)]}' { "log": [ { "commit": "2dec51466a08ac1c67da41bfd0518d43d983a2eb", "tree": "b6df8d1c1dfe41b4aa89d42ba9864358e6eea1d3", "parents": [ "fd6840714d9cf6e93f1d42b904860a94df316b85" ], "author": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Tue Sep 12 11:53:23 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:25:02 2006 -0400" }, "message": "NFSv4: It\u0027s perfectly legal for clp to be NULL here....\n\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "297de4f65698ee1e1c75e27d57933b5fa8227e72", "tree": "b04698edae97e64b3ad5290b33a9233f97f48c77", "parents": [ "058ad9cbf14b3c7480d01b20280cb4d5858f7a50" ], "author": { "name": "andros@citi.umich.edu", "email": "andros@citi.umich.edu", "time": "Tue Aug 29 12:19:41 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:56 2006 -0400" }, "message": "Fix a referral error Oops\n\nFix an oops when the referral server is not responding.\nCheck the error return from nfs4_set_client() in nfs4_create_referral_server.\n\nSigned-off-by: Andy Adamson \u003candros@citi.umich.edu\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "6daabf1b04c89f1fbd8eab5450261360943c8e20", "tree": "a4aa0653c5edaf6deb41a10c16b8476f331e7c72", "parents": [ "158998b6fe36f6acef087f574c96d44713499cc9" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Thu Aug 24 15:44:16 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:55 2006 -0400" }, "message": "NFS: Fix up compiler warnings on 64-bit platforms in client.c\n\nFix up warnings from compiling on ppc64.\n\nSigned-Off-By: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "5dd3177ae5012c1e2ad7a9ffdbd0e0d0de2f60e4", "tree": "2a8730d6443f6d33e8879cfc323396f9a570b97b", "parents": [ "275a082fe9308e710324e26ccb5363c53d8fd45f" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Thu Aug 24 01:03:05 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:54 2006 -0400" }, "message": "NFSv4: Fix a use-after-free issue with the nfs server.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "41877d207c46f050b709f452703ade20c3b4a096", "tree": "a0da315e01e6008823dcc46c602e13c550a085a8", "parents": [ "e1ec78928b4d5a31b7a847e65c6009f4229f7c0f" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Tue Aug 22 20:06:20 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:50 2006 -0400" }, "message": "NFS: Convert NFS client to use new rpc_create() API\n\nConvert NFS client mount logic to use rpc_create() instead of the old\nxprt_create_proto/rpc_create_client API.\n\nTest plan:\nMount stress tests.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "9c5bf38d85a31b946664bcc21078ef5bb10672f7", "tree": "cceee456ebefe2380a417746b366d67a11ec6ebe", "parents": [ "36b15c54cd0d6f707a3ac03e4a2a60bb530a95b9" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Tue Aug 22 20:06:14 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:38 2006 -0400" }, "message": "NFS: Fix nfs_alloc_client()\n\nThe scheme to indicate which services have been started up appears to be\nseriously broken.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "27ba851244f627a302d0fc6469d1ad413fc34fcb", "tree": "383016ee3e96fe7acf62067bda1ed70371ab4640", "parents": [ "6aaca566503296a73f956908ec98173946134fe2" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Sun Jul 30 14:40:56 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:37 2006 -0400" }, "message": "NFS: Fix error handling\n\nFix an error handling problem: nfs_put_client() can be given a NULL pointer if\nnfs_free_server() is asked to destroy a partially initialised record.\n\nSigned-Off-By: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "6aaca566503296a73f956908ec98173946134fe2", "tree": "7625bbfa14cddd93ed3e2afa03caf4b553116f76", "parents": [ "54ceac4515986030c2502960be620198dd8fe25b" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Tue Aug 22 20:06:13 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:37 2006 -0400" }, "message": "NFS: Add server and volume lists to /proc\n\nMake two new proc files available:\n\n\t/proc/fs/nfsfs/servers\n\t/proc/fs/nfsfs/volumes\n\nThe first lists the servers with which we are currently dealing (struct\nnfs_client), and the second lists the volumes we have on those servers (struct\nnfs_server).\n\nSigned-Off-By: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "54ceac4515986030c2502960be620198dd8fe25b", "tree": "b4ae4305c5652c0fe883ef5ea3243da91dbd2b34", "parents": [ "cf6d7b5de8535a9f0088c5cc28ee2dae87371b4a" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Tue Aug 22 20:06:13 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:37 2006 -0400" }, "message": "NFS: Share NFS superblocks per-protocol per-server per-FSID\n\nThe attached patch makes NFS share superblocks between mounts from the same\nserver and FSID over the same protocol.\n\nIt does this by creating each superblock with a false root and returning the\nreal root dentry in the vfsmount presented by get_sb(). The root dentry set\nstarts off as an anonymous dentry if we don\u0027t already have the dentry for its\ninode, otherwise it simply returns the dentry we already have.\n\nWe may thus end up with several trees of dentries in the superblock, and if at\nsome later point one of anonymous tree roots is discovered by normal filesystem\nactivity to be located in another tree within the superblock, the anonymous\nroot is named and materialises attached to the second tree at the appropriate\npoint.\n\nWhy do it this way? Why not pass an extra argument to the mount() syscall to\nindicate the subpath and then pathwalk from the server root to the desired\ndirectory? You can\u0027t guarantee this will work for two reasons:\n\n (1) The root and intervening nodes may not be accessible to the client.\n\n With NFS2 and NFS3, for instance, mountd is called on the server to get\n the filehandle for the tip of a path. mountd won\u0027t give us handles for\n anything we don\u0027t have permission to access, and so we can\u0027t set up NFS\n inodes for such nodes, and so can\u0027t easily set up dentries (we\u0027d have to\n have ghost inodes or something).\n\n With this patch we don\u0027t actually create dentries until we get handles\n from the server that we can use to set up their inodes, and we don\u0027t\n actually bind them into the tree until we know for sure where they go.\n\n (2) Inaccessible symbolic links.\n\n If we\u0027re asked to mount two exports from the server, eg:\n\n\tmount warthog:/warthog/aaa/xxx /mmm\n\tmount warthog:/warthog/bbb/yyy /nnn\n\n We may not be able to access anything nearer the root than xxx and yyy,\n but we may find out later that /mmm/www/yyy, say, is actually the same\n directory as the one mounted on /nnn. What we might then find out, for\n example, is that /warthog/bbb was actually a symbolic link to\n /warthog/aaa/xxx/www, but we can\u0027t actually determine that by talking to\n the server until /warthog is made available by NFS.\n\n This would lead to having constructed an errneous dentry tree which we\n can\u0027t easily fix. We can end up with a dentry marked as a directory when\n it should actually be a symlink, or we could end up with an apparently\n hardlinked directory.\n\n With this patch we need not make assumptions about the type of a dentry\n for which we can\u0027t retrieve information, nor need we assume we know its\n place in the grand scheme of things until we actually see that place.\n\nThis patch reduces the possibility of aliasing in the inode and page caches for\ninodes that may be accessed by more than one NFS export. It also reduces the\nnumber of superblocks required for NFS where there are many NFS exports being\nused from a server (home directory server + autofs for example).\n\nThis in turn makes it simpler to do local caching of network filesystems, as it\ncan then be guaranteed that there won\u0027t be links from multiple inodes in\nseparate superblocks to the same cache file.\n\nObviously, cache aliasing between different levels of NFS protocol could still\nbe a problem, but at least that gives us another key to use when indexing the\ncache.\n\nThis patch makes the following changes:\n\n (1) The server record construction/destruction has been abstracted out into\n its own set of functions to make things easier to get right. These have\n been moved into fs/nfs/client.c.\n\n All the code in fs/nfs/client.c has to do with the management of\n connections to servers, and doesn\u0027t touch superblocks in any way; the\n remaining code in fs/nfs/super.c has to do with VFS superblock management.\n\n (2) The sequence of events undertaken by NFS mount is now reordered:\n\n (a) A volume representation (struct nfs_server) is allocated.\n\n (b) A server representation (struct nfs_client) is acquired. This may be\n \t allocated or shared, and is keyed on server address, port and NFS\n \t version.\n\n (c) If allocated, the client representation is initialised. The state\n \t member variable of nfs_client is used to prevent a race during\n \t initialisation from two mounts.\n\n (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find\n \t the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we\n \t are given the root FH in advance.\n\n (e) The volume FSID is probed for on the root FH.\n\n (f) The volume representation is initialised from the FSINFO record\n \t retrieved on the root FH.\n\n (g) sget() is called to acquire a superblock. This may be allocated or\n \t shared, keyed on client pointer and FSID.\n\n (h) If allocated, the superblock is initialised.\n\n (i) If the superblock is shared, then the new nfs_server record is\n \t discarded.\n\n (j) The root dentry for this mount is looked up from the root FH.\n\n (k) The root dentry for this mount is assigned to the vfsmount.\n\n (3) nfs_readdir_lookup() creates dentries for each of the entries readdir()\n returns; this function now attaches disconnected trees from alternate\n roots that happen to be discovered attached to a directory being read (in\n the same way nfs_lookup() is made to do for lookup ops).\n\n The new d_materialise_unique() function is now used to do this, thus\n permitting the whole thing to be done under one set of locks, and thus\n avoiding any race between mount and lookup operations on the same\n directory.\n\n (4) The client management code uses a new debug facility: NFSDBG_CLIENT which\n is set by echoing 1024 to /proc/net/sunrpc/nfs_debug.\n\n (5) Clone mounts are now called xdev mounts.\n\n (6) Use the dentry passed to the statfs() op as the handle for retrieving fs\n statistics rather than the root dentry of the superblock (which is now a\n dummy).\n\nSigned-Off-By: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "5006a76cca8f86c6975c16fcf67e83b8b0eee2b6", "tree": "fbe711871729ddfc921e91ba86202a15c5a1a55f", "parents": [ "8fa5c000d7f986ef9cdc6d95f9f7fcee20e0a7d6" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Tue Aug 22 20:06:12 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:36 2006 -0400" }, "message": "NFS: Eliminate client_sys in favour of cl_rpcclient\n\nEliminate nfs_server::client_sys in favour of nfs_client::cl_rpcclient as we\nonly really need one per server that we\u0027re talking to since it doesn\u0027t have any\nsecurity on it.\n\nThe retransmission management variables are also moved to the common struct as\nthey\u0027re required to set up the cl_rpcclient connection.\n\nThe NFS2/3 client and client_acl connections are thenceforth derived by cloning\nthe cl_rpcclient connection and post-applying the authorisation flavour.\n\nThe code for setting up the initial common connection has been moved to\nclient.c as nfs_create_rpc_client(). All the NFS program definition tables are\nalso moved there as that\u0027s where they\u0027re now required rather than super.c.\n\nSigned-Off-By: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "24c8dbbb5f777187d660393599641ab3307b4b97", "tree": "9d50fdd57c7593d925a21e4bb049095a4e4ead6f", "parents": [ "e9326dcab413848e70ab746c7c5363da13e5f801" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Tue Aug 22 20:06:10 2006 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Sep 22 23:24:33 2006 -0400" }, "message": "NFS: Generalise the nfs_client structure\n\nGeneralise the nfs_client structure by:\n\n (1) Moving nfs_client to a more general place (nfs_fs_sb.h).\n\n (2) Renaming its maintenance routines to be non-NFS4 specific.\n\n (3) Move those maintenance routines to a new non-NFS4 specific file (client.c)\n and move the declarations to internal.h.\n\n (4) Make nfs_find/get_client() take a full sockaddr_in to include the port\n number (will be required for NFS2/3).\n\n (5) Make nfs_find/get_client() take the NFS protocol version (again will be\n required to differentiate NFS2, 3 \u0026 4 client records).\n\nAlso:\n\n (6) Make nfs_client construction proceed akin to inodes, marking them as under\n construction and providing a function to indicate completion.\n\n (7) Make nfs_get_client() wait interruptibly if it finds a client that it can\n share, but that client is currently being constructed.\n\n (8) Make nfs4_create_client() use (6) and (7) instead of locking cl_sem.\n\nSigned-Off-By: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" } ] }