ceph: fix inode number handling on arches with 32-bit ino_t

Tuan and Ulrich mentioned that they were hitting a problem on s390x,
which has a 32-bit ino_t value, even though it's a 64-bit arch (for
historical reasons).

I think the current handling of inode numbers in the ceph driver is
wrong. It tries to use 32-bit inode numbers on 32-bit arches, but that's
actually not a problem. 32-bit arches can deal with 64-bit inode numbers
just fine when userland code is compiled with LFS support (the common
case these days).

What we really want to do is just use 64-bit numbers everywhere, unless
someone has mounted with the ino32 mount option. In that case, we want
to ensure that we hash the inode number down to something that will fit
in 32 bits before presenting the value to userland.

Add new helper functions that do this, and only do the conversion before
presenting these values to userland in getattr and readdir.

The inode table hashvalue is changed to just cast the inode number to
unsigned long, as low-order bits are the most likely to vary anyway.

While it's not strictly required, we do want to put something in
inode->i_ino. Instead of basing it on BITS_PER_LONG, however, base it on
the size of the ino_t type.

NOTE: This is a user-visible change on 32-bit arches:

1/ inode numbers will be seen to have changed between kernel versions.
   32-bit arches will see large inode numbers now instead of the hashed
   ones they saw before.

2/ any really old software not built with LFS support may start failing
   stat() calls with -EOVERFLOW on inode numbers >2^32. Nothing much we
   can do about these, but hopefully the intersection of people running
   such code on ceph will be very small.

The workaround for both problems is to mount with "-o ino32".

[ idryomov: changelog tweak ]

URL: https://tracker.ceph.com/issues/46828
Reported-by: Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
Reported-and-Tested-by: Tuan Hoang1 <Tuan.Hoang1@ibm.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 13 insertions, 18 deletions

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 060bdcc5ce32..040eaad9d063 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -259,9 +259,7 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 			     dentry, dentry, d_inode(dentry));
 			ctx->pos = di->offset;
 			if (!dir_emit(ctx, dentry->d_name.name,
-				      dentry->d_name.len,
-				      ceph_translate_ino(dentry->d_sb,
-							 d_inode(dentry)->i_ino),
+				      dentry->d_name.len, ceph_present_inode(d_inode(dentry)),
 				      d_inode(dentry)->i_mode >> 12)) {
 				dput(dentry);
 				err = 0;
@@ -324,18 +322,21 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	/* always start with . and .. */
 	if (ctx->pos == 0) {
 		dout("readdir off 0 -> '.'\n");
-		if (!dir_emit(ctx, ".", 1, 
-			    ceph_translate_ino(inode->i_sb, inode->i_ino),
+		if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode),
 			    inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 1;
 	}
 	if (ctx->pos == 1) {
-		ino_t ino = parent_ino(file->f_path.dentry);
+		u64 ino;
+		struct dentry *dentry = file->f_path.dentry;
+
+		spin_lock(&dentry->d_lock);
+		ino = ceph_present_inode(dentry->d_parent->d_inode);
+		spin_unlock(&dentry->d_lock);
+
 		dout("readdir off 1 -> '..'\n");
-		if (!dir_emit(ctx, "..", 2,
-			    ceph_translate_ino(inode->i_sb, ino),
-			    inode->i_mode >> 12))
+		if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 2;
 	}
@@ -507,9 +508,6 @@ more:
 	}
 	for (; i < rinfo->dir_nr; i++) {
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
-		struct ceph_vino vino;
-		ino_t ino;
-		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -519,13 +517,10 @@ more:
 		     rde->name_len, rde->name, &rde->inode.in);
 
 		BUG_ON(!rde->inode.in);
-		ftype = le32_to_cpu(rde->inode.in->mode) >> 12;
-		vino.ino = le64_to_cpu(rde->inode.in->ino);
-		vino.snap = le64_to_cpu(rde->inode.in->snapid);
-		ino = ceph_vino_to_ino(vino);
 
 		if (!dir_emit(ctx, rde->name, rde->name_len,
-			      ceph_translate_ino(inode->i_sb, ino), ftype)) {
+			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
+			      le32_to_cpu(rde->inode.in->mode) >> 12)) {
 			dout("filldir stopping us...\n");
 			return 0;
 		}
@@ -1161,7 +1156,7 @@ retry:
 
 	if (try_async && op == CEPH_MDS_OP_UNLINK &&
 	    (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) {
-		dout("async unlink on %lu/%.*s caps=%s", dir->i_ino,
+		dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir),
 		     dentry->d_name.len, dentry->d_name.name,
 		     ceph_cap_string(req->r_dir_caps));
 		set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);