+ mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch added to mm-unstable branch

+ mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: mm/ksm: convert break_ksm() to use walk_page_range_vma()
has been added to the -mm mm-unstable branch.  Its filename is
     mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: David Hildenbrand <david@redhat.com>
Subject: mm/ksm: convert break_ksm() to use walk_page_range_vma()
Date: Fri, 30 Sep 2022 16:19:30 +0200

FOLL_MIGRATION exists only for the purpose of break_ksm(), and actually,
there is not even the need to wait for the migration to finish, we only
want to know if we're dealing with a KSM page.

Using follow_page() just to identify a KSM page overcomplicates GUP code. 
Let's use walk_page_range_vma() instead, because we don't actually care
about the page itself, we only need to know a single property -- no need
to even grab a reference on the page.

In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge
performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in
a performance degradation of ~4% (old: ~5010 MiB/s, new: ~4800 MiB/s).  I
don't think we particularly care for now.

Link: https://lkml.kernel.org/r/20220930141931.174362-7-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/ksm.c |   70 ++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 62 insertions(+), 8 deletions(-)

--- a/mm/ksm.c~mm-ksm-convert-break_ksm-to-use-walk_page_range_vma
+++ a/mm/ksm.c
@@ -39,6 +39,7 @@
 #include <linux/freezer.h>
 #include <linux/oom.h>
 #include <linux/numa.h>
+#include <linux/pagewalk.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -419,6 +420,60 @@ static inline bool ksm_test_exit(struct
 	return atomic_read(&mm->mm_users) == 0;
 }
 
+int break_ksm_pud_entry(pud_t *pud, unsigned long addr, unsigned long next,
+			struct mm_walk *walk)
+{
+	/* We only care about page tables to walk to a single base page. */
+	if (pud_leaf(*pud) || !pud_present(*pud))
+		return 1;
+	return 0;
+}
+
+int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next,
+			struct mm_walk *walk)
+{
+	bool *ksm_page = walk->private;
+	struct page *page = NULL;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+
+	/* We only care about page tables to walk to a single base page. */
+	if (pmd_leaf(*pmd) || !pmd_present(*pmd))
+		return 1;
+
+	/*
+	 * We only lookup a single page (a) no need to iterate; and (b)
+	 * always return 1 to exit immediately and not iterate in the caller.
+	 */
+	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	ptent = *pte;
+
+	if (pte_none(ptent))
+		return 1;
+	if (!pte_present(ptent)) {
+		swp_entry_t entry = pte_to_swp_entry(ptent);
+
+		/*
+		 * We only care about migration of KSM pages. As KSM pages
+		 * remain KSM pages until freed, no need to wait here for
+		 * migration to end to identify such.
+		 */
+		if (is_migration_entry(entry))
+			page = pfn_swap_entry_to_page(entry);
+	} else {
+		page = vm_normal_page(walk->vma, addr, ptent);
+	}
+	if (page && PageKsm(page))
+		*ksm_page = true;
+	pte_unmap_unlock(pte, ptl);
+	return 1;
+}
+
+static const struct mm_walk_ops break_ksm_ops = {
+	.pud_entry = break_ksm_pud_entry,
+	.pmd_entry = break_ksm_pmd_entry,
+};
+
 /*
  * We use break_ksm to break COW on a ksm page by triggering unsharing,
  * such that the ksm page will get replaced by an exclusive anonymous page.
@@ -434,20 +489,19 @@ static inline bool ksm_test_exit(struct
  */
 static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page;
 	vm_fault_t ret = 0;
 
+	if (WARN_ON_ONCE(!IS_ALIGNED(addr, PAGE_SIZE)))
+		return -EINVAL;
+
 	do {
 		bool ksm_page = false;
 
 		cond_resched();
-		page = follow_page(vma, addr,
-				FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
-		if (IS_ERR_OR_NULL(page))
-			break;
-		if (PageKsm(page))
-			ksm_page = true;
-		put_page(page);
+		ret = walk_page_range_vma(vma, addr, addr + PAGE_SIZE,
+					  &break_ksm_ops, &ksm_page);
+		if (WARN_ON_ONCE(ret < 0))
+			return ret;
 
 		if (!ksm_page)
 			return 0;
_

Patches currently in -mm which might be from david@redhat.com are

selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch
mm-ksm-simplify-break_ksm-to-not-rely-on-vm_fault_write.patch
mm-remove-vm_fault_write.patch
mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare.patch
mm-pagewalk-add-walk_page_range_vma.patch
mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch
mm-gup-remove-foll_migration.patch

+ mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: mm/ksm: convert break_ksm() to use walk_page_range_vma()
has been added to the -mm mm-unstable branch.  Its filename is
     mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: David Hildenbrand <david@redhat.com>
Subject: mm/ksm: convert break_ksm() to use walk_page_range_vma()
Date: Fri, 21 Oct 2022 12:11:40 +0200

FOLL_MIGRATION exists only for the purpose of break_ksm(), and actually,
there is not even the need to wait for the migration to finish, we only
want to know if we're dealing with a KSM page.

Using follow_page() just to identify a KSM page overcomplicates GUP code. 
Let's use walk_page_range_vma() instead, because we don't actually care
about the page itself, we only need to know a single property -- no need
to even grab a reference.

So, get rid of follow_page() usage such that we can get rid of
FOLL_MIGRATION now and eventually be able to get rid of follow_page() in
the future.

In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge
performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in
a performance degradation of ~2% (old: ~5010 MiB/s, new: ~4900 MiB/s).  I
don't think we particularly care for now.

Interestingly, the benchmark reduction is due to the single callback. 
Adding a second callback (e.g., pud_entry()) reduces the benchmark by
another 100-200 MiB/s.

Link: https://lkml.kernel.org/r/20221021101141.84170-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/ksm.c |   49 +++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 39 insertions(+), 10 deletions(-)

--- a/mm/ksm.c~mm-ksm-convert-break_ksm-to-use-walk_page_range_vma
+++ a/mm/ksm.c
@@ -39,6 +39,7 @@
 #include <linux/freezer.h>
 #include <linux/oom.h>
 #include <linux/numa.h>
+#include <linux/pagewalk.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -419,6 +420,39 @@ static inline bool ksm_test_exit(struct
 	return atomic_read(&mm->mm_users) == 0;
 }
 
+static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next,
+			struct mm_walk *walk)
+{
+	struct page *page = NULL;
+	spinlock_t *ptl;
+	pte_t *pte;
+	int ret;
+
+	if (pmd_leaf(*pmd) || !pmd_present(*pmd))
+		return 0;
+
+	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (pte_present(*pte)) {
+		page = vm_normal_page(walk->vma, addr, *pte);
+	} else if (!pte_none(*pte)) {
+		swp_entry_t entry = pte_to_swp_entry(*pte);
+
+		/*
+		 * As KSM pages remain KSM pages until freed, no need to wait
+		 * here for migration to end.
+		 */
+		if (is_migration_entry(entry))
+			page = pfn_swap_entry_to_page(entry);
+	}
+	ret = page && PageKsm(page);
+	pte_unmap_unlock(pte, ptl);
+	return ret;
+}
+
+static const struct mm_walk_ops break_ksm_ops = {
+	.pmd_entry = break_ksm_pmd_entry,
+};
+
 /*
  * We use break_ksm to break COW on a ksm page by triggering unsharing,
  * such that the ksm page will get replaced by an exclusive anonymous page.
@@ -434,21 +468,16 @@ static inline bool ksm_test_exit(struct
  */
 static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page;
 	vm_fault_t ret = 0;
 
 	do {
-		bool ksm_page = false;
+		int ksm_page;
 
 		cond_resched();
-		page = follow_page(vma, addr,
-				FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
-		if (IS_ERR_OR_NULL(page))
-			break;
-		if (PageKsm(page))
-			ksm_page = true;
-		put_page(page);
-
+		ksm_page = walk_page_range_vma(vma, addr, addr + 1,
+					       &break_ksm_ops, NULL);
+		if (WARN_ON_ONCE(ksm_page < 0))
+			return ksm_page;
 		if (!ksm_page)
 			return 0;
 		ret = handle_mm_fault(vma, addr,
_

Patches currently in -mm which might be from david@redhat.com are

selftests-vm-anon_cow-test-cow-handling-of-anonymous-memory.patch
selftests-vm-factor-out-pagemap_is_populated-into-vm_util.patch
selftests-vm-anon_cow-thp-tests.patch
selftests-vm-anon_cow-hugetlb-tests.patch
selftests-vm-anon_cow-add-liburing-test-cases.patch
mm-gup_test-start-stop-read-functionality-for-pin-longterm-test.patch
mm-gup_test-start-stop-read-functionality-for-pin-longterm-test-fix.patch
selftests-vm-anon_cow-add-r-o-longterm-tests-via-gup_test.patch
selftests-vm-add-ksm-unmerge-tests.patch
mm-pagewalk-dont-trigger-test_walk-in-walk_page_vma.patch
selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch
mm-ksm-simplify-break_ksm-to-not-rely-on-vm_fault_write.patch
mm-remove-vm_fault_write.patch
mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare.patch
mm-pagewalk-add-walk_page_range_vma.patch
mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch
mm-gup-remove-foll_migration.patch