[PATCH v3 2/2] mm, drm/ttm: Fix vm page protection handling

From: Thomas HellstrÃm (VMware)
Date: Fri Dec 06 2019 - 03:24:51 EST


From: Thomas Hellstrom <thellstrom@xxxxxxxxxx>

TTM graphics buffer objects may, transparently to user-space, move
between IO and system memory. When that happens, all PTEs pointing to the
old location are zapped before the move and then faulted in again if
needed. When that happens, the page protection caching mode- and
encryption bits may change and be different from those of
struct vm_area_struct::vm_page_prot.

We were using an ugly hack to set the page protection correctly.
Fix that and instead export and use vmf_insert_mixed_prot() or use
vmf_insert_pfn_prot().
Also get the default page protection from
struct vm_area_struct::vm_page_prot rather than using vm_get_page_prot().
This way we catch modifications done by the vm system for drivers that
want write-notification.

Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Cc: "JÃrÃme Glisse" <jglisse@xxxxxxxxxx>
Cc: "Christian KÃnig" <christian.koenig@xxxxxxx>
Signed-off-by: Thomas Hellstrom <thellstrom@xxxxxxxxxx>
Reviewed-by: Christian KÃnig <christian.koenig@xxxxxxx>
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 28 +++++++++++++++++++++-------
mm/memory.c | 1 +
2 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index e6495ca2630b..35d0a0e7aacc 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -173,7 +173,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
pgoff_t num_prefault)
{
struct vm_area_struct *vma = vmf->vma;
- struct vm_area_struct cvma = *vma;
struct ttm_buffer_object *bo = vma->vm_private_data;
struct ttm_bo_device *bdev = bo->bdev;
unsigned long page_offset;
@@ -244,7 +243,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
goto out_io_unlock;
}

- cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, prot);
+ prot = ttm_io_prot(bo->mem.placement, prot);
if (!bo->mem.bus.is_iomem) {
struct ttm_operation_ctx ctx = {
.interruptible = false,
@@ -260,7 +259,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
}
} else {
/* Iomem should not be marked encrypted */
- cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot);
+ prot = pgprot_decrypted(prot);
}

/*
@@ -283,11 +282,26 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
pfn = page_to_pfn(page);
}

+ /*
+ * Note that the value of @prot at this point may differ from
+ * the value of @vma->vm_page_prot in the caching- and
+ * encryption bits. This is because the exact location of the
+ * data may not be known at mmap() time and may also change
+ * at arbitrary times while the data is mmap'ed.
+ * This is ok as long as @vma->vm_page_prot is not used by
+ * the core vm to set caching- and encryption bits.
+ * This is ensured by core vm using pte_modify() to modify
+ * page table entry protection bits (that function preserves
+ * old caching- and encryption bits), and the @fault
+ * callback being the only function that creates new
+ * page table entries.
+ */
if (vma->vm_flags & VM_MIXEDMAP)
- ret = vmf_insert_mixed(&cvma, address,
- __pfn_to_pfn_t(pfn, PFN_DEV));
+ ret = vmf_insert_mixed_prot(vma, address,
+ __pfn_to_pfn_t(pfn, PFN_DEV),
+ prot);
else
- ret = vmf_insert_pfn(&cvma, address, pfn);
+ ret = vmf_insert_pfn_prot(vma, address, pfn, prot);

/* Never error on prefaulted PTEs */
if (unlikely((ret & VM_FAULT_ERROR))) {
@@ -319,7 +333,7 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
if (ret)
return ret;

- prot = vm_get_page_prot(vma->vm_flags);
+ prot = vma->vm_page_prot;
ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
return ret;
diff --git a/mm/memory.c b/mm/memory.c
index b9e7f1d56b1c..4c26c27afb0a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1769,6 +1769,7 @@ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
{
return __vm_insert_mixed(vma, addr, pfn, pgprot, false);
}
+EXPORT_SYMBOL(vmf_insert_mixed_prot);

vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn)
--
2.21.0