summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDave Jiang <dave.jiang@intel.com>2017-03-10 13:24:22 -0700
committerDan Williams <dan.j.williams@intel.com>2017-03-10 18:15:04 -0800
commit0134ed4fb9e78672ee9f7b18007114404c81e63f (patch)
tree3a377760fb66db5f8d5d4ae13934f17ff3a0274a
parentc1ae3cfa0e89fa1a7ecc4c99031f5e9ae99d9201 (diff)
downloadlinux-stable-0134ed4fb9e78672ee9f7b18007114404c81e63f.tar.gz
linux-stable-0134ed4fb9e78672ee9f7b18007114404c81e63f.tar.bz2
linux-stable-0134ed4fb9e78672ee9f7b18007114404c81e63f.zip
device-dax: fix pmd/pte 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. 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>
-rw-r--r--drivers/dax/dax.c15
1 files changed, 15 insertions, 0 deletions
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 8d9829ff2a78..a284dc532e46 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -427,6 +427,7 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
int rc = VM_FAULT_SIGBUS;
phys_addr_t phys;
pfn_t pfn;
+ unsigned int fault_size = PAGE_SIZE;
if (check_vma(dax_dev, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
@@ -437,6 +438,9 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
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__,
@@ -464,6 +468,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
phys_addr_t phys;
pgoff_t pgoff;
pfn_t pfn;
+ unsigned int fault_size = PMD_SIZE;
if (check_vma(dax_dev, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
@@ -480,6 +485,16 @@ static int __dax_dev_pmd_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 (pmd_addr < vmf->vma->vm_start ||
+ (pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
+ return VM_FAULT_SIGBUS;
+
pgoff = linear_page_index(vmf->vma, pmd_addr);
phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
if (phys == -1) {