shmem: add support to ignore swap

In doing experimentations with shmem having the option to avoid swap
becomes a useful mechanism. One of the *raves* about brd over shmem is
you can avoid swap, but that's not really a good reason to use brd if we
can instead use shmem. Using brd has its own good reasons to exist, but
just because "tmpfs" doesn't let you do that is not a great reason to
avoid it if we can easily add support for it.

I don't add support for reconfiguring incompatible options, but if we
really wanted to we can add support for that.

To avoid swap we use mapping_set_unevictable() upon inode creation, and
put a WARN_ON_ONCE() stop-gap on writepages() for reclaim.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Luis Chamberlain <[e-mail]>
Acked-by: Christian Brauner <[e-mail]>
Tested-by: Xin Hao <[e-mail]>
Reviewed-by: Davidlohr Bueso <[e-mail]>
Cc: Adam Manzanares <[e-mail]>
Cc: David Hildenbrand <[e-mail]>
Cc: Davidlohr Bueso <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Kees Cook <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Cc: Pankaj Raghav <[e-mail]>
Cc: Yosry Ahmed <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

Documentation/filesystems/tmpfs.rst

···
 
 tmpfs puts everything into the kernel internal caches and grows and
 shrinks to accommodate the files it contains and is able to swap
-unneeded pages out to swap space, and supports THP.
+unneeded pages out to swap space, if swap was enabled for the tmpfs
+mount. tmpfs also supports THP.
 
 tmpfs extends ramfs with a few userspace configurable options listed and
 explained further below, some of which can be reconfigured dynamically on the
···
 Contrary to brd ramdisks, tmpfs has its own filesystem, it does not rely on the
 block layer at all.
 
-Since tmpfs lives completely in the page cache and on swap, all tmpfs
-pages will be shown as "Shmem" in /proc/meminfo and "Shared" in
+Since tmpfs lives completely in the page cache and optionally on swap,
+all tmpfs pages will be shown as "Shmem" in /proc/meminfo and "Shared" in
 free(1). Notice that these counters also include shared memory
 (shmem, see ipcs(1)). The most reliable way to get the count is
 using df(1) and du(1).
···
            is half of the number of your physical RAM pages, or (on a
            machine with highmem) the number of lowmem RAM pages,
            whichever is the lower.
+noswap     Disables swap. Remounts must respect the original settings.
+           By default swap is enabled.
 =========  ============================================================
 
 These parameters accept a suffix k, m or g for kilo, mega and giga and

Documentation/mm/unevictable-lru.rst

···
 
  * Those owned by ramfs.
 
+ * Those owned by tmpfs with the noswap mount option.
+
  * Those mapped into SHM_LOCK'd shared memory regions.
 
  * Those mapped into VM_LOCKED [mlock()ed] VMAs.

include/linux/shmem_fs.h

···
 	kuid_t uid;		    /* Mount uid for root directory */
 	kgid_t gid;		    /* Mount gid for root directory */
 	bool full_inums;	    /* If i_ino should be uint or ino_t */
+	bool noswap;		    /* ignores VM reclaim / swap requests */
 	ino_t next_ino;		    /* The next per-sb inode number to use */
 	ino_t __percpu *ino_batch;  /* The next per-cpu inode number to use */
 	struct mempolicy *mpol;     /* default memory policy for mappings */

mm/shmem.c

···
 	bool full_inums;
 	int huge;
 	int seen;
+	bool noswap;
 #define SHMEM_SEEN_BLOCKS 1
 #define SHMEM_SEEN_INODES 2
 #define SHMEM_SEEN_HUGE 4
 #define SHMEM_SEEN_INUMS 8
+#define SHMEM_SEEN_NOSWAP 16
 };
 
 #ifdef CONFIG_TMPFS
···
 	struct address_space *mapping = folio->mapping;
 	struct inode *inode = mapping->host;
 	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	swp_entry_t swap;
 	pgoff_t index;
 
···
 	if (WARN_ON_ONCE(!wbc->for_reclaim))
 		goto redirty;
 
-	if (WARN_ON_ONCE(info->flags & VM_LOCKED))
+	if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap))
 		goto redirty;
 
 	if (!total_swap_pages)
···
 			shmem_set_inode_flags(inode, info->fsflags);
 		INIT_LIST_HEAD(&info->shrinklist);
 		INIT_LIST_HEAD(&info->swaplist);
+		if (sbinfo->noswap)
+			mapping_set_unevictable(inode->i_mapping);
 		simple_xattrs_init(&info->xattrs);
 		cache_no_acl(inode);
 		mapping_set_large_folios(inode->i_mapping);
···
 	Opt_uid,
 	Opt_inode32,
 	Opt_inode64,
+	Opt_noswap,
 };
 
 static const struct constant_table shmem_param_enums_huge[] = {
···
 	fsparam_u32   ("uid",		Opt_uid),
 	fsparam_flag  ("inode32",	Opt_inode32),
 	fsparam_flag  ("inode64",	Opt_inode64),
+	fsparam_flag  ("noswap",	Opt_noswap),
 	{}
 };
 
···
 		}
 		ctx->full_inums = true;
 		ctx->seen |= SHMEM_SEEN_INUMS;
+		break;
+	case Opt_noswap:
+		ctx->noswap = true;
+		ctx->seen |= SHMEM_SEEN_NOSWAP;
 		break;
 	}
 	return 0;
···
 		err = "Current inum too high to switch to 32-bit inums";
 		goto out;
 	}
+	if ((ctx->seen & SHMEM_SEEN_NOSWAP) && ctx->noswap && !sbinfo->noswap) {
+		err = "Cannot disable swap on remount";
+		goto out;
+	}
+	if (!(ctx->seen & SHMEM_SEEN_NOSWAP) && !ctx->noswap && sbinfo->noswap) {
+		err = "Cannot enable swap on remount if it was disabled on first mount";
+		goto out;
+	}
 
 	if (ctx->seen & SHMEM_SEEN_HUGE)
 		sbinfo->huge = ctx->huge;
···
 		sbinfo->mpol = ctx->mpol;	/* transfers initial ref */
 		ctx->mpol = NULL;
 	}
+
+	if (ctx->noswap)
+		sbinfo->noswap = true;
+
 	raw_spin_unlock(&sbinfo->stat_lock);
 	mpol_put(mpol);
 	return 0;
···
 		seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge));
 #endif
 	shmem_show_mpol(seq, sbinfo->mpol);
+	if (sbinfo->noswap)
+		seq_printf(seq, ",noswap");
 	return 0;
 }
 
···
 			ctx->inodes = shmem_default_max_inodes();
 		if (!(ctx->seen & SHMEM_SEEN_INUMS))
 			ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64);
+		sbinfo->noswap = ctx->noswap;
 	} else {
 		sb->s_flags |= SB_NOUSER;
 	}