From: Huang Ying
Swapin a THP as a whole isn't desirable at some situations. For
example, for random access pattern, swapin a THP as a whole will
inflate the reading greatly. So a sysfs interface:
/sys/kernel/mm/transparent_hugepage/swapin_enabled is added to
configure it. Three options as follow are provided,
- always: THP swapin will be enabled always
- madvise: THP swapin will be enabled only for VMA with VM_HUGEPAGE
flag set.
- never: THP swapin will be disabled always
The default configuration is: madvise.
During page fault, if a PMD swap mapping is found and THP swapin is
disabled, the huge swap cluster and the PMD swap mapping will be split
and fallback to normal page swapin.
Signed-off-by: "Huang, Ying"
Cc: "Kirill A. Shutemov"
Cc: Andrea Arcangeli
Cc: Michal Hocko
Cc: Johannes Weiner
Cc: Shaohua Li
Cc: Hugh Dickins
Cc: Minchan Kim
Cc: Rik van Riel
Cc: Dave Hansen
Cc: Naoya Horiguchi
Cc: Zi Yan
---
include/linux/huge_mm.h | 31 ++
mm/huge_memory.c| 89 -
2 files changed, 102 insertions(+), 18 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f5348d072351..1cfd43047f0d 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -62,6 +62,8 @@ enum transparent_hugepage_flag {
#ifdef CONFIG_DEBUG_VM
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
#endif
+ TRANSPARENT_HUGEPAGE_SWAPIN_FLAG,
+ TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG,
};
struct kobject;
@@ -404,11 +406,40 @@ static inline gfp_t alloc_hugepage_direct_gfpmask(struct
vm_area_struct *vma)
#ifdef CONFIG_THP_SWAP
extern int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd);
+
+static inline bool transparent_hugepage_swapin_enabled(
+ struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_NOHUGEPAGE)
+ return false;
+
+ if (is_vma_temporary_stack(vma))
+ return false;
+
+ if (test_bit(MMF_DISABLE_THP, >vm_mm->flags))
+ return false;
+
+ if (transparent_hugepage_flags &
+ (1 << TRANSPARENT_HUGEPAGE_SWAPIN_FLAG))
+ return true;
+
+ if (transparent_hugepage_flags &
+ (1 << TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG))
+ return !!(vma->vm_flags & VM_HUGEPAGE);
+
+ return false;
+}
#else /* CONFIG_THP_SWAP */
static inline int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
{
return 0;
}
+
+static inline bool transparent_hugepage_swapin_enabled(
+ struct vm_area_struct *vma)
+{
+ return false;
+}
#endif /* CONFIG_THP_SWAP */
#endif /* _LINUX_HUGE_MM_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e4d32384e10b..0538fe48918b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -57,7 +57,8 @@ unsigned long transparent_hugepage_flags __read_mostly =
#endif
(1pmd, orig_pmd))) {
- ret = split_swap_cluster(entry, false);
- /*
-* Retry if somebody else swap in the swap
-* entry
-*/
- if (ret == -EEXIST) {
- ret = 0;
- goto retry;
- /* swapoff occurs under us */
- } else if (ret == -EINVAL)
- ret = 0;
- else {
- count_vm_event(THP_SWPIN_FALLBACK);
- goto fallback;
- }
- }
+ if (likely(pmd_same(*vmf->pmd, orig_pmd)))
+ goto split;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
goto out;
}
@@ -1784,6 +1823,20 @@ int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t
orig_pmd)
if (page)
put_page(page);
return ret;
+split:
+ ret = split_swap_cluster(entry, false);
+ /* Retry if somebody else swap in the swap entry */
+ if (ret == -EEXIST) {
+ ret = 0;
+ goto retry;
+ }
+ /* swapoff occurs under