*stash (upm_base_support): mm: restrictedmem: Kirill's pinning implem…

…entation Originally-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Michael Roth <michael.roth@amd.com>
mdroth · Feb 12, 2023 · f780033 · f780033
1 parent 881eddb
commit f780033
Show file tree

Hide file tree

Showing 4 changed files with 51 additions and 36 deletions.
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
@@ -9,6 +9,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/xattr.h>
 #include <linux/fs_parser.h>
+#include <linux/magic.h>
 
 /* inode in-kernel data */
 
@@ -75,10 +76,9 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags);
 extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts);
 #ifdef CONFIG_SHMEM
-extern const struct address_space_operations shmem_aops;
 static inline bool shmem_mapping(struct address_space *mapping)
 {
-	return mapping->a_ops == &shmem_aops;
+	return mapping->host->i_sb->s_magic == TMPFS_MAGIC;
 }
 #else
 static inline bool shmem_mapping(struct address_space *mapping)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
@@ -941,8 +941,6 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 		goto out;
 	}
 
-	restrictedmem_error_page(p, mapping);
-
 	/*
 	 * The shmem page is kept in page cache instead of truncating
 	 * so is expected to have an extra refcount after error-handling.

diff --git a/mm/restrictedmem.c b/mm/restrictedmem.c
@@ -190,6 +190,51 @@ static struct file *restrictedmem_file_create(struct file *memfd)
 	return file;
 }
 
+static int restricted_error_remove_page(struct address_space *mapping,
+                                       struct page *page)
+{
+       struct super_block *sb = restrictedmem_mnt->mnt_sb;
+       struct inode *inode, *next;
+       pgoff_t start, end;
+
+       start = page->index;
+       end = start + thp_nr_pages(page);
+
+       spin_lock(&sb->s_inode_list_lock);
+       list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+               struct restrictedmem *rm = inode->i_mapping->private_data;
+               struct restrictedmem_notifier *notifier;
+               struct file *memfd = rm->memfd;
+               unsigned long index;
+
+               if (memfd->f_mapping != mapping)
+                       continue;
+
+               xa_for_each_range(&rm->bindings, index, notifier, start, end)
+                       notifier->ops->error(notifier, start, end);
+               break;
+       }
+       spin_unlock(&sb->s_inode_list_lock);
+
+       return 0;
+}
+
+#ifdef CONFIG_MIGRATION
+static int restricted_folio(struct address_space *mapping, struct folio *dst,
+                           struct folio *src, enum migrate_mode mode)
+{
+       return -EBUSY;
+}
+#endif
+
+static struct address_space_operations restricted_aops = {
+       .dirty_folio    = noop_dirty_folio,
+       .error_remove_page = restricted_error_remove_page,
+#ifdef CONFIG_MIGRATION
+       .migrate_folio  = restricted_folio,
+#endif
+};
+
 SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
 {
 	struct file *file, *restricted_file;
@@ -210,6 +255,8 @@ SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	file->f_flags |= O_LARGEFILE;
 
+	file->f_mapping->a_ops = &restricted_aops;
+
 	restricted_file = restrictedmem_file_create(file);
 	if (IS_ERR(restricted_file)) {
 		err = PTR_ERR(restricted_file);
@@ -294,32 +341,3 @@ int restrictedmem_get_page(struct file *file, pgoff_t offset,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(restrictedmem_get_page);
-
-void restrictedmem_error_page(struct page *page, struct address_space *mapping)
-{
-	struct super_block *sb = restrictedmem_mnt->mnt_sb;
-	struct inode *inode, *next;
-	pgoff_t start, end;
-
-	if (!shmem_mapping(mapping))
-		return;
-
-	start = page->index;
-	end = start + thp_nr_pages(page);
-
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
-		struct restrictedmem *rm = inode->i_mapping->private_data;
-		struct restrictedmem_notifier *notifier;
-		struct file *memfd = rm->memfd;
-		unsigned long index;
-
-		if (memfd->f_mapping != mapping)
-			continue;
-
-		xa_for_each_range(&rm->bindings, index, notifier, start, end)
-			notifier->ops->error(notifier, start, end);
-		break;
-	}
-	spin_unlock(&sb->s_inode_list_lock);
-}
diff --git a/mm/shmem.c b/mm/shmem.c
@@ -231,7 +231,7 @@ static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
 }
 
 static const struct super_operations shmem_ops;
-const struct address_space_operations shmem_aops;
+static const struct address_space_operations shmem_aops;
 static const struct file_operations shmem_file_operations;
 static const struct inode_operations shmem_inode_operations;
 static const struct inode_operations shmem_dir_inode_operations;
@@ -3894,7 +3894,7 @@ static int shmem_error_remove_page(struct address_space *mapping,
 	return 0;
 }
 
-const struct address_space_operations shmem_aops = {
+static const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.dirty_folio	= noop_dirty_folio,
 #ifdef CONFIG_TMPFS
@@ -3906,7 +3906,6 @@ const struct address_space_operations shmem_aops = {
 #endif
 	.error_remove_page = shmem_error_remove_page,
 };
-EXPORT_SYMBOL(shmem_aops);
 
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,