linux-kernel - [PATCH 3/3] mm: Add kernel PTE level pagetable pages account

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: <398ead25695e530f766849be5edafaf62c1c864d.1657096412.git.baolin.wang@linux.alibaba.com>
Date:   Wed,  6 Jul 2022 16:59:17 +0800
From:   Baolin Wang <baolin.wang@...ux.alibaba.com>
To:     akpm@...ux-foundation.org
Cc:     rppt@...ux.ibm.com, willy@...radead.org, will@...nel.org,
        aneesh.kumar@...ux.ibm.com, npiggin@...il.com,
        peterz@...radead.org, catalin.marinas@....com,
        chenhuacai@...nel.org, kernel@...0n.name,
        tsbogend@...ha.franken.de, dave.hansen@...ux.intel.com,
        luto@...nel.org, tglx@...utronix.de, mingo@...hat.com,
        bp@...en8.de, hpa@...or.com, arnd@...db.de, guoren@...nel.org,
        monstr@...str.eu, jonas@...thpole.se,
        stefan.kristiansson@...nalahti.fi, shorne@...il.com,
        baolin.wang@...ux.alibaba.com, x86@...nel.org,
        linux-arch@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
        loongarch@...ts.linux.dev, linux-mips@...r.kernel.org,
        linux-csky@...r.kernel.org, openrisc@...ts.librecores.org,
        linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: [PATCH 3/3] mm: Add kernel PTE level pagetable pages account

Now the kernel PTE level ptes are always protected by mm->page_table_lock
instead of split pagetable lock, so the kernel PTE level pagetable pages
are not accounted. Especially the vmalloc()/vmap() can consume lots of
kernel pagetable, so to get an accurate pagetable accounting, calling new
helpers page_{set,clear}_pgtable() when allocating or freeing a kernel
PTE level pagetable page.

Meanwhile converting architectures to use corresponding generic PTE pagetable
allocation and freeing functions.

Note this patch only adds accounting to the page tables allocated after boot.

Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
Reported-by: kernel test robot <oliver.sang@...el.com>
---
 arch/csky/include/asm/pgalloc.h |  2 +-
 arch/microblaze/mm/pgtable.c    |  2 +-
 arch/openrisc/mm/ioremap.c      |  2 +-
 arch/x86/mm/pgtable.c           |  2 +-
 include/asm-generic/pgalloc.h   | 14 ++++++++++++--
 5 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index 7d57e5d..56f8d25 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -29,7 +29,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	pte_t *pte;
 	unsigned long i;
 
-	pte = (pte_t *) __get_free_page(GFP_KERNEL);
+	pte = __pte_alloc_one_kernel(mm);
 	if (!pte)
 		return NULL;
 
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 9f73265..e96dd1b 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -245,7 +245,7 @@ unsigned long iopa(unsigned long addr)
 __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
 	if (mem_init_done)
-		return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		return __pte_alloc_one_kernel(mm);
 	else
 		return memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE,
 					      MEMBLOCK_LOW_LIMIT,
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index daae13a..3453acc 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -118,7 +118,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm)
 	pte_t *pte;
 
 	if (likely(mem_init_done)) {
-		pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
+		pte = __pte_alloc_one_kernel(mm);
 	} else {
 		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pte)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ea39670..20f3076 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -858,7 +858,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 	/* INVLPG to clear all paging-structure caches */
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
 
-	free_page((unsigned long)pte);
+	pte_free_kernel(NULL, pte);
 
 	return 1;
 }
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 8ce8d7c..cd8420f 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -18,7 +18,14 @@
  */
 static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm)
 {
-	return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL);
+	struct page *page;
+	gfp_t gfp = GFP_PGTABLE_KERNEL;
+
+	page = alloc_pages(gfp, 0);
+	if (!page)
+		return NULL;
+	page_set_pgtable(page);
+	return (pte_t *)page_address(page);
 }
 
 #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
@@ -41,7 +48,10 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
  */
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	free_page((unsigned long)pte);
+	struct page *page = virt_to_page(pte);
+
+	page_clear_pgtable(page);
+	__free_page(page);
 }
 
 /**
-- 
1.8.3.1