linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Nico Pache <npache@redhat.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: aarcange@redhat.com, akpm@linux-foundation.org,
	anshuman.khandual@arm.com, apopple@nvidia.com, baohua@kernel.org,
	baolin.wang@linux.alibaba.com, byungchul@sk.com,
	catalin.marinas@arm.com, cl@gentwo.org, corbet@lwn.net,
	dave.hansen@linux.intel.com, david@kernel.org, dev.jain@arm.com,
	gourry@gourry.net, hannes@cmpxchg.org, hughd@google.com,
	jackmanb@google.com, jack@suse.cz, jannh@google.com,
	jglisse@google.com, joshua.hahnjy@gmail.com, kas@kernel.org,
	lance.yang@linux.dev, Liam.Howlett@oracle.com,
	lorenzo.stoakes@oracle.com, mathieu.desnoyers@efficios.com,
	matthew.brost@intel.com, mhiramat@kernel.org, mhocko@suse.com,
	npache@redhat.com, peterx@redhat.com, pfalcato@suse.de,
	rakie.kim@sk.com, raquini@redhat.com, rdunlap@infradead.org,
	richard.weiyang@gmail.com, rientjes@google.com,
	rostedt@goodmis.org, rppt@kernel.org, ryan.roberts@arm.com,
	shivankg@amd.com, sunnanyong@huawei.com, surenb@google.com,
	thomas.hellstrom@linux.intel.com, tiwai@suse.de,
	usamaarif642@gmail.com, vbabka@suse.cz, vishal.moola@gmail.com,
	wangkefeng.wang@huawei.com, will@kernel.org, willy@infradead.org,
	yang@os.amperecomputing.com, ying.huang@linux.alibaba.com,
	ziy@nvidia.com, zokeefe@google.com
Subject: [PATCH mm-unstable v1 5/5] mm/khugepaged: unify khugepaged and madv_collapse with collapse_single_pmd()
Date: Wed, 11 Feb 2026 19:23:29 -0700	[thread overview]
Message-ID: <20260212022329.18892-2-npache@redhat.com> (raw)
In-Reply-To: <20260212022329.18892-1-npache@redhat.com>

The khugepaged daemon and madvise_collapse have two different
implementations that do almost the same thing.

Create collapse_single_pmd to increase code reuse and create an entry
point to these two users.

Refactor madvise_collapse and collapse_scan_mm_slot to use the new
collapse_single_pmd function. This introduces a minor behavioral change
that is most likely an undiscovered bug. The current implementation of
khugepaged tests collapse_test_exit_or_disable before calling
collapse_pte_mapped_thp, but we weren't doing it in the madvise_collapse
case. By unifying these two callers madvise_collapse now also performs
this check. We also modify the return value to be SCAN_ANY_PROCESS which
properly indicates that this process is no longer valid to operate on.

We also guard the khugepaged_pages_collapsed variable to ensure its only
incremented for khugepaged.

Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Nico Pache <npache@redhat.com>
---
 mm/khugepaged.c | 121 ++++++++++++++++++++++++++----------------------
 1 file changed, 66 insertions(+), 55 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index fa41480f6948..0839a781bedd 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2395,6 +2395,62 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm, unsigned long a
 	return result;
 }
 
+/*
+ * Try to collapse a single PMD starting at a PMD aligned addr, and return
+ * the results.
+ */
+static enum scan_result collapse_single_pmd(unsigned long addr,
+		struct vm_area_struct *vma, bool *mmap_locked,
+		struct collapse_control *cc)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	enum scan_result result;
+	struct file *file;
+	pgoff_t pgoff;
+
+	if (vma_is_anonymous(vma)) {
+		result = collapse_scan_pmd(mm, vma, addr, mmap_locked, cc);
+		goto end;
+	}
+
+	file = get_file(vma->vm_file);
+	pgoff = linear_page_index(vma, addr);
+
+	mmap_read_unlock(mm);
+	*mmap_locked = false;
+	result = collapse_scan_file(mm, addr, file, pgoff, cc);
+
+	if (!cc->is_khugepaged && result == SCAN_PAGE_DIRTY_OR_WRITEBACK &&
+	    mapping_can_writeback(file->f_mapping)) {
+		const loff_t lstart = (loff_t)pgoff << PAGE_SHIFT;
+		const loff_t lend = lstart + HPAGE_PMD_SIZE - 1;
+
+		filemap_write_and_wait_range(file->f_mapping, lstart, lend);
+	}
+	fput(file);
+
+	if (result != SCAN_PTE_MAPPED_HUGEPAGE)
+		goto end;
+
+	mmap_read_lock(mm);
+	*mmap_locked = true;
+	if (collapse_test_exit_or_disable(mm)) {
+		mmap_read_unlock(mm);
+		*mmap_locked = false;
+		return SCAN_ANY_PROCESS;
+	}
+	result = try_collapse_pte_mapped_thp(mm, addr, !cc->is_khugepaged);
+	if (result == SCAN_PMD_MAPPED)
+		result = SCAN_SUCCEED;
+	mmap_read_unlock(mm);
+	*mmap_locked = false;
+
+end:
+	if (cc->is_khugepaged && result == SCAN_SUCCEED)
+		++khugepaged_pages_collapsed;
+	return result;
+}
+
 static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *result,
 					    struct collapse_control *cc)
 	__releases(&khugepaged_mm_lock)
@@ -2466,34 +2522,9 @@ static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *
 			VM_BUG_ON(khugepaged_scan.address < hstart ||
 				  khugepaged_scan.address + HPAGE_PMD_SIZE >
 				  hend);
-			if (!vma_is_anonymous(vma)) {
-				struct file *file = get_file(vma->vm_file);
-				pgoff_t pgoff = linear_page_index(vma,
-						khugepaged_scan.address);
-
-				mmap_read_unlock(mm);
-				mmap_locked = false;
-				*result = collapse_scan_file(mm,
-					khugepaged_scan.address, file, pgoff, cc);
-				fput(file);
-				if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
-					mmap_read_lock(mm);
-					if (collapse_test_exit_or_disable(mm))
-						goto breakouterloop;
-					*result = try_collapse_pte_mapped_thp(mm,
-						khugepaged_scan.address, false);
-					if (*result == SCAN_PMD_MAPPED)
-						*result = SCAN_SUCCEED;
-					mmap_read_unlock(mm);
-				}
-			} else {
-				*result = collapse_scan_pmd(mm, vma,
-					khugepaged_scan.address, &mmap_locked, cc);
-			}
-
-			if (*result == SCAN_SUCCEED)
-				++khugepaged_pages_collapsed;
 
+			*result = collapse_single_pmd(khugepaged_scan.address,
+						      vma, &mmap_locked, cc);
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
 			progress += HPAGE_PMD_NR;
@@ -2799,6 +2830,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 			cond_resched();
 			mmap_read_lock(mm);
 			mmap_locked = true;
+			*lock_dropped = true;
 			result = hugepage_vma_revalidate(mm, addr, false, &vma,
 							 cc);
 			if (result  != SCAN_SUCCEED) {
@@ -2809,46 +2841,25 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 			hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
 		}
 		mmap_assert_locked(mm);
-		if (!vma_is_anonymous(vma)) {
-			struct file *file = get_file(vma->vm_file);
-			pgoff_t pgoff = linear_page_index(vma, addr);
 
-			mmap_read_unlock(mm);
-			mmap_locked = false;
-			*lock_dropped = true;
-			result = collapse_scan_file(mm, addr, file, pgoff, cc);
-
-			if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !triggered_wb &&
-			    mapping_can_writeback(file->f_mapping)) {
-				loff_t lstart = (loff_t)pgoff << PAGE_SHIFT;
-				loff_t lend = lstart + HPAGE_PMD_SIZE - 1;
+		result = collapse_single_pmd(addr, vma, &mmap_locked, cc);
 
-				filemap_write_and_wait_range(file->f_mapping, lstart, lend);
-				triggered_wb = true;
-				fput(file);
-				goto retry;
-			}
-			fput(file);
-		} else {
-			result = collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc);
-		}
 		if (!mmap_locked)
 			*lock_dropped = true;
 
-handle_result:
+		if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !triggered_wb) {
+			triggered_wb = true;
+			goto retry;
+		}
+
 		switch (result) {
 		case SCAN_SUCCEED:
 		case SCAN_PMD_MAPPED:
 			++thps;
 			break;
-		case SCAN_PTE_MAPPED_HUGEPAGE:
-			BUG_ON(mmap_locked);
-			mmap_read_lock(mm);
-			result = try_collapse_pte_mapped_thp(mm, addr, true);
-			mmap_read_unlock(mm);
-			goto handle_result;
 		/* Whitelisted set of results where continuing OK */
 		case SCAN_NO_PTE_TABLE:
+		case SCAN_PTE_MAPPED_HUGEPAGE:
 		case SCAN_PTE_NON_PRESENT:
 		case SCAN_PTE_UFFD_WP:
 		case SCAN_LACK_REFERENCED_PAGE:
-- 
2.53.0



  reply	other threads:[~2026-02-12  2:24 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-12  2:18 [PATCH mm-unstable v1 0/5] mm: khugepaged cleanups and mTHP prerequisites Nico Pache
2026-02-12  2:18 ` [PATCH mm-unstable v1 1/5] mm: consolidate anonymous folio PTE mapping into helpers Nico Pache
2026-02-12 14:38   ` Pedro Falcato
2026-02-12 15:55   ` Joshua Hahn
2026-02-12 19:33     ` Nico Pache
2026-02-12 16:09   ` Zi Yan
2026-02-12 19:45     ` Nico Pache
2026-02-12 20:06       ` Zi Yan
2026-02-12 20:13         ` David Hildenbrand (Arm)
2026-02-12  2:18 ` [PATCH mm-unstable v1 2/5] mm: introduce is_pmd_order helper Nico Pache
2026-02-12 14:40   ` Pedro Falcato
2026-02-12 16:11   ` Zi Yan
2026-02-12 19:45   ` David Hildenbrand (Arm)
2026-02-13  3:51   ` Barry Song
2026-02-14  7:24   ` Lance Yang
2026-02-20 10:38   ` Dev Jain
2026-02-20 10:42     ` David Hildenbrand (Arm)
2026-02-12  2:18 ` [PATCH mm-unstable v1 3/5] mm/khugepaged: define COLLAPSE_MAX_PTES_LIMIT as HPAGE_PMD_NR - 1 Nico Pache
2026-02-12  6:56   ` Vernon Yang
2026-02-12 14:45   ` Pedro Falcato
2026-02-12 16:21   ` Zi Yan
2026-02-12 19:51   ` David Hildenbrand (Arm)
2026-02-12  2:23 ` [PATCH mm-unstable v1 4/5] mm/khugepaged: rename hpage_collapse_* to collapse_* Nico Pache
2026-02-12  2:23   ` Nico Pache [this message]
2026-02-12 19:52   ` David Hildenbrand (Arm)
2026-02-12  2:25 ` [PATCH mm-unstable v1 5/5] mm/khugepaged: unify khugepaged and madv_collapse with collapse_single_pmd() Nico Pache
2026-02-12 15:33   ` Pedro Falcato
2026-02-12 17:34   ` Zi Yan
2026-02-12 20:03   ` David Hildenbrand (Arm)
2026-02-12 20:26     ` Nico Pache
2026-02-14  8:24       ` Lance Yang
2026-02-12  2:26 ` [PATCH mm-unstable v1 0/5] mm: khugepaged cleanups and mTHP prerequisites Nico Pache

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=20260212022329.18892-2-npache@redhat.com \
    --to=npache@redhat.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=anshuman.khandual@arm.com \
    --cc=apopple@nvidia.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=byungchul@sk.com \
    --cc=catalin.marinas@arm.com \
    --cc=cl@gentwo.org \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=gourry@gourry.net \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=jack@suse.cz \
    --cc=jackmanb@google.com \
    --cc=jannh@google.com \
    --cc=jglisse@google.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=kas@kernel.org \
    --cc=lance.yang@linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=matthew.brost@intel.com \
    --cc=mhiramat@kernel.org \
    --cc=mhocko@suse.com \
    --cc=peterx@redhat.com \
    --cc=pfalcato@suse.de \
    --cc=rakie.kim@sk.com \
    --cc=raquini@redhat.com \
    --cc=rdunlap@infradead.org \
    --cc=richard.weiyang@gmail.com \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=shivankg@amd.com \
    --cc=sunnanyong@huawei.com \
    --cc=surenb@google.com \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tiwai@suse.de \
    --cc=usamaarif642@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=vishal.moola@gmail.com \
    --cc=wangkefeng.wang@huawei.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=yang@os.amperecomputing.com \
    --cc=ying.huang@linux.alibaba.com \
    --cc=ziy@nvidia.com \
    --cc=zokeefe@google.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
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