[PATCH v2] kvm: avoid page allocation failure in kvm_set_memory_region()

[Igor Mammedov <imammedo@xxxxxxxxxx>]

KVM guest can fail to startup with following trace on host:

qemu-system-x86: page allocation failure: order:4, mode:0x40d0
Call Trace:
  dump_stack+0x47/0x67
  warn_alloc_failed+0xee/0x150
  __alloc_pages_direct_compact+0x14a/0x150
  __alloc_pages_nodemask+0x776/0xb80
  alloc_kmem_pages+0x3a/0x110
  kmalloc_order+0x13/0x50
  kmemdup+0x1b/0x40
  __kvm_set_memory_region+0x24a/0x9f0 [kvm]
  kvm_set_ioapic+0x130/0x130 [kvm]
  kvm_set_memory_region+0x21/0x40 [kvm]
  kvm_vm_ioctl+0x43f/0x750 [kvm]

Failure happens when attempting to allocate pages for
'struct kvm_memslots', however it doesn't have to be
present in physically contiguous (kmalloc-ed) address
space, change allocation to kvm_kvzalloc() so that
it will be vmalloc-ed when its size is more then a page.

Signed-off-by: Igor Mammedov <imammedo@xxxxxxxxxx>
---
v2:
 - alloc initial memslots with vmalloc
 - use kvfree in every place where memslots are freed

TODO:
 - work on follow up patches to allocate space for
   actual amount of memory_slots instead of possible maximum.
---
 virt/kvm/kvm_main.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a2214d9..cc6a25d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -471,7 +471,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
 	r = -ENOMEM;
-	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 	if (!kvm->memslots)
 		goto out_err_no_srcu;
 
@@ -522,7 +522,7 @@ out_err_no_srcu:
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
-	kfree(kvm->memslots);
+	kvfree(kvm->memslots);
 	kvm_arch_free_vm(kvm);
 	return ERR_PTR(r);
 }
@@ -578,7 +578,7 @@ static void kvm_free_physmem(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, slots)
 		kvm_free_physmem_slot(kvm, memslot, NULL);
 
-	kfree(kvm->memslots);
+	kvfree(kvm->memslots);
 }
 
 static void kvm_destroy_devices(struct kvm *kvm)
@@ -871,10 +871,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			goto out_free;
 	}
 
-	slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-			GFP_KERNEL);
+	slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 	if (!slots)
 		goto out_free;
+	memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 
 	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
 		slot = id_to_memslot(slots, mem->slot);
@@ -917,7 +917,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
 	kvm_free_physmem_slot(kvm, &old, &new);
-	kfree(old_memslots);
+	kvfree(old_memslots);
 
 	/*
 	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
@@ -936,7 +936,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	return 0;
 
 out_slots:
-	kfree(slots);
+	kvfree(slots);
 out_free:
 	kvm_free_physmem_slot(kvm, &new, &old);
 out:
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html