summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorVlastimil Babka <vbabka@suse.cz>2016-07-28 15:49:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-07-28 16:07:41 -0700
commit2516035499b9555f6acd373c9f12e44bcb50dbec (patch)
treef8c4cce437490ff0b9da7ecaa7df338bada86fea /mm
parent3eb2771b06d8e206a2f48cfc7c96bb4ef97e2471 (diff)
downloadop-kernel-dev-2516035499b9555f6acd373c9f12e44bcb50dbec.zip
op-kernel-dev-2516035499b9555f6acd373c9f12e44bcb50dbec.tar.gz
mm, thp: remove __GFP_NORETRY from khugepaged and madvised allocations
After the previous patch, we can distinguish costly allocations that should be really lightweight, such as THP page faults, with __GFP_NORETRY. This means we don't need to recognize khugepaged allocations via PF_KTHREAD anymore. We can also change THP page faults in areas where madvise(MADV_HUGEPAGE) was used to try as hard as khugepaged, as the process has indicated that it benefits from THP's and is willing to pay some initial latency costs. We can also make the flags handling less cryptic by distinguishing GFP_TRANSHUGE_LIGHT (no reclaim at all, default mode in page fault) from GFP_TRANSHUGE (only direct reclaim, khugepaged default). Adding __GFP_NORETRY or __GFP_KSWAPD_RECLAIM is done where needed. The patch effectively changes the current GFP_TRANSHUGE users as follows: * get_huge_zero_page() - the zero page lifetime should be relatively long and it's shared by multiple users, so it's worth spending some effort on it. We use GFP_TRANSHUGE, and __GFP_NORETRY is not added. This also restores direct reclaim to this allocation, which was unintentionally removed by commit e4a49efe4e7e ("mm: thp: set THP defrag by default to madvise and add a stall-free defrag option") * alloc_hugepage_khugepaged_gfpmask() - this is khugepaged, so latency is not an issue. So if khugepaged "defrag" is enabled (the default), do reclaim via GFP_TRANSHUGE without __GFP_NORETRY. We can remove the PF_KTHREAD check from page alloc. As a side-effect, khugepaged will now no longer check if the initial compaction was deferred or contended. This is OK, as khugepaged sleep times between collapsion attempts are long enough to prevent noticeable disruption, so we should allow it to spend some effort. * migrate_misplaced_transhuge_page() - already was masking out __GFP_RECLAIM, so just convert to GFP_TRANSHUGE_LIGHT which is equivalent. * alloc_hugepage_direct_gfpmask() - vma's with VM_HUGEPAGE (via madvise) are now allocating without __GFP_NORETRY. Other vma's keep using __GFP_NORETRY if direct reclaim/compaction is at all allowed (by default it's allowed only for madvised vma's). The rest is conversion to GFP_TRANSHUGE(_LIGHT). [mhocko@suse.com: suggested GFP_TRANSHUGE_LIGHT] Link: http://lkml.kernel.org/r/20160721073614.24395-7-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c29
-rw-r--r--mm/khugepaged.c2
-rw-r--r--mm/migrate.c2
-rw-r--r--mm/page_alloc.c6
4 files changed, 20 insertions, 19 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8f0cd35..2373f0a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -539,23 +539,26 @@ static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
}
/*
- * If THP is set to always then directly reclaim/compact as necessary
- * If set to defer then do no reclaim and defer to khugepaged
+ * If THP defrag is set to always then directly reclaim/compact as necessary
+ * If set to defer then do only background reclaim/compact and defer to khugepaged
* If set to madvise and the VMA is flagged then directly reclaim/compact
+ * When direct reclaim/compact is allowed, don't retry except for flagged VMA's
*/
static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
{
- gfp_t reclaim_flags = 0;
-
- if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags) &&
- (vma->vm_flags & VM_HUGEPAGE))
- reclaim_flags = __GFP_DIRECT_RECLAIM;
- else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
- reclaim_flags = __GFP_KSWAPD_RECLAIM;
- else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
- reclaim_flags = __GFP_DIRECT_RECLAIM;
-
- return GFP_TRANSHUGE | reclaim_flags;
+ bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+
+ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
+ &transparent_hugepage_flags) && vma_madvised)
+ return GFP_TRANSHUGE;
+ else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
+ &transparent_hugepage_flags))
+ return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+ else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
+ &transparent_hugepage_flags))
+ return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
+
+ return GFP_TRANSHUGE_LIGHT;
}
/* Caller must hold page table lock. */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d1423d7..79c52d0 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -694,7 +694,7 @@ static bool khugepaged_scan_abort(int nid)
/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */
static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)
{
- return GFP_TRANSHUGE | (khugepaged_defrag() ? __GFP_DIRECT_RECLAIM : 0);
+ return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT;
}
#ifdef CONFIG_NUMA
diff --git a/mm/migrate.c b/mm/migrate.c
index ed02682..f7ee04a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1934,7 +1934,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
goto out_dropref;
new_page = alloc_pages_node(node,
- (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM,
+ (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
HPAGE_PMD_ORDER);
if (!new_page)
goto out_fail;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c42ec37..09ba674 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3556,11 +3556,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
/*
* Looks like reclaim/compaction is worth trying, but
* sync compaction could be very expensive, so keep
- * using async compaction, unless it's khugepaged
- * trying to collapse.
+ * using async compaction.
*/
- if (!(current->flags & PF_KTHREAD))
- migration_mode = MIGRATE_ASYNC;
+ migration_mode = MIGRATE_ASYNC;
}
}
OpenPOWER on IntegriCloud