OpenCloudOS-Kernel/fs/afs/proc.c

706 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* /proc interface for AFS
*
* Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
#include "internal.h"
struct afs_vl_seq_net_private {
struct seq_net_private seq; /* Must be first */
struct afs_vlserver_list *vllist;
};
static inline struct afs_net *afs_seq2net(struct seq_file *m)
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:45 +08:00
{
return afs_net(seq_file_net(m));
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:45 +08:00
}
static inline struct afs_net *afs_seq2net_single(struct seq_file *m)
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:45 +08:00
{
return afs_net(seq_file_single_net(m));
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:45 +08:00
}
/*
* Display the list of cells known to the namespace.
*/
static int afs_proc_cells_show(struct seq_file *m, void *v)
{
struct afs_vlserver_list *vllist;
struct afs_cell *cell;
if (v == SEQ_START_TOKEN) {
/* display header on line 1 */
afs: Fix cell refcounting by splitting the usage counter Management of the lifetime of afs_cell struct has some problems due to the usage counter being used to determine whether objects of that type are in use in addition to whether anyone might be interested in the structure. This is made trickier by cell objects being cached for a period of time in case they're quickly reused as they hold the result of a setup process that may be slow (DNS lookups, AFS RPC ops). Problems include the cached root volume from alias resolution pinning its parent cell record, rmmod occasionally hanging and occasionally producing assertion failures. Fix this by splitting the count of active users from the struct reference count. Things then work as follows: (1) The cell cache keeps +1 on the cell's activity count and this has to be dropped before the cell can be removed. afs_manage_cell() tries to exchange the 1 to a 0 with the cells_lock write-locked, and if successful, the record is removed from the net->cells. (2) One struct ref is 'owned' by the activity count. That is put when the active count is reduced to 0 (final_destruction label). (3) A ref can be held on a cell whilst it is queued for management on a work queue without confusing the active count. afs_queue_cell() is added to wrap this. (4) The queue's ref is dropped at the end of the management. This is split out into a separate function, afs_manage_cell_work(). (5) The root volume record is put after a cell is removed (at the final_destruction label) rather then in the RCU destruction routine. (6) Volumes hold struct refs, but aren't active users. (7) Both counts are displayed in /proc/net/afs/cells. There are some management function changes: (*) afs_put_cell() now just decrements the refcount and triggers the RCU destruction if it becomes 0. It no longer sets a timer to have the manager do this. (*) afs_use_cell() and afs_unuse_cell() are added to increase and decrease the active count. afs_unuse_cell() sets the management timer. (*) afs_queue_cell() is added to queue a cell with approprate refs. There are also some other fixes: (*) Don't let /proc/net/afs/cells access a cell's vllist if it's NULL. (*) Make sure that candidate cells in lookups are properly destroyed rather than being simply kfree'd. This ensures the bits it points to are destroyed also. (*) afs_dec_cells_outstanding() is now called in cell destruction rather than at "final_destruction". This ensures that cell->net is still valid to the end of the destructor. (*) As a consequence of the previous two changes, move the increment of net->cells_outstanding that was at the point of insertion into the tree to the allocation routine to correctly balance things. Fixes: 989782dcdc91 ("afs: Overhaul cell database management") Signed-off-by: David Howells <dhowells@redhat.com>
2019-07-23 18:24:59 +08:00
seq_puts(m, "USE ACT TTL SV ST NAME\n");
return 0;
}
cell = list_entry(v, struct afs_cell, proc_link);
vllist = rcu_dereference(cell->vl_servers);
/* display one cell per line on subsequent lines */
afs: Fix cell refcounting by splitting the usage counter Management of the lifetime of afs_cell struct has some problems due to the usage counter being used to determine whether objects of that type are in use in addition to whether anyone might be interested in the structure. This is made trickier by cell objects being cached for a period of time in case they're quickly reused as they hold the result of a setup process that may be slow (DNS lookups, AFS RPC ops). Problems include the cached root volume from alias resolution pinning its parent cell record, rmmod occasionally hanging and occasionally producing assertion failures. Fix this by splitting the count of active users from the struct reference count. Things then work as follows: (1) The cell cache keeps +1 on the cell's activity count and this has to be dropped before the cell can be removed. afs_manage_cell() tries to exchange the 1 to a 0 with the cells_lock write-locked, and if successful, the record is removed from the net->cells. (2) One struct ref is 'owned' by the activity count. That is put when the active count is reduced to 0 (final_destruction label). (3) A ref can be held on a cell whilst it is queued for management on a work queue without confusing the active count. afs_queue_cell() is added to wrap this. (4) The queue's ref is dropped at the end of the management. This is split out into a separate function, afs_manage_cell_work(). (5) The root volume record is put after a cell is removed (at the final_destruction label) rather then in the RCU destruction routine. (6) Volumes hold struct refs, but aren't active users. (7) Both counts are displayed in /proc/net/afs/cells. There are some management function changes: (*) afs_put_cell() now just decrements the refcount and triggers the RCU destruction if it becomes 0. It no longer sets a timer to have the manager do this. (*) afs_use_cell() and afs_unuse_cell() are added to increase and decrease the active count. afs_unuse_cell() sets the management timer. (*) afs_queue_cell() is added to queue a cell with approprate refs. There are also some other fixes: (*) Don't let /proc/net/afs/cells access a cell's vllist if it's NULL. (*) Make sure that candidate cells in lookups are properly destroyed rather than being simply kfree'd. This ensures the bits it points to are destroyed also. (*) afs_dec_cells_outstanding() is now called in cell destruction rather than at "final_destruction". This ensures that cell->net is still valid to the end of the destructor. (*) As a consequence of the previous two changes, move the increment of net->cells_outstanding that was at the point of insertion into the tree to the allocation routine to correctly balance things. Fixes: 989782dcdc91 ("afs: Overhaul cell database management") Signed-off-by: David Howells <dhowells@redhat.com>
2019-07-23 18:24:59 +08:00
seq_printf(m, "%3u %3u %6lld %2u %2u %s\n",
refcount_read(&cell->ref),
afs: Fix cell refcounting by splitting the usage counter Management of the lifetime of afs_cell struct has some problems due to the usage counter being used to determine whether objects of that type are in use in addition to whether anyone might be interested in the structure. This is made trickier by cell objects being cached for a period of time in case they're quickly reused as they hold the result of a setup process that may be slow (DNS lookups, AFS RPC ops). Problems include the cached root volume from alias resolution pinning its parent cell record, rmmod occasionally hanging and occasionally producing assertion failures. Fix this by splitting the count of active users from the struct reference count. Things then work as follows: (1) The cell cache keeps +1 on the cell's activity count and this has to be dropped before the cell can be removed. afs_manage_cell() tries to exchange the 1 to a 0 with the cells_lock write-locked, and if successful, the record is removed from the net->cells. (2) One struct ref is 'owned' by the activity count. That is put when the active count is reduced to 0 (final_destruction label). (3) A ref can be held on a cell whilst it is queued for management on a work queue without confusing the active count. afs_queue_cell() is added to wrap this. (4) The queue's ref is dropped at the end of the management. This is split out into a separate function, afs_manage_cell_work(). (5) The root volume record is put after a cell is removed (at the final_destruction label) rather then in the RCU destruction routine. (6) Volumes hold struct refs, but aren't active users. (7) Both counts are displayed in /proc/net/afs/cells. There are some management function changes: (*) afs_put_cell() now just decrements the refcount and triggers the RCU destruction if it becomes 0. It no longer sets a timer to have the manager do this. (*) afs_use_cell() and afs_unuse_cell() are added to increase and decrease the active count. afs_unuse_cell() sets the management timer. (*) afs_queue_cell() is added to queue a cell with approprate refs. There are also some other fixes: (*) Don't let /proc/net/afs/cells access a cell's vllist if it's NULL. (*) Make sure that candidate cells in lookups are properly destroyed rather than being simply kfree'd. This ensures the bits it points to are destroyed also. (*) afs_dec_cells_outstanding() is now called in cell destruction rather than at "final_destruction". This ensures that cell->net is still valid to the end of the destructor. (*) As a consequence of the previous two changes, move the increment of net->cells_outstanding that was at the point of insertion into the tree to the allocation routine to correctly balance things. Fixes: 989782dcdc91 ("afs: Overhaul cell database management") Signed-off-by: David Howells <dhowells@redhat.com>
2019-07-23 18:24:59 +08:00
atomic_read(&cell->active),
cell->dns_expiry - ktime_get_real_seconds(),
afs: Fix cell refcounting by splitting the usage counter Management of the lifetime of afs_cell struct has some problems due to the usage counter being used to determine whether objects of that type are in use in addition to whether anyone might be interested in the structure. This is made trickier by cell objects being cached for a period of time in case they're quickly reused as they hold the result of a setup process that may be slow (DNS lookups, AFS RPC ops). Problems include the cached root volume from alias resolution pinning its parent cell record, rmmod occasionally hanging and occasionally producing assertion failures. Fix this by splitting the count of active users from the struct reference count. Things then work as follows: (1) The cell cache keeps +1 on the cell's activity count and this has to be dropped before the cell can be removed. afs_manage_cell() tries to exchange the 1 to a 0 with the cells_lock write-locked, and if successful, the record is removed from the net->cells. (2) One struct ref is 'owned' by the activity count. That is put when the active count is reduced to 0 (final_destruction label). (3) A ref can be held on a cell whilst it is queued for management on a work queue without confusing the active count. afs_queue_cell() is added to wrap this. (4) The queue's ref is dropped at the end of the management. This is split out into a separate function, afs_manage_cell_work(). (5) The root volume record is put after a cell is removed (at the final_destruction label) rather then in the RCU destruction routine. (6) Volumes hold struct refs, but aren't active users. (7) Both counts are displayed in /proc/net/afs/cells. There are some management function changes: (*) afs_put_cell() now just decrements the refcount and triggers the RCU destruction if it becomes 0. It no longer sets a timer to have the manager do this. (*) afs_use_cell() and afs_unuse_cell() are added to increase and decrease the active count. afs_unuse_cell() sets the management timer. (*) afs_queue_cell() is added to queue a cell with approprate refs. There are also some other fixes: (*) Don't let /proc/net/afs/cells access a cell's vllist if it's NULL. (*) Make sure that candidate cells in lookups are properly destroyed rather than being simply kfree'd. This ensures the bits it points to are destroyed also. (*) afs_dec_cells_outstanding() is now called in cell destruction rather than at "final_destruction". This ensures that cell->net is still valid to the end of the destructor. (*) As a consequence of the previous two changes, move the increment of net->cells_outstanding that was at the point of insertion into the tree to the allocation routine to correctly balance things. Fixes: 989782dcdc91 ("afs: Overhaul cell database management") Signed-off-by: David Howells <dhowells@redhat.com>
2019-07-23 18:24:59 +08:00
vllist ? vllist->nr_servers : 0,
afs: Detect cell aliases 1 - Cells with root volumes Put in the first phase of cell alias detection. This part handles alias detection for cells that have root.cell volumes (which is expected to be likely). When a cell becomes newly active, it is probed for its root.cell volume, and if it has one, this volume is compared against other root.cell volumes to find out if the list of fileserver UUIDs have any in common - and if that's the case, do the address lists of those fileservers have any addresses in common. If they do, the new cell is adjudged to be an alias of the old cell and the old cell is used instead. Comparing is aided by the server list in struct afs_server_list being sorted in UUID order and the addresses in the fileserver address lists being sorted in address order. The cell then retains the afs_volume object for the root.cell volume, even if it's not mounted for future alias checking. This necessary because: (1) Whilst fileservers have UUIDs that are meant to be globally unique, in practice they are not because cells get cloned without changing the UUIDs - so afs_server records need to be per cell. (2) Sometimes the DNS is used to make cell aliases - but if we don't know they're the same, we may end up with multiple superblocks and multiple afs_server records for the same thing, impairing our ability to deliver callback notifications of third party changes (3) The fileserver RPC API doesn't contain the cell name, so it can't tell us which cell it's notifying and can't see that a change made to to one cell should notify the same client that's also accessed as the other cell. Reported-by: Jeffrey Altman <jaltman@auristor.com> Signed-off-by: David Howells <dhowells@redhat.com>
2020-04-25 17:26:02 +08:00
cell->state,
cell->name);
return 0;
}
static void *afs_proc_cells_start(struct seq_file *m, loff_t *_pos)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__acquires(rcu)
{
rcu_read_lock();
return seq_hlist_start_head_rcu(&afs_seq2net(m)->proc_cells, *_pos);
}
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:45 +08:00
static void *afs_proc_cells_next(struct seq_file *m, void *v, loff_t *pos)
{
return seq_hlist_next_rcu(v, &afs_seq2net(m)->proc_cells, pos);
}
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:45 +08:00
static void afs_proc_cells_stop(struct seq_file *m, void *v)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__releases(rcu)
{
rcu_read_unlock();
}
static const struct seq_operations afs_proc_cells_ops = {
.start = afs_proc_cells_start,
.next = afs_proc_cells_next,
.stop = afs_proc_cells_stop,
.show = afs_proc_cells_show,
};
/*
* handle writes to /proc/fs/afs/cells
* - to add cells: echo "add <cellname> <IP>[:<IP>][:<IP>]"
*/
static int afs_proc_cells_write(struct file *file, char *buf, size_t size)
{
struct seq_file *m = file->private_data;
struct afs_net *net = afs_seq2net(m);
char *name, *args;
int ret;
/* trim to first NL */
name = memchr(buf, '\n', size);
if (name)
*name = 0;
/* split into command, name and argslist */
name = strchr(buf, ' ');
if (!name)
goto inval;
do {
*name++ = 0;
} while(*name == ' ');
if (!*name)
goto inval;
args = strchr(name, ' ');
if (args) {
do {
*args++ = 0;
} while(*args == ' ');
if (!*args)
goto inval;
}
/* determine command to perform */
_debug("cmd=%s name=%s args=%s", buf, name, args);
if (strcmp(buf, "add") == 0) {
struct afs_cell *cell;
cell = afs_lookup_cell(net, name, strlen(name), args, true);
if (IS_ERR(cell)) {
ret = PTR_ERR(cell);
goto done;
}
if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags))
afs_unuse_cell(net, cell, afs_cell_trace_unuse_no_pin);
} else {
goto inval;
}
ret = 0;
done:
_leave(" = %d", ret);
return ret;
inval:
ret = -EINVAL;
printk("kAFS: Invalid Command on /proc/fs/afs/cells file\n");
goto done;
}
/*
* Display the name of the current workstation cell.
*/
static int afs_proc_rootcell_show(struct seq_file *m, void *v)
{
struct afs_cell *cell;
struct afs_net *net;
net = afs_seq2net_single(m);
afs: Fix cell refcounting by splitting the usage counter Management of the lifetime of afs_cell struct has some problems due to the usage counter being used to determine whether objects of that type are in use in addition to whether anyone might be interested in the structure. This is made trickier by cell objects being cached for a period of time in case they're quickly reused as they hold the result of a setup process that may be slow (DNS lookups, AFS RPC ops). Problems include the cached root volume from alias resolution pinning its parent cell record, rmmod occasionally hanging and occasionally producing assertion failures. Fix this by splitting the count of active users from the struct reference count. Things then work as follows: (1) The cell cache keeps +1 on the cell's activity count and this has to be dropped before the cell can be removed. afs_manage_cell() tries to exchange the 1 to a 0 with the cells_lock write-locked, and if successful, the record is removed from the net->cells. (2) One struct ref is 'owned' by the activity count. That is put when the active count is reduced to 0 (final_destruction label). (3) A ref can be held on a cell whilst it is queued for management on a work queue without confusing the active count. afs_queue_cell() is added to wrap this. (4) The queue's ref is dropped at the end of the management. This is split out into a separate function, afs_manage_cell_work(). (5) The root volume record is put after a cell is removed (at the final_destruction label) rather then in the RCU destruction routine. (6) Volumes hold struct refs, but aren't active users. (7) Both counts are displayed in /proc/net/afs/cells. There are some management function changes: (*) afs_put_cell() now just decrements the refcount and triggers the RCU destruction if it becomes 0. It no longer sets a timer to have the manager do this. (*) afs_use_cell() and afs_unuse_cell() are added to increase and decrease the active count. afs_unuse_cell() sets the management timer. (*) afs_queue_cell() is added to queue a cell with approprate refs. There are also some other fixes: (*) Don't let /proc/net/afs/cells access a cell's vllist if it's NULL. (*) Make sure that candidate cells in lookups are properly destroyed rather than being simply kfree'd. This ensures the bits it points to are destroyed also. (*) afs_dec_cells_outstanding() is now called in cell destruction rather than at "final_destruction". This ensures that cell->net is still valid to the end of the destructor. (*) As a consequence of the previous two changes, move the increment of net->cells_outstanding that was at the point of insertion into the tree to the allocation routine to correctly balance things. Fixes: 989782dcdc91 ("afs: Overhaul cell database management") Signed-off-by: David Howells <dhowells@redhat.com>
2019-07-23 18:24:59 +08:00
down_read(&net->cells_lock);
cell = net->ws_cell;
if (cell)
seq_printf(m, "%s\n", cell->name);
up_read(&net->cells_lock);
return 0;
}
/*
* Set the current workstation cell and optionally supply its list of volume
* location servers.
*
* echo "cell.name:192.168.231.14" >/proc/fs/afs/rootcell
*/
static int afs_proc_rootcell_write(struct file *file, char *buf, size_t size)
{
struct seq_file *m = file->private_data;
struct afs_net *net = afs_seq2net_single(m);
char *s;
int ret;
ret = -EINVAL;
if (buf[0] == '.')
goto out;
if (memchr(buf, '/', size))
goto out;
/* trim to first NL */
s = memchr(buf, '\n', size);
if (s)
*s = 0;
/* determine command to perform */
_debug("rootcell=%s", buf);
ret = afs_cell_init(net, buf);
out:
_leave(" = %d", ret);
return ret;
}
static const char afs_vol_types[3][3] = {
[AFSVL_RWVOL] = "RW",
[AFSVL_ROVOL] = "RO",
[AFSVL_BACKVOL] = "BK",
};
/*
* Display the list of volumes known to a cell.
*/
static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
{
struct afs_volume *vol = hlist_entry(v, struct afs_volume, proc_link);
/* Display header on line 1 */
if (v == SEQ_START_TOKEN) {
seq_puts(m, "USE VID TY NAME\n");
return 0;
}
seq_printf(m, "%3d %08llx %s %s\n",
refcount_read(&vol->ref), vol->vid,
afs_vol_types[vol->type],
vol->name);
return 0;
}
static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__acquires(cell->proc_lock)
{
struct afs_cell *cell = pde_data(file_inode(m->file));
rcu_read_lock();
return seq_hlist_start_head_rcu(&cell->proc_volumes, *_pos);
}
static void *afs_proc_cell_volumes_next(struct seq_file *m, void *v,
loff_t *_pos)
{
struct afs_cell *cell = pde_data(file_inode(m->file));
return seq_hlist_next_rcu(v, &cell->proc_volumes, _pos);
}
static void afs_proc_cell_volumes_stop(struct seq_file *m, void *v)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__releases(cell->proc_lock)
{
rcu_read_unlock();
}
static const struct seq_operations afs_proc_cell_volumes_ops = {
.start = afs_proc_cell_volumes_start,
.next = afs_proc_cell_volumes_next,
.stop = afs_proc_cell_volumes_stop,
.show = afs_proc_cell_volumes_show,
};
static const char *const dns_record_sources[NR__dns_record_source + 1] = {
[DNS_RECORD_UNAVAILABLE] = "unav",
[DNS_RECORD_FROM_CONFIG] = "cfg",
[DNS_RECORD_FROM_DNS_A] = "A",
[DNS_RECORD_FROM_DNS_AFSDB] = "AFSDB",
[DNS_RECORD_FROM_DNS_SRV] = "SRV",
[DNS_RECORD_FROM_NSS] = "nss",
[NR__dns_record_source] = "[weird]"
};
static const char *const dns_lookup_statuses[NR__dns_lookup_status + 1] = {
[DNS_LOOKUP_NOT_DONE] = "no-lookup",
[DNS_LOOKUP_GOOD] = "good",
[DNS_LOOKUP_GOOD_WITH_BAD] = "good/bad",
[DNS_LOOKUP_BAD] = "bad",
[DNS_LOOKUP_GOT_NOT_FOUND] = "not-found",
[DNS_LOOKUP_GOT_LOCAL_FAILURE] = "local-failure",
[DNS_LOOKUP_GOT_TEMP_FAILURE] = "temp-failure",
[DNS_LOOKUP_GOT_NS_FAILURE] = "ns-failure",
[NR__dns_lookup_status] = "[weird]"
};
/*
* Display the list of Volume Location servers we're using for a cell.
*/
static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
{
const struct afs_vl_seq_net_private *priv = m->private;
const struct afs_vlserver_list *vllist = priv->vllist;
const struct afs_vlserver_entry *entry;
const struct afs_vlserver *vlserver;
const struct afs_addr_list *alist;
int i;
if (v == SEQ_START_TOKEN) {
seq_printf(m, "# source %s, status %s\n",
dns_record_sources[vllist ? vllist->source : 0],
dns_lookup_statuses[vllist ? vllist->status : 0]);
return 0;
}
entry = v;
vlserver = entry->server;
alist = rcu_dereference(vlserver->addresses);
seq_printf(m, "%s [p=%hu w=%hu s=%s,%s]:\n",
vlserver->name, entry->priority, entry->weight,
dns_record_sources[alist ? alist->source : entry->source],
dns_lookup_statuses[alist ? alist->status : entry->status]);
if (alist) {
for (i = 0; i < alist->nr_addrs; i++)
seq_printf(m, " %c %pISpc\n",
alist->preferred == i ? '>' : '-',
&alist->addrs[i].transport);
}
seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt);
seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n",
vlserver->probe.flags, vlserver->probe.error,
vlserver->probe.abort_code,
atomic_read(&vlserver->probe_outstanding));
return 0;
}
static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__acquires(rcu)
{
struct afs_vl_seq_net_private *priv = m->private;
struct afs_vlserver_list *vllist;
struct afs_cell *cell = pde_data(file_inode(m->file));
loff_t pos = *_pos;
rcu_read_lock();
vllist = rcu_dereference(cell->vl_servers);
priv->vllist = vllist;
if (pos < 0)
*_pos = pos = 0;
if (pos == 0)
return SEQ_START_TOKEN;
if (pos - 1 >= vllist->nr_servers)
return NULL;
return &vllist->servers[pos - 1];
}
static void *afs_proc_cell_vlservers_next(struct seq_file *m, void *v,
loff_t *_pos)
{
struct afs_vl_seq_net_private *priv = m->private;
struct afs_vlserver_list *vllist = priv->vllist;
loff_t pos;
pos = *_pos;
pos++;
*_pos = pos;
if (!vllist || pos - 1 >= vllist->nr_servers)
return NULL;
return &vllist->servers[pos - 1];
}
static void afs_proc_cell_vlservers_stop(struct seq_file *m, void *v)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__releases(rcu)
{
rcu_read_unlock();
}
static const struct seq_operations afs_proc_cell_vlservers_ops = {
.start = afs_proc_cell_vlservers_start,
.next = afs_proc_cell_vlservers_next,
.stop = afs_proc_cell_vlservers_stop,
.show = afs_proc_cell_vlservers_show,
};
/*
* Display the list of fileservers we're using within a namespace.
*/
static int afs_proc_servers_show(struct seq_file *m, void *v)
{
struct afs_server *server;
struct afs_addr_list *alist;
int i;
if (v == SEQ_START_TOKEN) {
seq_puts(m, "UUID REF ACT\n");
return 0;
}
server = list_entry(v, struct afs_server, proc_link);
alist = rcu_dereference(server->addresses);
seq_printf(m, "%pU %3d %3d\n",
&server->uuid,
refcount_read(&server->ref),
atomic_read(&server->active));
seq_printf(m, " - info: fl=%lx rtt=%u brk=%x\n",
server->flags, server->rtt, server->cb_s_break);
seq_printf(m, " - probe: last=%d out=%d\n",
(int)(jiffies - server->probed_at) / HZ,
atomic_read(&server->probe_outstanding));
seq_printf(m, " - ALIST v=%u rsp=%lx f=%lx\n",
alist->version, alist->responded, alist->failed);
for (i = 0; i < alist->nr_addrs; i++)
seq_printf(m, " [%x] %pISpc%s\n",
i, &alist->addrs[i].transport,
alist->preferred == i ? "*" : "");
return 0;
}
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
static void *afs_proc_servers_start(struct seq_file *m, loff_t *_pos)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__acquires(rcu)
{
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
rcu_read_lock();
return seq_hlist_start_head_rcu(&afs_seq2net(m)->fs_proc, *_pos);
}
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
static void *afs_proc_servers_next(struct seq_file *m, void *v, loff_t *_pos)
{
return seq_hlist_next_rcu(v, &afs_seq2net(m)->fs_proc, _pos);
}
static void afs_proc_servers_stop(struct seq_file *m, void *v)
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-10 04:12:31 +08:00
__releases(rcu)
{
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
rcu_read_unlock();
}
static const struct seq_operations afs_proc_servers_ops = {
.start = afs_proc_servers_start,
.next = afs_proc_servers_next,
.stop = afs_proc_servers_stop,
.show = afs_proc_servers_show,
};
/*
* Display the list of strings that may be substituted for the @sys pathname
* macro.
*/
static int afs_proc_sysname_show(struct seq_file *m, void *v)
{
struct afs_net *net = afs_seq2net(m);
struct afs_sysnames *sysnames = net->sysnames;
unsigned int i = (unsigned long)v - 1;
if (i < sysnames->nr)
seq_printf(m, "%s\n", sysnames->subs[i]);
return 0;
}
static void *afs_proc_sysname_start(struct seq_file *m, loff_t *pos)
__acquires(&net->sysnames_lock)
{
struct afs_net *net = afs_seq2net(m);
struct afs_sysnames *names;
read_lock(&net->sysnames_lock);
names = net->sysnames;
if (*pos >= names->nr)
return NULL;
return (void *)(unsigned long)(*pos + 1);
}
static void *afs_proc_sysname_next(struct seq_file *m, void *v, loff_t *pos)
{
struct afs_net *net = afs_seq2net(m);
struct afs_sysnames *names = net->sysnames;
*pos += 1;
if (*pos >= names->nr)
return NULL;
return (void *)(unsigned long)(*pos + 1);
}
static void afs_proc_sysname_stop(struct seq_file *m, void *v)
__releases(&net->sysnames_lock)
{
struct afs_net *net = afs_seq2net(m);
read_unlock(&net->sysnames_lock);
}
static const struct seq_operations afs_proc_sysname_ops = {
.start = afs_proc_sysname_start,
.next = afs_proc_sysname_next,
.stop = afs_proc_sysname_stop,
.show = afs_proc_sysname_show,
};
/*
* Allow the @sys substitution to be configured.
*/
static int afs_proc_sysname_write(struct file *file, char *buf, size_t size)
{
struct afs_sysnames *sysnames, *kill;
struct seq_file *m = file->private_data;
struct afs_net *net = afs_seq2net(m);
char *s, *p, *sub;
int ret, len;
sysnames = kzalloc(sizeof(*sysnames), GFP_KERNEL);
if (!sysnames)
return -ENOMEM;
refcount_set(&sysnames->usage, 1);
kill = sysnames;
p = buf;
while ((s = strsep(&p, " \t\n"))) {
len = strlen(s);
if (len == 0)
continue;
ret = -ENAMETOOLONG;
if (len >= AFSNAMEMAX)
goto error;
if (len >= 4 &&
s[len - 4] == '@' &&
s[len - 3] == 's' &&
s[len - 2] == 'y' &&
s[len - 1] == 's')
/* Protect against recursion */
goto invalid;
if (s[0] == '.' &&
(len < 2 || (len == 2 && s[1] == '.')))
goto invalid;
if (memchr(s, '/', len))
goto invalid;
ret = -EFBIG;
if (sysnames->nr >= AFS_NR_SYSNAME)
goto out;
if (strcmp(s, afs_init_sysname) == 0) {
sub = (char *)afs_init_sysname;
} else {
ret = -ENOMEM;
sub = kmemdup(s, len + 1, GFP_KERNEL);
if (!sub)
goto out;
}
sysnames->subs[sysnames->nr] = sub;
sysnames->nr++;
}
if (sysnames->nr == 0) {
sysnames->subs[0] = sysnames->blank;
sysnames->nr++;
}
write_lock(&net->sysnames_lock);
kill = net->sysnames;
net->sysnames = sysnames;
write_unlock(&net->sysnames_lock);
ret = 0;
out:
afs_put_sysnames(kill);
return ret;
invalid:
ret = -EINVAL;
error:
goto out;
}
void afs_put_sysnames(struct afs_sysnames *sysnames)
{
int i;
if (sysnames && refcount_dec_and_test(&sysnames->usage)) {
for (i = 0; i < sysnames->nr; i++)
if (sysnames->subs[i] != afs_init_sysname &&
sysnames->subs[i] != sysnames->blank)
kfree(sysnames->subs[i]);
kfree(sysnames);
}
}
/*
* Display general per-net namespace statistics
*/
static int afs_proc_stats_show(struct seq_file *m, void *v)
{
struct afs_net *net = afs_seq2net_single(m);
seq_puts(m, "kAFS statistics\n");
afs: Fix directory handling AFS directories are structured blobs that are downloaded just like files and then parsed by the lookup and readdir code and, as such, are currently handled in the pagecache like any other file, with the entire directory content being thrown away each time the directory changes. However, since the blob is a known structure and since the data version counter on a directory increases by exactly one for each change committed to that directory, we can actually edit the directory locally rather than fetching it from the server after each locally-induced change. What we can't do, though, is mix data from the server and data from the client since the server is technically at liberty to rearrange or compress a directory if it sees fit, provided it updates the data version number when it does so and breaks the callback (ie. sends a notification). Further, lookup with lookup-ahead, readdir and, when it arrives, local editing are likely want to scan the whole of a directory. So directory handling needs to be improved to maintain the coherency of the directory blob prior to permitting local directory editing. To this end: (1) If any directory page gets discarded, invalidate and reread the entire directory. (2) If readpage notes that if when it fetches a single page that the version number has changed, the entire directory is flagged for invalidation. (3) Read as much of the directory in one go as we can. Note that this removes local caching of directories in fscache for the moment as we can't pass the pages to fscache_read_or_alloc_pages() since page->lru is in use by the LRU. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-06 21:17:25 +08:00
seq_printf(m, "dir-mgmt: look=%u reval=%u inval=%u relpg=%u\n",
atomic_read(&net->n_lookup),
atomic_read(&net->n_reval),
afs: Fix directory handling AFS directories are structured blobs that are downloaded just like files and then parsed by the lookup and readdir code and, as such, are currently handled in the pagecache like any other file, with the entire directory content being thrown away each time the directory changes. However, since the blob is a known structure and since the data version counter on a directory increases by exactly one for each change committed to that directory, we can actually edit the directory locally rather than fetching it from the server after each locally-induced change. What we can't do, though, is mix data from the server and data from the client since the server is technically at liberty to rearrange or compress a directory if it sees fit, provided it updates the data version number when it does so and breaks the callback (ie. sends a notification). Further, lookup with lookup-ahead, readdir and, when it arrives, local editing are likely want to scan the whole of a directory. So directory handling needs to be improved to maintain the coherency of the directory blob prior to permitting local directory editing. To this end: (1) If any directory page gets discarded, invalidate and reread the entire directory. (2) If readpage notes that if when it fetches a single page that the version number has changed, the entire directory is flagged for invalidation. (3) Read as much of the directory in one go as we can. Note that this removes local caching of directories in fscache for the moment as we can't pass the pages to fscache_read_or_alloc_pages() since page->lru is in use by the LRU. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-06 21:17:25 +08:00
atomic_read(&net->n_inval),
atomic_read(&net->n_relpg));
seq_printf(m, "dir-data: rdpg=%u\n",
atomic_read(&net->n_read_dir));
seq_printf(m, "dir-edit: cr=%u rm=%u\n",
atomic_read(&net->n_dir_cr),
atomic_read(&net->n_dir_rm));
seq_printf(m, "file-rd : n=%u nb=%lu\n",
atomic_read(&net->n_fetches),
atomic_long_read(&net->n_fetch_bytes));
seq_printf(m, "file-wr : n=%u nb=%lu\n",
atomic_read(&net->n_stores),
atomic_long_read(&net->n_store_bytes));
return 0;
}
/*
* initialise /proc/fs/afs/<cell>/
*/
int afs_proc_cell_setup(struct afs_cell *cell)
{
struct proc_dir_entry *dir;
struct afs_net *net = cell->net;
_enter("%p{%s},%p", cell, cell->name, net->proc_afs);
dir = proc_net_mkdir(net->net, cell->name, net->proc_afs);
if (!dir)
goto error_dir;
if (!proc_create_net_data("vlservers", 0444, dir,
&afs_proc_cell_vlservers_ops,
sizeof(struct afs_vl_seq_net_private),
cell) ||
!proc_create_net_data("volumes", 0444, dir,
&afs_proc_cell_volumes_ops,
sizeof(struct seq_net_private),
cell))
goto error_tree;
_leave(" = 0");
return 0;
error_tree:
remove_proc_subtree(cell->name, net->proc_afs);
error_dir:
_leave(" = -ENOMEM");
return -ENOMEM;
}
/*
* remove /proc/fs/afs/<cell>/
*/
void afs_proc_cell_remove(struct afs_cell *cell)
{
struct afs_net *net = cell->net;
_enter("");
remove_proc_subtree(cell->name, net->proc_afs);
_leave("");
}
/*
* initialise the /proc/fs/afs/ directory
*/
int afs_proc_init(struct afs_net *net)
{
struct proc_dir_entry *p;
_enter("");
p = proc_net_mkdir(net->net, "afs", net->net->proc_net);
if (!p)
goto error_dir;
if (!proc_create_net_data_write("cells", 0644, p,
&afs_proc_cells_ops,
afs_proc_cells_write,
sizeof(struct seq_net_private),
NULL) ||
!proc_create_net_single_write("rootcell", 0644, p,
afs_proc_rootcell_show,
afs_proc_rootcell_write,
NULL) ||
!proc_create_net("servers", 0444, p, &afs_proc_servers_ops,
sizeof(struct seq_net_private)) ||
!proc_create_net_single("stats", 0444, p, afs_proc_stats_show, NULL) ||
!proc_create_net_data_write("sysname", 0644, p,
&afs_proc_sysname_ops,
afs_proc_sysname_write,
sizeof(struct seq_net_private),
NULL))
goto error_tree;
net->proc_afs = p;
_leave(" = 0");
return 0;
error_tree:
proc_remove(p);
error_dir:
_leave(" = -ENOMEM");
return -ENOMEM;
}
/*
* clean up the /proc/fs/afs/ directory
*/
void afs_proc_cleanup(struct afs_net *net)
{
proc_remove(net->proc_afs);
net->proc_afs = NULL;
}