Fix a number of bugs in the NFS idmapper code:
(1) Only registered key types can be passed to the core keys code, so
register the legacy idmapper key type.
This is a requirement because the unregister function cleans up keys
belonging to that key type so that there aren't dangling pointers to the
module left behind - including the key->type pointer.
(2) Rename the legacy key type. You can't have two key types with the same
name, and (1) would otherwise require that.
(3) complete_request_key() must be called in the error path of
nfs_idmap_legacy_upcall().
(4) There is one idmap struct for each nfs_client struct. This means that
idmap->idmap_key_cons is shared without the use of a lock. This is a
problem because key_instantiate_and_link() - as called indirectly by
idmap_pipe_downcall() - releases anyone waiting for the key to be
instantiated.
What happens is that idmap_pipe_downcall() running in the rpc.idmapd
thread, releases the NFS filesystem in whatever thread that is running in
to continue. This may then make another idmapper call, overwriting
idmap_key_cons before idmap_pipe_downcall() gets the chance to call
complete_request_key().
I *think* that reading idmap_key_cons only once, before
key_instantiate_and_link() is called, and then caching the result in a
variable is sufficient.
Bug (4) is the cause of:
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [< (null)>] (null)
PGD 0
Oops: 0010 [#1] SMP
CPU 1
Modules linked in: ppdev parport_pc lp parport ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack nfs fscache xt_CHECKSUM auth_rpcgss iptable_mangle nfs_acl bridge stp llc lockd be2iscsi iscsi_boot_sysfs bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi cxgb3 mdio ib_iser rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi snd_hda_codec_realtek snd_usb_audio snd_hda_intel snd_hda_codec snd_seq snd_pcm snd_hwdep snd_usbmidi_lib snd_rawmidi snd_timer uvcvideo videobuf2_core videodev media videobuf2_vmalloc snd_seq_device videobuf2_memops e1000e vhost_net iTCO_wdt joydev coretemp snd soundcore macvtap macvlan i2c_i801 snd_page_alloc tun iTCO_vendor_support microcode kvm_intel kvm sunrpc hid_logitech_dj usb_storage i915 drm_kms_helper drm i2c_algo_bit i2c_core video [last unloaded: scsi_wait_scan]
Pid: 1229, comm: rpc.idmapd Not tainted 3.4.2-1.fc16.x86_64 #1 Gateway DX4710-UB801A/G33M05G1
RIP: 0010:[<0000000000000000>] [< (null)>] (null)
RSP: 0018:ffff8801a3645d40 EFLAGS: 00010246
RAX: ffff880077707e30 RBX: ffff880077707f50 RCX: ffff8801a18ccd80
RDX: 0000000000000006 RSI: ffff8801a3645e75 RDI: ffff880077707f50
RBP: ffff8801a3645d88 R08: ffff8801a430f9c0 R09: ffff8801a3645db0
R10: 000000000000000a R11: 0000000000000246 R12: ffff8801a18ccd80
R13: ffff8801a3645e75 R14: ffff8801a430f9c0 R15: 0000000000000006
FS: 00007fb6fb51a700(0000) GS:ffff8801afc80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 00000001a49b0000 CR4: 00000000000027e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process rpc.idmapd (pid: 1229, threadinfo ffff8801a3644000, task ffff8801a3bf9710)
Stack:
ffffffff81260878 ffff8801a3645db0 ffff8801a3645db0 ffff880077707a90
ffff880077707f50 ffff8801a18ccd80 0000000000000006 ffff8801a3645e75
ffff8801a430f9c0 ffff8801a3645dd8 ffffffff81260983 ffff8801a3645de8
Call Trace:
[<ffffffff81260878>] ? __key_instantiate_and_link+0x58/0x100
[<ffffffff81260983>] key_instantiate_and_link+0x63/0xa0
[<ffffffffa057062b>] idmap_pipe_downcall+0x1cb/0x1e0 [nfs]
[<ffffffffa0107f57>] rpc_pipe_write+0x67/0x90 [sunrpc]
[<ffffffff8117f833>] vfs_write+0xb3/0x180
[<ffffffff8117fb5a>] sys_write+0x4a/0x90
[<ffffffff81600329>] system_call_fastpath+0x16/0x1b
Code: Bad RIP value.
RIP [< (null)>] (null)
RSP <ffff8801a3645d40>
CR2: 0000000000000000
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Steve Dickson <steved@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org [>= 3.4]
It was initially coded under the assumption that there would only be one
request at a time, so use a lock to enforce this requirement..
Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
CC: stable@vger.kernel.org [3.4+]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Ensure that a process that uses the nfs_client->cl_cons_state test
for whether the initialisation process is finished does not read
stale data.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Since the struct nfs_client gets added to the global nfs_client_list
before it is initialised, it is possible that rpc_pipefs_event can
end up trying to create idmapper entries on such a thing.
The solution is to have the mount notification wait for the
initialisation of each nfs_client to complete, and then to
skip any entries for which the it failed.
Reported-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Clean up: When naming fields and data types, follow established
conventions to facilitate accurate grep/cscope searches.
Introduced by commit e50a7a1a "NFS: make NFS client allocated per
network namespace context," Tue Jan 10, 2012.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Obviously we should check for NULL here instead of IS_ERR().
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable@vger.kernel.org [3.4]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This is bug fix.
Notifier callback is called from SUNRPC module. So before dereferencing NFS
module we have to make sure, that it's alive.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
New features include:
- Add NFS client support for containers.
This should enable most of the necessary functionality, including
lockd support, and support for rpc.statd, NFSv4 idmapper and
RPCSEC_GSS upcalls into the correct network namespace from
which the mount system call was issued.
- NFSv4 idmapper scalability improvements
Base the idmapper cache on the keyring interface to allow concurrent
access to idmapper entries. Start the process of migrating users from
the single-threaded daemon-based approach to the multi-threaded
request-key based approach.
- NFSv4.1 implementation id.
Allows the NFSv4.1 client and server to mutually identify each other
for logging and debugging purposes.
- Support the 'vers=4.1' mount option for mounting NFSv4.1 instead of
having to use the more counterintuitive 'vers=4,minorversion=1'.
- SUNRPC tracepoints.
Start the process of adding tracepoints in order to improve debugging
of the RPC layer.
- pNFS object layout support for autologin.
Important bugfixes include:
- Fix a bug in rpc_wake_up/rpc_wake_up_status that caused them to fail
to wake up all tasks when applied to priority waitqueues.
- Ensure that we handle read delegations correctly, when we try to
truncate a file.
- A number of fixes for NFSv4 state manager loops (mostly to do with
delegation recovery).
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.12 (GNU/Linux)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=LuHE
-----END PGP SIGNATURE-----
Merge tag 'nfs-for-3.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull NFS client updates for Linux 3.4 from Trond Myklebust:
"New features include:
- Add NFS client support for containers.
This should enable most of the necessary functionality, including
lockd support, and support for rpc.statd, NFSv4 idmapper and
RPCSEC_GSS upcalls into the correct network namespace from which
the mount system call was issued.
- NFSv4 idmapper scalability improvements
Base the idmapper cache on the keyring interface to allow
concurrent access to idmapper entries. Start the process of
migrating users from the single-threaded daemon-based approach to
the multi-threaded request-key based approach.
- NFSv4.1 implementation id.
Allows the NFSv4.1 client and server to mutually identify each
other for logging and debugging purposes.
- Support the 'vers=4.1' mount option for mounting NFSv4.1 instead of
having to use the more counterintuitive 'vers=4,minorversion=1'.
- SUNRPC tracepoints.
Start the process of adding tracepoints in order to improve
debugging of the RPC layer.
- pNFS object layout support for autologin.
Important bugfixes include:
- Fix a bug in rpc_wake_up/rpc_wake_up_status that caused them to
fail to wake up all tasks when applied to priority waitqueues.
- Ensure that we handle read delegations correctly, when we try to
truncate a file.
- A number of fixes for NFSv4 state manager loops (mostly to do with
delegation recovery)."
* tag 'nfs-for-3.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (224 commits)
NFS: fix sb->s_id in nfs debug prints
xprtrdma: Remove assumption that each segment is <= PAGE_SIZE
xprtrdma: The transport should not bug-check when a dup reply is received
pnfs-obj: autologin: Add support for protocol autologin
NFS: Remove nfs4_setup_sequence from generic rename code
NFS: Remove nfs4_setup_sequence from generic unlink code
NFS: Remove nfs4_setup_sequence from generic read code
NFS: Remove nfs4_setup_sequence from generic write code
NFS: Fix more NFS debug related build warnings
SUNRPC/LOCKD: Fix build warnings when CONFIG_SUNRPC_DEBUG is undefined
nfs: non void functions must return a value
SUNRPC: Kill compiler warning when RPC_DEBUG is unset
SUNRPC/NFS: Add Kbuild dependencies for NFS_DEBUG/RPC_DEBUG
NFS: Use cond_resched_lock() to reduce latencies in the commit scans
NFSv4: It is not safe to dereference lsp->ls_state in release_lockowner
NFS: ncommit count is being double decremented
SUNRPC: We must not use list_for_each_entry_safe() in rpc_wake_up()
Try using machine credentials for RENEW calls
NFSv4.1: Fix a few issues in filelayout_commit_pagelist
NFSv4.1: Clean ups and bugfixes for the pNFS read/writeback/commit code
...
This function could fail to queue the upcall if rpc.idmapd is not running,
causing a warning message to be printed. Instead, I want to check the
return value and revoke the key if the upcall can't be run.
Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Fix a number of "warning: symbol 'foo' was not declared. Should it be
static?" conditions.
Fix 2 cases of "warning: Using plain integer as NULL pointer"
fs/nfs/delegation.c:263:31: warning: restricted fmode_t degrades to integer
- We want to allow upgrades to a WRITE delegation, but should otherwise
consider servers that hand out duplicate delegations to be borken.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch removes the old hashmap-based caching and instead uses a
"request key actor" to place an upcall to the legacy idmapper rather
than going through /sbin/request-key. This will only be used as a
fallback if /etc/request-key.conf isn't configured to use nfsidmap.
Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
v3:
1) Lookup for client is performed from the beginning of the list on each PipeFS
event handling operation.
Lockdep is sad otherwise, because inode mutex is taken on PipeFS dentry
creation, which can be called on mount notification, where this per-net client
lock is taken on clients list walk.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Don't allocate the legacy idmapper tables until we actually need
them.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Instead of pre-allocating the storage for all the strings, we can
significantly reduce the size of that table by doing the allocation
when we do the downcall.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
This patch makes nfs_clients_lock allocated per network namespace. All items it
protects are already network namespace aware.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch splits global list of NFS clients into per-net-ns array of lists.
This looks more strict and clearer.
BTW, this patch also makes "/proc/fs/nfsfs/servers" entry content depends on
/proc mount owner pid namespace. See below for details.
NOTE: few words about how was /proc/fs/nfsfs/ entries content show per network
namespace done. This is a little bit tricky and not the best is could be. But
it's cheap (proper fix for /proc conteinerization is a hard nut to crack).
The idea is simple: take proper network namespace from pid namespace
child reaper nsproxy of /proc/ mount creator.
This actually means, that if there are 2 containers with different net
namespace sharing pid namespace, then read of /proc/fs/nfsfs/ entries will
always return content, taken from net namespace of pid namespace creator task
(and thus second namespace set wil be unvisible).
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch removes the CONFIG_NFS_USE_NEW_IDMAPPER compile option.
First, the idmapper will attempt to map the id using /sbin/request-key
and nfsidmap. If this fails (if /etc/request-key.conf is not configured
properly) then the idmapper will call the legacy code to perform the
mapping. I left a comment stating where the legacy code begins to make
it easier for somebody to remove in the future.
Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch addresses printks that have some context to show that they are
from fs/nfs/, but for the sake of consistency now start with NFS:
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Messages like "Got error -10052 from the server on DESTROY_SESSION. Session
has been destroyed regardless" can be confusing to users who aren't very
familiar with NFS.
NOTE: This patch ignores any printks() that start by printing __func__ - that
will be in a separate patch.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
v2:
1) Added "nfs_idmap_init" and "nfs_idmap_quit" definitions for kernels built
without CONFIG_NFS_V4 option set.
This patch subscribes NFS clients to RPC pipefs notifications. Idmap notifier
is registering on NFS module load. This notifier callback is responsible for
creation/destruction of PipeFS idmap pipe dentry for NFS4 clients.
Since ipdmap pipe is created in rpc client pipefs directory, we have make sure,
that this directory has been created already. IOW RPC client notifier callback
has been called already. To achive this, PipeFS notifier priorities has been
introduced (RPC clients notifier priority is greater than NFS idmap one).
But this approach gives another problem: unlink for RPC client directory will
be called before NFS idmap pipe unlink on UMOUNT event and will fail, because
directory is not empty.
The solution, introduced in this patch, is to try to remove client directory
once again after idmap pipe was unlinked. This looks like ugly hack, so
probably it should be replaced in some more elegant way.
Note that no locking required in notifier callback because PipeFS superblock
pointer is passed as an argument from it's creation or destruction routine and
thus we can be sure about it's validity.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch makes NFS idmap pipes dentries allocated and destroyed in network
namespace context by PipeFS network namespace aware routines.
Network namespace context is obtained from nfs_client structure.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This is a cleanup patch. We don't need this reference anymore.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch is a final step towards to removing PipeFS inode references from
kernel code other than PipeFS itself. It makes all kernel SUNRPC PipeFS users
depends on pipe private data, which state depend on their specific operations,
etc.
This patch completes SUNRPC PipeFS preparations and allows to create pipe
private data and PipeFS dentries independently.
Next step will be making SUNPRC PipeFS dentries allocated by SUNRPC PipeFS
network namespace aware routines.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
RPC pipe upcall doesn't requires only private pipe data. Thus RPC inode
references in this code can be removed.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
The kernel contains some special internal keyrings, for instance the DNS
resolver keyring :
2a93faf1 I----- 1 perm 1f030000 0 0 keyring .dns_resolver: empty
It would occasionally be useful to allow the contents of such keyrings to be
flushed by root (cache invalidation).
Allow a flag to be set on a keyring to mark that someone possessing the
sysadmin capability can clear the keyring, even without normal write access to
the keyring.
Set this flag on the special keyrings created by the DNS resolver, the NFS
identity mapper and the CIFS identity mapper.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Steve Dickson <steved@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
...so that we can do the uid/gid mapping outside the asynchronous RPC
context.
This fixes a bug in the current NFSv4 atomic open code where the client
isn't able to determine what the true uid/gid fields of the file are,
(because the asynchronous nature of the OPEN call denies it the ability
to do an upcall) and so fills them with default values, marking the
inode as needing revalidation.
Unfortunately, in some cases, the VFS will do some additional sanity
checks on the file, and may override the server's decision to allow
the open because it sees the wrong owner/group fields.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
The same function is used by idmap, gss and blocklayout code. Make it
generic.
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Cc: stable@kernel.org [3.0]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Many stupid corrections of duplicated includes based on the output of
scripts/checkincludes.pl.
Signed-off-by: Vitaliy Ivanov <vitalivanov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
The new behaviour is enabled using the new module parameter
'nfs4_disable_idmapping'.
Note that if the server rejects an unmapped uid or gid, then
the client will automatically switch back to using the idmapper.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trivial, but confusing when you're trying to grep through this
code....
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
The intent was to test "*desc" for allocation failures, but it tests
"desc" which is always a valid pointer here.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch creates a new idmapper system that uses the request-key function to
place a call into userspace to map user and group ids to names. The old
idmapper was single threaded, which prevented more than one request from running
at a single time. This means that a user would have to wait for an upcall to
finish before accessing a cached result.
The upcall result is stored on a keyring of type id_resolver. See the file
Documentation/filesystems/nfs/idmapper.txt for instructions.
Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
[Trond: fix up the return value of nfs_idmap_lookup_name and clean up code]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
fs/nfs/nfs4state.c:788:34: warning: Using plain integer as NULL pointer
fs/nfs/delegation.c:52:34: warning: Using plain integer as NULL pointer
fs/nfs/idmap.c:312:12: warning: Using plain integer as NULL pointer
fs/nfs/callback_xdr.c:257:6: warning: Using plain integer as NULL pointer
fs/nfs/callback_xdr.c:270:6: warning: Using plain integer as NULL pointer
fs/nfs/callback_xdr.c:281:6: warning: Using plain integer as NULL pointer
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Clean up: always use the same type when handling buffer lengths. As a
bonus, this prevents a mixed sign comparison in idmap_lookup_name.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
The idmap_pipe_upcall() function expects the copy_to_user() function to
return a negative error value if the call fails, but copy_to_user()
returns an unsigned long number of bytes that couldn't be copied.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Clean up white space damage and use standard kernel coding conventions for
return statements.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Change all the uses of f_{dentry,vfsmnt} to f_path.{dentry,mnt} in the nfs
client code.
Signed-off-by: Josef "Jeff" Sipek <jsipek@cs.sunysb.edu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The attached patch makes NFS share superblocks between mounts from the same
server and FSID over the same protocol.
It does this by creating each superblock with a false root and returning the
real root dentry in the vfsmount presented by get_sb(). The root dentry set
starts off as an anonymous dentry if we don't already have the dentry for its
inode, otherwise it simply returns the dentry we already have.
We may thus end up with several trees of dentries in the superblock, and if at
some later point one of anonymous tree roots is discovered by normal filesystem
activity to be located in another tree within the superblock, the anonymous
root is named and materialises attached to the second tree at the appropriate
point.
Why do it this way? Why not pass an extra argument to the mount() syscall to
indicate the subpath and then pathwalk from the server root to the desired
directory? You can't guarantee this will work for two reasons:
(1) The root and intervening nodes may not be accessible to the client.
With NFS2 and NFS3, for instance, mountd is called on the server to get
the filehandle for the tip of a path. mountd won't give us handles for
anything we don't have permission to access, and so we can't set up NFS
inodes for such nodes, and so can't easily set up dentries (we'd have to
have ghost inodes or something).
With this patch we don't actually create dentries until we get handles
from the server that we can use to set up their inodes, and we don't
actually bind them into the tree until we know for sure where they go.
(2) Inaccessible symbolic links.
If we're asked to mount two exports from the server, eg:
mount warthog:/warthog/aaa/xxx /mmm
mount warthog:/warthog/bbb/yyy /nnn
We may not be able to access anything nearer the root than xxx and yyy,
but we may find out later that /mmm/www/yyy, say, is actually the same
directory as the one mounted on /nnn. What we might then find out, for
example, is that /warthog/bbb was actually a symbolic link to
/warthog/aaa/xxx/www, but we can't actually determine that by talking to
the server until /warthog is made available by NFS.
This would lead to having constructed an errneous dentry tree which we
can't easily fix. We can end up with a dentry marked as a directory when
it should actually be a symlink, or we could end up with an apparently
hardlinked directory.
With this patch we need not make assumptions about the type of a dentry
for which we can't retrieve information, nor need we assume we know its
place in the grand scheme of things until we actually see that place.
This patch reduces the possibility of aliasing in the inode and page caches for
inodes that may be accessed by more than one NFS export. It also reduces the
number of superblocks required for NFS where there are many NFS exports being
used from a server (home directory server + autofs for example).
This in turn makes it simpler to do local caching of network filesystems, as it
can then be guaranteed that there won't be links from multiple inodes in
separate superblocks to the same cache file.
Obviously, cache aliasing between different levels of NFS protocol could still
be a problem, but at least that gives us another key to use when indexing the
cache.
This patch makes the following changes:
(1) The server record construction/destruction has been abstracted out into
its own set of functions to make things easier to get right. These have
been moved into fs/nfs/client.c.
All the code in fs/nfs/client.c has to do with the management of
connections to servers, and doesn't touch superblocks in any way; the
remaining code in fs/nfs/super.c has to do with VFS superblock management.
(2) The sequence of events undertaken by NFS mount is now reordered:
(a) A volume representation (struct nfs_server) is allocated.
(b) A server representation (struct nfs_client) is acquired. This may be
allocated or shared, and is keyed on server address, port and NFS
version.
(c) If allocated, the client representation is initialised. The state
member variable of nfs_client is used to prevent a race during
initialisation from two mounts.
(d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find
the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we
are given the root FH in advance.
(e) The volume FSID is probed for on the root FH.
(f) The volume representation is initialised from the FSINFO record
retrieved on the root FH.
(g) sget() is called to acquire a superblock. This may be allocated or
shared, keyed on client pointer and FSID.
(h) If allocated, the superblock is initialised.
(i) If the superblock is shared, then the new nfs_server record is
discarded.
(j) The root dentry for this mount is looked up from the root FH.
(k) The root dentry for this mount is assigned to the vfsmount.
(3) nfs_readdir_lookup() creates dentries for each of the entries readdir()
returns; this function now attaches disconnected trees from alternate
roots that happen to be discovered attached to a directory being read (in
the same way nfs_lookup() is made to do for lookup ops).
The new d_materialise_unique() function is now used to do this, thus
permitting the whole thing to be done under one set of locks, and thus
avoiding any race between mount and lookup operations on the same
directory.
(4) The client management code uses a new debug facility: NFSDBG_CLIENT which
is set by echoing 1024 to /proc/net/sunrpc/nfs_debug.
(5) Clone mounts are now called xdev mounts.
(6) Use the dentry passed to the statfs() op as the handle for retrieving fs
statistics rather than the root dentry of the superblock (which is now a
dummy).
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Return an error when starting the idmapping pipe so that we can detect it
failing.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Rename struct nfs4_client to struct nfs_client so that it can become the basis
for a general client record for NFS2 and NFS3 in addition to NFS4.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Fix ups for the splitting of the superblock stuff out of fs/nfs/inode.c,
including:
(*) Move the callback tcpport module param into callback.c.
(*) Move the idmap cache timeout module param into idmap.c.
(*) Changes to internal.h:
(*) namespace-nfs4.c was renamed to nfs4namespace.c.
(*) nfs_stat_to_errno() is in nfs2xdr.c, not nfs4xdr.c.
(*) nfs4xdr.c is contingent on CONFIG_NFS_V4.
(*) nfs4_path() is only uses if CONFIG_NFS_V4 is set.
Plus also:
(*) The sec_flavours[] table should really be const.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
David Howells