kvm: avoid page allocation failure in kvm_set_memory_region()

[ Upstream commit 744961341d472db6272ed9b42319a90f5a2aa7c4 ]

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@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cfbe0e7..272fee8 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -478,7 +478,7 @@ 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;
 
@@ -529,7 +529,7 @@ 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);
 }
@@ -585,7 +585,7 @@ 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)
@@ -867,10 +867,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
        }
 
        if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
-               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));
+
                slot = id_to_memslot(slots, mem->slot);
                slot->flags |= KVM_MEMSLOT_INVALID;
 
@@ -900,10 +901,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
         * will get overwritten by update_memslots anyway.
         */
        if (!slots) {
-               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));
        }
 
        /* actual memory is freed via old in kvm_free_physmem_slot below */
@@ -917,7 +918,7 @@ 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 +937,7 @@ 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: