LinuxPPC-Dev Archive on lore.kernel.org
 help / color / Atom feed
From: Christophe Leroy <christophe.leroy@csgroup.eu>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Paul Mackerras <paulus@samba.org>,
	Michael Ellerman <mpe@ellerman.id.au>,
	 Steven Price <steven.price@arm.com>,
	akpm@linux-foundation.org, dja@axtens.net
Cc: linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	Oliver O'Halloran <oohall@gmail.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v2 1/4] mm: pagewalk: Fix walk for hugepage tables
Date: Mon, 19 Apr 2021 10:47:25 +0000 (UTC)
Message-ID: <db6981c69f96a8c9c6dcf688b7f485e15993ddef.1618828806.git.christophe.leroy@csgroup.eu> (raw)
In-Reply-To: <cover.1618828806.git.christophe.leroy@csgroup.eu>

Pagewalk ignores hugepd entries and walk down the tables
as if it was traditionnal entries, leading to crazy result.

Add walk_hugepd_range() and use it to walk hugepage tables.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v2:
- Add a guard for NULL ops->pte_entry
- Take mm->page_table_lock when walking hugepage table, as suggested by follow_huge_pd()
---
 mm/pagewalk.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 5 deletions(-)

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index e81640d9f177..9b3db11a4d1d 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -58,6 +58,45 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return err;
 }
 
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
+			     unsigned long end, struct mm_walk *walk, int pdshift)
+{
+	int err = 0;
+	const struct mm_walk_ops *ops = walk->ops;
+	int shift = hugepd_shift(*phpd);
+	int page_size = 1 << shift;
+
+	if (!ops->pte_entry)
+		return 0;
+
+	if (addr & (page_size - 1))
+		return 0;
+
+	for (;;) {
+		pte_t *pte;
+
+		spin_lock(&walk->mm->page_table_lock);
+		pte = hugepte_offset(*phpd, addr, pdshift);
+		err = ops->pte_entry(pte, addr, addr + page_size, walk);
+		spin_unlock(&walk->mm->page_table_lock);
+
+		if (err)
+			break;
+		if (addr >= end - page_size)
+			break;
+		addr += page_size;
+	}
+	return err;
+}
+#else
+static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
+			     unsigned long end, struct mm_walk *walk, int pdshift)
+{
+	return 0;
+}
+#endif
+
 static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
@@ -108,7 +147,10 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 				goto again;
 		}
 
-		err = walk_pte_range(pmd, addr, next, walk);
+		if (is_hugepd(__hugepd(pmd_val(*pmd))))
+			err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT);
+		else
+			err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
 	} while (pmd++, addr = next, addr != end);
@@ -157,7 +199,10 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 		if (pud_none(*pud))
 			goto again;
 
-		err = walk_pmd_range(pud, addr, next, walk);
+		if (is_hugepd(__hugepd(pud_val(*pud))))
+			err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT);
+		else
+			err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
 	} while (pud++, addr = next, addr != end);
@@ -189,7 +234,9 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 			if (err)
 				break;
 		}
-		if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
+		if (is_hugepd(__hugepd(p4d_val(*p4d))))
+			err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT);
+		else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
 			err = walk_pud_range(p4d, addr, next, walk);
 		if (err)
 			break;
@@ -224,8 +271,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 			if (err)
 				break;
 		}
-		if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
-		    ops->pte_entry)
+		if (is_hugepd(__hugepd(pgd_val(*pgd))))
+			err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT);
+		else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry)
 			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;
-- 
2.25.0


  reply index

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-19 10:47 [PATCH v2 0/4] Convert powerpc to GENERIC_PTDUMP Christophe Leroy
2021-04-19 10:47 ` Christophe Leroy [this message]
2021-04-19 14:07   ` [PATCH v2 1/4] mm: pagewalk: Fix walk for hugepage tables Steven Price
2021-04-19 10:47 ` [PATCH v2 2/4] powerpc/mm: Leave a gap between early allocated IO areas Christophe Leroy
2021-04-19 10:47 ` [PATCH v2 3/4] powerpc/mm: Properly coalesce pages in ptdump Christophe Leroy
2021-04-19 10:47 ` [PATCH v2 4/4] powerpc/mm: Convert powerpc to GENERIC_PTDUMP Christophe Leroy

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=db6981c69f96a8c9c6dcf688b7f485e15993ddef.1618828806.git.christophe.leroy@csgroup.eu \
    --to=christophe.leroy@csgroup.eu \
    --cc=akpm@linux-foundation.org \
    --cc=benh@kernel.crashing.org \
    --cc=dja@axtens.net \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=oohall@gmail.com \
    --cc=paulus@samba.org \
    --cc=steven.price@arm.com \
    /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

LinuxPPC-Dev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linuxppc-dev/0 linuxppc-dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linuxppc-dev linuxppc-dev/ https://lore.kernel.org/linuxppc-dev \
		linuxppc-dev@lists.ozlabs.org linuxppc-dev@ozlabs.org
	public-inbox-index linuxppc-dev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.ozlabs.lists.linuxppc-dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git