[patch 193/212] mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Ben Widawsky <ben.widawsky@xxxxxxxxx>
Subject: mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY

Implement the missing huge page allocation functionality while obeying the
preferred node semantics.  This is similar to the implementation for
general page allocation, as it uses a fallback mechanism to try multiple
preferred nodes first, and then all other nodes.

To avoid adding too many "#ifdef CONFIG_NUMA" check, add a helper function
in mempolicy.h to check whether a mempolicy is MPOL_PREFERRED_MANY.

[akpm@xxxxxxxxxxxxxxxxxxxx: fix compiling issue when merging with other hugetlb patch]
[Thanks to 0day bot for catching the !CONFIG_NUMA compiling issue]
[mhocko@xxxxxxxx: suggest to remove the #ifdef CONFIG_NUMA check]
[ben.widawsky@xxxxxxxxx: add helpers to avoid ifdefs]
  Link: https://lore.kernel.org/r/20200630212517.308045-12-ben.widawsky@xxxxxxxxx
  Link: https://lkml.kernel.org/r/1627970362-61305-4-git-send-email-feng.tang@xxxxxxxxx
  Link: https://lkml.kernel.org/r/20210809024430.GA46432@xxxxxxxxxxxxxxxxxxxxxxx
[nathan@xxxxxxxxxx: initialize page to NULL in alloc_buddy_huge_page_with_mpol()]
  Link: https://lkml.kernel.org/r/20210810200632.3812797-1-nathan@xxxxxxxxxx
Link: https://lore.kernel.org/r/20200630212517.308045-12-ben.widawsky@xxxxxxxxx
Link: https://lkml.kernel.org/r/1627970362-61305-4-git-send-email-feng.tang@xxxxxxxxx
Link: https://lkml.kernel.org/r/20210809024430.GA46432@xxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ben Widawsky <ben.widawsky@xxxxxxxxx>
Signed-off-by: Feng Tang <feng.tang@xxxxxxxxx>
Signed-off-by: Nathan Chancellor <nathan@xxxxxxxxxx>
Co-developed-by: Feng Tang <feng.tang@xxxxxxxxx>
Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

 include/linux/mempolicy.h |   12 ++++++++++++
 mm/hugetlb.c              |   30 +++++++++++++++++++++++++-----
 2 files changed, 37 insertions(+), 5 deletions(-)

--- a/include/linux/mempolicy.h~mm-hugetlb-add-support-for-mempolicy-mpol_preferred_many
+++ a/include/linux/mempolicy.h
@@ -186,6 +186,12 @@ extern void mpol_put_task_policy(struct
 
 extern bool numa_demotion_enabled;
 
+static inline bool mpol_is_preferred_many(struct mempolicy *pol)
+{
+	return  (pol->mode == MPOL_PREFERRED_MANY);
+}
+
+
 #else
 
 struct mempolicy {};
@@ -296,5 +302,11 @@ static inline nodemask_t *policy_nodemas
 }
 
 #define numa_demotion_enabled	false
+
+static inline bool mpol_is_preferred_many(struct mempolicy *pol)
+{
+	return  false;
+}
+
 #endif /* CONFIG_NUMA */
 #endif
--- a/mm/hugetlb.c~mm-hugetlb-add-support-for-mempolicy-mpol_preferred_many
+++ a/mm/hugetlb.c
@@ -1145,7 +1145,7 @@ static struct page *dequeue_huge_page_vm
 				unsigned long address, int avoid_reserve,
 				long chg)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	gfp_t gfp_mask;
 	nodemask_t *nodemask;
@@ -1166,7 +1166,17 @@ static struct page *dequeue_huge_page_vm
 
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+
+	if (mpol_is_preferred_many(mpol)) {
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+
+		/* Fallback to all nodes if page==NULL */
+		nodemask = NULL;
+	}
+
+	if (!page)
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+
 	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
 		SetHPageRestoreReserve(page);
 		h->resv_huge_pages--;
@@ -2142,16 +2152,26 @@ static
 struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	gfp_t gfp_mask = htlb_alloc_mask(h);
 	int nid;
 	nodemask_t *nodemask;
 
 	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
-	page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask, false);
-	mpol_cond_put(mpol);
+	if (mpol_is_preferred_many(mpol)) {
+		gfp_t gfp = gfp_mask | __GFP_NOWARN;
+
+		gfp &=  ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+		page = alloc_surplus_huge_page(h, gfp, nid, nodemask, false);
 
+		/* Fallback to all nodes if page==NULL */
+		nodemask = NULL;
+	}
+
+	if (!page)
+		page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask, false);
+	mpol_cond_put(mpol);
 	return page;
 }
 
_



[Index of Archives]     [Kernel Archive]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]

  Powered by Linux