppc_linear_info *hpt_li;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c06a64b..41a00ea 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -143,7 +143,12 @@ extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
 extern void kvm_release_hpt(struct kvmppc_linear_info *li);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
+extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+				     struct kvm_memory_slot *dont);
+extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+				      unsigned long npages);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index d95d113..3c679ff 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -260,7 +260,7 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 
 /*
  * This is called to get a reference to a guest page if there isn't
- * one already in the kvm->arch.slot_phys[][] arrays.
+ * one already in the memslot->arch.slot_phys[] array.
  */
 static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 				  struct kvm_memory_slot *memslot,
@@ -275,7 +275,7 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	struct vm_area_struct *vma;
 	unsigned long pfn, i, npages;
 
-	physp = kvm->arch.slot_phys[memslot->id];
+	physp = memslot->arch.slot_phys;
 	if (!physp)
 		return -EINVAL;
 	if (physp[gfn - memslot->base_gfn])
@@ -1062,7 +1062,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		return NULL;
 	if (!kvm->arch.using_mmu_notifiers) {
-		physp = kvm->arch.slot_phys[memslot->id];
+		physp = memslot->arch.slot_phys;
 		if (!physp)
 			return NULL;
 		physp += gfn - memslot->base_gfn;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 83e929e..416de2c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1299,48 +1299,67 @@ static unsigned long slb_pgsize_encoding(unsigned long psize)
 	return senc;
 }
 
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+static void unpin_slot(struct kvm_memory_slot *memslot)
 {
-	unsigned long npages;
-	unsigned long *phys;
+	unsigned long *physp;
+	unsigned long j, npages, pfn;
+	struct page *page;
 
-	/* Allocate a slot_phys array */
-	phys = kvm->arch.slot_phys[mem->slot];
-	if (!kvm->arch.using_mmu_notifiers && !phys) {
-		npages = mem->memory_size >> PAGE_SHIFT;
-		phys = vzalloc(npages * sizeof(unsigned long));
-		if (!phys)
-			return -ENOMEM;
-		kvm->arch.slot_phys[mem->slot] = phys;
-		kvm->arch.slot_npages[mem->slot] = npages;
+	physp = memslot->arch.slot_phys;
+	npages = memslot->npages;
+	if (!physp)
+		return;
+	for (j = 0; j < npages; j++) {
+		if (!(physp[j] & KVMPPC_GOT_PAGE))
+			continue;
+		pfn = physp[j] >> PAGE_SHIFT;
+		page = pfn_to_page(pfn);
+		SetPageDirty(page);
+		put_page(page);
+	}
+}
+
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+	if (!dont || free->arch.rmap != dont->arch.rmap) {
+		vfree(free->arch.rmap);
+		free->arch.rmap = NULL;
 	}
+	if (!dont || free->arch.slot_phys != dont->arch.slot_phys) {
+		unpin_slot(free);
+		vfree(free->arch.slot_phys);
+		free->arch.slot_phys = NULL;
+	}
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
+	if (!slot->arch.rmap)
+		return -ENOMEM;
+	slot->arch.slot_phys = NULL;
 
 	return 0;
 }
 
-static void unpin_slot(struct kvm *kvm, int slot_id)
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot,
+				      struct kvm_userspace_memory_region *mem)
 {
-	unsigned long *physp;
-	unsigned long j, npages, pfn;
-	struct page *page;
+	unsigned long *phys;
 
-	physp = kvm->arch.slot_phys[slot_id];
-	npages = kvm->arch.slot_npages[slot_id];
-	if (physp) {
-		spin_lock(&kvm->arch.slot_phys_lock);
-		for (j = 0; j < npages; j++) {
-			if (!(physp[j] & KVMPPC_GOT_PAGE))
-				continue;
-			pfn = physp[j] >> PAGE_SHIFT;
-			page = pfn_to_page(pfn);
-			SetPageDirty(page);
-			put_page(page);
-		}
-		kvm->arch.slot_phys[slot_id] = NULL;
-		spin_unlock(&kvm->arch.slot_phys_lock);
-		vfree(physp);
+	/* Allocate a slot_phys array if needed */
+	phys = memslot->arch.slot_phys;
+	if (!kvm->arch.using_mmu_notifiers && !phys && memslot->npages) {
+		phys = vzalloc(memslot->npages * sizeof(unsigned long));
+		if (!phys)
+			return -ENOMEM;
+		memslot->arch.slot_phys = phys;
 	}
+
+	return 0;
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
@@ -1465,11 +1484,16 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		/* Initialize phys addrs of pages in RMO */
 		npages = ri->npages;
 		porder = __ilog2(npages);
-		physp = kvm->arch.slot_phys[memslot->id];
-		spin_lock(&kvm->arch.slot_phys_lock);
-		for (i = 0; i < npages; ++i)
-			physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) + porder;
-		spin_unlock(&kvm->arch.slot_phys_lock);
+		physp = memslot->arch.slot_phys;
+		if (physp) {
+			if (npages > memslot->npages)
+				npages = memslot->npages;
+			spin_lock(&kvm->arch.slot_phys_lock);
+			for (i = 0; i < npages; ++i)
+				physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) +
+					porder;
+			spin_unlock(&kvm->arch.slot_phys_lock);
+		}
 	}
 
 	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
@@ -1528,12 +1552,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	unsigned long i;
-
-	if (!kvm->arch.using_mmu_notifiers)
-		for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
-			unpin_slot(kvm, i);
-
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 56ac1a5..d95582c 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -183,7 +183,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	rmap = &memslot->arch.rmap[slot_fn];
 
 	if (!kvm->arch.using_mmu_notifiers) {
-		physp = kvm->arch.slot_phys[memslot->id];
+		physp = memslot->arch.slot_phys;
 		if (!physp)
 			return H_PARAMETER;
 		physp += slot_fn;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index b3c584f..fdadc9e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1220,7 +1220,19 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 }
 #endif /* CONFIG_PPC64 */
 
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	return 0;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot,
 				      struct kvm_userspace_memory_region *mem)
 {
 	return 0;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 5f0476a..5144057 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1438,7 +1438,19 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return -ENOTSUPP;
 }
 
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	return 0;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot,
 				      struct kvm_userspace_memory_region *mem)
 {
 	return 0;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 32d217c..10e4dfb 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -389,19 +389,12 @@ long kvm_arch_dev_ioctl(struct file *filp,
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
-	if (!dont || free->arch.rmap != dont->arch.rmap) {
-		vfree(free->arch.rmap);
-		free->arch.rmap = NULL;
-	}
+	kvmppc_core_free_memslot(free, dont);
 }
 
 int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 {
-	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
-	if (!slot->arch.rmap)
-		return -ENOMEM;
-
-	return 0;
+	return kvmppc_core_create_memslot(slot, npages);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -410,7 +403,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_userspace_memory_region *mem,
                                    int user_alloc)
 {
-	return kvmppc_core_prepare_memory_region(kvm, mem);
+	return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-- 
1.7.10.rc3.219.g53414

[PATCH 02/12] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots

[Paul Mackerras]

The generic KVM code uses SRCU (sleeping RCU) to protect accesses
to the memslots data structures against updates due to userspace
adding, modifying or removing memory slots.  We need to do that too,
both to avoid accessing stale copies of the memslots and to avoid
lockdep warnings.  This therefore adds srcu_read_lock/unlock pairs
around code that accesses and uses memslots.

Since the real-mode handlers for H_ENTER, H_REMOVE and H_BULK_REMOVE
need to access the memslots, and we don't want to call the SRCU code
in real mode (since we have no assurance that it would only access
the linear mapping), we hold the SRCU read lock for the VM while
in the guest.  This does mean that adding or removing memory slots
while some vcpus are executing in the guest will block for up to
two jiffies.  This tradeoff is acceptable since adding/removing
memory slots only happens rarely, while H_ENTER/H_REMOVE/H_BULK_REMOVE
are performance-critical hot paths.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s_64_mmu_hv.c |   17 +++++++++++++----
 arch/powerpc/kvm/book3s_hv.c        |   27 +++++++++++++++++++++++----
 2 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 3c679ff..a389cc6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
+#include <linux/srcu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -1057,20 +1058,22 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 	unsigned long hva, psize, offset;
 	unsigned long pa;
 	unsigned long *physp;
+	int srcu_idx;
 
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	memslot = gfn_to_memslot(kvm, gfn);
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
-		return NULL;
+		goto err;
 	if (!kvm->arch.using_mmu_notifiers) {
 		physp = memslot->arch.slot_phys;
 		if (!physp)
-			return NULL;
+			goto err;
 		physp += gfn - memslot->base_gfn;
 		pa = *physp;
 		if (!pa) {
 			if (kvmppc_get_guest_page(kvm, gfn, memslot,
 						  PAGE_SIZE) < 0)
-				return NULL;
+				goto err;
 			pa = *physp;
 		}
 		page = pfn_to_page(pa >> PAGE_SHIFT);
@@ -1079,9 +1082,11 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 		hva = gfn_to_hva_memslot(memslot, gfn);
 		npages = get_user_pages_fast(hva, 1, 1, pages);
 		if (npages < 1)
-			return NULL;
+			goto err;
 		page = pages[0];
 	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
 	psize = PAGE_SIZE;
 	if (PageHuge(page)) {
 		page = compound_head(page);
@@ -1091,6 +1096,10 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 	if (nb_ret)
 		*nb_ret = psize - offset;
 	return page_address(page) + offset;
+
+ err:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return NULL;
 }
 
 void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 416de2c..817837d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -30,6 +30,7 @@
 #include <linux/cpumask.h>
 #include <linux/spinlock.h>
 #include <linux/page-flags.h>
+#include <linux/srcu.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -366,13 +367,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	unsigned long req = kvmppc_get_gpr(vcpu, 3);
 	unsigned long target, ret = H_SUCCESS;
 	struct kvm_vcpu *tvcpu;
+	int idx;
 
 	switch (req) {
 	case H_ENTER:
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
 					      kvmppc_get_gpr(vcpu, 5),
 					      kvmppc_get_gpr(vcpu, 6),
 					      kvmppc_get_gpr(vcpu, 7));
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	case H_CEDE:
 		break;
@@ -411,6 +415,7 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			      struct task_struct *tsk)
 {
 	int r = RESUME_HOST;
+	int srcu_idx;
 
 	vcpu->stat.sum_exits++;
 
@@ -470,12 +475,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * have been handled already.
 	 */
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvmppc_book3s_hv_page_fault(run, vcpu,
 				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvmppc_book3s_hv_page_fault(run, vcpu,
 				kvmppc_get_pc(vcpu), 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		break;
 	/*
 	 * This occurs if the guest executes an illegal instruction.
@@ -820,6 +829,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	long ret;
 	u64 now;
 	int ptid, i, need_vpa_update;
+	int srcu_idx;
 
 	/* don't start if any threads have a signal pending */
 	need_vpa_update = 0;
@@ -898,6 +908,9 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	spin_unlock(&vc->lock);
 
 	kvm_guest_enter();
+
+	srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
+
 	__kvmppc_vcore_entry(NULL, vcpu0);
 	for (i = 0; i < threads_per_core; ++i)
 		kvmppc_release_hwthread(vc->pcpu + i);
@@ -913,6 +926,8 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->vcore_state = VCORE_EXITING;
 	spin_unlock(&vc->lock);
 
+	srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx);
+
 	/* make sure updates to secondary vcpu structs are visible now */
 	smp_mb();
 	kvm_guest_exit();
@@ -1381,6 +1396,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	unsigned long rmls;
 	unsigned long *physp;
 	unsigned long i, npages;
+	int srcu_idx;
 
 	mutex_lock(&kvm->lock);
 	if (kvm->arch.rma_setup_done)
@@ -1396,12 +1412,13 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	}
 
 	/* Look up the memslot for guest physical address 0 */
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	memslot = gfn_to_memslot(kvm, 0);
 
 	/* We must have some memory at 0 by now */
 	err = -EINVAL;
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
-		goto out;
+		goto out_srcu;
 
 	/* Look up the VMA for the start of this memory slot */
 	hva = memslot->userspace_addr;
@@ -1425,14 +1442,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		err = -EPERM;
 		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 			pr_err("KVM: CPU requires an RMO\n");
-			goto out;
+			goto out_srcu;
 		}
 
 		/* We can handle 4k, 64k or 16M pages in the VRMA */
 		err = -EINVAL;
 		if (!(psize == 0x1000 || psize == 0x10000 ||
 		      psize == 0x1000000))
-			goto out;
+			goto out_srcu;
 
 		/* Update VRMASD field in the LPCR */
 		senc = slb_pgsize_encoding(psize);
@@ -1455,7 +1472,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		err = -EINVAL;
 		if (rmls < 0) {
 			pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
-			goto out;
+			goto out_srcu;
 		}
 		atomic_inc(&ri->use_count);
 		kvm->arch.rma = ri;
@@ -1500,6 +1517,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	smp_wmb();
 	kvm->arch.rma_setup_done = 1;
 	err = 0;
+ out_srcu:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
  out:
 	mutex_unlock(&kvm->lock);
 	return err;
-- 
1.7.10.rc3.219.g53414

[PATCH 03/12] KVM: PPC: Book3S HV: Provide a way for userspace to get/set per-vCPU areas

[Paul Mackerras]

The PAPR paravirtualization interface lets guests register three
different types of per-vCPU buffer areas in its memory for communication
with the hypervisor.  These are called virtual processor areas (VPAs).
Currently the hypercalls to register and unregister VPAs are handled
by KVM in the kernel, and userspace has no way to know about or save
and restore these registrations across a migration.

This adds get and set ioctls to allow userspace to see what addresses
have been registered, and to register or unregister them.  This will
be needed for guest hibernation and migration, and is also needed so
that userspace can unregister them on reset (otherwise we corrupt
guest memory after reboot by writing to the VPAs registered by the
previous kernel).  We also add a capability to indicate that the
ioctls are supported.

This also fixes a bug where we were calling init_vpa unconditionally,
leading to an oops when unregistering the VPA.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_ppc.h |    2 ++
 arch/powerpc/kvm/book3s_hv.c       |   54 +++++++++++++++++++++++++++++++++++-
 arch/powerpc/kvm/powerpc.c         |   23 +++++++++++++++
 include/linux/kvm.h                |   12 ++++++++
 4 files changed, 90 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 41a00ea..4e0bc22 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -201,6 +201,8 @@ int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
 int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+int kvm_vcpu_get_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa);
+int kvm_vcpu_set_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa);
 
 void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 817837d..53d950b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -143,6 +143,57 @@ static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
 	vpa->yield_count = 1;
 }
 
+int kvm_vcpu_get_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa)
+{
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	vpa->vpa_addr = vcpu->arch.vpa.next_gpa;
+	vpa->slb_shadow_addr = vcpu->arch.slb_shadow.next_gpa;
+	vpa->slb_shadow_size = vcpu->arch.slb_shadow.len;
+	vpa->dtl_addr = vcpu->arch.dtl.next_gpa;
+	vpa->dtl_size = vcpu->arch.dtl.len;
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+	return 0;
+}
+
+static inline void set_vpa(struct kvmppc_vpa *v, unsigned long addr,
+			   unsigned long len)
+{
+	if (v->next_gpa != addr || v->len != len) {
+		v->next_gpa = addr;
+		v->len = addr ? len : 0;
+		v->update_pending = 1;
+	}
+}
+
+int kvm_vcpu_set_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa)
+{
+	/* check that addresses are cacheline aligned */
+	if ((vpa->vpa_addr & (L1_CACHE_BYTES - 1)) ||
+	    (vpa->slb_shadow_addr & (L1_CACHE_BYTES - 1)) ||
+	    (vpa->dtl_addr & (L1_CACHE_BYTES - 1)))
+		return -EINVAL;
+
+	/* DTL must be at least 1 entry long, if being set */
+	if (vpa->dtl_addr) {
+		if (vpa->dtl_size < sizeof(struct dtl_entry))
+			return -EINVAL;
+		vpa->dtl_size -= vpa->dtl_size % sizeof(struct dtl_entry);
+	}
+
+	/* DTL and SLB shadow require VPA */
+	if (!vpa->vpa_addr && (vpa->slb_shadow_addr || vpa->dtl_addr))
+		return -EINVAL;
+
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	set_vpa(&vcpu->arch.vpa, vpa->vpa_addr, sizeof(struct lppaca));
+	set_vpa(&vcpu->arch.slb_shadow, vpa->slb_shadow_addr,
+		vpa->slb_shadow_size);
+	set_vpa(&vcpu->arch.dtl, vpa->dtl_addr, vpa->dtl_size);
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+
+	return 0;
+}
+
 /* Length for a per-processor buffer is passed in at offset 4 in the buffer */
 struct reg_vpa {
 	u32 dummy;
@@ -321,7 +372,8 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
-		init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+		if (vcpu->arch.vpa.pinned_addr)
+			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
 	}
 	if (vcpu->arch.dtl.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 10e4dfb..72764ba 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -341,6 +341,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 		if (cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
 		break;
+	case KVM_CAP_PPC_VPA:
+		r = 1;
+		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_BOOK3S_64_HV
@@ -821,6 +824,26 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_PPC_GET_VPA_INFO: {
+		struct kvm_ppc_vpa vpa;
+		r = kvm_vcpu_get_vpa_info(vcpu, &vpa);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (copy_to_user(argp, &vpa, sizeof(vpa)))
+			break;
+		r = 0;
+	}
+	case KVM_PPC_SET_VPA_INFO: {
+		struct kvm_ppc_vpa vpa;
+		r = -EFAULT;
+		if (copy_from_user(&vpa, argp, sizeof(vpa)))
+			break;
+		r = kvm_vcpu_set_vpa_info(vcpu, &vpa);
+		break;
+	}
+#endif
 	default:
 		r = -EINVAL;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index f4f5be8..4a8bb4f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -622,6 +622,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 81
+#define KVM_CAP_PPC_VPA 83
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -959,4 +960,15 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+struct kvm_ppc_vpa {
+	__u64 vpa_addr;
+	__u64 slb_shadow_addr;
+	__u64 dtl_addr;
+	__u32 slb_shadow_size;
+	__u32 dtl_size;
+};
+
+#define KVM_PPC_GET_VPA_INFO	_IOR(KVMIO, 0xae, struct kvm_ppc_vpa)
+#define KVM_PPC_SET_VPA_INFO	_IOW(KVMIO, 0xaf, struct kvm_ppc_vpa)
+
 #endif /* __LINUX_KVM_H */
-- 
1.7.10.rc3.219.g53414

[PATCH 04/12] KVM: PPC: Book3S HV: Allow KVM guests to stop secondary threads coming online

[Paul Mackerras]

When a Book3S HV KVM guest is running, we need the host to be in
single-thread mode, that is, all of the cores (or at least all of
the cores where the KVM guest could run) to be running only one
active hardware thread.  This is because of the hardware restriction
in POWER processors that all of the hardware threads in the core
must be in the same logical partition.  Complying with this restriction
is much easier if, from the host kernel's point of view, only one
hardware thread is active.

This adds two hooks in the SMP hotplug code to allow the KVM code to
make sure that secondary threads (i.e. hardware threads other than
thread 0) cannot come online while any KVM guest exists.  The KVM
code still has to check that any core where it runs a guest has the
secondary threads offline, but having done that check it can now be
sure that they will not come online while the guest is running.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/smp.h |    8 ++++++++
 arch/powerpc/kernel/smp.c      |   44 ++++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c   |   12 +++++++++--
 3 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ebc24dc..b625a1a 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -66,6 +66,14 @@ void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);
 void generic_set_cpu_dead(unsigned int cpu);
 int generic_check_cpu_restart(unsigned int cpu);
+
+extern void inhibit_secondary_onlining(void);
+extern void uninhibit_secondary_onlining(void);
+
+#else /* HOTPLUG_CPU */
+static inline void inhibit_secondary_onlining(void) {}
+static inline void uninhibit_secondary_onlining(void) {}
+
 #endif
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007..ae46a22 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -410,6 +410,43 @@ int generic_check_cpu_restart(unsigned int cpu)
 {
 	return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
 }
+
+static atomic_t secondary_inhibit_count;
+
+/*
+ * Don't allow secondary CPU threads to come online
+ */
+void inhibit_secondary_onlining(void)
+{
+	/*
+	 * This makes secondary_inhibit_count stable during cpu
+	 * online/offline operations.
+	 */
+	get_online_cpus();
+
+	atomic_inc(&secondary_inhibit_count);
+	put_online_cpus();
+}
+
+/*
+ * Allow secondary CPU threads to come online again
+ */
+void uninhibit_secondary_onlining(void)
+{
+	get_online_cpus();
+	atomic_dec(&secondary_inhibit_count);
+	put_online_cpus();
+}
+
+static int secondaries_inhibited(void)
+{
+	return atomic_read(&secondary_inhibit_count);
+}
+
+#else /* HOTPLUG_CPU */
+
+#define secondaries_inhibited()		0
+
 #endif
 
 static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
@@ -428,6 +465,13 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc, c;
 
+	/*
+	 * Don't allow secondary threads to come online if inhibited
+	 */
+	if (threads_per_core > 1 && secondaries_inhibited() &&
+	    cpu % threads_per_core != 0)
+		return -EBUSY;
+
 	if (smp_ops == NULL ||
 	    (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
 		return -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 53d950b..310ffd7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -47,6 +47,7 @@
 #include <asm/page.h>
 #include <asm/hvcall.h>
 #include <asm/switch_to.h>
+#include <asm/smp.h>
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
@@ -918,8 +919,6 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	/*
 	 * Make sure we are running on thread 0, and that
 	 * secondary threads are offline.
-	 * XXX we should also block attempts to bring any
-	 * secondary threads online.
 	 */
 	if (threads_per_core > 1 && !on_primary_thread()) {
 		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
@@ -1618,11 +1617,20 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 	kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206);
 	spin_lock_init(&kvm->arch.slot_phys_lock);
+
+	/*
+	 * Don't allow secondary CPU threads to come online
+	 * while any KVM VMs exist.
+	 */
+	inhibit_secondary_onlining();
+
 	return 0;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
+	uninhibit_secondary_onlining();
+
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
-- 
1.7.10.rc3.219.g53414

[PATCH 05/12] KVM: PPC: Fix updates of vcpu->cpu on HV KVM

[Paul Mackerras]

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

This patch removes the powerpc "generic" updates of vcpu->cpu in
load and put, and moves them to the various backends.

The reason is that "HV" KVM does its own sauce with that field
and the generic updates might corrupt it. The field contains the
CPU# of the -first- HW CPU of the core always for all the VCPU
threads of a core (the one that's online from a host Linux
perspective).

However, the preempt notifiers are going to be called on the
threads VCPUs when they are running (due to them sleeping on our
private waitqueue) causing unload to be called, potentially
clobbering the value.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s_pr.c |    3 ++-
 arch/powerpc/kvm/booke.c     |    2 ++
 arch/powerpc/kvm/powerpc.c   |    2 --
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index fdadc9e..4490deb 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -64,7 +64,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
 	svcpu_put(svcpu);
 #endif
-
+	vcpu->cpu = smp_processor_id();
 #ifdef CONFIG_PPC_BOOK3S_32
 	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
 #endif
@@ -84,6 +84,7 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	kvmppc_giveup_ext(vcpu, MSR_FP);
 	kvmppc_giveup_ext(vcpu, MSR_VEC);
 	kvmppc_giveup_ext(vcpu, MSR_VSX);
+	vcpu->cpu = -1;
 }
 
 int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 5144057..ad73563 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1504,12 +1504,14 @@ void kvmppc_decrementer_func(unsigned long data)
 
 void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	vcpu->cpu = smp_processor_id();
 	current->thread.kvm_vcpu = vcpu;
 }
 
 void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	current->thread.kvm_vcpu = NULL;
+	vcpu->cpu = -1;
 }
 
 int __init kvmppc_booke_init(void)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 72764ba..1241b29 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -502,7 +502,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
 #endif
 	kvmppc_core_vcpu_load(vcpu, cpu);
-	vcpu->cpu = smp_processor_id();
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -511,7 +510,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_BOOKE
 	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
 #endif
-	vcpu->cpu = -1;
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
-- 
1.7.10.rc3.219.g53414

[PATCH 06/12] KVM: PPC: Book3S HV: Remove bogus update of thread IDs in HV KVM

[Paul Mackerras]

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

When making a vcpu non-runnable we incorrectly changed the
thread IDs of all other threads on the core, just remove that
code.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s_hv.c |    6 ------
 1 file changed, 6 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 310ffd7..e6d8579 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -759,17 +759,11 @@ extern void xics_wake_cpu(int cpu);
 static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 				   struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *v;
-
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 	--vc->n_runnable;
 	++vc->n_busy;
-	/* decrement the physical thread id of each following vcpu */
-	v = vcpu;
-	list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list)
-		--v->arch.ptid;
 	list_del(&vcpu->arch.run_list);
 }
 
-- 
1.7.10.rc3.219.g53414

[PATCH 07/12] KVM: PPC: Book3S HV: Fix some races in starting secondary threads

[Paul Mackerras]

Subsequent patches implementing in-kernel XICS emulation will make it
possible for IPIs to arrive at secondary threads at arbitrary times.
This fixes some races in how we start the secondary threads, which
if not fixed could lead to occasional crashes of the host kernel.

This makes sure that (a) we have grabbed all the secondary threads,
and verified that they are no longer in the kernel, before we start
any thread, (b) that the secondary thread loads its vcpu pointer
after clearing the IPI that woke it up (so we don't miss a wakeup),
and (c) that the secondary thread clears its vcpu pointer before
incrementing the nap count.  It also removes unnecessary setting
of the vcpu and vcore pointers in the paca in kvmppc_core_vcpu_load.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s_hv.c            |   41 ++++++++++++++++++-------------
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |   11 ++++++---
 2 files changed, 32 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e6d8579..2d0477a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -64,8 +64,6 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
-	local_paca->kvm_hstate.kvm_vcpu = vcpu;
-	local_paca->kvm_hstate.kvm_vcore = vc;
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
 		vc->stolen_tb += mftb() - vc->preempt_tb;
 }
@@ -776,6 +774,7 @@ static int kvmppc_grab_hwthread(int cpu)
 
 	/* Ensure the thread won't go into the kernel if it wakes */
 	tpaca->kvm_hstate.hwthread_req = 1;
+	tpaca->kvm_hstate.kvm_vcpu = NULL;
 
 	/*
 	 * If the thread is already executing in the kernel (e.g. handling
@@ -825,7 +824,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (vcpu->arch.ptid) {
-		kvmppc_grab_hwthread(cpu);
 		xics_wake_cpu(cpu);
 		++vc->n_woken;
 	}
@@ -851,7 +849,8 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
 
 /*
  * Check that we are on thread 0 and that any other threads in
- * this core are off-line.
+ * this core are off-line.  Then grab the threads so they can't
+ * enter the kernel.
  */
 static int on_primary_thread(void)
 {
@@ -863,6 +862,17 @@ static int on_primary_thread(void)
 	while (++thr < threads_per_core)
 		if (cpu_online(cpu + thr))
 			return 0;
+
+	/* Grab all hw threads so they can't go into the kernel */
+	for (thr = 1; thr < threads_per_core; ++thr) {
+		if (kvmppc_grab_hwthread(cpu + thr)) {
+			/* Couldn't grab one; let the others go */
+			do {
+				kvmppc_release_hwthread(cpu + thr);
+			} while (--thr > 0);
+			return 0;
+		}
+	}
 	return 1;
 }
 
@@ -911,16 +921,6 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	}
 
 	/*
-	 * Make sure we are running on thread 0, and that
-	 * secondary threads are offline.
-	 */
-	if (threads_per_core > 1 && !on_primary_thread()) {
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
-			vcpu->arch.ret = -EBUSY;
-		goto out;
-	}
-
-	/*
 	 * Assign physical thread IDs, first to non-ceded vcpus
 	 * and then to ceded ones.
 	 */
@@ -939,15 +939,22 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 		if (vcpu->arch.ceded)
 			vcpu->arch.ptid = ptid++;
 
+	/*
+	 * Make sure we are running on thread 0, and that
+	 * secondary threads are offline.
+	 */
+	if (threads_per_core > 1 && !on_primary_thread()) {
+		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+			vcpu->arch.ret = -EBUSY;
+		goto out;
+	}
+
 	vc->stolen_tb += mftb() - vc->preempt_tb;
 	vc->pcpu = smp_processor_id();
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		kvmppc_start_thread(vcpu);
 		kvmppc_create_dtl_entry(vcpu, vc);
 	}
-	/* Grab any remaining hw threads so they can't go into the kernel */
-	for (i = ptid; i < threads_per_core; ++i)
-		kvmppc_grab_hwthread(vc->pcpu + i);
 
 	preempt_disable();
 	spin_unlock(&vc->lock);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 44b72fe..1e90ef6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -134,8 +134,11 @@ kvm_start_guest:
 
 27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
 
+	/* reload vcpu pointer after clearing the IPI */
+	ld	r4,HSTATE_KVM_VCPU(r13)
+	cmpdi	r4,0
 	/* if we have no vcpu to run, go back to sleep */
-	beq	cr1,kvm_no_guest
+	beq	kvm_no_guest
 
 	/* were we napping due to cede? */
 	lbz	r0,HSTATE_NAPPING(r13)
@@ -1587,6 +1590,10 @@ secondary_too_late:
 	.endr
 
 secondary_nap:
+	/* Clear our vcpu pointer so we don't come back in early */
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+	lwsync
 	/* Clear any pending IPI - assume we're a secondary thread */
 	ld	r5, HSTATE_XICS_PHYS(r13)
 	li	r7, XICS_XIRR
@@ -1612,8 +1619,6 @@ secondary_nap:
 kvm_no_guest:
 	li	r0, KVM_HWTHREAD_IN_NAP
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
-	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
 
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
-- 
1.7.10.rc3.219.g53414

[PATCH 08/12] KVM: PPC: Book3s HV: Don't access runnable threads list without vcore lock

[Paul Mackerras]

There were a few places where we were traversing the list of runnable
threads in a virtual core, i.e. vc->runnable_threads, without holding
the vcore spinlock.  This extends the places where we hold the vcore
spinlock to cover everywhere that we traverse that list.

Since we possibly need to sleep inside kvmppc_book3s_hv_page_fault,
this moves the call of it from kvmppc_handle_exit out to
kvmppc_vcpu_run, where we don't hold the vcore lock.

In kvmppc_vcore_blocked, we don't actually need to check whether
all vcpus are ceded and don't have any pending exceptions, since the
caller has already done that.  The caller (kvmppc_run_vcpu) wasn't
actually checking for pending exceptions, so we add that.

The change of if to while in kvmppc_run_vcpu is to make sure that we
never call kvmppc_remove_runnable() when the vcore state is RUNNING or
EXITING.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_asm.h |    1 +
 arch/powerpc/kvm/book3s_hv.c       |   64 +++++++++++++++++-------------------
 2 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 76fdcfe..fb99a21 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -123,6 +123,7 @@
 #define RESUME_GUEST_NV         RESUME_FLAG_NV
 #define RESUME_HOST             RESUME_FLAG_HOST
 #define RESUME_HOST_NV          (RESUME_FLAG_HOST|RESUME_FLAG_NV)
+#define RESUME_PAGE_FAULT	(1<<2)
 
 #define KVM_GUEST_MODE_NONE	0
 #define KVM_GUEST_MODE_GUEST	1
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2d0477a..e729700 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -466,7 +466,6 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			      struct task_struct *tsk)
 {
 	int r = RESUME_HOST;
-	int srcu_idx;
 
 	vcpu->stat.sum_exits++;
 
@@ -526,16 +525,12 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * have been handled already.
 	 */
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
-		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = kvmppc_book3s_hv_page_fault(run, vcpu,
-				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
-		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+		r = RESUME_PAGE_FAULT;
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
-		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = kvmppc_book3s_hv_page_fault(run, vcpu,
-				kvmppc_get_pc(vcpu), 0);
-		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
+		vcpu->arch.fault_dsisr = 0;
+		r = RESUME_PAGE_FAULT;
 		break;
 	/*
 	 * This occurs if the guest executes an illegal instruction.
@@ -880,22 +875,24 @@ static int on_primary_thread(void)
  * Run a set of guest threads on a physical core.
  * Called with vc->lock held.
  */
-static int kvmppc_run_core(struct kvmppc_vcore *vc)
+static void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
 	struct kvm_vcpu *vcpu, *vcpu0, *vnext;
 	long ret;
 	u64 now;
 	int ptid, i, need_vpa_update;
 	int srcu_idx;
+	struct kvm_vcpu *vcpus_to_update[threads_per_core];
 
 	/* don't start if any threads have a signal pending */
 	need_vpa_update = 0;
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		if (signal_pending(vcpu->arch.run_task))
-			return 0;
-		need_vpa_update |= vcpu->arch.vpa.update_pending |
-			vcpu->arch.slb_shadow.update_pending |
-			vcpu->arch.dtl.update_pending;
+			return;
+		if (vcpu->arch.vpa.update_pending ||
+		    vcpu->arch.slb_shadow.update_pending ||
+		    vcpu->arch.dtl.update_pending)
+			vcpus_to_update[need_vpa_update++] = vcpu;
 	}
 
 	/*
@@ -915,8 +912,8 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	if (need_vpa_update) {
 		spin_unlock(&vc->lock);
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
-			kvmppc_update_vpas(vcpu);
+		for (i = 0; i < need_vpa_update; ++i)
+			kvmppc_update_vpas(vcpus_to_update[i]);
 		spin_lock(&vc->lock);
 	}
 
@@ -933,8 +930,10 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 			vcpu->arch.ptid = ptid++;
 		}
 	}
-	if (!vcpu0)
-		return 0;		/* nothing to run */
+	if (!vcpu0) {
+		vc->vcore_state = VCORE_INACTIVE;
+		return;		/* nothing to run; should never happen */
+	}
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
 		if (vcpu->arch.ceded)
 			vcpu->arch.ptid = ptid++;
@@ -987,6 +986,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	preempt_enable();
 	kvm_resched(vcpu);
 
+	spin_lock(&vc->lock);
 	now = get_tb();
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		/* cancel pending dec exception if dec is positive */
@@ -1010,7 +1010,6 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 		}
 	}
 
-	spin_lock(&vc->lock);
  out:
 	vc->vcore_state = VCORE_INACTIVE;
 	vc->preempt_tb = mftb();
@@ -1021,8 +1020,6 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 			wake_up(&vcpu->arch.cpu_run);
 		}
 	}
-
-	return 1;
 }
 
 /*
@@ -1046,20 +1043,11 @@ static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state)
 static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
 	DEFINE_WAIT(wait);
-	struct kvm_vcpu *v;
-	int all_idle = 1;
 
 	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 	vc->vcore_state = VCORE_SLEEPING;
 	spin_unlock(&vc->lock);
-	list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
-		if (!v->arch.ceded || v->arch.pending_exceptions) {
-			all_idle = 0;
-			break;
-		}
-	}
-	if (all_idle)
-		schedule();
+	schedule();
 	finish_wait(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
@@ -1115,7 +1103,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		vc->runner = vcpu;
 		n_ceded = 0;
 		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
-			n_ceded += v->arch.ceded;
+			if (!v->arch.pending_exceptions)
+				n_ceded += v->arch.ceded;
 		if (n_ceded == vc->n_runnable)
 			kvmppc_vcore_blocked(vc);
 		else
@@ -1136,8 +1125,9 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	}
 
 	if (signal_pending(current)) {
-		if (vc->vcore_state == VCORE_RUNNING ||
-		    vc->vcore_state == VCORE_EXITING) {
+		while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
+		       (vc->vcore_state == VCORE_RUNNING ||
+			vc->vcore_state == VCORE_EXITING)) {
 			spin_unlock(&vc->lock);
 			kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
 			spin_lock(&vc->lock);
@@ -1157,6 +1147,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
+	int srcu_idx;
 
 	if (!vcpu->arch.sane) {
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -1195,6 +1186,11 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		    !(vcpu->arch.shregs.msr & MSR_PR)) {
 			r = kvmppc_pseries_do_hcall(vcpu);
 			kvmppc_core_prepare_to_enter(vcpu);
+		} else if (r == RESUME_PAGE_FAULT) {
+			srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+			r = kvmppc_book3s_hv_page_fault(run, vcpu,
+				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+			srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		}
 	} while (r == RESUME_GUEST);
 
-- 
1.7.10.rc3.219.g53414

[PATCH 09/12] KVM: PPC: Book3S HV: Fixes for late-joining threads

[Paul Mackerras]

If a thread in a virtual core becomes runnable while other threads
in the same virtual core are already running in the guest, it is
possible for the latecomer to join the others on the core without
first pulling them all out of the guest.  Currently this only happens
rarely, when a vcpu is first started.  This fixes some bugs and
omissions in the code in this case.

First, we need to check for VPA updates for the latecomer and make
a DTL entry for it.  Secondly, if it comes along while the master
vcpu is doing a VPA update, we don't need to do anything since the
master will pick it up in kvmppc_run_core.  To handle this correctly
we introduce a new vcore state, VCORE_STARTING.  Thirdly, there is
a race because we currently clear the hardware thread's hwthread_req
before waiting to see it get to nap.  A latecomer thread could have
its hwthread_req cleared before it gets to test it, and therefore
never increment the nap_count, leading to messages about wait_for_nap
timeouts.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_host.h |    7 ++++---
 arch/powerpc/kvm/book3s_hv.c        |   14 +++++++++++---
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 68f5a30..218534d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -289,9 +289,10 @@ struct kvmppc_vcore {
 
 /* Values for vcore_state */
 #define VCORE_INACTIVE	0
-#define VCORE_RUNNING	1
-#define VCORE_EXITING	2
-#define VCORE_SLEEPING	3
+#define VCORE_SLEEPING	1
+#define VCORE_STARTING	2
+#define VCORE_RUNNING	3
+#define VCORE_EXITING	4
 
 /*
  * Struct used to manage memory for a virtual processor area
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e729700..ba41967 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -368,6 +368,11 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 
 static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 {
+	if (!(vcpu->arch.vpa.update_pending ||
+	      vcpu->arch.slb_shadow.update_pending ||
+	      vcpu->arch.dtl.update_pending))
+		return;
+
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
@@ -902,7 +907,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->n_woken = 0;
 	vc->nap_count = 0;
 	vc->entry_exit_count = 0;
-	vc->vcore_state = VCORE_RUNNING;
+	vc->vcore_state = VCORE_STARTING;
 	vc->in_guest = 0;
 	vc->napping_threads = 0;
 
@@ -955,6 +960,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 		kvmppc_create_dtl_entry(vcpu, vc);
 	}
 
+	vc->vcore_state = VCORE_RUNNING;
 	preempt_disable();
 	spin_unlock(&vc->lock);
 
@@ -963,8 +969,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
 
 	__kvmppc_vcore_entry(NULL, vcpu0);
-	for (i = 0; i < threads_per_core; ++i)
-		kvmppc_release_hwthread(vc->pcpu + i);
 
 	spin_lock(&vc->lock);
 	/* disable sending of IPIs on virtual external irqs */
@@ -973,6 +977,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/* wait for secondary threads to finish writing their state to memory */
 	if (vc->nap_count < vc->n_woken)
 		kvmppc_wait_for_nap(vc);
+	for (i = 0; i < threads_per_core; ++i)
+		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
 	vc->vcore_state = VCORE_EXITING;
 	spin_unlock(&vc->lock);
@@ -1063,6 +1069,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvm_run->exit_reason = 0;
 	vcpu->arch.ret = RESUME_GUEST;
 	vcpu->arch.trap = 0;
+	kvmppc_update_vpas(vcpu);
 
 	/*
 	 * Synchronize with other threads in this virtual core
@@ -1086,6 +1093,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		if (vc->vcore_state == VCORE_RUNNING &&
 		    VCORE_EXIT_COUNT(vc) == 0) {
 			vcpu->arch.ptid = vc->n_runnable - 1;
+			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
 		}
 
-- 
1.7.10.rc3.219.g53414

[PATCH 10/12] KVM: PPC: Book3S HV: Run virtual core whenever any vcpus in it can run

[Paul Mackerras]

Currently the Book3S HV code implements a policy on multi-threaded
processors (i.e. POWER7) that requires all of the active vcpus in a
virtual core to be ready to run before we run the virtual core.
However, that causes problems on reset, because reset stops all vcpus
except vcpu 0, and can also reduce throughput since all four threads
in a virtual core have to wait whenever any one of them hits a
hypervisor page fault.

This relaxes the policy, allowing the virtual core to run as soon as
any vcpu in it is runnable.  With this, the KVMPPC_VCPU_STOPPED state
and the KVMPPC_VCPU_BUSY_IN_HOST state have been combined into a single
KVMPPC_VCPU_NOTREADY state, since we no longer need to distinguish
between them.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_host.h |    5 +--
 arch/powerpc/kvm/book3s_hv.c        |   74 ++++++++++++++++++-----------------
 2 files changed, 40 insertions(+), 39 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 218534d..1e8cbd1 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -563,9 +563,8 @@ struct kvm_vcpu_arch {
 };
 
 /* Values for vcpu->arch.state */
-#define KVMPPC_VCPU_STOPPED		0
-#define KVMPPC_VCPU_BUSY_IN_HOST	1
-#define KVMPPC_VCPU_RUNNABLE		2
+#define KVMPPC_VCPU_NOTREADY		0
+#define KVMPPC_VCPU_RUNNABLE		1
 
 /* Values for vcpu->arch.io_gpr */
 #define KVM_MMIO_REG_MASK	0x001f
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ba41967..3047b59 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -669,10 +669,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
-	/*
-	 * We consider the vcpu stopped until we see the first run ioctl for it.
-	 */
-	vcpu->arch.state = KVMPPC_VCPU_STOPPED;
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 
 	init_waitqueue_head(&vcpu->arch.cpu_run);
 
@@ -759,9 +756,8 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 {
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 	--vc->n_runnable;
-	++vc->n_busy;
 	list_del(&vcpu->arch.run_list);
 }
 
@@ -1062,7 +1058,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int n_ceded;
-	int prev_state;
 	struct kvmppc_vcore *vc;
 	struct kvm_vcpu *v, *vn;
 
@@ -1079,7 +1074,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	vcpu->arch.ceded = 0;
 	vcpu->arch.run_task = current;
 	vcpu->arch.kvm_run = kvm_run;
-	prev_state = vcpu->arch.state;
 	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
 	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
 	++vc->n_runnable;
@@ -1089,35 +1083,26 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * If the vcore is already running, we may be able to start
 	 * this thread straight away and have it join in.
 	 */
-	if (prev_state == KVMPPC_VCPU_STOPPED) {
+	if (!signal_pending(current)) {
 		if (vc->vcore_state == VCORE_RUNNING &&
 		    VCORE_EXIT_COUNT(vc) == 0) {
 			vcpu->arch.ptid = vc->n_runnable - 1;
 			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
+		} else if (vc->vcore_state == VCORE_SLEEPING) {
+			wake_up(&vc->wq);
 		}
 
-	} else if (prev_state == KVMPPC_VCPU_BUSY_IN_HOST)
-		--vc->n_busy;
+	}
 
 	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
 	       !signal_pending(current)) {
-		if (vc->n_busy || vc->vcore_state != VCORE_INACTIVE) {
+		if (vc->vcore_state != VCORE_INACTIVE) {
 			spin_unlock(&vc->lock);
 			kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE);
 			spin_lock(&vc->lock);
 			continue;
 		}
-		vc->runner = vcpu;
-		n_ceded = 0;
-		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
-			if (!v->arch.pending_exceptions)
-				n_ceded += v->arch.ceded;
-		if (n_ceded == vc->n_runnable)
-			kvmppc_vcore_blocked(vc);
-		else
-			kvmppc_run_core(vc);
-
 		list_for_each_entry_safe(v, vn, &vc->runnable_threads,
 					 arch.run_list) {
 			kvmppc_core_prepare_to_enter(v);
@@ -1129,23 +1114,40 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 				wake_up(&v->arch.cpu_run);
 			}
 		}
+		if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
+			break;
+		vc->runner = vcpu;
+		n_ceded = 0;
+		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
+			if (!v->arch.pending_exceptions)
+				n_ceded += v->arch.ceded;
+		if (n_ceded == vc->n_runnable)
+			kvmppc_vcore_blocked(vc);
+		else
+			kvmppc_run_core(vc);
 		vc->runner = NULL;
 	}
 
-	if (signal_pending(current)) {
-		while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
-		       (vc->vcore_state == VCORE_RUNNING ||
-			vc->vcore_state == VCORE_EXITING)) {
-			spin_unlock(&vc->lock);
-			kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
-			spin_lock(&vc->lock);
-		}
-		if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
-			kvmppc_remove_runnable(vc, vcpu);
-			vcpu->stat.signal_exits++;
-			kvm_run->exit_reason = KVM_EXIT_INTR;
-			vcpu->arch.ret = -EINTR;
-		}
+	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
+	       (vc->vcore_state == VCORE_RUNNING ||
+		vc->vcore_state == VCORE_EXITING)) {
+		spin_unlock(&vc->lock);
+		kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
+		spin_lock(&vc->lock);
+	}
+
+	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
+		kvmppc_remove_runnable(vc, vcpu);
+		vcpu->stat.signal_exits++;
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		vcpu->arch.ret = -EINTR;
+	}
+
+	if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
+		/* Wake up some vcpu to run the core */
+		v = list_first_entry(&vc->runnable_threads,
+				     struct kvm_vcpu, arch.run_list);
+		wake_up(&v->arch.cpu_run);
 	}
 
 	spin_unlock(&vc->lock);
-- 
1.7.10.rc3.219.g53414

[PATCH 11/12] KVM: PPC: Book3S HV: Fix accounting of stolen time

[Paul Mackerras]

Currently the code that accounts stolen time tends to overestimate the
stolen time, and will sometimes report more stolen time in a DTL
(dispatch trace log) entry than has elapsed since the last DTL entry.
This can cause guests to underflow the user or system time measured
for some tasks, leading to ridiculous CPU percentages and total runtimes
being reported by top and other utilities.

In addition, the current code was designed for the previous policy where
a vcore would only run when all the vcpus in it were runnable, and so
only counted stolen time on a per-vcore basis.  Now that a vcore can
run while some of the vcpus in it are doing other things in the kernel
(e.g. handling a page fault), we need to count the time when a vcpu task
is preempted while it is not running as part of a vcore as stolen also.

To do this, we bring back the BUSY_IN_HOST vcpu state and extend the
vcpu_load/put functions to count preemption time while the vcpu is
in that state.  Handling the transitions between the RUNNING and
BUSY_IN_HOST states requires checking and updating two variables
(accumulated time stolen and time last preempted), so we add a new
spinlock, vcpu->arch.tbacct_lock.  This protects both the per-vcpu
stolen/preempt-time variables, and the per-vcore variables while this
vcpu is running the vcore.

Finally, we now don't count time spent in userspace as stolen time.
The task could be executing in userspace on behalf of the vcpu, or
it could be preempted, or the vcpu could be genuinely stopped.  Since
we have no way of dividing up the time between these cases, we don't
count any of it as stolen.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_host.h |    5 ++
 arch/powerpc/kvm/book3s_hv.c        |  127 ++++++++++++++++++++++++++++++-----
 2 files changed, 117 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1e8cbd1..3093896 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -559,12 +559,17 @@ struct kvm_vcpu_arch {
 	unsigned long dtl_index;
 	u64 stolen_logged;
 	struct kvmppc_vpa slb_shadow;
+
+	spinlock_t tbacct_lock;
+	u64 busy_stolen;
+	u64 busy_preempt;
 #endif
 };
 
 /* Values for vcpu->arch.state */
 #define KVMPPC_VCPU_NOTREADY		0
 #define KVMPPC_VCPU_RUNNABLE		1
+#define KVMPPC_VCPU_BUSY_IN_HOST	2
 
 /* Values for vcpu->arch.io_gpr */
 #define KVM_MMIO_REG_MASK	0x001f
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3047b59..3c978e1 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -57,23 +57,74 @@
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define EXIT_DEBUG_INT */
 
+/* Used as a "null" value for timebase values */
+#define TB_NIL	(~(u64)0)
+
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
+/*
+ * We use the vcpu_load/put functions to measure stolen time.
+ * Stolen time is counted as time when either the vcpu is able to
+ * run as part of a virtual core, but the task running the vcore
+ * is preempted or sleeping, or when the vcpu needs something done
+ * in the kernel by the task running the vcpu, but that task is
+ * preempted or sleeping.  Those two things have to be counted
+ * separately, since one of the vcpu tasks will take on the job
+ * of running the core, and the other vcpu tasks in the vcore will
+ * sleep waiting for it to do that, but that sleep shouldn't count
+ * as stolen time.
+ *
+ * Hence we accumulate stolen time when the vcpu can run as part of
+ * a vcore using vc->stolen_tb, and the stolen time when the vcpu
+ * needs its task to do other things in the kernel (for example,
+ * service a page fault) in busy_stolen.  We don't accumulate
+ * stolen time for a vcore when it is inactive, or for a vcpu
+ * when it is in state RUNNING or NOTREADY.  NOTREADY is a bit of
+ * a misnomer; it means that the vcpu task is not executing in
+ * the KVM_VCPU_RUN ioctl, i.e. it is in userspace or elsewhere in
+ * the kernel.  We don't have any way of dividing up that time
+ * between time that the vcpu is genuinely stopped, time that
+ * the task is actively working on behalf of the vcpu, and time
+ * that the task is preempted, so we don't count any of it as
+ * stolen.
+ *
+ * Updates to busy_stolen are protected by arch.tbacct_lock;
+ * updates to vc->stolen_tb are protected by the arch.tbacct_lock
+ * of the vcpu that has taken responsibility for running the vcore
+ * (i.e. vc->runner).  The stolen times are measured in units of
+ * timebase ticks.  (Note that the != TB_NIL checks below are
+ * purely defensive; they should never fail.)
+ */
+
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
-	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
+	spin_lock(&vcpu->arch.tbacct_lock);
+	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
+	    vc->preempt_tb != TB_NIL) {
 		vc->stolen_tb += mftb() - vc->preempt_tb;
+		vc->preempt_tb = TB_NIL;
+	}
+	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST &&
+	    vcpu->arch.busy_preempt != TB_NIL) {
+		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
+		vcpu->arch.busy_preempt = TB_NIL;
+	}
+	spin_unlock(&vcpu->arch.tbacct_lock);
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
+	spin_lock(&vcpu->arch.tbacct_lock);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
 		vc->preempt_tb = mftb();
+	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
+		vcpu->arch.busy_preempt = mftb();
+	spin_unlock(&vcpu->arch.tbacct_lock);
 }
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
@@ -389,24 +440,61 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 	spin_unlock(&vcpu->arch.vpa_update_lock);
 }
 
+/*
+ * Return the accumulated stolen time for the vcore up until `now'.
+ * The caller should hold the vcore lock.
+ */
+static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
+{
+	u64 p;
+
+	/*
+	 * If we are the task running the vcore, then since we hold
+	 * the vcore lock, we can't be preempted, so stolen_tb/preempt_tb
+	 * can't be updated, so we don't need the tbacct_lock.
+	 * If the vcore is inactive, it can't become active (since we
+	 * hold the vcore lock), so the vcpu load/put functions won't
+	 * update stolen_tb/preempt_tb, and we don't need tbacct_lock.
+	 */
+	if (vc->vcore_state != VCORE_INACTIVE &&
+	    vc->runner->arch.run_task != current) {
+		spin_lock(&vc->runner->arch.tbacct_lock);
+		p = vc->stolen_tb;
+		if (vc->preempt_tb != TB_NIL)
+			p += now - vc->preempt_tb;
+		spin_unlock(&vc->runner->arch.tbacct_lock);
+	} else {
+		p = vc->stolen_tb;
+	}
+	return p;
+}
+
 static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 				    struct kvmppc_vcore *vc)
 {
 	struct dtl_entry *dt;
 	struct lppaca *vpa;
-	unsigned long old_stolen;
+	unsigned long stolen;
+	unsigned long core_stolen;
+	u64 now;
 
 	dt = vcpu->arch.dtl_ptr;
 	vpa = vcpu->arch.vpa.pinned_addr;
-	old_stolen = vcpu->arch.stolen_logged;
-	vcpu->arch.stolen_logged = vc->stolen_tb;
+	now = mftb();
+	core_stolen = vcore_stolen_time(vc, now);
+	stolen = core_stolen - vcpu->arch.stolen_logged;
+	vcpu->arch.stolen_logged = core_stolen;
+	spin_lock(&vcpu->arch.tbacct_lock);
+	stolen += vcpu->arch.busy_stolen;
+	vcpu->arch.busy_stolen = 0;
+	spin_unlock(&vcpu->arch.tbacct_lock);
 	if (!dt || !vpa)
 		return;
 	memset(dt, 0, sizeof(struct dtl_entry));
 	dt->dispatch_reason = 7;
 	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
-	dt->timebase = mftb();
-	dt->enqueue_to_dispatch_time = vc->stolen_tb - old_stolen;
+	dt->timebase = now;
+	dt->enqueue_to_dispatch_time = stolen;
 	dt->srr0 = kvmppc_get_pc(vcpu);
 	dt->srr1 = vcpu->arch.shregs.msr;
 	++dt;
@@ -666,6 +754,8 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.pvr = mfspr(SPRN_PVR);
 	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
+	spin_lock_init(&vcpu->arch.tbacct_lock);
+	vcpu->arch.busy_preempt = TB_NIL;
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
@@ -681,7 +771,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			INIT_LIST_HEAD(&vcore->runnable_threads);
 			spin_lock_init(&vcore->lock);
 			init_waitqueue_head(&vcore->wq);
-			vcore->preempt_tb = mftb();
+			vcore->preempt_tb = TB_NIL;
 		}
 		kvm->arch.vcores[core] = vcore;
 	}
@@ -694,7 +784,6 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	++vcore->num_threads;
 	spin_unlock(&vcore->lock);
 	vcpu->arch.vcore = vcore;
-	vcpu->arch.stolen_logged = vcore->stolen_tb;
 
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
@@ -754,9 +843,17 @@ extern void xics_wake_cpu(int cpu);
 static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 				   struct kvm_vcpu *vcpu)
 {
+	u64 now;
+
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
+	spin_lock(&vcpu->arch.tbacct_lock);
+	now = mftb();
+	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
+		vcpu->arch.stolen_logged;
+	vcpu->arch.busy_preempt = now;
+	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
+	spin_unlock(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
 	list_del(&vcpu->arch.run_list);
 }
@@ -931,10 +1028,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 			vcpu->arch.ptid = ptid++;
 		}
 	}
-	if (!vcpu0) {
-		vc->vcore_state = VCORE_INACTIVE;
-		return;		/* nothing to run; should never happen */
-	}
+	if (!vcpu0)
+		goto out;	/* nothing to run; should never happen */
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
 		if (vcpu->arch.ceded)
 			vcpu->arch.ptid = ptid++;
@@ -949,7 +1044,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 		goto out;
 	}
 
-	vc->stolen_tb += mftb() - vc->preempt_tb;
 	vc->pcpu = smp_processor_id();
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		kvmppc_start_thread(vcpu);
@@ -1014,7 +1108,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 
  out:
 	vc->vcore_state = VCORE_INACTIVE;
-	vc->preempt_tb = mftb();
 	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
 				 arch.run_list) {
 		if (vcpu->arch.ret != RESUME_GUEST) {
@@ -1074,7 +1167,9 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	vcpu->arch.ceded = 0;
 	vcpu->arch.run_task = current;
 	vcpu->arch.kvm_run = kvm_run;
+	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
 	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
+	vcpu->arch.busy_preempt = TB_NIL;
 	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
 	++vc->n_runnable;
 
@@ -1188,6 +1283,7 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	flush_vsx_to_thread(current);
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
 	vcpu->arch.pgdir = current->mm->pgd;
+	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
 		r = kvmppc_run_vcpu(run, vcpu);
@@ -1205,6 +1301,7 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	} while (r == RESUME_GUEST);
 
  out:
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 	atomic_dec(&vcpu->kvm->arch.vcpus_running);
 	return r;
 }
-- 
1.7.10.rc3.219.g53414

[PATCH 12/12] KVM: PPC: Book3S HV: Fix calculation of guest phys address for MMIO emulation

[Paul Mackerras]

In the case where the host kernel is using a 64kB base page size and
the guest uses a 4k HPTE (hashed page table entry) to map an emulated
MMIO device, we were calculating the guest physical address wrongly.
We were calculating a gfn as the guest physical address shifted right
16 bits (PAGE_SHIFT) but then only adding back in 12 bits from the
effective address, since the HPTE had a 4k page size.  Thus the gpa
reported to userspace was missing 4 bits.

Instead, we now compute the guest physical address from the HPTE
without reference to the host page size, and then compute the gfn
by shifting the gpa right PAGE_SHIFT bits.

Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s_64_mmu_hv.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index a389cc6..632229c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -571,7 +571,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hptep, hpte[3], r;
 	unsigned long mmu_seq, psize, pte_size;
-	unsigned long gfn, hva, pfn;
+	unsigned long gpa, gfn, hva, pfn;
 	struct kvm_memory_slot *memslot;
 	unsigned long *rmap;
 	struct revmap_entry *rev;
@@ -609,15 +609,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	/* Translate the logical address and get the page */
 	psize = hpte_page_size(hpte[0], r);
-	gfn = hpte_rpn(r, psize);
+	gpa = (r & HPTE_R_RPN & ~(psize - 1)) | (ea & (psize - 1));
+	gfn = gpa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(kvm, gfn);
 
 	/* No memslot means it's an emulated MMIO region */
-	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
-		unsigned long gpa = (gfn << PAGE_SHIFT) | (ea & (psize - 1));
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
 					      dsisr & DSISR_ISSTORE);
-	}
 
 	if (!kvm->arch.using_mmu_notifiers)
 		return -EFAULT;		/* should never get here */
-- 
1.7.10.rc3.219.g53414

[PATCH v2 04/12] KVM: PPC: Book3S HV: Allow KVM guests to stop secondary threads coming online

[Paul Mackerras]

When a Book3S HV KVM guest is running, we need the host to be in
single-thread mode, that is, all of the cores (or at least all of
the cores where the KVM guest could run) to be running only one
active hardware thread.  This is because of the hardware restriction
in POWER processors that all of the hardware threads in the core
must be in the same logical partition.  Complying with this restriction
is much easier if, from the host kernel's point of view, only one
hardware thread is active.

This adds two hooks in the SMP hotplug code to allow the KVM code to
make sure that secondary threads (i.e. hardware threads other than
thread 0) cannot come online while any KVM guest exists.  The KVM
code still has to check that any core where it runs a guest has the
secondary threads offline, but having done that check it can now be
sure that they will not come online while the guest is running.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
v2: export {,un}inhibit_secondary_onlining for the case where KVM is
    a module.

 arch/powerpc/include/asm/smp.h |    8 +++++++
 arch/powerpc/kernel/smp.c      |   46 ++++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c   |   12 +++++++++--
 3 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ebc24dc..b625a1a 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -66,6 +66,14 @@ void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);
 void generic_set_cpu_dead(unsigned int cpu);
 int generic_check_cpu_restart(unsigned int cpu);
+
+extern void inhibit_secondary_onlining(void);
+extern void uninhibit_secondary_onlining(void);
+
+#else /* HOTPLUG_CPU */
+static inline void inhibit_secondary_onlining(void) {}
+static inline void uninhibit_secondary_onlining(void) {}
+
 #endif
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007..c45f51d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -410,6 +410,45 @@ int generic_check_cpu_restart(unsigned int cpu)
 {
 	return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
 }
+
+static atomic_t secondary_inhibit_count;
+
+/*
+ * Don't allow secondary CPU threads to come online
+ */
+void inhibit_secondary_onlining(void)
+{
+	/*
+	 * This makes secondary_inhibit_count stable during cpu
+	 * online/offline operations.
+	 */
+	get_online_cpus();
+
+	atomic_inc(&secondary_inhibit_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(inhibit_secondary_onlining);
+
+/*
+ * Allow secondary CPU threads to come online again
+ */
+void uninhibit_secondary_onlining(void)
+{
+	get_online_cpus();
+	atomic_dec(&secondary_inhibit_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining);
+
+static int secondaries_inhibited(void)
+{
+	return atomic_read(&secondary_inhibit_count);
+}
+
+#else /* HOTPLUG_CPU */
+
+#define secondaries_inhibited()		0
+
 #endif
 
 static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
@@ -428,6 +467,13 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc, c;
 
+	/*
+	 * Don't allow secondary threads to come online if inhibited
+	 */
+	if (threads_per_core > 1 && secondaries_inhibited() &&
+	    cpu % threads_per_core != 0)
+		return -EBUSY;
+
 	if (smp_ops == NULL ||
 	    (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
 		return -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 53d950b..310ffd7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -47,6 +47,7 @@
 #include <asm/page.h>
 #include <asm/hvcall.h>
 #include <asm/switch_to.h>
+#include <asm/smp.h>
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
@@ -918,8 +919,6 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	/*
 	 * Make sure we are running on thread 0, and that
 	 * secondary threads are offline.
-	 * XXX we should also block attempts to bring any
-	 * secondary threads online.
 	 */
 	if (threads_per_core > 1 && !on_primary_thread()) {
 		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
@@ -1618,11 +1617,20 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 	kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206);
 	spin_lock_init(&kvm->arch.slot_phys_lock);
+
+	/*
+	 * Don't allow secondary CPU threads to come online
+	 * while any KVM VMs exist.
+	 */
+	inhibit_secondary_onlining();
+
 	return 0;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
+	uninhibit_secondary_onlining();
+
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
-- 
1.7.10