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>

1 files changed, 25 insertions, 4 deletions

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;
 }