[Devel] [PATCH RHEL9 COMMIT] ms/mm/swap: convert __read_swap_cache_async() to use a folio

[Konstantin Khorenko]

The commit is pushed to "branch-rh9-5.14.0-362.8.1.vz9.35.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh9-5.14.0-362.8.1.vz9.35.9
------>
commit 3bb87414bb57239d5183c895f60b8d676a41a3db
Author: Matthew Wilcox (Oracle) <willy at infradead.org>
Date:   Thu Feb 1 14:33:16 2024 +0800

    ms/mm/swap: convert __read_swap_cache_async() to use a folio
    
    Remove a few hidden (and one visible) calls to compound_head().
    
    Link: https://lkml.kernel.org/r/20220902194653.1739778-12-willy@infradead.org
    Signed-off-by: Matthew Wilcox (Oracle) <willy at infradead.org>
    Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
    
    (cherry picked from commit a0d3374b070776e985bbd7b165b178fa688bf37a)
    Change: Also update vz specific hunk SetPageActive->folio_set_active.
    
    https://virtuozzo.atlassian.net/browse/PSBM-153264
    Signed-off-by: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
    
    Feature: fix ms/mm
    
    ======
    Patchset description:
    mm/swap: fix swapcache page/folio inconsistency
    
    This ports the switching from page to folio in add_to_swap_cache().
    
    We saw multiple different hangs on mmap_lock, where the task holding the
    lock was livelocked spinning in this stack:
    
      +-> __x64_sys_ioctl
        +-> kvm_vcpu_ioctl
          +-> kvm_arch_vcpu_ioctl_run
            +-> vcpu_run
              +-> vcpu_enter_guest
                +-> kvm_mmu_page_fault
                  +-> kvm_tdp_page_fault
                    +-> kvm_faultin_pfn
                      +-> __kvm_faultin_pfn
                        +-> hva_to_pfn
                          +-> get_user_pages_unlocked
    
      +-> get_user_pages_unlocked
        +-> mmap_read_lock # 1
        +-> __get_user_pages_locked # 2
          +-> for-loop # taken once
            +-> __get_user_pages
              +-> retry-loop # constantly spinning
                +-> faultin_page # return 0 to trigger retry
                  +-> handle_mm_fault
                    +-> __handle_mm_fault
                      +-> handle_pte_fault
                        +-> do_swap_page
                          +-> lookup_swap_cache # returns non-NULL
                          +-> if (swapcache)
                            +-> if (!folio_test_swapcache || page_private(page) != entry.val)
                              +-> goto out_page
                                +-> return 0
    
    That can be due to an inconsistency in swapcache flag setting/reading,
    one can see that PageSwapCache reads the flag from folio, but
    SetPageSwapCache/ClearPageSwapCache instead affect the flag from page.
    
    After applying those patches SetPageSwapCache/ClearPageSwapCache become
    unused, thus all paths seek this flag from folio now. With it I don't
    see any hangs on mmap_lock anymore (on the same test setup).
    
    Matthew Wilcox (Oracle) (2):
      mm/swap: convert __read_swap_cache_async() to use a folio
      mm/swap: convert add_to_swap_cache() to take a folio
---
 mm/swap_state.c | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/mm/swap_state.c b/mm/swap_state.c
index b16dc348bbd2..3a2323aba6f9 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -423,7 +423,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			bool *new_page_allocated, bool activate)
 {
 	struct swap_info_struct *si;
-	struct page *page;
+	struct folio *folio;
 	void *shadow = NULL;
 
 	*new_page_allocated = false;
@@ -438,11 +438,11 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		si = get_swap_device(entry);
 		if (!si)
 			return NULL;
-		page = find_get_page(swap_address_space(entry),
-				     swp_offset(entry));
+		folio = filemap_get_folio(swap_address_space(entry),
+						swp_offset(entry));
 		put_swap_device(si);
-		if (page)
-			return page;
+		if (folio)
+			return folio_file_page(folio, swp_offset(entry));
 
 		/*
 		 * Just skip read ahead for unused swap slot.
@@ -460,8 +460,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will
 		 * cause any racers to loop around until we add it to cache.
 		 */
-		page = alloc_page_vma(gfp_mask, vma, addr);
-		if (!page)
+		folio = vma_alloc_folio(gfp_mask, 0, vma, addr, false);
+		if (!folio)
 			return NULL;
 
 		/*
@@ -471,7 +471,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		if (!err)
 			break;
 
-		put_page(page);
+		folio_put(folio);
 		if (err != -EEXIST)
 			return NULL;
 
@@ -489,32 +489,33 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	 * The swap entry is ours to swap in. Prepare the new page.
 	 */
 
-	__SetPageLocked(page);
-	__SetPageSwapBacked(page);
+	__folio_set_locked(folio);
+	__folio_set_swapbacked(folio);
 
-	if (mem_cgroup_swapin_charge_page(page, NULL, gfp_mask, entry))
+	if (mem_cgroup_swapin_charge_page(&folio->page, NULL, gfp_mask, entry))
 		goto fail_unlock;
 
 	/* May fail (-ENOMEM) if XArray node allocation failed. */
-	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
+	if (add_to_swap_cache(&folio->page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
 		goto fail_unlock;
 
 	mem_cgroup_swapin_uncharge_swap(entry);
 
 	if (shadow)
-		workingset_refault(page_folio(page), shadow);
+		workingset_refault(folio, shadow);
 
 	/* Caller will initiate read into locked page */
 	if (activate)
-		SetPageActive(page);
-	lru_cache_add(page);
+		folio_set_active(folio);
+	/* Caller will initiate read into locked folio */
+	folio_add_lru(folio);
 	*new_page_allocated = true;
-	return page;
+	return &folio->page;
 
 fail_unlock:
-	put_swap_page(page, entry);
-	unlock_page(page);
-	put_page(page);
+	put_swap_page(&folio->page, entry);
+	folio_unlock(folio);
+	folio_put(folio);
 	return NULL;
 }