linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: SeongJae Park <sj@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: SeongJae Park <sj@kernel.org>,
	"Liam R.Howlett" <howlett@gmail.com>,
	David Hildenbrand <david@redhat.com>,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
	Rik van Riel <riel@surriel.com>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	Vlastimil Babka <vbabka@suse.cz>,
	kernel-team@meta.com, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org
Subject: [PATCH v2 2/4] mm/madvise: batch tlb flushes for MADV_FREE
Date: Fri,  4 Apr 2025 14:06:58 -0700	[thread overview]
Message-ID: <20250404210700.2156-3-sj@kernel.org> (raw)
In-Reply-To: <20250404210700.2156-1-sj@kernel.org>

MADV_FREE handling for [process_]madvise() flushes tlb for each vma of
each address range.  Update the logic to do tlb flushes in a batched
way.  Initialize an mmu_gather object from do_madvise() and
vector_madvise(), which are the entry level functions for
[process_]madvise(), respectively.  And pass those objects to the
function for per-vma work, via madvise_behavior struct.  Make the
per-vma logic not flushes tlb on their own but just saves the tlb
entries to the received mmu_gather object.  Finally, the entry level
functions flush the tlb entries that gathered for the entire user
request, at once.

Signed-off-by: SeongJae Park <sj@kernel.org>
---
 mm/madvise.c | 59 +++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 47 insertions(+), 12 deletions(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index 8bcfdd995d18..564095e381b2 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -799,12 +799,13 @@ static const struct mm_walk_ops madvise_free_walk_ops = {
 	.walk_lock		= PGWALK_RDLOCK,
 };
 
-static int madvise_free_single_vma(struct vm_area_struct *vma,
-			unsigned long start_addr, unsigned long end_addr)
+static int madvise_free_single_vma(
+		struct madvise_behavior *behavior, struct vm_area_struct *vma,
+		unsigned long start_addr, unsigned long end_addr)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_notifier_range range;
-	struct mmu_gather tlb;
+	struct mmu_gather *tlb = behavior->tlb;
 
 	/* MADV_FREE works for only anon vma at the moment */
 	if (!vma_is_anonymous(vma))
@@ -820,17 +821,14 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 				range.start, range.end);
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
 
 	mmu_notifier_invalidate_range_start(&range);
-	tlb_start_vma(&tlb, vma);
+	tlb_start_vma(tlb, vma);
 	walk_page_range(vma->vm_mm, range.start, range.end,
-			&madvise_free_walk_ops, &tlb);
-	tlb_end_vma(&tlb, vma);
+			&madvise_free_walk_ops, tlb);
+	tlb_end_vma(tlb, vma);
 	mmu_notifier_invalidate_range_end(&range);
-	tlb_finish_mmu(&tlb);
-
 	return 0;
 }
 
@@ -953,7 +951,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (action == MADV_DONTNEED || action == MADV_DONTNEED_LOCKED)
 		return madvise_dontneed_single_vma(vma, start, end);
 	else if (action == MADV_FREE)
-		return madvise_free_single_vma(vma, start, end);
+		return madvise_free_single_vma(behavior, vma, start, end);
 	else
 		return -EINVAL;
 }
@@ -1626,6 +1624,29 @@ static void madvise_unlock(struct mm_struct *mm, int behavior)
 		mmap_read_unlock(mm);
 }
 
+static bool madvise_batch_tlb_flush(int behavior)
+{
+	switch (behavior) {
+	case MADV_FREE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void madvise_init_tlb(struct madvise_behavior *madv_behavior,
+		struct mm_struct *mm)
+{
+	if (madvise_batch_tlb_flush(madv_behavior->behavior))
+		tlb_gather_mmu(madv_behavior->tlb, mm);
+}
+
+static void madvise_finish_tlb(struct madvise_behavior *madv_behavior)
+{
+	if (madvise_batch_tlb_flush(madv_behavior->behavior))
+		tlb_finish_mmu(madv_behavior->tlb);
+}
+
 static bool is_valid_madvise(unsigned long start, size_t len_in, int behavior)
 {
 	size_t len;
@@ -1782,14 +1803,20 @@ static int madvise_do_behavior(struct mm_struct *mm,
 int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
 {
 	int error;
-	struct madvise_behavior madv_behavior = {.behavior = behavior};
+	struct mmu_gather tlb;
+	struct madvise_behavior madv_behavior = {
+		.behavior = behavior,
+		.tlb = &tlb,
+	};
 
 	if (madvise_should_skip(start, len_in, behavior, &error))
 		return error;
 	error = madvise_lock(mm, behavior);
 	if (error)
 		return error;
+	madvise_init_tlb(&madv_behavior, mm);
 	error = madvise_do_behavior(mm, start, len_in, &madv_behavior);
+	madvise_finish_tlb(&madv_behavior);
 	madvise_unlock(mm, behavior);
 
 	return error;
@@ -1806,13 +1833,18 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
 {
 	ssize_t ret = 0;
 	size_t total_len;
-	struct madvise_behavior madv_behavior = {.behavior = behavior};
+	struct mmu_gather tlb;
+	struct madvise_behavior madv_behavior = {
+		.behavior = behavior,
+		.tlb = &tlb,
+	};
 
 	total_len = iov_iter_count(iter);
 
 	ret = madvise_lock(mm, behavior);
 	if (ret)
 		return ret;
+	madvise_init_tlb(&madv_behavior, mm);
 
 	while (iov_iter_count(iter)) {
 		unsigned long start = (unsigned long)iter_iov_addr(iter);
@@ -1841,14 +1873,17 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
 			}
 
 			/* Drop and reacquire lock to unwind race. */
+			madvise_finish_tlb(&madv_behavior);
 			madvise_unlock(mm, behavior);
 			madvise_lock(mm, behavior);
+			madvise_init_tlb(&madv_behavior, mm);
 			continue;
 		}
 		if (ret < 0)
 			break;
 		iov_iter_advance(iter, iter_iov_len(iter));
 	}
+	madvise_finish_tlb(&madv_behavior);
 	madvise_unlock(mm, behavior);
 
 	ret = (total_len - iov_iter_count(iter)) ? : ret;
-- 
2.39.5


  parent reply	other threads:[~2025-04-04 21:07 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-04 21:06 [PATCH v2 0/4] mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE SeongJae Park
2025-04-04 21:06 ` [PATCH v2 1/4] mm/madvise: define and use madvise_behavior struct for madvise_do_behavior() SeongJae Park
2025-04-04 21:06 ` SeongJae Park [this message]
2025-04-08 12:58   ` [PATCH v2 2/4] mm/madvise: batch tlb flushes for MADV_FREE Lorenzo Stoakes
2025-04-08 18:49     ` SeongJae Park
2025-04-04 21:06 ` [PATCH v2 3/4] mm/memory: split non-tlb flushing part from zap_page_range_single() SeongJae Park
2025-04-08 13:29   ` Lorenzo Stoakes
2025-04-08 20:12     ` SeongJae Park
2025-04-09 10:37       ` Lorenzo Stoakes
2025-04-04 21:07 ` [PATCH v2 4/4] mm/madvise: batch tlb flushes for MADV_DONTNEED[_LOCKED] SeongJae Park
2025-04-08 13:36   ` Lorenzo Stoakes
2025-04-08 20:16     ` SeongJae Park
2025-04-08 13:44 ` [PATCH v2 0/4] mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE Lorenzo Stoakes
2025-04-08 20:23   ` SeongJae Park
     [not found] <20250405013136.3863-1-hdanton@sina.com>
2025-04-05 16:30 ` [PATCH v2 2/4] mm/madvise: batch tlb flushes for MADV_FREE SeongJae Park
2025-04-05 23:46   ` SeongJae Park

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=20250404210700.2156-3-sj@kernel.org \
    --to=sj@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=howlett@gmail.com \
    --cc=kernel-team@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=riel@surriel.com \
    --cc=shakeel.butt@linux.dev \
    --cc=vbabka@suse.cz \
    /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).