The patch titled
Subject: drivers/virt/acrn: fix PFNMAP PTE checks in acrn_vm_ram_map()
has been added to the -mm mm-unstable branch. Its filename is
drivers-virt-acrn-fix-pfnmap-pte-checks-in-acrn_vm_ram_map.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/drivers-virt-acrn-fix-pfnmap-pte-checks-in-acrn_vm_ram_map.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: David Hildenbrand <david@xxxxxxxxxx>
Subject: drivers/virt/acrn: fix PFNMAP PTE checks in acrn_vm_ram_map()
Date: Wed, 10 Apr 2024 17:55:25 +0200
Patch series "mm: follow_pte() improvements and acrn follow_pte() fixes".
Patch #1 fixes a bunch of issues I spotted in the acrn driver. It
compiles, that's all I know. I'll appreciate some review and testing from
acrn folks.
Patch #2+#3 improve follow_pte(), passing a VMA instead of the MM, adding
more sanity checks, and improving the documentation. Gave it a quick test
on x86-64 using VM_PAT that ends up using follow_pte().
This patch (of 3):
We currently miss handling various cases, resulting in a dangerous
follow_pte() (previously follow_pfn()) usage.
(1) We're not checking PTE write permissions.
Maybe we should simply always require pte_write() like we do for
pin_user_pages_fast(FOLL_WRITE)? Hard to tell, so let's check for
ACRN_MEM_ACCESS_WRITE for now.
(2) We're not rejecting refcounted pages.
As we are not using MMU notifiers, messing with refcounted pages is
dangerous and can result in use-after-free. Let's make sure to reject them.
(3) We are only looking at the first PTE of a bigger range.
We only lookup a single PTE, but memmap->len may span a larger area.
Let's loop over all involved PTEs and make sure the PFN range is
actually contiguous. Reject everything else: it couldn't have worked
either way, and rather made use access PFNs we shouldn't be accessing.
Link: https://lkml.kernel.org/r/20240410155527.474777-1-david@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20240410155527.474777-2-david@xxxxxxxxxx
Fixes: 8a6e85f75a83 ("virt: acrn: obtain pa from VMA with PFNMAP flag")
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Fei Li <fei1.li@xxxxxxxxx>
Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Yonghua Huang <yonghua.huang@xxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/virt/acrn/mm.c | 63 +++++++++++++++++++++++++++++----------
1 file changed, 47 insertions(+), 16 deletions(-)
--- a/drivers/virt/acrn/mm.c~drivers-virt-acrn-fix-pfnmap-pte-checks-in-acrn_vm_ram_map
+++ a/drivers/virt/acrn/mm.c
@@ -156,23 +156,29 @@ int acrn_vm_memseg_unmap(struct acrn_vm
int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap)
{
struct vm_memory_region_batch *regions_info;
- int nr_pages, i = 0, order, nr_regions = 0;
+ int nr_pages, i, order, nr_regions = 0;
struct vm_memory_mapping *region_mapping;
struct vm_memory_region_op *vm_region;
struct page **pages = NULL, *page;
void *remap_vaddr;
int ret, pinned;
u64 user_vm_pa;
- unsigned long pfn;
struct vm_area_struct *vma;
if (!vm || !memmap)
return -EINVAL;
+ /* Get the page number of the map region */
+ nr_pages = memmap->len >> PAGE_SHIFT;
+ if (!nr_pages)
+ return -EINVAL;
+
mmap_read_lock(current->mm);
vma = vma_lookup(current->mm, memmap->vma_base);
if (vma && ((vma->vm_flags & VM_PFNMAP) != 0)) {
+ unsigned long start_pfn, cur_pfn;
spinlock_t *ptl;
+ bool writable;
pte_t *ptep;
if ((memmap->vma_base + memmap->len) > vma->vm_end) {
@@ -180,25 +186,53 @@ int acrn_vm_ram_map(struct acrn_vm *vm,
return -EINVAL;
}
- ret = follow_pte(vma->vm_mm, memmap->vma_base, &ptep, &ptl);
- if (ret < 0) {
- mmap_read_unlock(current->mm);
+ for (i = 0; i < nr_pages; i++) {
+ ret = follow_pte(vma->vm_mm,
+ memmap->vma_base + i * PAGE_SIZE,
+ &ptep, &ptl);
+ if (ret)
+ break;
+
+ cur_pfn = pte_pfn(ptep_get(ptep));
+ if (i == 0)
+ start_pfn = cur_pfn;
+ writable = !!pte_write(ptep_get(ptep));
+ pte_unmap_unlock(ptep, ptl);
+
+ /* Disallow write access if the PTE is not writable. */
+ if (!writable &&
+ (memmap->attr & ACRN_MEM_ACCESS_WRITE)) {
+ ret = -EFAULT;
+ break;
+ }
+
+ /* Disallow refcounted pages. */
+ if (pfn_valid(cur_pfn) &&
+ !PageReserved(pfn_to_page(cur_pfn))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ /* Disallow non-contiguous ranges. */
+ if (cur_pfn != start_pfn + i) {
+ ret = -EINVAL;
+ break;
+ }
+ }
+ mmap_read_unlock(current->mm);
+
+ if (ret) {
dev_dbg(acrn_dev.this_device,
"Failed to lookup PFN at VMA:%pK.\n", (void *)memmap->vma_base);
return ret;
}
- pfn = pte_pfn(ptep_get(ptep));
- pte_unmap_unlock(ptep, ptl);
- mmap_read_unlock(current->mm);
return acrn_mm_region_add(vm, memmap->user_vm_pa,
- PFN_PHYS(pfn), memmap->len,
+ PFN_PHYS(start_pfn), memmap->len,
ACRN_MEM_TYPE_WB, memmap->attr);
}
mmap_read_unlock(current->mm);
- /* Get the page number of the map region */
- nr_pages = memmap->len >> PAGE_SHIFT;
pages = vzalloc(array_size(nr_pages, sizeof(*pages)));
if (!pages)
return -ENOMEM;
@@ -242,12 +276,11 @@ int acrn_vm_ram_map(struct acrn_vm *vm,
mutex_unlock(&vm->regions_mapping_lock);
/* Calculate count of vm_memory_region_op */
- while (i < nr_pages) {
+ for (i = 0; i < nr_pages; i += 1 << order) {
page = pages[i];
VM_BUG_ON_PAGE(PageTail(page), page);
order = compound_order(page);
nr_regions++;
- i += 1 << order;
}
/* Prepare the vm_memory_region_batch */
@@ -264,8 +297,7 @@ int acrn_vm_ram_map(struct acrn_vm *vm,
regions_info->vmid = vm->vmid;
regions_info->regions_gpa = virt_to_phys(vm_region);
user_vm_pa = memmap->user_vm_pa;
- i = 0;
- while (i < nr_pages) {
+ for (i = 0; i < nr_pages; i += 1 << order) {
u32 region_size;
page = pages[i];
@@ -281,7 +313,6 @@ int acrn_vm_ram_map(struct acrn_vm *vm,
vm_region++;
user_vm_pa += region_size;
- i += 1 << order;
}
/* Inform the ACRN Hypervisor to set up EPT mappings */
_
Patches currently in -mm which might be from david@xxxxxxxxxx are
mm-madvise-make-madv_populate_readwrite-handle-vm_fault_retry-properly.patch
mm-madvise-dont-perform-madvise-vma-walk-for-madv_populate_readwrite.patch
mm-userfaultfd-dont-place-zeropages-when-zeropages-are-disallowed.patch
s390-mm-re-enable-the-shared-zeropage-for-pv-and-skeys-kvm-guests.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared-fix.patch
selftests-memfd_secret-add-vmsplice-test.patch
mm-merge-folio_is_secretmem-and-folio_fast_pin_allowed-into-gup_fast_folio_allowed.patch
mm-optimize-config_per_vma_lock-member-placement-in-vm_area_struct.patch
mm-remove-prot-parameter-from-move_pte.patch
mm-gup-consistently-name-gup-fast-functions.patch
mm-treewide-rename-config_have_fast_gup-to-config_have_gup_fast.patch
mm-use-gup-fast-instead-fast-gup-in-remaining-comments.patch
drivers-virt-acrn-fix-pfnmap-pte-checks-in-acrn_vm_ram_map.patch
mm-pass-vma-instead-of-mm-to-follow_pte.patch
mm-follow_pte-improvements.patch
