linux-kernel - [RFC PATCH 7/8] x86: make __split_large

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]

Date:	Fri, 20 Jul 2012 15:13:13 +0800
From:	Wen Congyang <wency@...fujitsu.com>
To:	linux-mm@...ck.org, linux-kernel@...r.kernel.org,
	linuxppc-dev@...ts.ozlabs.org, linux-acpi@...r.kernel.org
CC:	rientjes@...gle.com, liuj97@...il.com, len.brown@...el.com,
	benh@...nel.crashing.org, paulus@...ba.org, cl@...ux.com,
	minchan.kim@...il.com, akpm@...ux-foundation.org,
	kosaki.motohiro@...fujitsu.com,
	Yasuaki ISIMATU <isimatu.yasuaki@...fujitsu.com>
Subject: [RFC PATCH 7/8] x86: make __split_large_page() generally avialable

We need to clear page table after calling __remove_pages(). We may
need to clear part of pmd or pud's entry when clearing the page table.
So we need to split it to small page. Make __split_large_page()
generally avialable, and we call call this function to split large page.

CC: David Rientjes <rientjes@...gle.com>
CC: Jiang Liu <liuj97@...il.com>
CC: Len Brown <len.brown@...el.com>
CC: Benjamin Herrenschmidt <benh@...nel.crashing.org>
CC: Paul Mackerras <paulus@...ba.org>
CC: Christoph Lameter <cl@...ux.com>
Cc: Minchan Kim <minchan.kim@...il.com>
CC: Andrew Morton <akpm@...ux-foundation.org>
CC: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
CC: Yasuaki Ishimatsu <isimatu.yasuaki@...fujitsu.com>
Signed-off-by: Wen Congyang <wency@...fujitsu.com>
---
 arch/x86/include/asm/pgtable_types.h |    1 +
 arch/x86/mm/pageattr.c               |   47 ++++++++++++++++++----------------
 2 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 013286a..b725af2 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -334,6 +334,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a718e0d..7dcb6f9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -501,21 +501,13 @@ out_unlock:
 	return do_split;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
 {
 	unsigned long pfn, pfninc = 1;
 	unsigned int i, level;
-	pte_t *pbase, *tmp;
+	pte_t *tmp;
 	pgprot_t ref_prot;
-	struct page *base;
-
-	if (!debug_pagealloc)
-		spin_unlock(&cpa_lock);
-	base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
-	if (!debug_pagealloc)
-		spin_lock(&cpa_lock);
-	if (!base)
-		return -ENOMEM;
+	struct page *base = virt_to_page(pbase);
 
 	spin_lock(&pgd_lock);
 	/*
@@ -523,10 +515,11 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	 * up for us already:
 	 */
 	tmp = lookup_address(address, &level);
-	if (tmp != kpte)
-		goto out_unlock;
+	if (tmp != kpte) {
+		spin_unlock(&pgd_lock);
+		return 1;
+	}
 
-	pbase = (pte_t *)page_address(base);
 	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
 	ref_prot = pte_pgprot(pte_clrhuge(*kpte));
 	/*
@@ -579,17 +572,27 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	 * going on.
 	 */
 	__flush_tlb_all();
+	spin_unlock(&pgd_lock);
 
-	base = NULL;
+	return 0;
+}
 
-out_unlock:
-	/*
-	 * If we dropped out via the lookup_address check under
-	 * pgd_lock then stick the page back into the pool:
-	 */
-	if (base)
+static int split_large_page(pte_t *kpte, unsigned long address)
+{
+	pte_t *pbase;
+	struct page *base;
+
+	if (!debug_pagealloc)
+		spin_unlock(&cpa_lock);
+	base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
+	if (!debug_pagealloc)
+		spin_lock(&cpa_lock);
+	if (!base)
+		return -ENOMEM;
+
+	pbase = (pte_t *)page_address(base);
+	if (__split_large_page(kpte, address, pbase))
 		__free_page(base);
-	spin_unlock(&pgd_lock);
 
 	return 0;
 }
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/