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>,
	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 8/9] mm/madvise: batch tlb flushes for [process_]madvise(MADV_{DONTNEED[_LOCKED],FREE})
Date: Mon, 10 Mar 2025 10:23:17 -0700	[thread overview]
Message-ID: <20250310172318.653630-9-sj@kernel.org> (raw)
In-Reply-To: <20250310172318.653630-1-sj@kernel.org>

MADV_DONTNEED[_LOCKED] and MADV_FREE internal logics for
[process_]madvise() can be invoked with batched tlb flushes.  Update
vector_madvise() and do_madvise(), which are called for the two system
calls  respectively, to use those in the efficient way.  Initialize an
mmu_gather object before starting the internal works, and flush the
gathered tlb entries at once after all the internal works are done.

Signed-off-by: SeongJae Park <sj@kernel.org>
---
 mm/madvise.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 47 insertions(+), 4 deletions(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index d7ea71c6422c..d5f4ce3041a4 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -905,6 +905,7 @@ static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
 
 struct madvise_behavior {
 	int behavior;
+	struct mmu_gather *tlb;
 };
 
 static long madvise_dontneed_free(struct vm_area_struct *vma,
@@ -964,9 +965,11 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	}
 
 	if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED)
-		return madvise_dontneed_single_vma(NULL, vma, start, end);
+		return madvise_dontneed_single_vma(
+				madv_behavior->tlb, vma, start, end);
 	else if (behavior == MADV_FREE)
-		return madvise_free_single_vma(NULL, vma, start, end);
+		return madvise_free_single_vma(
+				madv_behavior->tlb, vma, start, end);
 	else
 		return -EINVAL;
 }
@@ -1639,6 +1642,32 @@ 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_DONTNEED:
+	case MADV_DONTNEED_LOCKED:
+		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))
+		return;
+	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))
+		return;
+	tlb_finish_mmu(madv_behavior->tlb);
+}
+
 static bool is_valid_madvise(unsigned long start, size_t len_in, int behavior)
 {
 	size_t len;
@@ -1791,14 +1820,20 @@ 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;
@@ -1815,13 +1850,18 @@ 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);
@@ -1850,14 +1890,17 @@ 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:[~2025-03-10 17:23 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-10 17:23 [PATCH 0/9] mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE SeongJae Park
2025-03-10 17:23 ` [PATCH 1/9] mm/madvise: use is_memory_failure() from madvise_do_behavior() SeongJae Park
2025-03-11 11:27   ` Lorenzo Stoakes
2025-03-10 17:23 ` [PATCH 2/9] mm/madvise: split out populate behavior check logic SeongJae Park
2025-03-11 11:29   ` Lorenzo Stoakes
2025-03-10 17:23 ` [PATCH 3/9] mm/madvise: deduplicate madvise_do_behavior() skip case handlings SeongJae Park
2025-03-11 12:02   ` Lorenzo Stoakes
2025-03-11 20:54     ` SeongJae Park
2025-03-10 17:23 ` [PATCH 4/9] mm/madvise: remove len parameter of madvise_do_behavior() SeongJae Park
2025-03-11 12:05   ` Lorenzo Stoakes
2025-03-10 17:23 ` [PATCH 5/9] mm/madvise: define and use madvise_behavior struct for madvise_do_behavior() SeongJae Park
2025-03-11 12:17   ` Lorenzo Stoakes
2025-03-11 20:56     ` SeongJae Park
2025-03-12  5:47       ` Lorenzo Stoakes
2025-03-12 17:23         ` SeongJae Park
2025-03-10 17:23 ` [PATCH 6/9] mm/memory: split non-tlb flushing part from zap_page_range_single() SeongJae Park
2025-03-11 12:45   ` Lorenzo Stoakes
2025-03-11 20:58     ` SeongJae Park
2025-03-31 20:24       ` SeongJae Park
2025-04-01  1:45   ` Liam R. Howlett
2025-04-01  2:48     ` SeongJae Park
2025-04-01 14:03       ` Liam R. Howlett
2025-04-01 21:25         ` SeongJae Park
2025-03-10 17:23 ` [PATCH 7/9] mm/madvise: let madvise_{dontneed,free}_single_vma() caller batches tlb flushes SeongJae Park
2025-03-11 13:07   ` Lorenzo Stoakes
2025-03-11 21:00     ` SeongJae Park
2025-03-10 17:23 ` SeongJae Park [this message]
2025-03-11 13:59   ` [PATCH 8/9] mm/madvise: batch tlb flushes for [process_]madvise(MADV_{DONTNEED[_LOCKED],FREE}) Lorenzo Stoakes
2025-03-11 21:01     ` SeongJae Park
2025-04-01 21:17   ` SeongJae Park
2025-03-10 17:23 ` [PATCH 9/9] mm/madvise: remove !tlb support from madvise_{dontneed,free}_single_vma() SeongJae Park
2025-03-11 14:01   ` Lorenzo Stoakes
2025-03-11 21:02     ` SeongJae Park
2025-03-12 13:46       ` Lorenzo Stoakes
2025-04-01 21:22         ` SeongJae Park
2025-03-10 22:39 ` [PATCH 0/9] mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE Andrew Morton
2025-03-10 23:15   ` Shakeel Butt
2025-03-10 23:36     ` Roman Gushchin
2025-03-11 11:17       ` Lorenzo Stoakes
2025-03-10 23:27   ` SeongJae Park
2025-03-11 12:49 ` Lorenzo Stoakes
2025-03-11 21:03   ` 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=20250310172318.653630-9-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=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