user/sven/linux.git/fs, branch v3.3.4

tcp: allow splice() to build full TSO packets

2012-04-27T17:16:54Z

[ This combines upstream commit 2f53384424251c06038ae612e56231b96ab610ee and the follow-on bug fix commit 35f9c09fe9c72eb8ca2b8e89a593e1c151f28fc2 ] vmsplice()/splice(pipe, socket) call do_tcp_sendpages() one page at a time, adding at most 4096 bytes to an skb. (assuming PAGE_SIZE=4096) The call to tcp_push() at the end of do_tcp_sendpages() forces an immediate xmit when pipe is not already filled, and tso_fragment() try to split these skb to MSS multiples. 4096 bytes are usually split in a skb with 2 MSS, and a remaining sub-mss skb (assuming MTU=1500) This makes slow start suboptimal because many small frames are sent to qdisc/driver layers instead of big ones (constrained by cwnd and packets in flight of course) In fact, applications using sendmsg() (adding an additional memory copy) instead of vmsplice()/splice()/sendfile() are a bit faster because of this anomaly, especially if serving small files in environments with large initial [c]wnd. Call tcp_push() only if MSG_MORE is not set in the flags parameter. This bit is automatically provided by splice() internals but for the last page, or on all pages if user specified SPLICE_F_MORE splice() flag. In some workloads, this can reduce number of sent logical packets by an order of magnitude, making zero-copy TCP actually faster than one-copy :) Reported-by: Tom Herbert Cc: Nandita Dukkipati Cc: Neal Cardwell Cc: Tom Herbert Cc: Yuchung Cheng Cc: H.K. Jerry Chu Cc: Maciej Żenczykowski Cc: Mahesh Bandewar Cc: Ilpo Järvinen Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman

lockd: fix the endianness bug

2012-04-27T17:16:53Z

commit e847469bf77a1d339274074ed068d461f0c872bc upstream. comparing be32 values for < is not doing the right thing... Signed-off-by: Al Viro Cc: "J. Bruce Fields" Cc: Trond Myklebust Signed-off-by: Greg Kroah-Hartman

ocfs2: ->e_leaf_clusters endianness breakage

2012-04-27T17:16:53Z

commit 72094e43e3af5020510f920321d71f1798fa896d upstream. le16, not le32... Signed-off-by: Al Viro Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Greg Kroah-Hartman

ocfs2: ->rl_count endianness breakage

2012-04-27T17:16:53Z

commit 28748b325dc2d730ccc312830a91c4ae0c0d9379 upstream. le16, not le32... Signed-off-by: Al Viro Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Greg Kroah-Hartman

ocfs: ->rl_used breakage on big-endian

2012-04-27T17:16:53Z

commit e1bf4cc620fd143766ddfcee3b004a1d1bb34fd0 upstream. it's le16, not le32 or le64... Signed-off-by: Al Viro Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Greg Kroah-Hartman

ocfs2: ->l_next_free_req breakage on big-endian

2012-04-27T17:16:53Z

commit 3a251f04fe97c3d335b745c98e4b377e3c3899f2 upstream. It's le16, not le32... Signed-off-by: Al Viro Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Greg Kroah-Hartman

btrfs: btrfs_root_readonly() broken on big-endian

2012-04-27T17:16:53Z

commit 6ed3cf2cdfce4c9f1d73171bd3f27d9cb77b734e upstream. ->root_flags is __le64 and all accesses to it go through the helpers that do proper conversions. Except for btrfs_root_readonly(), which checks bit 0 as in host-endian... Signed-off-by: Al Viro Cc: Chris Mason Signed-off-by: Greg Kroah-Hartman

nfsd: fix compose_entry_fh() failure exits

2012-04-27T17:16:52Z

commit efe39651f08813180f37dc508d950fc7d92b29a8 upstream. Restore the original logics ("fail on mountpoints, negatives and in case of fh_compose() failures"). Since commit 8177e (nfsd: clean up readdirplus encoding) that got broken - rv = fh_compose(fhp, exp, dchild, &cd->fh); if (rv) goto out; if (!dchild->d_inode) goto out; rv = 0; out: is equivalent to rv = fh_compose(fhp, exp, dchild, &cd->fh); out: and the second check has no effect whatsoever... Signed-off-by: Al Viro Cc: "J. Bruce Fields" Signed-off-by: Greg Kroah-Hartman

nfsd: fix endianness breakage in TEST_STATEID handling

2012-04-27T17:16:52Z

commit 02f5fde5df0ea930e70f93763dd48beff182b208 upstream. ->ts_id_status gets nfs errno, i.e. it's already big-endian; no need to apply htonl() to it. Broken by commit 174568 (NFSD: Added TEST_STATEID operation) last year... Signed-off-by: Al Viro Cc: "J. Bruce Fields" Signed-off-by: Greg Kroah-Hartman

nfsd: fix error values returned by nfsd4_lockt() when nfsd_open() fails

2012-04-27T17:16:52Z

commit 04da6e9d63427b2d0fd04766712200c250b3278f upstream. nfsd_open() already returns an NFS error value; only vfs_test_lock() result needs to be fed through nfserrno(). Broken by commit 55ef12 (nfsd: Ensure nfsv4 calls the underlying filesystem on LOCKT) three years ago... Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman