Received-SPF: pass (google.com: domain of linux-kernel+bounces-119744-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Kairui Song <ryncsn@gmail.com>
To: linux-mm@kvack.org
Cc: "Huang, Ying" <ying.huang@intel.com>,
	Chris Li <chrisl@kernel.org>,
	Minchan Kim <minchan@kernel.org>,
	Barry Song <v-songbaohua@oppo.com>,
	Ryan Roberts <ryan.roberts@arm.com>,
	Yu Zhao <yuzhao@google.com>,
	SeongJae Park <sj@kernel.org>,
	David Hildenbrand <david@redhat.com>,
	Yosry Ahmed <yosryahmed@google.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Matthew Wilcox <willy@infradead.org>,
	Nhat Pham <nphamcs@gmail.com>,
	Chengming Zhou <zhouchengming@bytedance.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org,
	Kairui Song <kasong@tencent.com>
Subject: [RFC PATCH 02/10] mm/swap: move no readahead swapin code to a stand-alone helper
Date: Wed, 27 Mar 2024 02:50:24 +0800
Message-ID: <20240326185032.72159-3-ryncsn@gmail.com>
In-Reply-To: <20240326185032.72159-1-ryncsn@gmail.com>
References: <20240326185032.72159-1-ryncsn@gmail.com>
Reply-To: Kairui Song <kasong@tencent.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Kairui Song <kasong@tencent.com>

Simply move the routine to a standalone function, having a cleaner
split and avoid helpers being referenced corss multiple files.

Basically no feature change, but the error path is very slightly
different. Previously a mem_cgroup_swapin_charge_folio fail will cause
direct OOM, now we go through the error checking path in do_swap_pte, if
the page is already there, just return as the page fault was handled.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/memory.c     | 42 +++-------------------------------
 mm/swap.h       |  8 +++++++
 mm/swap_state.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+), 39 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index f2bc6dd15eb8..e42fadc25268 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3937,7 +3937,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	swp_entry_t entry;
 	pte_t pte;
 	vm_fault_t ret = 0;
-	void *shadow = NULL;
 
 	if (!pte_unmap_same(vmf))
 		goto out;
@@ -4001,47 +4000,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
-			/*
-			 * Prevent parallel swapin from proceeding with
-			 * the cache flag. Otherwise, another thread may
-			 * finish swapin first, free the entry, and swapout
-			 * reusing the same entry. It's undetectable as
-			 * pte_same() returns true due to entry reuse.
-			 */
-			if (swapcache_prepare(entry)) {
-				/* Relax a bit to prevent rapid repeated page faults */
-				schedule_timeout_uninterruptible(1);
+			/* skip swapcache and readahead */
+			folio = swapin_direct(entry, GFP_HIGHUSER_MOVABLE, vmf);
+			if (PTR_ERR(folio) == -EBUSY)
 				goto out;
-			}
 			need_clear_cache = true;
-
-			/* skip swapcache */
-			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
-						vma, vmf->address, false);
 			page = &folio->page;
-			if (folio) {
-				__folio_set_locked(folio);
-				__folio_set_swapbacked(folio);
-
-				if (mem_cgroup_swapin_charge_folio(folio,
-							vma->vm_mm, GFP_KERNEL,
-							entry)) {
-					ret = VM_FAULT_OOM;
-					goto out_page;
-				}
-				mem_cgroup_swapin_uncharge_swap(entry);
-
-				shadow = get_shadow_from_swap_cache(entry);
-				if (shadow)
-					workingset_refault(folio, shadow);
-
-				folio_add_lru(folio);
-
-				/* To provide entry to swap_read_folio() */
-				folio->swap = entry;
-				swap_read_folio(folio, true, NULL);
-				folio->private = NULL;
-			}
 		} else {
 			page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
 						vmf);
diff --git a/mm/swap.h b/mm/swap.h
index fc2f6ade7f80..40e902812cc5 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -55,6 +55,8 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_flags,
 		bool skip_if_exists);
 struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
 		struct mempolicy *mpol, pgoff_t ilx);
+struct folio *swapin_direct(swp_entry_t entry, gfp_t flag,
+			    struct vm_fault *vmf);
 struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
 			      struct vm_fault *vmf);
 
@@ -87,6 +89,12 @@ static inline struct folio *swap_cluster_readahead(swp_entry_t entry,
 	return NULL;
 }
 
+static inline struct folio *swapin_direct(swp_entry_t entry, gfp_t flag,
+			struct vm_fault *vmf)
+{
+	return NULL;
+}
+
 static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
 			struct vm_fault *vmf)
 {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index bfc7e8c58a6d..0a3fa48b3893 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -879,6 +879,66 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 	return folio;
 }
 
+/**
+ * swapin_direct - swap in folios skipping swap cache and readahead
+ * @entry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
+ * @vmf: fault information
+ *
+ * Returns the struct folio for entry and addr after the swap entry is read
+ * in.
+ */
+struct folio *swapin_direct(swp_entry_t entry, gfp_t gfp_mask,
+			    struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
+	void *shadow = NULL;
+
+	/*
+	 * Prevent parallel swapin from proceeding with
+	 * the cache flag. Otherwise, another thread may
+	 * finish swapin first, free the entry, and swapout
+	 * reusing the same entry. It's undetectable as
+	 * pte_same() returns true due to entry reuse.
+	 */
+	if (swapcache_prepare(entry)) {
+		/* Relax a bit to prevent rapid repeated page faults */
+		schedule_timeout_uninterruptible(1);
+		return ERR_PTR(-EBUSY);
+	}
+
+	/* skip swapcache */
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
+				vma, vmf->address, false);
+	if (folio) {
+		__folio_set_locked(folio);
+		__folio_set_swapbacked(folio);
+
+		if (mem_cgroup_swapin_charge_folio(folio,
+					vma->vm_mm, GFP_KERNEL,
+					entry)) {
+			folio_unlock(folio);
+			folio_put(folio);
+			return NULL;
+		}
+		mem_cgroup_swapin_uncharge_swap(entry);
+
+		shadow = get_shadow_from_swap_cache(entry);
+		if (shadow)
+			workingset_refault(folio, shadow);
+
+		folio_add_lru(folio);
+
+		/* To provide entry to swap_read_folio() */
+		folio->swap = entry;
+		swap_read_folio(folio, true, NULL);
+		folio->private = NULL;
+	}
+
+	return folio;
+}
+
 /**
  * swapin_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory
-- 
2.43.0