3:22 a.m.
For VM_PFNMAP and VM_MIXEDMAP we use vm_ops->pfn_mkwrite instead of
vm_ops->page_mkwrite to notify abort write access. This means we want
vma->vm_page_prot to be write-protected if the VMA provides this vm_ops.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Yigal Korman <yigal(a)plexistor.com>
Cc: Boaz Harrosh <boaz(a)plexistor.com>
Cc: Matthew Wilcox <matthew.r.wilcox(a)intel.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Dave Chinner <david(a)fromorbit.com>
---
mm/mmap.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index df6d5f07035b..3f78bceefe5a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1498,7 +1498,8 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
return 0;
/* The backer wishes to know when pages are first written to? */
- if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+ if (vma->vm_ops &&
+ (vma->vm_ops->page_mkwrite || vma->vm_ops->pfn_mkwrite))
return 1;
/* The open routine did something to the protections that pgprot_modify
--
2.5.0
3:54 a.m.
On 09/01/2015 01:22 PM, Kirill A. Shutemov wrote:
For VM_PFNMAP and VM_MIXEDMAP we use vm_ops->pfn_mkwrite instead
of
vm_ops->page_mkwrite to notify abort write access. This means we want
vma->vm_page_prot to be write-protected if the VMA provides this vm_ops.
Hi Kirill
I will test with this right away and ACK on this.
Hmm so are you saying we might be missing some buffer modifications right now.
What would be a theoretical scenario that will cause these missed events?
I would like to put a test in our test rigs that should fail today and this
patch fixes.
[In our system every modified pmem block is also RDMAed to a remote
pmem for HA, a missed modification will make the two copies unsynced]
Thanks for catching this
Boaz
Signed-off-by: Kirill A. Shutemov
<kirill.shutemov(a)linux.intel.com>
Cc: Yigal Korman <yigal(a)plexistor.com>
Cc: Boaz Harrosh <boaz(a)plexistor.com>
Cc: Matthew Wilcox <matthew.r.wilcox(a)intel.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Dave Chinner <david(a)fromorbit.com>
---
mm/mmap.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index df6d5f07035b..3f78bceefe5a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1498,7 +1498,8 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
return 0;
/* The backer wishes to know when pages are first written to? */
- if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+ if (vma->vm_ops &&
+ (vma->vm_ops->page_mkwrite || vma->vm_ops->pfn_mkwrite))
return 1;
/* The open routine did something to the protections that pgprot_modify
4:10 a.m.
On Tue, Sep 01, 2015 at 01:54:26PM +0300, Boaz Harrosh wrote:
On 09/01/2015 01:22 PM, Kirill A. Shutemov wrote:
> For VM_PFNMAP and VM_MIXEDMAP we use vm_ops->pfn_mkwrite instead of
> vm_ops->page_mkwrite to notify abort write access. This means we want
> vma->vm_page_prot to be write-protected if the VMA provides this vm_ops.
>
Hi Kirill
I will test with this right away and ACK on this.
Hmm so are you saying we might be missing some buffer modifications right now.
What would be a theoretical scenario that will cause these missed events?
On writable mapping with vm_ops->pfn_mkwrite, but without
vm_ops->page_mkwrite: read fault followed by write access to the pfn.
Writable pte will be set up on read fault and write fault will not be
generated.
I found it examining Dave's complain on generic/080:
http://lkml.kernel.org/g/20150831233803.GO3902@dastard
Although I don't think it's the reason.
I would like to put a test in our test rigs that should fail today
and this
patch fixes.
[In our system every modified pmem block is also RDMAed to a remote
pmem for HA, a missed modification will make the two copies unsynced]
It shouldn't be a problem for ext2/ext4 as they provide both pfn_mkwrite
and page_mkwrite.
--
Kirill A. Shutemov
4:21 a.m.
On 09/01/2015 02:10 PM, Kirill A. Shutemov wrote:
On Tue, Sep 01, 2015 at 01:54:26PM +0300, Boaz Harrosh wrote:
> On 09/01/2015 01:22 PM, Kirill A. Shutemov wrote:
>> For VM_PFNMAP and VM_MIXEDMAP we use vm_ops->pfn_mkwrite instead of
>> vm_ops->page_mkwrite to notify abort write access. This means we want
>> vma->vm_page_prot to be write-protected if the VMA provides this vm_ops.
>>
>
> Hi Kirill
>
> I will test with this right away and ACK on this.
>
> Hmm so are you saying we might be missing some buffer modifications right now.
>
> What would be a theoretical scenario that will cause these missed events?
On writable mapping with vm_ops->pfn_mkwrite, but without
vm_ops->page_mkwrite: read fault followed by write access to the pfn.
Writable pte will be set up on read fault and write fault will not be
generated.
I found it examining Dave's complain on generic/080:
http://lkml.kernel.org/g/20150831233803.GO3902@dastard
Although I don't think it's the reason.
> I would like to put a test in our test rigs that should fail today and this
> patch fixes.
>
> [In our system every modified pmem block is also RDMAed to a remote
> pmem for HA, a missed modification will make the two copies unsynced]
It shouldn't be a problem for ext2/ext4 as they provide both pfn_mkwrite
and page_mkwrite.
Ha right we have both as well, and so should xfs I think (because of the
zero pages thing, in fact any dax.c user should).
Thanks so this verifies why we could not see any such breakage.
ACK-by: Boaz Harrosh <boaz(a)plexistor.com>
2492
days inactive
2492
days old
3 comments
3 participants
participants (3)
-
Boaz Harrosh -
Kirill A. Shutemov -
Kirill A. Shutemov