Doing debugfs creation after vm creation leaves things in a
quasi-initialized state for a while. This is further complicated by the
fact that we tear down debugfs from kvm_destroy_vm(). Align debugfs and
stats init/destroy with the vm init/destroy pattern to avoid any
headaches.
Note the fix for a benign mistake in error handling for calls to
kvm_arch_create_vm_debugfs() rolled in. Since all implementations of
the function return 0 unconditionally it isn't actually a bug at
the moment.
Lastly, tear down debugfs/stats data in the kvm_create_vm_debugfs()
error path. Previously it was safe to assume that kvm_destroy_vm() would
take out the garbage, that is no longer the case.
Signed-off-by: Oliver Upton <oupton@xxxxxxxxxx>
---
virt/kvm/kvm_main.c | 42 +++++++++++++++++++-----------------------
1 file changed, 19 insertions(+), 23 deletions(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1abbc6b07c19..54793de42d14 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -951,7 +951,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
char dir_name[ITOA_MAX_LEN * 2];
struct kvm_stat_data *stat_data;
const struct _kvm_stats_desc *pdesc;
- int i, ret;
+ int i, ret = -ENOMEM;
int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
kvm_vcpu_stats_header.num_desc;
@@ -980,13 +980,13 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
sizeof(*kvm->debugfs_stat_data),
GFP_KERNEL_ACCOUNT);
if (!kvm->debugfs_stat_data)
- return -ENOMEM;
+ goto out_err;
for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
pdesc = &kvm_vm_stats_desc[i];
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
- return -ENOMEM;
+ goto out_err;
stat_data->kvm = kvm;
stat_data->desc = pdesc;
@@ -1001,7 +1001,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
pdesc = &kvm_vcpu_stats_desc[i];
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
- return -ENOMEM;
+ goto out_err;
stat_data->kvm = kvm;
stat_data->desc = pdesc;
@@ -1013,12 +1013,13 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
}
ret = kvm_arch_create_vm_debugfs(kvm);
- if (ret) {
- kvm_destroy_vm_debugfs(kvm);
- return i;
- }
+ if (ret)
+ goto out_err;
return 0;
+out_err:
+ kvm_destroy_vm_debugfs(kvm);
+ return ret;
}
/*
@@ -1049,7 +1050,7 @@ int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
return 0;
}
-static struct kvm *kvm_create_vm(unsigned long type)
+static struct kvm *kvm_create_vm(unsigned long type, int fd)
{
struct kvm *kvm = kvm_arch_alloc_vm();
struct kvm_memslots *slots;
@@ -1134,7 +1135,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
r = kvm_arch_post_init_vm(kvm);
if (r)
- goto out_err;
+ goto out_err_mmu_notifier;
mutex_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
@@ -1150,12 +1151,18 @@ static struct kvm *kvm_create_vm(unsigned long type)
*/
if (!try_module_get(kvm_chardev_ops.owner)) {
r = -ENODEV;
- goto out_err;
+ goto out_err_mmu_notifier;
}
+ r = kvm_create_vm_debugfs(kvm, fd);
+ if (r)
+ goto out_err;
+
return kvm;
out_err:
+ module_put(kvm_chardev_ops.owner);
+out_err_mmu_notifier:
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
if (kvm->mmu_notifier.ops)
mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
@@ -4760,7 +4767,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
if (fd < 0)
return fd;
- kvm = kvm_create_vm(type);
+ kvm = kvm_create_vm(type, fd);
if (IS_ERR(kvm)) {
r = PTR_ERR(kvm);
goto put_fd;
@@ -4777,17 +4784,6 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
goto put_kvm;
}
- /*
- * Don't call kvm_put_kvm anymore at this point; file->f_op is
- * already set, with ->release() being kvm_vm_release(). In error
- * cases it will be called by the final fput(file) and will take
- * care of doing kvm_put_kvm(kvm).
- */
- if (kvm_create_vm_debugfs(kvm, r) < 0) {
- fput(file);
- r = -ENOMEM;
- goto put_fd;
- }
kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm);
fd_install(fd, file);
--
2.36.0.rc0.470.gd361397f0d-goog
