diff mbox series

dax: enable dax fault handler to report VM_FAULT_HWPOISON

Message ID 20230406175556.452442-1-jane.chu@oracle.com
State New
Headers
Series dax: enable dax fault handler to report VM_FAULT_HWPOISON |

Commit Message

Jane Chu April 6, 2023, 5:55 p.m. UTC 
  When dax fault handler fails to provision the fault page due to
hwpoison, it returns VM_FAULT_SIGBUS which lead to a sigbus delivered
to userspace with .si_code BUS_ADRERR.  Channel dax backend driver's
detection on hwpoison to the filesystem to provide the precise reason
for the fault.

Signed-off-by: Jane Chu <jane.chu@oracle.com>
---
 drivers/nvdimm/pmem.c |  2 +-
 fs/dax.c              | 14 ++++++++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)

Comments

Matthew Wilcox April 6, 2023, 7:32 p.m. UTC | #1 
On Thu, Apr 06, 2023 at 11:55:56AM -0600, Jane Chu wrote:
>  static vm_fault_t dax_fault_return(int error)
>  {
>  	if (error == 0)
>  		return VM_FAULT_NOPAGE;
> -	return vmf_error(error);
> +	else if (error == -ENOMEM)
> +		return VM_FAULT_OOM;
> +	else if (error == -EHWPOISON)
> +		return VM_FAULT_HWPOISON;
> +	return VM_FAULT_SIGBUS;
>  }

Why would we want to handle it here instead of changing vmf_error()?
Jane Chu April 6, 2023, 8:38 p.m. UTC | #2 
On 4/6/2023 12:32 PM, Matthew Wilcox wrote:
> On Thu, Apr 06, 2023 at 11:55:56AM -0600, Jane Chu wrote:
>>   static vm_fault_t dax_fault_return(int error)
>>   {
>>   	if (error == 0)
>>   		return VM_FAULT_NOPAGE;
>> -	return vmf_error(error);
>> +	else if (error == -ENOMEM)
>> +		return VM_FAULT_OOM;
>> +	else if (error == -EHWPOISON)
>> +		return VM_FAULT_HWPOISON;
>> +	return VM_FAULT_SIGBUS;
>>   }
> 
> Why would we want to handle it here instead of changing vmf_error()?

I think it's related to the comment about the the corrupted range of
a hwpoison caused fault - something no need to worry about now.

I will move the change to vmf_error() in a respin.

Thanks!
-jane
diff mbox series

Patch

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index ceea55f621cc..46e094e56159 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -260,7 +260,7 @@  __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 		long actual_nr;
 
 		if (mode != DAX_RECOVERY_WRITE)
-			return -EIO;
+			return -EHWPOISON;
 
 		/*
 		 * Set the recovery stride is set to kernel page size because
diff --git a/fs/dax.c b/fs/dax.c
index 3e457a16c7d1..3f22686abc88 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1456,7 +1456,7 @@  static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
 				DAX_ACCESS, &kaddr, NULL);
-		if (map_len == -EIO && iov_iter_rw(iter) == WRITE) {
+		if (map_len == -EHWPOISON && iov_iter_rw(iter) == WRITE) {
 			map_len = dax_direct_access(dax_dev, pgoff,
 					PHYS_PFN(size), DAX_RECOVERY_WRITE,
 					&kaddr, NULL);
@@ -1550,11 +1550,21 @@  dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
+/*
+ * Concerning hwpoison triggered page fault: dax is THP, a pmd
+ * level fault handler will fallback (VM_FAULT_FALLBACK) before
+ * give up, hence return VM_FAULT_HWPOISON which implies
+ * corrupted range is PAGE_SIZE.
+ */
 static vm_fault_t dax_fault_return(int error)
 {
 	if (error == 0)
 		return VM_FAULT_NOPAGE;
-	return vmf_error(error);
+	else if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	else if (error == -EHWPOISON)
+		return VM_FAULT_HWPOISON;
+	return VM_FAULT_SIGBUS;
 }
 
 /*