linux-kernel - [PATCH v3 6/6] mm, thp: introduce FOLL_SPLIT

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: <20190612220320.2223898-7-songliubraving@fb.com>
Date:   Wed, 12 Jun 2019 15:03:20 -0700
From:   Song Liu <songliubraving@...com>
To:     <linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>
CC:     <namit@...are.com>, <peterz@...radead.org>, <oleg@...hat.com>,
        <rostedt@...dmis.org>, <mhiramat@...nel.org>,
        <matthew.wilcox@...cle.com>, <kirill.shutemov@...ux.intel.com>,
        <kernel-team@...com>, Song Liu <songliubraving@...com>
Subject: [PATCH v3 6/6] mm, thp: introduce FOLL_SPLIT_PMD

This patches introduces a new foll_flag: FOLL_SPLIT_PMD. As the name says
FOLL_SPLIT_PMD splits huge pmd for given mm_struct, the underlining huge
page stays as-is.

FOLL_SPLIT_PMD is useful for cases where we need to use regular pages,
but would switch back to huge page and huge pmd on. One of such example
is uprobe. The following patches use FOLL_SPLIT_PMD in uprobe.

Signed-off-by: Song Liu <songliubraving@...com>
---
 include/linux/mm.h |  1 +
 mm/gup.c           | 38 +++++++++++++++++++++++++++++++++++---
 2 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ab8c7d84cd0..e605acc4fc81 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2642,6 +2642,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_COW	0x4000	/* internal GUP flag */
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
+#define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 
 /*
  * NOTE on FOLL_LONGTERM:
diff --git a/mm/gup.c b/mm/gup.c
index ddde097cf9e4..3d05bddb56c9 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -398,7 +398,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 	}
-	if (flags & FOLL_SPLIT) {
+	if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
 		int ret;
 		page = pmd_page(*pmd);
 		if (is_huge_zero_page(page)) {
@@ -407,7 +407,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 			split_huge_pmd(vma, pmd, address);
 			if (pmd_trans_unstable(pmd))
 				ret = -EBUSY;
-		} else {
+		} else if (flags & FOLL_SPLIT) {
 			if (unlikely(!try_get_page(page))) {
 				spin_unlock(ptl);
 				return ERR_PTR(-ENOMEM);
@@ -419,8 +419,40 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 			put_page(page);
 			if (pmd_none(*pmd))
 				return no_page_table(vma, flags);
-		}
+		} else {  /* flags & FOLL_SPLIT_PMD */
+			unsigned long addr;
+			pgprot_t prot;
+			pte_t *pte;
+			int i;
+
+			spin_unlock(ptl);
+			split_huge_pmd(vma, pmd, address);
+			lock_page(page);
+			pte = get_locked_pte(mm, address, &ptl);
+			if (!pte) {
+				unlock_page(page);
+				return no_page_table(vma, flags);
+			}
 
+			/* get refcount for every small page */
+			page_ref_add(page, HPAGE_PMD_NR);
+
+			prot = READ_ONCE(vma->vm_page_prot);
+			for (i = 0, addr = address & PMD_MASK;
+			     i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
+				struct page *p = page + i;
+
+				pte = pte_offset_map(pmd, addr);
+				VM_BUG_ON(!pte_none(*pte));
+				set_pte_at(mm, addr, pte, mk_pte(p, prot));
+				page_add_file_rmap(p, false);
+			}
+
+			spin_unlock(ptl);
+			unlock_page(page);
+			add_mm_counter(mm, mm_counter_file(page), HPAGE_PMD_NR);
+			ret = 0;
+		}
 		return ret ? ERR_PTR(ret) :
 			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 	}
-- 
2.17.1