When MPOL_MF_STRICT was specified and an existing page was already on a node that does not follow the policy, mbind() should return -EIO. But commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") broke the rule.
And, commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support thp migration") didn't return the correct value for THP mbind() too.
If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an existing page was already on a node that does not follow the policy. And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified.
Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind...
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de --- mm/mempolicy.c | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index abe7a67..401c817 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -447,6 +447,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); }
+/* + * The queue_pages_pmd() may have three kind of return value. + * 1 - pages are placed on he right node or queued successfully. + * 0 - THP get split. + * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing + * page was already on a node that does not follow the policy. + */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -456,7 +463,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long flags;
if (unlikely(is_pmd_migration_entry(*pmd))) { - ret = 1; + ret = -EIO; goto unlock; } page = pmd_page(*pmd); @@ -473,8 +480,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(walk->vma)) { + ret = -EIO; + goto unlock; + } + migrate_page_add(page, qp->pagelist, flags); + } else + ret = -EIO; unlock: spin_unlock(ptl); out: @@ -499,8 +513,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret) + if (ret > 0) return 0; + else if (ret < 0) + return ret; }
if (pmd_trans_unstable(pmd)) @@ -521,11 +537,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue; - migrate_page_add(page, qp->pagelist, flags); + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(vma)) + break; + migrate_page_add(page, qp->pagelist, flags); + } else + break; } pte_unmap_unlock(pte - 1, ptl); cond_resched(); - return 0; + return addr != end ? -EIO : 0; }
static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, @@ -595,7 +616,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags;
- if (!vma_migratable(vma)) + /* + * Need check MPOL_MF_STRICT to return -EIO if possible + * regardless of vma_migratable + */ + if (!vma_migratable(vma) && + !(flags & MPOL_MF_STRICT)) return 1;
if (endvma > end) @@ -622,7 +648,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, }
/* queue pages from current vma */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & MPOL_MF_VALID) return 0; return 1; }
On Wed, 20 Mar 2019, Yang Shi wrote:
When MPOL_MF_STRICT was specified and an existing page was already on a node that does not follow the policy, mbind() should return -EIO. But commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") broke the rule.
And, commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support thp migration") didn't return the correct value for THP mbind() too.
If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an existing page was already on a node that does not follow the policy. And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified.
Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind...
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de
Acked-by: David Rientjes rientjes@google.com
Thanks. I think this needs stable for 4.0+, can you confirm?
On 3/19/19 5:49 PM, David Rientjes wrote:
On Wed, 20 Mar 2019, Yang Shi wrote:
When MPOL_MF_STRICT was specified and an existing page was already on a node that does not follow the policy, mbind() should return -EIO. But commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") broke the rule.
And, commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support thp migration") didn't return the correct value for THP mbind() too.
If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an existing page was already on a node that does not follow the policy. And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified.
Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind...
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de
Acked-by: David Rientjes rientjes@google.com
Thanks. I think this needs stable for 4.0+, can you confirm?
Thanks. Yes, this needs stable for 4.0+.
Yang
On Wed, Mar 20, 2019 at 12:06 AM Yang Shi yang.shi@linux.alibaba.com wrote:
When MPOL_MF_STRICT was specified and an existing page was already on a node that does not follow the policy, mbind() should return -EIO. But commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") broke the rule.
And, commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support thp migration") didn't return the correct value for THP mbind() too.
If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an existing page was already on a node that does not follow the policy. And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified.
Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind...
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de
mm/mempolicy.c | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index abe7a67..401c817 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -447,6 +447,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); }
+/*
- The queue_pages_pmd() may have three kind of return value.
- 1 - pages are placed on he right node or queued successfully.
Minor typo -> s/he/the ?
- 0 - THP get split.
- -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
page was already on a node that does not follow the policy.- */
static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -456,7 +463,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long flags;
if (unlikely(is_pmd_migration_entry(*pmd))) {
ret = 1;
ret = -EIO; goto unlock; } page = pmd_page(*pmd);@@ -473,8 +480,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {if (!vma_migratable(walk->vma)) {ret = -EIO;goto unlock;}migrate_page_add(page, qp->pagelist, flags);} elseret = -EIO;unlock: spin_unlock(ptl); out: @@ -499,8 +513,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
if (ret)
if (ret > 0) return 0;else if (ret < 0)return ret; } if (pmd_trans_unstable(pmd))@@ -521,11 +537,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue;
migrate_page_add(page, qp->pagelist, flags);
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {if (!vma_migratable(vma))break;migrate_page_add(page, qp->pagelist, flags);} elsebreak; } pte_unmap_unlock(pte - 1, ptl); cond_resched();
return 0;
return addr != end ? -EIO : 0;}
static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, @@ -595,7 +616,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags;
if (!vma_migratable(vma))
/** Need check MPOL_MF_STRICT to return -EIO if possible* regardless of vma_migratable*/if (!vma_migratable(vma) &&!(flags & MPOL_MF_STRICT)) return 1; if (endvma > end)@@ -622,7 +648,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, }
/* queue pages from current vma */
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
if (flags & MPOL_MF_VALID) return 0; return 1;}
1.8.3.1
On Wed, 20 Mar 2019 11:23:03 +0530 Souptick Joarder jrdr.linux@gmail.com wrote:
--- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -447,6 +447,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); }
+/*
- The queue_pages_pmd() may have three kind of return value.
- 1 - pages are placed on he right node or queued successfully.
Minor typo -> s/he/the ?
Yes, that comment needs some help. This?
--- a/mm/mempolicy.c~mm-mempolicy-make-mbind-return-eio-when-mpol_mf_strict-is-specified-fix +++ a/mm/mempolicy.c @@ -429,9 +429,9 @@ static inline bool queue_pages_required( }
/* - * The queue_pages_pmd() may have three kind of return value. - * 1 - pages are placed on he right node or queued successfully. - * 0 - THP get split. + * queue_pages_pmd() has three possible return values: + * 1 - pages are placed on the right node or queued successfully. + * 0 - THP was split. * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing * page was already on a node that does not follow the policy. */ _
On 3/20/19 3:16 PM, Andrew Morton wrote:
On Wed, 20 Mar 2019 11:23:03 +0530 Souptick Joarder jrdr.linux@gmail.com wrote:
--- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -447,6 +447,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); }
+/*
- The queue_pages_pmd() may have three kind of return value.
- 1 - pages are placed on he right node or queued successfully.
Minor typo -> s/he/the ?
Yes, that comment needs some help. This?
--- a/mm/mempolicy.c~mm-mempolicy-make-mbind-return-eio-when-mpol_mf_strict-is-specified-fix +++ a/mm/mempolicy.c @@ -429,9 +429,9 @@ static inline bool queue_pages_required( } /*
- The queue_pages_pmd() may have three kind of return value.
- 1 - pages are placed on he right node or queued successfully.
- 0 - THP get split.
- queue_pages_pmd() has three possible return values:
- 1 - pages are placed on the right node or queued successfully.
*/
- 0 - THP was split.
- -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
page was already on a node that does not follow the policy.
It looks good to me. Thanks, Andrew.
Yang
_
On Wed, Mar 20, 2019 at 02:35:56AM +0800, Yang Shi wrote:
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de
Hi Yang, thanks for the patch.
Some observations below.
} page = pmd_page(*pmd); @@ -473,8 +480,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma)) {ret = -EIO;goto unlock;}- migrate_page_add(page, qp->pagelist, flags);
- } else
ret = -EIO;
if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { ret = -EIO; goto unlock; }
migrate_page_add(page, qp->pagelist, flags); unlock: spin_unlock(ptl); out: return ret;
seems more clean to me?
unlock: spin_unlock(ptl); out: @@ -499,8 +513,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
if (ret)
if (ret > 0) return 0;else if (ret < 0)return ret;
I would go with the following, but that's a matter of taste I guess.
if (ret < 0) return ret; else return 0;
} if (pmd_trans_unstable(pmd)) @@ -521,11 +537,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue;
migrate_page_add(page, qp->pagelist, flags);
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {if (!vma_migratable(vma))break;migrate_page_add(page, qp->pagelist, flags);} elsebreak;
I might be missing something, but AFAICS neither vma nor flags is going to change while we are in queue_pages_pte_range(), so, could not we move the check just above the loop? In that way, 1) we only perform the check once and 2) if we enter the loop we know that we are going to do some work, so, something like:
index af171ccb56a2..7c0e44389826 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -487,6 +487,9 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0;
+ if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma)) + return -EIO; + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte))
} pte_unmap_unlock(pte - 1, ptl); cond_resched();
- return 0;
- return addr != end ? -EIO : 0;
If we can do the above, we can leave the return value as it was.
On 3/20/19 1:16 AM, Oscar Salvador wrote:
On Wed, Mar 20, 2019 at 02:35:56AM +0800, Yang Shi wrote:
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de
Hi Yang, thanks for the patch.
Some observations below.
} page = pmd_page(*pmd); @@ -473,8 +480,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma)) {ret = -EIO;goto unlock;}- migrate_page_add(page, qp->pagelist, flags);
- } else
ret = -EIO;if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { ret = -EIO; goto unlock; }
migrate_page_add(page, qp->pagelist, flags); unlock: spin_unlock(ptl); out: return ret;
seems more clean to me?
Yes, it sounds so.
unlock: spin_unlock(ptl); out: @@ -499,8 +513,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
if (ret)
if (ret > 0) return 0;else if (ret < 0)return ret;I would go with the following, but that's a matter of taste I guess.
if (ret < 0) return ret; else return 0;
No, this is not correct. queue_pages_pmd() may return 0, which means THP gets split. If it returns 0 the code should just fall through instead of returning.
} if (pmd_trans_unstable(pmd)) @@ -521,11 +537,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue;
migrate_page_add(page, qp->pagelist, flags);
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {if (!vma_migratable(vma))break;migrate_page_add(page, qp->pagelist, flags);} elsebreak;I might be missing something, but AFAICS neither vma nor flags is going to change while we are in queue_pages_pte_range(), so, could not we move the check just above the loop? In that way, 1) we only perform the check once and 2) if we enter the loop we know that we are going to do some work, so, something like:
index af171ccb56a2..7c0e44389826 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -487,6 +487,9 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0;
if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma))return -EIO;
It sounds not correct to me. We need check if there is existing page on the node which is not allowed by the policy. This is what queue_pages_required() does.
Thanks, Yang
pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte))} pte_unmap_unlock(pte - 1, ptl); cond_resched();
- return 0;
- return addr != end ? -EIO : 0;
If we can do the above, we can leave the return value as it was.
On Wed, 2019-03-20 at 11:31 -0700, Yang Shi wrote:
No, this is not correct. queue_pages_pmd() may return 0, which means THP gets split. If it returns 0 the code should just fall through instead of returning.
Right, I overlooked that.
It sounds not correct to me. We need check if there is existing page on the node which is not allowed by the policy. This is what queue_pages_required() does.
Bleh, I guess it was too early in the morning. That is the whole point of it actually, so that was quite wrong.
Sorry for trying to mislead you ;-)
Reviewed-by: Oscar Salvador osalvador@suse.de
On Wed, Mar 20, 2019 at 02:35:56AM +0800, Yang Shi wrote:
When MPOL_MF_STRICT was specified and an existing page was already on a node that does not follow the policy, mbind() should return -EIO. But commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") broke the rule.
And, commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support thp migration") didn't return the correct value for THP mbind() too.
If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an existing page was already on a node that does not follow the policy. And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified.
Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind...
Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Reported-by: Cyril Hrubis chrubis@suse.cz Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Suggested-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Oscar Salvador osalvador@suse.de
mm/mempolicy.c | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index abe7a67..401c817 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -447,6 +447,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } +/*
- The queue_pages_pmd() may have three kind of return value.
- 1 - pages are placed on he right node or queued successfully.
- 0 - THP get split.
- -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
page was already on a node that does not follow the policy.- */
static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -456,7 +463,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) {
ret = 1;
ret = -EIO;@@ -473,8 +480,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma)) {ret = -EIO;goto unlock;}- migrate_page_add(page, qp->pagelist, flags);
- } else
ret = -EIO;unlock: spin_unlock(ptl); out: @@ -499,8 +513,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
if (ret)
if (ret > 0) return 0;else if (ret < 0)return ret;if (pmd_trans_unstable(pmd)) @@ -521,11 +537,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue;
migrate_page_add(page, qp->pagelist, flags);
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {if (!vma_migratable(vma))break;migrate_page_add(page, qp->pagelist, flags);} elsebreak;
- return 0;
- return addr != end ? -EIO : 0;
} static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, @@ -595,7 +616,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags;
- if (!vma_migratable(vma))
- /*
* Need check MPOL_MF_STRICT to return -EIO if possible* regardless of vma_migratable*/- if (!vma_migratable(vma) &&
!(flags & MPOL_MF_STRICT))if (endvma > end) @@ -622,7 +648,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, } /* queue pages from current vma */
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
- if (flags & MPOL_MF_VALID) return 0; return 1;
}
1.8.3.1
Acked-by: Rafael Aquini aquini@redhat.com
linux-stable-mirror@lists.linaro.org
-
Andrew Morton -
David Rientjes -
Oscar Salvador -
Rafael Aquini -
Souptick Joarder -
Yang Shi