linux-kernel - [PATCH -V8 13/21] swap: Support PMD swap mapping in madvise

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20181207054122.27822-14-ying.huang@intel.com>
Date:   Fri,  7 Dec 2018 13:41:13 +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@...nel.org>,
        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>,
        Daniel Jordan <daniel.m.jordan@...cle.com>
Subject: [PATCH -V8 13/21] swap: Support PMD swap mapping in madvise_free()

When madvise_free() found a PMD swap mapping, if only part of the huge
swap cluster is operated on, the PMD swap mapping will be split and
fallback to PTE swap mapping processing.  Otherwise, if all huge swap
cluster is operated on, free_swap_and_cache() will be called to
decrease the PMD swap mapping count and probably free the swap space
and the THP in swap cache too.

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@...nel.org>
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>
Cc: Daniel Jordan <daniel.m.jordan@...cle.com>
---
 mm/huge_memory.c | 52 ++++++++++++++++++++++++++++++++++--------------
 mm/madvise.c     |  2 +-
 2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f3c0a9e8fb9a..9cf5d4fa6d98 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1899,6 +1899,15 @@ int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
 }
 #endif
 
+static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
+{
+	pgtable_t pgtable;
+
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+	pte_free(mm, pgtable);
+	mm_dec_nr_ptes(mm);
+}
+
 /*
  * Return true if we do MADV_FREE successfully on entire pmd page.
  * Otherwise, return false.
@@ -1919,15 +1928,37 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		goto out_unlocked;
 
 	orig_pmd = *pmd;
-	if (is_huge_zero_pmd(orig_pmd))
-		goto out;
-
 	if (unlikely(!pmd_present(orig_pmd))) {
-		VM_BUG_ON(thp_migration_supported() &&
-				  !is_pmd_migration_entry(orig_pmd));
-		goto out;
+		swp_entry_t entry = pmd_to_swp_entry(orig_pmd);
+
+		if (is_migration_entry(entry)) {
+			VM_BUG_ON(!thp_migration_supported());
+			goto out;
+		} else if (IS_ENABLED(CONFIG_THP_SWAP) &&
+			   !non_swap_entry(entry)) {
+			/*
+			 * If part of THP is discarded, split the PMD
+			 * swap mapping and operate on the PTEs
+			 */
+			if (next - addr != HPAGE_PMD_SIZE) {
+				__split_huge_swap_pmd(vma, addr, pmd);
+				goto out;
+			}
+			free_swap_and_cache(entry, HPAGE_PMD_NR);
+			pmd_clear(pmd);
+			zap_deposited_table(mm, pmd);
+			if (current->mm == mm)
+				sync_mm_rss(mm);
+			add_mm_counter(mm, MM_SWAPENTS, -HPAGE_PMD_NR);
+			ret = true;
+			goto out;
+		} else
+			VM_BUG_ON(1);
 	}
 
+	if (is_huge_zero_pmd(orig_pmd))
+		goto out;
+
 	page = pmd_page(orig_pmd);
 	/*
 	 * If other processes are mapping this page, we couldn't discard
@@ -1973,15 +2004,6 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return ret;
 }
 
-static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
-{
-	pgtable_t pgtable;
-
-	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
-	pte_free(mm, pgtable);
-	mm_dec_nr_ptes(mm);
-}
-
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index cbb3d7e38e51..0c1f96c605f8 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -321,7 +321,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	unsigned long next;
 
 	next = pmd_addr_end(addr, end);
-	if (pmd_trans_huge(*pmd))
+	if (pmd_trans_huge(*pmd) || is_swap_pmd(*pmd))
 		if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
 			goto next;
 
-- 
2.18.1