On 08/02/2018 16:00, Matthew Wilcox wrote:
> On Thu, Feb 08, 2018 at 03:35:58PM +0100, Laurent Dufour wrote:
>> I reviewed that part of code, and I think I could now change the way
>> pte_unmap_safe() is checking for the pte's value. Since we now have all the
>> needed details in the vm_fault structure, I will pass it to
>> pte_unamp_same() and deal with the VMA checks when locking for the pte as
>> it is done in the other part of the page fault handler by calling
>> pte_spinlock().
>
> This does indeed look much better! Thank you!
>
>> This means that this patch will be dropped, and pte_unmap_same() will become :
>>
>> static inline int pte_unmap_same(struct vm_fault *vmf, int *same)
>> {
>> int ret = 0;
>>
>> *same = 1;
>> #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
>> if (sizeof(pte_t) > sizeof(unsigned long)) {
>> if (pte_spinlock(vmf)) {
>> *same = pte_same(*vmf->pte, vmf->orig_pte);
>> spin_unlock(vmf->ptl);
>> }
>> else
>> ret = VM_FAULT_RETRY;
>> }
>> #endif
>> pte_unmap(vmf->pte);
>> return ret;
>> }
>
> I'm not a huge fan of auxiliary return values. Perhaps we could do this
> instead:
>
> ret = pte_unmap_same(vmf);
> if (ret != VM_FAULT_NOTSAME) {
> if (page)
> put_page(page);
> goto out;
> }
> ret = 0;
>
> (we have a lot of unused bits in VM_FAULT_, so adding a new one shouldn't
> be a big deal)
I do agree, using an auxiliary return value is not a good idea.
What about the following changes based on your suggestion ?
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7de4323b9e89..0cd31a37bb3d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1212,6 +1212,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
#define VM_FAULT_NEEDDSYNC 0x2000 /* ->fault did not modify page tables
* and needs fsync() to complete (for
* synchronous page faults in DAX) */
+#define VM_FAULT_PTNOTSAME 0x4000 /* Page table entries have changed */
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
diff --git a/mm/memory.c b/mm/memory.c
index b7da99c74fef..c9b419f8e4c5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2433,21 +2433,30 @@ static inline bool pte_map_lock(struct vm_fault *vmf)
* parts, do_swap_page must check under lock before unmapping the pte and
* proceeding (but do_wp_page is only called after already making such a check;
* and do_anonymous_page can safely check later on).
+ *
+ * pte_unmap_same() returns:
+ * 0 if the PTE are the same
+ * VM_FAULT_PTNOTSAME if the PTE are different
+ * VM_FAULT_RETRY if the VMA has changed in our back during
+ * a speculative page fault handling.
*/
-static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
- pte_t *page_table, pte_t orig_pte)
+static inline int pte_unmap_same(struct vm_fault *vmf)
{
- int same = 1;
+ int ret = 0;
+
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
if (sizeof(pte_t) > sizeof(unsigned long)) {
- spinlock_t *ptl = pte_lockptr(mm, pmd);
- spin_lock(ptl);
- same = pte_same(*page_table, orig_pte);
- spin_unlock(ptl);
+ if (pte_spinlock(vmf)) {
+ if (!pte_same(*vmf->pte, vmf->orig_pte))
+ ret = VM_FAULT_PTNOTSAME;
+ spin_unlock(vmf->ptl);
+ }
+ else
+ ret = VM_FAULT_RETRY;
}
#endif
- pte_unmap(page_table);
- return same;
+ pte_unmap(vmf->pte);
+ return ret;
}
static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
@@ -3037,7 +3046,7 @@ int do_swap_page(struct vm_fault *vmf)
pte_t pte;
int locked;
int exclusive = 0;
- int ret = 0;
+ int ret;
bool vma_readahead = swap_use_vma_readahead();
if (vma_readahead) {
@@ -3045,9 +3054,16 @@ int do_swap_page(struct vm_fault *vmf)
swapcache = page;
}
- if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) {
+ ret = pte_unmap_same(vmf);
+ if (ret) {
if (page)
put_page(page);
+ /*
+ * In the case the PTE are different, meaning that the
+ * page has already been processed by another CPU, we return 0.
+ */
+ if (ret == VM_FAULT_PTNOTSAME)
+ ret = 0;
goto out;
}
Thanks,
Laurent.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
