[PATCH RFC 32/37] mm: Call arch_swap_prepare_to_restore() before arch_swap_restore()

[Alexandru Elisei <alexandru.elisei@xxxxxxx>]

arch_swap_restore() allows an architecture to restore metadata before the
page is swapped in and it's called in atomic context (with the ptl lock
held). Introduce arch_swap_prepare_to_restore() to allow such architectures
to perform extra work in a blocking context.

Signed-off-by: Alexandru Elisei <alexandru.elisei@xxxxxxx>
---
 include/linux/pgtable.h |  7 +++++++
 mm/memory.c             | 11 +++++++++++
 mm/shmem.c              |  4 ++++
 mm/swapfile.c           |  4 ++++
 4 files changed, 26 insertions(+)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 0119ffa2c0ab..0bce12f9eaab 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -816,6 +816,13 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 }
 #endif
 
+#ifndef __HAVE_ARCH_SWAP_PREPARE_TO_RESTORE
+static inline int arch_swap_prepare_to_restore(swp_entry_t entry, struct folio *folio)
+{
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PGD_OFFSET_GATE
 #define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
 #endif
diff --git a/mm/memory.c b/mm/memory.c
index 6c4a6151c7b2..5f7587109ac2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3724,6 +3724,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
+	int error;
 	vm_fault_t ret = 0;
 	void *shadow = NULL;
 
@@ -3892,6 +3893,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	folio_throttle_swaprate(folio, GFP_KERNEL);
 
+	/*
+	 * Some architecture may need to perform certain operations before
+	 * arch_swap_restore() in preemptible context (like memory allocations).
+	 */
+	error = arch_swap_prepare_to_restore(entry, folio);
+	if (error) {
+		ret = VM_FAULT_ERROR;
+		goto out_page;
+	}
+
 	/*
 	 * Back out if somebody else already faulted in this pte.
 	 */
diff --git a/mm/shmem.c b/mm/shmem.c
index 0b772ec34caa..4704be6a4e9b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1796,6 +1796,10 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	}
 	folio_wait_writeback(folio);
 
+	error = arch_swap_prepare_to_restore(swap, folio);
+	if (error)
+		goto unlock;
+
 	/*
 	 * Some architectures may have to restore extra metadata to the
 	 * folio after reading from swap.
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6d719ed5c616..387971e2c5f0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1756,6 +1756,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
 		hwposioned = true;
 
+	ret = arch_swap_prepare_to_restore(entry, folio);
+	if (ret)
+		return ret;
+
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
 						swp_entry_to_pte(entry)))) {
-- 
2.41.0