All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v2] dax: fix device-dax fault handling so that it would fallback
@ 2017-03-10 18:00 Dave Jiang
  2017-03-10 18:21 ` Dan Williams
  0 siblings, 1 reply; 3+ messages in thread
From: Dave Jiang @ 2017-03-10 18:00 UTC (permalink / raw)
  To: dan.j.williams; +Cc: linux-nvdimm

Jeff Moyer reports that:
"
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.

[ 4614.138357] dax dax1.0: dax_open
[ 4614.154838] dax dax1.0: dax_mmap
[ 4614.171898] dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 - 0x7f0ce0800000)
[ 4614.211720] dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf600) failed
[ 4614.568911] 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
"

It looks like the code does not fallback at all when handling faults. Adding
additional boundary checks and code that determines when to fallback.

Reported-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/dax/dax.c |   27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 174690a..80c6db279 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: pgoff_to_phys(%#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) {
@@ -503,6 +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;
@@ -519,6 +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) {

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

^ permalink raw reply related	[flat|nested] 3+ messages in thread
* Re: [PATCH v2] dax: fix device-dax fault handling so that it would fallback
  2017-03-10 18:00 [PATCH v2] dax: fix device-dax fault handling so that it would fallback Dave Jiang
@ 2017-03-10 18:21 ` Dan Williams
  2017-03-10 18:25   ` Dave Jiang
  0 siblings, 1 reply; 3+ messages in thread
From: Dan Williams @ 2017-03-10 18:21 UTC (permalink / raw)
  To: Dave Jiang; +Cc: linux-nvdimm

On Fri, Mar 10, 2017 at 10:00 AM, Dave Jiang <dave.jiang@intel.com> wrote:
> Jeff Moyer reports that:
> "
> 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.
>
> [ 4614.138357] dax dax1.0: dax_open
> [ 4614.154838] dax dax1.0: dax_mmap
> [ 4614.171898] dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 - 0x7f0ce0800000)
> [ 4614.211720] dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf600) failed
> [ 4614.568911] 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
> "
>
> It looks like the code does not fallback at all when handling faults. Adding
> additional boundary checks and code that determines when to fallback.
>
> Reported-by: Jeff Moyer <jmoyer@redhat.com>
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> ---
>  drivers/dax/dax.c |   27 +++++++++++++++++++++++++++
>  1 file changed, 27 insertions(+)
>
> diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
> index 174690a..80c6db279 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: pgoff_to_phys(%#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) {
> @@ -503,6 +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;
> @@ -519,6 +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) {
>

This looks good to me.

Let's split the __dax_dev_pud_fault() changes to its own patch. That
way we can mark the pte+pmd changes in a commit tagged for -stable and
the pud patch can remain for just 4.11-rc.
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

^ permalink raw reply	[flat|nested] 3+ messages in thread
* Re: [PATCH v2] dax: fix device-dax fault handling so that it would fallback
  2017-03-10 18:21 ` Dan Williams
@ 2017-03-10 18:25   ` Dave Jiang
  0 siblings, 0 replies; 3+ messages in thread
From: Dave Jiang @ 2017-03-10 18:25 UTC (permalink / raw)
  To: Dan Williams; +Cc: linux-nvdimm



On 03/10/2017 11:21 AM, Dan Williams wrote:
> On Fri, Mar 10, 2017 at 10:00 AM, Dave Jiang <dave.jiang@intel.com> wrote:
>> Jeff Moyer reports that:
>> "
>> 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.
>>
>> [ 4614.138357] dax dax1.0: dax_open
>> [ 4614.154838] dax dax1.0: dax_mmap
>> [ 4614.171898] dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 - 0x7f0ce0800000)
>> [ 4614.211720] dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf600) failed
>> [ 4614.568911] 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
>> "
>>
>> It looks like the code does not fallback at all when handling faults. Adding
>> additional boundary checks and code that determines when to fallback.
>>
>> Reported-by: Jeff Moyer <jmoyer@redhat.com>
>> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
>> ---
>>  drivers/dax/dax.c |   27 +++++++++++++++++++++++++++
>>  1 file changed, 27 insertions(+)
>>
>> diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
>> index 174690a..80c6db279 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: pgoff_to_phys(%#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) {
>> @@ -503,6 +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;
>> @@ -519,6 +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) {
>>
> 
> This looks good to me.
> 
> Let's split the __dax_dev_pud_fault() changes to its own patch. That
> way we can mark the pte+pmd changes in a commit tagged for -stable and
> the pud patch can remain for just 4.11-rc.
> 

Ok, I shall split them into two patches. Although because of the 1G
changes in 4.11-rc, there's some work for the stable backport.
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

^ permalink raw reply	[flat|nested] 3+ messages in thread
end of thread, other threads:[~2017-03-10 18:25 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-03-10 18:00 [PATCH v2] dax: fix device-dax fault handling so that it would fallback Dave Jiang
2017-03-10 18:21 ` Dan Williams
2017-03-10 18:25   ` Dave Jiang

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.