[v4 4/5] KVM: PPC: Book3S HV: retry page migration before erroring-out

[Ram Pai <linuxram@us.ibm.com>]

The page requested for page-in; sometimes, can have transient
references, and hence cannot migrate immediately. Retry a few times
before returning error.

The same is true for non-migrated pages that are migrated in
H_SVM_INIT_DONE hanlder.  Retry a few times before returning error.

H_SVM_PAGE_IN interface is enhanced to return H_BUSY if the page is
not in a migratable state.

Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Claudio Carvalho <cclaudio@linux.ibm.com>
Cc: kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org

Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
 Documentation/powerpc/ultravisor.rst |   1 +
 arch/powerpc/kvm/book3s_hv_uvmem.c   | 106 ++++++++++++++++++++++++-----------
 2 files changed, 74 insertions(+), 33 deletions(-)

diff --git a/Documentation/powerpc/ultravisor.rst b/Documentation/powerpc/ultravisor.rst
index ba6b1bf..fe533ad 100644
--- a/Documentation/powerpc/ultravisor.rst
+++ b/Documentation/powerpc/ultravisor.rst
@@ -1035,6 +1035,7 @@ Return values
 	* H_PARAMETER	if ``guest_pa`` is invalid.
 	* H_P2		if ``flags`` is invalid.
 	* H_P3		if ``order`` of page is invalid.
+	* H_BUSY	if ``page`` is not in a state to pagein
 
 Description
 ~~~~~~~~~~~
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 3274663..a206984 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -672,7 +672,7 @@ static int kvmppc_svm_migrate_page(struct vm_area_struct *vma,
 		return ret;
 
 	if (!(*mig.src & MIGRATE_PFN_MIGRATE)) {
-		ret = -1;
+		ret = -2;
 		goto out_finalize;
 	}
 
@@ -700,43 +700,73 @@ static int kvmppc_svm_migrate_page(struct vm_area_struct *vma,
 	return ret;
 }
 
-int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
-		const struct kvm_memory_slot *memslot)
+/*
+ * return 1, if some page migration failed because of transient error,
+ * while the remaining pages migrated successfully.
+ * The caller can use this as a hint to retry.
+ *
+ * return 0 otherwise. *ret indicates the success status
+ * of this call.
+ */
+static bool __kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot, int *ret)
 {
 	unsigned long gfn = memslot->base_gfn;
 	struct vm_area_struct *vma;
 	unsigned long start, end;
-	int ret = 0;
+	bool retry = false;
 
+	*ret = 0;
 	while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) {
 
 		mmap_read_lock(kvm->mm);
 		start = gfn_to_hva(kvm, gfn);
 		if (kvm_is_error_hva(start)) {
-			ret = H_STATE;
+			*ret = H_STATE;
 			goto next;
 		}
 
 		end = start + (1UL << PAGE_SHIFT);
 		vma = find_vma_intersection(kvm->mm, start, end);
 		if (!vma || vma->vm_start > start || vma->vm_end < end) {
-			ret = H_STATE;
+			*ret = H_STATE;
 			goto next;
 		}
 
 		mutex_lock(&kvm->arch.uvmem_lock);
-		ret = kvmppc_svm_migrate_page(vma, start, end,
+		*ret = kvmppc_svm_migrate_page(vma, start, end,
 				(gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false);
 		mutex_unlock(&kvm->arch.uvmem_lock);
-		if (ret)
-			ret = H_STATE;
 
 next:
 		mmap_read_unlock(kvm->mm);
+		if (*ret == -2) {
+			retry = true;
+			continue;
+		}
 
-		if (ret)
-			break;
+		if (*ret)
+			return false;
 	}
+	return retry;
+}
+
+#define REPEAT_COUNT 10
+
+int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	int ret = 0, repeat_count = REPEAT_COUNT;
+
+	/*
+	 * try migration of pages in the memslot 'repeat_count' number of
+	 * times, provided each time migration fails because of transient
+	 * errors only.
+	 */
+	while (__kvmppc_uv_migrate_mem_slot(kvm, memslot, &ret) &&
+		repeat_count--)
+		;
+
 	return ret;
 }
 
@@ -812,7 +842,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	struct vm_area_struct *vma;
 	int srcu_idx;
 	unsigned long gfn = gpa >> page_shift;
-	int ret;
+	int ret, repeat_count = REPEAT_COUNT;
 
 	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
 		return H_UNSUPPORTED;
@@ -826,34 +856,44 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	if (flags & H_PAGE_IN_SHARED)
 		return kvmppc_share_page(kvm, gpa, page_shift);
 
-	ret = H_PARAMETER;
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	mmap_read_lock(kvm->mm);
 
-	start = gfn_to_hva(kvm, gfn);
-	if (kvm_is_error_hva(start))
-		goto out;
-
-	mutex_lock(&kvm->arch.uvmem_lock);
 	/* Fail the page-in request of an already paged-in page */
-	if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
-		goto out_unlock;
+	mutex_lock(&kvm->arch.uvmem_lock);
+	ret = kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+	if (ret) {
+		srcu_read_unlock(&kvm->srcu, srcu_idx);
+		return H_PARAMETER;
+	}
 
-	end = start + (1UL << page_shift);
-	vma = find_vma_intersection(kvm->mm, start, end);
-	if (!vma || vma->vm_start > start || vma->vm_end < end)
-		goto out_unlock;
+	do {
+		ret = H_PARAMETER;
+		mmap_read_lock(kvm->mm);
 
-	if (kvmppc_svm_migrate_page(vma, start, end, gpa, kvm, page_shift,
-				true))
-		goto out_unlock;
+		start = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(start)) {
+			mmap_read_unlock(kvm->mm);
+			break;
+		}
 
-	ret = H_SUCCESS;
+		end = start + (1UL << page_shift);
+		vma = find_vma_intersection(kvm->mm, start, end);
+		if (!vma || vma->vm_start > start || vma->vm_end < end) {
+			mmap_read_unlock(kvm->mm);
+			break;
+		}
+
+		mutex_lock(&kvm->arch.uvmem_lock);
+		ret = kvmppc_svm_migrate_page(vma, start, end, gpa, kvm, page_shift, true);
+		mutex_unlock(&kvm->arch.uvmem_lock);
+
+		mmap_read_unlock(kvm->mm);
+	} while (ret == -2 && repeat_count--);
+
+	if (ret == -2)
+		ret = H_BUSY;
 
-out_unlock:
-	mutex_unlock(&kvm->arch.uvmem_lock);
-out:
-	mmap_read_unlock(kvm->mm);
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return ret;
 }
-- 
1.8.3.1