From: Nico Pache <npache@redhat.com>
To: linux-mm@kvack.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org
Cc: david@redhat.com, ziy@nvidia.com, baolin.wang@linux.alibaba.com,
lorenzo.stoakes@oracle.com, Liam.Howlett@oracle.com,
ryan.roberts@arm.com, dev.jain@arm.com, corbet@lwn.net,
rostedt@goodmis.org, mhiramat@kernel.org,
mathieu.desnoyers@efficios.com, akpm@linux-foundation.org,
baohua@kernel.org, willy@infradead.org, peterx@redhat.com,
wangkefeng.wang@huawei.com, usamaarif642@gmail.com,
sunnanyong@huawei.com, vishal.moola@gmail.com,
thomas.hellstrom@linux.intel.com, yang@os.amperecomputing.com,
kas@kernel.org, aarcange@redhat.com, raquini@redhat.com,
anshuman.khandual@arm.com, catalin.marinas@arm.com,
tiwai@suse.de, will@kernel.org, dave.hansen@linux.intel.com,
jack@suse.cz, cl@gentwo.org, jglisse@google.com,
surenb@google.com, zokeefe@google.com, hannes@cmpxchg.org,
rientjes@google.com, mhocko@suse.com, rdunlap@infradead.org,
hughd@google.com, richard.weiyang@gmail.com,
lance.yang@linux.dev, vbabka@suse.cz, rppt@kernel.org,
jannh@google.com, pfalcato@suse.de
Subject: [PATCH v11 02/15] introduce collapse_single_pmd to unify khugepaged and madvise_collapse
Date: Thu, 11 Sep 2025 21:27:57 -0600 [thread overview]
Message-ID: <20250912032810.197475-3-npache@redhat.com> (raw)
In-Reply-To: <20250912032810.197475-1-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properly indicates that this process is no longer valid to operate on.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: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Nico Pache <npache@redhat.com>
---
mm/khugepaged.c | 97 ++++++++++++++++++++++++++-----------------------
1 file changed, 52 insertions(+), 45 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 40fa6e0a6b2d..63d2ba4b2b6d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2370,6 +2370,53 @@ static int collapse_scan_file(struct mm_struct *mm, unsigned long addr,
return result;
}
+/*
+ * Try to collapse a single PMD starting at a PMD aligned addr, and return
+ * the results.
+ */
+static int 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;
+ int 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);
+ 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 = 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, int *result,
struct collapse_control *cc)
__releases(&khugepaged_mm_lock)
@@ -2443,34 +2490,9 @@ static unsigned int collapse_scan_mm_slot(unsigned int pages, int *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 = 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;
@@ -2786,34 +2808,19 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
mmap_assert_locked(mm);
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
- 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;
- result = collapse_scan_file(mm, addr, file, pgoff, cc);
- fput(file);
- } else {
- result = collapse_scan_pmd(mm, vma, addr,
- &mmap_locked, cc);
- }
+ result = collapse_single_pmd(addr, vma, &mmap_locked, cc);
+
if (!mmap_locked)
*lock_dropped = true;
-handle_result:
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 = collapse_pte_mapped_thp(mm, addr, true);
- mmap_read_unlock(mm);
- goto handle_result;
/* Whitelisted set of results where continuing OK */
+ case SCAN_PTE_MAPPED_HUGEPAGE:
case SCAN_PMD_NULL:
case SCAN_PTE_NON_PRESENT:
case SCAN_PTE_UFFD_WP:
--
2.51.0
next prev parent reply other threads:[~2025-09-12 3:29 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-12 3:27 [PATCH v11 00/15] khugepaged: mTHP support Nico Pache
2025-09-12 3:27 ` [PATCH v11 01/15] khugepaged: rename hpage_collapse_* to collapse_* Nico Pache
2025-09-12 3:27 ` Nico Pache [this message]
2025-09-12 3:27 ` [PATCH v11 03/15] khugepaged: generalize hugepage_vma_revalidate for mTHP support Nico Pache
2025-09-12 3:27 ` [PATCH v11 04/15] khugepaged: generalize alloc_charge_folio() Nico Pache
2025-09-12 3:28 ` [PATCH v11 05/15] khugepaged: generalize __collapse_huge_page_* for mTHP support Nico Pache
2025-09-12 3:28 ` [PATCH v11 06/15] khugepaged: introduce collapse_max_ptes_none helper function Nico Pache
2025-09-12 13:35 ` Lorenzo Stoakes
2025-09-12 23:26 ` Nico Pache
2025-09-15 10:30 ` Lorenzo Stoakes
2025-09-12 3:28 ` [PATCH v11 07/15] khugepaged: generalize collapse_huge_page for mTHP collapse Nico Pache
2025-09-12 3:28 ` [PATCH v11 08/15] khugepaged: skip collapsing mTHP to smaller orders Nico Pache
2025-09-12 3:28 ` [PATCH v11 09/15] khugepaged: add per-order mTHP collapse failure statistics Nico Pache
2025-09-12 9:35 ` Baolin Wang
2025-09-12 3:28 ` [PATCH v11 10/15] khugepaged: improve tracepoints for mTHP orders Nico Pache
2025-09-12 3:28 ` [PATCH v11 11/15] khugepaged: introduce collapse_allowable_orders helper function Nico Pache
2025-09-12 9:24 ` Baolin Wang
2025-09-12 3:28 ` [PATCH v11 12/15] khugepaged: Introduce mTHP collapse support Nico Pache
2025-09-12 3:28 ` [PATCH v11 13/15] khugepaged: avoid unnecessary mTHP collapse attempts Nico Pache
2025-09-12 3:28 ` [PATCH v11 14/15] khugepaged: run khugepaged for all orders Nico Pache
2025-09-12 3:28 ` [PATCH v11 15/15] Documentation: mm: update the admin guide for mTHP collapse Nico Pache
2025-09-12 8:43 ` [PATCH v11 00/15] khugepaged: mTHP support Lorenzo Stoakes
2025-09-12 12:19 ` Kiryl Shutsemau
2025-09-12 12:25 ` David Hildenbrand
2025-09-12 13:37 ` Johannes Weiner
2025-09-12 13:46 ` David Hildenbrand
2025-09-12 14:01 ` Lorenzo Stoakes
2025-09-12 15:35 ` Pedro Falcato
2025-09-12 15:45 ` Lorenzo Stoakes
2025-09-12 15:15 ` Pedro Falcato
2025-09-12 15:38 ` Kiryl Shutsemau
2025-09-12 15:43 ` David Hildenbrand
2025-09-12 15:44 ` Kiryl Shutsemau
2025-09-12 15:51 ` David Hildenbrand
2025-09-15 13:43 ` Johannes Weiner
2025-09-15 14:45 ` David Hildenbrand
2025-09-12 23:31 ` Nico Pache
2025-09-15 9:22 ` Kiryl Shutsemau
2025-09-15 10:22 ` David Hildenbrand
2025-09-15 10:35 ` Lorenzo Stoakes
2025-09-15 10:39 ` David Hildenbrand
2025-09-15 10:40 ` Lorenzo Stoakes
2025-09-15 10:44 ` David Hildenbrand
2025-09-15 10:48 ` Lorenzo Stoakes
2025-09-15 10:52 ` David Hildenbrand
2025-09-15 10:59 ` Lorenzo Stoakes
2025-09-15 11:10 ` David Hildenbrand
2025-09-15 11:13 ` Lorenzo Stoakes
2025-09-15 11:16 ` David Hildenbrand
2025-09-15 12:16 ` Usama Arif
2025-09-15 10:43 ` Lorenzo Stoakes
2025-09-15 10:52 ` David Hildenbrand
2025-09-15 11:02 ` Lorenzo Stoakes
2025-09-15 11:14 ` David Hildenbrand
2025-09-15 11:23 ` Lorenzo Stoakes
2025-09-15 11:29 ` David Hildenbrand
2025-09-15 11:35 ` Lorenzo Stoakes
2025-09-15 11:45 ` David Hildenbrand
2025-09-15 12:01 ` Kiryl Shutsemau
2025-09-15 12:09 ` Lorenzo Stoakes
2025-09-15 11:41 ` Nico Pache
2025-09-15 12:59 ` David Hildenbrand
2025-09-12 13:47 ` David Hildenbrand
2025-09-12 14:28 ` David Hildenbrand
2025-09-12 14:35 ` Kiryl Shutsemau
2025-09-12 14:56 ` David Hildenbrand
2025-09-12 15:41 ` Kiryl Shutsemau
2025-09-12 15:45 ` David Hildenbrand
2025-09-12 15:51 ` Lorenzo Stoakes
2025-09-12 17:53 ` David Hildenbrand
2025-09-12 18:21 ` Lorenzo Stoakes
2025-09-13 0:28 ` Nico Pache
2025-09-15 10:44 ` Lorenzo Stoakes
2025-09-15 10:25 ` David Hildenbrand
2025-09-15 10:32 ` Lorenzo Stoakes
2025-09-15 10:37 ` David Hildenbrand
2025-09-15 10:46 ` Lorenzo Stoakes
2025-09-13 0:18 ` Nico Pache
2025-09-12 23:35 ` 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=20250912032810.197475-3-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=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=catalin.marinas@arm.com \
--cc=cl@gentwo.org \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=dev.jain@arm.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jack@suse.cz \
--cc=jannh@google.com \
--cc=jglisse@google.com \
--cc=kas@kernel.org \
--cc=lance.yang@linux.dev \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mhocko@suse.com \
--cc=peterx@redhat.com \
--cc=pfalcato@suse.de \
--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=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=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;
as well as URLs for NNTP newsgroup(s).