virtiofs: implement FUSE_INIT map_alignment field

The device communicates FUSE_SETUPMAPPING/FUSE_REMOVMAPPING alignment
constraints via the FUST_INIT map_alignment field.  Parse this field and
ensure our DAX mappings meet the alignment constraints.

We don't actually align anything differently since our mappings are
already 2MB aligned.  Just check the value when the connection is
established.  If it becomes necessary to honor arbitrary alignments in
the future we'll have to adjust how mappings are sized.

The upshot of this commit is that we can be confident that mappings will
work even when emulating x86 on Power and similar combinations where the
host page sizes are different.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

4 files changed, 34 insertions, 3 deletions

diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 031106020f75..fec8a2bd75b3 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -9,7 +9,10 @@
 #include <linux/dax.h>
 #include <linux/pfn_t.h>
 
-/* Default memory range size, 2MB */
+/*
+ * Default memory range size.  A power of 2 so it agrees with common FUSE_INIT
+ * map_alignment values 4KB and 64KB.
+ */
 #define FUSE_DAX_SHIFT	21
 #define FUSE_DAX_SZ	(1 << FUSE_DAX_SHIFT)
 #define FUSE_DAX_PAGES	(FUSE_DAX_SZ / PAGE_SIZE)
@@ -123,3 +126,13 @@ int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
 	fc->dax = fcd;
 	return 0;
 }
+
+bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment)
+{
+	if (fc->dax && (map_alignment > FUSE_DAX_SHIFT)) {
+		pr_warn("FUSE: map_alignment %u incompatible with dax mem range size %u\n",
+			map_alignment, FUSE_DAX_SZ);
+		return false;
+	}
+	return true;
+}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 97af7952373a..2f3f04aa64c7 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1106,5 +1106,6 @@ void fuse_free_conn(struct fuse_conn *fc);
 
 int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
 void fuse_dax_conn_free(struct fuse_conn *fc);
+bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
 
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1780dfe063ab..67e99cee5a4f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -908,9 +908,10 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_args *args,
 {
 	struct fuse_init_args *ia = container_of(args, typeof(*ia), args);
 	struct fuse_init_out *arg = &ia->out;
+	bool ok = true;
 
 	if (error || arg->major != FUSE_KERNEL_VERSION)
-		fc->conn_error = 1;
+		ok = false;
 	else {
 		unsigned long ra_pages;
 
@@ -973,6 +974,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_args *args,
 					min_t(unsigned int, FUSE_MAX_MAX_PAGES,
 					max_t(unsigned int, arg->max_pages, 1));
 			}
+			if (IS_ENABLED(CONFIG_FUSE_DAX) &&
+			    arg->flags & FUSE_MAP_ALIGNMENT &&
+			    !fuse_dax_check_alignment(fc, arg->map_alignment)) {
+				ok = false;
+			}
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -988,6 +994,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_args *args,
 	}
 	kfree(ia);
 
+	if (!ok) {
+		fc->conn_init = 0;
+		fc->conn_error = 1;
+	}
+
 	fuse_set_initialized(fc);
 	wake_up_all(&fc->blocked_waitq);
 }
@@ -1011,6 +1022,10 @@ void fuse_send_init(struct fuse_conn *fc)
 		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
 		FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA;
+#ifdef CONFIG_FUSE_DAX
+	if (fc->dax)
+		ia->in.flags |= FUSE_MAP_ALIGNMENT;
+#endif
 	ia->args.opcode = FUSE_INIT;
 	ia->args.in_numargs = 1;
 	ia->args.in_args[0].size = sizeof(ia->in);
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 373cada89815..5b85819e045f 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -313,7 +313,9 @@ struct fuse_file_lock {
  * FUSE_CACHE_SYMLINKS: cache READLINK responses
  * FUSE_NO_OPENDIR_SUPPORT: kernel supports zero-message opendir
  * FUSE_EXPLICIT_INVAL_DATA: only invalidate cached pages on explicit request
- * FUSE_MAP_ALIGNMENT: map_alignment field is valid
+ * FUSE_MAP_ALIGNMENT: init_out.map_alignment contains log2(byte alignment) for
+ *		       foffset and moffset fields in struct
+ *		       fuse_setupmapping_out and fuse_removemapping_one.
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)