Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   Kairui Song <ryncsn@gmail.com>
To:     linux-mm@kvack.org
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        "Huang, Ying" <ying.huang@intel.com>,
        David Hildenbrand <david@redhat.com>,
        Hugh Dickins <hughd@google.com>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Matthew Wilcox <willy@infradead.org>,
        Michal Hocko <mhocko@suse.com>, linux-kernel@vger.kernel.org,
        Kairui Song <kasong@tencent.com>
Subject: [PATCH 16/24] mm/swap: reduce scope of get_swap_device in swapin path
Date:   Mon, 20 Nov 2023 03:47:32 +0800
Message-ID: <20231119194740.94101-17-ryncsn@gmail.com>
In-Reply-To: <20231119194740.94101-1-ryncsn@gmail.com>
References: <20231119194740.94101-1-ryncsn@gmail.com>
Reply-To: Kairui Song <kasong@tencent.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Kairui Song <kasong@tencent.com>

Move get_swap_device into swapin_readahead, simplify the code
and prepare for follow up commits.

For the later part in do_swap_page, using swp_swap_info directly is fine
since in that context, the swap device is pinned by swapcache reference.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/memory.c     | 16 ++++------------
 mm/swap_state.c |  8 ++++++--
 mm/swapfile.c   |  4 +++-
 3 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 22af9f3e8c75..e399b37ef395 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3789,7 +3789,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct folio *swapcache = NULL, *folio = NULL;
 	enum swap_cache_result cache_result;
 	struct page *page;
-	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
 	bool exclusive = false;
 	swp_entry_t entry;
@@ -3845,14 +3844,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		goto out;
 	}
 
-	/* Prevent swapoff from happening to us. */
-	si = get_swap_device(entry);
-	if (unlikely(!si))
-		goto out;
-
 	page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
 				vmf, &cache_result);
-	if (page) {
+	if (PTR_ERR(page) == -EBUSY) {
+		goto out;
+	} else if (page) {
 		folio = page_folio(page);
 		if (cache_result != SWAP_CACHE_HIT) {
 			/* Had to read the page from swap area: Major fault */
@@ -3964,7 +3960,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			 */
 			exclusive = true;
 		} else if (exclusive && folio_test_writeback(folio) &&
-			  data_race(si->flags & SWP_STABLE_WRITES)) {
+			   (swp_swap_info(entry)->flags & SWP_STABLE_WRITES)) {
 			/*
 			 * This is tricky: not all swap backends support
 			 * concurrent page modifications while under writeback.
@@ -4068,8 +4064,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
-	if (si)
-		put_swap_device(si);
 	return ret;
 out_nomap:
 	if (vmf->pte)
@@ -4082,8 +4076,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		folio_unlock(swapcache);
 		folio_put(swapcache);
 	}
-	if (si)
-		put_swap_device(si);
 	return ret;
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 51de2a0412df..ff8a166603d0 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -922,6 +922,11 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	struct page *page;
 	pgoff_t ilx;
 
+	/* Prevent swapoff from happening to us */
+	si = get_swap_device(entry);
+	if (unlikely(!si))
+		return ERR_PTR(-EBUSY);
+
 	folio = swap_cache_get_folio(entry, vmf, &shadow);
 	if (folio) {
 		page = folio_file_page(folio, swp_offset(entry));
@@ -929,7 +934,6 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		goto done;
 	}
 
-	si = swp_swap_info(entry);
 	mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx);
 	if (swap_use_no_readahead(si, swp_offset(entry))) {
 		page = swapin_no_readahead(entry, gfp_mask, mpol, ilx, vmf->vma->vm_mm);
@@ -944,8 +948,8 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		cache_result = SWAP_CACHE_MISS;
 	}
 	mpol_cond_put(mpol);
-
 done:
+	put_swap_device(si);
 	if (result)
 		*result = cache_result;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b6d57fff5e21..925ad92486a4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1857,7 +1857,9 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		pte = NULL;
 		page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
 					&vmf, NULL);
-		if (page)
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+		else if (page)
 			folio = page_folio(page);
 		if (!folio) {
 			/*
-- 
2.42.0