diff options
author | Dave Jiang <dave.jiang@intel.com> | 2017-03-10 23:24:27 +0300 |
---|---|---|
committer | Dan Williams <dan.j.williams@intel.com> | 2017-03-11 06:55:53 +0300 |
commit | 70b085b06c4560a69e95607f77bb4c2b2e41943c (patch) | |
tree | e667d70ececd084f7a365600c596e2d81ec4bcaf /drivers/dax | |
parent | 0134ed4fb9e78672ee9f7b18007114404c81e63f (diff) | |
download | linux-70b085b06c4560a69e95607f77bb4c2b2e41943c.tar.xz |
device-dax: fix pud fault fallback handling
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.
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>
Diffstat (limited to 'drivers/dax')
-rw-r--r-- | drivers/dax/dax.c | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index a284dc532e46..523fecec7bda 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -518,6 +518,8 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) phys_addr_t phys; pgoff_t pgoff; pfn_t pfn; + unsigned int fault_size = PUD_SIZE; + if (check_vma(dax_dev, vmf->vma, __func__)) return VM_FAULT_SIGBUS; @@ -534,6 +536,16 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) 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 (pud_addr < vmf->vma->vm_start || + (pud_addr + PUD_SIZE) > vmf->vma->vm_end) + return VM_FAULT_SIGBUS; + pgoff = linear_page_index(vmf->vma, pud_addr); phys = pgoff_to_phys(dax_dev, pgoff, PUD_SIZE); if (phys == -1) { |