From: Pratyush Yadav <ptyadav@amazon.de>

shmem_inode_info::flags can have the VM flags VM_NORESERVE and
VM_LOCKED. These are used to suppress pre-accounting or to lock the
pages in the inode respectively. Using the VM flags directly makes it
difficult to add shmem-specific flags that are unrelated to VM behavior
since one would need to find a VM flag not used by shmem and re-purpose
it.

Introduce SHMEM_F_NORESERVE and SHMEM_F_LOCKED which represent the same
information, but their bits are independent of the VM flags. Callers can
still pass VM_NORESERVE to shmem_get_inode(), but it gets transformed to
the shmem-specific flag internally.

No functional changes intended.

Signed-off-by: Pratyush Yadav <ptyadav@amazon.de>
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
 include/linux/shmem_fs.h |  6 ++++++
 mm/shmem.c               | 24 +++++++++++++-----------
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 5f03a39a26f7..578a5f3d1935 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -10,6 +10,7 @@
 #include <linux/xattr.h>
 #include <linux/fs_parser.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/bits.h>
 
 /* inode in-kernel data */
 
@@ -17,6 +18,11 @@
 #define SHMEM_MAXQUOTAS 2
 #endif
 
+/* Suppress pre-accounting of the entire object size. */
+#define SHMEM_F_NORESERVE	BIT(0)
+/* Disallow swapping. */
+#define SHMEM_F_LOCKED		BIT(1)
+
 struct shmem_inode_info {
 	spinlock_t		lock;
 	unsigned int		seals;		/* shmem seals */
diff --git a/mm/shmem.c b/mm/shmem.c
index 3a5a65b1f41a..953d89f62882 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -175,20 +175,20 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
  */
 static inline int shmem_acct_size(unsigned long flags, loff_t size)
 {
-	return (flags & VM_NORESERVE) ?
+	return (flags & SHMEM_F_NORESERVE) ?
 		0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size));
 }
 
 static inline void shmem_unacct_size(unsigned long flags, loff_t size)
 {
-	if (!(flags & VM_NORESERVE))
+	if (!(flags & SHMEM_F_NORESERVE))
 		vm_unacct_memory(VM_ACCT(size));
 }
 
 static inline int shmem_reacct_size(unsigned long flags,
 		loff_t oldsize, loff_t newsize)
 {
-	if (!(flags & VM_NORESERVE)) {
+	if (!(flags & SHMEM_F_NORESERVE)) {
 		if (VM_ACCT(newsize) > VM_ACCT(oldsize))
 			return security_vm_enough_memory_mm(current->mm,
 					VM_ACCT(newsize) - VM_ACCT(oldsize));
@@ -206,7 +206,7 @@ static inline int shmem_reacct_size(unsigned long flags,
  */
 static inline int shmem_acct_blocks(unsigned long flags, long pages)
 {
-	if (!(flags & VM_NORESERVE))
+	if (!(flags & SHMEM_F_NORESERVE))
 		return 0;
 
 	return security_vm_enough_memory_mm(current->mm,
@@ -215,7 +215,7 @@ static inline int shmem_acct_blocks(unsigned long flags, long pages)
 
 static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 {
-	if (flags & VM_NORESERVE)
+	if (flags & SHMEM_F_NORESERVE)
 		vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
 }
 
@@ -1557,7 +1557,7 @@ int shmem_writeout(struct folio *folio, struct writeback_control *wbc)
 	if (WARN_ON_ONCE(!wbc->for_reclaim))
 		goto redirty;
 
-	if ((info->flags & VM_LOCKED) || sbinfo->noswap)
+	if ((info->flags & SHMEM_F_LOCKED) || sbinfo->noswap)
 		goto redirty;
 
 	if (!total_swap_pages)
@@ -2910,15 +2910,15 @@ int shmem_lock(struct file *file, int lock, struct ucounts *ucounts)
 	 * ipc_lock_object() when called from shmctl_do_lock(),
 	 * no serialization needed when called from shm_destroy().
 	 */
-	if (lock && !(info->flags & VM_LOCKED)) {
+	if (lock && !(info->flags & SHMEM_F_LOCKED)) {
 		if (!user_shm_lock(inode->i_size, ucounts))
 			goto out_nomem;
-		info->flags |= VM_LOCKED;
+		info->flags |= SHMEM_F_LOCKED;
 		mapping_set_unevictable(file->f_mapping);
 	}
-	if (!lock && (info->flags & VM_LOCKED) && ucounts) {
+	if (!lock && (info->flags & SHMEM_F_LOCKED) && ucounts) {
 		user_shm_unlock(inode->i_size, ucounts);
-		info->flags &= ~VM_LOCKED;
+		info->flags &= ~SHMEM_F_LOCKED;
 		mapping_clear_unevictable(file->f_mapping);
 	}
 	retval = 0;
@@ -3062,7 +3062,9 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap,
 	spin_lock_init(&info->lock);
 	atomic_set(&info->stop_eviction, 0);
 	info->seals = F_SEAL_SEAL;
-	info->flags = flags & VM_NORESERVE;
+	info->flags = 0;
+	if (flags & VM_NORESERVE)
+		info->flags |= SHMEM_F_NORESERVE;
 	info->i_crtime = inode_get_mtime(inode);
 	info->fsflags = (dir == NULL) ? 0 :
 		SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
-- 
2.50.0.727.gbf7dc18ff4-goog

Hi all,

On Wed, Jun 25 2025, Pasha Tatashin wrote:

> From: Pratyush Yadav <ptyadav@amazon.de>
>
> shmem_inode_info::flags can have the VM flags VM_NORESERVE and
> VM_LOCKED. These are used to suppress pre-accounting or to lock the
> pages in the inode respectively. Using the VM flags directly makes it
> difficult to add shmem-specific flags that are unrelated to VM behavior
> since one would need to find a VM flag not used by shmem and re-purpose
> it.
>
> Introduce SHMEM_F_NORESERVE and SHMEM_F_LOCKED which represent the same
> information, but their bits are independent of the VM flags. Callers can
> still pass VM_NORESERVE to shmem_get_inode(), but it gets transformed to
> the shmem-specific flag internally.
>
> No functional changes intended.

I was reading through this patch again and just realized that I missed a
spot. __shmem_file_setup() passes VM flags to shmem_{un,}acct_size(),
even though it now expects SHMEM_F flag. Below fixup patch should fix
that.

--- 8< ---
From d027524e390de15af1c6d9310bf6bea0194be79f Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <ptyadav@amazon.de>
Date: Thu, 26 Jun 2025 14:50:27 +0200
Subject: [PATCH] fixup! mm: shmem: use SHMEM_F_* flags instead of VM_* flags

Signed-off-by: Pratyush Yadav <ptyadav@amazon.de>
---
 mm/shmem.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 6b13eb40e7dc2..83ae446f779ef 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -5809,8 +5809,10 @@ static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap,
 /* common code */
 
 static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name,
-			loff_t size, unsigned long flags, unsigned int i_flags)
+			loff_t size, unsigned long vm_flags,
+			unsigned int i_flags)
 {
+	unsigned long flags = (vm_flags & VM_NORESERVE) ? SHMEM_F_NORESERVE : 0;
 	struct inode *inode;
 	struct file *res;
 
@@ -5827,7 +5829,7 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name,
 		return ERR_PTR(-ENOMEM);
 
 	inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL,
-				S_IFREG | S_IRWXUGO, 0, flags);
+				S_IFREG | S_IRWXUGO, 0, vm_flags);
 	if (IS_ERR(inode)) {
 		shmem_unacct_size(flags, size);
 		return ERR_CAST(inode);
-- 
Regards,
Pratyush Yadav

On Thu, Jun 26, 2025 at 1:01 PM Pratyush Yadav <pratyush@kernel.org> wrote:
>
> Hi all,
>
> On Wed, Jun 25 2025, Pasha Tatashin wrote:
>
> > From: Pratyush Yadav <ptyadav@amazon.de>
> >
> > shmem_inode_info::flags can have the VM flags VM_NORESERVE and
> > VM_LOCKED. These are used to suppress pre-accounting or to lock the
> > pages in the inode respectively. Using the VM flags directly makes it
> > difficult to add shmem-specific flags that are unrelated to VM behavior
> > since one would need to find a VM flag not used by shmem and re-purpose
> > it.
> >
> > Introduce SHMEM_F_NORESERVE and SHMEM_F_LOCKED which represent the same
> > information, but their bits are independent of the VM flags. Callers can
> > still pass VM_NORESERVE to shmem_get_inode(), but it gets transformed to
> > the shmem-specific flag internally.
> >
> > No functional changes intended.
>
> I was reading through this patch again and just realized that I missed a
> spot. __shmem_file_setup() passes VM flags to shmem_{un,}acct_size(),
> even though it now expects SHMEM_F flag. Below fixup patch should fix
> that.

Added for v2.

Pasha