aufs6: mmap

Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>

fs/proc/base.c

@@ -2218,7 +2218,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
 	rc = -ENOENT;
 	vma = find_exact_vma(mm, vm_start, vm_end);
 	if (vma && vma->vm_file) {
-		*path = vma->vm_file->f_path;
+		*path = vma_pr_or_file(vma)->f_path;
 		path_get(path);
 		rc = 0;
 	}

fs/proc/nommu.c

@@ -39,7 +39,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
 	file = region->vm_file;
 
 	if (file) {
-		struct inode *inode = file_inode(region->vm_file);
+		struct inode *inode;
+
+		file = vmr_pr_or_file(region);
+		inode = file_inode(file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 	}

fs/proc/task_mmu.c

@@ -285,7 +285,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	const char *name = NULL;
 
 	if (file) {
-		struct inode *inode = file_inode(vma->vm_file);
+		struct inode *inode;
+
+		file = vma_pr_or_file(vma);
+		inode = file_inode(file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -1950,7 +1953,7 @@ static int show_numa_map(struct seq_file *m, void *v)
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md = &numa_priv->md;
-	struct file *file = vma->vm_file;
+	struct file *file = vma_pr_or_file(vma);
 	struct mm_struct *mm = vma->vm_mm;
 	struct mempolicy *pol;
 	char buffer[64];

fs/proc/task_nommu.c

@@ -150,7 +150,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 	file = vma->vm_file;
 
 	if (file) {
-		struct inode *inode = file_inode(vma->vm_file);
+		struct inode *inode;
+
+		file = vma_pr_or_file(vma);
+		inode = file_inode(file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;

include/linux/mm.h

@@ -2387,6 +2387,43 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
 						unsigned long addr);
 
+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
+extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
+extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
+				      int);
+extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
+extern void vma_do_fput(struct vm_area_struct *, const char[], int);
+
+#define vma_file_update_time(vma)	vma_do_file_update_time(vma, __func__, \
+								__LINE__)
+#define vma_pr_or_file(vma)		vma_do_pr_or_file(vma, __func__, \
+							  __LINE__)
+#define vma_get_file(vma)		vma_do_get_file(vma, __func__, __LINE__)
+#define vma_fput(vma)			vma_do_fput(vma, __func__, __LINE__)
+
+#ifndef CONFIG_MMU
+extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
+extern void vmr_do_fput(struct vm_region *, const char[], int);
+
+#define vmr_pr_or_file(region)		vmr_do_pr_or_file(region, __func__, \
+							  __LINE__)
+#define vmr_fput(region)		vmr_do_fput(region, __func__, __LINE__)
+#endif /* !CONFIG_MMU */
+
+#else
+
+#define vma_file_update_time(vma)	file_update_time((vma)->vm_file)
+#define vma_pr_or_file(vma)		(vma)->vm_file
+#define vma_get_file(vma)		get_file((vma)->vm_file)
+#define vma_fput(vma)			fput((vma)->vm_file)
+
+#ifndef CONFIG_MMU
+#define vmr_pr_or_file(region)		(region)->vm_file
+#define vmr_fput(region)		fput((region)->vm_file)
+#endif /* !CONFIG_MMU */
+
+#endif /* CONFIG_AUFS_FS */
+
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,

include/linux/mm_types.h

@@ -449,6 +449,9 @@ struct vm_region {
 	unsigned long	vm_top;		/* region allocated to here */
 	unsigned long	vm_pgoff;	/* the offset in vm_file corresponding to vm_start */
 	struct file	*vm_file;	/* the backing file or NULL */
+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
+	struct file	*vm_prfile;	/* the virtual backing file or NULL */
+#endif
 
 	int		vm_usage;	/* region usage count (access under nommu_region_sem) */
 	bool		vm_icache_flushed : 1; /* true if the icache has been flushed for
@@ -562,6 +565,9 @@ struct vm_area_struct {
 	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
 					   units */
 	struct file * vm_file;		/* File we map to (can be NULL). */
+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
+	struct file *vm_prfile;		/* shadow of vm_file */
+#endif
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
 #ifdef CONFIG_ANON_VMA_NAME

kernel/fork.c

@@ -731,7 +731,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (file) {
 			struct address_space *mapping = file->f_mapping;
 
-			get_file(file);
+			vma_get_file(tmp);
 			i_mmap_lock_write(mapping);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping_allow_writable(mapping);

mm/Makefile

@@ -139,3 +139,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
 obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
+obj-y += prfile.o

mm/filemap.c

@@ -3580,7 +3580,7 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
 	vm_fault_t ret = VM_FAULT_LOCKED;
 
 	sb_start_pagefault(mapping->host->i_sb);
-	file_update_time(vmf->vma->vm_file);
+	vma_file_update_time(vmf->vma);
 	folio_lock(folio);
 	if (folio->mapping != mapping) {
 		folio_unlock(folio);

mm/mmap.c

@@ -140,7 +140,7 @@ static void remove_vma(struct vm_area_struct *vma, bool unreachable)
 	if (vma->vm_ops && vma->vm_ops->close)
 		vma->vm_ops->close(vma);
 	if (vma->vm_file)
-		fput(vma->vm_file);
+		vma_fput(vma);
 	mpol_put(vma_policy(vma));
 	if (unreachable)
 		__vm_area_free(vma);
@@ -2365,7 +2365,7 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		goto out_free_mpol;
 
 	if (new->vm_file)
-		get_file(new->vm_file);
+		vma_get_file(new);
 
 	if (new->vm_ops && new->vm_ops->open)
 		new->vm_ops->open(new);
@@ -2875,7 +2875,7 @@ close_and_free_vma:
 
 	if (file || vma->vm_file) {
 unmap_and_free_vma:
-		fput(vma->vm_file);
+		vma_fput(vma);
 		vma->vm_file = NULL;
 
 		/* Undo any partial mapping done by a device driver. */
@@ -2936,6 +2936,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	unsigned long populate = 0;
 	unsigned long ret = -EINVAL;
 	struct file *file;
+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
+	struct file *prfile;
+#endif
 
 	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
 		     current->comm, current->pid);
@@ -2994,10 +2997,34 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (vma->vm_flags & VM_LOCKED)
 		flags |= MAP_LOCKED;
 
+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
+	vma_get_file(vma);
+	file = vma->vm_file;
+	prfile = vma->vm_prfile;
+	ret = do_mmap(vma->vm_file, start, size,
+			prot, flags, pgoff, &populate, NULL);
+	if (!IS_ERR_VALUE(ret) && file && prfile) {
+		struct vm_area_struct *new_vma;
+
+		new_vma = find_vma(mm, ret);
+		if (!new_vma->vm_prfile)
+			new_vma->vm_prfile = prfile;
+		if (new_vma != vma)
+			get_file(prfile);
+	}
+	/*
+	 * two fput()s instead of vma_fput(vma),
+	 * coz vma may not be available anymore.
+	 */
+	fput(file);
+	if (prfile)
+		fput(prfile);
+#else
 	file = get_file(vma->vm_file);
 	ret = do_mmap(vma->vm_file, start, size,
 			prot, flags, pgoff, &populate, NULL);
 	fput(file);
+#endif /* CONFIG_AUFS_FS */
 out:
 	mmap_write_unlock(mm);
 	if (populate)
@@ -3342,7 +3369,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		if (anon_vma_clone(new_vma, vma))
 			goto out_free_mempol;
 		if (new_vma->vm_file)
-			get_file(new_vma->vm_file);
+			vma_get_file(new_vma);
 		if (new_vma->vm_ops && new_vma->vm_ops->open)
 			new_vma->vm_ops->open(new_vma);
 		vma_start_write(new_vma);
@@ -3358,7 +3385,7 @@ out_vma_link:
 		new_vma->vm_ops->close(new_vma);
 
 	if (new_vma->vm_file)
-		fput(new_vma->vm_file);
+		vma_fput(new_vma);
 
 	unlink_anon_vmas(new_vma);
 out_free_mempol:

mm/nommu.c

@@ -523,7 +523,7 @@ static void __put_nommu_region(struct vm_region *region)
 		up_write(&nommu_region_sem);
 
 		if (region->vm_file)
-			fput(region->vm_file);
+			vmr_fput(region);
 
 		/* IO memory and memory shared directly out of the pagecache
 		 * from ramfs/tmpfs mustn't be released here */
@@ -602,7 +602,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_ops && vma->vm_ops->close)
 		vma->vm_ops->close(vma);
 	if (vma->vm_file)
-		fput(vma->vm_file);
+		vma_fput(vma);
 	put_nommu_region(vma->vm_region);
 	vm_area_free(vma);
 }
@@ -1137,7 +1137,7 @@ unsigned long do_mmap(struct file *file,
 					goto error_just_free;
 				}
 			}
-			fput(region->vm_file);
+			vmr_fput(region);
 			kmem_cache_free(vm_region_jar, region);
 			region = pregion;
 			result = start;
@@ -1219,10 +1219,10 @@ error_just_free:
 error:
 	vma_iter_free(&vmi);
 	if (region->vm_file)
-		fput(region->vm_file);
+		vmr_fput(region);
 	kmem_cache_free(vm_region_jar, region);
 	if (vma->vm_file)
-		fput(vma->vm_file);
+		vma_fput(vma);
 	vm_area_free(vma);
 	return ret;
 

mm/prfile.c

@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Mainly for aufs which mmap(2) different file and wants to print different
+ * path in /proc/PID/maps.
+ * Call these functions via macros defined in linux/mm.h.
+ *
+ * See Documentation/filesystems/aufs/design/06mmap.txt
+ *
+ * Copyright (c) 2014-2022 Junjro R. Okajima
+ * Copyright (c) 2014 Ian Campbell
+ */
+
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+
+/* #define PRFILE_TRACE */
+static inline void prfile_trace(struct file *f, struct file *pr,
+			      const char func[], int line, const char func2[])
+{
+#ifdef PRFILE_TRACE
+	if (pr)
+		pr_info("%s:%d: %s, %pD2\n", func, line, func2, f);
+#endif
+}
+
+void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
+			     int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	file_update_time(f);
+	if (f && pr)
+		file_update_time(pr);
+}
+
+struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
+			       int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	return (f && pr) ? pr : f;
+}
+
+void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	get_file(f);
+	if (f && pr)
+		get_file(pr);
+}
+
+void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	fput(f);
+	if (f && pr)
+		fput(pr);
+}
+
+#ifndef CONFIG_MMU
+struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
+			       int line)
+{
+	struct file *f = region->vm_file, *pr = region->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	return (f && pr) ? pr : f;
+}
+
+void vmr_do_fput(struct vm_region *region, const char func[], int line)
+{
+	struct file *f = region->vm_file, *pr = region->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	fput(f);
+	if (f && pr)
+		fput(pr);
+}
+#endif /* !CONFIG_MMU */