mm: shmem: use SHMEM_F_* flags instead of VM_* flags

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.

Link: https://lkml.kernel.org/r/20251125165850.3389713-11-pasha.tatashin@soleen.com
Signed-off-by: Pratyush Yadav <ptyadav@amazon.de>
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: David Matlack <dmatlack@google.com>
Cc: Aleksander Lobakin <aleksander.lobakin@intel.com>
Cc: Alexander Graf <graf@amazon.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andriy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: anish kumar <yesanishhere@gmail.com>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Chanwoo Choi <cw00.choi@samsung.com>
Cc: Chen Ridong <chenridong@huawei.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Wagner <wagi@kernel.org>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Jeffery <djeffery@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guixin Liu <kanie@linux.alibaba.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joanthan Cameron <Jonathan.Cameron@huawei.com>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lennart Poettering <lennart@poettering.net>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Matthew Maurer <mmaurer@google.com>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Myugnjoo Ham <myungjoo.ham@samsung.com>
Cc: Parav Pandit <parav@nvidia.com>
Cc: Pratyush Yadav <pratyush@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: Samiullah Khawaja <skhawaja@google.com>
Cc: Song Liu <song@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Stuart Hayes <stuart.w.hayes@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: William Tu <witu@nvidia.com>
Cc: Yoann Congal <yoann.congal@smile.fr>
Cc: Zhu Yanjun <yanjun.zhu@linux.dev>
Cc: Zijun Hu <quic_zijuhu@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 0e47465ef0fd506638c0b972e1e98a9815208b1a..650874b400b51eba0f43366eff5a57c45ed7c170 100644 (file)
--- 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>
 
 struct swap_iocb;
 
@@ -19,6 +20,11 @@ struct swap_iocb;
 #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 58701d14dd96cd4aaf17f817c6a8eaa05086bfc9..1d5036dec08a1516305be32dcff07d676d34d637 100644 (file)
--- 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));
 }
 
@@ -1551,7 +1551,7 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
        int nr_pages;
        bool split = false;
 
-       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 +3062,7 @@ 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 = (flags & VM_NORESERVE) ? SHMEM_F_NORESERVE : 0;
        info->i_crtime = inode_get_mtime(inode);
        info->fsflags = (dir == NULL) ? 0 :
                SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
@@ -5804,8 +5804,10 @@ 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;
 
@@ -5822,7 +5824,7 @@ 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);