mm: anonymous shared memory naming

Since commit 9a10064f5625 ("mm: add a field to store names for private
anonymous memory"), name for private anonymous memory, but not shared
anonymous, can be set.  However, naming shared anonymous memory just as
useful for tracking purposes.

Extend the functionality to be able to set names for shared anon.

There are two ways to create anonymous shared memory, using memfd or
directly via mmap():
1. fd = memfd_create(...)
   mem = mmap(..., MAP_SHARED, fd, ...)
2. mem = mmap(..., MAP_SHARED | MAP_ANONYMOUS, -1, ...)

In both cases the anonymous shared memory is created the same way by
mapping an unlinked file on tmpfs.

The memfd way allows to give a name for anonymous shared memory, but
not useful when parts of shared memory require to have distinct names.

Example use case: The VMM maps VM memory as anonymous shared memory (not
private because VMM is sandboxed and drivers are running in their own
processes).  However, the VM tells back to the VMM how parts of the memory
are actually used by the guest, how each of the segments should be backed
(i.e.  4K pages, 2M pages), and some other information about the segments.
The naming allows us to monitor the effective memory footprint for each
of these segments from the host without looking inside the guest.

Sample output:
  /* Create shared anonymous segmenet */
  anon_shmem = mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
                    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
  /* Name the segment: "MY-NAME" */
  rv = prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME,
             anon_shmem, SIZE, "MY-NAME");

cat /proc/<pid>/maps (and smaps):
7fc8e2b4c000-7fc8f2b4c000 rw-s 00000000 00:01 1024 [anon_shmem:MY-NAME]

If the segment is not named, the output is:
7fc8e2b4c000-7fc8f2b4c000 rw-s 00000000 00:01 1024 /dev/zero (deleted)

Link: https://lkml.kernel.org/r/20221115020602.804224-1-pasha.tatashin@soleen.com
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Colin Cross <ccross@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: xu xin <cgel.zte@gmail.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 57 insertions, 30 deletions

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 898c99eae8e4..b8f175ae4853 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -426,14 +426,16 @@ with the memory region, as the case would be with BSS (uninitialized data).
 The "pathname" shows the name associated file for this mapping.  If the mapping
 is not associated with a file:
 
- =============              ====================================
+ ===================        ===========================================
  [heap]                     the heap of the program
  [stack]                    the stack of the main process
  [vdso]                     the "virtual dynamic shared object",
                             the kernel system call handler
- [anon:<name>]              an anonymous mapping that has been
+ [anon:<name>]              a private anonymous mapping that has been
                             named by userspace
- =============              ====================================
+ [anon_shmem:<name>]        an anonymous shared memory mapping that has
+                            been named by userspace
+ ===================        ===========================================
 
  or if empty, the mapping is anonymous.
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 8a74cdcc9af0..89338950afd3 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -274,6 +274,7 @@ static void show_vma_header_prefix(struct seq_file *m,
 static void
 show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 {
+	struct anon_vma_name *anon_name = NULL;
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	vm_flags_t flags = vma->vm_flags;
@@ -293,6 +294,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	start = vma->vm_start;
 	end = vma->vm_end;
 	show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino);
+	if (mm)
+		anon_name = anon_vma_name(vma);
 
 	/*
 	 * Print the dentry name for named mappings, and a
@@ -300,7 +303,14 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	 */
 	if (file) {
 		seq_pad(m, ' ');
-		seq_file_path(m, file, "\n");
+		/*
+		 * If user named this anon shared memory via
+		 * prctl(PR_SET_VMA ..., use the provided name.
+		 */
+		if (anon_name)
+			seq_printf(m, "[anon_shmem:%s]", anon_name->name);
+		else
+			seq_file_path(m, file, "\n");
 		goto done;
 	}
 
@@ -312,8 +322,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		struct anon_vma_name *anon_name;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -330,7 +338,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 			goto done;
 		}
 
-		anon_name = anon_vma_name(vma);
 		if (anon_name) {
 			seq_pad(m, ' ');
 			seq_printf(m, "[anon:%s]", anon_name->name);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f873441303b7..686879dbb0bd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -700,8 +700,10 @@ static inline unsigned long vma_iter_addr(struct vma_iterator *vmi)
  * paths in userfault.
  */
 bool vma_is_shmem(struct vm_area_struct *vma);
+bool vma_is_anon_shmem(struct vm_area_struct *vma);
 #else
 static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; }
+static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; }
 #endif
 
 int vma_is_stack_for_current(struct vm_area_struct *vma);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6b0009e7d4ae..157c2e22cc7f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -549,21 +549,11 @@ struct vm_area_struct {
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree.
 	 *
-	 * For private anonymous mappings, a pointer to a null terminated string
-	 * containing the name given to the vma, or NULL if unnamed.
 	 */
-
-	union {
-		struct {
-			struct rb_node rb;
-			unsigned long rb_subtree_last;
-		} shared;
-		/*
-		 * Serialized by mmap_sem. Never use directly because it is
-		 * valid only when vm_file is NULL. Use anon_vma_name instead.
-		 */
-		struct anon_vma_name *anon_name;
-	};
+	struct {
+		struct rb_node rb;
+		unsigned long rb_subtree_last;
+	} shared;
 
 	/*
 	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
@@ -584,6 +574,14 @@ struct vm_area_struct {
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
+#ifdef CONFIG_ANON_VMA_NAME
+	/*
+	 * For private and shared anonymous mappings, a pointer to a null
+	 * terminated string containing the name given to the vma, or NULL if
+	 * unnamed. Serialized by mmap_sem. Use anon_vma_name to access.
+	 */
+	struct anon_vma_name *anon_name;
+#endif
 #ifdef CONFIG_SWAP
 	atomic_long_t swap_readahead_info;
 #endif
diff --git a/mm/madvise.c b/mm/madvise.c
index b913ba6efc10..83b0c91a126b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -95,9 +95,6 @@ struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
 {
 	mmap_assert_locked(vma->vm_mm);
 
-	if (vma->vm_file)
-		return NULL;
-
 	return vma->anon_name;
 }
 
@@ -183,7 +180,7 @@ success:
 	 * vm_flags is protected by the mmap_lock held in write mode.
 	 */
 	vma->vm_flags = new_flags;
-	if (!vma->vm_file) {
+	if (!vma->vm_file || vma_is_anon_shmem(vma)) {
 		error = replace_anon_vma_name(vma, anon_name);
 		if (error)
 			return error;
@@ -1273,7 +1270,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma,
 	int error;
 
 	/* Only anonymous mappings can be named */
-	if (vma->vm_file)
+	if (vma->vm_file && !vma_is_anon_shmem(vma))
 		return -EBADF;
 
 	error = madvise_update_vma(vma, prev, start, end, vma->vm_flags,
diff --git a/mm/shmem.c b/mm/shmem.c
index 7428ae3fa4b9..f418d21205be 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -237,11 +237,17 @@ static const struct inode_operations shmem_inode_operations;
 static const struct inode_operations shmem_dir_inode_operations;
 static const struct inode_operations shmem_special_inode_operations;
 static const struct vm_operations_struct shmem_vm_ops;
+static const struct vm_operations_struct shmem_anon_vm_ops;
 static struct file_system_type shmem_fs_type;
 
+bool vma_is_anon_shmem(struct vm_area_struct *vma)
+{
+	return vma->vm_ops == &shmem_anon_vm_ops;
+}
+
 bool vma_is_shmem(struct vm_area_struct *vma)
 {
-	return vma->vm_ops == &shmem_vm_ops;
+	return vma_is_anon_shmem(vma) || vma->vm_ops == &shmem_vm_ops;
 }
 
 static LIST_HEAD(shmem_swaplist);
@@ -2263,7 +2269,8 @@ out_nomem:
 
 static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	struct shmem_inode_info *info = SHMEM_I(file_inode(file));
+	struct inode *inode = file_inode(file);
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	int ret;
 
 	ret = seal_check_future_write(info->seals, vma);
@@ -2274,7 +2281,11 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_MTE_ALLOWED;
 
 	file_accessed(file);
-	vma->vm_ops = &shmem_vm_ops;
+	/* This is anonymous shared memory if it is unlinked at the time of mmap */
+	if (inode->i_nlink)
+		vma->vm_ops = &shmem_vm_ops;
+	else
+		vma->vm_ops = &shmem_anon_vm_ops;
 	return 0;
 }
 
@@ -3988,6 +3999,15 @@ static const struct vm_operations_struct shmem_vm_ops = {
 #endif
 };
 
+static const struct vm_operations_struct shmem_anon_vm_ops = {
+	.fault		= shmem_fault,
+	.map_pages	= filemap_map_pages,
+#ifdef CONFIG_NUMA
+	.set_policy     = shmem_set_policy,
+	.get_policy     = shmem_get_policy,
+#endif
+};
+
 int shmem_init_fs_context(struct fs_context *fc)
 {
 	struct shmem_options *ctx;
@@ -4163,6 +4183,7 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
 #define shmem_vm_ops				generic_file_vm_ops
+#define shmem_anon_vm_ops			generic_file_vm_ops
 #define shmem_file_operations			ramfs_file_operations
 #define shmem_get_inode(sb, dir, mode, dev, flags)	ramfs_get_inode(sb, dir, mode, dev)
 #define shmem_acct_size(flags, size)		0
@@ -4268,7 +4289,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	vma->vm_file = file;
-	vma->vm_ops = &shmem_vm_ops;
+	vma->vm_ops = &shmem_anon_vm_ops;
 
 	return 0;
 }