vfio/pci: Handle concurrent vma faults

[ Upstream commit 6a45ece4c9af473555f01f0f8b97eba56e3c7d0d ]

io_remap_pfn_range() will trigger a BUG_ON if it encounters a
populated pte within the mapping range.  This can occur because we map
the entire vma on fault and multiple faults can be blocked behind the
vma_lock.  This leads to traces like the one reported below.

We can use our vma_list to test whether a given vma is mapped to avoid
this issue.

[ 1591.733256] kernel BUG at mm/memory.c:2177!
[ 1591.739515] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[ 1591.747381] Modules linked in: vfio_iommu_type1 vfio_pci vfio_virqfd vfio pv680_mii(O)
[ 1591.760536] CPU: 2 PID: 227 Comm: lcore-worker-2 Tainted: G O 5.11.0-rc3+ #1
[ 1591.770735] Hardware name:  , BIOS HixxxxFPGA 1P B600 V121-1
[ 1591.778872] pstate: 40400009 (nZcv daif +PAN -UAO -TCO BTYPE=--)
[ 1591.786134] pc : remap_pfn_range+0x214/0x340
[ 1591.793564] lr : remap_pfn_range+0x1b8/0x340
[ 1591.799117] sp : ffff80001068bbd0
[ 1591.803476] x29: ffff80001068bbd0 x28: 0000042eff6f0000
[ 1591.810404] x27: 0000001100910000 x26: 0000001300910000
[ 1591.817457] x25: 0068000000000fd3 x24: ffffa92f1338e358
[ 1591.825144] x23: 0000001140000000 x22: 0000000000000041
[ 1591.832506] x21: 0000001300910000 x20: ffffa92f141a4000
[ 1591.839520] x19: 0000001100a00000 x18: 0000000000000000
[ 1591.846108] x17: 0000000000000000 x16: ffffa92f11844540
[ 1591.853570] x15: 0000000000000000 x14: 0000000000000000
[ 1591.860768] x13: fffffc0000000000 x12: 0000000000000880
[ 1591.868053] x11: ffff0821bf3d01d0 x10: ffff5ef2abd89000
[ 1591.875932] x9 : ffffa92f12ab0064 x8 : ffffa92f136471c0
[ 1591.883208] x7 : 0000001140910000 x6 : 0000000200000000
[ 1591.890177] x5 : 0000000000000001 x4 : 0000000000000001
[ 1591.896656] x3 : 0000000000000000 x2 : 0168044000000fd3
[ 1591.903215] x1 : ffff082126261880 x0 : fffffc2084989868
[ 1591.910234] Call trace:
[ 1591.914837]  remap_pfn_range+0x214/0x340
[ 1591.921765]  vfio_pci_mmap_fault+0xac/0x130 [vfio_pci]
[ 1591.931200]  __do_fault+0x44/0x12c
[ 1591.937031]  handle_mm_fault+0xcc8/0x1230
[ 1591.942475]  do_page_fault+0x16c/0x484
[ 1591.948635]  do_translation_fault+0xbc/0xd8
[ 1591.954171]  do_mem_abort+0x4c/0xc0
[ 1591.960316]  el0_da+0x40/0x80
[ 1591.965585]  el0_sync_handler+0x168/0x1b0
[ 1591.971608]  el0_sync+0x174/0x180
[ 1591.978312] Code: eb1b027f 540000c0 f9400022 b4fffe02 (d4210000)

Fixes: 11c4cd07ba ("vfio-pci: Fault mmaps to enable vma tracking")
Reported-by: Zeng Tao <prime.zeng@hisilicon.com>
Suggested-by: Zeng Tao <prime.zeng@hisilicon.com>
Link: https://lore.kernel.org/r/162497742783.3883260.3282953006487785034.stgit@omen
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Alex Williamson 2021-06-28 14:08:12 -06:00 committed by Greg Kroah-Hartman
parent 363d85bfae
commit 0885ea1d47

View File

@ -1614,6 +1614,7 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct vfio_pci_device *vdev = vma->vm_private_data;
struct vfio_pci_mmap_vma *mmap_vma;
vm_fault_t ret = VM_FAULT_NOPAGE;
mutex_lock(&vdev->vma_lock);
@ -1621,24 +1622,36 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
if (!__vfio_pci_memory_enabled(vdev)) {
ret = VM_FAULT_SIGBUS;
mutex_unlock(&vdev->vma_lock);
goto up_out;
}
/*
* We populate the whole vma on fault, so we need to test whether
* the vma has already been mapped, such as for concurrent faults
* to the same vma. io_remap_pfn_range() will trigger a BUG_ON if
* we ask it to fill the same range again.
*/
list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
if (mmap_vma->vma == vma)
goto up_out;
}
if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
vma->vm_end - vma->vm_start,
vma->vm_page_prot)) {
ret = VM_FAULT_SIGBUS;
zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
goto up_out;
}
if (__vfio_pci_add_vma(vdev, vma)) {
ret = VM_FAULT_OOM;
mutex_unlock(&vdev->vma_lock);
goto up_out;
zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
}
mutex_unlock(&vdev->vma_lock);
if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
vma->vm_end - vma->vm_start, vma->vm_page_prot))
ret = VM_FAULT_SIGBUS;
up_out:
up_read(&vdev->memory_lock);
mutex_unlock(&vdev->vma_lock);
return ret;
}