Merge a760542666 ("mm: shmem: don't truncate page if memory failure happens") into android-mainline

Steps on the way to 5.17-rc1

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ia5757863cdca404809ab212a169d02d7bcb1b4be

Documentation/vm/arch_pgtable_helpers.rst

@@ -247,12 +247,12 @@ SWAP Page Table Helpers
 | __swp_to_pmd_entry        | Creates a mapped PMD from a swapped entry (arch) |
 +---------------------------+--------------------------------------------------+
 | is_migration_entry        | Tests a migration (read or write) swapped entry  |
-+---------------------------+--------------------------------------------------+
-| is_write_migration_entry  | Tests a write migration swapped entry            |
-+---------------------------+--------------------------------------------------+
-| make_migration_entry_read | Converts into read migration swapped entry       |
-+---------------------------+--------------------------------------------------+
-| make_migration_entry      | Creates a migration swapped entry (read or write)|
-+---------------------------+--------------------------------------------------+
++-------------------------------+----------------------------------------------+
+| is_writable_migration_entry   | Tests a write migration swapped entry        |
++-------------------------------+----------------------------------------------+
+| make_readable_migration_entry | Creates a read migration swapped entry       |
++-------------------------------+----------------------------------------------+
+| make_writable_migration_entry | Creates a write migration swapped entry      |
++-------------------------------+----------------------------------------------+
 
 [1] https://lore.kernel.org/linux-mm/20181017020930.GN30832@redhat.com/

fs/inode.c

@@ -526,6 +526,55 @@ void __remove_inode_hash(struct inode *inode)
 }
 EXPORT_SYMBOL(__remove_inode_hash);
 
+void dump_mapping(const struct address_space *mapping)
+{
+	struct inode *host;
+	const struct address_space_operations *a_ops;
+	struct hlist_node *dentry_first;
+	struct dentry *dentry_ptr;
+	struct dentry dentry;
+	unsigned long ino;
+
+	/*
+	 * If mapping is an invalid pointer, we don't want to crash
+	 * accessing it, so probe everything depending on it carefully.
+	 */
+	if (get_kernel_nofault(host, &mapping->host) ||
+	    get_kernel_nofault(a_ops, &mapping->a_ops)) {
+		pr_warn("invalid mapping:%px\n", mapping);
+		return;
+	}
+
+	if (!host) {
+		pr_warn("aops:%ps\n", a_ops);
+		return;
+	}
+
+	if (get_kernel_nofault(dentry_first, &host->i_dentry.first) ||
+	    get_kernel_nofault(ino, &host->i_ino)) {
+		pr_warn("aops:%ps invalid inode:%px\n", a_ops, host);
+		return;
+	}
+
+	if (!dentry_first) {
+		pr_warn("aops:%ps ino:%lx\n", a_ops, ino);
+		return;
+	}
+
+	dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
+	if (get_kernel_nofault(dentry, dentry_ptr)) {
+		pr_warn("aops:%ps ino:%lx invalid dentry:%px\n",
+				a_ops, ino, dentry_ptr);
+		return;
+	}
+
+	/*
+	 * if dentry is corrupted, the %pd handler may still crash,
+	 * but it's unlikely that we reach here with a corrupt mapping
+	 */
+	pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry);
+}
+
 void clear_inode(struct inode *inode)
 {
 	/*

include/linux/fs.h

@@ -3093,6 +3093,7 @@ extern void unlock_new_inode(struct inode *);
 extern void discard_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 extern void evict_inodes(struct super_block *sb);
+void dump_mapping(const struct address_space *);
 
 /*
  * Userspace may rely on the the inode number being non-zero. For example, glibc

mm/debug.c

@@ -112,56 +112,8 @@ static void __dump_page(struct page *page)
 		type = "ksm ";
 	else if (PageAnon(page))
 		type = "anon ";
-	else if (mapping) {
-		struct inode *host;
-		const struct address_space_operations *a_ops;
-		struct hlist_node *dentry_first;
-		struct dentry *dentry_ptr;
-		struct dentry dentry;
-		unsigned long ino;
-
-		/*
-		 * mapping can be invalid pointer and we don't want to crash
-		 * accessing it, so probe everything depending on it carefully
-		 */
-		if (get_kernel_nofault(host, &mapping->host) ||
-		    get_kernel_nofault(a_ops, &mapping->a_ops)) {
-			pr_warn("failed to read mapping contents, not a valid kernel address?\n");
-			goto out_mapping;
-		}
-
-		if (!host) {
-			pr_warn("aops:%ps\n", a_ops);
-			goto out_mapping;
-		}
-
-		if (get_kernel_nofault(dentry_first, &host->i_dentry.first) ||
-		    get_kernel_nofault(ino, &host->i_ino)) {
-			pr_warn("aops:%ps with invalid host inode %px\n",
-					a_ops, host);
-			goto out_mapping;
-		}
-
-		if (!dentry_first) {
-			pr_warn("aops:%ps ino:%lx\n", a_ops, ino);
-			goto out_mapping;
-		}
-
-		dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
-		if (get_kernel_nofault(dentry, dentry_ptr)) {
-			pr_warn("aops:%ps ino:%lx with invalid dentry %px\n",
-					a_ops, ino, dentry_ptr);
-		} else {
-			/*
-			 * if dentry is corrupted, the %pd handler may still
-			 * crash, but it's unlikely that we reach here with a
-			 * corrupted struct page
-			 */
-			pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n",
-					a_ops, ino, &dentry);
-		}
-	}
-out_mapping:
+	else if (mapping)
+		dump_mapping(mapping);
 	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
 
 	pr_warn("%sflags: %pGp%s\n", type, &head->flags,

mm/debug_vm_pgtable.c

@@ -888,8 +888,8 @@ static void __init swap_migration_tests(struct pgtable_debug_args *args)
 	pr_debug("Validating swap migration\n");
 
 	/*
-	 * make_migration_entry() expects given page to be
-	 * locked, otherwise it stumbles upon a BUG_ON().
+	 * make_[readable|writable]_migration_entry() expects given page to
+	 * be locked, otherwise it stumbles upon a BUG_ON().
 	 */
 	__SetPageLocked(page);
 	swp = make_writable_migration_entry(page_to_pfn(page));

mm/gup.c

@@ -642,12 +642,17 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	}
 retry:
 	if (!pmd_present(pmdval)) {
+		/*
+		 * Should never reach here, if thp migration is not supported;
+		 * Otherwise, it must be a thp migration entry.
+		 */
+		VM_BUG_ON(!thp_migration_supported() ||
+				  !is_pmd_migration_entry(pmdval));
+
 		if (likely(!(flags & FOLL_MIGRATION)))
 			return no_page_table(vma, flags);
-		VM_BUG_ON(thp_migration_supported() &&
-				  !is_pmd_migration_entry(pmdval));
-		if (is_pmd_migration_entry(pmdval))
-			pmd_migration_entry_wait(mm, pmd);
+
+		pmd_migration_entry_wait(mm, pmd);
 		pmdval = READ_ONCE(*pmd);
 		/*
 		 * MADV_DONTNEED may convert the pmd to null because
@@ -1672,21 +1677,22 @@ size_t fault_in_writeable(char __user *uaddr, size_t size)
 
 	if (unlikely(size == 0))
 		return 0;
+	if (!user_write_access_begin(uaddr, size))
+		return size;
 	if (!PAGE_ALIGNED(uaddr)) {
-		if (unlikely(__put_user(0, uaddr) != 0))
-			return size;
+		unsafe_put_user(0, uaddr, out);
 		uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr);
 	}
 	end = (char __user *)PAGE_ALIGN((unsigned long)start + size);
 	if (unlikely(end < start))
 		end = NULL;
 	while (uaddr != end) {
-		if (unlikely(__put_user(0, uaddr) != 0))
-			goto out;
+		unsafe_put_user(0, uaddr, out);
 		uaddr += PAGE_SIZE;
 	}
 
 out:
+	user_write_access_end();
 	if (size > uaddr - start)
 		return size - (uaddr - start);
 	return 0;
@@ -1771,21 +1777,22 @@ size_t fault_in_readable(const char __user *uaddr, size_t size)
 
 	if (unlikely(size == 0))
 		return 0;
+	if (!user_read_access_begin(uaddr, size))
+		return size;
 	if (!PAGE_ALIGNED(uaddr)) {
-		if (unlikely(__get_user(c, uaddr) != 0))
-			return size;
+		unsafe_get_user(c, uaddr, out);
 		uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr);
 	}
 	end = (const char __user *)PAGE_ALIGN((unsigned long)start + size);
 	if (unlikely(end < start))
 		end = NULL;
 	while (uaddr != end) {
-		if (unlikely(__get_user(c, uaddr) != 0))
-			goto out;
+		unsafe_get_user(c, uaddr, out);
 		uaddr += PAGE_SIZE;
 	}
 
 out:
+	user_read_access_end();
 	(void)c;
 	if (size > uaddr - start)
 		return size - (uaddr - start);

mm/memory-failure.c

@@ -58,6 +58,7 @@
 #include <linux/ratelimit.h>
 #include <linux/page-isolation.h>
 #include <linux/pagewalk.h>
+#include <linux/shmem_fs.h>
 #include "internal.h"
 #include "ras/ras_event.h"
 
@@ -867,6 +868,7 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 {
 	int ret;
 	struct address_space *mapping;
+	bool extra_pins;
 
 	delete_from_lru_cache(p);
 
@@ -895,18 +897,24 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 		goto out;
 	}
 
+	/*
+	 * The shmem page is kept in page cache instead of truncating
+	 * so is expected to have an extra refcount after error-handling.
+	 */
+	extra_pins = shmem_mapping(mapping);
+
 	/*
 	 * Truncation is a bit tricky. Enable it per file system for now.
 	 *
 	 * Open: to take i_rwsem or not for this? Right now we don't.
 	 */
 	ret = truncate_error_page(p, page_to_pfn(p), mapping);
+	if (has_extra_refcount(ps, p, extra_pins))
+		ret = MF_FAILED;
+
 out:
 	unlock_page(p);
 
-	if (has_extra_refcount(ps, p, false))
-		ret = MF_FAILED;
-
 	return ret;
 }
 

mm/shmem.c

@@ -2439,6 +2439,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t index = pos >> PAGE_SHIFT;
+	int ret = 0;
 
 	/* i_rwsem is held by caller */
 	if (unlikely(info->seals & (F_SEAL_GROW |
@@ -2449,7 +2450,19 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			return -EPERM;
 	}
 
-	return shmem_getpage(inode, index, pagep, SGP_WRITE);
+	ret = shmem_getpage(inode, index, pagep, SGP_WRITE);
+
+	if (ret)
+		return ret;
+
+	if (PageHWPoison(*pagep)) {
+		unlock_page(*pagep);
+		put_page(*pagep);
+		*pagep = NULL;
+		return -EIO;
+	}
+
+	return 0;
 }
 
 static int
@@ -2536,6 +2549,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			if (sgp == SGP_CACHE)
 				set_page_dirty(page);
 			unlock_page(page);
+
+			if (PageHWPoison(page)) {
+				put_page(page);
+				error = -EIO;
+				break;
+			}
 		}
 
 		/*
@@ -3075,7 +3094,8 @@ static const char *shmem_get_link(struct dentry *dentry,
 		page = find_get_page(inode->i_mapping, 0);
 		if (!page)
 			return ERR_PTR(-ECHILD);
-		if (!PageUptodate(page)) {
+		if (PageHWPoison(page) ||
+		    !PageUptodate(page)) {
 			put_page(page);
 			return ERR_PTR(-ECHILD);
 		}
@@ -3083,6 +3103,13 @@ static const char *shmem_get_link(struct dentry *dentry,
 		error = shmem_getpage(inode, 0, &page, SGP_READ);
 		if (error)
 			return ERR_PTR(error);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (PageHWPoison(page)) {
+			unlock_page(page);
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
 		unlock_page(page);
 	}
 	set_delayed_call(done, shmem_put_link, page);
@@ -3733,6 +3760,13 @@ static void shmem_destroy_inodecache(void)
 	kmem_cache_destroy(shmem_inode_cachep);
 }
 
+/* Keep the page in page cache instead of truncating it */
+static int shmem_error_remove_page(struct address_space *mapping,
+				   struct page *page)
+{
+	return 0;
+}
+
 const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.set_page_dirty	= __set_page_dirty_no_writeback,
@@ -3743,7 +3777,7 @@ const struct address_space_operations shmem_aops = {
 #ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
 #endif
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_page = shmem_error_remove_page,
 };
 EXPORT_SYMBOL(shmem_aops);
 
@@ -4151,9 +4185,14 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 	error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE,
 				  gfp, NULL, NULL, NULL);
 	if (error)
-		page = ERR_PTR(error);
-	else
-		unlock_page(page);
+		return ERR_PTR(error);
+
+	unlock_page(page);
+	if (PageHWPoison(page)) {
+		put_page(page);
+		return ERR_PTR(-EIO);
+	}
+
 	return page;
 #else
 	/*

mm/truncate.c

@@ -205,7 +205,6 @@ static void truncate_cleanup_folio(struct folio *folio)
 static int
 invalidate_complete_page(struct address_space *mapping, struct page *page)
 {
-	int ret;
 
 	if (page->mapping != mapping)
 		return 0;
@@ -213,9 +212,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	if (page_has_private(page) && !try_to_release_page(page, 0))
 		return 0;
 
-	ret = remove_mapping(mapping, page);
-
-	return ret;
+	return remove_mapping(mapping, page);
 }
 
 int truncate_inode_folio(struct address_space *mapping, struct folio *folio)

mm/userfaultfd.c

@@ -232,6 +232,11 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
 		goto out;
 	}
 
+	if (PageHWPoison(page)) {
+		ret = -EIO;
+		goto out_release;
+	}
+
 	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
 				       page, false, wp_copy);
 	if (ret)