| 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: <20180509083846.14823-7-ying.huang@intel.com>
Date: Wed, 9 May 2018 16:38:31 +0800
From: "Huang, Ying" <ying.huang@...el.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: 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 -V2 06/21] mm, THP, swap: Support PMD swap mapping when splitting huge PMD
From: Huang Ying <ying.huang@...el.com>
A huge PMD need to be split when zap a part of the PMD mapping etc.
If the PMD mapping is a swap mapping, we need to split it too. This
patch implemented the support for this. This is similar as splitting
the PMD page mapping, except we need to decrease the PMD swap mapping
count for the huge swap cluster too. If the PMD swap mapping count
becomes 0, the huge swap cluster will be split.
Notice: is_huge_zero_pmd() and pmd_page() doesn't work well with swap
PMD, so pmd_present() check is called before them.
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/swap.h | 6 ++++++
mm/huge_memory.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++-----
mm/swapfile.c | 28 +++++++++++++++++++++++++
3 files changed, 87 insertions(+), 5 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7ed2c727c9b6..bb9de2cb952a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -618,11 +618,17 @@ static inline swp_entry_t get_swap_page(struct page *page)
#ifdef CONFIG_THP_SWAP
extern int split_swap_cluster(swp_entry_t entry);
+extern int split_swap_cluster_map(swp_entry_t entry);
#else
static inline int split_swap_cluster(swp_entry_t entry)
{
return 0;
}
+
+static inline int split_swap_cluster_map(swp_entry_t entry)
+{
+ return 0;
+}
#endif
#ifdef CONFIG_MEMCG
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 323acdd14e6e..86800ef7c61c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1605,6 +1605,47 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
return 0;
}
+#ifdef CONFIG_THP_SWAP
+static void __split_huge_swap_pmd(struct vm_area_struct *vma,
+ unsigned long haddr,
+ pmd_t *pmd)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pgtable_t pgtable;
+ pmd_t _pmd;
+ swp_entry_t entry;
+ int i, soft_dirty;
+
+ entry = pmd_to_swp_entry(*pmd);
+ soft_dirty = pmd_soft_dirty(*pmd);
+
+ split_swap_cluster_map(entry);
+
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+ pmd_populate(mm, &_pmd, pgtable);
+
+ for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE, entry.val++) {
+ pte_t *pte, ptent;
+
+ pte = pte_offset_map(&_pmd, haddr);
+ VM_BUG_ON(!pte_none(*pte));
+ ptent = swp_entry_to_pte(entry);
+ if (soft_dirty)
+ ptent = pte_swp_mksoft_dirty(ptent);
+ set_pte_at(mm, haddr, pte, ptent);
+ pte_unmap(pte);
+ }
+ smp_wmb(); /* make pte visible before pmd */
+ pmd_populate(mm, pmd, pgtable);
+}
+#else
+static inline void __split_huge_swap_pmd(struct vm_area_struct *vma,
+ unsigned long haddr,
+ pmd_t *pmd)
+{
+}
+#endif
+
/*
* Return true if we do MADV_FREE successfully on entire pmd page.
* Otherwise, return false.
@@ -2071,7 +2112,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
- VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
+ VM_BUG_ON(!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd)
&& !pmd_devmap(*pmd));
count_vm_event(THP_SPLIT_PMD);
@@ -2093,8 +2134,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
put_page(page);
add_mm_counter(mm, MM_FILEPAGES, -HPAGE_PMD_NR);
return;
- } else if (is_huge_zero_pmd(*pmd)) {
+ } else if (pmd_present(*pmd) && is_huge_zero_pmd(*pmd)) {
/*
+ * is_huge_zero_pmd() may return true for PMD swap
+ * entry, so checking pmd_present() firstly.
+ *
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_invalidate_range() see comments below inside
* __split_huge_pmd() ?
@@ -2137,6 +2181,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
page = pfn_to_page(swp_offset(entry));
} else
#endif
+ if (thp_swap_supported() && is_swap_pmd(old_pmd))
+ return __split_huge_swap_pmd(vma, haddr, pmd);
+ else
page = pmd_page(old_pmd);
VM_BUG_ON_PAGE(!page_count(page), page);
page_ref_add(page, HPAGE_PMD_NR - 1);
@@ -2228,14 +2275,15 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
* pmd against. Otherwise we can end up replacing wrong page.
*/
VM_BUG_ON(freeze && !page);
- if (page && page != pmd_page(*pmd))
- goto out;
+ /* pmd_page() should be called only if pmd_present() */
+ if (page && (!pmd_present(*pmd) || page != pmd_page(*pmd)))
+ goto out;
if (pmd_trans_huge(*pmd)) {
page = pmd_page(*pmd);
if (PageMlocked(page))
clear_page_mlock(page);
- } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
+ } else if (!(pmd_devmap(*pmd) || is_swap_pmd(*pmd)))
goto out;
__split_huge_pmd_locked(vma, pmd, haddr, freeze);
out:
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 819f5fd6918e..acf2d0c30457 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -4041,6 +4041,34 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
}
}
+#ifdef CONFIG_THP_SWAP
+/* The corresponding page table shouldn't be changed under us */
+int split_swap_cluster_map(swp_entry_t entry)
+{
+ struct swap_info_struct *si;
+ struct swap_cluster_info *ci;
+ unsigned long offset = swp_offset(entry);
+
+ VM_BUG_ON(!is_cluster_offset(offset));
+ si = _swap_info_get(entry);
+ if (!si)
+ return -EBUSY;
+ ci = lock_cluster(si, offset);
+ /* The swap cluster has been split by someone else */
+ if (!cluster_is_huge(ci))
+ goto out;
+ cluster_set_count(ci, cluster_count(ci) - 1);
+ VM_BUG_ON(cluster_count(ci) < SWAPFILE_CLUSTER);
+ if (cluster_count(ci) == SWAPFILE_CLUSTER &&
+ !(si->swap_map[offset] & SWAP_HAS_CACHE))
+ cluster_clear_huge(ci);
+
+out:
+ unlock_cluster(ci);
+ return 0;
+}
+#endif
+
static int __init swapfile_init(void)
{
int nid;
--
2.16.1
Powered by blists - more mailing lists