linux.git/drivers/virt, branch v5.16.1

nitro_enclaves: Use get_user_pages_unlocked() call to handle mmap assert

2021-12-21T10:08:19+00:00

After commit 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked()
annotations to find_vma*()"), the call to get_user_pages() will trigger
the mmap assert.

static inline void mmap_assert_locked(struct mm_struct *mm)
{
	lockdep_assert_held(&mm->mmap_lock);
	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
}

[   62.521410] kernel BUG at include/linux/mmap_lock.h:156!
...........................................................
[   62.538938] RIP: 0010:find_vma+0x32/0x80
...........................................................
[   62.605889] Call Trace:
[   62.608502]  
[   62.610956]  ? lock_timer_base+0x61/0x80
[   62.614106]  find_extend_vma+0x19/0x80
[   62.617195]  __get_user_pages+0x9b/0x6a0
[   62.620356]  __gup_longterm_locked+0x42d/0x450
[   62.623721]  ? finish_wait+0x41/0x80
[   62.626748]  ? __kmalloc+0x178/0x2f0
[   62.629768]  ne_set_user_memory_region_ioctl.isra.0+0x225/0x6a0 [nitro_enclaves]
[   62.635776]  ne_enclave_ioctl+0x1cf/0x6d7 [nitro_enclaves]
[   62.639541]  __x64_sys_ioctl+0x82/0xb0
[   62.642620]  do_syscall_64+0x3b/0x90
[   62.645642]  entry_SYSCALL_64_after_hwframe+0x44/0xae

Use get_user_pages_unlocked() when setting the enclave memory regions.
That's a similar pattern as mmap_read_lock() used together with
get_user_pages().

Fixes: 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()")
Cc: stable@vger.kernel.org
Signed-off-by: Andra Paraschiv 
Link: https://lore.kernel.org/r/20211220195856.6549-1-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman

virt: acrn: Introduce interfaces for virtual device creating/destroying

2021-10-05T14:14:10+00:00

The ACRN hypervisor can emulate a virtual device within hypervisor for a
Guest VM. The emulated virtual device can work without the ACRN
userspace after creation. The hypervisor do the emulation of that device.

To support the virtual device creating/destroying, HSM provides the
following ioctls:
  - ACRN_IOCTL_CREATE_VDEV
    Pass data struct acrn_vdev from userspace to the hypervisor, and inform
    the hypervisor to create a virtual device for a User VM.
  - ACRN_IOCTL_DESTROY_VDEV
    Pass data struct acrn_vdev from userspace to the hypervisor, and inform
    the hypervisor to destroy a virtual device of a User VM.

These new APIs will be used by user space code vm_add_hv_vdev and
vm_remove_hv_vdev in
https://github.com/projectacrn/acrn-hypervisor/blob/master/devicemodel/core/vmmapi.c

Signed-off-by: Shuo Liu 
Signed-off-by: Fei Li 
Link: https://lore.kernel.org/r/20210923084128.18902-3-fei1.li@intel.com
Signed-off-by: Greg Kroah-Hartman

virt: acrn: Introduce interfaces for MMIO device passthrough

2021-10-05T14:14:10+00:00

MMIO device passthrough enables an OS in a virtual machine to directly
access a MMIO device in the host. It promises almost the native
performance, which is required in performance-critical scenarios of
ACRN.

HSM provides the following ioctls:
  - Assign - ACRN_IOCTL_ASSIGN_MMIODEV
    Pass data struct acrn_mmiodev from userspace to the hypervisor, and
    inform the hypervisor to assign a MMIO device to a User VM.

  - De-assign - ACRN_IOCTL_DEASSIGN_PCIDEV
    Pass data struct acrn_mmiodev from userspace to the hypervisor, and
    inform the hypervisor to de-assign a MMIO device from a User VM.

These new APIs will be used by user space code vm_assign_mmiodev and
vm_deassign_mmiodev in
https://github.com/projectacrn/acrn-hypervisor/blob/master/devicemodel/core/vmmapi.c

Signed-off-by: Shuo Liu 
Signed-off-by: Fei Li 
Link: https://lore.kernel.org/r/20210923084128.18902-2-fei1.li@intel.com
Signed-off-by: Greg Kroah-Hartman

nitro_enclaves: Add fixes for checkpatch match open parenthesis reports

2021-09-14T09:11:20+00:00

Update the codebase formatting to fix the reports from the checkpatch
script, to match the open parenthesis.

Reviewed-by: George-Aurelian Popescu 
Signed-off-by: Andra Paraschiv 
Link: https://lore.kernel.org/r/20210827154930.40608-6-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman

nitro_enclaves: Update copyright statement to include 2021

2021-09-14T09:11:20+00:00

Update the copyright statement to include 2021, as a change has been
made over this year.

Check commit d874742f6a73 ("nitro_enclaves: Set Bus Master for the NE
PCI device") for the codebase update from this file (ne_pci_dev.c).

Reviewed-by: George-Aurelian Popescu 
Signed-off-by: Andra Paraschiv 
Link: https://lore.kernel.org/r/20210827154930.40608-5-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman

nitro_enclaves: Add fix for the kernel-doc report

2021-09-14T09:11:20+00:00

Fix the reported issue from the kernel-doc script, to have a comment per
identifier.

Reviewed-by: George-Aurelian Popescu 
Signed-off-by: Andra Paraschiv 
Link: https://lore.kernel.org/r/20210827154930.40608-4-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman

nitro_enclaves: Enable Arm64 support

2021-09-14T09:11:19+00:00

Update the kernel config to enable the Nitro Enclaves kernel driver for
Arm64 support.

Reviewed-by: George-Aurelian Popescu 
Acked-by: Stefano Garzarella 
Signed-off-by: Andra Paraschiv 
Link: https://lore.kernel.org/r/20210827154930.40608-2-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman

virt: acrn: Do hcall_destroy_vm() before resource release

2021-07-27T14:48:45+00:00

The ACRN hypervisor has scenarios which could run a real-time guest VM.
The real-time guest VM occupies dedicated CPU cores, be assigned with
dedicated PCI devices. It can run without the Service VM after boot up.
hcall_destroy_vm() returns failure when a real-time guest VM refuses.
The clearing of flag ACRN_VM_FLAG_DESTROYED causes some kernel resource
double-freed in a later acrn_vm_destroy().

Do hcall_destroy_vm() before resource release to drop this chance to
destroy the VM if hypercall fails.

Fixes: 9c5137aedd11 ("virt: acrn: Introduce VM management interfaces")
Cc: stable 
Signed-off-by: Shuo Liu 
Signed-off-by: Fei Li 
Link: https://lore.kernel.org/r/20210722062736.15050-1-fei1.li@intel.com
Signed-off-by: Greg Kroah-Hartman

nitro_enclaves: Set Bus Master for the NE PCI device

2021-06-24T13:48:27+00:00

Enable Bus Master for the NE PCI device, according to the PCI spec
for submitting memory or I/O requests:

 Master Enable – Controls the ability of a PCI Express
  Endpoint to issue Memory and I/O Read/Write Requests, and
  the ability of a Root or Switch Port to forward Memory and
  I/O Read/Write Requests in the Upstream direction

Cc: Andra Paraschiv 
Cc: Alexandru Vasile 
Cc: Alexandru Ciobotaru 
Reviewed-by: Andra Paraschiv 
Signed-off-by: Longpeng(Mike) 
Link: https://lore.kernel.org/r/20210621004046.1419-1-longpeng2@huawei.com
Signed-off-by: Greg Kroah-Hartman

nitro_enclaves: Fix stale file descriptors on failed usercopy

2021-04-29T17:06:49+00:00

A failing usercopy of the slot uid will lead to a stale entry in the
file descriptor table as put_unused_fd() won't release it. This enables
userland to refer to a dangling 'file' object through that still valid
file descriptor, leading to all kinds of use-after-free exploitation
scenarios.

Exchanging put_unused_fd() for close_fd(), ksys_close() or alike won't
solve the underlying issue, as the file descriptor might have been
replaced in the meantime, e.g. via userland calling close() on it
(leading to a NULL pointer dereference in the error handling code as
'fget(enclave_fd)' will return a NULL pointer) or by dup2()'ing a
completely different file object to that very file descriptor, leading
to the same situation: a dangling file descriptor pointing to a freed
object -- just in this case to a file object of user's choosing.

Generally speaking, after the call to fd_install() the file descriptor
is live and userland is free to do whatever with it. We cannot rely on
it to still refer to our enclave object afterwards. In fact, by abusing
userfaultfd() userland can hit the condition without any racing and
abuse the error handling in the nitro code as it pleases.

To fix the above issues, defer the call to fd_install() until all
possible errors are handled. In this case it's just the usercopy, so do
it directly in ne_create_vm_ioctl() itself.

Signed-off-by: Mathias Krause 
Signed-off-by: Andra Paraschiv 
Cc: stable 
Link: https://lore.kernel.org/r/20210429165941.27020-2-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman