linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Baolin Wang <baolin.wang@linux.alibaba.com>
To: akpm@linux-foundation.org
Cc: rppt@linux.ibm.com, willy@infradead.org,
	baolin.wang@linux.alibaba.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: [RFC PATCH v2 2/3] mm: Add PUD level pagetable account
Date: Wed, 22 Jun 2022 16:58:53 +0800	[thread overview]
Message-ID: <f7b2a6f6f5dfecbcac07fa3e187f10860c3a39ee.1655887440.git.baolin.wang@linux.alibaba.com> (raw)
In-Reply-To: <cover.1655887440.git.baolin.wang@linux.alibaba.com>
In-Reply-To: <cover.1655887440.git.baolin.wang@linux.alibaba.com>

Now the PUD level ptes are always protected by mm->page_table_lock,
which means no split pagetable lock needed. So the generic PUD level
pagetable pages allocation will not call pgtable_pte_page_ctor/dtor(),
that means we will miss to account PUD level pagetable pages.

Adding pagetable account by calling pgtable_set_and_inc() or
pgtable_clear_and_dec() when allocating or freeing PUD level pagetable
pages to help to get an accurate pagetable accounting.

Moreover this patch will also mark the PUD level pagetable with PG_table
flag, which will help to do sanity validation in unpoison_memory() and
get more accurate pagetable accounting by /proc/kpageflags interface.

Meanwhile converting the architectures with using generic PUD pagatable
allocation to add corresponding pgtable_set_and_inc() or pgtable_clear_and_dec()
to account PUD level pagetable.

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
 arch/arm64/include/asm/tlb.h         |  5 ++++-
 arch/loongarch/include/asm/pgalloc.h | 11 ++++++++---
 arch/mips/include/asm/pgalloc.h      | 11 ++++++++---
 arch/s390/include/asm/tlb.h          |  1 +
 arch/x86/mm/pgtable.c                |  5 ++++-
 include/asm-generic/pgalloc.h        | 12 ++++++++++--
 6 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index c995d1f..47e0623 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -94,7 +94,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_remove_table(tlb, virt_to_page(pudp));
+	struct page *page = virt_to_page(pudp);
+
+	pgtable_clear_and_dec(page);
+	tlb_remove_table(tlb, page);
 }
 #endif
 
diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index b0a57b2..50a896f 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -89,10 +89,15 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	pud_t *pud;
+	struct page *pg;
+
+	pg = alloc_pages(GFP_KERNEL & ~__GFP_HIGHMEM, PUD_ORDER);
+	if (!pg)
+		return NULL;
 
-	pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER);
-	if (pud)
-		pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table);
+	pgtable_set_and_inc(pg);
+	pud = (pud_t *)page_address(pg);
+	pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table);
 	return pud;
 }
 
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index 867e9c3..0950f5f 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -89,11 +89,16 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
+	struct page *pg;
 	pud_t *pud;
 
-	pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER);
-	if (pud)
-		pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table);
+	pg = alloc_pages(GFP_KERNEL & ~__GFP_HIGHMEM, PUD_ORDER);
+	if (!pg)
+		return NULL;
+
+	pgtable_set_and_inc(pg);
+	pud = (pud_t *)page_address(pg);
+	pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table);
 	return pud;
 }
 
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index fe6407f..45f9541 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -125,6 +125,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 {
 	if (mm_pud_folded(tlb->mm))
 		return;
+	pgtable_clear_and_dec(virt_to_page(pud));
 	tlb->mm->context.flush_mm = 1;
 	tlb->freed_tables = 1;
 	tlb->cleared_p4ds = 1;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a932d77..a8ab3f9 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -76,8 +76,11 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
+	struct page *page = virt_to_page(pud);
+
+	pgtable_clear_and_dec(page);
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_page(pud));
+	paravirt_tlb_remove_table(tlb, page);
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 977bea1..328a714 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -149,11 +149,16 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 
 static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
+	struct page *page;
 	gfp_t gfp = GFP_PGTABLE_USER;
 
 	if (mm == &init_mm)
 		gfp = GFP_PGTABLE_KERNEL;
-	return (pud_t *)get_zeroed_page(gfp);
+	page = alloc_pages((gfp | __GFP_ZERO) & ~__GFP_HIGHMEM, 0);
+	if (!page)
+		return NULL;
+	pgtable_set_and_inc(page);
+	return (pud_t *)page_address(page);
 }
 
 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE
@@ -174,8 +179,11 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 
 static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
 {
+	struct page *page = virt_to_page(pud);
+
 	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	free_page((unsigned long)pud);
+	pgtable_clear_and_dec(page);
+	__free_page(page);
 }
 
 #ifndef __HAVE_ARCH_PUD_FREE
-- 
1.8.3.1



  parent reply	other threads:[~2022-06-22  8:59 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-22  8:58 [RFC PATCH v2 0/3] Add PUD and kernel PTE " Baolin Wang
2022-06-22  8:58 ` [RFC PATCH v2 1/3] mm: Factor out the pagetable pages account into new helper function Baolin Wang
2022-06-23 16:07   ` Matthew Wilcox
2022-06-24  8:41     ` Baolin Wang
2022-06-22  8:58 ` Baolin Wang [this message]
2022-06-22 14:38   ` [RFC PATCH v2 2/3] mm: Add PUD level pagetable account Mike Rapoport
2022-06-23  3:32     ` Baolin Wang
2022-06-23 13:28     ` Matthew Wilcox
2022-06-24  8:52       ` Baolin Wang
2022-06-22  8:58 ` [RFC PATCH v2 3/3] mm: Add kernel PTE level pagetable pages account Baolin Wang
2022-06-22 14:44   ` Mike Rapoport
2022-06-23  3:34     ` Baolin Wang
2022-07-12  6:08   ` [mm] 0bf5cdf08f: BUG:Bad_page_state_in_process kernel test robot
2022-07-13  9:17     ` Baolin Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=f7b2a6f6f5dfecbcac07fa3e187f10860c3a39ee.1655887440.git.baolin.wang@linux.alibaba.com \
    --to=baolin.wang@linux.alibaba.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=rppt@linux.ibm.com \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox