LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Steven Price <steven.price@arm.com>
To: linux-mm@kvack.org
Cc: "Steven Price" <steven.price@arm.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Ard Biesheuvel" <ard.biesheuvel@linaro.org>,
	"Arnd Bergmann" <arnd@arndb.de>, "Borislav Petkov" <bp@alien8.de>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"James Morse" <james.morse@arm.com>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Will Deacon" <will@kernel.org>,
	x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	"Mark Rutland" <Mark.Rutland@arm.com>,
	"Liang, Kan" <kan.liang@linux.intel.com>,
	"Andrew Morton" <akpm@linux-foundation.org>
Subject: [PATCH v10 11/22] mm: pagewalk: Add p4d_entry() and pgd_entry()
Date: Wed, 31 Jul 2019 16:45:52 +0100
Message-ID: <20190731154603.41797-12-steven.price@arm.com> (raw)
In-Reply-To: <20190731154603.41797-1-steven.price@arm.com>

pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410
("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were
no users. We're about to add users so reintroduce them, along with
p4d_entry() as we now have 5 levels of tables.

Note that commit a00cc7d9dd93d66a ("mm, x86: add support for
PUD-sized transparent hugepages") already re-added pud_entry() but with
different semantics to the other callbacks. Since there have never
been upstream users of this, revert the semantics back to match the
other callbacks. This means pud_entry() is called for all entries, not
just transparent huge pages.

Signed-off-by: Steven Price <steven.price@arm.com>
---
 include/linux/mm.h | 18 ++++++++++++------
 mm/pagewalk.c      | 27 ++++++++++++++++-----------
 2 files changed, 28 insertions(+), 17 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0334ca97c584..0a1e83c4e267 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1432,15 +1432,14 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 
 /**
  * mm_walk - callbacks for walk_page_range
- * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
- *	       this handler should only handle pud_trans_huge() puds.
- *	       the pmd_entry or pte_entry callbacks will be used for
- *	       regular PUDs.
- * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
+ * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
+ * @p4d_entry: if set, called for each non-empty P4D entry
+ * @pud_entry: if set, called for each non-empty PUD entry
+ * @pmd_entry: if set, called for each non-empty PMD entry
  *	       this handler is required to be able to handle
  *	       pmd_trans_huge() pmds.  They may simply choose to
  *	       split_huge_page() instead of handling it explicitly.
- * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
+ * @pte_entry: if set, called for each non-empty PTE (lowest-level) entry
  * @pte_hole: if set, called for each hole at all levels
  * @hugetlb_entry: if set, called for each hugetlb entry
  * @test_walk: caller specific callback function to determine whether
@@ -1453,8 +1452,15 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  * @private:   private data for callbacks' usage
  *
  * (see the comment on walk_page_range() for more details)
+ *
+ * p?d_entry callbacks are called even if those levels are folded on a partial
+ * architecture/configuration.
  */
 struct mm_walk {
+	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
+	int (*p4d_entry)(p4d_t *p4d, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
 	int (*pud_entry)(pud_t *pud, unsigned long addr,
 			 unsigned long next, struct mm_walk *walk);
 	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index c3084ff2569d..98373a9f88b8 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -90,15 +90,9 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 		}
 
 		if (walk->pud_entry) {
-			spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
-
-			if (ptl) {
-				err = walk->pud_entry(pud, addr, next, walk);
-				spin_unlock(ptl);
-				if (err)
-					break;
-				continue;
-			}
+			err = walk->pud_entry(pud, addr, next, walk);
+			if (err)
+				break;
 		}
 
 		split_huge_pud(walk->vma, pud, addr);
@@ -131,7 +125,12 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
-		if (walk->pmd_entry || walk->pte_entry)
+		if (walk->p4d_entry) {
+			err = walk->p4d_entry(p4d, addr, next, walk);
+			if (err)
+				break;
+		}
+		if (walk->pud_entry || walk->pmd_entry || walk->pte_entry)
 			err = walk_pud_range(p4d, addr, next, walk);
 		if (err)
 			break;
@@ -157,7 +156,13 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
-		if (walk->pmd_entry || walk->pte_entry)
+		if (walk->pgd_entry) {
+			err = walk->pgd_entry(pgd, addr, next, walk);
+			if (err)
+				break;
+		}
+		if (walk->p4d_entry || walk->pud_entry || walk->pmd_entry ||
+				walk->pte_entry)
 			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;
-- 
2.20.1


  parent reply index

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-31 15:45 [PATCH v10 00/22] Generic page walk and ptdump Steven Price
2019-07-31 15:45 ` [PATCH v10 01/22] mm: Add generic p?d_leaf() macros Steven Price
2019-07-31 15:45 ` [PATCH v10 02/22] arc: mm: Add p?d_leaf() definitions Steven Price
2019-07-31 15:45 ` [PATCH v10 03/22] arm: " Steven Price
2019-07-31 15:45 ` [PATCH v10 04/22] arm64: " Steven Price
2019-07-31 15:45 ` [PATCH v10 05/22] mips: " Steven Price
2019-07-31 18:35   ` Paul Burton
2019-07-31 15:45 ` [PATCH v10 06/22] powerpc: " Steven Price
2019-07-31 15:45 ` [PATCH v10 07/22] riscv: " Steven Price
2019-07-31 15:45 ` [PATCH v10 08/22] s390: " Steven Price
2019-07-31 15:45 ` [PATCH v10 09/22] sparc: " Steven Price
2019-07-31 15:45 ` [PATCH v10 10/22] x86: " Steven Price
2019-07-31 15:45 ` Steven Price [this message]
2019-07-31 15:45 ` [PATCH v10 12/22] mm: pagewalk: Allow walking without vma Steven Price
2019-07-31 15:45 ` [PATCH v10 13/22] mm: pagewalk: Add test_p?d callbacks Steven Price
2019-07-31 15:45 ` [PATCH v10 14/22] mm: pagewalk: Add 'depth' parameter to pte_hole Steven Price
2019-07-31 15:45 ` [PATCH v10 15/22] x86: mm: Point to struct seq_file from struct pg_state Steven Price
2019-07-31 15:45 ` [PATCH v10 16/22] x86: mm+efi: Convert ptdump_walk_pgd_level() to take a mm_struct Steven Price
2019-07-31 15:45 ` [PATCH v10 17/22] x86: mm: Convert ptdump_walk_pgd_level_debugfs() to take an mm_struct Steven Price
2019-07-31 15:45 ` [PATCH v10 18/22] x86: mm: Convert ptdump_walk_pgd_level_core() " Steven Price
2019-07-31 15:46 ` [PATCH v10 19/22] mm: Add generic ptdump Steven Price
2019-07-31 15:46 ` [PATCH v10 20/22] x86: mm: Convert dump_pagetables to use walk_page_range Steven Price
2019-08-06 23:58   ` Andrew Morton
2019-08-07 12:58     ` Steven Price
2019-08-07 20:16       ` Andrew Morton
2019-07-31 15:46 ` [PATCH v10 21/22] arm64: mm: Convert mm/dump.c to use walk_page_range() Steven Price
2019-07-31 15:46 ` [PATCH v10 22/22] arm64: mm: Display non-present entries in ptdump Steven Price

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=20190731154603.41797-12-steven.price@arm.com \
    --to=steven.price@arm.com \
    --cc=Mark.Rutland@arm.com \
    --cc=akpm@linux-foundation.org \
    --cc=ard.biesheuvel@linaro.org \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jglisse@redhat.com \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    --cc=x86@kernel.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

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

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


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