[PATCH] device-dax: fix pmd/pte fault fallback handling

[PATCH] device-dax: fix pmd/pte fault fallback handling

[Dave Jiang]

commit: 0134ed4fb9e7 upstream.
Backported for 4.9-stable and 4.10-stable.

Jeff Moyer reports:

    With a device dax alignment of 4KB or 2MB, I get sigbus when running
    the attached fio job file for the current kernel (4.11.0-rc1+).  If
    I specify an alignment of 1GB, it works.

    I turned on debug output, and saw that it was failing in the huge
    fault code.

     dax dax1.0: dax_open
     dax dax1.0: dax_mmap
     dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 -
     dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf60
     dax dax1.0: dax_release

    fio config for reproduce:
    [global]
    ioengine=dev-dax
    direct=0
    filename=/dev/dax0.0
    bs=2m

    [write]
    rw=write

    [read]
    stonewall
    rw=read

The driver fails to fallback when taking a fault that is larger than
the device alignment, or handling a larger fault when a smaller
mapping is already established. While we could support larger
mappings for a device with a smaller alignment, that change is
too large for the immediate fix. The simplest change is to force
fallback until the fault size matches the alignment.

Fixes: dee410792419 ("/dev/dax, core: file operations and dax-mmap")

Cc: <stable@vger.kernel.org>
Reported-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c |   15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index ed758b7..20ab6bf 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -427,6 +427,7 @@ static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 	int rc = VM_FAULT_SIGBUS;
 	phys_addr_t phys;
 	pfn_t pfn;
+	unsigned int fault_size = PAGE_SIZE;
 
 	if (check_vma(dax_dev, vma, __func__))
 		return VM_FAULT_SIGBUS;
@@ -437,6 +438,9 @@ static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		return VM_FAULT_SIGBUS;
 	}
 
+	if (fault_size != dax_region->align)
+		return VM_FAULT_SIGBUS;
+
 	phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
 	if (phys == -1) {
 		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
@@ -482,6 +486,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 	phys_addr_t phys;
 	pgoff_t pgoff;
 	pfn_t pfn;
+	unsigned int fault_size = PMD_SIZE;
 
 	if (check_vma(dax_dev, vma, __func__))
 		return VM_FAULT_SIGBUS;
@@ -498,6 +503,16 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 		return VM_FAULT_SIGBUS;
 	}
 
+	if (fault_size < dax_region->align)
+		return VM_FAULT_SIGBUS;
+	else if (fault_size > dax_region->align)
+		return VM_FAULT_FALLBACK;
+
+	/* if we are outside of the VMA */
+	if (pmd_addr < vma->vm_start ||
+			(pmd_addr + PMD_SIZE) > vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
 	pgoff = linear_page_index(vma, pmd_addr);
 	phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
 	if (phys == -1) {

Re: [PATCH] device-dax: fix pmd/pte fault fallback handling

[Dan Williams]

On Mon, Mar 27, 2017 at 10:54 AM, Dave Jiang <dave.jiang@intel.com> wrote:
> commit: 0134ed4fb9e7 upstream.

I would include the full sha just like other stable commits.

> Backported for 4.9-stable and 4.10-stable.

Next time I would put this info in the subject, something like:

"[PATCH -stable 4.9, 4.10] device-dax: fix pmd/pte fault fallback handling"

Other than that this looks good and passes my testing, so this backport:

Acked-by: Dan Williams <dan.j.williams@intel.com>

Re: [PATCH] device-dax: fix pmd/pte fault fallback handling

[Greg KH]

On Mon, Mar 27, 2017 at 10:54:01AM -0700, Dave Jiang wrote:
> commit: 0134ed4fb9e7 upstream.
> Backported for 4.9-stable and 4.10-stable.

Thanks for this, now queued up.

greg k-h