diff options
| author | Dave Jiang <dave.jiang@intel.com> | 2017-03-10 13:24:22 -0700 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2017-03-30 09:41:27 +0200 |
| commit | eae72468c45d827484a2c0980a519f5220b1985c (patch) | |
| tree | 5b964ad7baf29975a8c6e4094120e15d0ebffc58 | |
| parent | 81ec3dc1de0af47a4f38a276f68f55f4e7e8e621 (diff) | |
device-dax: fix pmd/pte fault fallback handling
commit 0134ed4fb9e78672ee9f7b18007114404c81e63f upstream.
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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -rw-r--r-- | drivers/dax/dax.c | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 286447a83dab..152552d2c306 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -334,6 +334,7 @@ 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; @@ -344,6 +345,9 @@ 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__, @@ -389,6 +393,7 @@ 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; @@ -405,6 +410,16 @@ 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) { |