| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20180417020230.26412-12-ying.huang@intel.com>
Date: Tue, 17 Apr 2018 10:02:20 +0800
From: "Huang, Ying" <ying.huang@...el.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Tim Chen <tim.c.chen@...el.com>, Andi Kleen <ak@...ux.intel.com>,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
Huang Ying <ying.huang@...el.com>,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Michal Hocko <mhocko@...e.com>,
Johannes Weiner <hannes@...xchg.org>,
Shaohua Li <shli@...nel.org>, Hugh Dickins <hughd@...gle.com>,
Minchan Kim <minchan@...nel.org>,
Rik van Riel <riel@...hat.com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Naoya Horiguchi <n-horiguchi@...jp.nec.com>,
Zi Yan <zi.yan@...rutgers.edu>
Subject: [PATCH -mm 11/21] mm, THP, swap: Add sysfs interface to configure THP swapin
From: Huang Ying <ying.huang@...el.com>
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" <ying.huang@...el.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Cc: Andrea Arcangeli <aarcange@...hat.com>
Cc: Michal Hocko <mhocko@...e.com>
Cc: Johannes Weiner <hannes@...xchg.org>
Cc: Shaohua Li <shli@...nel.org>
Cc: Hugh Dickins <hughd@...gle.com>
Cc: Minchan Kim <minchan@...nel.org>
Cc: Rik van Riel <riel@...hat.com>
Cc: Dave Hansen <dave.hansen@...ux.intel.com>
Cc: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Cc: Zi Yan <zi.yan@...rutgers.edu>
---
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, &vma->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
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
- (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
+ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)|
+ (1<<TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG);
static struct shrinker deferred_split_shrinker;
@@ -316,6 +317,53 @@ static struct kobj_attribute debug_cow_attr =
__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
#endif /* CONFIG_DEBUG_VM */
+#ifdef CONFIG_THP_SWAP
+static ssize_t swapin_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ if (test_bit(TRANSPARENT_HUGEPAGE_SWAPIN_FLAG,
+ &transparent_hugepage_flags))
+ return sprintf(buf, "[always] madvise never\n");
+ else if (test_bit(TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG,
+ &transparent_hugepage_flags))
+ return sprintf(buf, "always [madvise] never\n");
+ else
+ return sprintf(buf, "always madvise [never]\n");
+}
+
+static ssize_t swapin_enabled_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ ssize_t ret = count;
+
+ if (!memcmp("always", buf,
+ min(sizeof("always")-1, count))) {
+ clear_bit(TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG,
+ &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_SWAPIN_FLAG,
+ &transparent_hugepage_flags);
+ } else if (!memcmp("madvise", buf,
+ min(sizeof("madvise")-1, count))) {
+ clear_bit(TRANSPARENT_HUGEPAGE_SWAPIN_FLAG,
+ &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG,
+ &transparent_hugepage_flags);
+ } else if (!memcmp("never", buf,
+ min(sizeof("never")-1, count))) {
+ clear_bit(TRANSPARENT_HUGEPAGE_SWAPIN_FLAG,
+ &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_SWAPIN_REQ_MADV_FLAG,
+ &transparent_hugepage_flags);
+ } else
+ ret = -EINVAL;
+
+ return ret;
+}
+static struct kobj_attribute swapin_enabled_attr =
+ __ATTR(swapin_enabled, 0644, swapin_enabled_show, swapin_enabled_store);
+#endif /* CONFIG_THP_SWAP */
+
static struct attribute *hugepage_attr[] = {
&enabled_attr.attr,
&defrag_attr.attr,
@@ -326,6 +374,9 @@ static struct attribute *hugepage_attr[] = {
#endif
#ifdef CONFIG_DEBUG_VM
&debug_cow_attr.attr,
+#endif
+#ifdef CONFIG_THP_SWAP
+ &swapin_enabled_attr.attr,
#endif
NULL,
};
@@ -1648,6 +1699,9 @@ int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
retry:
page = lookup_swap_cache(entry, NULL, vmf->address);
if (!page) {
+ if (!transparent_hugepage_swapin_enabled(vma))
+ goto split;
+
page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma,
haddr, false);
if (!page) {
@@ -1655,23 +1709,8 @@ int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
* Back out if somebody else faulted in this pmd
* while we released the pmd lock.
*/
- if (likely(pmd_same(*vmf->pmd, 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 us */
+ if (ret == -EINVAL) {
+ delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ return 0;
+ }
+ count_vm_event(THP_SWPIN_FALLBACK);
+ goto fallback;
}
#else
static inline void __split_huge_swap_pmd(struct vm_area_struct *vma,
--
2.17.0
Powered by blists - more mailing lists