linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yafang Shao <laoar.shao@gmail.com>
To: akpm@linux-foundation.org, david@redhat.com, ziy@nvidia.com,
	baolin.wang@linux.alibaba.com, lorenzo.stoakes@oracle.com,
	Liam.Howlett@oracle.com, npache@redhat.com, ryan.roberts@arm.com,
	dev.jain@arm.com, hannes@cmpxchg.org, usamaarif642@gmail.com,
	gutierrez.asier@huawei-partners.com, willy@infradead.org,
	ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
	ameryhung@gmail.com, rientjes@google.com, corbet@lwn.net,
	21cnbao@gmail.com, shakeel.butt@linux.dev, tj@kernel.org,
	lance.yang@linux.dev
Cc: bpf@vger.kernel.org, linux-mm@kvack.org,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	Yafang Shao <laoar.shao@gmail.com>
Subject: [PATCH v8 mm-new 01/12] mm: thp: remove disabled task from khugepaged_mm_slot
Date: Fri, 26 Sep 2025 17:33:32 +0800	[thread overview]
Message-ID: <20250926093343.1000-2-laoar.shao@gmail.com> (raw)
In-Reply-To: <20250926093343.1000-1-laoar.shao@gmail.com>

Since a task with MMF_DISABLE_THP_COMPLETELY cannot use THP, remove it from
the khugepaged_mm_slot to stop khugepaged from processing it.

After this change, the following semantic relationship always holds:

  MMF_VM_HUGEPAGE is set     == task is in khugepaged mm_slot
  MMF_VM_HUGEPAGE is not set == task is not in khugepaged mm_slot

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Lance Yang <lance.yang@linux.dev>
---
 include/linux/khugepaged.h |  4 ++++
 kernel/sys.c               |  7 ++++--
 mm/khugepaged.c            | 49 ++++++++++++++++++++------------------
 3 files changed, 35 insertions(+), 25 deletions(-)

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index eb1946a70cff..f14680cd9854 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -15,6 +15,7 @@ extern void __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern void khugepaged_enter_vma(struct vm_area_struct *vma,
 				 vm_flags_t vm_flags);
+extern void khugepaged_enter_mm(struct mm_struct *mm);
 extern void khugepaged_min_free_kbytes_update(void);
 extern bool current_is_khugepaged(void);
 extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
@@ -42,6 +43,9 @@ static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
 {
 }
+static inline void khugepaged_enter_mm(struct mm_struct *mm)
+{
+}
 static inline int collapse_pte_mapped_thp(struct mm_struct *mm,
 					  unsigned long addr, bool install_pmd)
 {
diff --git a/kernel/sys.c b/kernel/sys.c
index a46d9b75880b..2c445bf44ce3 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/mm_inline.h>
+#include <linux/khugepaged.h>
 #include <linux/utsname.h>
 #include <linux/mman.h>
 #include <linux/reboot.h>
@@ -2479,7 +2480,7 @@ static int prctl_set_thp_disable(bool thp_disable, unsigned long flags,
 	/* Flags are only allowed when disabling. */
 	if ((!thp_disable && flags) || (flags & ~PR_THP_DISABLE_EXCEPT_ADVISED))
 		return -EINVAL;
-	if (mmap_write_lock_killable(current->mm))
+	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 	if (thp_disable) {
 		if (flags & PR_THP_DISABLE_EXCEPT_ADVISED) {
@@ -2493,7 +2494,9 @@ static int prctl_set_thp_disable(bool thp_disable, unsigned long flags,
 		mm_flags_clear(MMF_DISABLE_THP_COMPLETELY, mm);
 		mm_flags_clear(MMF_DISABLE_THP_EXCEPT_ADVISED, mm);
 	}
-	mmap_write_unlock(current->mm);
+
+	khugepaged_enter_mm(mm);
+	mmap_write_unlock(mm);
 	return 0;
 }
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 7ab2d1a42df3..f47ac8c19447 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -396,15 +396,10 @@ void __init khugepaged_destroy(void)
 	kmem_cache_destroy(mm_slot_cache);
 }
 
-static inline int hpage_collapse_test_exit(struct mm_struct *mm)
-{
-	return atomic_read(&mm->mm_users) == 0;
-}
-
 static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
 {
-	return hpage_collapse_test_exit(mm) ||
-		mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
+	return !atomic_read(&mm->mm_users) ||			/* exit */
+		mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);  /* disable */
 }
 
 static bool hugepage_pmd_enabled(void)
@@ -437,7 +432,7 @@ void __khugepaged_enter(struct mm_struct *mm)
 	int wakeup;
 
 	/* __khugepaged_exit() must not run from under us */
-	VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm);
+	VM_WARN_ON_ONCE(hpage_collapse_test_exit_or_disable(mm));
 	if (unlikely(mm_flags_test_and_set(MMF_VM_HUGEPAGE, mm)))
 		return;
 
@@ -460,14 +455,25 @@ void __khugepaged_enter(struct mm_struct *mm)
 		wake_up_interruptible(&khugepaged_wait);
 }
 
+void khugepaged_enter_mm(struct mm_struct *mm)
+{
+	if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm))
+		return;
+	if (mm_flags_test(MMF_VM_HUGEPAGE, mm))
+		return;
+	if (!hugepage_pmd_enabled())
+		return;
+
+	__khugepaged_enter(mm);
+}
+
 void khugepaged_enter_vma(struct vm_area_struct *vma,
 			  vm_flags_t vm_flags)
 {
-	if (!mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) &&
-	    hugepage_pmd_enabled()) {
-		if (thp_vma_allowable_order(vma, vm_flags, TVA_KHUGEPAGED, PMD_ORDER))
-			__khugepaged_enter(vma->vm_mm);
-	}
+	if (!thp_vma_allowable_order(vma, vm_flags, TVA_KHUGEPAGED, PMD_ORDER))
+		return;
+
+	khugepaged_enter_mm(vma->vm_mm);
 }
 
 void __khugepaged_exit(struct mm_struct *mm)
@@ -491,7 +497,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 	} else if (slot) {
 		/*
 		 * This is required to serialize against
-		 * hpage_collapse_test_exit() (which is guaranteed to run
+		 * hpage_collapse_test_exit_or_disable() (which is guaranteed to run
 		 * under mmap sem read mode). Stop here (after we return all
 		 * pagetables will be destroyed) until khugepaged has finished
 		 * working on the pagetables under the mmap_lock.
@@ -1429,16 +1435,13 @@ static void collect_mm_slot(struct mm_slot *slot)
 
 	lockdep_assert_held(&khugepaged_mm_lock);
 
-	if (hpage_collapse_test_exit(mm)) {
+	if (hpage_collapse_test_exit_or_disable(mm)) {
 		/* free mm_slot */
 		hash_del(&slot->hash);
 		list_del(&slot->mm_node);
 
-		/*
-		 * Not strictly needed because the mm exited already.
-		 *
-		 * mm_flags_clear(MMF_VM_HUGEPAGE, mm);
-		 */
+		/* If the mm is disabled, this flag must be cleared. */
+		mm_flags_clear(MMF_VM_HUGEPAGE, mm);
 
 		/* khugepaged_mm_lock actually not necessary for the below */
 		mm_slot_free(mm_slot_cache, slot);
@@ -1749,7 +1752,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED)
 			continue;
 
-		if (hpage_collapse_test_exit(mm))
+		if (hpage_collapse_test_exit_or_disable(mm))
 			continue;
 		/*
 		 * When a vma is registered with uffd-wp, we cannot recycle
@@ -2500,9 +2503,9 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 	VM_BUG_ON(khugepaged_scan.mm_slot != slot);
 	/*
 	 * Release the current mm_slot if this mm is about to die, or
-	 * if we scanned all vmas of this mm.
+	 * if we scanned all vmas of this mm, or if this mm is disabled.
 	 */
-	if (hpage_collapse_test_exit(mm) || !vma) {
+	if (hpage_collapse_test_exit_or_disable(mm) || !vma) {
 		/*
 		 * Make sure that if mm_users is reaching zero while
 		 * khugepaged runs here, khugepaged_exit will find
-- 
2.47.3



  reply	other threads:[~2025-09-26  9:34 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-26  9:33 [PATCH v8 mm-new 00/12] mm, bpf: BPF based THP order selection Yafang Shao
2025-09-26  9:33 ` Yafang Shao [this message]
2025-09-26 14:11   ` [PATCH v8 mm-new 01/12] mm: thp: remove disabled task from khugepaged_mm_slot Usama Arif
2025-09-28  2:21     ` Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 02/12] mm: thp: remove vm_flags parameter from khugepaged_enter_vma() Yafang Shao
2025-09-26 14:49   ` Usama Arif
2025-09-28  2:35     ` Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 03/12] mm: thp: remove vm_flags parameter from thp_vma_allowable_order() Yafang Shao
2025-09-26 14:54   ` Usama Arif
2025-09-26  9:33 ` [PATCH v8 mm-new 04/12] mm: thp: add support for BPF based THP order selection Yafang Shao
2025-09-26 15:13   ` Usama Arif
2025-09-26 19:17     ` Randy Dunlap
2025-09-28  2:13     ` Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 05/12] mm: thp: decouple THP allocation between swap and page fault paths Yafang Shao
2025-09-26 15:19   ` Usama Arif
2025-09-26  9:33 ` [PATCH v8 mm-new 06/12] mm: thp: enable THP allocation exclusively through khugepaged Yafang Shao
2025-09-26 15:27   ` Usama Arif
2025-09-28  2:58     ` Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 07/12] bpf: mark mm->owner as __safe_rcu_or_null Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 08/12] bpf: mark vma->vm_mm as __safe_trusted_or_null Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 09/12] selftests/bpf: add a simple BPF based THP policy Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 10/12] selftests/bpf: add test case to update " Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 11/12] selftests/bpf: add test cases for invalid thp_adjust usage Yafang Shao
2025-09-26  9:33 ` [PATCH v8 mm-new 12/12] Documentation: add BPF-based THP policy management Yafang Shao

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=20250926093343.1000-2-laoar.shao@gmail.com \
    --to=laoar.shao@gmail.com \
    --cc=21cnbao@gmail.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=ameryhung@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=daniel@iogearbox.net \
    --cc=david@redhat.com \
    --cc=dev.jain@arm.com \
    --cc=gutierrez.asier@huawei-partners.com \
    --cc=hannes@cmpxchg.org \
    --cc=lance.yang@linux.dev \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=npache@redhat.com \
    --cc=rientjes@google.com \
    --cc=ryan.roberts@arm.com \
    --cc=shakeel.butt@linux.dev \
    --cc=tj@kernel.org \
    --cc=usamaarif642@gmail.com \
    --cc=willy@infradead.org \
    --cc=ziy@nvidia.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