diff options
Diffstat (limited to 'fs')
145 files changed, 6922 insertions, 5754 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 04f86b8c100e..8cd471da3255 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -45,7 +45,7 @@ config ARCH_USE_GNU_PROPERTY config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y if !BINFMT_ELF - depends on (ARM || (SUPERH32 && !MMU) || C6X) + depends on (ARM || (SUPERH && !MMU) || C6X) select ELFCORE help ELF FDPIC binaries are based on ELF, but allow the individual load diff --git a/fs/afs/Makefile b/fs/afs/Makefile index 10359bea7070..75c4e4043d1d 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -18,6 +18,7 @@ kafs-y := \ file.o \ flock.o \ fsclient.o \ + fs_operation.o \ fs_probe.o \ inode.o \ main.o \ @@ -30,6 +31,7 @@ kafs-y := \ server_list.o \ super.o \ vlclient.o \ + vl_alias.o \ vl_list.o \ vl_probe.o \ vl_rotate.o \ diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b6d49d646ade..432cb4b23961 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -10,7 +10,7 @@ #include <linux/in.h> -#define AFS_MAXCELLNAME 64 /* Maximum length of a cell name */ +#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */ #define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */ #define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */ #define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */ @@ -146,7 +146,6 @@ struct afs_file_status { struct afs_status_cb { struct afs_file_status status; struct afs_callback callback; - unsigned int cb_break; /* Pre-op callback break counter */ bool have_status; /* True if status record was retrieved */ bool have_cb; /* True if cb record was retrieved */ bool have_error; /* True if status.abort_code indicates an error */ diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index e9b8029920ec..9c65ffb8a523 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -22,6 +22,7 @@ enum AFSVL_Operations { VLGETENTRYBYNAMEU = 527, /* AFS Get VLDB entry by name (UUID-variant) */ VLGETADDRSU = 533, /* AFS Get addrs for fileserver */ YVLGETENDPOINTS = 64002, /* YFS Get endpoints for file/volume server */ + YVLGETCELLNAME = 64014, /* YFS Get actual cell name */ VLGETCAPABILITIES = 65537, /* AFS Get server capabilities */ }; diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 2dca8df1a18d..7d9b23d981bf 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -21,192 +21,17 @@ #include "internal.h" /* - * Create volume and callback interests on a server. - */ -static struct afs_cb_interest *afs_create_interest(struct afs_server *server, - struct afs_vnode *vnode) -{ - struct afs_vol_interest *new_vi, *vi; - struct afs_cb_interest *new; - struct hlist_node **pp; - - new_vi = kzalloc(sizeof(struct afs_vol_interest), GFP_KERNEL); - if (!new_vi) - return NULL; - - new = kzalloc(sizeof(struct afs_cb_interest), GFP_KERNEL); - if (!new) { - kfree(new_vi); - return NULL; - } - - new_vi->usage = 1; - new_vi->vid = vnode->volume->vid; - INIT_HLIST_NODE(&new_vi->srv_link); - INIT_HLIST_HEAD(&new_vi->cb_interests); - - refcount_set(&new->usage, 1); - new->sb = vnode->vfs_inode.i_sb; - new->vid = vnode->volume->vid; - new->server = afs_get_server(server, afs_server_trace_get_new_cbi); - INIT_HLIST_NODE(&new->cb_vlink); - - write_lock(&server->cb_break_lock); - - for (pp = &server->cb_volumes.first; *pp; pp = &(*pp)->next) { - vi = hlist_entry(*pp, struct afs_vol_interest, srv_link); - if (vi->vid < new_vi->vid) - continue; - if (vi->vid > new_vi->vid) - break; - vi->usage++; - goto found_vi; - } - - new_vi->srv_link.pprev = pp; - new_vi->srv_link.next = *pp; - if (*pp) - (*pp)->pprev = &new_vi->srv_link.next; - *pp = &new_vi->srv_link; - vi = new_vi; - new_vi = NULL; -found_vi: - - new->vol_interest = vi; - hlist_add_head(&new->cb_vlink, &vi->cb_interests); - - write_unlock(&server->cb_break_lock); - kfree(new_vi); - return new; -} - -/* - * Set up an interest-in-callbacks record for a volume on a server and - * register it with the server. - * - Called with vnode->io_lock held. - */ -int afs_register_server_cb_interest(struct afs_vnode *vnode, - struct afs_server_list *slist, - unsigned int index) -{ - struct afs_server_entry *entry = &slist->servers[index]; - struct afs_cb_interest *cbi, *vcbi, *new, *old; - struct afs_server *server = entry->server; - -again: - vcbi = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->io_lock)); - if (vcbi && likely(vcbi == entry->cb_interest)) - return 0; - - read_lock(&slist->lock); - cbi = afs_get_cb_interest(entry->cb_interest); - read_unlock(&slist->lock); - - if (vcbi) { - if (vcbi == cbi) { - afs_put_cb_interest(afs_v2net(vnode), cbi); - return 0; - } - - /* Use a new interest in the server list for the same server - * rather than an old one that's still attached to a vnode. - */ - if (cbi && vcbi->server == cbi->server) { - write_seqlock(&vnode->cb_lock); - old = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->cb_lock.lock)); - rcu_assign_pointer(vnode->cb_interest, cbi); - write_sequnlock(&vnode->cb_lock); - afs_put_cb_interest(afs_v2net(vnode), old); - return 0; - } - - /* Re-use the one attached to the vnode. */ - if (!cbi && vcbi->server == server) { - write_lock(&slist->lock); - if (entry->cb_interest) { - write_unlock(&slist->lock); - afs_put_cb_interest(afs_v2net(vnode), cbi); - goto again; - } - - entry->cb_interest = cbi; - write_unlock(&slist->lock); - return 0; - } - } - - if (!cbi) { - new = afs_create_interest(server, vnode); - if (!new) - return -ENOMEM; - - write_lock(&slist->lock); - if (!entry->cb_interest) { - entry->cb_interest = afs_get_cb_interest(new); - cbi = new; - new = NULL; - } else { - cbi = afs_get_cb_interest(entry->cb_interest); - } - write_unlock(&slist->lock); - afs_put_cb_interest(afs_v2net(vnode), new); - } - - ASSERT(cbi); - - /* Change the server the vnode is using. This entails scrubbing any - * interest the vnode had in the previous server it was using. - */ - write_seqlock(&vnode->cb_lock); - - old = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->cb_lock.lock)); - rcu_assign_pointer(vnode->cb_interest, cbi); - vnode->cb_s_break = cbi->server->cb_s_break; - vnode->cb_v_break = vnode->volume->cb_v_break; - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - - write_sequnlock(&vnode->cb_lock); - afs_put_cb_interest(afs_v2net(vnode), old); - return 0; -} - -/* - * Remove an interest on a server. - */ -void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) -{ - struct afs_vol_interest *vi; - - if (cbi && refcount_dec_and_test(&cbi->usage)) { - if (!hlist_unhashed(&cbi->cb_vlink)) { - write_lock(&cbi->server->cb_break_lock); - - hlist_del_init(&cbi->cb_vlink); - vi = cbi->vol_interest; - cbi->vol_interest = NULL; - if (--vi->usage == 0) - hlist_del(&vi->srv_link); - else - vi = NULL; - - write_unlock(&cbi->server->cb_break_lock); - if (vi) - kfree_rcu(vi, rcu); - afs_put_server(net, cbi->server, afs_server_trace_put_cbi); - } - kfree_rcu(cbi, rcu); - } -} - -/* - * allow the fileserver to request callback state (re-)initialisation + * Allow the fileserver to request callback state (re-)initialisation. + * Unfortunately, UUIDs are not guaranteed unique. */ void afs_init_callback_state(struct afs_server *server) { - server->cb_s_break++; + rcu_read_lock(); + do { + server->cb_s_break++; + server = rcu_dereference(server->uuid_next); + } while (0); + rcu_read_unlock(); } /* @@ -238,69 +63,109 @@ void afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason } /* + * Look up a volume by volume ID under RCU conditions. + */ +static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, + afs_volid_t vid) +{ + struct afs_volume *volume = NULL; + struct rb_node *p; + int seq = 0; + + do { + /* Unfortunately, rbtree walking doesn't give reliable results + * under just the RCU read lock, so we have to check for + * changes. + */ + read_seqbegin_or_lock(&cell->volume_lock, &seq); + + p = rcu_dereference_raw(cell->volumes.rb_node); + while (p) { + volume = rb_entry(p, struct afs_volume, cell_node); + + if (volume->vid < vid) + p = rcu_dereference_raw(p->rb_left); + else if (volume->vid > vid) + p = rcu_dereference_raw(p->rb_right); + else + break; + volume = NULL; + } + + } while (need_seqretry(&cell->volume_lock, seq)); + + done_seqretry(&cell->volume_lock, seq); + return volume; +} + +/* * allow the fileserver to explicitly break one callback * - happens when * - the backing file is changed * - a lock is released */ -static void afs_break_one_callback(struct afs_server *server, +static void afs_break_one_callback(struct afs_volume *volume, struct afs_fid *fid) { - struct afs_vol_interest *vi; - struct afs_cb_interest *cbi; - struct afs_iget_data data; + struct super_block *sb; struct afs_vnode *vnode; struct inode *inode; - read_lock(&server->cb_break_lock); - hlist_for_each_entry(vi, &server->cb_volumes, srv_link) { - if (vi->vid < fid->vid) - continue; - if (vi->vid > fid->vid) { - vi = NULL; - break; - } - //atomic_inc(&vi->usage); - break; + if (fid->vnode == 0 && fid->unique == 0) { + /* The callback break applies to an entire volume. */ + write_lock(&volume->cb_v_break_lock); + volume->cb_v_break++; + trace_afs_cb_break(fid, volume->cb_v_break, + afs_cb_break_for_volume_callback, false); + write_unlock(&volume->cb_v_break_lock); + return; } - /* TODO: Find all matching volumes if we couldn't match the server and - * break them anyway. + /* See if we can find a matching inode - even an I_NEW inode needs to + * be marked as it can have its callback broken before we finish + * setting up the local inode. */ - if (!vi) - goto out; + sb = rcu_dereference(volume->sb); + if (!sb) + return; + + inode = find_inode_rcu(sb, fid->vnode, afs_ilookup5_test_by_fid, fid); + if (inode) { + vnode = AFS_FS_I(inode); + afs_break_callback(vnode, afs_cb_break_for_callback); + } else { + trace_afs_cb_miss(fid, afs_cb_break_for_callback); + } +} + +static void afs_break_some_callbacks(struct afs_server *server, + struct afs_callback_break *cbb, + size_t *_count) +{ + struct afs_callback_break *residue = cbb; + struct afs_volume *volume; + afs_volid_t vid = cbb->fid.vid; + size_t i; - /* Step through all interested superblocks. There may be more than one - * because of cell aliasing. + volume = afs_lookup_volume_rcu(server->cell, vid); + + /* TODO: Find all matching volumes if we couldn't match the server and + * break them anyway. */ - hlist_for_each_entry(cbi, &vi->cb_interests, cb_vlink) { - if (fid->vnode == 0 && fid->unique == 0) { - /* The callback break applies to an entire volume. */ - struct afs_super_info *as = AFS_FS_S(cbi->sb); - struct afs_volume *volume = as->volume; - write_lock(&volume->cb_v_break_lock); - volume->cb_v_break++; - trace_afs_cb_break(fid, volume->cb_v_break, - afs_cb_break_for_volume_callback, false); - write_unlock(&volume->cb_v_break_lock); + for (i = *_count; i > 0; cbb++, i--) { + if (cbb->fid.vid == vid) { + _debug("- Fid { vl=%08llx n=%llu u=%u }", + cbb->fid.vid, + cbb->fid.vnode, + cbb->fid.unique); + --*_count; + if (volume) + afs_break_one_callback(volume, &cbb->fid); } else { - data.volume = NULL; - data.fid = *fid; - inode = ilookup5_nowait(cbi->sb, fid->vnode, - afs_iget5_test, &data); - if (inode) { - vnode = AFS_FS_I(inode); - afs_break_callback(vnode, afs_cb_break_for_callback); - iput(inode); - } else { - trace_afs_cb_miss(fid, afs_cb_break_for_callback); - } + *residue++ = *cbb; } } - -out: - read_unlock(&server->cb_break_lock); } /* @@ -313,29 +178,11 @@ void afs_break_callbacks(struct afs_server *server, size_t count, ASSERT(server != NULL); - /* TODO: Sort the callback break list by volume ID */ + rcu_read_lock(); - for (; count > 0; callbacks++, count--) { - _debug("- Fid { vl=%08llx n=%llu u=%u }", - callbacks->fid.vid, - callbacks->fid.vnode, - callbacks->fid.unique); - afs_break_one_callback(server, &callbacks->fid); - } + while (count > 0) + afs_break_some_callbacks(server, callbacks, &count); - _leave(""); + rcu_read_unlock(); return; } - -/* - * Clear the callback interests in a server list. - */ -void afs_clear_callback_interests(struct afs_net *net, struct afs_server_list *slist) -{ - int i; - - for (i = 0; i < slist->nr_servers; i++) { - afs_put_cb_interest(net, slist->servers[i].cb_interest); - slist->servers[i].cb_interest = NULL; - } -} diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 78ba5f932287..005921e3b38d 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -161,9 +161,13 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, atomic_set(&cell->usage, 2); INIT_WORK(&cell->manager, afs_manage_cell); - INIT_LIST_HEAD(&cell->proc_volumes); - rwlock_init(&cell->proc_lock); + cell->volumes = RB_ROOT; + INIT_HLIST_HEAD(&cell->proc_volumes); + seqlock_init(&cell->volume_lock); + cell->fs_servers = RB_ROOT; + seqlock_init(&cell->fs_lock); rwlock_init(&cell->vl_servers_lock); + cell->flags = (1 << AFS_CELL_FL_CHECK_ALIAS); /* Provide a VL server list, filling it in if we were given a list of * addresses to use. @@ -481,7 +485,9 @@ static void afs_cell_destroy(struct rcu_head *rcu) ASSERTCMP(atomic_read(&cell->usage), ==, 0); + afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root); afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers)); + afs_put_cell(cell->net, cell->alias_of); key_put(cell->anonymous_key); kfree(cell); diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 380ad5ace7cf..bef413818af7 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -118,8 +118,6 @@ bool afs_cm_incoming_call(struct afs_call *call) { _enter("{%u, CB.OP %u}", call->service_id, call->operation_ID); - call->epoch = rxrpc_kernel_get_epoch(call->net->socket, call->rxcall); - switch (call->operation_ID) { case CBCallBack: call->type = &afs_SRXCBCallBack; @@ -150,49 +148,6 @@ bool afs_cm_incoming_call(struct afs_call *call) } /* - * Record a probe to the cache manager from a server. - */ -static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server) -{ - _enter(""); - - if (test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags) && - !test_bit(AFS_SERVER_FL_PROBING, &server->flags)) { - if (server->cm_epoch == call->epoch) - return 0; - - if (!server->probe.said_rebooted) { - pr_notice("kAFS: FS rebooted %pU\n", &server->uuid); - server->probe.said_rebooted = true; - } - } - - spin_lock(&server->probe_lock); - - if (!test_and_set_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) { - server->cm_epoch = call->epoch; - server->probe.cm_epoch = call->epoch; - goto out; - } - - if (server->probe.cm_probed && - call->epoch != server->probe.cm_epoch && - !server->probe.said_inconsistent) { - pr_notice("kAFS: FS endpoints inconsistent %pU\n", - &server->uuid); - server->probe.said_inconsistent = true; - } - - if (!server->probe.cm_probed || call->epoch == server->cm_epoch) - server->probe.cm_epoch = server->cm_epoch; - -out: - server->probe.cm_probed = true; - spin_unlock(&server->probe_lock); - return 0; -} - -/* * Find the server record by peer address and record a probe to the cache * manager from a server. */ @@ -210,7 +165,7 @@ static int afs_find_cm_server_by_peer(struct afs_call *call) } call->server = server; - return afs_record_cm_probe(call, server); + return 0; } /* @@ -231,7 +186,7 @@ static int afs_find_cm_server_by_uuid(struct afs_call *call, } call->server = server; - return afs_record_cm_probe(call, server); + return 0; } /* @@ -268,7 +223,9 @@ static void SRXAFSCB_CallBack(struct work_struct *work) * to maintain cache coherency. */ if (call->server) { - trace_afs_server(call->server, atomic_read(&call->server->usage), + trace_afs_server(call->server, + atomic_read(&call->server->ref), + atomic_read(&call->server->active), afs_server_trace_callback); afs_break_callbacks(call->server, call->count, call->request); } @@ -305,8 +262,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->count = ntohl(call->tmp); _debug("FID count: %u", call->count); if (call->count > AFSCBMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_cb_fid_count); + return afs_protocol_error(call, afs_eproto_cb_fid_count); call->buffer = kmalloc(array3_size(call->count, 3, 4), GFP_KERNEL); @@ -351,8 +307,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->count2 = ntohl(call->tmp); _debug("CB count: %u", call->count2); if (call->count2 != call->count && call->count2 != 0) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_cb_count); + return afs_protocol_error(call, afs_eproto_cb_count); call->iter = &call->def_iter; iov_iter_discard(&call->def_iter, READ, call->count2 * 3 * 4); call->unmarshall++; @@ -509,7 +464,8 @@ static int afs_deliver_cb_probe(struct afs_call *call) } /* - * allow the fileserver to quickly find out if the fileserver has been rebooted + * Allow the fileserver to quickly find out if the cache manager has been + * rebooted. */ static void SRXAFSCB_ProbeUuid(struct work_struct *work) { @@ -581,7 +537,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) return afs_io_error(call, afs_io_error_cm_reply); - return afs_find_cm_server_by_uuid(call, call->request); + return afs_find_cm_server_by_peer(call); } /* @@ -672,8 +628,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call) call->count = ntohl(call->tmp); _debug("FID count: %u", call->count); if (call->count > YFSCBMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_cb_fid_count); + return afs_protocol_error(call, afs_eproto_cb_fid_count); size = array_size(call->count, sizeof(struct yfs_xdr_YFSFid)); call->buffer = kmalloc(size, GFP_KERNEL); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index d1e1caa23c8b..25cbe0aeeec5 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -99,8 +99,6 @@ struct afs_lookup_cookie { bool found; bool one_only; unsigned short nr_fids; - struct inode **inodes; - struct afs_status_cb *statuses; struct afs_fid fids[50]; }; @@ -618,8 +616,8 @@ static int afs_lookup_filldir(struct dir_context *ctx, const char *name, } } else if (cookie->name.len == nlen && memcmp(cookie->name.name, name, nlen) == 0) { - cookie->fids[0].vnode = ino; - cookie->fids[0].unique = dtype; + cookie->fids[1].vnode = ino; + cookie->fids[1].unique = dtype; cookie->found = 1; if (cookie->one_only) return -1; @@ -631,6 +629,111 @@ static int afs_lookup_filldir(struct dir_context *ctx, const char *name, } /* + * Deal with the result of a successful lookup operation. Turn all the files + * into inodes and save the first one - which is the one we actually want. + */ +static void afs_do_lookup_success(struct afs_operation *op) +{ + struct afs_vnode_param *vp; + struct afs_vnode *vnode; + struct inode *inode; + u32 abort_code; + int i; + + _enter(""); + + for (i = 0; i < op->nr_files; i++) { + switch (i) { + case 0: + vp = &op->file[0]; + abort_code = vp->scb.status.abort_code; + if (abort_code != 0) { + op->abort_code = abort_code; + op->error = afs_abort_to_error(abort_code); + } + break; + + case 1: + vp = &op->file[1]; + break; + + default: + vp = &op->more_files[i - 2]; + break; + } + + if (!vp->scb.have_status && !vp->scb.have_error) + continue; + + _debug("do [%u]", i); + if (vp->vnode) { + if (!test_bit(AFS_VNODE_UNSET, &vp->vnode->flags)) + afs_vnode_commit_status(op, vp); + } else if (vp->scb.status.abort_code == 0) { + inode = afs_iget(op, vp); + if (!IS_ERR(inode)) { + vnode = AFS_FS_I(inode); + afs_cache_permit(vnode, op->key, + 0 /* Assume vnode->cb_break is 0 */ + + op->cb_v_break, + &vp->scb); + vp->vnode = vnode; + vp->put_vnode = true; + } + } else { + _debug("- abort %d %llx:%llx.%x", + vp->scb.status.abort_code, + vp->fid.vid, vp->fid.vnode, vp->fid.unique); + } + } + + _leave(""); +} + +static const struct afs_operation_ops afs_inline_bulk_status_operation = { + .issue_afs_rpc = afs_fs_inline_bulk_status, + .issue_yfs_rpc = yfs_fs_inline_bulk_status, + .success = afs_do_lookup_success, +}; + +static const struct afs_operation_ops afs_fetch_status_operation = { + .issue_afs_rpc = afs_fs_fetch_status, + .issue_yfs_rpc = yfs_fs_fetch_status, + .success = afs_do_lookup_success, +}; + +/* + * See if we know that the server we expect to use doesn't support + * FS.InlineBulkStatus. + */ +static bool afs_server_supports_ibulk(struct afs_vnode *dvnode) +{ + struct afs_server_list *slist; + struct afs_volume *volume = dvnode->volume; + struct afs_server *server; + bool ret = true; + int i; + + if (!test_bit(AFS_VOLUME_MAYBE_NO_IBULK, &volume->flags)) + return true; + + rcu_read_lock(); + slist = rcu_dereference(volume->servers); + + for (i = 0; i < slist->nr_servers; i++) { + server = slist->servers[i].server; + if (server == dvnode->cb_server) { + if (test_bit(AFS_SERVER_FL_NO_IBULK, &server->flags)) + ret = false; + break; + } + } + + rcu_read_unlock(); + return ret; +} + +/* * Do a lookup in a directory. We make use of bulk lookup to query a slew of * files in one go and create inodes for them. The inode of the file we were * asked for is returned. @@ -639,16 +742,13 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct key *key) { struct afs_lookup_cookie *cookie; - struct afs_cb_interest *dcbi, *cbi = NULL; - struct afs_super_info *as = dir->i_sb->s_fs_info; - struct afs_status_cb *scb; - struct afs_iget_data iget_data; - struct afs_fs_cursor fc; - struct afs_server *server; + struct afs_vnode_param *vp; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); - int ret, i; + long ret; + int i; _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); @@ -656,72 +756,74 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, if (!cookie) return ERR_PTR(-ENOMEM); + for (i = 0; i < ARRAY_SIZE(cookie->fids); i++) + cookie->fids[i].vid = dvnode->fid.vid; cookie->ctx.actor = afs_lookup_filldir; cookie->name = dentry->d_name; - cookie->nr_fids = 1; /* slot 0 is saved for the fid we actually want */ - - read_seqlock_excl(&dvnode->cb_lock); - dcbi = rcu_dereference_protected(dvnode->cb_interest, - lockdep_is_held(&dvnode->cb_lock.lock)); - if (dcbi) { - server = dcbi->server; - if (server && - test_bit(AFS_SERVER_FL_NO_IBULK, &server->flags)) - cookie->one_only = true; - } - read_sequnlock_excl(&dvnode->cb_lock); + cookie->nr_fids = 2; /* slot 0 is saved for the fid we actually want + * and slot 1 for the directory */ - for (i = 0; i < 50; i++) - cookie->fids[i].vid = as->volume->vid; + if (!afs_server_supports_ibulk(dvnode)) + cookie->one_only = true; /* search the directory */ ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version); - if (ret < 0) { - inode = ERR_PTR(ret); + if (ret < 0) goto out; - } dentry->d_fsdata = (void *)(unsigned long)data_version; - inode = ERR_PTR(-ENOENT); + ret = -ENOENT; if (!cookie->found) goto out; /* Check to see if we already have an inode for the primary fid. */ - iget_data.fid = cookie->fids[0]; - iget_data.volume = dvnode->volume; - iget_data.cb_v_break = dvnode->volume->cb_v_break; - iget_data.cb_s_break = 0; - inode = ilookup5(dir->i_sb, cookie->fids[0].vnode, - afs_iget5_test, &iget_data); + inode = ilookup5(dir->i_sb, cookie->fids[1].vnode, + afs_ilookup5_test_by_fid, &cookie->fids[1]); if (inode) - goto out; + goto out; /* We do */ - /* Need space for examining all the selected files */ - inode = ERR_PTR(-ENOMEM); - cookie->statuses = kvcalloc(cookie->nr_fids, sizeof(struct afs_status_cb), - GFP_KERNEL); - if (!cookie->statuses) + /* Okay, we didn't find it. We need to query the server - and whilst + * we're doing that, we're going to attempt to look up a bunch of other + * vnodes also. + */ + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) { + ret = PTR_ERR(op); goto out; + } - cookie->inodes = kcalloc(cookie->nr_fids, sizeof(struct inode *), - GFP_KERNEL); - if (!cookie->inodes) - goto out_s; + afs_op_set_vnode(op, 0, dvnode); + afs_op_set_fid(op, 1, &cookie->fids[1]); - for (i = 1; i < cookie->nr_fids; i++) { - scb = &cookie->statuses[i]; + op->nr_files = cookie->nr_fids; + _debug("nr_files %u", op->nr_files); - /* Find any inodes that already exist and get their - * callback counters. - */ - iget_data.fid = cookie->fids[i]; - ti = ilookup5_nowait(dir->i_sb, iget_data.fid.vnode, - afs_iget5_test, &iget_data); - if (!IS_ERR_OR_NULL(ti)) { - vnode = AFS_FS_I(ti); - scb->cb_break = afs_calc_vnode_cb_break(vnode); - cookie->inodes[i] = ti; + /* Need space for examining all the selected files */ + op->error = -ENOMEM; + if (op->nr_files > 2) { + op->more_files = kvcalloc(op->nr_files - 2, + sizeof(struct afs_vnode_param), + GFP_KERNEL); + if (!op->more_files) + goto out_op; + + for (i = 2; i < op->nr_files; i++) { + vp = &op->more_files[i - 2]; + vp->fid = cookie->fids[i]; + + /* Find any inodes that already exist and get their + * callback counters. + */ + ti = ilookup5_nowait(dir->i_sb, vp->fid.vnode, + afs_ilookup5_test_by_fid, &vp->fid); + if (!IS_ERR_OR_NULL(ti)) { + vnode = AFS_FS_I(ti); + vp->dv_before = vnode->status.data_version; + vp->cb_break_before = afs_calc_vnode_cb_break(vnode); + vp->vnode = vnode; + vp->put_vnode = true; + } } } @@ -729,120 +831,40 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, * lookups contained therein are stored in the reply without aborting * the whole operation. */ - if (cookie->one_only) - goto no_inline_bulk_status; - - inode = ERR_PTR(-ERESTARTSYS); - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - while (afs_select_fileserver(&fc)) { - if (test_bit(AFS_SERVER_FL_NO_IBULK, - &fc.cbi->server->flags)) { - fc.ac.abort_code = RX_INVALID_OPERATION; - fc.ac.error = -ECONNABORTED; - break; - } - iget_data.cb_v_break = dvnode->volume->cb_v_break; - iget_data.cb_s_break = fc.cbi->server->cb_s_break; - afs_fs_inline_bulk_status(&fc, - afs_v2net(dvnode), - cookie->fids, - cookie->statuses, - cookie->nr_fids, NULL); - } - - if (fc.ac.error == 0) - cbi = afs_get_cb_interest(fc.cbi); - if (fc.ac.abort_code == RX_INVALID_OPERATION) - set_bit(AFS_SERVER_FL_NO_IBULK, &fc.cbi->server->flags); - inode = ERR_PTR(afs_end_vnode_operation(&fc)); + op->error = -ENOTSUPP; + if (!cookie->one_only) { + op->ops = &afs_inline_bulk_status_operation; + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); } - if (!IS_ERR(inode)) - goto success; - if (fc.ac.abort_code != RX_INVALID_OPERATION) - goto out_c; - -no_inline_bulk_status: - /* We could try FS.BulkStatus next, but this aborts the entire op if - * any of the lookups fails - so, for the moment, revert to - * FS.FetchStatus for just the primary fid. - */ - inode = ERR_PTR(-ERESTARTSYS); - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - while (afs_select_fileserver(&fc)) { - iget_data.cb_v_break = dvnode->volume->cb_v_break; - iget_data.cb_s_break = fc.cbi->server->cb_s_break; - scb = &cookie->statuses[0]; - afs_fs_fetch_status(&fc, - afs_v2net(dvnode), - cookie->fids, - scb, - NULL); - } - - if (fc.ac.error == 0) - cbi = afs_get_cb_interest(fc.cbi); - inode = ERR_PTR(afs_end_vnode_operation(&fc)); + if (op->error == -ENOTSUPP) { + /* We could try FS.BulkStatus next, but this aborts the entire + * op if any of the lookups fails - so, for the moment, revert + * to FS.FetchStatus for op->file[1]. + */ + op->fetch_status.which = 1; + op->ops = &afs_fetch_status_operation; + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); } + inode = ERR_PTR(op->error); - if (IS_ERR(inode)) - goto out_c; - -success: - /* Turn all the files into inodes and save the first one - which is the - * one we actually want. - */ - scb = &cookie->statuses[0]; - if (scb->status.abort_code != 0) - inode = ERR_PTR(afs_abort_to_error(scb->status.abort_code)); - - for (i = 0; i < cookie->nr_fids; i++) { - struct afs_status_cb *scb = &cookie->statuses[i]; - - if (!scb->have_status && !scb->have_error) - continue; - - if (cookie->inodes[i]) { - struct afs_vnode *iv = AFS_FS_I(cookie->inodes[i]); - - if (test_bit(AFS_VNODE_UNSET, &iv->flags)) - continue; - - afs_vnode_commit_status(&fc, iv, - scb->cb_break, NULL, scb); - continue; - } - - if (scb->status.abort_code != 0) - continue; - - iget_data.fid = cookie->fids[i]; - ti = afs_iget(dir->i_sb, key, &iget_data, scb, cbi, dvnode); - if (!IS_ERR(ti)) - afs_cache_permit(AFS_FS_I(ti), key, - 0 /* Assume vnode->cb_break is 0 */ + - iget_data.cb_v_break, - scb); - if (i == 0) { - inode = ti; - } else { - if (!IS_ERR(ti)) - iput(ti); - } +out_op: + if (op->error == 0) { + inode = &op->file[1].vnode->vfs_inode; + op->file[1].vnode = NULL; } -out_c: - afs_put_cb_interest(afs_v2net(dvnode), cbi); - if (cookie->inodes) { - for (i = 0; i < cookie->nr_fids; i++) - iput(cookie->inodes[i]); - kfree(cookie->inodes); - } -out_s: - kvfree(cookie->statuses); + if (op->file[0].scb.have_status) + dentry->d_fsdata = (void *)(unsigned long)op->file[0].scb.status.data_version; + else + dentry->d_fsdata = (void *)(unsigned long)op->file[0].dv_before; + ret = afs_put_operation(op); out: kfree(cookie); - return inode; + _leave(""); + return inode ?: ERR_PTR(ret); } /* @@ -958,6 +980,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, if (!IS_ERR_OR_NULL(inode)) fid = AFS_FS_I(inode)->fid; + _debug("splice %px", dentry->d_inode); d = d_splice_alias(inode, dentry); if (!IS_ERR_OR_NULL(d)) { d->d_fsdata = dentry->d_fsdata; @@ -965,6 +988,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, } else { trace_afs_lookup(dvnode, &dentry->d_name, &fid); } + _leave(""); return d; } @@ -1215,130 +1239,97 @@ void afs_d_release(struct dentry *dentry) /* * Create a new inode for create/mkdir/symlink */ -static void afs_vnode_new_inode(struct afs_fs_cursor *fc, - struct dentry *new_dentry, - struct afs_iget_data *new_data, - struct afs_status_cb *new_scb) +static void afs_vnode_new_inode(struct afs_operation *op) { + struct afs_vnode_param *vp = &op->file[1]; struct afs_vnode *vnode; struct inode *inode; - if (fc->ac.error < 0) - return; + _enter(""); + + ASSERTCMP(op->error, ==, 0); - inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key, - new_data, new_scb, fc->cbi, fc->vnode); + inode = afs_iget(op, vp); if (IS_ERR(inode)) { /* ENOMEM or EINTR at a really inconvenient time - just abandon * the new directory on the server. */ - fc->ac.error = PTR_ERR(inode); + op->error = PTR_ERR(inode); return; } vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - if (fc->ac.error == 0) - afs_cache_permit(vnode, fc->key, vnode->cb_break, new_scb); - d_instantiate(new_dentry, inode); + if (!op->error) + afs_cache_permit(vnode, op->key, vnode->cb_break, &vp->scb); + d_instantiate(op->dentry, inode); } -static void afs_prep_for_new_inode(struct afs_fs_cursor *fc, - struct afs_iget_data *iget_data) +static void afs_create_success(struct afs_operation *op) { - iget_data->volume = fc->vnode->volume; - iget_data->cb_v_break = fc->vnode->volume->cb_v_break; - iget_data->cb_s_break = fc->cbi->server->cb_s_break; + _enter("op=%08x", op->debug_id); + afs_check_for_remote_deletion(op, op->file[0].vnode); + afs_vnode_commit_status(op, &op->file[0]); + afs_update_dentry_version(op, &op->file[0], op->dentry); + afs_vnode_new_inode(op); } -/* - * Note that a dentry got changed. We need to set d_fsdata to the data version - * number derived from the result of the operation. It doesn't matter if - * d_fsdata goes backwards as we'll just revalidate. - */ -static void afs_update_dentry_version(struct afs_fs_cursor *fc, - struct dentry *dentry, - struct afs_status_cb *scb) +static void afs_create_edit_dir(struct afs_operation *op) +{ + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; + struct afs_vnode *dvnode = dvp->vnode; + + _enter("op=%08x", op->debug_id); + + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) + afs_edit_dir_add(dvnode, &op->dentry->d_name, &vp->fid, + op->create.reason); + up_write(&dvnode->validate_lock); +} + +static void afs_create_put(struct afs_operation *op) { - if (fc->ac.error == 0) - dentry->d_fsdata = - (void *)(unsigned long)scb->status.data_version; + _enter("op=%08x", op->debug_id); + + if (op->error) + d_drop(op->dentry); } +static const struct afs_operation_ops afs_mkdir_operation = { + .issue_afs_rpc = afs_fs_make_dir, + .issue_yfs_rpc = yfs_fs_make_dir, + .success = afs_create_success, + .edit_dir = afs_create_edit_dir, + .put = afs_create_put, +}; + /* * create a directory on an AFS filesystem */ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { - struct afs_iget_data iget_data; - struct afs_status_cb *scb; - struct afs_fs_cursor fc; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct key *key; - afs_dataversion_t data_version; - int ret; - - mode |= S_IFDIR; _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); - ret = -ENOMEM; - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - goto error; - - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) { + d_drop(dentry); + return PTR_ERR(op); } - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - data_version = dvnode->status.data_version + 1; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_prep_for_new_inode(&fc, &iget_data); - afs_fs_create(&fc, dentry->d_name.name, mode, - &scb[0], &iget_data.fid, &scb[1]); - } - - afs_check_for_remote_deletion(&fc, dvnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &data_version, &scb[0]); - afs_update_dentry_version(&fc, dentry, &scb[0]); - afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); - ret = afs_end_vnode_operation(&fc); - if (ret < 0) - goto error_key; - } else { - goto error_key; - } - - if (ret == 0) { - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == data_version) - afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, - afs_edit_dir_for_create); - up_write(&dvnode->validate_lock); - } - - key_put(key); - kfree(scb); - _leave(" = 0"); - return 0; - -error_key: - key_put(key); -error_scb: - kfree(scb); -error: - d_drop(dentry); - _leave(" = %d", ret); - return ret; + afs_op_set_vnode(op, 0, dvnode); + op->file[0].dv_delta = 1; + op->dentry = dentry; + op->create.mode = S_IFDIR | mode; + op->create.reason = afs_edit_dir_for_mkdir; + op->ops = &afs_mkdir_operation; + return afs_do_sync_operation(op); } /* @@ -1356,76 +1347,86 @@ static void afs_dir_remove_subdir(struct dentry *dentry) } } +static void afs_rmdir_success(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + afs_check_for_remote_deletion(op, op->file[0].vnode); + afs_vnode_commit_status(op, &op->file[0]); + afs_update_dentry_version(op, &op->file[0], op->dentry); +} + +static void afs_rmdir_edit_dir(struct afs_operation *op) +{ + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode *dvnode = dvp->vnode; + + _enter("op=%08x", op->debug_id); + afs_dir_remove_subdir(op->dentry); + + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) + afs_edit_dir_remove(dvnode, &op->dentry->d_name, + afs_edit_dir_for_rmdir); + up_write(&dvnode->validate_lock); +} + +static void afs_rmdir_put(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + if (op->file[1].vnode) + up_write(&op->file[1].vnode->rmdir_lock); +} + +static const struct afs_operation_ops afs_rmdir_operation = { + .issue_afs_rpc = afs_fs_remove_dir, + .issue_yfs_rpc = yfs_fs_remove_dir, + .success = afs_rmdir_success, + .edit_dir = afs_rmdir_edit_dir, + .put = afs_rmdir_put, +}; + /* * remove a directory from an AFS filesystem */ static int afs_rmdir(struct inode *dir, struct dentry *dentry) { - struct afs_status_cb *scb; - struct afs_fs_cursor fc; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; - struct key *key; - afs_dataversion_t data_version; int ret; _enter("{%llx:%llu},{%pd}", dvnode->fid.vid, dvnode->fid.vnode, dentry); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error; - } + afs_op_set_vnode(op, 0, dvnode); + op->file[0].dv_delta = 1; + + op->dentry = dentry; + op->ops = &afs_rmdir_operation; /* Try to make sure we have a callback promise on the victim. */ if (d_really_is_positive(dentry)) { vnode = AFS_FS_I(d_inode(dentry)); - ret = afs_validate(vnode, key); + ret = afs_validate(vnode, op->key); if (ret < 0) - goto error_key; + goto error; } if (vnode) { ret = down_write_killable(&vnode->rmdir_lock); if (ret < 0) - goto error_key; + goto error; + op->file[1].vnode = vnode; } - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - data_version = dvnode->status.data_version + 1; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_remove(&fc, vnode, dentry->d_name.name, true, scb); - } - - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &data_version, scb); - afs_update_dentry_version(&fc, dentry, scb); - ret = afs_end_vnode_operation(&fc); - if (ret == 0) { - afs_dir_remove_subdir(dentry); - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == data_version) - afs_edit_dir_remove(dvnode, &dentry->d_name, - afs_edit_dir_for_rmdir); - up_write(&dvnode->validate_lock); - } - } + return afs_do_sync_operation(op); - if (vnode) - up_write(&vnode->rmdir_lock); -error_key: - key_put(key); error: - kfree(scb); - return ret; + return afs_put_operation(op); } /* @@ -1438,52 +1439,90 @@ error: * However, if we didn't have a callback promise outstanding, or it was * outstanding on a different server, then it won't break it either... */ -static int afs_dir_remove_link(struct afs_vnode *dvnode, struct dentry *dentry, - struct key *key) +static void afs_dir_remove_link(struct afs_operation *op) { - int ret = 0; + struct afs_vnode *dvnode = op->file[0].vnode; + struct afs_vnode *vnode = op->file[1].vnode; + struct dentry *dentry = op->dentry; + int ret; - if (d_really_is_positive(dentry)) { - struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); + if (op->error != 0 || + (op->file[1].scb.have_status && op->file[1].scb.have_error)) + return; + if (d_really_is_positive(dentry)) + return; - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { - /* Already done */ - } else if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { - write_seqlock(&vnode->cb_lock); - drop_nlink(&vnode->vfs_inode); - if (vnode->vfs_inode.i_nlink == 0) { - set_bit(AFS_VNODE_DELETED, &vnode->flags); - __afs_break_callback(vnode, afs_cb_break_for_unlink); - } - write_sequnlock(&vnode->cb_lock); - ret = 0; - } else { - afs_break_callback(vnode, afs_cb_break_for_unlink); + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { + /* Already done */ + } else if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + write_seqlock(&vnode->cb_lock); + drop_nlink(&vnode->vfs_inode); + if (vnode->vfs_inode.i_nlink == 0) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + __afs_break_callback(vnode, afs_cb_break_for_unlink); + } + write_sequnlock(&vnode->cb_lock); + } else { + afs_break_callback(vnode, afs_cb_break_for_unlink); - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) - kdebug("AFS_VNODE_DELETED"); + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) + _debug("AFS_VNODE_DELETED"); - ret = afs_validate(vnode, key); - if (ret == -ESTALE) - ret = 0; - } - _debug("nlink %d [val %d]", vnode->vfs_inode.i_nlink, ret); + ret = afs_validate(vnode, op->key); + if (ret != -ESTALE) + op->error = ret; } - return ret; + _debug("nlink %d [val %d]", vnode->vfs_inode.i_nlink, op->error); +} + +static void afs_unlink_success(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + afs_check_for_remote_deletion(op, op->file[0].vnode); + afs_vnode_commit_status(op, &op->file[0]); + afs_vnode_commit_status(op, &op->file[1]); + afs_update_dentry_version(op, &op->file[0], op->dentry); + afs_dir_remove_link(op); +} + +static void afs_unlink_edit_dir(struct afs_operation *op) +{ + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode *dvnode = dvp->vnode; + + _enter("op=%08x", op->debug_id); + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) + afs_edit_dir_remove(dvnode, &op->dentry->d_name, + afs_edit_dir_for_unlink); + up_write(&dvnode->validate_lock); +} + +static void afs_unlink_put(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + if (op->unlink.need_rehash && op->error < 0 && op->error != -ENOENT) + d_rehash(op->dentry); } +static const struct afs_operation_ops afs_unlink_operation = { + .issue_afs_rpc = afs_fs_remove_file, + .issue_yfs_rpc = yfs_fs_remove_file, + .success = afs_unlink_success, + .edit_dir = afs_unlink_edit_dir, + .put = afs_unlink_put, +}; + /* * Remove a file or symlink from an AFS filesystem. */ static int afs_unlink(struct inode *dir, struct dentry *dentry) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); - struct key *key; - bool need_rehash = false; int ret; _enter("{%llx:%llu},{%pd}", @@ -1492,269 +1531,176 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) if (dentry->d_name.len >= AFSNAMEMAX) return -ENAMETOOLONG; - ret = -ENOMEM; - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - goto error; + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; - } + afs_op_set_vnode(op, 0, dvnode); + op->file[0].dv_delta = 1; /* Try to make sure we have a callback promise on the victim. */ - ret = afs_validate(vnode, key); - if (ret < 0) - goto error_key; + ret = afs_validate(vnode, op->key); + if (ret < 0) { + op->error = ret; + goto error; + } spin_lock(&dentry->d_lock); if (d_count(dentry) > 1) { spin_unlock(&dentry->d_lock); /* Start asynchronous writeout of the inode */ write_inode_now(d_inode(dentry), 0); - ret = afs_sillyrename(dvnode, vnode, dentry, key); - goto error_key; + op->error = afs_sillyrename(dvnode, vnode, dentry, op->key); + goto error; } if (!d_unhashed(dentry)) { /* Prevent a race with RCU lookup. */ __d_drop(dentry); - need_rehash = true; + op->unlink.need_rehash = true; } spin_unlock(&dentry->d_lock); - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t data_version = dvnode->status.data_version + 1; - afs_dataversion_t data_version_2 = vnode->status.data_version; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); - - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && - !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { - yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, - &scb[0], &scb[1]); - if (fc.ac.error != -ECONNABORTED || - fc.ac.abort_code != RXGEN_OPCODE) - continue; - set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); - } - - afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]); - } + op->file[1].vnode = vnode; + op->dentry = dentry; + op->ops = &afs_unlink_operation; + return afs_do_sync_operation(op); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &data_version, &scb[0]); - afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, - &data_version_2, &scb[1]); - afs_update_dentry_version(&fc, dentry, &scb[0]); - ret = afs_end_vnode_operation(&fc); - if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) - ret = afs_dir_remove_link(dvnode, dentry, key); - - if (ret == 0) { - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == data_version) - afs_edit_dir_remove(dvnode, &dentry->d_name, - afs_edit_dir_for_unlink); - up_write(&dvnode->validate_lock); - } - } - - if (need_rehash && ret < 0 && ret != -ENOENT) - d_rehash(dentry); - -error_key: - key_put(key); -error_scb: - kfree(scb); error: - _leave(" = %d", ret); - return ret; + return afs_put_operation(op); } +static const struct afs_operation_ops afs_create_operation = { + .issue_afs_rpc = afs_fs_create_file, + .issue_yfs_rpc = yfs_fs_create_file, + .success = afs_create_success, + .edit_dir = afs_create_edit_dir, + .put = afs_create_put, +}; + /* * create a regular file on an AFS filesystem */ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct afs_iget_data iget_data; - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct key *key; - afs_dataversion_t data_version; - int ret; - - mode |= S_IFREG; + int ret = -ENAMETOOLONG; - _enter("{%llx:%llu},{%pd},%ho,", + _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); - ret = -ENAMETOOLONG; if (dentry->d_name.len >= AFSNAMEMAX) goto error; - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) { + ret = PTR_ERR(op); goto error; } - ret = -ENOMEM; - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - goto error_scb; + afs_op_set_vnode(op, 0, dvnode); + op->file[0].dv_delta = 1; - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - data_version = dvnode->status.data_version + 1; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_prep_for_new_inode(&fc, &iget_data); - afs_fs_create(&fc, dentry->d_name.name, mode, - &scb[0], &iget_data.fid, &scb[1]); - } + op->dentry = dentry; + op->create.mode = S_IFREG | mode; + op->create.reason = afs_edit_dir_for_create; + op->ops = &afs_create_operation; + return afs_do_sync_operation(op); - afs_check_for_remote_deletion(&fc, dvnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &data_version, &scb[0]); - afs_update_dentry_version(&fc, dentry, &scb[0]); - afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); - ret = afs_end_vnode_operation(&fc); - if (ret < 0) - goto error_key; - } else { - goto error_key; - } - - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == data_version) - afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, - afs_edit_dir_for_create); - up_write(&dvnode->validate_lock); - - kfree(scb); - key_put(key); - _leave(" = 0"); - return 0; - -error_scb: - kfree(scb); -error_key: - key_put(key); error: d_drop(dentry); _leave(" = %d", ret); return ret; } +static void afs_link_success(struct afs_operation *op) +{ + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; + + _enter("op=%08x", op->debug_id); + afs_vnode_commit_status(op, dvp); + afs_vnode_commit_status(op, vp); + afs_update_dentry_version(op, dvp, op->dentry); + if (op->dentry_2->d_parent == op->dentry->d_parent) + afs_update_dentry_version(op, dvp, op->dentry_2); + ihold(&vp->vnode->vfs_inode); + d_instantiate(op->dentry, &vp->vnode->vfs_inode); +} + +static void afs_link_put(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + if (op->error) + d_drop(op->dentry); +} + +static const struct afs_operation_ops afs_link_operation = { + .issue_afs_rpc = afs_fs_link, + .issue_yfs_rpc = yfs_fs_link, + .success = afs_link_success, + .edit_dir = afs_create_edit_dir, + .put = afs_link_put, +}; + /* * create a hard link between files in an AFS filesystem */ static int afs_link(struct dentry *from, struct inode *dir, struct dentry *dentry) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); struct afs_vnode *vnode = AFS_FS_I(d_inode(from)); - struct key *key; - afs_dataversion_t data_version; - int ret; + int ret = -ENAMETOOLONG; _enter("{%llx:%llu},{%llx:%llu},{%pd}", vnode->fid.vid, vnode->fid.vnode, dvnode->fid.vid, dvnode->fid.vnode, dentry); - ret = -ENAMETOOLONG; if (dentry->d_name.len >= AFSNAMEMAX) goto error; - ret = -ENOMEM; - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) { + ret = PTR_ERR(op); goto error; - - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; - } - - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - data_version = dvnode->status.data_version + 1; - - if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) { - afs_end_vnode_operation(&fc); - goto error_key; - } - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); - afs_fs_link(&fc, vnode, dentry->d_name.name, - &scb[0], &scb[1]); - } - - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &data_version, &scb[0]); - afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, - NULL, &scb[1]); - ihold(&vnode->vfs_inode); - afs_update_dentry_version(&fc, dentry, &scb[0]); - d_instantiate(dentry, &vnode->vfs_inode); - - mutex_unlock(&vnode->io_lock); - ret = afs_end_vnode_operation(&fc); - if (ret < 0) - goto error_key; - } else { - goto error_key; } - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == data_version) - afs_edit_dir_add(dvnode, &dentry->d_name, &vnode->fid, - afs_edit_dir_for_link); - up_write(&dvnode->validate_lock); + afs_op_set_vnode(op, 0, dvnode); + afs_op_set_vnode(op, 1, vnode); + op->file[0].dv_delta = 1; - key_put(key); - kfree(scb); - _leave(" = 0"); - return 0; + op->dentry = dentry; + op->dentry_2 = from; + op->ops = &afs_link_operation; + op->create.reason = afs_edit_dir_for_link; + return afs_do_sync_operation(op); -error_key: - key_put(key); -error_scb: - kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); return ret; } +static const struct afs_operation_ops afs_symlink_operation = { + .issue_afs_rpc = afs_fs_symlink, + .issue_yfs_rpc = yfs_fs_symlink, + .success = afs_create_success, + .edit_dir = afs_create_edit_dir, + .put = afs_create_put, +}; + /* * create a symlink in an AFS filesystem */ static int afs_symlink(struct inode *dir, struct dentry *dentry, const char *content) { - struct afs_iget_data iget_data; - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct key *key; - afs_dataversion_t data_version; int ret; _enter("{%llx:%llu},{%pd},%s", @@ -1769,62 +1715,115 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, if (strlen(content) >= AFSPATHMAX) goto error; - ret = -ENOMEM; - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) { + ret = PTR_ERR(op); goto error; - - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; } - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - data_version = dvnode->status.data_version + 1; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_prep_for_new_inode(&fc, &iget_data); - afs_fs_symlink(&fc, dentry->d_name.name, content, - &scb[0], &iget_data.fid, &scb[1]); - } + afs_op_set_vnode(op, 0, dvnode); + op->file[0].dv_delta = 1; - afs_check_for_remote_deletion(&fc, dvnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &data_version, &scb[0]); - afs_update_dentry_version(&fc, dentry, &scb[0]); - afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); - ret = afs_end_vnode_operation(&fc); - if (ret < 0) - goto error_key; - } else { - goto error_key; - } - - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == data_version) - afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, - afs_edit_dir_for_symlink); - up_write(&dvnode->validate_lock); + op->dentry = dentry; + op->ops = &afs_symlink_operation; + op->create.reason = afs_edit_dir_for_symlink; + op->create.symlink = content; + return afs_do_sync_operation(op); - key_put(key); - kfree(scb); - _leave(" = 0"); - return 0; - -error_key: - key_put(key); -error_scb: - kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); return ret; } +static void afs_rename_success(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + + afs_vnode_commit_status(op, &op->file[0]); + if (op->file[1].vnode != op->file[0].vnode) + afs_vnode_commit_status(op, &op->file[1]); +} + +static void afs_rename_edit_dir(struct afs_operation *op) +{ + struct afs_vnode_param *orig_dvp = &op->file[0]; + struct afs_vnode_param *new_dvp = &op->file[1]; + struct afs_vnode *orig_dvnode = orig_dvp->vnode; + struct afs_vnode *new_dvnode = new_dvp->vnode; + struct afs_vnode *vnode = AFS_FS_I(d_inode(op->dentry)); + struct dentry *old_dentry = op->dentry; + struct dentry *new_dentry = op->dentry_2; + struct inode *new_inode; + + _enter("op=%08x", op->debug_id); + + if (op->rename.rehash) { + d_rehash(op->rename.rehash); + op->rename.rehash = NULL; + } + + down_write(&orig_dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) && + orig_dvnode->status.data_version == orig_dvp->dv_before + orig_dvp->dv_delta) + afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name, + afs_edit_dir_for_rename_0); + + if (new_dvnode != orig_dvnode) { + up_write(&orig_dvnode->validate_lock); + down_write(&new_dvnode->validate_lock); + } + + if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags) && + new_dvnode->status.data_version == new_dvp->dv_before + new_dvp->dv_delta) { + if (!op->rename.new_negative) + afs_edit_dir_remove(new_dvnode, &new_dentry->d_name, + afs_edit_dir_for_rename_1); + + afs_edit_dir_add(new_dvnode, &new_dentry->d_name, + &vnode->fid, afs_edit_dir_for_rename_2); + } + + new_inode = d_inode(new_dentry); + if (new_inode) { + spin_lock(&new_inode->i_lock); + if (new_inode->i_nlink > 0) + drop_nlink(new_inode); + spin_unlock(&new_inode->i_lock); + } + + /* Now we can update d_fsdata on the dentries to reflect their + * new parent's data_version. + * + * Note that if we ever implement RENAME_EXCHANGE, we'll have + * to update both dentries with opposing dir versions. + */ + afs_update_dentry_version(op, new_dvp, op->dentry); + afs_update_dentry_version(op, new_dvp, op->dentry_2); + + d_move(old_dentry, new_dentry); + + up_write(&new_dvnode->validate_lock); +} + +static void afs_rename_put(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + if (op->rename.rehash) + d_rehash(op->rename.rehash); + dput(op->rename.tmp); + if (op->error) + d_rehash(op->dentry); +} + +static const struct afs_operation_ops afs_rename_operation = { + .issue_afs_rpc = afs_fs_rename, + .issue_yfs_rpc = yfs_fs_rename, + .success = afs_rename_success, + .edit_dir = afs_rename_edit_dir, + .put = afs_rename_put, +}; + /* * rename a file in an AFS filesystem and/or move it between directories */ @@ -1832,15 +1831,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *orig_dvnode, *new_dvnode, *vnode; - struct dentry *tmp = NULL, *rehash = NULL; - struct inode *new_inode; - struct key *key; - afs_dataversion_t orig_data_version; - afs_dataversion_t new_data_version; - bool new_negative = d_is_negative(new_dentry); int ret; if (flags) @@ -1860,16 +1852,19 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dvnode->fid.vid, new_dvnode->fid.vnode, new_dentry); - ret = -ENOMEM; - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - goto error; + op = afs_alloc_operation(NULL, orig_dvnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - key = afs_request_key(orig_dvnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; - } + afs_op_set_vnode(op, 0, orig_dvnode); + afs_op_set_vnode(op, 1, new_dvnode); /* May be same as orig_dvnode */ + op->file[0].dv_delta = 1; + op->file[1].dv_delta = 1; + + op->dentry = old_dentry; + op->dentry_2 = new_dentry; + op->rename.new_negative = d_is_negative(new_dentry); + op->ops = &afs_rename_operation; /* For non-directories, check whether the target is busy and if so, * make a copy of the dentry and then do a silly-rename. If the @@ -1882,26 +1877,26 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, */ if (!d_unhashed(new_dentry)) { d_drop(new_dentry); - rehash = new_dentry; + op->rename.rehash = new_dentry; } if (d_count(new_dentry) > 2) { /* copy the target dentry's name */ ret = -ENOMEM; - tmp = d_alloc(new_dentry->d_parent, - &new_dentry->d_name); - if (!tmp) - goto error_rehash; + op->rename.tmp = d_alloc(new_dentry->d_parent, + &new_dentry->d_name); + if (!op->rename.tmp) + goto error; ret = afs_sillyrename(new_dvnode, AFS_FS_I(d_inode(new_dentry)), - new_dentry, key); + new_dentry, op->key); if (ret) - goto error_rehash; + goto error; - new_dentry = tmp; - rehash = NULL; - new_negative = true; + op->dentry_2 = op->rename.tmp; + op->rename.rehash = NULL; + op->rename.new_negative = true; } } @@ -1916,98 +1911,10 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, */ d_drop(old_dentry); - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { - orig_data_version = orig_dvnode->status.data_version + 1; - - if (orig_dvnode != new_dvnode) { - if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) { - afs_end_vnode_operation(&fc); - goto error_rehash_old; - } - new_data_version = new_dvnode->status.data_version + 1; - } else { - new_data_version = orig_data_version; - } - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode); - fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode); - afs_fs_rename(&fc, old_dentry->d_name.name, - new_dvnode, new_dentry->d_name.name, - &scb[0], &scb[1]); - } + return afs_do_sync_operation(op); - afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break, - &orig_data_version, &scb[0]); - if (new_dvnode != orig_dvnode) { - afs_vnode_commit_status(&fc, new_dvnode, fc.cb_break_2, - &new_data_version, &scb[1]); - mutex_unlock(&new_dvnode->io_lock); - } - ret = afs_end_vnode_operation(&fc); - if (ret < 0) - goto error_rehash_old; - } - - if (ret == 0) { - if (rehash) - d_rehash(rehash); - down_write(&orig_dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) && - orig_dvnode->status.data_version == orig_data_version) - afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name, - afs_edit_dir_for_rename_0); - if (orig_dvnode != new_dvnode) { - up_write(&orig_dvnode->validate_lock); - - down_write(&new_dvnode->validate_lock); - } - if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags) && - orig_dvnode->status.data_version == new_data_version) { - if (!new_negative) - afs_edit_dir_remove(new_dvnode, &new_dentry->d_name, - afs_edit_dir_for_rename_1); - - afs_edit_dir_add(new_dvnode, &new_dentry->d_name, - &vnode->fid, afs_edit_dir_for_rename_2); - } - - new_inode = d_inode(new_dentry); - if (new_inode) { - spin_lock(&new_inode->i_lock); - if (new_inode->i_nlink > 0) - drop_nlink(new_inode); - spin_unlock(&new_inode->i_lock); - } - - /* Now we can update d_fsdata on the dentries to reflect their - * new parent's data_version. - * - * Note that if we ever implement RENAME_EXCHANGE, we'll have - * to update both dentries with opposing dir versions. - */ - afs_update_dentry_version(&fc, old_dentry, &scb[1]); - afs_update_dentry_version(&fc, new_dentry, &scb[1]); - d_move(old_dentry, new_dentry); - up_write(&new_dvnode->validate_lock); - goto error_tmp; - } - -error_rehash_old: - d_rehash(new_dentry); -error_rehash: - if (rehash) - d_rehash(rehash); -error_tmp: - if (tmp) - dput(tmp); - key_put(key); -error_scb: - kfree(scb); error: - _leave(" = %d", ret); - return ret; + return afs_put_operation(op); } /* diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index d94e2b7cddff..b14e3d9a25e2 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -12,6 +12,47 @@ #include <linux/fsnotify.h> #include "internal.h" +static void afs_silly_rename_success(struct afs_operation *op) +{ + _enter("op=%08x", op->debug_id); + + afs_vnode_commit_status(op, &op->file[0]); +} + +static void afs_silly_rename_edit_dir(struct afs_operation *op) +{ + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode *dvnode = dvp->vnode; + struct afs_vnode *vnode = AFS_FS_I(d_inode(op->dentry)); + struct dentry *old = op->dentry; + struct dentry *new = op->dentry_2; + + spin_lock(&old->d_lock); + old->d_flags |= DCACHE_NFSFS_RENAMED; + spin_unlock(&old->d_lock); + if (dvnode->silly_key != op->key) { + key_put(dvnode->silly_key); + dvnode->silly_key = key_get(op->key); + } + + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) { + afs_edit_dir_remove(dvnode, &old->d_name, + afs_edit_dir_for_silly_0); + afs_edit_dir_add(dvnode, &new->d_name, + &vnode->fid, afs_edit_dir_for_silly_1); + } + up_write(&dvnode->validate_lock); +} + +static const struct afs_operation_ops afs_silly_rename_operation = { + .issue_afs_rpc = afs_fs_rename, + .issue_yfs_rpc = yfs_fs_rename, + .success = afs_silly_rename_success, + .edit_dir = afs_silly_rename_edit_dir, +}; + /* * Actually perform the silly rename step. */ @@ -19,56 +60,22 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode struct dentry *old, struct dentry *new, struct key *key) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; - afs_dataversion_t dir_data_version; - int ret = -ERESTARTSYS; + struct afs_operation *op; _enter("%pd,%pd", old, new); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; + op = afs_alloc_operation(key, dvnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - trace_afs_silly_rename(vnode, false); - if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - dir_data_version = dvnode->status.data_version + 1; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_rename(&fc, old->d_name.name, - dvnode, new->d_name.name, - scb, scb); - } - - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &dir_data_version, scb); - ret = afs_end_vnode_operation(&fc); - } + afs_op_set_vnode(op, 0, dvnode); - if (ret == 0) { - spin_lock(&old->d_lock); - old->d_flags |= DCACHE_NFSFS_RENAMED; - spin_unlock(&old->d_lock); - if (dvnode->silly_key != key) { - key_put(dvnode->silly_key); - dvnode->silly_key = key_get(key); - } - - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == dir_data_version) { - afs_edit_dir_remove(dvnode, &old->d_name, - afs_edit_dir_for_silly_0); - afs_edit_dir_add(dvnode, &new->d_name, - &vnode->fid, afs_edit_dir_for_silly_1); - } - up_write(&dvnode->validate_lock); - } + op->dentry = old; + op->dentry_2 = new; + op->ops = &afs_silly_rename_operation; - kfree(scb); - _leave(" = %d", ret); - return ret; + trace_afs_silly_rename(vnode, false); + return afs_do_sync_operation(op); } /** @@ -139,65 +146,66 @@ out: return ret; } +static void afs_silly_unlink_success(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[1].vnode; + + _enter("op=%08x", op->debug_id); + afs_check_for_remote_deletion(op, op->file[0].vnode); + afs_vnode_commit_status(op, &op->file[0]); + afs_vnode_commit_status(op, &op->file[1]); + afs_update_dentry_version(op, &op->file[0], op->dentry); + + drop_nlink(&vnode->vfs_inode); + if (vnode->vfs_inode.i_nlink == 0) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } +} + +static void afs_silly_unlink_edit_dir(struct afs_operation *op) +{ + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode *dvnode = dvp->vnode; + + _enter("op=%08x", op->debug_id); + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) + afs_edit_dir_remove(dvnode, &op->dentry->d_name, + afs_edit_dir_for_unlink); + up_write(&dvnode->validate_lock); +} + +static const struct afs_operation_ops afs_silly_unlink_operation = { + .issue_afs_rpc = afs_fs_remove_file, + .issue_yfs_rpc = yfs_fs_remove_file, + .success = afs_silly_unlink_success, + .edit_dir = afs_silly_unlink_edit_dir, +}; + /* * Tell the server to remove a sillyrename file. */ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode, struct dentry *dentry, struct key *key) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; - int ret = -ERESTARTSYS; + struct afs_operation *op; _enter(""); - scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; + op = afs_alloc_operation(NULL, dvnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - trace_afs_silly_rename(vnode, true); - if (afs_begin_vnode_operation(&fc, dvnode, key, false)) { - afs_dataversion_t dir_data_version = dvnode->status.data_version + 1; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(dvnode); - - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && - !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { - yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, - &scb[0], &scb[1]); - if (fc.ac.error != -ECONNABORTED || - fc.ac.abort_code != RXGEN_OPCODE) - continue; - set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); - } - - afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]); - } + afs_op_set_vnode(op, 0, dvnode); + afs_op_set_vnode(op, 1, vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break, - &dir_data_version, &scb[0]); - ret = afs_end_vnode_operation(&fc); - if (ret == 0) { - drop_nlink(&vnode->vfs_inode); - if (vnode->vfs_inode.i_nlink == 0) { - set_bit(AFS_VNODE_DELETED, &vnode->flags); - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } - } - if (ret == 0) { - down_write(&dvnode->validate_lock); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && - dvnode->status.data_version == dir_data_version) - afs_edit_dir_remove(dvnode, &dentry->d_name, - afs_edit_dir_for_unlink); - up_write(&dvnode->validate_lock); - } - } + op->dentry = dentry; + op->ops = &afs_silly_unlink_operation; - kfree(scb); - _leave(" = %d", ret); - return ret; + trace_afs_silly_rename(vnode, true); + return afs_do_sync_operation(op); } /* diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 7503899c0a1b..b79879aacc02 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -10,6 +10,99 @@ #include <linux/dns_resolver.h> #include "internal.h" +static atomic_t afs_autocell_ino; + +/* + * iget5() comparator for inode created by autocell operations + * + * These pseudo inodes don't match anything. + */ +static int afs_iget5_pseudo_test(struct inode *inode, void *opaque) +{ + return 0; +} + +/* + * iget5() inode initialiser + */ +static int afs_iget5_pseudo_set(struct inode *inode, void *opaque) +{ + struct afs_super_info *as = AFS_FS_S(inode->i_sb); + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_fid *fid = opaque; + + vnode->volume = as->volume; + vnode->fid = *fid; + inode->i_ino = fid->vnode; + inode->i_generation = fid->unique; + return 0; +} + +/* + * Create an inode for a dynamic root directory or an autocell dynamic + * automount dir. + */ +struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) +{ + struct afs_super_info *as = AFS_FS_S(sb); + struct afs_vnode *vnode; + struct inode *inode; + struct afs_fid fid = {}; + + _enter(""); + + if (as->volume) + fid.vid = as->volume->vid; + if (root) { + fid.vnode = 1; + fid.unique = 1; + } else { + fid.vnode = atomic_inc_return(&afs_autocell_ino); + fid.unique = 0; + } + + inode = iget5_locked(sb, fid.vnode, + afs_iget5_pseudo_test, afs_iget5_pseudo_set, &fid); + if (!inode) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", + inode, inode->i_ino, fid.vid, fid.vnode, fid.unique); + + vnode = AFS_FS_I(inode); + + /* there shouldn't be an existing inode */ + BUG_ON(!(inode->i_state & I_NEW)); + + inode->i_size = 0; + inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; + if (root) { + inode->i_op = &afs_dynroot_inode_operations; + inode->i_fop = &simple_dir_operations; + } else { + inode->i_op = &afs_autocell_inode_operations; + } + set_nlink(inode, 2); + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode); + inode->i_blocks = 0; + inode->i_generation = 0; + + set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags); + if (!root) { + set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); + inode->i_flags |= S_AUTOMOUNT; + } + + inode->i_flags |= S_NOATIME; + unlock_new_inode(inode); + _leave(" = %p", inode); + return inode; +} + /* * Probe to see if a cell may exist. This prevents positive dentries from * being created unnecessarily. diff --git a/fs/afs/file.c b/fs/afs/file.c index 8415733f7bc1..506c47471b42 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -69,7 +69,7 @@ static const struct vm_operations_struct afs_vm_ops = { */ void afs_put_wb_key(struct afs_wb_key *wbk) { - if (refcount_dec_and_test(&wbk->usage)) { + if (wbk && refcount_dec_and_test(&wbk->usage)) { key_put(wbk->key); kfree(wbk); } @@ -220,14 +220,35 @@ static void afs_file_readpage_read_complete(struct page *page, } #endif +static void afs_fetch_data_success(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + + _enter("op=%08x", op->debug_id); + afs_check_for_remote_deletion(op, vnode); + afs_vnode_commit_status(op, &op->file[0]); + afs_stat_v(vnode, n_fetches); + atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes); +} + +static void afs_fetch_data_put(struct afs_operation *op) +{ + afs_put_read(op->fetch.req); +} + +static const struct afs_operation_ops afs_fetch_data_operation = { + .issue_afs_rpc = afs_fs_fetch_data, + .issue_yfs_rpc = yfs_fs_fetch_data, + .success = afs_fetch_data_success, + .put = afs_fetch_data_put, +}; + /* * Fetch file data from the volume. */ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *req) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; - int ret; + struct afs_operation *op; _enter("%s{%llx:%llu.%u},%x,,,", vnode->volume->name, @@ -236,34 +257,15 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *re vnode->fid.unique, key_serial(key)); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; - - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - afs_dataversion_t data_version = vnode->status.data_version; + op = afs_alloc_operation(key, vnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_fetch_data(&fc, scb, req); - } - - afs_check_for_remote_deletion(&fc, vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - ret = afs_end_vnode_operation(&fc); - } + afs_op_set_vnode(op, 0, vnode); - if (ret == 0) { - afs_stat_v(vnode, n_fetches); - atomic_long_add(req->actual_len, - &afs_v2net(vnode)->n_fetch_bytes); - } - - kfree(scb); - _leave(" = %d", ret); - return ret; + op->fetch.req = afs_get_read(req); + op->ops = &afs_fetch_data_operation; + return afs_do_sync_operation(op); } /* diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 0f2a94ba73cb..70e518f7bc19 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -70,7 +70,8 @@ static void afs_schedule_lock_extension(struct afs_vnode *vnode) */ void afs_lock_op_done(struct afs_call *call) { - struct afs_vnode *vnode = call->lvnode; + struct afs_operation *op = call->op; + struct afs_vnode *vnode = op->lock.lvnode; if (call->error == 0) { spin_lock(&vnode->lock); @@ -172,15 +173,28 @@ static void afs_kill_lockers_enoent(struct afs_vnode *vnode) vnode->lock_key = NULL; } +static void afs_lock_success(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + + _enter("op=%08x", op->debug_id); + afs_check_for_remote_deletion(op, vnode); + afs_vnode_commit_status(op, &op->file[0]); +} + +static const struct afs_operation_ops afs_set_lock_operation = { + .issue_afs_rpc = afs_fs_set_lock, + .issue_yfs_rpc = yfs_fs_set_lock, + .success = afs_lock_success, +}; + /* * Get a lock on a file */ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, afs_lock_type_t type) { - struct afs_status_cb *scb; - struct afs_fs_cursor fc; - int ret; + struct afs_operation *op; _enter("%s{%llx:%llu.%u},%x,%u", vnode->volume->name, @@ -189,35 +203,29 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, vnode->fid.unique, key_serial(key), type); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; + op = afs_alloc_operation(key, vnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_set_lock(&fc, type, scb); - } - - afs_check_for_remote_deletion(&fc, vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); - ret = afs_end_vnode_operation(&fc); - } + afs_op_set_vnode(op, 0, vnode); - kfree(scb); - _leave(" = %d", ret); - return ret; + op->lock.type = type; + op->ops = &afs_set_lock_operation; + return afs_do_sync_operation(op); } +static const struct afs_operation_ops afs_extend_lock_operation = { + .issue_afs_rpc = afs_fs_extend_lock, + .issue_yfs_rpc = yfs_fs_extend_lock, + .success = afs_lock_success, +}; + /* * Extend a lock on a file */ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) { - struct afs_status_cb *scb; - struct afs_fs_cursor fc; - int ret; + struct afs_operation *op; _enter("%s{%llx:%llu.%u},%x", vnode->volume->name, @@ -226,35 +234,29 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) vnode->fid.unique, key_serial(key)); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; - - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, false)) { - while (afs_select_current_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_extend_lock(&fc, scb); - } + op = afs_alloc_operation(key, vnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - afs_check_for_remote_deletion(&fc, vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); - ret = afs_end_vnode_operation(&fc); - } + afs_op_set_vnode(op, 0, vnode); - kfree(scb); - _leave(" = %d", ret); - return ret; + op->flags |= AFS_OPERATION_UNINTR; + op->ops = &afs_extend_lock_operation; + return afs_do_sync_operation(op); } +static const struct afs_operation_ops afs_release_lock_operation = { + .issue_afs_rpc = afs_fs_release_lock, + .issue_yfs_rpc = yfs_fs_release_lock, + .success = afs_lock_success, +}; + /* * Release a lock on a file */ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) { - struct afs_status_cb *scb; - struct afs_fs_cursor fc; - int ret; + struct afs_operation *op; _enter("%s{%llx:%llu.%u},%x", vnode->volume->name, @@ -263,25 +265,15 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) vnode->fid.unique, key_serial(key)); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; + op = afs_alloc_operation(key, vnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, false)) { - while (afs_select_current_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_release_lock(&fc, scb); - } + afs_op_set_vnode(op, 0, vnode); - afs_check_for_remote_deletion(&fc, vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); - ret = afs_end_vnode_operation(&fc); - } - - kfree(scb); - _leave(" = %d", ret); - return ret; + op->flags |= AFS_OPERATION_UNINTR; + op->ops = &afs_release_lock_operation; + return afs_do_sync_operation(op); } /* diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c new file mode 100644 index 000000000000..2d2dff5688a4 --- /dev/null +++ b/fs/afs/fs_operation.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Fileserver-directed operation handling. + * + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/fs.h> +#include "internal.h" + +static atomic_t afs_operation_debug_counter; + +/* + * Create an operation against a volume. + */ +struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *volume) +{ + struct afs_operation *op; + + _enter(""); + + op = kzalloc(sizeof(*op), GFP_KERNEL); + if (!op) + return ERR_PTR(-ENOMEM); + + if (!key) { + key = afs_request_key(volume->cell); + if (IS_ERR(key)) { + kfree(op); + return ERR_CAST(key); + } + } else { + key_get(key); + } + + op->key = key; + op->volume = afs_get_volume(volume, afs_volume_trace_get_new_op); + op->net = volume->cell->net; + op->cb_v_break = volume->cb_v_break; + op->debug_id = atomic_inc_return(&afs_operation_debug_counter); + op->error = -EDESTADDRREQ; + op->ac.error = SHRT_MAX; + + _leave(" = [op=%08x]", op->debug_id); + return op; +} + +/* + * Lock the vnode(s) being operated upon. + */ +static bool afs_get_io_locks(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + struct afs_vnode *vnode2 = op->file[1].vnode; + + _enter(""); + + if (op->flags & AFS_OPERATION_UNINTR) { + mutex_lock(&vnode->io_lock); + op->flags |= AFS_OPERATION_LOCK_0; + _leave(" = t [1]"); + return true; + } + + if (!vnode2 || !op->file[1].need_io_lock || vnode == vnode2) + vnode2 = NULL; + + if (vnode2 > vnode) + swap(vnode, vnode2); + + if (mutex_lock_interruptible(&vnode->io_lock) < 0) { + op->error = -EINTR; + op->flags |= AFS_OPERATION_STOP; + _leave(" = f [I 0]"); + return false; + } + op->flags |= AFS_OPERATION_LOCK_0; + + if (vnode2) { + if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) { + op->error = -EINTR; + op->flags |= AFS_OPERATION_STOP; + mutex_unlock(&vnode->io_lock); + op->flags &= ~AFS_OPERATION_LOCK_0; + _leave(" = f [I 1]"); + return false; + } + op->flags |= AFS_OPERATION_LOCK_1; + } + + _leave(" = t [2]"); + return true; +} + +static void afs_drop_io_locks(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + struct afs_vnode *vnode2 = op->file[1].vnode; + + _enter(""); + + if (op->flags & AFS_OPERATION_LOCK_1) + mutex_unlock(&vnode2->io_lock); + if (op->flags & AFS_OPERATION_LOCK_0) + mutex_unlock(&vnode->io_lock); +} + +static void afs_prepare_vnode(struct afs_operation *op, struct afs_vnode_param *vp, + unsigned int index) +{ + struct afs_vnode *vnode = vp->vnode; + + if (vnode) { + vp->fid = vnode->fid; + vp->dv_before = vnode->status.data_version; + vp->cb_break_before = afs_calc_vnode_cb_break(vnode); + if (vnode->lock_state != AFS_VNODE_LOCK_NONE) + op->flags |= AFS_OPERATION_CUR_ONLY; + } + + if (vp->fid.vnode) + _debug("PREP[%u] {%llx:%llu.%u}", + index, vp->fid.vid, vp->fid.vnode, vp->fid.unique); +} + +/* + * Begin an operation on the fileserver. + * + * Fileserver operations are serialised on the server by vnode, so we serialise + * them here also using the io_lock. + */ +bool afs_begin_vnode_operation(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + + ASSERT(vnode); + + _enter(""); + + if (op->file[0].need_io_lock) + if (!afs_get_io_locks(op)) + return false; + + afs_prepare_vnode(op, &op->file[0], 0); + afs_prepare_vnode(op, &op->file[1], 1); + op->cb_v_break = op->volume->cb_v_break; + _leave(" = true"); + return true; +} + +/* + * Tidy up a filesystem cursor and unlock the vnode. + */ +static void afs_end_vnode_operation(struct afs_operation *op) +{ + _enter(""); + + if (op->error == -EDESTADDRREQ || + op->error == -EADDRNOTAVAIL || + op->error == -ENETUNREACH || + op->error == -EHOSTUNREACH) + afs_dump_edestaddrreq(op); + + afs_drop_io_locks(op); + + if (op->error == -ECONNABORTED) + op->error = afs_abort_to_error(op->ac.abort_code); +} + +/* + * Wait for an in-progress operation to complete. + */ +void afs_wait_for_operation(struct afs_operation *op) +{ + _enter(""); + + while (afs_select_fileserver(op)) { + op->cb_s_break = op->server->cb_s_break; + if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) && + op->ops->issue_yfs_rpc) + op->ops->issue_yfs_rpc(op); + else + op->ops->issue_afs_rpc(op); + + op->error = afs_wait_for_call_to_complete(op->call, &op->ac); + } + + if (op->error == 0) { + _debug("success"); + op->ops->success(op); + } + + afs_end_vnode_operation(op); + + if (op->error == 0 && op->ops->edit_dir) { + _debug("edit_dir"); + op->ops->edit_dir(op); + } + _leave(""); +} + +/* + * Dispose of an operation. + */ +int afs_put_operation(struct afs_operation *op) +{ + int i, ret = op->error; + + _enter("op=%08x,%d", op->debug_id, ret); + + if (op->ops && op->ops->put) + op->ops->put(op); + if (op->file[0].put_vnode) + iput(&op->file[0].vnode->vfs_inode); + if (op->file[1].put_vnode) + iput(&op->file[1].vnode->vfs_inode); + + if (op->more_files) { + for (i = 0; i < op->nr_files - 2; i++) + if (op->more_files[i].put_vnode) + iput(&op->more_files[i].vnode->vfs_inode); + kfree(op->more_files); + } + + afs_end_cursor(&op->ac); + afs_put_serverlist(op->net, op->server_list); + afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op); + kfree(op); + return ret; +} + +int afs_do_sync_operation(struct afs_operation *op) +{ + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + return afs_put_operation(op); +} diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 37d1bba57b00..b34f74b0f319 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* AFS fileserver probing * - * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2018, 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ @@ -11,15 +11,86 @@ #include "internal.h" #include "protocol_yfs.h" -static bool afs_fs_probe_done(struct afs_server *server) +static unsigned int afs_fs_probe_fast_poll_interval = 30 * HZ; +static unsigned int afs_fs_probe_slow_poll_interval = 5 * 60 * HZ; + +/* + * Start the probe polling timer. We have to supply it with an inc on the + * outstanding server count. + */ +static void afs_schedule_fs_probe(struct afs_net *net, + struct afs_server *server, bool fast) +{ + unsigned long atj; + + if (!net->live) + return; + + atj = server->probed_at; + atj += fast ? afs_fs_probe_fast_poll_interval : afs_fs_probe_slow_poll_interval; + + afs_inc_servers_outstanding(net); + if (timer_reduce(&net->fs_probe_timer, atj)) + afs_dec_servers_outstanding(net); +} + +/* + * Handle the completion of a set of probes. + */ +static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server) +{ + bool responded = server->probe.responded; + + write_seqlock(&net->fs_lock); + if (responded) { + list_add_tail(&server->probe_link, &net->fs_probe_slow); + } else { + server->rtt = UINT_MAX; + clear_bit(AFS_SERVER_FL_RESPONDING, &server->flags); + list_add_tail(&server->probe_link, &net->fs_probe_fast); + } + write_sequnlock(&net->fs_lock); + + afs_schedule_fs_probe(net, server, !responded); +} + +/* + * Handle the completion of a probe. + */ +static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server) +{ + _enter(""); + + if (atomic_dec_and_test(&server->probe_outstanding)) + afs_finished_fs_probe(net, server); + + wake_up_all(&server->probe_wq); +} + +/* + * Handle inability to send a probe due to ENOMEM when trying to allocate a + * call struct. + */ +static void afs_fs_probe_not_done(struct afs_net *net, + struct afs_server *server, + struct afs_addr_cursor *ac) { - if (!atomic_dec_and_test(&server->probe_outstanding)) - return false; + struct afs_addr_list *alist = ac->alist; + unsigned int index = ac->index; + + _enter(""); + + trace_afs_io_error(0, -ENOMEM, afs_io_error_fs_probe_fail); + spin_lock(&server->probe_lock); - wake_up_var(&server->probe_outstanding); - clear_bit_unlock(AFS_SERVER_FL_PROBING, &server->flags); - wake_up_bit(&server->flags, AFS_SERVER_FL_PROBING); - return true; + server->probe.local_failure = true; + if (server->probe.error == 0) + server->probe.error = -ENOMEM; + + set_bit(index, &alist->failed); + + spin_unlock(&server->probe_lock); + return afs_done_one_fs_probe(net, server); } /* @@ -30,10 +101,8 @@ void afs_fileserver_probe_result(struct afs_call *call) { struct afs_addr_list *alist = call->alist; struct afs_server *server = call->server; - unsigned int server_index = call->server_index; unsigned int index = call->addr_ix; unsigned int rtt_us = 0; - bool have_result = false; int ret = call->error; _enter("%pU,%u", &server->uuid, index); @@ -52,8 +121,9 @@ void afs_fileserver_probe_result(struct afs_call *call) goto responded; case -ENOMEM: case -ENONET: + clear_bit(index, &alist->responded); server->probe.local_failure = true; - afs_io_error(call, afs_io_error_fs_probe_fail); + trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ case -ERFKILL: @@ -72,12 +142,11 @@ void afs_fileserver_probe_result(struct afs_call *call) server->probe.error == -ETIMEDOUT || server->probe.error == -ETIME)) server->probe.error = ret; - afs_io_error(call, afs_io_error_fs_probe_fail); + trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail); goto out; } responded: - set_bit(index, &alist->responded); clear_bit(index, &alist->failed); if (call->service_id == YFS_FS_SERVICE) { @@ -95,39 +164,34 @@ responded: rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); if (rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; + server->rtt = rtt_us; alist->preferred = index; - have_result = true; } smp_wmb(); /* Set rtt before responded. */ server->probe.responded = true; - set_bit(AFS_SERVER_FL_PROBED, &server->flags); + set_bit(index, &alist->responded); + set_bit(AFS_SERVER_FL_RESPONDING, &server->flags); out: spin_unlock(&server->probe_lock); - _debug("probe [%u][%u] %pISpc rtt=%u ret=%d", - server_index, index, &alist->addrs[index].transport, rtt_us, ret); + _debug("probe %pU [%u] %pISpc rtt=%u ret=%d", + &server->uuid, index, &alist->addrs[index].transport, + rtt_us, ret); - have_result |= afs_fs_probe_done(server); - if (have_result) - wake_up_all(&server->probe_wq); + return afs_done_one_fs_probe(call->net, server); } /* - * Probe all of a fileserver's addresses to find out the best route and to - * query its capabilities. + * Probe one or all of a fileserver's addresses to find out the best route and + * to query its capabilities. */ -static int afs_do_probe_fileserver(struct afs_net *net, - struct afs_server *server, - struct key *key, - unsigned int server_index, - struct afs_error *_e) +void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server, + struct key *key, bool all) { struct afs_addr_cursor ac = { .index = 0, }; - struct afs_call *call; - bool in_progress = false; _enter("%pU", &server->uuid); @@ -137,50 +201,25 @@ static int afs_do_probe_fileserver(struct afs_net *net, afs_get_addrlist(ac.alist); read_unlock(&server->fs_lock); - atomic_set(&server->probe_outstanding, ac.alist->nr_addrs); + server->probed_at = jiffies; + atomic_set(&server->probe_outstanding, all ? ac.alist->nr_addrs : 1); memset(&server->probe, 0, sizeof(server->probe)); server->probe.rtt = UINT_MAX; - for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - call = afs_fs_get_capabilities(net, server, &ac, key, server_index); - if (!IS_ERR(call)) { - afs_put_call(call); - in_progress = true; - } else { - afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code); - } - } - - if (!in_progress) - afs_fs_probe_done(server); - afs_put_addrlist(ac.alist); - return in_progress; -} + ac.index = ac.alist->preferred; + if (ac.index < 0 || ac.index >= ac.alist->nr_addrs) + all = true; -/* - * Send off probes to all unprobed servers. - */ -int afs_probe_fileservers(struct afs_net *net, struct key *key, - struct afs_server_list *list) -{ - struct afs_server *server; - struct afs_error e; - bool in_progress = false; - int i; - - e.error = 0; - e.responded = false; - for (i = 0; i < list->nr_servers; i++) { - server = list->servers[i].server; - if (test_bit(AFS_SERVER_FL_PROBED, &server->flags)) - continue; - - if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags) && - afs_do_probe_fileserver(net, server, key, i, &e)) - in_progress = true; + if (all) { + for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) + if (!afs_fs_get_capabilities(net, server, &ac, key)) + afs_fs_probe_not_done(net, server, &ac); + } else { + if (!afs_fs_get_capabilities(net, server, &ac, key)) + afs_fs_probe_not_done(net, server, &ac); } - return in_progress ? 0 : e.error; + afs_put_addrlist(ac.alist); } /* @@ -190,7 +229,7 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried) { struct wait_queue_entry *waits; struct afs_server *server; - unsigned int rtt = UINT_MAX; + unsigned int rtt = UINT_MAX, rtt_s; bool have_responders = false; int pref = -1, i; @@ -200,7 +239,7 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried) for (i = 0; i < slist->nr_servers; i++) { if (test_bit(i, &untried)) { server = slist->servers[i].server; - if (!test_bit(AFS_SERVER_FL_PROBING, &server->flags)) + if (!atomic_read(&server->probe_outstanding)) __clear_bit(i, &untried); if (server->probe.responded) have_responders = true; @@ -230,7 +269,7 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried) server = slist->servers[i].server; if (server->probe.responded) goto stop; - if (test_bit(AFS_SERVER_FL_PROBING, &server->flags)) + if (atomic_read(&server->probe_outstanding)) still_probing = true; } } @@ -246,10 +285,11 @@ stop: for (i = 0; i < slist->nr_servers; i++) { if (test_bit(i, &untried)) { server = slist->servers[i].server; - if (server->probe.responded && - server->probe.rtt < rtt) { + rtt_s = READ_ONCE(server->rtt); + if (test_bit(AFS_SERVER_FL_RESPONDING, &server->flags) && + rtt_s < rtt) { pref = i; - rtt = server->probe.rtt; + rtt = rtt_s; } remove_wait_queue(&server->probe_wq, &waits[i]); @@ -265,3 +305,156 @@ stop: slist->preferred = pref; return 0; } + +/* + * Probe timer. We have an increment on fs_outstanding that we need to pass + * along to the work item. + */ +void afs_fs_probe_timer(struct timer_list *timer) +{ + struct afs_net *net = container_of(timer, struct afs_net, fs_probe_timer); + + if (!queue_work(afs_wq, &net->fs_prober)) + afs_dec_servers_outstanding(net); +} + +/* + * Dispatch a probe to a server. + */ +static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server, bool all) + __releases(&net->fs_lock) +{ + struct key *key = NULL; + + /* We remove it from the queues here - it will be added back to + * one of the queues on the completion of the probe. + */ + list_del_init(&server->probe_link); + + afs_get_server(server, afs_server_trace_get_probe); + write_sequnlock(&net->fs_lock); + + afs_fs_probe_fileserver(net, server, key, all); + afs_put_server(net, server, afs_server_trace_put_probe); +} + +/* + * Probe a server immediately without waiting for its due time to come + * round. This is used when all of the addresses have been tried. + */ +void afs_probe_fileserver(struct afs_net *net, struct afs_server *server) +{ + write_seqlock(&net->fs_lock); + if (!list_empty(&server->probe_link)) + return afs_dispatch_fs_probe(net, server, true); + write_sequnlock(&net->fs_lock); +} + +/* + * Probe dispatcher to regularly dispatch probes to keep NAT alive. + */ +void afs_fs_probe_dispatcher(struct work_struct *work) +{ + struct afs_net *net = container_of(work, struct afs_net, fs_prober); + struct afs_server *fast, *slow, *server; + unsigned long nowj, timer_at, poll_at; + bool first_pass = true, set_timer = false; + + if (!net->live) + return; + + _enter(""); + + if (list_empty(&net->fs_probe_fast) && list_empty(&net->fs_probe_slow)) { + _leave(" [none]"); + return; + } + +again: + write_seqlock(&net->fs_lock); + + fast = slow = server = NULL; + nowj = jiffies; + timer_at = nowj + MAX_JIFFY_OFFSET; + + if (!list_empty(&net->fs_probe_fast)) { + fast = list_first_entry(&net->fs_probe_fast, struct afs_server, probe_link); + poll_at = fast->probed_at + afs_fs_probe_fast_poll_interval; + if (time_before(nowj, poll_at)) { + timer_at = poll_at; + set_timer = true; + fast = NULL; + } + } + + if (!list_empty(&net->fs_probe_slow)) { + slow = list_first_entry(&net->fs_probe_slow, struct afs_server, probe_link); + poll_at = slow->probed_at + afs_fs_probe_slow_poll_interval; + if (time_before(nowj, poll_at)) { + if (time_before(poll_at, timer_at)) + timer_at = poll_at; + set_timer = true; + slow = NULL; + } + } + + server = fast ?: slow; + if (server) + _debug("probe %pU", &server->uuid); + + if (server && (first_pass || !need_resched())) { + afs_dispatch_fs_probe(net, server, server == fast); + first_pass = false; + goto again; + } + + write_sequnlock(&net->fs_lock); + + if (server) { + if (!queue_work(afs_wq, &net->fs_prober)) + afs_dec_servers_outstanding(net); + _leave(" [requeue]"); + } else if (set_timer) { + if (timer_reduce(&net->fs_probe_timer, timer_at)) + afs_dec_servers_outstanding(net); + _leave(" [timer]"); + } else { + afs_dec_servers_outstanding(net); + _leave(" [quiesce]"); + } +} + +/* + * Wait for a probe on a particular fileserver to complete for 2s. + */ +int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr) +{ + struct wait_queue_entry wait; + unsigned long timo = 2 * HZ; + + if (atomic_read(&server->probe_outstanding) == 0) + goto dont_wait; + + init_wait_entry(&wait, 0); + for (;;) { + prepare_to_wait_event(&server->probe_wq, &wait, + is_intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); + if (timo == 0 || + server->probe.responded || + atomic_read(&server->probe_outstanding) == 0 || + (is_intr && signal_pending(current))) + break; + timo = schedule_timeout(timo); + } + + finish_wait(&server->probe_wq, &wait); + +dont_wait: + if (server->probe.responded) + return 0; + if (is_intr && signal_pending(current)) + return -ERESTARTSYS; + if (timo == 0) + return -ETIME; + return -EDESTADDRREQ; +} diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index d2b3798c1932..acb4d0ca2649 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -13,12 +13,6 @@ #include "internal.h" #include "afs_fs.h" #include "xdr_fs.h" -#include "protocol_yfs.h" - -static inline void afs_use_fs_server(struct afs_call *call, struct afs_cb_interest *cbi) -{ - call->cbi = afs_get_cb_interest(cbi); -} /* * decode an AFSFid block @@ -56,16 +50,15 @@ static void xdr_dump_bad(const __be32 *bp) /* * decode an AFSFetchStatus block */ -static int xdr_decode_AFSFetchStatus(const __be32 **_bp, - struct afs_call *call, - struct afs_status_cb *scb) +static void xdr_decode_AFSFetchStatus(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp; struct afs_file_status *status = &scb->status; bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus); u64 data_version, size; u32 type, abort_code; - int ret; abort_code = ntohl(xdr->abort_code); @@ -79,7 +72,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, */ status->abort_code = abort_code; scb->have_error = true; - goto good; + goto advance; } pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version)); @@ -89,7 +82,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, if (abort_code != 0 && inline_error) { status->abort_code = abort_code; scb->have_error = true; - goto good; + goto advance; } type = ntohl(xdr->type); @@ -125,15 +118,13 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, data_version |= (u64)ntohl(xdr->data_version_hi) << 32; status->data_version = data_version; scb->have_status = true; -good: - ret = 0; advance: *_bp = (const void *)*_bp + sizeof(*xdr); - return ret; + return; bad: xdr_dump_bad(*_bp); - ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + afs_protocol_error(call, afs_eproto_bad_status); goto advance; } @@ -243,8 +234,10 @@ static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp, /* * deliver reply data to an FS.FetchStatus */ -static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) +static int afs_deliver_fs_fetch_status(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[op->fetch_status.which]; const __be32 *bp; int ret; @@ -254,11 +247,9 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSCallBack(&bp, call, call->out_scb); - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSCallBack(&bp, call, &vp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -267,54 +258,39 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) /* * FS.FetchStatus operation type */ -static const struct afs_call_type afs_RXFSFetchStatus_vnode = { - .name = "FS.FetchStatus(vnode)", +static const struct afs_call_type afs_RXFSFetchStatus = { + .name = "FS.FetchStatus", .op = afs_FS_FetchStatus, - .deliver = afs_deliver_fs_fetch_status_vnode, + .deliver = afs_deliver_fs_fetch_status, .destructor = afs_flat_call_destructor, }; /* * fetch the status information for a file */ -int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb, - struct afs_volsync *volsync) +void afs_fs_fetch_status(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[op->fetch_status.which]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_file_status(fc, scb, volsync); - _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &afs_RXFSFetchStatus_vnode, + call = afs_alloc_flat_call(op->net, &afs_RXFSFetchStatus, 16, (21 + 3 + 6) * 4); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = volsync; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHSTATUS); - bp[1] = htonl(vnode->fid.vid); - bp[2] = htonl(vnode->fid.vnode); - bp[3] = htonl(vnode->fid.unique); + bp[1] = htonl(vp->fid.vid); + bp[2] = htonl(vp->fid.vnode); + bp[3] = htonl(vp->fid.unique); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -322,7 +298,9 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb */ static int afs_deliver_fs_fetch_data(struct afs_call *call) { - struct afs_read *req = call->read_request; + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[0]; + struct afs_read *req = op->fetch.req; const __be32 *bp; unsigned int size; int ret; @@ -419,14 +397,12 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSCallBack(&bp, call, call->out_scb); - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSCallBack(&bp, call, &vp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); - req->data_version = call->out_scb->status.data_version; - req->file_size = call->out_scb->status.size; + req->data_version = vp->scb.status.data_version; + req->file_size = vp->scb.status.size; call->unmarshall++; @@ -449,14 +425,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) return 0; } -static void afs_fetch_data_destructor(struct afs_call *call) -{ - struct afs_read *req = call->read_request; - - afs_put_read(req); - afs_flat_call_destructor(call); -} - /* * FS.FetchData operation type */ @@ -464,102 +432,79 @@ static const struct afs_call_type afs_RXFSFetchData = { .name = "FS.FetchData", .op = afs_FS_FetchData, .deliver = afs_deliver_fs_fetch_data, - .destructor = afs_fetch_data_destructor, + .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSFetchData64 = { .name = "FS.FetchData64", .op = afs_FS_FetchData64, .deliver = afs_deliver_fs_fetch_data, - .destructor = afs_fetch_data_destructor, + .destructor = afs_flat_call_destructor, }; /* * fetch data from a very large file */ -static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, - struct afs_status_cb *scb, - struct afs_read *req) +static void afs_fs_fetch_data64(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; + struct afs_read *req = op->fetch.req; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(net, &afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = NULL; - call->read_request = afs_get_read(req); + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA64); - bp[1] = htonl(vnode->fid.vid); - bp[2] = htonl(vnode->fid.vnode); - bp[3] = htonl(vnode->fid.unique); + bp[1] = htonl(vp->fid.vid); + bp[2] = htonl(vp->fid.vnode); + bp[3] = htonl(vp->fid.unique); bp[4] = htonl(upper_32_bits(req->pos)); bp[5] = htonl(lower_32_bits(req->pos)); bp[6] = 0; bp[7] = htonl(lower_32_bits(req->len)); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * fetch data from a file */ -int afs_fs_fetch_data(struct afs_fs_cursor *fc, - struct afs_status_cb *scb, - struct afs_read *req) +void afs_fs_fetch_data(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_read *req = op->fetch.req; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_data(fc, scb, req); - if (upper_32_bits(req->pos) || upper_32_bits(req->len) || upper_32_bits(req->pos + req->len)) - return afs_fs_fetch_data64(fc, scb, req); + return afs_fs_fetch_data64(op); _enter(""); - call = afs_alloc_flat_call(net, &afs_RXFSFetchData, 24, (21 + 3 + 6) * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSFetchData, 24, (21 + 3 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = NULL; - call->read_request = afs_get_read(req); + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA); - bp[1] = htonl(vnode->fid.vid); - bp[2] = htonl(vnode->fid.vnode); - bp[3] = htonl(vnode->fid.unique); + bp[1] = htonl(vp->fid.vid); + bp[2] = htonl(vp->fid.vnode); + bp[3] = htonl(vp->fid.unique); bp[4] = htonl(lower_32_bits(req->pos)); bp[5] = htonl(lower_32_bits(req->len)); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -567,6 +512,9 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_create_vnode(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; const __be32 *bp; int ret; @@ -576,15 +524,11 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_AFSFid(&bp, call->out_fid); - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_AFSCallBack(&bp, call, call->out_scb); - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFid(&bp, &op->file[1].fid); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_AFSCallBack(&bp, call, &vp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -600,6 +544,52 @@ static const struct afs_call_type afs_RXFSCreateFile = { .destructor = afs_flat_call_destructor, }; +/* + * Create a file. + */ +void afs_fs_create_file(struct afs_operation *op) +{ + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_call *call; + size_t namesz, reqsz, padsz; + __be32 *bp; + + _enter(""); + + namesz = name->len; + padsz = (4 - (namesz & 3)) & 3; + reqsz = (5 * 4) + namesz + padsz + (6 * 4); + + call = afs_alloc_flat_call(op->net, &afs_RXFSCreateFile, + reqsz, (3 + 21 + 21 + 3 + 6) * 4); + if (!call) + return afs_op_nomem(op); + + /* marshall the parameters */ + bp = call->request; + *bp++ = htonl(FSCREATEFILE); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); + *bp++ = htonl(namesz); + memcpy(bp, name->name, namesz); + bp = (void *) bp + namesz; + if (padsz > 0) { + memset(bp, 0, padsz); + bp = (void *) bp + padsz; + } + *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); + *bp++ = htonl(op->mtime.tv_sec); /* mtime */ + *bp++ = 0; /* owner */ + *bp++ = 0; /* group */ + *bp++ = htonl(op->create.mode & S_IALLUGO); /* unix mode */ + *bp++ = 0; /* segment size */ + + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); +} + static const struct afs_call_type afs_RXFSMakeDir = { .name = "FS.MakeDir", .op = afs_FS_MakeDir, @@ -608,80 +598,58 @@ static const struct afs_call_type afs_RXFSMakeDir = { }; /* - * create a file or make a directory + * Create a new directory */ -int afs_fs_create(struct afs_fs_cursor *fc, - const char *name, - umode_t mode, - struct afs_status_cb *dvnode_scb, - struct afs_fid *newfid, - struct afs_status_cb *new_scb) +void afs_fs_make_dir(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)){ - if (S_ISDIR(mode)) - return yfs_fs_make_dir(fc, name, mode, dvnode_scb, - newfid, new_scb); - else - return yfs_fs_create_file(fc, name, mode, dvnode_scb, - newfid, new_scb); - } - _enter(""); - namesz = strlen(name); + namesz = name->len; padsz = (4 - (namesz & 3)) & 3; reqsz = (5 * 4) + namesz + padsz + (6 * 4); - call = afs_alloc_flat_call( - net, S_ISDIR(mode) ? &afs_RXFSMakeDir : &afs_RXFSCreateFile, - reqsz, (3 + 21 + 21 + 3 + 6) * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSMakeDir, + reqsz, (3 + 21 + 21 + 3 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_fid = newfid; - call->out_scb = new_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; - *bp++ = htonl(S_ISDIR(mode) ? FSMAKEDIR : FSCREATEFILE); - *bp++ = htonl(dvnode->fid.vid); - *bp++ = htonl(dvnode->fid.vnode); - *bp++ = htonl(dvnode->fid.unique); + *bp++ = htonl(FSMAKEDIR); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); *bp++ = htonl(namesz); - memcpy(bp, name, namesz); + memcpy(bp, name->name, namesz); bp = (void *) bp + namesz; if (padsz > 0) { memset(bp, 0, padsz); bp = (void *) bp + padsz; } *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); - *bp++ = htonl(dvnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(op->mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ - *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ + *bp++ = htonl(op->create.mode & S_IALLUGO); /* unix mode */ *bp++ = 0; /* segment size */ - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* - * Deliver reply data to any operation that returns directory status and volume - * sync. + * Deliver reply data to any operation that returns status and volume sync. */ -static int afs_deliver_fs_dir_status_and_vol(struct afs_call *call) +static int afs_deliver_fs_file_status_and_vol(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[0]; const __be32 *bp; int ret; @@ -691,81 +659,108 @@ static int afs_deliver_fs_dir_status_and_vol(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; } /* - * FS.RemoveDir/FS.RemoveFile operation type + * FS.RemoveFile operation type */ static const struct afs_call_type afs_RXFSRemoveFile = { .name = "FS.RemoveFile", .op = afs_FS_RemoveFile, - .deliver = afs_deliver_fs_dir_status_and_vol, + .deliver = afs_deliver_fs_file_status_and_vol, .destructor = afs_flat_call_destructor, }; +/* + * Remove a file. + */ +void afs_fs_remove_file(struct afs_operation *op) +{ + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_call *call; + size_t namesz, reqsz, padsz; + __be32 *bp; + + _enter(""); + + namesz = name->len; + padsz = (4 - (namesz & 3)) & 3; + reqsz = (5 * 4) + namesz + padsz; + + call = afs_alloc_flat_call(op->net, &afs_RXFSRemoveFile, + reqsz, (21 + 6) * 4); + if (!call) + return afs_op_nomem(op); + + /* marshall the parameters */ + bp = call->request; + *bp++ = htonl(FSREMOVEFILE); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); + *bp++ = htonl(namesz); + memcpy(bp, name->name, namesz); + bp = (void *) bp + namesz; + if (padsz > 0) { + memset(bp, 0, padsz); + bp = (void *) bp + padsz; + } + + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); +} + static const struct afs_call_type afs_RXFSRemoveDir = { .name = "FS.RemoveDir", .op = afs_FS_RemoveDir, - .deliver = afs_deliver_fs_dir_status_and_vol, + .deliver = afs_deliver_fs_file_status_and_vol, .destructor = afs_flat_call_destructor, }; /* - * remove a file or directory + * Remove a directory. */ -int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, bool isdir, struct afs_status_cb *dvnode_scb) +void afs_fs_remove_dir(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_remove(fc, vnode, name, isdir, dvnode_scb); - _enter(""); - namesz = strlen(name); + namesz = name->len; padsz = (4 - (namesz & 3)) & 3; reqsz = (5 * 4) + namesz + padsz; - call = afs_alloc_flat_call( - net, isdir ? &afs_RXFSRemoveDir : &afs_RXFSRemoveFile, - reqsz, (21 + 6) * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSRemoveDir, + reqsz, (21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; - *bp++ = htonl(isdir ? FSREMOVEDIR : FSREMOVEFILE); - *bp++ = htonl(dvnode->fid.vid); - *bp++ = htonl(dvnode->fid.vnode); - *bp++ = htonl(dvnode->fid.unique); + *bp++ = htonl(FSREMOVEDIR); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); *bp++ = htonl(namesz); - memcpy(bp, name, namesz); + memcpy(bp, name->name, namesz); bp = (void *) bp + namesz; if (padsz > 0) { memset(bp, 0, padsz); bp = (void *) bp + padsz; } - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -773,6 +768,9 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int afs_deliver_fs_link(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; const __be32 *bp; int ret; @@ -784,13 +782,9 @@ static int afs_deliver_fs_link(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -809,56 +803,44 @@ static const struct afs_call_type afs_RXFSLink = { /* * make a hard link */ -int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, - struct afs_status_cb *dvnode_scb, - struct afs_status_cb *vnode_scb) +void afs_fs_link(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); size_t namesz, reqsz, padsz; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_link(fc, vnode, name, dvnode_scb, vnode_scb); - _enter(""); - namesz = strlen(name); + namesz = name->len; padsz = (4 - (namesz & 3)) & 3; reqsz = (5 * 4) + namesz + padsz + (3 * 4); - call = afs_alloc_flat_call(net, &afs_RXFSLink, reqsz, (21 + 21 + 6) * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSLink, reqsz, (21 + 21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_scb = vnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSLINK); - *bp++ = htonl(dvnode->fid.vid); - *bp++ = htonl(dvnode->fid.vnode); - *bp++ = htonl(dvnode->fid.unique); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); *bp++ = htonl(namesz); - memcpy(bp, name, namesz); + memcpy(bp, name->name, namesz); bp = (void *) bp + namesz; if (padsz > 0) { memset(bp, 0, padsz); bp = (void *) bp + padsz; } - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &vnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); + + trace_afs_make_fs_call1(call, &vp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -866,6 +848,9 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int afs_deliver_fs_symlink(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; const __be32 *bp; int ret; @@ -877,14 +862,10 @@ static int afs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_AFSFid(&bp, call->out_fid); - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFid(&bp, &vp->fid); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -903,75 +884,58 @@ static const struct afs_call_type afs_RXFSSymlink = { /* * create a symbolic link */ -int afs_fs_symlink(struct afs_fs_cursor *fc, - const char *name, - const char *contents, - struct afs_status_cb *dvnode_scb, - struct afs_fid *newfid, - struct afs_status_cb *new_scb) +void afs_fs_symlink(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz, c_namesz, c_padsz; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_symlink(fc, name, contents, dvnode_scb, - newfid, new_scb); - _enter(""); - namesz = strlen(name); + namesz = name->len; padsz = (4 - (namesz & 3)) & 3; - c_namesz = strlen(contents); + c_namesz = strlen(op->create.symlink); c_padsz = (4 - (c_namesz & 3)) & 3; reqsz = (6 * 4) + namesz + padsz + c_namesz + c_padsz + (6 * 4); - call = afs_alloc_flat_call(net, &afs_RXFSSymlink, reqsz, + call = afs_alloc_flat_call(op->net, &afs_RXFSSymlink, reqsz, (3 + 21 + 21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_fid = newfid; - call->out_scb = new_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSYMLINK); - *bp++ = htonl(dvnode->fid.vid); - *bp++ = htonl(dvnode->fid.vnode); - *bp++ = htonl(dvnode->fid.unique); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); *bp++ = htonl(namesz); - memcpy(bp, name, namesz); + memcpy(bp, name->name, namesz); bp = (void *) bp + namesz; if (padsz > 0) { memset(bp, 0, padsz); bp = (void *) bp + padsz; } *bp++ = htonl(c_namesz); - memcpy(bp, contents, c_namesz); + memcpy(bp, op->create.symlink, c_namesz); bp = (void *) bp + c_namesz; if (c_padsz > 0) { memset(bp, 0, c_padsz); bp = (void *) bp + c_padsz; } *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); - *bp++ = htonl(dvnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(op->mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(S_IRWXUGO); /* unix mode */ *bp++ = 0; /* segment size */ - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -979,6 +943,9 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_rename(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *orig_dvp = &op->file[0]; + struct afs_vnode_param *new_dvp = &op->file[1]; const __be32 *bp; int ret; @@ -986,17 +953,13 @@ static int afs_deliver_fs_rename(struct afs_call *call) if (ret < 0) return ret; + bp = call->buffer; /* If the two dirs are the same, we have two copies of the same status * report, so we just decode it twice. */ - bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &orig_dvp->scb); + xdr_decode_AFSFetchStatus(&bp, call, &new_dvp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -1015,31 +978,22 @@ static const struct afs_call_type afs_RXFSRename = { /* * Rename/move a file or directory. */ -int afs_fs_rename(struct afs_fs_cursor *fc, - const char *orig_name, - struct afs_vnode *new_dvnode, - const char *new_name, - struct afs_status_cb *orig_dvnode_scb, - struct afs_status_cb *new_dvnode_scb) +void afs_fs_rename(struct afs_operation *op) { - struct afs_vnode *orig_dvnode = fc->vnode; + struct afs_vnode_param *orig_dvp = &op->file[0]; + struct afs_vnode_param *new_dvp = &op->file[1]; + const struct qstr *orig_name = &op->dentry->d_name; + const struct qstr *new_name = &op->dentry_2->d_name; struct afs_call *call; - struct afs_net *net = afs_v2net(orig_dvnode); size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_rename(fc, orig_name, - new_dvnode, new_name, - orig_dvnode_scb, - new_dvnode_scb); - _enter(""); - o_namesz = strlen(orig_name); + o_namesz = orig_name->len; o_padsz = (4 - (o_namesz & 3)) & 3; - n_namesz = strlen(new_name); + n_namesz = new_name->len; n_padsz = (4 - (n_namesz & 3)) & 3; reqsz = (4 * 4) + @@ -1047,51 +1001,46 @@ int afs_fs_rename(struct afs_fs_cursor *fc, (3 * 4) + 4 + n_namesz + n_padsz; - call = afs_alloc_flat_call(net, &afs_RXFSRename, reqsz, (21 + 21 + 6) * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSRename, reqsz, (21 + 21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = orig_dvnode_scb; - call->out_scb = new_dvnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSRENAME); - *bp++ = htonl(orig_dvnode->fid.vid); - *bp++ = htonl(orig_dvnode->fid.vnode); - *bp++ = htonl(orig_dvnode->fid.unique); + *bp++ = htonl(orig_dvp->fid.vid); + *bp++ = htonl(orig_dvp->fid.vnode); + *bp++ = htonl(orig_dvp->fid.unique); *bp++ = htonl(o_namesz); - memcpy(bp, orig_name, o_namesz); + memcpy(bp, orig_name->name, o_namesz); bp = (void *) bp + o_namesz; if (o_padsz > 0) { memset(bp, 0, o_padsz); bp = (void *) bp + o_padsz; } - *bp++ = htonl(new_dvnode->fid.vid); - *bp++ = htonl(new_dvnode->fid.vnode); - *bp++ = htonl(new_dvnode->fid.unique); + *bp++ = htonl(new_dvp->fid.vid); + *bp++ = htonl(new_dvp->fid.vnode); + *bp++ = htonl(new_dvp->fid.unique); *bp++ = htonl(n_namesz); - memcpy(bp, new_name, n_namesz); + memcpy(bp, new_name->name, n_namesz); bp = (void *) bp + n_namesz; if (n_padsz > 0) { memset(bp, 0, n_padsz); bp = (void *) bp + n_padsz; } - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call2(call, &orig_dvnode->fid, orig_name, new_name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call2(call, &orig_dvp->fid, orig_name, new_name); + afs_make_op_call(op, call, GFP_NOFS); } /* - * deliver reply data to an FS.StoreData + * Deliver reply data to FS.StoreData or FS.StoreStatus */ static int afs_deliver_fs_store_data(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[0]; const __be32 *bp; int ret; @@ -1103,10 +1052,8 @@ static int afs_deliver_fs_store_data(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -1132,90 +1079,69 @@ static const struct afs_call_type afs_RXFSStoreData64 = { /* * store a set of pages to a very large file */ -static int afs_fs_store_data64(struct afs_fs_cursor *fc, - struct address_space *mapping, - pgoff_t first, pgoff_t last, - unsigned offset, unsigned to, - loff_t size, loff_t pos, loff_t i_size, - struct afs_status_cb *scb) +static void afs_fs_store_data64(struct afs_operation *op, + loff_t pos, loff_t size, loff_t i_size) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &afs_RXFSStoreData64, + call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData64, (4 + 6 + 3 * 2) * 4, (21 + 6) * 4); if (!call) - return -ENOMEM; + return afs_op_nomem(op); - call->key = fc->key; - call->mapping = mapping; - call->first = first; - call->last = last; - call->first_offset = offset; - call->last_to = to; call->send_pages = true; - call->out_scb = scb; /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSTOREDATA64); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); *bp++ = htonl(AFS_SET_MTIME); /* mask */ - *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(op->mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = 0; /* unix mode */ *bp++ = 0; /* segment size */ - *bp++ = htonl(pos >> 32); - *bp++ = htonl((u32) pos); - *bp++ = htonl(size >> 32); - *bp++ = htonl((u32) size); - *bp++ = htonl(i_size >> 32); - *bp++ = htonl((u32) i_size); - - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + *bp++ = htonl(upper_32_bits(pos)); + *bp++ = htonl(lower_32_bits(pos)); + *bp++ = htonl(upper_32_bits(size)); + *bp++ = htonl(lower_32_bits(size)); + *bp++ = htonl(upper_32_bits(i_size)); + *bp++ = htonl(lower_32_bits(i_size)); + + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * store a set of pages */ -int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, - pgoff_t first, pgoff_t last, - unsigned offset, unsigned to, - struct afs_status_cb *scb) +void afs_fs_store_data(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); loff_t size, pos, i_size; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_store_data(fc, mapping, first, last, offset, to, scb); - _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - size = (loff_t)to - (loff_t)offset; - if (first != last) - size += (loff_t)(last - first) << PAGE_SHIFT; - pos = (loff_t)first << PAGE_SHIFT; - pos += offset; + size = (loff_t)op->store.last_to - (loff_t)op->store.first_offset; + if (op->store.first != op->store.last) + size += (loff_t)(op->store.last - op->store.first) << PAGE_SHIFT; + pos = (loff_t)op->store.first << PAGE_SHIFT; + pos += op->store.first_offset; - i_size = i_size_read(&vnode->vfs_inode); + i_size = i_size_read(&vp->vnode->vfs_inode); if (pos + size > i_size) i_size = size + pos; @@ -1223,73 +1149,38 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, (unsigned long long) size, (unsigned long long) pos, (unsigned long long) i_size); - if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32) - return afs_fs_store_data64(fc, mapping, first, last, offset, to, - size, pos, i_size, scb); + if (upper_32_bits(pos) || upper_32_bits(i_size) || upper_32_bits(size) || + upper_32_bits(pos + size)) + return afs_fs_store_data64(op, pos, size, i_size); - call = afs_alloc_flat_call(net, &afs_RXFSStoreData, + call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData, (4 + 6 + 3) * 4, (21 + 6) * 4); if (!call) - return -ENOMEM; + return afs_op_nomem(op); - call->key = fc->key; - call->mapping = mapping; - call->first = first; - call->last = last; - call->first_offset = offset; - call->last_to = to; call->send_pages = true; - call->out_scb = scb; /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSTOREDATA); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); *bp++ = htonl(AFS_SET_MTIME); /* mask */ - *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(op->mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = 0; /* unix mode */ *bp++ = 0; /* segment size */ - *bp++ = htonl(pos); - *bp++ = htonl(size); - *bp++ = htonl(i_size); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); -} - -/* - * deliver reply data to an FS.StoreStatus - */ -static int afs_deliver_fs_store_status(struct afs_call *call) -{ - const __be32 *bp; - int ret; - - _enter(""); + *bp++ = htonl(lower_32_bits(pos)); + *bp++ = htonl(lower_32_bits(size)); + *bp++ = htonl(lower_32_bits(i_size)); - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); - - _leave(" = 0 [done]"); - return 0; + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1298,21 +1189,21 @@ static int afs_deliver_fs_store_status(struct afs_call *call) static const struct afs_call_type afs_RXFSStoreStatus = { .name = "FS.StoreStatus", .op = afs_FS_StoreStatus, - .deliver = afs_deliver_fs_store_status, + .deliver = afs_deliver_fs_store_data, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSStoreData_as_Status = { .name = "FS.StoreData", .op = afs_FS_StoreData, - .deliver = afs_deliver_fs_store_status, + .deliver = afs_deliver_fs_store_data, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSStoreData64_as_Status = { .name = "FS.StoreData64", .op = afs_FS_StoreData64, - .deliver = afs_deliver_fs_store_status, + .deliver = afs_deliver_fs_store_data, .destructor = afs_flat_call_destructor, }; @@ -1320,85 +1211,74 @@ static const struct afs_call_type afs_RXFSStoreData64_as_Status = { * set the attributes on a very large file, using FS.StoreData rather than * FS.StoreStatus so as to alter the file size also */ -static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr, - struct afs_status_cb *scb) +static void afs_fs_setattr_size64(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct iattr *attr = op->setattr.attr; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); ASSERT(attr->ia_valid & ATTR_SIZE); - call = afs_alloc_flat_call(net, &afs_RXFSStoreData64_as_Status, + call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData64_as_Status, (4 + 6 + 3 * 2) * 4, (21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSTOREDATA64); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = htonl(attr->ia_size >> 32); /* position of start of write */ - *bp++ = htonl((u32) attr->ia_size); - *bp++ = 0; /* size of write */ + *bp++ = htonl(upper_32_bits(attr->ia_size)); /* position of start of write */ + *bp++ = htonl(lower_32_bits(attr->ia_size)); + *bp++ = 0; /* size of write */ *bp++ = 0; - *bp++ = htonl(attr->ia_size >> 32); /* new file length */ - *bp++ = htonl((u32) attr->ia_size); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + *bp++ = htonl(upper_32_bits(attr->ia_size)); /* new file length */ + *bp++ = htonl(lower_32_bits(attr->ia_size)); + + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * set the attributes on a file, using FS.StoreData rather than FS.StoreStatus * so as to alter the file size also */ -static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, - struct afs_status_cb *scb) +static void afs_fs_setattr_size(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct iattr *attr = op->setattr.attr; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); ASSERT(attr->ia_valid & ATTR_SIZE); - if (attr->ia_size >> 32) - return afs_fs_setattr_size64(fc, attr, scb); + if (upper_32_bits(attr->ia_size)) + return afs_fs_setattr_size64(op); - call = afs_alloc_flat_call(net, &afs_RXFSStoreData_as_Status, + call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData_as_Status, (4 + 6 + 3) * 4, (21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSTOREDATA); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); xdr_encode_AFS_StoreStatus(&bp, attr); @@ -1406,57 +1286,44 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, *bp++ = 0; /* size of write */ *bp++ = htonl(attr->ia_size); /* new file length */ - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * set the attributes on a file, using FS.StoreData if there's a change in file * size, and FS.StoreStatus otherwise */ -int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, - struct afs_status_cb *scb) +void afs_fs_setattr(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct iattr *attr = op->setattr.attr; __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_setattr(fc, attr, scb); - if (attr->ia_valid & ATTR_SIZE) - return afs_fs_setattr_size(fc, attr, scb); + return afs_fs_setattr_size(op); _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &afs_RXFSStoreStatus, + call = afs_alloc_flat_call(op->net, &afs_RXFSStoreStatus, (4 + 6) * 4, (21 + 6) * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSTORESTATUS); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); - xdr_encode_AFS_StoreStatus(&bp, attr); + xdr_encode_AFS_StoreStatus(&bp, op->setattr.attr); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1464,6 +1331,7 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, */ static int afs_deliver_fs_get_volume_status(struct afs_call *call) { + struct afs_operation *op = call->op; const __be32 *bp; char *p; u32 size; @@ -1485,7 +1353,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus); + xdr_decode_AFSFetchVolumeStatus(&bp, &op->volstatus.vs); call->unmarshall++; afs_extract_to_tmp(call); /* Fall through */ @@ -1499,8 +1367,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) call->count = ntohl(call->tmp); _debug("volname length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_volname_len); + return afs_protocol_error(call, afs_eproto_volname_len); size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; @@ -1529,8 +1396,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) call->count = ntohl(call->tmp); _debug("offline msg length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_offline_msg_len); + return afs_protocol_error(call, afs_eproto_offline_msg_len); size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; @@ -1560,8 +1426,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) call->count = ntohl(call->tmp); _debug("motd length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_motd_len); + return afs_protocol_error(call, afs_eproto_motd_len); size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; @@ -1601,37 +1466,26 @@ static const struct afs_call_type afs_RXFSGetVolumeStatus = { /* * fetch the status of a volume */ -int afs_fs_get_volume_status(struct afs_fs_cursor *fc, - struct afs_volume_status *vs) +void afs_fs_get_volume_status(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_get_volume_status(fc, vs); - _enter(""); - call = afs_alloc_flat_call(net, &afs_RXFSGetVolumeStatus, 2 * 4, + call = afs_alloc_flat_call(op->net, &afs_RXFSGetVolumeStatus, 2 * 4, max(12 * 4, AFSOPAQUEMAX + 1)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_volstatus = vs; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSGETVOLUMESTATUS); - bp[1] = htonl(vnode->fid.vid); + bp[1] = htonl(vp->fid.vid); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1639,6 +1493,7 @@ int afs_fs_get_volume_status(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_xxxx_lock(struct afs_call *call) { + struct afs_operation *op = call->op; const __be32 *bp; int ret; @@ -1650,7 +1505,7 @@ static int afs_deliver_fs_xxxx_lock(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -1691,114 +1546,80 @@ static const struct afs_call_type afs_RXFSReleaseLock = { /* * Set a lock on a file */ -int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type, - struct afs_status_cb *scb) +void afs_fs_set_lock(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_set_lock(fc, type, scb); - _enter(""); - call = afs_alloc_flat_call(net, &afs_RXFSSetLock, 5 * 4, 6 * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSSetLock, 5 * 4, 6 * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->lvnode = vnode; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSETLOCK); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); - *bp++ = htonl(type); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_calli(call, &vnode->fid, type); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); + *bp++ = htonl(op->lock.type); + + trace_afs_make_fs_calli(call, &vp->fid, op->lock.type); + afs_make_op_call(op, call, GFP_NOFS); } /* * extend a lock on a file */ -int afs_fs_extend_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) +void afs_fs_extend_lock(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_extend_lock(fc, scb); - _enter(""); - call = afs_alloc_flat_call(net, &afs_RXFSExtendLock, 4 * 4, 6 * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSExtendLock, 4 * 4, 6 * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->lvnode = vnode; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSEXTENDLOCK); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); + + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * release a lock on a file */ -int afs_fs_release_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) +void afs_fs_release_lock(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_release_lock(fc, scb); - _enter(""); - call = afs_alloc_flat_call(net, &afs_RXFSReleaseLock, 4 * 4, 6 * 4); + call = afs_alloc_flat_call(op->net, &afs_RXFSReleaseLock, 4 * 4, 6 * 4); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->lvnode = vnode; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSRELEASELOCK); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); + + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1842,7 +1663,7 @@ int afs_fs_give_up_all_callbacks(struct afs_net *net, bp = call->request; *bp++ = htonl(FSGIVEUPALLCALLBACKS); - /* Can't take a ref on server */ + call->server = afs_use_server(server, afs_server_trace_give_up_cb); afs_make_call(ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, ac); } @@ -1905,14 +1726,13 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { }; /* - * Probe a fileserver for the capabilities that it supports. This can - * return up to 196 words. + * Probe a fileserver for the capabilities that it supports. This RPC can + * reply with up to 196 words. The operation is asynchronous and if we managed + * to allocate a call, true is returned the result is delivered through the + * ->done() - otherwise we return false to indicate we didn't even try. */ -struct afs_call *afs_fs_get_capabilities(struct afs_net *net, - struct afs_server *server, - struct afs_addr_cursor *ac, - struct key *key, - unsigned int server_index) +bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server, + struct afs_addr_cursor *ac, struct key *key) { struct afs_call *call; __be32 *bp; @@ -1921,11 +1741,10 @@ struct afs_call *afs_fs_get_capabilities(struct afs_net *net, call = afs_alloc_flat_call(net, &afs_RXFSGetCapabilities, 1 * 4, 16 * 4); if (!call) - return ERR_PTR(-ENOMEM); + return false; call->key = key; - call->server = afs_get_server(server, afs_server_trace_get_caps); - call->server_index = server_index; + call->server = afs_use_server(server, afs_server_trace_get_caps); call->upgrade = true; call->async = true; call->max_lifespan = AFS_PROBE_MAX_LIFESPAN; @@ -1934,87 +1753,10 @@ struct afs_call *afs_fs_get_capabilities(struct afs_net *net, bp = call->request; *bp++ = htonl(FSGETCAPABILITIES); - /* Can't take a ref on server */ trace_afs_make_fs_call(call, NULL); afs_make_call(ac, call, GFP_NOFS); - return call; -} - -/* - * Deliver reply data to an FS.FetchStatus with no vnode. - */ -static int afs_deliver_fs_fetch_status(struct afs_call *call) -{ - const __be32 *bp; - int ret; - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSCallBack(&bp, call, call->out_scb); - xdr_decode_AFSVolSync(&bp, call->out_volsync); - - _leave(" = 0 [done]"); - return 0; -} - -/* - * FS.FetchStatus operation type - */ -static const struct afs_call_type afs_RXFSFetchStatus = { - .name = "FS.FetchStatus", - .op = afs_FS_FetchStatus, - .deliver = afs_deliver_fs_fetch_status, - .destructor = afs_flat_call_destructor, -}; - -/* - * Fetch the status information for a fid without needing a vnode handle. - */ -int afs_fs_fetch_status(struct afs_fs_cursor *fc, - struct afs_net *net, - struct afs_fid *fid, - struct afs_status_cb *scb, - struct afs_volsync *volsync) -{ - struct afs_call *call; - __be32 *bp; - - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_status(fc, net, fid, scb, volsync); - - _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), fid->vid, fid->vnode); - - call = afs_alloc_flat_call(net, &afs_RXFSFetchStatus, 16, (21 + 3 + 6) * 4); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_fid = fid; - call->out_scb = scb; - call->out_volsync = volsync; - - /* marshall the parameters */ - bp = call->request; - bp[0] = htonl(FSFETCHSTATUS); - bp[1] = htonl(fid->vid); - bp[2] = htonl(fid->vnode); - bp[3] = htonl(fid->unique); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + afs_put_call(call); + return true; } /* @@ -2022,6 +1764,7 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) { + struct afs_operation *op = call->op; struct afs_status_cb *scb; const __be32 *bp; u32 tmp; @@ -2043,10 +1786,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; tmp = ntohl(call->tmp); - _debug("status count: %u/%u", tmp, call->count2); - if (tmp != call->count2) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_ibulkst_count); + _debug("status count: %u/%u", tmp, op->nr_files); + if (tmp != op->nr_files) + return afs_protocol_error(call, afs_eproto_ibulkst_count); call->count = 0; call->unmarshall++; @@ -2060,14 +1802,23 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) if (ret < 0) return ret; + switch (call->count) { + case 0: + scb = &op->file[0].scb; + break; + case 1: + scb = &op->file[1].scb; + break; + default: + scb = &op->more_files[call->count - 2].scb; + break; + } + bp = call->buffer; - scb = &call->out_scb[call->count]; - ret = xdr_decode_AFSFetchStatus(&bp, call, scb); - if (ret < 0) - return ret; + xdr_decode_AFSFetchStatus(&bp, call, scb); call->count++; - if (call->count < call->count2) + if (call->count < op->nr_files) goto more_counts; call->count = 0; @@ -2084,9 +1835,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) tmp = ntohl(call->tmp); _debug("CB count: %u", tmp); - if (tmp != call->count2) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_ibulkst_cb_count); + if (tmp != op->nr_files) + return afs_protocol_error(call, afs_eproto_ibulkst_cb_count); call->count = 0; call->unmarshall++; more_cbs: @@ -2100,11 +1850,22 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; _debug("unmarshall CB array"); + switch (call->count) { + case 0: + scb = &op->file[0].scb; + break; + case 1: + scb = &op->file[1].scb; + break; + default: + scb = &op->more_files[call->count - 2].scb; + break; + } + bp = call->buffer; - scb = &call->out_scb[call->count]; xdr_decode_AFSCallBack(&bp, call, scb); call->count++; - if (call->count < call->count2) + if (call->count < op->nr_files) goto more_cbs; afs_extract_to_buf(call, 6 * sizeof(__be32)); @@ -2117,7 +1878,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSVolSync(&bp, &op->volsync); call->unmarshall++; @@ -2129,6 +1890,16 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return 0; } +static void afs_done_fs_inline_bulk_status(struct afs_call *call) +{ + if (call->error == -ECONNABORTED && + call->abort_code == RX_INVALID_OPERATION) { + set_bit(AFS_SERVER_FL_NO_IBULK, &call->server->flags); + if (call->op) + set_bit(AFS_VOLUME_MAYBE_NO_IBULK, &call->op->volume->flags); + } +} + /* * FS.InlineBulkStatus operation type */ @@ -2136,58 +1907,53 @@ static const struct afs_call_type afs_RXFSInlineBulkStatus = { .name = "FS.InlineBulkStatus", .op = afs_FS_InlineBulkStatus, .deliver = afs_deliver_fs_inline_bulk_status, + .done = afs_done_fs_inline_bulk_status, .destructor = afs_flat_call_destructor, }; /* * Fetch the status information for up to 50 files */ -int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, - struct afs_net *net, - struct afs_fid *fids, - struct afs_status_cb *statuses, - unsigned int nr_fids, - struct afs_volsync *volsync) +void afs_fs_inline_bulk_status(struct afs_operation *op) { + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; struct afs_call *call; __be32 *bp; int i; - if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_inline_bulk_status(fc, net, fids, statuses, - nr_fids, volsync); + if (test_bit(AFS_SERVER_FL_NO_IBULK, &op->server->flags)) { + op->error = -ENOTSUPP; + return; + } _enter(",%x,{%llx:%llu},%u", - key_serial(fc->key), fids[0].vid, fids[1].vnode, nr_fids); + key_serial(op->key), vp->fid.vid, vp->fid.vnode, op->nr_files); - call = afs_alloc_flat_call(net, &afs_RXFSInlineBulkStatus, - (2 + nr_fids * 3) * 4, + call = afs_alloc_flat_call(op->net, &afs_RXFSInlineBulkStatus, + (2 + op->nr_files * 3) * 4, 21 * 4); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = statuses; - call->out_volsync = volsync; - call->count2 = nr_fids; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSINLINEBULKSTATUS); - *bp++ = htonl(nr_fids); - for (i = 0; i < nr_fids; i++) { - *bp++ = htonl(fids[i].vid); - *bp++ = htonl(fids[i].vnode); - *bp++ = htonl(fids[i].unique); + *bp++ = htonl(op->nr_files); + *bp++ = htonl(dvp->fid.vid); + *bp++ = htonl(dvp->fid.vnode); + *bp++ = htonl(dvp->fid.unique); + *bp++ = htonl(vp->fid.vid); + *bp++ = htonl(vp->fid.vnode); + *bp++ = htonl(vp->fid.unique); + for (i = 0; i < op->nr_files - 2; i++) { + *bp++ = htonl(op->more_files[i].fid.vid); + *bp++ = htonl(op->more_files[i].fid.vnode); + *bp++ = htonl(op->more_files[i].fid.unique); } - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &fids[0]); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -2195,6 +1961,8 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_fetch_acl(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[0]; struct afs_acl *acl; const __be32 *bp; unsigned int size; @@ -2220,7 +1988,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) acl = kmalloc(struct_size(acl, data, size), GFP_KERNEL); if (!acl) return -ENOMEM; - call->ret_acl = acl; + op->acl = acl; acl->size = call->count2; afs_extract_begin(call, acl->data, size); call->unmarshall++; @@ -2243,10 +2011,8 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); + xdr_decode_AFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_AFSVolSync(&bp, &op->volsync); call->unmarshall++; @@ -2258,12 +2024,6 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) return 0; } -static void afs_destroy_fs_fetch_acl(struct afs_call *call) -{ - kfree(call->ret_acl); - afs_flat_call_destructor(call); -} - /* * FS.FetchACL operation type */ @@ -2271,68 +2031,33 @@ static const struct afs_call_type afs_RXFSFetchACL = { .name = "FS.FetchACL", .op = afs_FS_FetchACL, .deliver = afs_deliver_fs_fetch_acl, - .destructor = afs_destroy_fs_fetch_acl, }; /* * Fetch the ACL for a file. */ -struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc, - struct afs_status_cb *scb) +void afs_fs_fetch_acl(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &afs_RXFSFetchACL, 16, (21 + 6) * 4); - if (!call) { - fc->ac.error = -ENOMEM; - return ERR_PTR(-ENOMEM); - } - - call->key = fc->key; - call->ret_acl = NULL; - call->out_scb = scb; - call->out_volsync = NULL; + call = afs_alloc_flat_call(op->net, &afs_RXFSFetchACL, 16, (21 + 6) * 4); + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHACL); - bp[1] = htonl(vnode->fid.vid); - bp[2] = htonl(vnode->fid.vnode); - bp[3] = htonl(vnode->fid.unique); - - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_make_call(&fc->ac, call, GFP_KERNEL); - return (struct afs_acl *)afs_wait_for_call_to_complete(call, &fc->ac); -} - -/* - * Deliver reply data to any operation that returns file status and volume - * sync. - */ -static int afs_deliver_fs_file_status_and_vol(struct afs_call *call) -{ - const __be32 *bp; - int ret; + bp[1] = htonl(vp->fid.vid); + bp[2] = htonl(vp->fid.vnode); + bp[3] = htonl(vp->fid.unique); - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - bp = call->buffer; - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_AFSVolSync(&bp, call->out_volsync); - - _leave(" = 0 [done]"); - return 0; + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_KERNEL); } /* @@ -2348,42 +2073,34 @@ static const struct afs_call_type afs_RXFSStoreACL = { /* * Fetch the ACL for a file. */ -int afs_fs_store_acl(struct afs_fs_cursor *fc, const struct afs_acl *acl, - struct afs_status_cb *scb) +void afs_fs_store_acl(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + const struct afs_acl *acl = op->acl; size_t size; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); size = round_up(acl->size, 4); - call = afs_alloc_flat_call(net, &afs_RXFSStoreACL, + call = afs_alloc_flat_call(op->net, &afs_RXFSStoreACL, 5 * 4 + size, (21 + 6) * 4); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = NULL; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSSTOREACL); - bp[1] = htonl(vnode->fid.vid); - bp[2] = htonl(vnode->fid.vnode); - bp[3] = htonl(vnode->fid.unique); + bp[1] = htonl(vp->fid.vid); + bp[2] = htonl(vp->fid.vnode); + bp[3] = htonl(vp->fid.unique); bp[4] = htonl(acl->size); memcpy(&bp[5], acl->data, acl->size); if (acl->size != size) memset((void *)&bp[5] + acl->size, 0, size - acl->size); - trace_afs_make_fs_call(call, &vnode->fid); - afs_make_call(&fc->ac, call, GFP_KERNEL); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_KERNEL); } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 281470fe1183..7dde703df40c 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -67,16 +67,18 @@ static void afs_set_i_size(struct afs_vnode *vnode, u64 size) /* * Initialise an inode from the vnode status. */ -static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, - struct afs_cb_interest *cbi, - struct afs_vnode *parent_vnode, - struct afs_status_cb *scb) +static int afs_inode_init_from_status(struct afs_operation *op, + struct afs_vnode_param *vp, + struct afs_vnode *vnode) { - struct afs_cb_interest *old_cbi = NULL; - struct afs_file_status *status = &scb->status; + struct afs_file_status *status = &vp->scb.status; struct inode *inode = AFS_VNODE_TO_I(vnode); struct timespec64 t; + _enter("{%llx:%llu.%u} %s", + vp->fid.vid, vp->fid.vnode, vp->fid.unique, + op->type ? op->type->name : "???"); + _debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu", status->type, status->nlink, @@ -86,12 +88,15 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, write_seqlock(&vnode->cb_lock); + vnode->cb_v_break = op->cb_v_break; + vnode->cb_s_break = op->cb_s_break; vnode->status = *status; t = status->mtime_client; inode->i_ctime = t; inode->i_mtime = t; inode->i_atime = t; + inode->i_flags |= S_NOATIME; inode->i_uid = make_kuid(&init_user_ns, status->owner); inode->i_gid = make_kgid(&init_user_ns, status->group); set_nlink(&vnode->vfs_inode, status->nlink); @@ -128,9 +133,9 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, inode_nohighmem(inode); break; default: - dump_vnode(vnode, parent_vnode); + dump_vnode(vnode, op->file[0].vnode != vnode ? op->file[0].vnode : NULL); write_sequnlock(&vnode->cb_lock); - return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type); + return afs_protocol_error(NULL, afs_eproto_file_type); } afs_set_i_size(vnode, status->size); @@ -138,39 +143,36 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, vnode->invalid_before = status->data_version; inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - if (!scb->have_cb) { + if (!vp->scb.have_cb) { /* it's a symlink we just created (the fileserver * didn't give us a callback) */ vnode->cb_expires_at = ktime_get_real_seconds(); } else { - vnode->cb_expires_at = scb->callback.expires_at; - old_cbi = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->cb_lock.lock)); - if (cbi != old_cbi) - rcu_assign_pointer(vnode->cb_interest, afs_get_cb_interest(cbi)); - else - old_cbi = NULL; + vnode->cb_expires_at = vp->scb.callback.expires_at; + vnode->cb_server = op->server; set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); } write_sequnlock(&vnode->cb_lock); - afs_put_cb_interest(afs_v2net(vnode), old_cbi); return 0; } /* * Update the core inode struct from a returned status record. */ -static void afs_apply_status(struct afs_fs_cursor *fc, - struct afs_vnode *vnode, - struct afs_status_cb *scb, - const afs_dataversion_t *expected_version) +static void afs_apply_status(struct afs_operation *op, + struct afs_vnode_param *vp) { - struct afs_file_status *status = &scb->status; + struct afs_file_status *status = &vp->scb.status; + struct afs_vnode *vnode = vp->vnode; struct timespec64 t; umode_t mode; bool data_changed = false; + _enter("{%llx:%llu.%u} %s", + vp->fid.vid, vp->fid.vnode, vp->fid.unique, + op->type ? op->type->name : "???"); + BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags)); if (status->type != vnode->status.type) { @@ -179,7 +181,7 @@ static void afs_apply_status(struct afs_fs_cursor *fc, vnode->fid.vnode, vnode->fid.unique, status->type, vnode->status.type); - afs_protocol_error(NULL, -EBADMSG, afs_eproto_bad_status); + afs_protocol_error(NULL, afs_eproto_bad_status); return; } @@ -209,14 +211,13 @@ static void afs_apply_status(struct afs_fs_cursor *fc, vnode->status = *status; - if (expected_version && - *expected_version != status->data_version) { + if (vp->dv_before + vp->dv_delta != status->data_version) { if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s\n", vnode->fid.vid, vnode->fid.vnode, - (unsigned long long)*expected_version, + (unsigned long long)vp->dv_before + vp->dv_delta, (unsigned long long)status->data_version, - fc->type ? fc->type->name : "???"); + op->type ? op->type->name : "???"); vnode->invalid_before = status->data_version; if (vnode->status.type == AFS_FTYPE_DIR) { @@ -243,22 +244,15 @@ static void afs_apply_status(struct afs_fs_cursor *fc, /* * Apply a callback to a vnode. */ -static void afs_apply_callback(struct afs_fs_cursor *fc, - struct afs_vnode *vnode, - struct afs_status_cb *scb, - unsigned int cb_break) +static void afs_apply_callback(struct afs_operation *op, + struct afs_vnode_param *vp) { - struct afs_cb_interest *old; - struct afs_callback *cb = &scb->callback; + struct afs_callback *cb = &vp->scb.callback; + struct afs_vnode *vnode = vp->vnode; - if (!afs_cb_is_broken(cb_break, vnode, fc->cbi)) { + if (!afs_cb_is_broken(vp->cb_break_before, vnode)) { vnode->cb_expires_at = cb->expires_at; - old = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->cb_lock.lock)); - if (old != fc->cbi) { - rcu_assign_pointer(vnode->cb_interest, afs_get_cb_interest(fc->cbi)); - afs_put_cb_interest(afs_v2net(vnode), old); - } + vnode->cb_server = op->server; set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); } } @@ -267,106 +261,108 @@ static void afs_apply_callback(struct afs_fs_cursor *fc, * Apply the received status and callback to an inode all in the same critical * section to avoid races with afs_validate(). */ -void afs_vnode_commit_status(struct afs_fs_cursor *fc, - struct afs_vnode *vnode, - unsigned int cb_break, - const afs_dataversion_t *expected_version, - struct afs_status_cb *scb) +void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *vp) { - if (fc->ac.error != 0) - return; + struct afs_vnode *vnode = vp->vnode; + + _enter(""); + + ASSERTCMP(op->error, ==, 0); write_seqlock(&vnode->cb_lock); - if (scb->have_error) { - if (scb->status.abort_code == VNOVNODE) { + if (vp->scb.have_error) { + if (vp->scb.status.abort_code == VNOVNODE) { set_bit(AFS_VNODE_DELETED, &vnode->flags); clear_nlink(&vnode->vfs_inode); __afs_break_callback(vnode, afs_cb_break_for_deleted); } } else { - if (scb->have_status) - afs_apply_status(fc, vnode, scb, expected_version); - if (scb->have_cb) - afs_apply_callback(fc, vnode, scb, cb_break); + if (vp->scb.have_status) + afs_apply_status(op, vp); + if (vp->scb.have_cb) + afs_apply_callback(op, vp); } write_sequnlock(&vnode->cb_lock); - if (fc->ac.error == 0 && scb->have_status) - afs_cache_permit(vnode, fc->key, cb_break, scb); + if (op->error == 0 && vp->scb.have_status) + afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb); } +static void afs_fetch_status_success(struct afs_operation *op) +{ + struct afs_vnode_param *vp = &op->file[0]; + struct afs_vnode *vnode = vp->vnode; + int ret; + + if (vnode->vfs_inode.i_state & I_NEW) { + ret = afs_inode_init_from_status(op, vp, vnode); + op->error = ret; + if (ret == 0) + afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb); + } else { + afs_vnode_commit_status(op, vp); + } +} + +static const struct afs_operation_ops afs_fetch_status_operation = { + .issue_afs_rpc = afs_fs_fetch_status, + .issue_yfs_rpc = yfs_fs_fetch_status, + .success = afs_fetch_status_success, +}; + /* * Fetch file status from the volume. */ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool is_new, afs_access_t *_caller_access) { - struct afs_status_cb *scb; - struct afs_fs_cursor fc; - int ret; + struct afs_operation *op; _enter("%s,{%llx:%llu.%u,S=%lx}", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, vnode->flags); - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - return -ENOMEM; + op = afs_alloc_operation(key, vnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - afs_dataversion_t data_version = vnode->status.data_version; + afs_op_set_vnode(op, 0, vnode); - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_fetch_file_status(&fc, scb, NULL); - } - - if (fc.error) { - /* Do nothing. */ - } else if (is_new) { - ret = afs_inode_init_from_status(vnode, key, fc.cbi, - NULL, scb); - fc.error = ret; - if (ret == 0) - afs_cache_permit(vnode, key, fc.cb_break, scb); - } else { - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - } - afs_check_for_remote_deletion(&fc, vnode); - ret = afs_end_vnode_operation(&fc); - } + op->nr_files = 1; + op->ops = &afs_fetch_status_operation; + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); - if (ret == 0 && _caller_access) - *_caller_access = scb->status.caller_access; - kfree(scb); - _leave(" = %d", ret); - return ret; + if (_caller_access) + *_caller_access = op->file[0].scb.status.caller_access; + return afs_put_operation(op); } /* - * iget5() comparator + * ilookup() comparator */ -int afs_iget5_test(struct inode *inode, void *opaque) +int afs_ilookup5_test_by_fid(struct inode *inode, void *opaque) { - struct afs_iget_data *iget_data = opaque; struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_fid *fid = opaque; - return memcmp(&vnode->fid, &iget_data->fid, sizeof(iget_data->fid)) == 0; + return (fid->vnode == vnode->fid.vnode && + fid->vnode_hi == vnode->fid.vnode_hi && + fid->unique == vnode->fid.unique); } /* - * iget5() comparator for inode created by autocell operations - * - * These pseudo inodes don't match anything. + * iget5() comparator */ -static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque) +static int afs_iget5_test(struct inode *inode, void *opaque) { - return 0; + struct afs_vnode_param *vp = opaque; + //struct afs_vnode *vnode = AFS_FS_I(inode); + + return afs_ilookup5_test_by_fid(inode, &vp->fid); } /* @@ -374,99 +370,22 @@ static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque) */ static int afs_iget5_set(struct inode *inode, void *opaque) { - struct afs_iget_data *iget_data = opaque; + struct afs_vnode_param *vp = opaque; + struct afs_super_info *as = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); - vnode->fid = iget_data->fid; - vnode->volume = iget_data->volume; - vnode->cb_v_break = iget_data->cb_v_break; - vnode->cb_s_break = iget_data->cb_s_break; + vnode->volume = as->volume; + vnode->fid = vp->fid; /* YFS supports 96-bit vnode IDs, but Linux only supports * 64-bit inode numbers. */ - inode->i_ino = iget_data->fid.vnode; - inode->i_generation = iget_data->fid.unique; + inode->i_ino = vnode->fid.vnode; + inode->i_generation = vnode->fid.unique; return 0; } /* - * Create an inode for a dynamic root directory or an autocell dynamic - * automount dir. - */ -struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) -{ - struct afs_super_info *as; - struct afs_vnode *vnode; - struct inode *inode; - static atomic_t afs_autocell_ino; - - struct afs_iget_data iget_data = { - .cb_v_break = 0, - .cb_s_break = 0, - }; - - _enter(""); - - as = sb->s_fs_info; - if (as->volume) { - iget_data.volume = as->volume; - iget_data.fid.vid = as->volume->vid; - } - if (root) { - iget_data.fid.vnode = 1; - iget_data.fid.unique = 1; - } else { - iget_data.fid.vnode = atomic_inc_return(&afs_autocell_ino); - iget_data.fid.unique = 0; - } - - inode = iget5_locked(sb, iget_data.fid.vnode, - afs_iget5_pseudo_dir_test, afs_iget5_set, - &iget_data); - if (!inode) { - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - - _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", - inode, inode->i_ino, iget_data.fid.vid, iget_data.fid.vnode, - iget_data.fid.unique); - - vnode = AFS_FS_I(inode); - - /* there shouldn't be an existing inode */ - BUG_ON(!(inode->i_state & I_NEW)); - - inode->i_size = 0; - inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; - if (root) { - inode->i_op = &afs_dynroot_inode_operations; - inode->i_fop = &simple_dir_operations; - } else { - inode->i_op = &afs_autocell_inode_operations; - } - set_nlink(inode, 2); - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode); - inode->i_blocks = 0; - inode_set_iversion_raw(inode, 0); - inode->i_generation = 0; - - set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags); - if (!root) { - set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); - inode->i_flags |= S_AUTOMOUNT; - } - - inode->i_flags |= S_NOATIME; - unlock_new_inode(inode); - _leave(" = %p", inode); - return inode; -} - -/* * Get a cache cookie for an inode. */ static void afs_get_inode_cache(struct afs_vnode *vnode) @@ -501,58 +420,41 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) /* * inode retrieval */ -struct inode *afs_iget(struct super_block *sb, struct key *key, - struct afs_iget_data *iget_data, - struct afs_status_cb *scb, - struct afs_cb_interest *cbi, - struct afs_vnode *parent_vnode) +struct inode *afs_iget(struct afs_operation *op, struct afs_vnode_param *vp) { - struct afs_super_info *as; + struct afs_vnode_param *dvp = &op->file[0]; + struct super_block *sb = dvp->vnode->vfs_inode.i_sb; struct afs_vnode *vnode; - struct afs_fid *fid = &iget_data->fid; struct inode *inode; int ret; - _enter(",{%llx:%llu.%u},,", fid->vid, fid->vnode, fid->unique); + _enter(",{%llx:%llu.%u},,", vp->fid.vid, vp->fid.vnode, vp->fid.unique); - as = sb->s_fs_info; - iget_data->volume = as->volume; - - inode = iget5_locked(sb, fid->vnode, afs_iget5_test, afs_iget5_set, - iget_data); + inode = iget5_locked(sb, vp->fid.vnode, afs_iget5_test, afs_iget5_set, vp); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } - _debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }", - inode, fid->vid, fid->vnode, fid->unique); - vnode = AFS_FS_I(inode); + _debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }", + inode, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); + /* deal with an existing inode */ if (!(inode->i_state & I_NEW)) { _leave(" = %p", inode); return inode; } - if (!scb) { - /* it's a remotely extant inode */ - ret = afs_fetch_status(vnode, key, true, NULL); - if (ret < 0) - goto bad_inode; - } else { - ret = afs_inode_init_from_status(vnode, key, cbi, parent_vnode, - scb); - if (ret < 0) - goto bad_inode; - } + ret = afs_inode_init_from_status(op, vp, vnode); + if (ret < 0) + goto bad_inode; afs_get_inode_cache(vnode); /* success */ clear_bit(AFS_VNODE_UNSET, &vnode->flags); - inode->i_flags |= S_NOATIME; unlock_new_inode(inode); _leave(" = %p", inode); return inode; @@ -564,6 +466,74 @@ bad_inode: return ERR_PTR(ret); } +static int afs_iget5_set_root(struct inode *inode, void *opaque) +{ + struct afs_super_info *as = AFS_FS_S(inode->i_sb); + struct afs_vnode *vnode = AFS_FS_I(inode); + + vnode->volume = as->volume; + vnode->fid.vid = as->volume->vid, + vnode->fid.vnode = 1; + vnode->fid.unique = 1; + inode->i_ino = 1; + inode->i_generation = 1; + return 0; +} + +/* + * Set up the root inode for a volume. This is always vnode 1, unique 1 within + * the volume. + */ +struct inode *afs_root_iget(struct super_block *sb, struct key *key) +{ + struct afs_super_info *as = AFS_FS_S(sb); + struct afs_operation *op; + struct afs_vnode *vnode; + struct inode *inode; + int ret; + + _enter(",{%llx},,", as->volume->vid); + + inode = iget5_locked(sb, 1, NULL, afs_iget5_set_root, NULL); + if (!inode) { + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); + } + + _debug("GOT ROOT INODE %p { vl=%llx }", inode, as->volume->vid); + + BUG_ON(!(inode->i_state & I_NEW)); + + vnode = AFS_FS_I(inode); + vnode->cb_v_break = as->volume->cb_v_break, + + op = afs_alloc_operation(key, as->volume); + if (IS_ERR(op)) { + ret = PTR_ERR(op); + goto error; + } + + afs_op_set_vnode(op, 0, vnode); + + op->nr_files = 1; + op->ops = &afs_fetch_status_operation; + ret = afs_do_sync_operation(op); + if (ret < 0) + goto error; + + afs_get_inode_cache(vnode); + + clear_bit(AFS_VNODE_UNSET, &vnode->flags); + unlock_new_inode(inode); + _leave(" = %p", inode); + return inode; + +error: + iget_failed(inode); + _leave(" = %d [bad]", ret); + return ERR_PTR(ret); +} + /* * mark the data attached to an inode as obsolete due to a write on the server * - might also want to ditch all the outstanding writes and dirty pages @@ -586,12 +556,30 @@ void afs_zap_data(struct afs_vnode *vnode) } /* + * Get the server reinit counter for a vnode's current server. + */ +static bool afs_get_s_break_rcu(struct afs_vnode *vnode, unsigned int *_s_break) +{ + struct afs_server_list *slist = rcu_dereference(vnode->volume->servers); + struct afs_server *server; + int i; + + for (i = 0; i < slist->nr_servers; i++) { + server = slist->servers[i].server; + if (server == vnode->cb_server) { + *_s_break = READ_ONCE(server->cb_s_break); + return true; + } + } + + return false; +} + +/* * Check the validity of a vnode/inode. */ bool afs_check_validity(struct afs_vnode *vnode) { - struct afs_cb_interest *cbi; - struct afs_server *server; struct afs_volume *volume = vnode->volume; enum afs_cb_break_reason need_clear = afs_cb_break_no_break; time64_t now = ktime_get_real_seconds(); @@ -604,11 +592,8 @@ bool afs_check_validity(struct afs_vnode *vnode) cb_v_break = READ_ONCE(volume->cb_v_break); cb_break = vnode->cb_break; - if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { - cbi = rcu_dereference(vnode->cb_interest); - server = rcu_dereference(cbi->server); - cb_s_break = READ_ONCE(server->cb_s_break); - + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) && + afs_get_s_break_rcu(vnode, &cb_s_break)) { if (vnode->cb_s_break != cb_s_break || vnode->cb_v_break != cb_v_break) { vnode->cb_s_break = cb_s_break; @@ -755,7 +740,6 @@ int afs_drop_inode(struct inode *inode) */ void afs_evict_inode(struct inode *inode) { - struct afs_cb_interest *cbi; struct afs_vnode *vnode; vnode = AFS_FS_I(inode); @@ -772,15 +756,6 @@ void afs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - write_seqlock(&vnode->cb_lock); - cbi = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->cb_lock.lock)); - if (cbi) { - afs_put_cb_interest(afs_i2net(inode), cbi); - rcu_assign_pointer(vnode->cb_interest, NULL); - } - write_sequnlock(&vnode->cb_lock); - while (!list_empty(&vnode->wb_keys)) { struct afs_wb_key *wbk = list_entry(vnode->wb_keys.next, struct afs_wb_key, vnode_link); @@ -808,16 +783,24 @@ void afs_evict_inode(struct inode *inode) _leave(""); } +static void afs_setattr_success(struct afs_operation *op) +{ + afs_vnode_commit_status(op, &op->file[0]); +} + +static const struct afs_operation_ops afs_setattr_operation = { + .issue_afs_rpc = afs_fs_setattr, + .issue_yfs_rpc = yfs_fs_setattr, + .success = afs_setattr_success, +}; + /* * set the attributes of an inode */ int afs_setattr(struct dentry *dentry, struct iattr *attr) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); - struct key *key; - int ret = -ENOMEM; _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, @@ -829,48 +812,22 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) return 0; } - scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); - if (!scb) - goto error; - /* flush any dirty data outstanding on a regular file */ if (S_ISREG(vnode->vfs_inode.i_mode)) filemap_write_and_wait(vnode->vfs_inode.i_mapping); - if (attr->ia_valid & ATTR_FILE) { - key = afs_file_key(attr->ia_file); - } else { - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; - } - } - - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, false)) { - afs_dataversion_t data_version = vnode->status.data_version; + op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ? + afs_file_key(attr->ia_file) : NULL), + vnode->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - if (attr->ia_valid & ATTR_SIZE) - data_version++; + afs_op_set_vnode(op, 0, vnode); + op->setattr.attr = attr; - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_setattr(&fc, attr, scb); - } - - afs_check_for_remote_deletion(&fc, vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - ret = afs_end_vnode_operation(&fc); - } + if (attr->ia_valid & ATTR_SIZE) + op->file[0].dv_delta = 1; - if (!(attr->ia_valid & ATTR_FILE)) - key_put(key); - -error_scb: - kfree(scb); -error: - _leave(" = %d", ret); - return ret; + op->ops = &afs_setattr_operation; + return afs_do_sync_operation(op); } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 80255513e230..e1621b0670cc 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -59,13 +59,6 @@ struct afs_fs_context { struct key *key; /* key to use for secure mounting */ }; -struct afs_iget_data { - struct afs_fid fid; - struct afs_volume *volume; /* volume on which resides */ - unsigned int cb_v_break; /* Pre-fetch volume break count */ - unsigned int cb_s_break; /* Pre-fetch server break count */ -}; - enum afs_call_state { AFS_CALL_CL_REQUESTING, /* Client: Request is being sent */ AFS_CALL_CL_AWAIT_REPLY, /* Client: Awaiting reply */ @@ -90,7 +83,6 @@ struct afs_addr_list { unsigned char nr_ipv4; /* Number of IPv4 addresses */ enum dns_record_source source:8; enum dns_lookup_status status:8; - unsigned long probed; /* Mask of servers that have been probed */ unsigned long failed; /* Mask of addrs that failed locally/ICMP */ unsigned long responded; /* Mask of addrs that responded */ struct sockaddr_rxrpc addrs[]; @@ -111,10 +103,7 @@ struct afs_call { struct afs_net *net; /* The network namespace */ struct afs_server *server; /* The fileserver record if fs op (pins ref) */ struct afs_vlserver *vlserver; /* The vlserver record if vl op */ - struct afs_cb_interest *cbi; /* Callback interest for server used */ - struct afs_vnode *lvnode; /* vnode being locked */ void *request; /* request data (first part) */ - struct address_space *mapping; /* Pages being written from */ struct iov_iter def_iter; /* Default buffer/data iterator */ struct iov_iter *iter; /* Iterator currently in use */ union { /* Convenience for ->def_iter */ @@ -126,32 +115,19 @@ struct afs_call { long ret0; /* Value to reply with instead of 0 */ struct afs_addr_list *ret_alist; struct afs_vldb_entry *ret_vldb; - struct afs_acl *ret_acl; + char *ret_str; }; - struct afs_fid *out_fid; - struct afs_status_cb *out_dir_scb; - struct afs_status_cb *out_scb; - struct yfs_acl *out_yacl; - struct afs_volsync *out_volsync; - struct afs_volume_status *out_volstatus; - struct afs_read *read_request; + struct afs_operation *op; unsigned int server_index; - pgoff_t first; /* first page in mapping to deal with */ - pgoff_t last; /* last page in mapping to deal with */ atomic_t usage; enum afs_call_state state; spinlock_t state_lock; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ - u32 epoch; unsigned int max_lifespan; /* Maximum lifespan to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ - unsigned first_offset; /* offset into mapping[first] */ - union { - unsigned last_to; /* amount of mapping[last] */ - unsigned count2; /* count used in unmarshalling */ - }; + unsigned count2; /* count used in unmarshalling */ unsigned char unmarshall; /* unmarshalling phase */ unsigned char addr_ix; /* Address in ->alist */ bool drop_ref; /* T if need to drop ref for incoming call */ @@ -161,6 +137,7 @@ struct afs_call { bool upgrade; /* T to request service upgrade */ bool have_reply_time; /* T if have got reply_time */ bool intr; /* T if interruptible */ + bool unmarshalling_error; /* T if an unmarshalling error occurred */ u16 service_id; /* Actual service ID (after upgrade) */ unsigned int debug_id; /* Trace ID */ u32 operation_ID; /* operation ID for an incoming call */ @@ -291,6 +268,7 @@ struct afs_net { struct timer_list cells_timer; atomic_t cells_outstanding; seqlock_t cells_lock; + struct mutex cells_alias_lock; struct mutex proc_cells_lock; struct hlist_head proc_cells; @@ -299,9 +277,10 @@ struct afs_net { * cell, but in practice, people create aliases and subsets and there's * no easy way to distinguish them. */ - seqlock_t fs_lock; /* For fs_servers */ + seqlock_t fs_lock; /* For fs_servers, fs_probe_*, fs_proc */ struct rb_root fs_servers; /* afs_server (by server UUID or address) */ - struct list_head fs_updates; /* afs_server (by update_at) */ + struct list_head fs_probe_fast; /* List of afs_server to probe at 30s intervals */ + struct list_head fs_probe_slow; /* List of afs_server to probe at 5m intervals */ struct hlist_head fs_proc; /* procfs servers list */ struct hlist_head fs_addresses4; /* afs_server (by lowest IPv4 addr) */ @@ -310,6 +289,9 @@ struct afs_net { struct work_struct fs_manager; struct timer_list fs_timer; + + struct work_struct fs_prober; + struct timer_list fs_probe_timer; atomic_t servers_outstanding; /* File locking renewal management */ @@ -360,8 +342,10 @@ enum afs_cell_state { * for authentication and encryption. The cell name is not typically used in * the protocol. * - * There is no easy way to determine if two cells are aliases or one is a - * subset of another. + * Two cells are determined to be aliases if they have an explicit alias (YFS + * only), share any VL servers in common or have at least one volume in common. + * "In common" means that the address list of the VL servers or the fileservers + * share at least one endpoint. */ struct afs_cell { union { @@ -369,6 +353,8 @@ struct afs_cell { struct rb_node net_node; /* Node in net->cells */ }; struct afs_net *net; + struct afs_cell *alias_of; /* The cell this is an alias of */ + struct afs_volume *root_volume; /* The root.cell volume if there is one */ struct key *anonymous_key; /* anonymous user key for this cell */ struct work_struct manager; /* Manager for init/deinit/dns */ struct hlist_node proc_link; /* /proc cell list link */ @@ -381,15 +367,21 @@ struct afs_cell { unsigned long flags; #define AFS_CELL_FL_NO_GC 0 /* The cell was added manually, don't auto-gc */ #define AFS_CELL_FL_DO_LOOKUP 1 /* DNS lookup requested */ +#define AFS_CELL_FL_CHECK_ALIAS 2 /* Need to check for aliases */ enum afs_cell_state state; short error; enum dns_record_source dns_source:8; /* Latest source of data from lookup */ enum dns_lookup_status dns_status:8; /* Latest status of data from lookup */ unsigned int dns_lookup_count; /* Counter of DNS lookups */ + /* The volumes belonging to this cell */ + struct rb_root volumes; /* Tree of volumes on this server */ + struct hlist_head proc_volumes; /* procfs volume list */ + seqlock_t volume_lock; /* For volumes */ + /* Active fileserver interaction state. */ - struct list_head proc_volumes; /* procfs volume list */ - rwlock_t proc_lock; + struct rb_root fs_servers; /* afs_server (by server UUID) */ + seqlock_t fs_lock; /* For fs_servers */ /* VL server list. */ rwlock_t vl_servers_lock; /* Lock on vl_servers */ @@ -471,6 +463,7 @@ struct afs_vldb_entry { #define AFS_VLDB_QUERY_ERROR 4 /* - VL server returned error */ uuid_t fs_server[AFS_NMAXNSERVERS]; + u32 addr_version[AFS_NMAXNSERVERS]; /* Registration change counters */ u8 fs_mask[AFS_NMAXNSERVERS]; #define AFS_VOL_VTM_RW 0x01 /* R/W version of the volume is available (on this server) */ #define AFS_VOL_VTM_RO 0x02 /* R/O version of the volume is available (on this server) */ @@ -492,94 +485,64 @@ struct afs_server { }; struct afs_addr_list __rcu *addresses; - struct rb_node uuid_rb; /* Link in net->servers */ + struct afs_cell *cell; /* Cell to which belongs (pins ref) */ + struct rb_node uuid_rb; /* Link in net->fs_servers */ + struct afs_server __rcu *uuid_next; /* Next server with same UUID */ + struct afs_server *uuid_prev; /* Previous server with same UUID */ + struct list_head probe_link; /* Link in net->fs_probe_list */ struct hlist_node addr4_link; /* Link in net->fs_addresses4 */ struct hlist_node addr6_link; /* Link in net->fs_addresses6 */ struct hlist_node proc_link; /* Link in net->fs_proc */ struct afs_server *gc_next; /* Next server in manager's list */ - time64_t put_time; /* Time at which last put */ - time64_t update_at; /* Time at which to next update the record */ + time64_t unuse_time; /* Time at which last unused */ unsigned long flags; -#define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */ -#define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */ -#define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */ -#define AFS_SERVER_FL_UPDATING 4 -#define AFS_SERVER_FL_PROBED 5 /* The fileserver has been probed */ -#define AFS_SERVER_FL_PROBING 6 /* Fileserver is being probed */ -#define AFS_SERVER_FL_NO_IBULK 7 /* Fileserver doesn't support FS.InlineBulkStatus */ +#define AFS_SERVER_FL_RESPONDING 0 /* The server is responding */ +#define AFS_SERVER_FL_UPDATING 1 +#define AFS_SERVER_FL_NEEDS_UPDATE 2 /* Fileserver address list is out of date */ +#define AFS_SERVER_FL_NOT_READY 4 /* The record is not ready for use */ +#define AFS_SERVER_FL_NOT_FOUND 5 /* VL server says no such server */ +#define AFS_SERVER_FL_VL_FAIL 6 /* Failed to access VL server */ #define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */ -#define AFS_SERVER_FL_IS_YFS 9 /* Server is YFS not AFS */ -#define AFS_SERVER_FL_NO_RM2 10 /* Fileserver doesn't support YFS.RemoveFile2 */ -#define AFS_SERVER_FL_HAVE_EPOCH 11 /* ->epoch is valid */ - atomic_t usage; +#define AFS_SERVER_FL_IS_YFS 16 /* Server is YFS not AFS */ +#define AFS_SERVER_FL_NO_IBULK 17 /* Fileserver doesn't support FS.InlineBulkStatus */ +#define AFS_SERVER_FL_NO_RM2 18 /* Fileserver doesn't support YFS.RemoveFile2 */ + atomic_t ref; /* Object refcount */ + atomic_t active; /* Active user count */ u32 addr_version; /* Address list version */ - u32 cm_epoch; /* Server RxRPC epoch */ + unsigned int rtt; /* Server's current RTT in uS */ unsigned int debug_id; /* Debugging ID for traces */ /* file service access */ rwlock_t fs_lock; /* access lock */ /* callback promise management */ - struct hlist_head cb_volumes; /* List of volume interests on this server */ unsigned cb_s_break; /* Break-everything counter. */ - rwlock_t cb_break_lock; /* Volume finding lock */ /* Probe state */ + unsigned long probed_at; /* Time last probe was dispatched (jiffies) */ wait_queue_head_t probe_wq; atomic_t probe_outstanding; spinlock_t probe_lock; struct { - unsigned int rtt; /* RTT as ktime/64 */ + unsigned int rtt; /* RTT in uS */ u32 abort_code; - u32 cm_epoch; short error; bool responded:1; bool is_yfs:1; bool not_yfs:1; bool local_failure:1; - bool cm_probed:1; - bool said_rebooted:1; - bool said_inconsistent:1; } probe; }; /* - * Volume collation in the server's callback interest list. - */ -struct afs_vol_interest { - struct hlist_node srv_link; /* Link in server->cb_volumes */ - struct hlist_head cb_interests; /* List of callback interests on the server */ - union { - struct rcu_head rcu; - afs_volid_t vid; /* Volume ID to match */ - }; - unsigned int usage; -}; - -/* - * Interest by a superblock on a server. - */ -struct afs_cb_interest { - struct hlist_node cb_vlink; /* Link in vol_interest->cb_interests */ - struct afs_vol_interest *vol_interest; - struct afs_server *server; /* Server on which this interest resides */ - struct super_block *sb; /* Superblock on which inodes reside */ - union { - struct rcu_head rcu; - afs_volid_t vid; /* Volume ID to match */ - }; - refcount_t usage; -}; - -/* - * Replaceable server list. + * Replaceable volume server list. */ struct afs_server_entry { struct afs_server *server; - struct afs_cb_interest *cb_interest; }; struct afs_server_list { + afs_volid_t vids[AFS_MAXTYPES]; /* Volume IDs */ refcount_t usage; unsigned char nr_servers; unsigned char preferred; /* Preferred server */ @@ -593,11 +556,16 @@ struct afs_server_list { * Live AFS volume management. */ struct afs_volume { - afs_volid_t vid; /* volume ID */ + union { + struct rcu_head rcu; + afs_volid_t vid; /* volume ID */ + }; atomic_t usage; time64_t update_at; /* Time at which to next update */ struct afs_cell *cell; /* Cell to which belongs (pins ref) */ - struct list_head proc_link; /* Link in cell->vl_proc */ + struct rb_node cell_node; /* Link in cell->volumes */ + struct hlist_node proc_link; /* Link in cell->proc_volumes */ + struct super_block __rcu *sb; /* Superblock on which inodes reside */ unsigned long flags; #define AFS_VOLUME_NEEDS_UPDATE 0 /* - T if an update needs performing */ #define AFS_VOLUME_UPDATING 1 /* - T if an update is in progress */ @@ -605,10 +573,11 @@ struct afs_volume { #define AFS_VOLUME_DELETED 3 /* - T if volume appears deleted */ #define AFS_VOLUME_OFFLINE 4 /* - T if volume offline notice given */ #define AFS_VOLUME_BUSY 5 /* - T if volume busy notice given */ +#define AFS_VOLUME_MAYBE_NO_IBULK 6 /* - T if some servers don't have InlineBulkStatus */ #ifdef CONFIG_AFS_FSCACHE struct fscache_cookie *cache; /* caching cookie */ #endif - struct afs_server_list *servers; /* List of servers on which volume resides */ + struct afs_server_list __rcu *servers; /* List of servers on which volume resides */ rwlock_t servers_lock; /* Lock for ->servers */ unsigned int servers_seq; /* Incremented each time ->servers changes */ @@ -616,7 +585,6 @@ struct afs_volume { rwlock_t cb_v_break_lock; afs_voltype_t type; /* type of volume */ - short error; char type_force; /* force volume type (suppress R/O -> R/W) */ u8 name_len; u8 name[AFS_MAXVOLNAME + 1]; /* NUL-padded volume name */ @@ -677,11 +645,11 @@ struct afs_vnode { afs_lock_type_t lock_type : 8; /* outstanding callback notification on this file */ - struct afs_cb_interest __rcu *cb_interest; /* Server on which this resides */ + void *cb_server; /* Server with callback/filelock */ unsigned int cb_s_break; /* Mass break counter on ->server */ unsigned int cb_v_break; /* Mass break counter on ->volume */ unsigned int cb_break; /* Break counter on vnode */ - seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */ + seqlock_t cb_lock; /* Lock for ->cb_server, ->status, ->cb_*break */ time64_t cb_expires_at; /* time at which callback expires */ }; @@ -758,29 +726,118 @@ struct afs_vl_cursor { }; /* - * Cursor for iterating over a set of fileservers. + * Fileserver operation methods. + */ +struct afs_operation_ops { + void (*issue_afs_rpc)(struct afs_operation *op); + void (*issue_yfs_rpc)(struct afs_operation *op); + void (*success)(struct afs_operation *op); + void (*aborted)(struct afs_operation *op); + void (*edit_dir)(struct afs_operation *op); + void (*put)(struct afs_operation *op); +}; + +struct afs_vnode_param { + struct afs_vnode *vnode; + struct afs_fid fid; /* Fid to access */ + struct afs_status_cb scb; /* Returned status and callback promise */ + afs_dataversion_t dv_before; /* Data version before the call */ + unsigned int cb_break_before; /* cb_break + cb_s_break before the call */ + u8 dv_delta; /* Expected change in data version */ + bool put_vnode; /* T if we have a ref on the vnode */ + bool need_io_lock; /* T if we need the I/O lock on this */ +}; + +/* + * Fileserver operation wrapper, handling server and address rotation + * asynchronously. May make simultaneous calls to multiple servers. */ -struct afs_fs_cursor { +struct afs_operation { + struct afs_net *net; /* Network namespace */ + struct key *key; /* Key for the cell */ const struct afs_call_type *type; /* Type of call done */ + const struct afs_operation_ops *ops; + + /* Parameters/results for the operation */ + struct afs_volume *volume; /* Volume being accessed */ + struct afs_vnode_param file[2]; + struct afs_vnode_param *more_files; + struct afs_volsync volsync; + struct dentry *dentry; /* Dentry to be altered */ + struct dentry *dentry_2; /* Second dentry to be altered */ + struct timespec64 mtime; /* Modification time to record */ + short nr_files; /* Number of entries in file[], more_files */ + short error; + unsigned int abort_code; + unsigned int debug_id; + + unsigned int cb_v_break; /* Volume break counter before op */ + unsigned int cb_s_break; /* Server break counter before op */ + + union { + struct { + int which; /* Which ->file[] to fetch for */ + } fetch_status; + struct { + int reason; /* enum afs_edit_dir_reason */ + mode_t mode; + const char *symlink; + } create; + struct { + bool need_rehash; + } unlink; + struct { + struct dentry *rehash; + struct dentry *tmp; + bool new_negative; + } rename; + struct { + struct afs_read *req; + } fetch; + struct { + struct afs_vnode *lvnode; /* vnode being locked */ + afs_lock_type_t type; + } lock; + struct { + struct address_space *mapping; /* Pages being written from */ + pgoff_t first; /* first page in mapping to deal with */ + pgoff_t last; /* last page in mapping to deal with */ + unsigned first_offset; /* offset into mapping[first] */ + unsigned last_to; /* amount of mapping[last] */ + } store; + struct { + struct iattr *attr; + } setattr; + struct afs_acl *acl; + struct yfs_acl *yacl; + struct { + struct afs_volume_status vs; + struct kstatfs *buf; + } volstatus; + }; + + /* Fileserver iteration state */ struct afs_addr_cursor ac; - struct afs_vnode *vnode; struct afs_server_list *server_list; /* Current server list (pins ref) */ - struct afs_cb_interest *cbi; /* Server on which this resides (pins ref) */ - struct key *key; /* Key for the server */ + struct afs_server *server; /* Server we're using (ref pinned by server_list) */ + struct afs_call *call; unsigned long untried; /* Bitmask of untried servers */ - unsigned int cb_break; /* cb_break + cb_s_break before the call */ - unsigned int cb_break_2; /* cb_break + cb_s_break (2nd vnode) */ short index; /* Current server */ - short error; - unsigned short flags; -#define AFS_FS_CURSOR_STOP 0x0001 /* Set to cease iteration */ -#define AFS_FS_CURSOR_VBUSY 0x0002 /* Set if seen VBUSY */ -#define AFS_FS_CURSOR_VMOVED 0x0004 /* Set if seen VMOVED */ -#define AFS_FS_CURSOR_VNOVOL 0x0008 /* Set if seen VNOVOL */ -#define AFS_FS_CURSOR_CUR_ONLY 0x0010 /* Set if current server only (file lock held) */ -#define AFS_FS_CURSOR_NO_VSLEEP 0x0020 /* Set to prevent sleep on VBUSY, VOFFLINE, ... */ -#define AFS_FS_CURSOR_INTR 0x0040 /* Set if op is interruptible */ unsigned short nr_iterations; /* Number of server iterations */ + + unsigned int flags; +#define AFS_OPERATION_STOP 0x0001 /* Set to cease iteration */ +#define AFS_OPERATION_VBUSY 0x0002 /* Set if seen VBUSY */ +#define AFS_OPERATION_VMOVED 0x0004 /* Set if seen VMOVED */ +#define AFS_OPERATION_VNOVOL 0x0008 /* Set if seen VNOVOL */ +#define AFS_OPERATION_CUR_ONLY 0x0010 /* Set if current server only (file lock held) */ +#define AFS_OPERATION_NO_VSLEEP 0x0020 /* Set to prevent sleep on VBUSY, VOFFLINE, ... */ +#define AFS_OPERATION_UNINTR 0x0040 /* Set if op is uninterruptible */ +#define AFS_OPERATION_DOWNGRADE 0x0080 /* Set to retry with downgraded opcode */ +#define AFS_OPERATION_LOCK_0 0x0100 /* Set if have io_lock on file[0] */ +#define AFS_OPERATION_LOCK_1 0x0200 /* Set if have io_lock on file[1] */ +#define AFS_OPERATION_TRIED_ALL 0x0400 /* Set if we've tried all the fileservers */ +#define AFS_OPERATION_RETRY_SERVER 0x0800 /* Set if we should retry the current server */ }; /* @@ -838,29 +895,15 @@ extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break *); -extern int afs_register_server_cb_interest(struct afs_vnode *, - struct afs_server_list *, unsigned int); -extern void afs_put_cb_interest(struct afs_net *, struct afs_cb_interest *); -extern void afs_clear_callback_interests(struct afs_net *, struct afs_server_list *); - -static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest *cbi) -{ - if (cbi) - refcount_inc(&cbi->usage); - return cbi; -} - static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) { return vnode->cb_break + vnode->cb_v_break; } static inline bool afs_cb_is_broken(unsigned int cb_break, - const struct afs_vnode *vnode, - const struct afs_cb_interest *cbi) + const struct afs_vnode *vnode) { - return !cbi || cb_break != (vnode->cb_break + - vnode->volume->cb_v_break); + return cb_break != (vnode->cb_break + vnode->volume->cb_v_break); } /* @@ -952,71 +995,81 @@ extern int afs_flock(struct file *, int, struct file_lock *); /* * fsclient.c */ -extern int afs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_status_cb *, - struct afs_volsync *); -extern int afs_fs_give_up_callbacks(struct afs_net *, struct afs_server *); -extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_status_cb *, struct afs_read *); -extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, - struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); -extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, - struct afs_status_cb *); -extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, - struct afs_status_cb *, struct afs_status_cb *); -extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, - struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); -extern int afs_fs_rename(struct afs_fs_cursor *, const char *, - struct afs_vnode *, const char *, - struct afs_status_cb *, struct afs_status_cb *); -extern int afs_fs_store_data(struct afs_fs_cursor *, struct address_space *, - pgoff_t, pgoff_t, unsigned, unsigned, struct afs_status_cb *); -extern int afs_fs_setattr(struct afs_fs_cursor *, struct iattr *, struct afs_status_cb *); -extern int afs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); -extern int afs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t, struct afs_status_cb *); -extern int afs_fs_extend_lock(struct afs_fs_cursor *, struct afs_status_cb *); -extern int afs_fs_release_lock(struct afs_fs_cursor *, struct afs_status_cb *); +extern void afs_fs_fetch_status(struct afs_operation *); +extern void afs_fs_fetch_data(struct afs_operation *); +extern void afs_fs_create_file(struct afs_operation *); +extern void afs_fs_make_dir(struct afs_operation *); +extern void afs_fs_remove_file(struct afs_operation *); +extern void afs_fs_remove_dir(struct afs_operation *); +extern void afs_fs_link(struct afs_operation *); +extern void afs_fs_symlink(struct afs_operation *); +extern void afs_fs_rename(struct afs_operation *); +extern void afs_fs_store_data(struct afs_operation *); +extern void afs_fs_setattr(struct afs_operation *); +extern void afs_fs_get_volume_status(struct afs_operation *); +extern void afs_fs_set_lock(struct afs_operation *); +extern void afs_fs_extend_lock(struct afs_operation *); +extern void afs_fs_release_lock(struct afs_operation *); extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *, struct afs_addr_cursor *, struct key *); -extern struct afs_call *afs_fs_get_capabilities(struct afs_net *, struct afs_server *, - struct afs_addr_cursor *, struct key *, - unsigned int); -extern int afs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_status_cb *, - unsigned int, struct afs_volsync *); -extern int afs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_status_cb *, - struct afs_volsync *); +extern bool afs_fs_get_capabilities(struct afs_net *, struct afs_server *, + struct afs_addr_cursor *, struct key *); +extern void afs_fs_inline_bulk_status(struct afs_operation *); struct afs_acl { u32 size; u8 data[]; }; -extern struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *, struct afs_status_cb *); -extern int afs_fs_store_acl(struct afs_fs_cursor *, const struct afs_acl *, - struct afs_status_cb *); +extern void afs_fs_fetch_acl(struct afs_operation *); +extern void afs_fs_store_acl(struct afs_operation *); + +/* + * fs_operation.c + */ +extern struct afs_operation *afs_alloc_operation(struct key *, struct afs_volume *); +extern int afs_put_operation(struct afs_operation *); +extern bool afs_begin_vnode_operation(struct afs_operation *); +extern void afs_wait_for_operation(struct afs_operation *); +extern int afs_do_sync_operation(struct afs_operation *); + +static inline void afs_op_nomem(struct afs_operation *op) +{ + op->error = -ENOMEM; +} + +static inline void afs_op_set_vnode(struct afs_operation *op, unsigned int n, + struct afs_vnode *vnode) +{ + op->file[n].vnode = vnode; + op->file[n].need_io_lock = true; +} + +static inline void afs_op_set_fid(struct afs_operation *op, unsigned int n, + const struct afs_fid *fid) +{ + op->file[n].fid = *fid; +} /* * fs_probe.c */ extern void afs_fileserver_probe_result(struct afs_call *); -extern int afs_probe_fileservers(struct afs_net *, struct key *, struct afs_server_list *); +extern void afs_fs_probe_fileserver(struct afs_net *, struct afs_server *, struct key *, bool); extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long); +extern void afs_probe_fileserver(struct afs_net *, struct afs_server *); +extern void afs_fs_probe_dispatcher(struct work_struct *); +extern int afs_wait_for_one_fs_probe(struct afs_server *, bool); /* * inode.c */ -extern void afs_vnode_commit_status(struct afs_fs_cursor *, - struct afs_vnode *, - unsigned int, - const afs_dataversion_t *, - struct afs_status_cb *); +extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *); extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); -extern int afs_iget5_test(struct inode *, void *); +extern int afs_ilookup5_test_by_fid(struct inode *, void *); extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool); -extern struct inode *afs_iget(struct super_block *, struct key *, - struct afs_iget_data *, struct afs_status_cb *, - struct afs_cb_interest *, - struct afs_vnode *); +extern struct inode *afs_iget(struct afs_operation *, struct afs_vnode_param *); +extern struct inode *afs_root_iget(struct super_block *, struct key *); extern void afs_zap_data(struct afs_vnode *); extern bool afs_check_validity(struct afs_vnode *); extern int afs_validate(struct afs_vnode *, struct key *); @@ -1104,11 +1157,8 @@ static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {} /* * rotate.c */ -extern bool afs_begin_vnode_operation(struct afs_fs_cursor *, struct afs_vnode *, - struct key *, bool); -extern bool afs_select_fileserver(struct afs_fs_cursor *); -extern bool afs_select_current_fileserver(struct afs_fs_cursor *); -extern int afs_end_vnode_operation(struct afs_fs_cursor *); +extern bool afs_select_fileserver(struct afs_operation *); +extern void afs_dump_edestaddrreq(const struct afs_operation *); /* * rxrpc.c @@ -1128,12 +1178,17 @@ extern void afs_flat_call_destructor(struct afs_call *); extern void afs_send_empty_reply(struct afs_call *); extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, bool); -extern int afs_protocol_error(struct afs_call *, int, enum afs_eproto_cause); +extern int afs_protocol_error(struct afs_call *, enum afs_eproto_cause); -static inline void afs_set_fc_call(struct afs_call *call, struct afs_fs_cursor *fc) +static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *call, + gfp_t gfp) { - call->intr = fc->flags & AFS_FS_CURSOR_INTR; - fc->type = call->type; + op->call = call; + op->type = call->type; + call->op = op; + call->key = op->key; + call->intr = !(op->flags & AFS_OPERATION_UNINTR); + afs_make_call(&op->ac, call, gfp); } static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) @@ -1241,13 +1296,33 @@ extern spinlock_t afs_server_peer_lock; extern struct afs_server *afs_find_server(struct afs_net *, const struct sockaddr_rxrpc *); extern struct afs_server *afs_find_server_by_uuid(struct afs_net *, const uuid_t *); -extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *); +extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *, u32); extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace); +extern struct afs_server *afs_use_server(struct afs_server *, enum afs_server_trace); +extern void afs_unuse_server(struct afs_net *, struct afs_server *, enum afs_server_trace); +extern void afs_unuse_server_notime(struct afs_net *, struct afs_server *, enum afs_server_trace); extern void afs_put_server(struct afs_net *, struct afs_server *, enum afs_server_trace); extern void afs_manage_servers(struct work_struct *); extern void afs_servers_timer(struct timer_list *); +extern void afs_fs_probe_timer(struct timer_list *); extern void __net_exit afs_purge_servers(struct afs_net *); -extern bool afs_check_server_record(struct afs_fs_cursor *, struct afs_server *); +extern bool afs_check_server_record(struct afs_operation *, struct afs_server *); + +static inline void afs_inc_servers_outstanding(struct afs_net *net) +{ + atomic_inc(&net->servers_outstanding); +} + +static inline void afs_dec_servers_outstanding(struct afs_net *net) +{ + if (atomic_dec_and_test(&net->servers_outstanding)) + wake_up_var(&net->servers_outstanding); +} + +static inline bool afs_is_probing_server(struct afs_server *server) +{ + return list_empty(&server->probe_link); +} /* * server_list.c @@ -1279,6 +1354,12 @@ extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uu extern struct afs_call *afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, struct key *, struct afs_vlserver *, unsigned int); extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *); +extern char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *); + +/* + * vl_alias.c + */ +extern int afs_cell_detect_alias(struct afs_cell *, struct key *); /* * vl_probe.c @@ -1322,18 +1403,12 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, /* * volume.c */ -static inline struct afs_volume *__afs_get_volume(struct afs_volume *volume) -{ - if (volume) - atomic_inc(&volume->usage); - return volume; -} - extern struct afs_volume *afs_create_volume(struct afs_fs_context *); extern void afs_activate_volume(struct afs_volume *); extern void afs_deactivate_volume(struct afs_volume *); -extern void afs_put_volume(struct afs_cell *, struct afs_volume *); -extern int afs_check_volume_status(struct afs_volume *, struct afs_fs_cursor *); +extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace); +extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace); +extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); /* * write.c @@ -1362,36 +1437,24 @@ extern ssize_t afs_listxattr(struct dentry *, char *, size_t); /* * yfsclient.c */ -extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_status_cb *, - struct afs_volsync *); -extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_status_cb *, struct afs_read *); -extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, struct afs_status_cb *, - struct afs_fid *, struct afs_status_cb *); -extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, struct afs_status_cb *, - struct afs_fid *, struct afs_status_cb *); -extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, - struct afs_status_cb *, struct afs_status_cb *); -extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, - struct afs_status_cb *); -extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, - struct afs_status_cb *, struct afs_status_cb *); -extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, - struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); -extern int yfs_fs_rename(struct afs_fs_cursor *, const char *, struct afs_vnode *, const char *, - struct afs_status_cb *, struct afs_status_cb *); -extern int yfs_fs_store_data(struct afs_fs_cursor *, struct address_space *, - pgoff_t, pgoff_t, unsigned, unsigned, struct afs_status_cb *); -extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *, struct afs_status_cb *); -extern int yfs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); -extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t, struct afs_status_cb *); -extern int yfs_fs_extend_lock(struct afs_fs_cursor *, struct afs_status_cb *); -extern int yfs_fs_release_lock(struct afs_fs_cursor *, struct afs_status_cb *); -extern int yfs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_status_cb *, - struct afs_volsync *); -extern int yfs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_status_cb *, - unsigned int, struct afs_volsync *); +extern void yfs_fs_fetch_file_status(struct afs_operation *); +extern void yfs_fs_fetch_data(struct afs_operation *); +extern void yfs_fs_create_file(struct afs_operation *); +extern void yfs_fs_make_dir(struct afs_operation *); +extern void yfs_fs_remove_file2(struct afs_operation *); +extern void yfs_fs_remove_file(struct afs_operation *); +extern void yfs_fs_remove_dir(struct afs_operation *); +extern void yfs_fs_link(struct afs_operation *); +extern void yfs_fs_symlink(struct afs_operation *); +extern void yfs_fs_rename(struct afs_operation *); +extern void yfs_fs_store_data(struct afs_operation *); +extern void yfs_fs_setattr(struct afs_operation *); +extern void yfs_fs_get_volume_status(struct afs_operation *); +extern void yfs_fs_set_lock(struct afs_operation *); +extern void yfs_fs_extend_lock(struct afs_operation *); +extern void yfs_fs_release_lock(struct afs_operation *); +extern void yfs_fs_fetch_status(struct afs_operation *); +extern void yfs_fs_inline_bulk_status(struct afs_operation *); struct yfs_acl { struct afs_acl *acl; /* Dir/file/symlink ACL */ @@ -1404,10 +1467,8 @@ struct yfs_acl { }; extern void yfs_free_opaque_acl(struct yfs_acl *); -extern struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *, struct yfs_acl *, - struct afs_status_cb *); -extern int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *, const struct afs_acl *, - struct afs_status_cb *); +extern void yfs_fs_fetch_opaque_acl(struct afs_operation *); +extern void yfs_fs_store_opaque_acl2(struct afs_operation *); /* * Miscellaneous inline functions. @@ -1422,15 +1483,29 @@ static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode) return &vnode->vfs_inode; } -static inline void afs_check_for_remote_deletion(struct afs_fs_cursor *fc, +static inline void afs_check_for_remote_deletion(struct afs_operation *op, struct afs_vnode *vnode) { - if (fc->ac.error == -ENOENT) { + if (op->error == -ENOENT) { set_bit(AFS_VNODE_DELETED, &vnode->flags); afs_break_callback(vnode, afs_cb_break_for_deleted); } } +/* + * Note that a dentry got changed. We need to set d_fsdata to the data version + * number derived from the result of the operation. It doesn't matter if + * d_fsdata goes backwards as we'll just revalidate. + */ +static inline void afs_update_dentry_version(struct afs_operation *op, + struct afs_vnode_param *dir_vp, + struct dentry *dentry) +{ + if (!op->error) + dentry->d_fsdata = + (void *)(unsigned long)dir_vp->scb.status.data_version; +} + static inline int afs_io_error(struct afs_call *call, enum afs_io_error where) { trace_afs_io_error(call->debug_id, -EIO, where); diff --git a/fs/afs/main.c b/fs/afs/main.c index c9c45d7078bd..9c79c91e8005 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -82,12 +82,14 @@ static int __net_init afs_net_init(struct net *net_ns) INIT_WORK(&net->cells_manager, afs_manage_cells); timer_setup(&net->cells_timer, afs_cells_timer, 0); + mutex_init(&net->cells_alias_lock); mutex_init(&net->proc_cells_lock); INIT_HLIST_HEAD(&net->proc_cells); seqlock_init(&net->fs_lock); net->fs_servers = RB_ROOT; - INIT_LIST_HEAD(&net->fs_updates); + INIT_LIST_HEAD(&net->fs_probe_fast); + INIT_LIST_HEAD(&net->fs_probe_slow); INIT_HLIST_HEAD(&net->fs_proc); INIT_HLIST_HEAD(&net->fs_addresses4); @@ -96,6 +98,8 @@ static int __net_init afs_net_init(struct net *net_ns) INIT_WORK(&net->fs_manager, afs_manage_servers); timer_setup(&net->fs_timer, afs_servers_timer, 0); + INIT_WORK(&net->fs_prober, afs_fs_probe_dispatcher); + timer_setup(&net->fs_probe_timer, afs_fs_probe_timer, 0); ret = -ENOMEM; sysnames = kzalloc(sizeof(*sysnames), GFP_KERNEL); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 468e1713bce1..22d00cf1913d 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -38,7 +38,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) if (v == SEQ_START_TOKEN) { /* display header on line 1 */ - seq_puts(m, "USE TTL SV NAME\n"); + seq_puts(m, "USE TTL SV ST NAME\n"); return 0; } @@ -46,10 +46,11 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) vllist = rcu_dereference(cell->vl_servers); /* display one cell per line on subsequent lines */ - seq_printf(m, "%3u %6lld %2u %s\n", + seq_printf(m, "%3u %6lld %2u %2u %s\n", atomic_read(&cell->usage), cell->dns_expiry - ktime_get_real_seconds(), vllist->nr_servers, + cell->state, cell->name); return 0; } @@ -208,11 +209,10 @@ static const char afs_vol_types[3][3] = { */ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v) { - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); - struct afs_volume *vol = list_entry(v, struct afs_volume, proc_link); + struct afs_volume *vol = hlist_entry(v, struct afs_volume, proc_link); /* Display header on line 1 */ - if (v == &cell->proc_volumes) { + if (v == SEQ_START_TOKEN) { seq_puts(m, "USE VID TY NAME\n"); return 0; } @@ -230,8 +230,8 @@ static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos) { struct afs_cell *cell = PDE_DATA(file_inode(m->file)); - read_lock(&cell->proc_lock); - return seq_list_start_head(&cell->proc_volumes, *_pos); + 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, @@ -239,15 +239,13 @@ static void *afs_proc_cell_volumes_next(struct seq_file *m, void *v, { struct afs_cell *cell = PDE_DATA(file_inode(m->file)); - return seq_list_next(v, &cell->proc_volumes, _pos); + return seq_hlist_next_rcu(v, &cell->proc_volumes, _pos); } static void afs_proc_cell_volumes_stop(struct seq_file *m, void *v) __releases(cell->proc_lock) { - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); - - read_unlock(&cell->proc_lock); + rcu_read_unlock(); } static const struct seq_operations afs_proc_cell_volumes_ops = { @@ -378,20 +376,26 @@ static int afs_proc_servers_show(struct seq_file *m, void *v) int i; if (v == SEQ_START_TOKEN) { - seq_puts(m, "UUID USE ADDR\n"); + 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 %pISpc%s\n", + seq_printf(m, "%pU %3d %3d\n", &server->uuid, - atomic_read(&server->usage), - &alist->addrs[0].transport, - alist->preferred == 0 ? "*" : ""); - for (i = 1; i < alist->nr_addrs; i++) - seq_printf(m, " %pISpc%s\n", - &alist->addrs[i].transport, + atomic_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; } diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h index 32be9c698348..b5bd03b1d3c7 100644 --- a/fs/afs/protocol_yfs.h +++ b/fs/afs/protocol_yfs.h @@ -8,7 +8,7 @@ #define YFS_FS_SERVICE 2500 #define YFS_CM_SERVICE 2501 -#define YFSCBMAX 1024 +#define YFSCBMAX 1024 enum YFS_CM_Operations { YFSCBProbe = 206, /* probe client */ diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 2a3305e42b14..6a0935cb822f 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -15,60 +15,32 @@ #include "afs_fs.h" /* - * Begin an operation on the fileserver. - * - * Fileserver operations are serialised on the server by vnode, so we serialise - * them here also using the io_lock. - */ -bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - struct key *key, bool intr) -{ - memset(fc, 0, sizeof(*fc)); - fc->vnode = vnode; - fc->key = key; - fc->ac.error = SHRT_MAX; - fc->error = -EDESTADDRREQ; - - if (intr) { - fc->flags |= AFS_FS_CURSOR_INTR; - if (mutex_lock_interruptible(&vnode->io_lock) < 0) { - fc->error = -EINTR; - fc->flags |= AFS_FS_CURSOR_STOP; - return false; - } - } else { - mutex_lock(&vnode->io_lock); - } - - if (vnode->lock_state != AFS_VNODE_LOCK_NONE) - fc->flags |= AFS_FS_CURSOR_CUR_ONLY; - return true; -} - -/* * Begin iteration through a server list, starting with the vnode's last used * server if possible, or the last recorded good server if not. */ -static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, +static bool afs_start_fs_iteration(struct afs_operation *op, struct afs_vnode *vnode) { - struct afs_cb_interest *cbi; + struct afs_server *server; + void *cb_server; int i; - read_lock(&vnode->volume->servers_lock); - fc->server_list = afs_get_serverlist(vnode->volume->servers); - read_unlock(&vnode->volume->servers_lock); + read_lock(&op->volume->servers_lock); + op->server_list = afs_get_serverlist( + rcu_dereference_protected(op->volume->servers, + lockdep_is_held(&op->volume->servers_lock))); + read_unlock(&op->volume->servers_lock); - fc->untried = (1UL << fc->server_list->nr_servers) - 1; - fc->index = READ_ONCE(fc->server_list->preferred); + op->untried = (1UL << op->server_list->nr_servers) - 1; + op->index = READ_ONCE(op->server_list->preferred); - cbi = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->io_lock)); - if (cbi) { + cb_server = vnode->cb_server; + if (cb_server) { /* See if the vnode's preferred record is still available */ - for (i = 0; i < fc->server_list->nr_servers; i++) { - if (fc->server_list->servers[i].cb_interest == cbi) { - fc->index = i; + for (i = 0; i < op->server_list->nr_servers; i++) { + server = op->server_list->servers[i].server; + if (server == cb_server) { + op->index = i; goto found_interest; } } @@ -77,21 +49,18 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, * serving this vnode, then we can't switch to another server * and have to return an error. */ - if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) { - fc->error = -ESTALE; + if (op->flags & AFS_OPERATION_CUR_ONLY) { + op->error = -ESTALE; return false; } /* Note that the callback promise is effectively broken */ write_seqlock(&vnode->cb_lock); - ASSERTCMP(cbi, ==, rcu_access_pointer(vnode->cb_interest)); - rcu_assign_pointer(vnode->cb_interest, NULL); + ASSERTCMP(cb_server, ==, vnode->cb_server); + vnode->cb_server = NULL; if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) vnode->cb_break++; write_sequnlock(&vnode->cb_lock); - - afs_put_cb_interest(afs_v2net(vnode), cbi); - cbi = NULL; } found_interest: @@ -118,12 +87,12 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code) /* * Sleep and retry the operation to the same fileserver. */ -static bool afs_sleep_and_retry(struct afs_fs_cursor *fc) +static bool afs_sleep_and_retry(struct afs_operation *op) { - if (fc->flags & AFS_FS_CURSOR_INTR) { + if (!(op->flags & AFS_OPERATION_UNINTR)) { msleep_interruptible(1000); if (signal_pending(current)) { - fc->error = -ERESTARTSYS; + op->error = -ERESTARTSYS; return false; } } else { @@ -137,26 +106,26 @@ static bool afs_sleep_and_retry(struct afs_fs_cursor *fc) * Select the fileserver to use. May be called multiple times to rotate * through the fileservers. */ -bool afs_select_fileserver(struct afs_fs_cursor *fc) +bool afs_select_fileserver(struct afs_operation *op) { struct afs_addr_list *alist; struct afs_server *server; - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *vnode = op->file[0].vnode; struct afs_error e; u32 rtt; - int error = fc->ac.error, i; + int error = op->ac.error, i; _enter("%lx[%d],%lx[%d],%d,%d", - fc->untried, fc->index, - fc->ac.tried, fc->ac.index, - error, fc->ac.abort_code); + op->untried, op->index, + op->ac.tried, op->ac.index, + error, op->ac.abort_code); - if (fc->flags & AFS_FS_CURSOR_STOP) { + if (op->flags & AFS_OPERATION_STOP) { _leave(" = f [stopped]"); return false; } - fc->nr_iterations++; + op->nr_iterations++; /* Evaluate the result of the previous operation, if there was one. */ switch (error) { @@ -166,8 +135,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) case 0: default: /* Success or local failure. Stop. */ - fc->error = error; - fc->flags |= AFS_FS_CURSOR_STOP; + op->error = error; + op->flags |= AFS_OPERATION_STOP; _leave(" = f [okay/local %d]", error); return false; @@ -175,42 +144,42 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) /* The far side rejected the operation on some grounds. This * might involve the server being busy or the volume having been moved. */ - switch (fc->ac.abort_code) { + switch (op->ac.abort_code) { case VNOVOL: /* This fileserver doesn't know about the volume. * - May indicate that the VL is wrong - retry once and compare * the results. * - May indicate that the fileserver couldn't attach to the vol. */ - if (fc->flags & AFS_FS_CURSOR_VNOVOL) { - fc->error = -EREMOTEIO; + if (op->flags & AFS_OPERATION_VNOVOL) { + op->error = -EREMOTEIO; goto next_server; } - write_lock(&vnode->volume->servers_lock); - fc->server_list->vnovol_mask |= 1 << fc->index; - write_unlock(&vnode->volume->servers_lock); + write_lock(&op->volume->servers_lock); + op->server_list->vnovol_mask |= 1 << op->index; + write_unlock(&op->volume->servers_lock); - set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags); - error = afs_check_volume_status(vnode->volume, fc); + set_bit(AFS_VOLUME_NEEDS_UPDATE, &op->volume->flags); + error = afs_check_volume_status(op->volume, op); if (error < 0) goto failed_set_error; - if (test_bit(AFS_VOLUME_DELETED, &vnode->volume->flags)) { - fc->error = -ENOMEDIUM; + if (test_bit(AFS_VOLUME_DELETED, &op->volume->flags)) { + op->error = -ENOMEDIUM; goto failed; } /* If the server list didn't change, then assume that * it's the fileserver having trouble. */ - if (vnode->volume->servers == fc->server_list) { - fc->error = -EREMOTEIO; + if (rcu_access_pointer(op->volume->servers) == op->server_list) { + op->error = -EREMOTEIO; goto next_server; } /* Try again */ - fc->flags |= AFS_FS_CURSOR_VNOVOL; + op->flags |= AFS_OPERATION_VNOVOL; _leave(" = t [vnovol]"); return true; @@ -220,20 +189,20 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) case VONLINE: case VDISKFULL: case VOVERQUOTA: - fc->error = afs_abort_to_error(fc->ac.abort_code); + op->error = afs_abort_to_error(op->ac.abort_code); goto next_server; case VOFFLINE: - if (!test_and_set_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags)) { - afs_busy(vnode->volume, fc->ac.abort_code); - clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags); + if (!test_and_set_bit(AFS_VOLUME_OFFLINE, &op->volume->flags)) { + afs_busy(op->volume, op->ac.abort_code); + clear_bit(AFS_VOLUME_BUSY, &op->volume->flags); } - if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) { - fc->error = -EADV; + if (op->flags & AFS_OPERATION_NO_VSLEEP) { + op->error = -EADV; goto failed; } - if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) { - fc->error = -ESTALE; + if (op->flags & AFS_OPERATION_CUR_ONLY) { + op->error = -ESTALE; goto failed; } goto busy; @@ -244,17 +213,17 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) /* Retry after going round all the servers unless we * have a file lock we need to maintain. */ - if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) { - fc->error = -EBUSY; + if (op->flags & AFS_OPERATION_NO_VSLEEP) { + op->error = -EBUSY; goto failed; } - if (!test_and_set_bit(AFS_VOLUME_BUSY, &vnode->volume->flags)) { - afs_busy(vnode->volume, fc->ac.abort_code); - clear_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags); + if (!test_and_set_bit(AFS_VOLUME_BUSY, &op->volume->flags)) { + afs_busy(op->volume, op->ac.abort_code); + clear_bit(AFS_VOLUME_OFFLINE, &op->volume->flags); } busy: - if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) { - if (!afs_sleep_and_retry(fc)) + if (op->flags & AFS_OPERATION_CUR_ONLY) { + if (!afs_sleep_and_retry(op)) goto failed; /* Retry with same server & address */ @@ -262,7 +231,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) return true; } - fc->flags |= AFS_FS_CURSOR_VBUSY; + op->flags |= AFS_OPERATION_VBUSY; goto next_server; case VMOVED: @@ -273,15 +242,15 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * We also limit the number of VMOVED hops we will * honour, just in case someone sets up a loop. */ - if (fc->flags & AFS_FS_CURSOR_VMOVED) { - fc->error = -EREMOTEIO; + if (op->flags & AFS_OPERATION_VMOVED) { + op->error = -EREMOTEIO; goto failed; } - fc->flags |= AFS_FS_CURSOR_VMOVED; + op->flags |= AFS_OPERATION_VMOVED; - set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags); - set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags); - error = afs_check_volume_status(vnode->volume, fc); + set_bit(AFS_VOLUME_WAIT, &op->volume->flags); + set_bit(AFS_VOLUME_NEEDS_UPDATE, &op->volume->flags); + error = afs_check_volume_status(op->volume, op); if (error < 0) goto failed_set_error; @@ -294,23 +263,23 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * * TODO: Retry a few times with sleeps. */ - if (vnode->volume->servers == fc->server_list) { - fc->error = -ENOMEDIUM; + if (rcu_access_pointer(op->volume->servers) == op->server_list) { + op->error = -ENOMEDIUM; goto failed; } goto restart_from_beginning; default: - clear_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags); - clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags); - fc->error = afs_abort_to_error(fc->ac.abort_code); + clear_bit(AFS_VOLUME_OFFLINE, &op->volume->flags); + clear_bit(AFS_VOLUME_BUSY, &op->volume->flags); + op->error = afs_abort_to_error(op->ac.abort_code); goto failed; } case -ETIMEDOUT: case -ETIME: - if (fc->error != -EDESTADDRREQ) + if (op->error != -EDESTADDRREQ) goto iterate_address; /* Fall through */ case -ERFKILL: @@ -320,103 +289,94 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) case -EHOSTDOWN: case -ECONNREFUSED: _debug("no conn"); - fc->error = error; + op->error = error; goto iterate_address; case -ECONNRESET: _debug("call reset"); - fc->error = error; + op->error = error; goto failed; } restart_from_beginning: _debug("restart"); - afs_end_cursor(&fc->ac); - afs_put_cb_interest(afs_v2net(vnode), fc->cbi); - fc->cbi = NULL; - afs_put_serverlist(afs_v2net(vnode), fc->server_list); - fc->server_list = NULL; + afs_end_cursor(&op->ac); + op->server = NULL; + afs_put_serverlist(op->net, op->server_list); + op->server_list = NULL; start: _debug("start"); /* See if we need to do an update of the volume record. Note that the * volume may have moved or even have been deleted. */ - error = afs_check_volume_status(vnode->volume, fc); + error = afs_check_volume_status(op->volume, op); if (error < 0) goto failed_set_error; - if (!afs_start_fs_iteration(fc, vnode)) + if (!afs_start_fs_iteration(op, vnode)) goto failed; - _debug("__ VOL %llx __", vnode->volume->vid); - error = afs_probe_fileservers(afs_v2net(vnode), fc->key, fc->server_list); - if (error < 0) - goto failed_set_error; + _debug("__ VOL %llx __", op->volume->vid); pick_server: - _debug("pick [%lx]", fc->untried); + _debug("pick [%lx]", op->untried); - error = afs_wait_for_fs_probes(fc->server_list, fc->untried); + error = afs_wait_for_fs_probes(op->server_list, op->untried); if (error < 0) goto failed_set_error; /* Pick the untried server with the lowest RTT. If we have outstanding * callbacks, we stick with the server we're already using if we can. */ - if (fc->cbi) { - _debug("cbi %u", fc->index); - if (test_bit(fc->index, &fc->untried)) + if (op->server) { + _debug("server %u", op->index); + if (test_bit(op->index, &op->untried)) goto selected_server; - afs_put_cb_interest(afs_v2net(vnode), fc->cbi); - fc->cbi = NULL; - _debug("nocbi"); + op->server = NULL; + _debug("no server"); } - fc->index = -1; + op->index = -1; rtt = U32_MAX; - for (i = 0; i < fc->server_list->nr_servers; i++) { - struct afs_server *s = fc->server_list->servers[i].server; + for (i = 0; i < op->server_list->nr_servers; i++) { + struct afs_server *s = op->server_list->servers[i].server; - if (!test_bit(i, &fc->untried) || !s->probe.responded) + if (!test_bit(i, &op->untried) || + !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags)) continue; if (s->probe.rtt < rtt) { - fc->index = i; + op->index = i; rtt = s->probe.rtt; } } - if (fc->index == -1) + if (op->index == -1) goto no_more_servers; selected_server: - _debug("use %d", fc->index); - __clear_bit(fc->index, &fc->untried); + _debug("use %d", op->index); + __clear_bit(op->index, &op->untried); /* We're starting on a different fileserver from the list. We need to * check it, create a callback intercept, find its address list and * probe its capabilities before we use it. */ - ASSERTCMP(fc->ac.alist, ==, NULL); - server = fc->server_list->servers[fc->index].server; + ASSERTCMP(op->ac.alist, ==, NULL); + server = op->server_list->servers[op->index].server; - if (!afs_check_server_record(fc, server)) + if (!afs_check_server_record(op, server)) goto failed; _debug("USING SERVER: %pU", &server->uuid); - /* Make sure we've got a callback interest record for this server. We - * have to link it in before we send the request as we can be sent a - * break request before we've finished decoding the reply and - * installing the vnode. - */ - error = afs_register_server_cb_interest(vnode, fc->server_list, - fc->index); - if (error < 0) - goto failed_set_error; - - fc->cbi = afs_get_cb_interest( - rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->io_lock))); + op->flags |= AFS_OPERATION_RETRY_SERVER; + op->server = server; + if (vnode->cb_server != server) { + vnode->cb_server = server; + vnode->cb_s_break = server->cb_s_break; + vnode->cb_v_break = vnode->volume->cb_v_break; + clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } read_lock(&server->fs_lock); alist = rcu_dereference_protected(server->addresses, @@ -424,44 +384,68 @@ selected_server: afs_get_addrlist(alist); read_unlock(&server->fs_lock); - memset(&fc->ac, 0, sizeof(fc->ac)); +retry_server: + memset(&op->ac, 0, sizeof(op->ac)); - if (!fc->ac.alist) - fc->ac.alist = alist; + if (!op->ac.alist) + op->ac.alist = alist; else afs_put_addrlist(alist); - fc->ac.index = -1; + op->ac.index = -1; iterate_address: - ASSERT(fc->ac.alist); + ASSERT(op->ac.alist); /* Iterate over the current server's address list to try and find an * address on which it will respond to us. */ - if (!afs_iterate_addresses(&fc->ac)) - goto next_server; + if (!afs_iterate_addresses(&op->ac)) + goto out_of_addresses; - _debug("address [%u] %u/%u", fc->index, fc->ac.index, fc->ac.alist->nr_addrs); + _debug("address [%u] %u/%u %pISp", + op->index, op->ac.index, op->ac.alist->nr_addrs, + &op->ac.alist->addrs[op->ac.index].transport); _leave(" = t"); return true; +out_of_addresses: + /* We've now had a failure to respond on all of a server's addresses - + * immediately probe them again and consider retrying the server. + */ + afs_probe_fileserver(op->net, op->server); + if (op->flags & AFS_OPERATION_RETRY_SERVER) { + alist = op->ac.alist; + error = afs_wait_for_one_fs_probe( + op->server, !(op->flags & AFS_OPERATION_UNINTR)); + switch (error) { + case 0: + op->flags &= ~AFS_OPERATION_RETRY_SERVER; + goto retry_server; + case -ERESTARTSYS: + goto failed_set_error; + case -ETIME: + case -EDESTADDRREQ: + goto next_server; + } + } + next_server: _debug("next"); - afs_end_cursor(&fc->ac); + afs_end_cursor(&op->ac); goto pick_server; no_more_servers: /* That's all the servers poked to no good effect. Try again if some * of them were busy. */ - if (fc->flags & AFS_FS_CURSOR_VBUSY) + if (op->flags & AFS_OPERATION_VBUSY) goto restart_from_beginning; e.error = -EDESTADDRREQ; e.responded = false; - for (i = 0; i < fc->server_list->nr_servers; i++) { - struct afs_server *s = fc->server_list->servers[i].server; + for (i = 0; i < op->server_list->nr_servers; i++) { + struct afs_server *s = op->server_list->servers[i].server; afs_prioritise_error(&e, READ_ONCE(s->probe.error), s->probe.abort_code); @@ -470,101 +454,18 @@ no_more_servers: error = e.error; failed_set_error: - fc->error = error; + op->error = error; failed: - fc->flags |= AFS_FS_CURSOR_STOP; - afs_end_cursor(&fc->ac); - _leave(" = f [failed %d]", fc->error); - return false; -} - -/* - * Select the same fileserver we used for a vnode before and only that - * fileserver. We use this when we have a lock on that file, which is backed - * only by the fileserver we obtained it from. - */ -bool afs_select_current_fileserver(struct afs_fs_cursor *fc) -{ - struct afs_vnode *vnode = fc->vnode; - struct afs_cb_interest *cbi; - struct afs_addr_list *alist; - int error = fc->ac.error; - - _enter(""); - - cbi = rcu_dereference_protected(vnode->cb_interest, - lockdep_is_held(&vnode->io_lock)); - - switch (error) { - case SHRT_MAX: - if (!cbi) { - fc->error = -ESTALE; - fc->flags |= AFS_FS_CURSOR_STOP; - return false; - } - - fc->cbi = afs_get_cb_interest(cbi); - - read_lock(&cbi->server->fs_lock); - alist = rcu_dereference_protected(cbi->server->addresses, - lockdep_is_held(&cbi->server->fs_lock)); - afs_get_addrlist(alist); - read_unlock(&cbi->server->fs_lock); - if (!alist) { - fc->error = -ESTALE; - fc->flags |= AFS_FS_CURSOR_STOP; - return false; - } - - memset(&fc->ac, 0, sizeof(fc->ac)); - fc->ac.alist = alist; - fc->ac.index = -1; - goto iterate_address; - - case 0: - default: - /* Success or local failure. Stop. */ - fc->error = error; - fc->flags |= AFS_FS_CURSOR_STOP; - _leave(" = f [okay/local %d]", error); - return false; - - case -ECONNABORTED: - fc->error = afs_abort_to_error(fc->ac.abort_code); - fc->flags |= AFS_FS_CURSOR_STOP; - _leave(" = f [abort]"); - return false; - - case -ERFKILL: - case -EADDRNOTAVAIL: - case -ENETUNREACH: - case -EHOSTUNREACH: - case -EHOSTDOWN: - case -ECONNREFUSED: - case -ETIMEDOUT: - case -ETIME: - _debug("no conn"); - fc->error = error; - goto iterate_address; - } - -iterate_address: - /* Iterate over the current server's address list to try and find an - * address on which it will respond to us. - */ - if (afs_iterate_addresses(&fc->ac)) { - _leave(" = t"); - return true; - } - - afs_end_cursor(&fc->ac); + op->flags |= AFS_OPERATION_STOP; + afs_end_cursor(&op->ac); + _leave(" = f [failed %d]", op->error); return false; } /* * Dump cursor state in the case of the error being EDESTADDRREQ. */ -static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc) +void afs_dump_edestaddrreq(const struct afs_operation *op) { static int count; int i; @@ -576,13 +477,14 @@ static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc) rcu_read_lock(); pr_notice("EDESTADDR occurred\n"); - pr_notice("FC: cbb=%x cbb2=%x fl=%hx err=%hd\n", - fc->cb_break, fc->cb_break_2, fc->flags, fc->error); + pr_notice("FC: cbb=%x cbb2=%x fl=%x err=%hd\n", + op->file[0].cb_break_before, + op->file[1].cb_break_before, op->flags, op->error); pr_notice("FC: ut=%lx ix=%d ni=%u\n", - fc->untried, fc->index, fc->nr_iterations); + op->untried, op->index, op->nr_iterations); - if (fc->server_list) { - const struct afs_server_list *sl = fc->server_list; + if (op->server_list) { + const struct afs_server_list *sl = op->server_list; pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n", sl->nr_servers, sl->preferred, sl->vnovol_mask); for (i = 0; i < sl->nr_servers; i++) { @@ -596,41 +498,16 @@ static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc) a->version, a->nr_ipv4, a->nr_addrs, a->max_addrs, a->preferred); - pr_notice("FC: - pr=%lx R=%lx F=%lx\n", - a->probed, a->responded, a->failed); - if (a == fc->ac.alist) + pr_notice("FC: - R=%lx F=%lx\n", + a->responded, a->failed); + if (a == op->ac.alist) pr_notice("FC: - current\n"); } } } pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n", - fc->ac.tried, fc->ac.index, fc->ac.abort_code, fc->ac.error, - fc->ac.responded, fc->ac.nr_iterations); + op->ac.tried, op->ac.index, op->ac.abort_code, op->ac.error, + op->ac.responded, op->ac.nr_iterations); rcu_read_unlock(); } - -/* - * Tidy up a filesystem cursor and unlock the vnode. - */ -int afs_end_vnode_operation(struct afs_fs_cursor *fc) -{ - struct afs_net *net = afs_v2net(fc->vnode); - - if (fc->error == -EDESTADDRREQ || - fc->error == -EADDRNOTAVAIL || - fc->error == -ENETUNREACH || - fc->error == -EHOSTUNREACH) - afs_dump_edestaddrreq(fc); - - mutex_unlock(&fc->vnode->io_lock); - - afs_end_cursor(&fc->ac); - afs_put_cb_interest(net, fc->cbi); - afs_put_serverlist(net, fc->server_list); - - if (fc->error == -ECONNABORTED) - fc->error = afs_abort_to_error(fc->ac.abort_code); - - return fc->error; -} diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index e313dae01674..8fc8fb406a5a 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -181,8 +181,7 @@ void afs_put_call(struct afs_call *call) if (call->type->destructor) call->type->destructor(call); - afs_put_server(call->net, call->server, afs_server_trace_put_call); - afs_put_cb_interest(call->net, call->cbi); + afs_unuse_server_notime(call->net, call->server, afs_server_trace_put_call); afs_put_addrlist(call->alist); kfree(call->request); @@ -281,18 +280,19 @@ static void afs_load_bvec(struct afs_call *call, struct msghdr *msg, struct bio_vec *bv, pgoff_t first, pgoff_t last, unsigned offset) { + struct afs_operation *op = call->op; struct page *pages[AFS_BVEC_MAX]; unsigned int nr, n, i, to, bytes = 0; nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX); - n = find_get_pages_contig(call->mapping, first, nr, pages); + n = find_get_pages_contig(op->store.mapping, first, nr, pages); ASSERTCMP(n, ==, nr); msg->msg_flags |= MSG_MORE; for (i = 0; i < nr; i++) { to = PAGE_SIZE; if (first + i >= last) { - to = call->last_to; + to = op->store.last_to; msg->msg_flags &= ~MSG_MORE; } bv[i].bv_page = pages[i]; @@ -322,13 +322,14 @@ static void afs_notify_end_request_tx(struct sock *sock, */ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) { + struct afs_operation *op = call->op; struct bio_vec bv[AFS_BVEC_MAX]; unsigned int bytes, nr, loop, offset; - pgoff_t first = call->first, last = call->last; + pgoff_t first = op->store.first, last = op->store.last; int ret; - offset = call->first_offset; - call->first_offset = 0; + offset = op->store.first_offset; + op->store.first_offset = 0; do { afs_load_bvec(call, msg, bv, first, last, offset); @@ -338,7 +339,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) bytes = msg->msg_iter.count; nr = msg->msg_iter.nr_segs; - ret = rxrpc_kernel_send_data(call->net->socket, call->rxcall, msg, + ret = rxrpc_kernel_send_data(op->net->socket, call->rxcall, msg, bytes, afs_notify_end_request_tx); for (loop = 0; loop < nr; loop++) put_page(bv[loop].bv_page); @@ -348,7 +349,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) first += nr; } while (first <= last); - trace_afs_sent_pages(call, call->first, last, first, ret); + trace_afs_sent_pages(call, op->store.first, last, first, ret); return ret; } @@ -383,16 +384,18 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) */ tx_total_len = call->request_size; if (call->send_pages) { - if (call->last == call->first) { - tx_total_len += call->last_to - call->first_offset; + struct afs_operation *op = call->op; + + if (op->store.last == op->store.first) { + tx_total_len += op->store.last_to - op->store.first_offset; } else { /* It looks mathematically like you should be able to * combine the following lines with the ones above, but * unsigned arithmetic is fun when it wraps... */ - tx_total_len += PAGE_SIZE - call->first_offset; - tx_total_len += call->last_to; - tx_total_len += (call->last - call->first - 1) * PAGE_SIZE; + tx_total_len += PAGE_SIZE - op->store.first_offset; + tx_total_len += op->store.last_to; + tx_total_len += (op->store.last - op->store.first - 1) * PAGE_SIZE; } } @@ -538,13 +541,15 @@ static void afs_deliver_to_call(struct afs_call *call) ret = call->type->deliver(call); state = READ_ONCE(call->state); + if (ret == 0 && call->unmarshalling_error) + ret = -EBADMSG; switch (ret) { case 0: afs_queue_call_work(call); if (state == AFS_CALL_CL_PROC_REPLY) { - if (call->cbi) + if (call->op) set_bit(AFS_SERVER_FL_MAY_HAVE_CB, - &call->cbi->server->flags); + &call->op->server->flags); goto call_complete; } ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY); @@ -957,9 +962,11 @@ int afs_extract_data(struct afs_call *call, bool want_more) /* * Log protocol error production. */ -noinline int afs_protocol_error(struct afs_call *call, int error, +noinline int afs_protocol_error(struct afs_call *call, enum afs_eproto_cause cause) { - trace_afs_protocol_error(call, error, cause); - return error; + trace_afs_protocol_error(call, cause); + if (call) + call->unmarshalling_error = true; + return -EBADMSG; } diff --git a/fs/afs/security.c b/fs/afs/security.c index ce9de1e6742b..90d852704328 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -170,8 +170,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, break; } - if (afs_cb_is_broken(cb_break, vnode, - rcu_dereference(vnode->cb_interest))) { + if (afs_cb_is_broken(cb_break, vnode)) { changed = true; break; } @@ -201,7 +200,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } } - if (afs_cb_is_broken(cb_break, vnode, rcu_dereference(vnode->cb_interest))) + if (afs_cb_is_broken(cb_break, vnode)) goto someone_else_changed_it; /* We need a ref on any permits list we want to copy as we'll have to @@ -281,8 +280,7 @@ found: rcu_read_lock(); spin_lock(&vnode->lock); zap = rcu_access_pointer(vnode->permit_cache); - if (!afs_cb_is_broken(cb_break, vnode, rcu_dereference(vnode->cb_interest)) && - zap == permits) + if (!afs_cb_is_broken(cb_break, vnode) && zap == permits) rcu_assign_pointer(vnode->permit_cache, replacement); else zap = replacement; diff --git a/fs/afs/server.c b/fs/afs/server.c index 11b90ac7ea30..039e3488511c 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -12,19 +12,11 @@ #include "protocol_yfs.h" static unsigned afs_server_gc_delay = 10; /* Server record timeout in seconds */ -static unsigned afs_server_update_delay = 30; /* Time till VLDB recheck in secs */ static atomic_t afs_server_debug_id; -static void afs_inc_servers_outstanding(struct afs_net *net) -{ - atomic_inc(&net->servers_outstanding); -} - -static void afs_dec_servers_outstanding(struct afs_net *net) -{ - if (atomic_dec_and_test(&net->servers_outstanding)) - wake_up_var(&net->servers_outstanding); -} +static struct afs_server *afs_maybe_use_server(struct afs_server *, + enum afs_server_trace); +static void __afs_put_server(struct afs_net *, struct afs_server *); /* * Find a server by one of its addresses. @@ -41,7 +33,7 @@ struct afs_server *afs_find_server(struct afs_net *net, do { if (server) - afs_put_server(net, server, afs_server_trace_put_find_rsq); + afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq); server = NULL; read_seqbegin_or_lock(&net->fs_addr_lock, &seq); @@ -79,9 +71,9 @@ struct afs_server *afs_find_server(struct afs_net *net, } server = NULL; + continue; found: - if (server && !atomic_inc_not_zero(&server->usage)) - server = NULL; + server = afs_maybe_use_server(server, afs_server_trace_get_by_addr); } while (need_seqretry(&net->fs_addr_lock, seq)); @@ -92,7 +84,7 @@ struct afs_server *afs_find_server(struct afs_net *net, } /* - * Look up a server by its UUID + * Look up a server by its UUID and mark it active. */ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uuid) { @@ -108,7 +100,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu * changes. */ if (server) - afs_put_server(net, server, afs_server_trace_put_uuid_rsq); + afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; read_seqbegin_or_lock(&net->fs_lock, &seq); @@ -123,7 +115,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu } else if (diff > 0) { p = p->rb_right; } else { - afs_get_server(server, afs_server_trace_get_by_uuid); + afs_use_server(server, afs_server_trace_get_by_uuid); break; } @@ -138,13 +130,16 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu } /* - * Install a server record in the namespace tree + * Install a server record in the namespace tree. If there's a clash, we stick + * it into a list anchored on whichever afs_server struct is actually in the + * tree. */ -static struct afs_server *afs_install_server(struct afs_net *net, +static struct afs_server *afs_install_server(struct afs_cell *cell, struct afs_server *candidate) { const struct afs_addr_list *alist; - struct afs_server *server; + struct afs_server *server, *next; + struct afs_net *net = cell->net; struct rb_node **pp, *p; int diff; @@ -160,12 +155,30 @@ static struct afs_server *afs_install_server(struct afs_net *net, _debug("- consider %p", p); server = rb_entry(p, struct afs_server, uuid_rb); diff = memcmp(&candidate->uuid, &server->uuid, sizeof(uuid_t)); - if (diff < 0) + if (diff < 0) { pp = &(*pp)->rb_left; - else if (diff > 0) + } else if (diff > 0) { pp = &(*pp)->rb_right; - else - goto exists; + } else { + if (server->cell == cell) + goto exists; + + /* We have the same UUID representing servers in + * different cells. Append the new server to the list. + */ + for (;;) { + next = rcu_dereference_protected( + server->uuid_next, + lockdep_is_held(&net->fs_lock.lock)); + if (!next) + break; + server = next; + } + rcu_assign_pointer(server->uuid_next, candidate); + candidate->uuid_prev = server; + server = candidate; + goto added_dup; + } } server = candidate; @@ -173,6 +186,7 @@ static struct afs_server *afs_install_server(struct afs_net *net, rb_insert_color(&server->uuid_rb, &net->fs_servers); hlist_add_head_rcu(&server->proc_link, &net->fs_proc); +added_dup: write_seqlock(&net->fs_addr_lock); alist = rcu_dereference_protected(server->addresses, lockdep_is_held(&net->fs_addr_lock.lock)); @@ -199,13 +213,14 @@ exists: } /* - * allocate a new server record + * Allocate a new server record and mark it active. */ -static struct afs_server *afs_alloc_server(struct afs_net *net, +static struct afs_server *afs_alloc_server(struct afs_cell *cell, const uuid_t *uuid, struct afs_addr_list *alist) { struct afs_server *server; + struct afs_net *net = cell->net; _enter(""); @@ -213,20 +228,21 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, if (!server) goto enomem; - atomic_set(&server->usage, 1); + atomic_set(&server->ref, 1); + atomic_set(&server->active, 1); server->debug_id = atomic_inc_return(&afs_server_debug_id); RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; - server->update_at = ktime_get_real_seconds() + afs_server_update_delay; rwlock_init(&server->fs_lock); - INIT_HLIST_HEAD(&server->cb_volumes); - rwlock_init(&server->cb_break_lock); init_waitqueue_head(&server->probe_wq); + INIT_LIST_HEAD(&server->probe_link); spin_lock_init(&server->probe_lock); + server->cell = cell; + server->rtt = UINT_MAX; afs_inc_servers_outstanding(net); - trace_afs_server(server, 1, afs_server_trace_alloc); + trace_afs_server(server, 1, 1, afs_server_trace_alloc); _leave(" = %p", server); return server; @@ -264,7 +280,7 @@ static struct afs_addr_list *afs_vl_lookup_addrs(struct afs_cell *cell, * Get or create a fileserver record. */ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key, - const uuid_t *uuid) + const uuid_t *uuid, u32 addr_version) { struct afs_addr_list *alist; struct afs_server *server, *candidate; @@ -272,26 +288,34 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key, _enter("%p,%pU", cell->net, uuid); server = afs_find_server_by_uuid(cell->net, uuid); - if (server) + if (server) { + if (server->addr_version != addr_version) + set_bit(AFS_SERVER_FL_NEEDS_UPDATE, &server->flags); return server; + } alist = afs_vl_lookup_addrs(cell, key, uuid); if (IS_ERR(alist)) return ERR_CAST(alist); - candidate = afs_alloc_server(cell->net, uuid, alist); + candidate = afs_alloc_server(cell, uuid, alist); if (!candidate) { afs_put_addrlist(alist); return ERR_PTR(-ENOMEM); } - server = afs_install_server(cell->net, candidate); + server = afs_install_server(cell, candidate); if (server != candidate) { afs_put_addrlist(alist); kfree(candidate); + } else { + /* Immediately dispatch an asynchronous probe to each interface + * on the fileserver. This will make sure the repeat-probing + * service is started. + */ + afs_fs_probe_fileserver(cell->net, server, key, true); } - _leave(" = %p{%d}", server, atomic_read(&server->usage)); return server; } @@ -327,9 +351,38 @@ void afs_servers_timer(struct timer_list *timer) struct afs_server *afs_get_server(struct afs_server *server, enum afs_server_trace reason) { - unsigned int u = atomic_inc_return(&server->usage); + unsigned int u = atomic_inc_return(&server->ref); + + trace_afs_server(server, u, atomic_read(&server->active), reason); + return server; +} + +/* + * Try to get a reference on a server object. + */ +static struct afs_server *afs_maybe_use_server(struct afs_server *server, + enum afs_server_trace reason) +{ + unsigned int r = atomic_fetch_add_unless(&server->ref, 1, 0); + unsigned int a; + + if (r == 0) + return NULL; + + a = atomic_inc_return(&server->active); + trace_afs_server(server, r, a, reason); + return server; +} + +/* + * Get an active count on a server object. + */ +struct afs_server *afs_use_server(struct afs_server *server, enum afs_server_trace reason) +{ + unsigned int r = atomic_inc_return(&server->ref); + unsigned int a = atomic_inc_return(&server->active); - trace_afs_server(server, u, reason); + trace_afs_server(server, r, a, reason); return server; } @@ -344,32 +397,57 @@ void afs_put_server(struct afs_net *net, struct afs_server *server, if (!server) return; - server->put_time = ktime_get_real_seconds(); - - usage = atomic_dec_return(&server->usage); + usage = atomic_dec_return(&server->ref); + trace_afs_server(server, usage, atomic_read(&server->active), reason); + if (unlikely(usage == 0)) + __afs_put_server(net, server); +} - trace_afs_server(server, usage, reason); +/* + * Drop an active count on a server object without updating the last-unused + * time. + */ +void afs_unuse_server_notime(struct afs_net *net, struct afs_server *server, + enum afs_server_trace reason) +{ + if (server) { + unsigned int active = atomic_dec_return(&server->active); - if (likely(usage > 0)) - return; + if (active == 0) + afs_set_server_timer(net, afs_server_gc_delay); + afs_put_server(net, server, reason); + } +} - afs_set_server_timer(net, afs_server_gc_delay); +/* + * Drop an active count on a server object. + */ +void afs_unuse_server(struct afs_net *net, struct afs_server *server, + enum afs_server_trace reason) +{ + if (server) { + server->unuse_time = ktime_get_real_seconds(); + afs_unuse_server_notime(net, server, reason); + } } static void afs_server_rcu(struct rcu_head *rcu) { struct afs_server *server = container_of(rcu, struct afs_server, rcu); - trace_afs_server(server, atomic_read(&server->usage), - afs_server_trace_free); + trace_afs_server(server, atomic_read(&server->ref), + atomic_read(&server->active), afs_server_trace_free); afs_put_addrlist(rcu_access_pointer(server->addresses)); kfree(server); } -/* - * destroy a dead server - */ -static void afs_destroy_server(struct afs_net *net, struct afs_server *server) +static void __afs_put_server(struct afs_net *net, struct afs_server *server) +{ + call_rcu(&server->rcu, afs_server_rcu); + afs_dec_servers_outstanding(net); +} + +static void afs_give_up_callbacks(struct afs_net *net, struct afs_server *server) { struct afs_addr_list *alist = rcu_access_pointer(server->addresses); struct afs_addr_cursor ac = { @@ -378,19 +456,18 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) .error = 0, }; - trace_afs_server(server, atomic_read(&server->usage), - afs_server_trace_give_up_cb); + afs_fs_give_up_all_callbacks(net, server, &ac, NULL); +} +/* + * destroy a dead server + */ +static void afs_destroy_server(struct afs_net *net, struct afs_server *server) +{ if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags)) - afs_fs_give_up_all_callbacks(net, server, &ac, NULL); + afs_give_up_callbacks(net, server); - wait_var_event(&server->probe_outstanding, - atomic_read(&server->probe_outstanding) == 0); - - trace_afs_server(server, atomic_read(&server->usage), - afs_server_trace_destroy); - call_rcu(&server->rcu, afs_server_rcu); - afs_dec_servers_outstanding(net); + afs_put_server(net, server, afs_server_trace_destroy); } /* @@ -398,32 +475,49 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) */ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list) { - struct afs_server *server; - bool deleted; - int usage; + struct afs_server *server, *next, *prev; + int active; while ((server = gc_list)) { gc_list = server->gc_next; write_seqlock(&net->fs_lock); - usage = 1; - deleted = atomic_try_cmpxchg(&server->usage, &usage, 0); - trace_afs_server(server, usage, afs_server_trace_gc); - if (deleted) { - rb_erase(&server->uuid_rb, &net->fs_servers); - hlist_del_rcu(&server->proc_link); - } - write_sequnlock(&net->fs_lock); - if (deleted) { - write_seqlock(&net->fs_addr_lock); + active = atomic_read(&server->active); + if (active == 0) { + trace_afs_server(server, atomic_read(&server->ref), + active, afs_server_trace_gc); + next = rcu_dereference_protected( + server->uuid_next, lockdep_is_held(&net->fs_lock.lock)); + prev = server->uuid_prev; + if (!prev) { + /* The one at the front is in the tree */ + if (!next) { + rb_erase(&server->uuid_rb, &net->fs_servers); + } else { + rb_replace_node_rcu(&server->uuid_rb, + &next->uuid_rb, + &net->fs_servers); + next->uuid_prev = NULL; + } + } else { + /* This server is not at the front */ + rcu_assign_pointer(prev->uuid_next, next); + if (next) + next->uuid_prev = prev; + } + + list_del(&server->probe_link); + hlist_del_rcu(&server->proc_link); if (!hlist_unhashed(&server->addr4_link)) hlist_del_rcu(&server->addr4_link); if (!hlist_unhashed(&server->addr6_link)) hlist_del_rcu(&server->addr6_link); - write_sequnlock(&net->fs_addr_lock); - afs_destroy_server(net, server); } + write_sequnlock(&net->fs_lock); + + if (active == 0) + afs_destroy_server(net, server); } } @@ -452,15 +546,14 @@ void afs_manage_servers(struct work_struct *work) for (cursor = rb_first(&net->fs_servers); cursor; cursor = rb_next(cursor)) { struct afs_server *server = rb_entry(cursor, struct afs_server, uuid_rb); - int usage = atomic_read(&server->usage); + int active = atomic_read(&server->active); - _debug("manage %pU %u", &server->uuid, usage); + _debug("manage %pU %u", &server->uuid, active); - ASSERTCMP(usage, >=, 1); - ASSERTIFCMP(purging, usage, ==, 1); + ASSERTIFCMP(purging, active, ==, 0); - if (usage == 1) { - time64_t expire_at = server->put_time; + if (active == 0) { + time64_t expire_at = server->unuse_time; if (!test_bit(AFS_SERVER_FL_VL_FAIL, &server->flags) && !test_bit(AFS_SERVER_FL_NOT_FOUND, &server->flags)) @@ -525,26 +618,27 @@ void afs_purge_servers(struct afs_net *net) /* * Get an update for a server's address list. */ -static noinline bool afs_update_server_record(struct afs_fs_cursor *fc, struct afs_server *server) +static noinline bool afs_update_server_record(struct afs_operation *op, + struct afs_server *server) { struct afs_addr_list *alist, *discard; _enter(""); - trace_afs_server(server, atomic_read(&server->usage), afs_server_trace_update); + trace_afs_server(server, atomic_read(&server->ref), atomic_read(&server->active), + afs_server_trace_update); - alist = afs_vl_lookup_addrs(fc->vnode->volume->cell, fc->key, - &server->uuid); + alist = afs_vl_lookup_addrs(op->volume->cell, op->key, &server->uuid); if (IS_ERR(alist)) { if ((PTR_ERR(alist) == -ERESTARTSYS || PTR_ERR(alist) == -EINTR) && - !(fc->flags & AFS_FS_CURSOR_INTR) && + (op->flags & AFS_OPERATION_UNINTR) && server->addresses) { _leave(" = t [intr]"); return true; } - fc->error = PTR_ERR(alist); - _leave(" = f [%d]", fc->error); + op->error = PTR_ERR(alist); + _leave(" = f [%d]", op->error); return false; } @@ -558,7 +652,6 @@ static noinline bool afs_update_server_record(struct afs_fs_cursor *fc, struct a write_unlock(&server->fs_lock); } - server->update_at = ktime_get_real_seconds() + afs_server_update_delay; afs_put_addrlist(discard); _leave(" = t"); return true; @@ -567,10 +660,8 @@ static noinline bool afs_update_server_record(struct afs_fs_cursor *fc, struct a /* * See if a server's address list needs updating. */ -bool afs_check_server_record(struct afs_fs_cursor *fc, struct afs_server *server) +bool afs_check_server_record(struct afs_operation *op, struct afs_server *server) { - time64_t now = ktime_get_real_seconds(); - long diff; bool success; int ret, retries = 0; @@ -579,25 +670,29 @@ bool afs_check_server_record(struct afs_fs_cursor *fc, struct afs_server *server ASSERT(server); retry: - diff = READ_ONCE(server->update_at) - now; - if (diff > 0) { - _leave(" = t [not now %ld]", diff); - return true; - } + if (test_bit(AFS_SERVER_FL_UPDATING, &server->flags)) + goto wait; + if (test_bit(AFS_SERVER_FL_NEEDS_UPDATE, &server->flags)) + goto update; + _leave(" = t [good]"); + return true; +update: if (!test_and_set_bit_lock(AFS_SERVER_FL_UPDATING, &server->flags)) { - success = afs_update_server_record(fc, server); + clear_bit(AFS_SERVER_FL_NEEDS_UPDATE, &server->flags); + success = afs_update_server_record(op, server); clear_bit_unlock(AFS_SERVER_FL_UPDATING, &server->flags); wake_up_bit(&server->flags, AFS_SERVER_FL_UPDATING); _leave(" = %d", success); return success; } +wait: ret = wait_on_bit(&server->flags, AFS_SERVER_FL_UPDATING, - (fc->flags & AFS_FS_CURSOR_INTR) ? - TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); + (op->flags & AFS_OPERATION_UNINTR) ? + TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE); if (ret == -ERESTARTSYS) { - fc->error = ret; + op->error = ret; _leave(" = f [intr]"); return false; } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 888d91d195d9..ed9056703505 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -14,11 +14,9 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist) int i; if (slist && refcount_dec_and_test(&slist->usage)) { - for (i = 0; i < slist->nr_servers; i++) { - afs_put_cb_interest(net, slist->servers[i].cb_interest); - afs_put_server(net, slist->servers[i].server, - afs_server_trace_put_slist); - } + for (i = 0; i < slist->nr_servers; i++) + afs_unuse_server(net, slist->servers[i].server, + afs_server_trace_put_slist); kfree(slist); } } @@ -46,12 +44,16 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, refcount_set(&slist->usage, 1); rwlock_init(&slist->lock); + for (i = 0; i < AFS_MAXTYPES; i++) + slist->vids[i] = vldb->vid[i]; + /* Make sure a records exists for each server in the list. */ for (i = 0; i < vldb->nr_servers; i++) { if (!(vldb->fs_mask[i] & type_mask)) continue; - server = afs_lookup_server(cell, key, &vldb->fs_server[i]); + server = afs_lookup_server(cell, key, &vldb->fs_server[i], + vldb->addr_version[i]); if (IS_ERR(server)) { ret = PTR_ERR(server); if (ret == -ENOENT || @@ -123,31 +125,5 @@ changed: } } - /* Keep the old callback interest records where possible so that we - * maintain callback interception. - */ - i = 0; - j = 0; - while (i < old->nr_servers && j < new->nr_servers) { - if (new->servers[j].server == old->servers[i].server) { - struct afs_cb_interest *cbi = old->servers[i].cb_interest; - if (cbi) { - new->servers[j].cb_interest = cbi; - refcount_inc(&cbi->usage); - } - i++; - j++; - continue; - } - - if (new->servers[j].server < old->servers[i].server) { - j++; - continue; - } - - i++; - continue; - } - return true; } diff --git a/fs/afs/super.c b/fs/afs/super.c index dda7a9a66848..b552357b1d13 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -352,7 +352,9 @@ static int afs_validate_fc(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_volume *volume; + struct afs_cell *cell; struct key *key; + int ret; if (!ctx->dyn_root) { if (ctx->no_cell) { @@ -365,6 +367,7 @@ static int afs_validate_fc(struct fs_context *fc) return -EDESTADDRREQ; } + reget_key: /* We try to do the mount securely. */ key = afs_request_key(ctx->cell); if (IS_ERR(key)) @@ -373,10 +376,26 @@ static int afs_validate_fc(struct fs_context *fc) ctx->key = key; if (ctx->volume) { - afs_put_volume(ctx->cell, ctx->volume); + afs_put_volume(ctx->net, ctx->volume, + afs_volume_trace_put_validate_fc); ctx->volume = NULL; } + if (test_bit(AFS_CELL_FL_CHECK_ALIAS, &ctx->cell->flags)) { + ret = afs_cell_detect_alias(ctx->cell, key); + if (ret < 0) + return ret; + if (ret == 1) { + _debug("switch to alias"); + key_put(ctx->key); + ctx->key = NULL; + cell = afs_get_cell(ctx->cell->alias_of); + afs_put_cell(ctx->net, ctx->cell); + ctx->cell = cell; + goto reget_key; + } + } + volume = afs_create_volume(ctx); if (IS_ERR(volume)) return PTR_ERR(volume); @@ -421,7 +440,6 @@ static int afs_set_super(struct super_block *sb, struct fs_context *fc) static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) { struct afs_super_info *as = AFS_FS_S(sb); - struct afs_iget_data iget_data; struct inode *inode = NULL; int ret; @@ -446,13 +464,7 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) } else { sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); - iget_data.fid.vid = as->volume->vid; - iget_data.fid.vnode = 1; - iget_data.fid.vnode_hi = 0; - iget_data.fid.unique = 1; - iget_data.cb_v_break = as->volume->cb_v_break; - iget_data.cb_s_break = 0; - inode = afs_iget(sb, ctx->key, &iget_data, NULL, NULL, NULL); + inode = afs_root_iget(sb, ctx->key); } if (IS_ERR(inode)) @@ -473,6 +485,7 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) goto error; } else { sb->s_d_op = &afs_fs_dentry_operations; + rcu_assign_pointer(as->volume->sb, sb); } _leave(" = 0"); @@ -496,7 +509,8 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc) as->dyn_root = true; } else { as->cell = afs_get_cell(ctx->cell); - as->volume = __afs_get_volume(ctx->volume); + as->volume = afs_get_volume(ctx->volume, + afs_volume_trace_get_alloc_sbi); } } return as; @@ -505,8 +519,9 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc) static void afs_destroy_sbi(struct afs_super_info *as) { if (as) { - afs_put_volume(as->cell, as->volume); - afs_put_cell(afs_net(as->net_ns), as->cell); + struct afs_net *net = afs_net(as->net_ns); + afs_put_volume(net, as->volume, afs_volume_trace_put_destroy_sbi); + afs_put_cell(net, as->cell); put_net(as->net_ns); kfree(as); } @@ -515,7 +530,6 @@ static void afs_destroy_sbi(struct afs_super_info *as) static void afs_kill_super(struct super_block *sb) { struct afs_super_info *as = AFS_FS_S(sb); - struct afs_net *net = afs_net(as->net_ns); if (as->dyn_root) afs_dynroot_depopulate(sb); @@ -524,7 +538,7 @@ static void afs_kill_super(struct super_block *sb) * deactivating the superblock. */ if (as->volume) - afs_clear_callback_interests(net, as->volume->servers); + rcu_assign_pointer(as->volume->sb, NULL); kill_anon_super(sb); if (as->volume) afs_deactivate_volume(as->volume); @@ -592,7 +606,7 @@ static void afs_free_fc(struct fs_context *fc) struct afs_fs_context *ctx = fc->fs_private; afs_destroy_sbi(fc->s_fs_info); - afs_put_volume(ctx->cell, ctx->volume); + afs_put_volume(ctx->net, ctx->volume, afs_volume_trace_put_free_fc); afs_put_cell(ctx->net, ctx->cell); key_put(ctx->key); kfree(ctx); @@ -674,7 +688,6 @@ static struct inode *afs_alloc_inode(struct super_block *sb) vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; - RCU_INIT_POINTER(vnode->cb_interest, NULL); #ifdef CONFIG_AFS_FSCACHE vnode->cache = NULL; #endif @@ -704,22 +717,38 @@ static void afs_destroy_inode(struct inode *inode) _debug("DESTROY INODE %p", inode); - ASSERTCMP(rcu_access_pointer(vnode->cb_interest), ==, NULL); - atomic_dec(&afs_count_active_inodes); } +static void afs_get_volume_status_success(struct afs_operation *op) +{ + struct afs_volume_status *vs = &op->volstatus.vs; + struct kstatfs *buf = op->volstatus.buf; + + if (vs->max_quota == 0) + buf->f_blocks = vs->part_max_blocks; + else + buf->f_blocks = vs->max_quota; + + if (buf->f_blocks > vs->blocks_in_use) + buf->f_bavail = buf->f_bfree = + buf->f_blocks - vs->blocks_in_use; +} + +static const struct afs_operation_ops afs_get_volume_status_operation = { + .issue_afs_rpc = afs_fs_get_volume_status, + .issue_yfs_rpc = yfs_fs_get_volume_status, + .success = afs_get_volume_status_success, +}; + /* * return information about an AFS volume */ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct afs_super_info *as = AFS_FS_S(dentry->d_sb); - struct afs_fs_cursor fc; - struct afs_volume_status vs; + struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); - struct key *key; - int ret; buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = AFS_BLOCK_SIZE; @@ -732,31 +761,13 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) - return PTR_ERR(key); + op = afs_alloc_operation(NULL, as->volume); + if (IS_ERR(op)) + return PTR_ERR(op); - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - fc.flags |= AFS_FS_CURSOR_NO_VSLEEP; - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_get_volume_status(&fc, &vs); - } - - afs_check_for_remote_deletion(&fc, fc.vnode); - ret = afs_end_vnode_operation(&fc); - } - - key_put(key); - - if (ret == 0) { - if (vs.max_quota == 0) - buf->f_blocks = vs.part_max_blocks; - else - buf->f_blocks = vs.max_quota; - buf->f_bavail = buf->f_bfree = buf->f_blocks - vs.blocks_in_use; - } - - return ret; + afs_op_set_vnode(op, 0, vnode); + op->nr_files = 1; + op->volstatus.buf = buf; + op->ops = &afs_get_volume_status_operation; + return afs_do_sync_operation(op); } diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c new file mode 100644 index 000000000000..093895c49c21 --- /dev/null +++ b/fs/afs/vl_alias.c @@ -0,0 +1,382 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* AFS cell alias detection + * + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/namei.h> +#include <keys/rxrpc-type.h> +#include "internal.h" + +/* + * Sample a volume. + */ +static struct afs_volume *afs_sample_volume(struct afs_cell *cell, struct key *key, + const char *name, unsigned int namelen) +{ + struct afs_volume *volume; + struct afs_fs_context fc = { + .type = 0, /* Explicitly leave it to the VLDB */ + .volnamesz = namelen, + .volname = name, + .net = cell->net, + .cell = cell, + .key = key, /* This might need to be something */ + }; + + volume = afs_create_volume(&fc); + _leave(" = %px", volume); + return volume; +} + +/* + * Compare two addresses. + */ +static int afs_compare_addrs(const struct sockaddr_rxrpc *srx_a, + const struct sockaddr_rxrpc *srx_b) +{ + short port_a, port_b; + int addr_a, addr_b, diff; + + diff = (short)srx_a->transport_type - (short)srx_b->transport_type; + if (diff) + goto out; + + switch (srx_a->transport_type) { + case AF_INET: { + const struct sockaddr_in *a = &srx_a->transport.sin; + const struct sockaddr_in *b = &srx_b->transport.sin; + addr_a = ntohl(a->sin_addr.s_addr); + addr_b = ntohl(b->sin_addr.s_addr); + diff = addr_a - addr_b; + if (diff == 0) { + port_a = ntohs(a->sin_port); + port_b = ntohs(b->sin_port); + diff = port_a - port_b; + } + break; + } + + case AF_INET6: { + const struct sockaddr_in6 *a = &srx_a->transport.sin6; + const struct sockaddr_in6 *b = &srx_b->transport.sin6; + diff = memcmp(&a->sin6_addr, &b->sin6_addr, 16); + if (diff == 0) { + port_a = ntohs(a->sin6_port); + port_b = ntohs(b->sin6_port); + diff = port_a - port_b; + } + break; + } + + default: + BUG(); + } + +out: + return diff; +} + +/* + * Compare the address lists of a pair of fileservers. + */ +static int afs_compare_fs_alists(const struct afs_server *server_a, + const struct afs_server *server_b) +{ + const struct afs_addr_list *la, *lb; + int a = 0, b = 0, addr_matches = 0; + + la = rcu_dereference(server_a->addresses); + lb = rcu_dereference(server_b->addresses); + + while (a < la->nr_addrs && b < lb->nr_addrs) { + const struct sockaddr_rxrpc *srx_a = &la->addrs[a]; + const struct sockaddr_rxrpc *srx_b = &lb->addrs[b]; + int diff = afs_compare_addrs(srx_a, srx_b); + + if (diff < 0) { + a++; + } else if (diff > 0) { + b++; + } else { + addr_matches++; + a++; + b++; + } + } + + return addr_matches; +} + +/* + * Compare the fileserver lists of two volumes. The server lists are sorted in + * order of ascending UUID. + */ +static int afs_compare_volume_slists(const struct afs_volume *vol_a, + const struct afs_volume *vol_b) +{ + const struct afs_server_list *la, *lb; + int i, a = 0, b = 0, uuid_matches = 0, addr_matches = 0; + + la = rcu_dereference(vol_a->servers); + lb = rcu_dereference(vol_b->servers); + + for (i = 0; i < AFS_MAXTYPES; i++) + if (la->vids[i] != lb->vids[i]) + return 0; + + while (a < la->nr_servers && b < lb->nr_servers) { + const struct afs_server *server_a = la->servers[a].server; + const struct afs_server *server_b = lb->servers[b].server; + int diff = memcmp(&server_a->uuid, &server_b->uuid, sizeof(uuid_t)); + + if (diff < 0) { + a++; + } else if (diff > 0) { + b++; + } else { + uuid_matches++; + addr_matches += afs_compare_fs_alists(server_a, server_b); + a++; + b++; + } + } + + _leave(" = %d [um %d]", addr_matches, uuid_matches); + return addr_matches; +} + +/* + * Compare root.cell volumes. + */ +static int afs_compare_cell_roots(struct afs_cell *cell) +{ + struct afs_cell *p; + + _enter(""); + + rcu_read_lock(); + + hlist_for_each_entry_rcu(p, &cell->net->proc_cells, proc_link) { + if (p == cell || p->alias_of) + continue; + if (!p->root_volume) + continue; /* Ignore cells that don't have a root.cell volume. */ + + if (afs_compare_volume_slists(cell->root_volume, p->root_volume) != 0) + goto is_alias; + } + + rcu_read_unlock(); + _leave(" = 0"); + return 0; + +is_alias: + rcu_read_unlock(); + cell->alias_of = afs_get_cell(p); + return 1; +} + +/* + * Query the new cell for a volume from a cell we're already using. + */ +static int afs_query_for_alias_one(struct afs_cell *cell, struct key *key, + struct afs_cell *p) +{ + struct afs_volume *volume, *pvol = NULL; + int ret; + + /* Arbitrarily pick a volume from the list. */ + read_seqlock_excl(&p->volume_lock); + if (!RB_EMPTY_ROOT(&p->volumes)) + pvol = afs_get_volume(rb_entry(p->volumes.rb_node, + struct afs_volume, cell_node), + afs_volume_trace_get_query_alias); + read_sequnlock_excl(&p->volume_lock); + if (!pvol) + return 0; + + _enter("%s:%s", cell->name, pvol->name); + + /* And see if it's in the new cell. */ + volume = afs_sample_volume(cell, key, pvol->name, pvol->name_len); + if (IS_ERR(volume)) { + afs_put_volume(cell->net, pvol, afs_volume_trace_put_query_alias); + if (PTR_ERR(volume) != -ENOMEDIUM) + return PTR_ERR(volume); + /* That volume is not in the new cell, so not an alias */ + return 0; + } + + /* The new cell has a like-named volume also - compare volume ID, + * server and address lists. + */ + ret = 0; + if (pvol->vid == volume->vid) { + rcu_read_lock(); + if (afs_compare_volume_slists(volume, pvol)) + ret = 1; + rcu_read_unlock(); + } + + afs_put_volume(cell->net, volume, afs_volume_trace_put_query_alias); + afs_put_volume(cell->net, pvol, afs_volume_trace_put_query_alias); + return ret; +} + +/* + * Query the new cell for volumes we know exist in cells we're already using. + */ +static int afs_query_for_alias(struct afs_cell *cell, struct key *key) +{ + struct afs_cell *p; + + _enter("%s", cell->name); + + if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) + return -ERESTARTSYS; + + hlist_for_each_entry(p, &cell->net->proc_cells, proc_link) { + if (p == cell || p->alias_of) + continue; + if (RB_EMPTY_ROOT(&p->volumes)) + continue; + if (p->root_volume) + continue; /* Ignore cells that have a root.cell volume. */ + afs_get_cell(p); + mutex_unlock(&cell->net->proc_cells_lock); + + if (afs_query_for_alias_one(cell, key, p) != 0) + goto is_alias; + + if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) { + afs_put_cell(cell->net, p); + return -ERESTARTSYS; + } + + afs_put_cell(cell->net, p); + } + + mutex_unlock(&cell->net->proc_cells_lock); + _leave(" = 0"); + return 0; + +is_alias: + cell->alias_of = p; /* Transfer our ref */ + return 1; +} + +/* + * Look up a VLDB record for a volume. + */ +static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) +{ + struct afs_vl_cursor vc; + char *cell_name = ERR_PTR(-EDESTADDRREQ); + bool skipped = false, not_skipped = false; + int ret; + + if (!afs_begin_vlserver_operation(&vc, cell, key)) + return ERR_PTR(-ERESTARTSYS); + + while (afs_select_vlserver(&vc)) { + if (!test_bit(AFS_VLSERVER_FL_IS_YFS, &vc.server->flags)) { + vc.ac.error = -EOPNOTSUPP; + skipped = true; + continue; + } + not_skipped = true; + cell_name = afs_yfsvl_get_cell_name(&vc); + } + + ret = afs_end_vlserver_operation(&vc); + if (skipped && !not_skipped) + ret = -EOPNOTSUPP; + return ret < 0 ? ERR_PTR(ret) : cell_name; +} + +static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) +{ + struct afs_cell *master; + char *cell_name; + + cell_name = afs_vl_get_cell_name(cell, key); + if (IS_ERR(cell_name)) + return PTR_ERR(cell_name); + + if (strcmp(cell_name, cell->name) == 0) { + kfree(cell_name); + return 0; + } + + master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), + NULL, false); + kfree(cell_name); + if (IS_ERR(master)) + return PTR_ERR(master); + + cell->alias_of = master; /* Transfer our ref */ + return 1; +} + +static int afs_do_cell_detect_alias(struct afs_cell *cell, struct key *key) +{ + struct afs_volume *root_volume; + int ret; + + _enter("%s", cell->name); + + ret = yfs_check_canonical_cell_name(cell, key); + if (ret != -EOPNOTSUPP) + return ret; + + /* Try and get the root.cell volume for comparison with other cells */ + root_volume = afs_sample_volume(cell, key, "root.cell", 9); + if (!IS_ERR(root_volume)) { + cell->root_volume = root_volume; + return afs_compare_cell_roots(cell); + } + + if (PTR_ERR(root_volume) != -ENOMEDIUM) + return PTR_ERR(root_volume); + + /* Okay, this cell doesn't have an root.cell volume. We need to + * locate some other random volume and use that to check. + */ + return afs_query_for_alias(cell, key); +} + +/* + * Check to see if a new cell is an alias of a cell we already have. At this + * point we have the cell's volume server list. + * + * Returns 0 if we didn't detect an alias, 1 if we found an alias and an error + * if we had problems gathering the data required. In the case the we did + * detect an alias, cell->alias_of is set to point to the assumed master. + */ +int afs_cell_detect_alias(struct afs_cell *cell, struct key *key) +{ + struct afs_net *net = cell->net; + int ret; + + if (mutex_lock_interruptible(&net->cells_alias_lock) < 0) + return -ERESTARTSYS; + + if (test_bit(AFS_CELL_FL_CHECK_ALIAS, &cell->flags)) { + ret = afs_do_cell_detect_alias(cell, key); + if (ret >= 0) + clear_bit_unlock(AFS_CELL_FL_CHECK_ALIAS, &cell->flags); + } else { + ret = cell->alias_of ? 1 : 0; + } + + mutex_unlock(&net->cells_alias_lock); + + if (ret == 1) + pr_notice("kAFS: Cell %s is an alias of %s\n", + cell->name, cell->alias_of->name); + return ret; +} diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index 72eacc14e6e1..f405ca8b240a 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -151,6 +151,10 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc) vc->error = error; vc->flags |= AFS_VL_CURSOR_RETRY; goto next_server; + + case -EOPNOTSUPP: + _debug("notsupp"); + goto next_server; } restart_from_beginning: diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index 516e9a3bb5b4..fd82850cd424 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -82,6 +82,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) for (j = 0; j < 6; j++) uuid->node[j] = (u8)ntohl(xdr->node[j]); + entry->addr_version[n] = ntohl(uvldb->serverUnique[i]); entry->nr_servers++; } @@ -447,8 +448,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) call->count2 = ntohl(*bp); /* Type or next count */ if (call->count > YFS_MAXENDPOINTS) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_fsendpt_num); + return afs_protocol_error(call, afs_eproto_yvl_fsendpt_num); alist = afs_alloc_addrlist(call->count, FS_SERVICE, AFS_FS_PORT); if (!alist) @@ -468,8 +468,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) size = sizeof(__be32) * (1 + 4 + 1); break; default: - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_fsendpt_type); + return afs_protocol_error(call, afs_eproto_yvl_fsendpt_type); } size += sizeof(__be32); @@ -487,21 +486,20 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) switch (call->count2) { case YFS_ENDPOINT_IPV4: if (ntohl(bp[0]) != sizeof(__be32) * 2) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_fsendpt4_len); + return afs_protocol_error( + call, afs_eproto_yvl_fsendpt4_len); afs_merge_fs_addr4(alist, bp[1], ntohl(bp[2])); bp += 3; break; case YFS_ENDPOINT_IPV6: if (ntohl(bp[0]) != sizeof(__be32) * 5) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_fsendpt6_len); + return afs_protocol_error( + call, afs_eproto_yvl_fsendpt6_len); afs_merge_fs_addr6(alist, bp + 1, ntohl(bp[5])); bp += 6; break; default: - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_fsendpt_type); + return afs_protocol_error(call, afs_eproto_yvl_fsendpt_type); } /* Got either the type of the next entry or the count of @@ -519,8 +517,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) if (!call->count) goto end; if (call->count > YFS_MAXENDPOINTS) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_vlendpt_type); + return afs_protocol_error(call, afs_eproto_yvl_vlendpt_type); afs_extract_to_buf(call, 1 * sizeof(__be32)); call->unmarshall = 3; @@ -547,8 +544,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) size = sizeof(__be32) * (1 + 4 + 1); break; default: - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_vlendpt_type); + return afs_protocol_error(call, afs_eproto_yvl_vlendpt_type); } if (call->count > 1) @@ -566,19 +562,18 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) switch (call->count2) { case YFS_ENDPOINT_IPV4: if (ntohl(bp[0]) != sizeof(__be32) * 2) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_vlendpt4_len); + return afs_protocol_error( + call, afs_eproto_yvl_vlendpt4_len); bp += 3; break; case YFS_ENDPOINT_IPV6: if (ntohl(bp[0]) != sizeof(__be32) * 5) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_vlendpt6_len); + return afs_protocol_error( + call, afs_eproto_yvl_vlendpt6_len); bp += 6; break; default: - return afs_protocol_error(call, -EBADMSG, - afs_eproto_yvl_vlendpt_type); + return afs_protocol_error(call, afs_eproto_yvl_vlendpt_type); } /* Got either the type of the next entry or the count of @@ -650,3 +645,114 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc, afs_make_call(&vc->ac, call, GFP_KERNEL); return (struct afs_addr_list *)afs_wait_for_call_to_complete(call, &vc->ac); } + +/* + * Deliver reply data to a YFSVL.GetCellName operation. + */ +static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) +{ + char *cell_name; + u32 namesz, paddedsz; + int ret; + + _enter("{%u,%zu/%u}", + call->unmarshall, iov_iter_count(call->iter), call->count); + + switch (call->unmarshall) { + case 0: + afs_extract_to_tmp(call); + call->unmarshall++; + + /* Fall through - and extract the cell name length */ + case 1: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + namesz = ntohl(call->tmp); + if (namesz > AFS_MAXCELLNAME) + return afs_protocol_error(call, afs_eproto_cellname_len); + paddedsz = (namesz + 3) & ~3; + call->count = namesz; + call->count2 = paddedsz - namesz; + + cell_name = kmalloc(namesz + 1, GFP_KERNEL); + if (!cell_name) + return -ENOMEM; + cell_name[namesz] = 0; + call->ret_str = cell_name; + + afs_extract_begin(call, cell_name, namesz); + call->unmarshall++; + + /* Fall through - and extract cell name */ + case 2: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + afs_extract_discard(call, call->count2); + call->unmarshall++; + + /* Fall through - and extract padding */ + case 3: + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + call->unmarshall++; + break; + } + + _leave(" = 0 [done]"); + return 0; +} + +static void afs_destroy_yfsvl_get_cell_name(struct afs_call *call) +{ + kfree(call->ret_str); + afs_flat_call_destructor(call); +} + +/* + * VL.GetCapabilities operation type + */ +static const struct afs_call_type afs_YFSVLGetCellName = { + .name = "YFSVL.GetCellName", + .op = afs_YFSVL_GetCellName, + .deliver = afs_deliver_yfsvl_get_cell_name, + .destructor = afs_destroy_yfsvl_get_cell_name, +}; + +/* + * Probe a volume server for the capabilities that it supports. This can + * return up to 196 words. + * + * We use this to probe for service upgrade to determine what the server at the + * other end supports. + */ +char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *vc) +{ + struct afs_call *call; + struct afs_net *net = vc->cell->net; + __be32 *bp; + + _enter(""); + + call = afs_alloc_flat_call(net, &afs_YFSVLGetCellName, 1 * 4, 0); + if (!call) + return ERR_PTR(-ENOMEM); + + call->key = vc->key; + call->ret_str = NULL; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; + + /* marshall the parameters */ + bp = call->request; + *bp++ = htonl(YVLGETCELLNAME); + + /* Can't take a ref on server */ + trace_afs_make_vl_call(call); + afs_make_call(&vc->ac, call, GFP_KERNEL); + return (char *)afs_wait_for_call_to_complete(call, &vc->ac); +} diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 4310336b9bb8..9bc0509e3634 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -13,6 +13,56 @@ unsigned __read_mostly afs_volume_gc_delay = 10; unsigned __read_mostly afs_volume_record_life = 60 * 60; /* + * Insert a volume into a cell. If there's an existing volume record, that is + * returned instead with a ref held. + */ +static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell, + struct afs_volume *volume) +{ + struct afs_volume *p; + struct rb_node *parent = NULL, **pp; + + write_seqlock(&cell->volume_lock); + + pp = &cell->volumes.rb_node; + while (*pp) { + parent = *pp; + p = rb_entry(parent, struct afs_volume, cell_node); + if (p->vid < volume->vid) { + pp = &(*pp)->rb_left; + } else if (p->vid > volume->vid) { + pp = &(*pp)->rb_right; + } else { + volume = afs_get_volume(p, afs_volume_trace_get_cell_insert); + goto found; + } + } + + rb_link_node_rcu(&volume->cell_node, parent, pp); + rb_insert_color(&volume->cell_node, &cell->volumes); + hlist_add_head_rcu(&volume->proc_link, &cell->proc_volumes); + +found: + write_sequnlock(&cell->volume_lock); + return volume; + +} + +static void afs_remove_volume_from_cell(struct afs_volume *volume) +{ + struct afs_cell *cell = volume->cell; + + if (!hlist_unhashed(&volume->proc_link)) { + trace_afs_volume(volume->vid, atomic_read(&volume->usage), + afs_volume_trace_remove); + write_seqlock(&cell->volume_lock); + hlist_del_rcu(&volume->proc_link); + rb_erase(&volume->cell_node, &cell->volumes); + write_sequnlock(&cell->volume_lock); + } +} + +/* * Allocate a volume record and load it up from a vldb record. */ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, @@ -39,7 +89,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, volume->name_len = vldb->name_len; atomic_set(&volume->usage, 1); - INIT_LIST_HEAD(&volume->proc_link); + INIT_HLIST_NODE(&volume->proc_link); rwlock_init(&volume->servers_lock); rwlock_init(&volume->cb_v_break_lock); memcpy(volume->name, vldb->name, vldb->name_len + 1); @@ -51,7 +101,8 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, } refcount_set(&slist->usage, 1); - volume->servers = slist; + rcu_assign_pointer(volume->servers, slist); + trace_afs_volume(volume->vid, 1, afs_volume_trace_alloc); return volume; error_1: @@ -62,6 +113,25 @@ error_0: } /* + * Look up or allocate a volume record. + */ +static struct afs_volume *afs_lookup_volume(struct afs_fs_context *params, + struct afs_vldb_entry *vldb, + unsigned long type_mask) +{ + struct afs_volume *candidate, *volume; + + candidate = afs_alloc_volume(params, vldb, type_mask); + if (IS_ERR(candidate)) + return candidate; + + volume = afs_insert_volume_into_cell(params->cell, candidate); + if (volume != candidate) + afs_put_volume(params->net, candidate, afs_volume_trace_put_cell_dup); + return volume; +} + +/* * Look up a VLDB record for a volume. */ static struct afs_vldb_entry *afs_vl_lookup_vldb(struct afs_cell *cell, @@ -138,7 +208,7 @@ struct afs_volume *afs_create_volume(struct afs_fs_context *params) } type_mask = 1UL << params->type; - volume = afs_alloc_volume(params, vldb, type_mask); + volume = afs_lookup_volume(params, vldb, type_mask); error: kfree(vldb); @@ -156,23 +226,42 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) ASSERTCMP(volume->cache, ==, NULL); #endif - afs_put_serverlist(net, volume->servers); + afs_remove_volume_from_cell(volume); + afs_put_serverlist(net, rcu_access_pointer(volume->servers)); afs_put_cell(net, volume->cell); - kfree(volume); + trace_afs_volume(volume->vid, atomic_read(&volume->usage), + afs_volume_trace_free); + kfree_rcu(volume, rcu); _leave(" [destroyed]"); } /* - * Drop a reference on a volume record. + * Get a reference on a volume record. */ -void afs_put_volume(struct afs_cell *cell, struct afs_volume *volume) +struct afs_volume *afs_get_volume(struct afs_volume *volume, + enum afs_volume_trace reason) { if (volume) { - _enter("%s", volume->name); + int u = atomic_inc_return(&volume->usage); + trace_afs_volume(volume->vid, u, reason); + } + return volume; +} + - if (atomic_dec_and_test(&volume->usage)) - afs_destroy_volume(cell->net, volume); +/* + * Drop a reference on a volume record. + */ +void afs_put_volume(struct afs_net *net, struct afs_volume *volume, + enum afs_volume_trace reason) +{ + if (volume) { + afs_volid_t vid = volume->vid; + int u = atomic_dec_return(&volume->usage); + trace_afs_volume(vid, u, reason); + if (u == 0) + afs_destroy_volume(net, volume); } } @@ -188,10 +277,6 @@ void afs_activate_volume(struct afs_volume *volume) NULL, 0, volume, 0, true); #endif - - write_lock(&volume->cell->proc_lock); - list_add_tail(&volume->proc_link, &volume->cell->proc_volumes); - write_unlock(&volume->cell->proc_lock); } /* @@ -201,10 +286,6 @@ void afs_deactivate_volume(struct afs_volume *volume) { _enter("%s", volume->name); - write_lock(&volume->cell->proc_lock); - list_del_init(&volume->proc_link); - write_unlock(&volume->cell->proc_lock); - #ifdef CONFIG_AFS_FSCACHE fscache_relinquish_cookie(volume->cache, NULL, test_bit(AFS_VOLUME_DELETED, &volume->flags)); @@ -256,17 +337,17 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) write_lock(&volume->servers_lock); discard = new; - old = volume->servers; + old = rcu_dereference_protected(volume->servers, + lockdep_is_held(&volume->servers_lock)); if (afs_annotate_server_list(new, old)) { new->seq = volume->servers_seq + 1; - volume->servers = new; + rcu_assign_pointer(volume->servers, new); smp_wmb(); volume->servers_seq++; discard = old; } volume->update_at = ktime_get_real_seconds() + afs_volume_record_life; - clear_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); write_unlock(&volume->servers_lock); ret = 0; @@ -281,25 +362,27 @@ error: /* * Make sure the volume record is up to date. */ -int afs_check_volume_status(struct afs_volume *volume, struct afs_fs_cursor *fc) +int afs_check_volume_status(struct afs_volume *volume, struct afs_operation *op) { - time64_t now = ktime_get_real_seconds(); int ret, retries = 0; _enter(""); - if (volume->update_at <= now) - set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); - retry: - if (!test_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags) && - !test_bit(AFS_VOLUME_WAIT, &volume->flags)) { - _leave(" = 0"); - return 0; - } - + if (test_bit(AFS_VOLUME_WAIT, &volume->flags)) + goto wait; + if (volume->update_at <= ktime_get_real_seconds() || + test_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags)) + goto update; + _leave(" = 0"); + return 0; + +update: if (!test_and_set_bit_lock(AFS_VOLUME_UPDATING, &volume->flags)) { - ret = afs_update_volume_status(volume, fc->key); + clear_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); + ret = afs_update_volume_status(volume, op->key); + if (ret < 0) + set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); clear_bit_unlock(AFS_VOLUME_WAIT, &volume->flags); clear_bit_unlock(AFS_VOLUME_UPDATING, &volume->flags); wake_up_bit(&volume->flags, AFS_VOLUME_WAIT); @@ -307,14 +390,15 @@ retry: return ret; } +wait: if (!test_bit(AFS_VOLUME_WAIT, &volume->flags)) { _leave(" = 0 [no wait]"); return 0; } ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, - (fc->flags & AFS_FS_CURSOR_INTR) ? - TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); + (op->flags & AFS_OPERATION_UNINTR) ? + TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE); if (ret == -ERESTARTSYS) { _leave(" = %d", ret); return ret; diff --git a/fs/afs/write.c b/fs/afs/write.c index cb76566763db..97bccde3298b 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -349,82 +349,111 @@ static void afs_pages_written_back(struct afs_vnode *vnode, } /* - * write to a file + * Find a key to use for the writeback. We cached the keys used to author the + * writes on the vnode. *_wbk will contain the last writeback key used or NULL + * and we need to start from there if it's set. */ -static int afs_store_data(struct address_space *mapping, - pgoff_t first, pgoff_t last, - unsigned offset, unsigned to) +static int afs_get_writeback_key(struct afs_vnode *vnode, + struct afs_wb_key **_wbk) { - struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct afs_fs_cursor fc; - struct afs_status_cb *scb; struct afs_wb_key *wbk = NULL; struct list_head *p; int ret = -ENOKEY, ret2; - _enter("%s{%llx:%llu.%u},%lx,%lx,%x,%x", - vnode->volume->name, - vnode->fid.vid, - vnode->fid.vnode, - vnode->fid.unique, - first, last, offset, to); - - scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); - if (!scb) - return -ENOMEM; - spin_lock(&vnode->wb_lock); - p = vnode->wb_keys.next; + if (*_wbk) + p = (*_wbk)->vnode_link.next; + else + p = vnode->wb_keys.next; - /* Iterate through the list looking for a valid key to use. */ -try_next_key: while (p != &vnode->wb_keys) { wbk = list_entry(p, struct afs_wb_key, vnode_link); _debug("wbk %u", key_serial(wbk->key)); ret2 = key_validate(wbk->key); - if (ret2 == 0) - goto found_key; + if (ret2 == 0) { + refcount_inc(&wbk->usage); + _debug("USE WB KEY %u", key_serial(wbk->key)); + break; + } + + wbk = NULL; if (ret == -ENOKEY) ret = ret2; p = p->next; } spin_unlock(&vnode->wb_lock); - afs_put_wb_key(wbk); - kfree(scb); - _leave(" = %d [no keys]", ret); - return ret; + if (*_wbk) + afs_put_wb_key(*_wbk); + *_wbk = wbk; + return 0; +} -found_key: - refcount_inc(&wbk->usage); - spin_unlock(&vnode->wb_lock); +static void afs_store_data_success(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; - _debug("USE WB KEY %u", key_serial(wbk->key)); + afs_vnode_commit_status(op, &op->file[0]); + if (op->error == 0) { + afs_pages_written_back(vnode, op->store.first, op->store.last); + afs_stat_v(vnode, n_stores); + atomic_long_add((op->store.last * PAGE_SIZE + op->store.last_to) - + (op->store.first * PAGE_SIZE + op->store.first_offset), + &afs_v2net(vnode)->n_store_bytes); + } +} - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, wbk->key, false)) { - afs_dataversion_t data_version = vnode->status.data_version + 1; +static const struct afs_operation_ops afs_store_data_operation = { + .issue_afs_rpc = afs_fs_store_data, + .issue_yfs_rpc = yfs_fs_store_data, + .success = afs_store_data_success, +}; - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_store_data(&fc, mapping, first, last, offset, to, scb); - } +/* + * write to a file + */ +static int afs_store_data(struct address_space *mapping, + pgoff_t first, pgoff_t last, + unsigned offset, unsigned to) +{ + struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct afs_operation *op; + struct afs_wb_key *wbk = NULL; + int ret; - afs_check_for_remote_deletion(&fc, vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - if (fc.ac.error == 0) - afs_pages_written_back(vnode, first, last); - ret = afs_end_vnode_operation(&fc); + _enter("%s{%llx:%llu.%u},%lx,%lx,%x,%x", + vnode->volume->name, + vnode->fid.vid, + vnode->fid.vnode, + vnode->fid.unique, + first, last, offset, to); + + ret = afs_get_writeback_key(vnode, &wbk); + if (ret) { + _leave(" = %d [no keys]", ret); + return ret; } - switch (ret) { - case 0: - afs_stat_v(vnode, n_stores); - atomic_long_add((last * PAGE_SIZE + to) - - (first * PAGE_SIZE + offset), - &afs_v2net(vnode)->n_store_bytes); - break; + op = afs_alloc_operation(wbk->key, vnode->volume); + if (IS_ERR(op)) { + afs_put_wb_key(wbk); + return -ENOMEM; + } + + afs_op_set_vnode(op, 0, vnode); + op->file[0].dv_delta = 1; + op->store.mapping = mapping; + op->store.first = first; + op->store.last = last; + op->store.first_offset = offset; + op->store.last_to = to; + op->ops = &afs_store_data_operation; + +try_next_key: + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + + switch (op->error) { case -EACCES: case -EPERM: case -ENOKEY: @@ -432,16 +461,19 @@ found_key: case -EKEYREJECTED: case -EKEYREVOKED: _debug("next"); - spin_lock(&vnode->wb_lock); - p = wbk->vnode_link.next; - afs_put_wb_key(wbk); - goto try_next_key; + + ret = afs_get_writeback_key(vnode, &wbk); + if (ret == 0) { + key_put(op->key); + op->key = key_get(wbk->key); + goto try_next_key; + } + break; } afs_put_wb_key(wbk); - kfree(scb); - _leave(" = %d", ret); - return ret; + _leave(" = %d", op->error); + return afs_put_operation(op); } /* diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index 7af41fd5f3ee..84f3c4f57531 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -35,6 +35,25 @@ ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size) } /* + * Deal with the result of a successful fetch ACL operation. + */ +static void afs_acl_success(struct afs_operation *op) +{ + afs_vnode_commit_status(op, &op->file[0]); +} + +static void afs_acl_put(struct afs_operation *op) +{ + kfree(op->acl); +} + +static const struct afs_operation_ops afs_fetch_acl_operation = { + .issue_afs_rpc = afs_fs_fetch_acl, + .success = afs_acl_success, + .put = afs_acl_put, +}; + +/* * Get a file's ACL. */ static int afs_xattr_get_acl(const struct xattr_handler *handler, @@ -42,37 +61,23 @@ static int afs_xattr_get_acl(const struct xattr_handler *handler, struct inode *inode, const char *name, void *buffer, size_t size) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_acl *acl = NULL; - struct key *key; - int ret = -ENOMEM; + int ret; - scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); - if (!scb) - goto error; - - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; - } + op = afs_alloc_operation(NULL, vnode->volume); + if (IS_ERR(op)) + return -ENOMEM; - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - afs_dataversion_t data_version = vnode->status.data_version; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - acl = afs_fs_fetch_acl(&fc, scb); - } + afs_op_set_vnode(op, 0, vnode); + op->ops = &afs_fetch_acl_operation; - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - ret = afs_end_vnode_operation(&fc); - } + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + acl = op->acl; + op->acl = NULL; + ret = afs_put_operation(op); if (ret == 0) { ret = acl->size; @@ -80,18 +85,37 @@ static int afs_xattr_get_acl(const struct xattr_handler *handler, if (acl->size <= size) memcpy(buffer, acl->data, acl->size); else - ret = -ERANGE; + op->error = -ERANGE; } - kfree(acl); } - key_put(key); -error_scb: - kfree(scb); -error: + kfree(acl); return ret; } +static bool afs_make_acl(struct afs_operation *op, + const void *buffer, size_t size) +{ + struct afs_acl *acl; + + acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); + if (!acl) { + afs_op_nomem(op); + return false; + } + + acl->size = size; + memcpy(acl->data, buffer, size); + op->acl = acl; + return true; +} + +static const struct afs_operation_ops afs_store_acl_operation = { + .issue_afs_rpc = afs_fs_store_acl, + .success = afs_acl_success, + .put = afs_acl_put, +}; + /* * Set a file's AFS3 ACL. */ @@ -100,55 +124,22 @@ static int afs_xattr_set_acl(const struct xattr_handler *handler, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(inode); - struct afs_acl *acl = NULL; - struct key *key; - int ret = -ENOMEM; if (flags == XATTR_CREATE) return -EINVAL; - scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); - if (!scb) - goto error; - - acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); - if (!acl) - goto error_scb; - - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_acl; - } - - acl->size = size; - memcpy(acl->data, buffer, size); - - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - afs_dataversion_t data_version = vnode->status.data_version; + op = afs_alloc_operation(NULL, vnode->volume); + if (IS_ERR(op)) + return -ENOMEM; - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_store_acl(&fc, acl, scb); - } + afs_op_set_vnode(op, 0, vnode); + if (!afs_make_acl(op, buffer, size)) + return afs_put_operation(op); - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - ret = afs_end_vnode_operation(&fc); - } - - key_put(key); -error_acl: - kfree(acl); -error_scb: - kfree(scb); -error: - return ret; + op->ops = &afs_store_acl_operation; + return afs_do_sync_operation(op); } static const struct xattr_handler afs_xattr_afs_acl_handler = { @@ -157,6 +148,17 @@ static const struct xattr_handler afs_xattr_afs_acl_handler = { .set = afs_xattr_set_acl, }; +static void yfs_acl_put(struct afs_operation *op) +{ + yfs_free_opaque_acl(op->yacl); +} + +static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = { + .issue_yfs_rpc = yfs_fs_fetch_opaque_acl, + .success = afs_acl_success, + /* Don't free op->yacl in .put here */ +}; + /* * Get a file's YFS ACL. */ @@ -165,11 +167,9 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler, struct inode *inode, const char *name, void *buffer, size_t size) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(inode); struct yfs_acl *yacl = NULL; - struct key *key; char buf[16], *data; int which = 0, dsize, ret = -ENOMEM; @@ -193,75 +193,62 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler, else if (which == 3) yacl->flags |= YFS_ACL_WANT_VOL_ACL; - scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); - if (!scb) + op = afs_alloc_operation(NULL, vnode->volume); + if (IS_ERR(op)) goto error_yacl; - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_scb; - } + afs_op_set_vnode(op, 0, vnode); + op->yacl = yacl; + op->ops = &yfs_fetch_opaque_acl_operation; - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - afs_dataversion_t data_version = vnode->status.data_version; + afs_begin_vnode_operation(op); + afs_wait_for_operation(op); + ret = afs_put_operation(op); - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - yfs_fs_fetch_opaque_acl(&fc, yacl, scb); + if (ret == 0) { + switch (which) { + case 0: + data = yacl->acl->data; + dsize = yacl->acl->size; + break; + case 1: + data = buf; + dsize = scnprintf(buf, sizeof(buf), "%u", yacl->inherit_flag); + break; + case 2: + data = buf; + dsize = scnprintf(buf, sizeof(buf), "%u", yacl->num_cleaned); + break; + case 3: + data = yacl->vol_acl->data; + dsize = yacl->vol_acl->size; + break; + default: + ret = -EOPNOTSUPP; + goto error_yacl; } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - ret = afs_end_vnode_operation(&fc); - } - - if (ret < 0) - goto error_key; - - switch (which) { - case 0: - data = yacl->acl->data; - dsize = yacl->acl->size; - break; - case 1: - data = buf; - dsize = scnprintf(buf, sizeof(buf), "%u", yacl->inherit_flag); - break; - case 2: - data = buf; - dsize = scnprintf(buf, sizeof(buf), "%u", yacl->num_cleaned); - break; - case 3: - data = yacl->vol_acl->data; - dsize = yacl->vol_acl->size; - break; - default: - ret = -EOPNOTSUPP; - goto error_key; - } - - ret = dsize; - if (size > 0) { - if (dsize > size) { - ret = -ERANGE; - goto error_key; + ret = dsize; + if (size > 0) { + if (dsize <= size) + memcpy(buffer, data, dsize); + else + ret = -ERANGE; } - memcpy(buffer, data, dsize); } -error_key: - key_put(key); -error_scb: - kfree(scb); error_yacl: yfs_free_opaque_acl(yacl); error: return ret; } +static const struct afs_operation_ops yfs_store_opaque_acl2_operation = { + .issue_yfs_rpc = yfs_fs_store_opaque_acl2, + .success = afs_acl_success, + .put = yfs_acl_put, +}; + /* * Set a file's YFS ACL. */ @@ -270,56 +257,23 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { - struct afs_fs_cursor fc; - struct afs_status_cb *scb; + struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(inode); - struct afs_acl *acl = NULL; - struct key *key; - int ret = -ENOMEM; if (flags == XATTR_CREATE || strcmp(name, "acl") != 0) return -EINVAL; - scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); - if (!scb) - goto error; - - acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); - if (!acl) - goto error_scb; + op = afs_alloc_operation(NULL, vnode->volume); + if (IS_ERR(op)) + return -ENOMEM; - acl->size = size; - memcpy(acl->data, buffer, size); + afs_op_set_vnode(op, 0, vnode); + if (!afs_make_acl(op, buffer, size)) + return afs_put_operation(op); - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) { - ret = PTR_ERR(key); - goto error_acl; - } - - ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key, true)) { - afs_dataversion_t data_version = vnode->status.data_version; - - while (afs_select_fileserver(&fc)) { - fc.cb_break = afs_calc_vnode_cb_break(vnode); - yfs_fs_store_opaque_acl2(&fc, acl, scb); - } - - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break, - &data_version, scb); - ret = afs_end_vnode_operation(&fc); - } - -error_acl: - kfree(acl); - key_put(key); -error_scb: - kfree(scb); -error: - return ret; + op->ops = &yfs_store_opaque_acl2_operation; + return afs_do_sync_operation(op); } static const struct xattr_handler afs_xattr_yfs_handler = { diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index fe413e7a5cf4..b0a6e40b4da3 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -17,11 +17,6 @@ static const struct afs_fid afs_zero_fid; -static inline void afs_use_fs_server(struct afs_call *call, struct afs_cb_interest *cbi) -{ - call->cbi = afs_get_cb_interest(cbi); -} - #define xdr_size(x) (sizeof(*x) / sizeof(__be32)) static void xdr_decode_YFSFid(const __be32 **_bp, struct afs_fid *fid) @@ -79,6 +74,11 @@ static __be32 *xdr_encode_string(__be32 *bp, const char *p, unsigned int len) return bp + len / sizeof(__be32); } +static __be32 *xdr_encode_name(__be32 *bp, const struct qstr *p) +{ + return xdr_encode_string(bp, p->name, p->len); +} + static s64 linux_to_yfs_time(const struct timespec64 *t) { /* Convert to 100ns intervals. */ @@ -179,21 +179,20 @@ static void xdr_dump_bad(const __be32 *bp) /* * Decode a YFSFetchStatus block */ -static int xdr_decode_YFSFetchStatus(const __be32 **_bp, - struct afs_call *call, - struct afs_status_cb *scb) +static void xdr_decode_YFSFetchStatus(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp; struct afs_file_status *status = &scb->status; u32 type; - int ret; status->abort_code = ntohl(xdr->abort_code); if (status->abort_code != 0) { if (status->abort_code == VNOVNODE) status->nlink = 0; scb->have_error = true; - goto good; + goto advance; } type = ntohl(xdr->type); @@ -221,15 +220,13 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp, status->size = xdr_to_u64(xdr->size); status->data_version = xdr_to_u64(xdr->data_version); scb->have_status = true; -good: - ret = 0; advance: *_bp += xdr_size(xdr); - return ret; + return; bad: xdr_dump_bad(*_bp); - ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + afs_protocol_error(call, afs_eproto_bad_status); goto advance; } @@ -339,6 +336,7 @@ static void xdr_decode_YFSFetchVolumeStatus(const __be32 **_bp, */ static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) { + struct afs_operation *op = call->op; const __be32 *bp; int ret; @@ -348,11 +346,9 @@ static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_YFSCallBack(&bp, call, call->out_scb); - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFetchStatus(&bp, call, &op->file[0].scb); + xdr_decode_YFSCallBack(&bp, call, &op->file[0].scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -364,6 +360,7 @@ static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) */ static int yfs_deliver_status_and_volsync(struct afs_call *call) { + struct afs_operation *op = call->op; const __be32 *bp; int ret; @@ -372,10 +369,8 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFetchStatus(&bp, call, &op->file[0].scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -394,44 +389,33 @@ static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = { /* * Fetch the status information for a file. */ -int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb, - struct afs_volsync *volsync) +void yfs_fs_fetch_file_status(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &yfs_RXYFSFetchStatus_vnode, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchStatus_vnode, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = volsync; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSFETCHSTATUS); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -439,7 +423,9 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb */ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) { - struct afs_read *req = call->read_request; + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[0]; + struct afs_read *req = op->fetch.req; const __be32 *bp; unsigned int size; int ret; @@ -534,14 +520,12 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_YFSCallBack(&bp, call, call->out_scb); - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_YFSCallBack(&bp, call, &vp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); - req->data_version = call->out_scb->status.data_version; - req->file_size = call->out_scb->status.size; + req->data_version = vp->scb.status.data_version; + req->file_size = vp->scb.status.size; call->unmarshall++; /* Fall through */ @@ -565,12 +549,6 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) return 0; } -static void yfs_fetch_data_destructor(struct afs_call *call) -{ - afs_put_read(call->read_request); - afs_flat_call_destructor(call); -} - /* * YFS.FetchData64 operation type */ @@ -578,25 +556,24 @@ static const struct afs_call_type yfs_RXYFSFetchData64 = { .name = "YFS.FetchData64", .op = yfs_FS_FetchData64, .deliver = yfs_deliver_fs_fetch_data64, - .destructor = yfs_fetch_data_destructor, + .destructor = afs_flat_call_destructor, }; /* * Fetch data from a file. */ -int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb, - struct afs_read *req) +void yfs_fs_fetch_data(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; + struct afs_read *req = op->fetch.req; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%llx:%llu},%llx,%llx", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode, + key_serial(op->key), vp->fid.vid, vp->fid.vnode, req->pos, req->len); - call = afs_alloc_flat_call(net, &yfs_RXYFSFetchData64, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchData64, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid) + sizeof(struct yfs_xdr_u64) * 2, @@ -604,27 +581,19 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb, sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = NULL; - call->read_request = afs_get_read(req); + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSFETCHDATA64); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); bp = xdr_encode_u64(bp, req->pos); bp = xdr_encode_u64(bp, req->len); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -632,6 +601,9 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb, */ static int yfs_deliver_fs_create_vnode(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; const __be32 *bp; int ret; @@ -643,15 +615,11 @@ static int yfs_deliver_fs_create_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_YFSFid(&bp, call->out_fid); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_YFSCallBack(&bp, call, call->out_scb); - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFid(&bp, &op->file[1].fid); + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_YFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_YFSCallBack(&bp, call, &vp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -670,26 +638,20 @@ static const struct afs_call_type afs_RXFSCreateFile = { /* * Create a file. */ -int yfs_fs_create_file(struct afs_fs_cursor *fc, - const char *name, - umode_t mode, - struct afs_status_cb *dvnode_scb, - struct afs_fid *newfid, - struct afs_status_cb *new_scb) +void yfs_fs_create_file(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); - size_t namesz, reqsz, rplsz; + size_t reqsz, rplsz; __be32 *bp; _enter(""); - namesz = strlen(name); reqsz = (sizeof(__be32) + sizeof(__be32) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(namesz) + + xdr_strlen(name->len) + sizeof(struct yfs_xdr_YFSStoreStatus) + sizeof(__be32)); rplsz = (sizeof(struct yfs_xdr_YFSFid) + @@ -698,30 +660,22 @@ int yfs_fs_create_file(struct afs_fs_cursor *fc, sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); - call = afs_alloc_flat_call(net, &afs_RXFSCreateFile, reqsz, rplsz); + call = afs_alloc_flat_call(op->net, &afs_RXFSCreateFile, reqsz, rplsz); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_fid = newfid; - call->out_scb = new_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSCREATEFILE); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &dvnode->fid); - bp = xdr_encode_string(bp, name, namesz); - bp = xdr_encode_YFSStoreStatus_mode(bp, mode); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); + bp = xdr_encode_YFSStoreStatus_mode(bp, op->create.mode); bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */ yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } static const struct afs_call_type yfs_RXFSMakeDir = { @@ -734,26 +688,20 @@ static const struct afs_call_type yfs_RXFSMakeDir = { /* * Make a directory. */ -int yfs_fs_make_dir(struct afs_fs_cursor *fc, - const char *name, - umode_t mode, - struct afs_status_cb *dvnode_scb, - struct afs_fid *newfid, - struct afs_status_cb *new_scb) +void yfs_fs_make_dir(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); - size_t namesz, reqsz, rplsz; + size_t reqsz, rplsz; __be32 *bp; _enter(""); - namesz = strlen(name); reqsz = (sizeof(__be32) + sizeof(struct yfs_xdr_RPCFlags) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(namesz) + + xdr_strlen(name->len) + sizeof(struct yfs_xdr_YFSStoreStatus)); rplsz = (sizeof(struct yfs_xdr_YFSFid) + sizeof(struct yfs_xdr_YFSFetchStatus) + @@ -761,29 +709,21 @@ int yfs_fs_make_dir(struct afs_fs_cursor *fc, sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); - call = afs_alloc_flat_call(net, &yfs_RXFSMakeDir, reqsz, rplsz); + call = afs_alloc_flat_call(op->net, &yfs_RXFSMakeDir, reqsz, rplsz); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_fid = newfid; - call->out_scb = new_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSMAKEDIR); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &dvnode->fid); - bp = xdr_encode_string(bp, name, namesz); - bp = xdr_encode_YFSStoreStatus_mode(bp, mode); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); + bp = xdr_encode_YFSStoreStatus_mode(bp, op->create.mode); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -791,6 +731,9 @@ int yfs_fs_make_dir(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_remove_file2(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; struct afs_fid fid; const __be32 *bp; int ret; @@ -802,20 +745,24 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - + xdr_decode_YFSFetchStatus(&bp, call, &dvp->scb); xdr_decode_YFSFid(&bp, &fid); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); /* Was deleted if vnode->status.abort_code == VNOVNODE. */ - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSVolSync(&bp, &op->volsync); return 0; } +static void yfs_done_fs_remove_file2(struct afs_call *call) +{ + if (call->error == -ECONNABORTED && + call->abort_code == RX_INVALID_OPERATION) { + set_bit(AFS_SERVER_FL_NO_RM2, &call->server->flags); + call->op->flags |= AFS_OPERATION_DOWNGRADE; + } +} + /* * YFS.RemoveFile2 operation type. */ @@ -823,55 +770,44 @@ static const struct afs_call_type yfs_RXYFSRemoveFile2 = { .name = "YFS.RemoveFile2", .op = yfs_FS_RemoveFile2, .deliver = yfs_deliver_fs_remove_file2, + .done = yfs_done_fs_remove_file2, .destructor = afs_flat_call_destructor, }; /* * Remove a file and retrieve new file status. */ -int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, struct afs_status_cb *dvnode_scb, - struct afs_status_cb *vnode_scb) +void yfs_fs_remove_file2(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + struct afs_vnode_param *dvp = &op->file[0]; + const struct qstr *name = &op->dentry->d_name; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); - size_t namesz; __be32 *bp; _enter(""); - namesz = strlen(name); - - call = afs_alloc_flat_call(net, &yfs_RXYFSRemoveFile2, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSRemoveFile2, sizeof(__be32) + sizeof(struct yfs_xdr_RPCFlags) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(namesz), + xdr_strlen(name->len), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSFid) + sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_scb = vnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSREMOVEFILE2); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &dvnode->fid); - bp = xdr_encode_string(bp, name, namesz); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -879,6 +815,8 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_remove(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; const __be32 *bp; int ret; @@ -889,11 +827,8 @@ static int yfs_deliver_fs_remove(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); return 0; } @@ -907,6 +842,43 @@ static const struct afs_call_type yfs_RXYFSRemoveFile = { .destructor = afs_flat_call_destructor, }; +/* + * Remove a file. + */ +void yfs_fs_remove_file(struct afs_operation *op) +{ + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_call *call; + __be32 *bp; + + _enter(""); + + if (!test_bit(AFS_SERVER_FL_NO_RM2, &op->server->flags)) + return yfs_fs_remove_file2(op); + + call = afs_alloc_flat_call(op->net, &yfs_RXYFSRemoveFile, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(name->len), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return afs_op_nomem(op); + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSREMOVEFILE); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); + yfs_check_req(call, bp); + + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); +} + static const struct afs_call_type yfs_RXYFSRemoveDir = { .name = "YFS.RemoveDir", .op = yfs_FS_RemoveDir, @@ -915,48 +887,37 @@ static const struct afs_call_type yfs_RXYFSRemoveDir = { }; /* - * remove a file or directory + * Remove a directory. */ -int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, bool isdir, - struct afs_status_cb *dvnode_scb) +void yfs_fs_remove_dir(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); - size_t namesz; __be32 *bp; _enter(""); - namesz = strlen(name); - call = afs_alloc_flat_call( - net, isdir ? &yfs_RXYFSRemoveDir : &yfs_RXYFSRemoveFile, - sizeof(__be32) + - sizeof(struct yfs_xdr_RPCFlags) + - sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(namesz), - sizeof(struct yfs_xdr_YFSFetchStatus) + - sizeof(struct yfs_xdr_YFSVolSync)); + call = afs_alloc_flat_call(op->net, &yfs_RXYFSRemoveDir, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(name->len), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; - bp = xdr_encode_u32(bp, isdir ? YFSREMOVEDIR : YFSREMOVEFILE); + bp = xdr_encode_u32(bp, YFSREMOVEDIR); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &dvnode->fid); - bp = xdr_encode_string(bp, name, namesz); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -964,6 +925,9 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_link(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; const __be32 *bp; int ret; @@ -974,13 +938,9 @@ static int yfs_deliver_fs_link(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_YFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; } @@ -998,50 +958,39 @@ static const struct afs_call_type yfs_RXYFSLink = { /* * Make a hard link. */ -int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, - struct afs_status_cb *dvnode_scb, - struct afs_status_cb *vnode_scb) +void yfs_fs_link(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); - size_t namesz; __be32 *bp; _enter(""); - namesz = strlen(name); - call = afs_alloc_flat_call(net, &yfs_RXYFSLink, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSLink, sizeof(__be32) + sizeof(struct yfs_xdr_RPCFlags) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(namesz) + + xdr_strlen(name->len) + sizeof(struct yfs_xdr_YFSFid), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_scb = vnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSLINK); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &dvnode->fid); - bp = xdr_encode_string(bp, name, namesz); - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); + bp = xdr_encode_YFSFid(bp, &vp->fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &vnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &vp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1049,6 +998,9 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_symlink(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; const __be32 *bp; int ret; @@ -1060,14 +1012,10 @@ static int yfs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_YFSFid(&bp, call->out_fid); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFid(&bp, &vp->fid); + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_YFSFetchStatus(&bp, call, &dvp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; @@ -1086,28 +1034,22 @@ static const struct afs_call_type yfs_RXYFSSymlink = { /* * Create a symbolic link. */ -int yfs_fs_symlink(struct afs_fs_cursor *fc, - const char *name, - const char *contents, - struct afs_status_cb *dvnode_scb, - struct afs_fid *newfid, - struct afs_status_cb *vnode_scb) +void yfs_fs_symlink(struct afs_operation *op) { - struct afs_vnode *dvnode = fc->vnode; + const struct qstr *name = &op->dentry->d_name; + struct afs_vnode_param *dvp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(dvnode); - size_t namesz, contents_sz; + size_t contents_sz; __be32 *bp; _enter(""); - namesz = strlen(name); - contents_sz = strlen(contents); - call = afs_alloc_flat_call(net, &yfs_RXYFSSymlink, + contents_sz = strlen(op->create.symlink); + call = afs_alloc_flat_call(op->net, &yfs_RXYFSSymlink, sizeof(__be32) + sizeof(struct yfs_xdr_RPCFlags) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(namesz) + + xdr_strlen(name->len) + xdr_strlen(contents_sz) + sizeof(struct yfs_xdr_YFSStoreStatus), sizeof(struct yfs_xdr_YFSFid) + @@ -1115,28 +1057,20 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = dvnode_scb; - call->out_fid = newfid; - call->out_scb = vnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSSYMLINK); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &dvnode->fid); - bp = xdr_encode_string(bp, name, namesz); - bp = xdr_encode_string(bp, contents, contents_sz); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_name(bp, name); + bp = xdr_encode_string(bp, op->create.symlink, contents_sz); bp = xdr_encode_YFSStoreStatus_mode(bp, S_IRWXUGO); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &dvnode->fid, name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call1(call, &dvp->fid, name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1144,6 +1078,9 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_rename(struct afs_call *call) { + struct afs_operation *op = call->op; + struct afs_vnode_param *orig_dvp = &op->file[0]; + struct afs_vnode_param *new_dvp = &op->file[1]; const __be32 *bp; int ret; @@ -1154,14 +1091,12 @@ static int yfs_deliver_fs_rename(struct afs_call *call) return ret; bp = call->buffer; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); - if (ret < 0) - return ret; - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - - xdr_decode_YFSVolSync(&bp, call->out_volsync); + /* If the two dirs are the same, we have two copies of the same status + * report, so we just decode it twice. + */ + xdr_decode_YFSFetchStatus(&bp, call, &orig_dvp->scb); + xdr_decode_YFSFetchStatus(&bp, call, &new_dvp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); _leave(" = 0 [done]"); return 0; } @@ -1179,55 +1114,42 @@ static const struct afs_call_type yfs_RXYFSRename = { /* * Rename a file or directory. */ -int yfs_fs_rename(struct afs_fs_cursor *fc, - const char *orig_name, - struct afs_vnode *new_dvnode, - const char *new_name, - struct afs_status_cb *orig_dvnode_scb, - struct afs_status_cb *new_dvnode_scb) +void yfs_fs_rename(struct afs_operation *op) { - struct afs_vnode *orig_dvnode = fc->vnode; + struct afs_vnode_param *orig_dvp = &op->file[0]; + struct afs_vnode_param *new_dvp = &op->file[1]; + const struct qstr *orig_name = &op->dentry->d_name; + const struct qstr *new_name = &op->dentry_2->d_name; struct afs_call *call; - struct afs_net *net = afs_v2net(orig_dvnode); - size_t o_namesz, n_namesz; __be32 *bp; _enter(""); - o_namesz = strlen(orig_name); - n_namesz = strlen(new_name); - call = afs_alloc_flat_call(net, &yfs_RXYFSRename, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSRename, sizeof(__be32) + sizeof(struct yfs_xdr_RPCFlags) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(o_namesz) + + xdr_strlen(orig_name->len) + sizeof(struct yfs_xdr_YFSFid) + - xdr_strlen(n_namesz), + xdr_strlen(new_name->len), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_dir_scb = orig_dvnode_scb; - call->out_scb = new_dvnode_scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSRENAME); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &orig_dvnode->fid); - bp = xdr_encode_string(bp, orig_name, o_namesz); - bp = xdr_encode_YFSFid(bp, &new_dvnode->fid); - bp = xdr_encode_string(bp, new_name, n_namesz); + bp = xdr_encode_YFSFid(bp, &orig_dvp->fid); + bp = xdr_encode_name(bp, orig_name); + bp = xdr_encode_YFSFid(bp, &new_dvp->fid); + bp = xdr_encode_name(bp, new_name); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call2(call, &orig_dvnode->fid, orig_name, new_name); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call2(call, &orig_dvp->fid, orig_name, new_name); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1243,27 +1165,23 @@ static const struct afs_call_type yfs_RXYFSStoreData64 = { /* * Store a set of pages to a large file. */ -int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, - pgoff_t first, pgoff_t last, - unsigned offset, unsigned to, - struct afs_status_cb *scb) +void yfs_fs_store_data(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); loff_t size, pos, i_size; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - size = (loff_t)to - (loff_t)offset; - if (first != last) - size += (loff_t)(last - first) << PAGE_SHIFT; - pos = (loff_t)first << PAGE_SHIFT; - pos += offset; + size = (loff_t)op->store.last_to - (loff_t)op->store.first_offset; + if (op->store.first != op->store.last) + size += (loff_t)(op->store.last - op->store.first) << PAGE_SHIFT; + pos = (loff_t)op->store.first << PAGE_SHIFT; + pos += op->store.first_offset; - i_size = i_size_read(&vnode->vfs_inode); + i_size = i_size_read(&vp->vnode->vfs_inode); if (pos + size > i_size) i_size = size + pos; @@ -1271,7 +1189,7 @@ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, (unsigned long long)size, (unsigned long long)pos, (unsigned long long)i_size); - call = afs_alloc_flat_call(net, &yfs_RXYFSStoreData64, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSStoreData64, sizeof(__be32) + sizeof(__be32) + sizeof(struct yfs_xdr_YFSFid) + @@ -1280,33 +1198,24 @@ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->mapping = mapping; - call->first = first; - call->last = last; - call->first_offset = offset; - call->last_to = to; + return afs_op_nomem(op); + + call->key = op->key; call->send_pages = true; - call->out_scb = scb; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSSTOREDATA64); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); - bp = xdr_encode_YFSStoreStatus_mtime(bp, &vnode->vfs_inode.i_mtime); + bp = xdr_encode_YFSFid(bp, &vp->fid); + bp = xdr_encode_YFSStoreStatus_mtime(bp, &op->mtime); bp = xdr_encode_u64(bp, pos); bp = xdr_encode_u64(bp, size); bp = xdr_encode_u64(bp, i_size); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1330,18 +1239,17 @@ static const struct afs_call_type yfs_RXYFSStoreData64_as_Status = { * Set the attributes on a file, using YFS.StoreData64 rather than * YFS.StoreStatus so as to alter the file size also. */ -static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, - struct afs_status_cb *scb) +static void yfs_fs_setattr_size(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct iattr *attr = op->setattr.attr; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &yfs_RXYFSStoreData64_as_Status, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSStoreData64_as_Status, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid) + sizeof(struct yfs_xdr_YFSStoreStatus) + @@ -1349,72 +1257,59 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSSTOREDATA64); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); bp = xdr_encode_YFS_StoreStatus(bp, attr); bp = xdr_encode_u64(bp, attr->ia_size); /* position of start of write */ bp = xdr_encode_u64(bp, 0); /* size of write */ bp = xdr_encode_u64(bp, attr->ia_size); /* new file length */ yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * Set the attributes on a file, using YFS.StoreData64 if there's a change in * file size, and YFS.StoreStatus otherwise. */ -int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, - struct afs_status_cb *scb) +void yfs_fs_setattr(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct iattr *attr = op->setattr.attr; __be32 *bp; if (attr->ia_valid & ATTR_SIZE) - return yfs_fs_setattr_size(fc, attr, scb); + return yfs_fs_setattr_size(op); _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSStoreStatus, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid) + sizeof(struct yfs_xdr_YFSStoreStatus), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSSTORESTATUS); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); bp = xdr_encode_YFS_StoreStatus(bp, attr); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1422,6 +1317,7 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, */ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) { + struct afs_operation *op = call->op; const __be32 *bp; char *p; u32 size; @@ -1443,7 +1339,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus); + xdr_decode_YFSFetchVolumeStatus(&bp, &op->volstatus.vs); call->unmarshall++; afs_extract_to_tmp(call); /* Fall through */ @@ -1457,8 +1353,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) call->count = ntohl(call->tmp); _debug("volname length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_volname_len); + return afs_protocol_error(call, afs_eproto_volname_len); size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; @@ -1487,8 +1382,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) call->count = ntohl(call->tmp); _debug("offline msg length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_offline_msg_len); + return afs_protocol_error(call, afs_eproto_offline_msg_len); size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; @@ -1518,8 +1412,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) call->count = ntohl(call->tmp); _debug("motd length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_motd_len); + return afs_protocol_error(call, afs_eproto_motd_len); size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; @@ -1560,17 +1453,15 @@ static const struct afs_call_type yfs_RXYFSGetVolumeStatus = { /* * fetch the status of a volume */ -int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, - struct afs_volume_status *vs) +void yfs_fs_get_volume_status(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(net, &yfs_RXYFSGetVolumeStatus, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSGetVolumeStatus, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_u64), max_t(size_t, @@ -1578,23 +1469,17 @@ int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, sizeof(__be32), AFSOPAQUEMAX + 1)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->out_volstatus = vs; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSGETVOLUMESTATUS); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_u64(bp, vnode->fid.vid); + bp = xdr_encode_u64(bp, vp->fid.vid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1632,118 +1517,93 @@ static const struct afs_call_type yfs_RXYFSReleaseLock = { /* * Set a lock on a file */ -int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type, - struct afs_status_cb *scb) +void yfs_fs_set_lock(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(net, &yfs_RXYFSSetLock, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSSetLock, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid) + sizeof(__be32), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->lvnode = vnode; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSSETLOCK); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); - bp = xdr_encode_u32(bp, type); + bp = xdr_encode_YFSFid(bp, &vp->fid); + bp = xdr_encode_u32(bp, op->lock.type); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_calli(call, &vnode->fid, type); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_calli(call, &vp->fid, op->lock.type); + afs_make_op_call(op, call, GFP_NOFS); } /* * extend a lock on a file */ -int yfs_fs_extend_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) +void yfs_fs_extend_lock(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(net, &yfs_RXYFSExtendLock, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSExtendLock, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->lvnode = vnode; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSEXTENDLOCK); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* * release a lock on a file */ -int yfs_fs_release_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) +void yfs_fs_release_lock(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(net, &yfs_RXYFSReleaseLock, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSReleaseLock, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); if (!call) - return -ENOMEM; - - call->key = fc->key; - call->lvnode = vnode; - call->out_scb = scb; + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSRELEASELOCK); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1759,45 +1619,33 @@ static const struct afs_call_type yfs_RXYFSFetchStatus = { /* * Fetch the status information for a fid without needing a vnode handle. */ -int yfs_fs_fetch_status(struct afs_fs_cursor *fc, - struct afs_net *net, - struct afs_fid *fid, - struct afs_status_cb *scb, - struct afs_volsync *volsync) +void yfs_fs_fetch_status(struct afs_operation *op) { + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), fid->vid, fid->vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &yfs_RXYFSFetchStatus, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchStatus, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid), sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = volsync; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSFETCHSTATUS); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, fid); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1805,6 +1653,7 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) { + struct afs_operation *op = call->op; struct afs_status_cb *scb; const __be32 *bp; u32 tmp; @@ -1826,10 +1675,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; tmp = ntohl(call->tmp); - _debug("status count: %u/%u", tmp, call->count2); - if (tmp != call->count2) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_ibulkst_count); + _debug("status count: %u/%u", tmp, op->nr_files); + if (tmp != op->nr_files) + return afs_protocol_error(call, afs_eproto_ibulkst_count); call->count = 0; call->unmarshall++; @@ -1843,14 +1691,23 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) if (ret < 0) return ret; + switch (call->count) { + case 0: + scb = &op->file[0].scb; + break; + case 1: + scb = &op->file[1].scb; + break; + default: + scb = &op->more_files[call->count - 2].scb; + break; + } + bp = call->buffer; - scb = &call->out_scb[call->count]; - ret = xdr_decode_YFSFetchStatus(&bp, call, scb); - if (ret < 0) - return ret; + xdr_decode_YFSFetchStatus(&bp, call, scb); call->count++; - if (call->count < call->count2) + if (call->count < op->nr_files) goto more_counts; call->count = 0; @@ -1867,9 +1724,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) tmp = ntohl(call->tmp); _debug("CB count: %u", tmp); - if (tmp != call->count2) - return afs_protocol_error(call, -EBADMSG, - afs_eproto_ibulkst_cb_count); + if (tmp != op->nr_files) + return afs_protocol_error(call, afs_eproto_ibulkst_cb_count); call->count = 0; call->unmarshall++; more_cbs: @@ -1883,11 +1739,22 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; _debug("unmarshall CB array"); + switch (call->count) { + case 0: + scb = &op->file[0].scb; + break; + case 1: + scb = &op->file[1].scb; + break; + default: + scb = &op->more_files[call->count - 2].scb; + break; + } + bp = call->buffer; - scb = &call->out_scb[call->count]; xdr_decode_YFSCallBack(&bp, call, scb); call->count++; - if (call->count < call->count2) + if (call->count < op->nr_files) goto more_cbs; afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); @@ -1900,7 +1767,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSVolSync(&bp, &op->volsync); call->unmarshall++; /* Fall through */ @@ -1926,50 +1793,39 @@ static const struct afs_call_type yfs_RXYFSInlineBulkStatus = { /* * Fetch the status information for up to 1024 files */ -int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, - struct afs_net *net, - struct afs_fid *fids, - struct afs_status_cb *statuses, - unsigned int nr_fids, - struct afs_volsync *volsync) +void yfs_fs_inline_bulk_status(struct afs_operation *op) { + struct afs_vnode_param *dvp = &op->file[0]; + struct afs_vnode_param *vp = &op->file[1]; struct afs_call *call; __be32 *bp; int i; _enter(",%x,{%llx:%llu},%u", - key_serial(fc->key), fids[0].vid, fids[1].vnode, nr_fids); + key_serial(op->key), vp->fid.vid, vp->fid.vnode, op->nr_files); - call = afs_alloc_flat_call(net, &yfs_RXYFSInlineBulkStatus, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSInlineBulkStatus, sizeof(__be32) + sizeof(__be32) + sizeof(__be32) + - sizeof(struct yfs_xdr_YFSFid) * nr_fids, + sizeof(struct yfs_xdr_YFSFid) * op->nr_files, sizeof(struct yfs_xdr_YFSFetchStatus)); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = statuses; - call->out_volsync = volsync; - call->count2 = nr_fids; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSINLINEBULKSTATUS); bp = xdr_encode_u32(bp, 0); /* RPCFlags */ - bp = xdr_encode_u32(bp, nr_fids); - for (i = 0; i < nr_fids; i++) - bp = xdr_encode_YFSFid(bp, &fids[i]); + bp = xdr_encode_u32(bp, op->nr_files); + bp = xdr_encode_YFSFid(bp, &dvp->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); + for (i = 0; i < op->nr_files - 2; i++) + bp = xdr_encode_YFSFid(bp, &op->more_files[i].fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &fids[0]); - afs_set_fc_call(call, fc); - afs_make_call(&fc->ac, call, GFP_NOFS); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_NOFS); } /* @@ -1977,7 +1833,9 @@ int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) { - struct yfs_acl *yacl = call->out_yacl; + struct afs_operation *op = call->op; + struct afs_vnode_param *vp = &op->file[0]; + struct yfs_acl *yacl = op->yacl; struct afs_acl *acl; const __be32 *bp; unsigned int size; @@ -2067,10 +1925,8 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) bp = call->buffer; yacl->inherit_flag = ntohl(*bp++); yacl->num_cleaned = ntohl(*bp++); - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, call->out_volsync); + xdr_decode_YFSFetchStatus(&bp, call, &vp->scb); + xdr_decode_YFSVolSync(&bp, &op->volsync); call->unmarshall++; /* Fall through */ @@ -2105,45 +1961,33 @@ static const struct afs_call_type yfs_RXYFSFetchOpaqueACL = { /* * Fetch the YFS advanced ACLs for a file. */ -struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *fc, - struct yfs_acl *yacl, - struct afs_status_cb *scb) +void yfs_fs_fetch_opaque_acl(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); - call = afs_alloc_flat_call(net, &yfs_RXYFSFetchOpaqueACL, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchOpaqueACL, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid), sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); - if (!call) { - fc->ac.error = -ENOMEM; - return ERR_PTR(-ENOMEM); - } - - call->key = fc->key; - call->out_yacl = yacl; - call->out_scb = scb; - call->out_volsync = NULL; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSFETCHOPAQUEACL); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); yfs_check_req(call, bp); - afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); - afs_make_call(&fc->ac, call, GFP_KERNEL); - return (struct yfs_acl *)afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_KERNEL); } /* @@ -2159,46 +2003,38 @@ static const struct afs_call_type yfs_RXYFSStoreOpaqueACL2 = { /* * Fetch the YFS ACL for a file. */ -int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl, - struct afs_status_cb *scb) +void yfs_fs_store_opaque_acl2(struct afs_operation *op) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_acl *acl = op->acl; size_t size; __be32 *bp; _enter(",%x,{%llx:%llu},,", - key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + key_serial(op->key), vp->fid.vid, vp->fid.vnode); size = round_up(acl->size, 4); - call = afs_alloc_flat_call(net, &yfs_RXYFSStoreOpaqueACL2, + call = afs_alloc_flat_call(op->net, &yfs_RXYFSStoreOpaqueACL2, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid) + sizeof(__be32) + size, sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); - if (!call) { - fc->ac.error = -ENOMEM; - return -ENOMEM; - } - - call->key = fc->key; - call->out_scb = scb; - call->out_volsync = NULL; + if (!call) + return afs_op_nomem(op); /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSSTOREOPAQUEACL2); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &vp->fid); bp = xdr_encode_u32(bp, acl->size); memcpy(bp, acl->data, acl->size); if (acl->size != size) memset((void *)bp + acl->size, 0, size - acl->size); yfs_check_req(call, bp); - trace_afs_make_fs_call(call, &vnode->fid); - afs_make_call(&fc->ac, call, GFP_KERNEL); - return afs_wait_for_call_to_complete(call, &fc->ac); + trace_afs_make_fs_call(call, &vp->fid); + afs_make_op_call(op, call, GFP_KERNEL); } diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 8035d2a44561..54f0ce444272 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -15,6 +15,7 @@ #include <linux/time.h> #include <linux/namei.h> #include <linux/poll.h> +#include <linux/fiemap.h> static int bad_file_open(struct inode *inode, struct file *filp) { diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 8e8346a81723..3e84e9bb9084 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -151,7 +151,7 @@ static int load_aout_binary(struct linux_binprm * bprm) return -ENOMEM; /* Flush all traces of the currently running executable */ - retval = flush_old_exec(bprm); + retval = begin_new_exec(bprm); if (retval) return retval; @@ -174,7 +174,6 @@ static int load_aout_binary(struct linux_binprm * bprm) if (retval < 0) return retval; - install_exec_creds(bprm); if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8945671fe0e5..e5d50bd880e9 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -279,8 +279,8 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, NEW_AUX_ENT(AT_BASE_PLATFORM, (elf_addr_t)(unsigned long)u_base_platform); } - if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) { - NEW_AUX_ENT(AT_EXECFD, bprm->interp_data); + if (bprm->have_execfd) { + NEW_AUX_ENT(AT_EXECFD, bprm->execfd); } #undef NEW_AUX_ENT /* AT_NULL is zero; clear the rest too */ @@ -353,8 +353,6 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, return 0; } -#ifndef elf_map - static unsigned long elf_map(struct file *filep, unsigned long addr, const struct elf_phdr *eppnt, int prot, int type, unsigned long total_size) @@ -394,8 +392,6 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, return(map_addr); } -#endif /* !elf_map */ - static unsigned long total_mapping_size(const struct elf_phdr *cmds, int nr) { int i, first_idx = -1, last_idx = -1; @@ -975,7 +971,7 @@ out_free_interp: goto out_free_dentry; /* Flush all traces of the currently running executable */ - retval = flush_old_exec(bprm); + retval = begin_new_exec(bprm); if (retval) goto out_free_dentry; @@ -989,7 +985,6 @@ out_free_interp: current->flags |= PF_RANDOMIZE; setup_new_exec(bprm); - install_exec_creds(bprm); /* Do this so that we can load the interpreter, if need be. We will change some of these later */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index d9501a86cec9..aaf332d32326 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -338,7 +338,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) interp_params.flags |= ELF_FDPIC_FLAG_CONSTDISP; /* flush all traces of the currently running executable */ - retval = flush_old_exec(bprm); + retval = begin_new_exec(bprm); if (retval) goto error; @@ -434,7 +434,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->start_stack = current->mm->start_brk + stack_size; #endif - install_exec_creds(bprm); if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0) goto error; @@ -589,7 +588,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) + (k_base_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH; - if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) + if (bprm->have_execfd) nitems++; csp = sp; @@ -629,10 +628,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, (elf_addr_t) (unsigned long) u_base_platform); } - if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) { + if (bprm->have_execfd) { nr = 0; csp -= 2 * sizeof(unsigned long); - NEW_AUX_ENT(AT_EXECFD, bprm->interp_data); + NEW_AUX_ENT(AT_EXECFD, bprm->execfd); } nr = 0; diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c index 466497860c62..06b9b9fddf70 100644 --- a/fs/binfmt_em86.c +++ b/fs/binfmt_em86.c @@ -48,10 +48,6 @@ static int load_em86(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; - allow_write_access(bprm->file); - fput(bprm->file); - bprm->file = NULL; - /* Unlike in the script case, we don't have to do any hairy * parsing to find our interpreter... it's hardcoded! */ @@ -68,15 +64,15 @@ static int load_em86(struct linux_binprm *bprm) * user environment and arguments are stored. */ remove_arg_zero(bprm); - retval = copy_strings_kernel(1, &bprm->filename, bprm); + retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) return retval; bprm->argc++; if (i_arg) { - retval = copy_strings_kernel(1, &i_arg, bprm); + retval = copy_string_kernel(i_arg, bprm); if (retval < 0) return retval; bprm->argc++; } - retval = copy_strings_kernel(1, &i_name, bprm); + retval = copy_string_kernel(i_name, bprm); if (retval < 0) return retval; bprm->argc++; @@ -89,13 +85,8 @@ static int load_em86(struct linux_binprm *bprm) if (IS_ERR(file)) return PTR_ERR(file); - bprm->file = file; - - retval = prepare_binprm(bprm); - if (retval < 0) - return retval; - - return search_binary_handler(bprm); + bprm->interpreter = file; + return 0; } static struct linux_binfmt em86_format = { diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 831a2b25ba79..9b82bc111d0a 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -534,7 +534,7 @@ static int load_flat_file(struct linux_binprm *bprm, /* Flush all traces of the currently running executable */ if (id == 0) { - ret = flush_old_exec(bprm); + ret = begin_new_exec(bprm); if (ret) goto err; @@ -963,8 +963,6 @@ static int load_flat_binary(struct linux_binprm *bprm) } } - install_exec_creds(bprm); - set_binfmt(&flat_format); #ifdef CONFIG_MMU diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index cdb45829354d..3880a82da1dc 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -134,7 +134,6 @@ static int load_misc_binary(struct linux_binprm *bprm) Node *fmt; struct file *interp_file = NULL; int retval; - int fd_binary = -1; retval = -ENOEXEC; if (!enabled) @@ -160,51 +159,25 @@ static int load_misc_binary(struct linux_binprm *bprm) goto ret; } - if (fmt->flags & MISC_FMT_OPEN_BINARY) { + if (fmt->flags & MISC_FMT_OPEN_BINARY) + bprm->have_execfd = 1; - /* if the binary should be opened on behalf of the - * interpreter than keep it open and assign descriptor - * to it - */ - fd_binary = get_unused_fd_flags(0); - if (fd_binary < 0) { - retval = fd_binary; - goto ret; - } - fd_install(fd_binary, bprm->file); - - /* if the binary is not readable than enforce mm->dumpable=0 - regardless of the interpreter's permissions */ - would_dump(bprm, bprm->file); - - allow_write_access(bprm->file); - bprm->file = NULL; - - /* mark the bprm that fd should be passed to interp */ - bprm->interp_flags |= BINPRM_FLAGS_EXECFD; - bprm->interp_data = fd_binary; - - } else { - allow_write_access(bprm->file); - fput(bprm->file); - bprm->file = NULL; - } /* make argv[1] be the path to the binary */ - retval = copy_strings_kernel(1, &bprm->interp, bprm); + retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) - goto error; + goto ret; bprm->argc++; /* add the interp as argv[0] */ - retval = copy_strings_kernel(1, &fmt->interpreter, bprm); + retval = copy_string_kernel(fmt->interpreter, bprm); if (retval < 0) - goto error; + goto ret; bprm->argc++; /* Update interp in case binfmt_script needs it. */ retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) - goto error; + goto ret; if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); @@ -215,38 +188,16 @@ static int load_misc_binary(struct linux_binprm *bprm) } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) - goto error; - - bprm->file = interp_file; - if (fmt->flags & MISC_FMT_CREDENTIALS) { - loff_t pos = 0; - - /* - * No need to call prepare_binprm(), it's already been - * done. bprm->buf is stale, update from interp_file. - */ - memset(bprm->buf, 0, BINPRM_BUF_SIZE); - retval = kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, - &pos); - } else - retval = prepare_binprm(bprm); - - if (retval < 0) - goto error; + goto ret; - retval = search_binary_handler(bprm); - if (retval < 0) - goto error; + bprm->interpreter = interp_file; + if (fmt->flags & MISC_FMT_CREDENTIALS) + bprm->execfd_creds = 1; + retval = 0; ret: dput(fmt->dentry); return retval; -error: - if (fd_binary > 0) - ksys_close(fd_binary); - bprm->interp_flags = 0; - bprm->interp_data = 0; - goto ret; } /* Command parsers */ diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index e9e6a6f4a35f..1b6625e95958 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -16,14 +16,14 @@ #include <linux/fs.h> static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } -static inline char *next_non_spacetab(char *first, const char *last) +static inline const char *next_non_spacetab(const char *first, const char *last) { for (; first <= last; first++) if (!spacetab(*first)) return first; return NULL; } -static inline char *next_terminator(char *first, const char *last) +static inline const char *next_terminator(const char *first, const char *last) { for (; first <= last; first++) if (spacetab(*first) || !*first) @@ -33,8 +33,7 @@ static inline char *next_terminator(char *first, const char *last) static int load_script(struct linux_binprm *bprm) { - const char *i_arg, *i_name; - char *cp, *buf_end; + const char *i_name, *i_sep, *i_arg, *i_end, *buf_end; struct file *file; int retval; @@ -43,20 +42,6 @@ static int load_script(struct linux_binprm *bprm) return -ENOEXEC; /* - * If the script filename will be inaccessible after exec, typically - * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give - * up now (on the assumption that the interpreter will want to load - * this file). - */ - if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; - - /* Release since we are not mapping a binary into memory. */ - allow_write_access(bprm->file); - fput(bprm->file); - bprm->file = NULL; - - /* * This section handles parsing the #! line into separate * interpreter path and argument strings. We must be careful * because bprm->buf is not yet guaranteed to be NUL-terminated @@ -71,39 +56,43 @@ static int load_script(struct linux_binprm *bprm) * parse them on its own. */ buf_end = bprm->buf + sizeof(bprm->buf) - 1; - cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); - if (!cp) { - cp = next_non_spacetab(bprm->buf + 2, buf_end); - if (!cp) + i_end = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!i_end) { + i_end = next_non_spacetab(bprm->buf + 2, buf_end); + if (!i_end) return -ENOEXEC; /* Entire buf is spaces/tabs */ /* * If there is no later space/tab/NUL we must assume the * interpreter path is truncated. */ - if (!next_terminator(cp, buf_end)) + if (!next_terminator(i_end, buf_end)) return -ENOEXEC; - cp = buf_end; + i_end = buf_end; } - /* NUL-terminate the buffer and any trailing spaces/tabs. */ - *cp = '\0'; - while (cp > bprm->buf) { - cp--; - if ((*cp == ' ') || (*cp == '\t')) - *cp = '\0'; - else - break; - } - for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++); - if (*cp == '\0') + /* Trim any trailing spaces/tabs from i_end */ + while (spacetab(i_end[-1])) + i_end--; + + /* Skip over leading spaces/tabs */ + i_name = next_non_spacetab(bprm->buf+2, i_end); + if (!i_name || (i_name == i_end)) return -ENOEXEC; /* No interpreter name found */ - i_name = cp; + + /* Is there an optional argument? */ i_arg = NULL; - for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++) - /* nothing */ ; - while ((*cp == ' ') || (*cp == '\t')) - *cp++ = '\0'; - if (*cp) - i_arg = cp; + i_sep = next_terminator(i_name, i_end); + if (i_sep && (*i_sep != '\0')) + i_arg = next_non_spacetab(i_sep, i_end); + + /* + * If the script filename will be inaccessible after exec, typically + * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give + * up now (on the assumption that the interpreter will want to load + * this file). + */ + if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) + return -ENOENT; + /* * OK, we've parsed out the interpreter name and * (optional) argument. @@ -117,17 +106,19 @@ static int load_script(struct linux_binprm *bprm) retval = remove_arg_zero(bprm); if (retval) return retval; - retval = copy_strings_kernel(1, &bprm->interp, bprm); + retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) return retval; bprm->argc++; + *((char *)i_end) = '\0'; if (i_arg) { - retval = copy_strings_kernel(1, &i_arg, bprm); + *((char *)i_sep) = '\0'; + retval = copy_string_kernel(i_arg, bprm); if (retval < 0) return retval; bprm->argc++; } - retval = copy_strings_kernel(1, &i_name, bprm); + retval = copy_string_kernel(i_name, bprm); if (retval) return retval; bprm->argc++; @@ -142,11 +133,8 @@ static int load_script(struct linux_binprm *bprm) if (IS_ERR(file)) return PTR_ERR(file); - bprm->file = file; - retval = prepare_binprm(bprm); - if (retval < 0) - return retval; - return search_binary_handler(bprm); + bprm->interpreter = file; + return 0; } static struct linux_binfmt script_format = { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 602bf3af9fb4..87f60a48f750 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -5,6 +5,7 @@ #include <linux/rbtree.h> #include <linux/refcount.h> +#include <linux/fiemap.h> #include "ulist.h" /* diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 768c8be4c765..31ac8c682f19 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7828,14 +7828,12 @@ const struct iomap_dio_ops btrfs_dops = { .submit_io = btrfs_submit_direct, }; -#define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC) - static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { int ret; - ret = fiemap_check_flags(fieinfo, BTRFS_FIEMAP_FLAGS); + ret = fiemap_prep(inode, fieinfo, start, &len, 0); if (ret) return ret; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 916567d770f5..3ad1a98fd567 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -221,6 +221,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) struct cifs_ses *ses; struct cifs_tcon *tcon; int i, j; + const char *security_types[] = {"Unspecified", "LANMAN", "NTLM", + "NTLMv2", "RawNTLMSSP", "Kerberos"}; seq_puts(m, "Display Internal CIFS Data Structures for Debugging\n" @@ -375,6 +377,10 @@ skip_rdma: ses->ses_count, ses->serverOS, ses->serverNOS, ses->capabilities, ses->status); } + + seq_printf(m,"Security type: %s\n", + security_types[server->ops->select_sectype(server, ses->sectype)]); + if (server->rdma) seq_printf(m, "RDMA\n\t"); seq_printf(m, "TCP status: %d Instance: %d\n\tLocal Users To " diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index 100b0056a369..5e66dab712d0 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -8,6 +8,12 @@ #ifndef _H_CIFS_DEBUG #define _H_CIFS_DEBUG +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "CIFS: " fmt + void cifs_dump_mem(char *label, void *data, int length); void cifs_dump_detail(void *buf, struct TCP_Server_Info *ptcp_info); void cifs_dump_mids(struct TCP_Server_Info *); @@ -46,92 +52,81 @@ extern int cifsFYI; */ /* Information level messages, minor events */ -#define cifs_info_func(ratefunc, fmt, ...) \ -do { \ - pr_info_ ## ratefunc("CIFS: " fmt, ##__VA_ARGS__); \ -} while (0) +#define cifs_info_func(ratefunc, fmt, ...) \ + pr_info_ ## ratefunc(fmt, ##__VA_ARGS__) -#define cifs_info(fmt, ...) \ -do { \ - cifs_info_func(ratelimited, fmt, ##__VA_ARGS__); \ -} while (0) +#define cifs_info(fmt, ...) \ + cifs_info_func(ratelimited, fmt, ##__VA_ARGS__) /* information message: e.g., configuration, major event */ -#define cifs_dbg_func(ratefunc, type, fmt, ...) \ -do { \ - if ((type) & FYI && cifsFYI & CIFS_INFO) { \ - pr_debug_ ## ratefunc("%s: " \ - fmt, __FILE__, ##__VA_ARGS__); \ - } else if ((type) & VFS) { \ - pr_err_ ## ratefunc("CIFS VFS: " \ - fmt, ##__VA_ARGS__); \ - } else if ((type) & NOISY && (NOISY != 0)) { \ - pr_debug_ ## ratefunc(fmt, ##__VA_ARGS__); \ - } \ +#define cifs_dbg_func(ratefunc, type, fmt, ...) \ +do { \ + if ((type) & FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ ## ratefunc("%s: " fmt, \ + __FILE__, ##__VA_ARGS__); \ + } else if ((type) & VFS) { \ + pr_err_ ## ratefunc("VFS: " fmt, ##__VA_ARGS__); \ + } else if ((type) & NOISY && (NOISY != 0)) { \ + pr_debug_ ## ratefunc(fmt, ##__VA_ARGS__); \ + } \ } while (0) -#define cifs_dbg(type, fmt, ...) \ -do { \ - if ((type) & ONCE) \ - cifs_dbg_func(once, \ - type, fmt, ##__VA_ARGS__); \ - else \ - cifs_dbg_func(ratelimited, \ - type, fmt, ##__VA_ARGS__); \ +#define cifs_dbg(type, fmt, ...) \ +do { \ + if ((type) & ONCE) \ + cifs_dbg_func(once, type, fmt, ##__VA_ARGS__); \ + else \ + cifs_dbg_func(ratelimited, type, fmt, ##__VA_ARGS__); \ } while (0) -#define cifs_server_dbg_func(ratefunc, type, fmt, ...) \ -do { \ - const char *sn = ""; \ - if (server && server->hostname) \ - sn = server->hostname; \ - if ((type) & FYI && cifsFYI & CIFS_INFO) { \ - pr_debug_ ## ratefunc("%s: \\\\%s " fmt, \ - __FILE__, sn, ##__VA_ARGS__); \ - } else if ((type) & VFS) { \ - pr_err_ ## ratefunc("CIFS VFS: \\\\%s " fmt, \ - sn, ##__VA_ARGS__); \ - } else if ((type) & NOISY && (NOISY != 0)) { \ - pr_debug_ ## ratefunc("\\\\%s " fmt, \ - sn, ##__VA_ARGS__); \ - } \ +#define cifs_server_dbg_func(ratefunc, type, fmt, ...) \ +do { \ + const char *sn = ""; \ + if (server && server->hostname) \ + sn = server->hostname; \ + if ((type) & FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ ## ratefunc("%s: \\\\%s " fmt, \ + __FILE__, sn, ##__VA_ARGS__); \ + } else if ((type) & VFS) { \ + pr_err_ ## ratefunc("VFS: \\\\%s " fmt, \ + sn, ##__VA_ARGS__); \ + } else if ((type) & NOISY && (NOISY != 0)) { \ + pr_debug_ ## ratefunc("\\\\%s " fmt, \ + sn, ##__VA_ARGS__); \ + } \ } while (0) -#define cifs_server_dbg(type, fmt, ...) \ -do { \ - if ((type) & ONCE) \ - cifs_server_dbg_func(once, \ - type, fmt, ##__VA_ARGS__); \ - else \ - cifs_server_dbg_func(ratelimited, \ - type, fmt, ##__VA_ARGS__); \ +#define cifs_server_dbg(type, fmt, ...) \ +do { \ + if ((type) & ONCE) \ + cifs_server_dbg_func(once, type, fmt, ##__VA_ARGS__); \ + else \ + cifs_server_dbg_func(ratelimited, type, fmt, \ + ##__VA_ARGS__); \ } while (0) -#define cifs_tcon_dbg_func(ratefunc, type, fmt, ...) \ -do { \ - const char *tn = ""; \ - if (tcon && tcon->treeName) \ - tn = tcon->treeName; \ - if ((type) & FYI && cifsFYI & CIFS_INFO) { \ - pr_debug_ ## ratefunc("%s: %s " fmt, \ - __FILE__, tn, ##__VA_ARGS__); \ - } else if ((type) & VFS) { \ - pr_err_ ## ratefunc("CIFS VFS: %s " fmt, \ - tn, ##__VA_ARGS__); \ - } else if ((type) & NOISY && (NOISY != 0)) { \ - pr_debug_ ## ratefunc("%s " fmt, \ - tn, ##__VA_ARGS__); \ - } \ +#define cifs_tcon_dbg_func(ratefunc, type, fmt, ...) \ +do { \ + const char *tn = ""; \ + if (tcon && tcon->treeName) \ + tn = tcon->treeName; \ + if ((type) & FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ ## ratefunc("%s: %s " fmt, \ + __FILE__, tn, ##__VA_ARGS__); \ + } else if ((type) & VFS) { \ + pr_err_ ## ratefunc("VFS: %s " fmt, tn, ##__VA_ARGS__); \ + } else if ((type) & NOISY && (NOISY != 0)) { \ + pr_debug_ ## ratefunc("%s " fmt, tn, ##__VA_ARGS__); \ + } \ } while (0) -#define cifs_tcon_dbg(type, fmt, ...) \ -do { \ - if ((type) & ONCE) \ - cifs_tcon_dbg_func(once, \ - type, fmt, ##__VA_ARGS__); \ - else \ - cifs_tcon_dbg_func(ratelimited, \ - type, fmt, ##__VA_ARGS__); \ +#define cifs_tcon_dbg(type, fmt, ...) \ +do { \ + if ((type) & ONCE) \ + cifs_tcon_dbg_func(once, type, fmt, ##__VA_ARGS__); \ + else \ + cifs_tcon_dbg_func(ratelimited, type, fmt, \ + ##__VA_ARGS__); \ } while (0) /* @@ -159,9 +154,7 @@ do { \ } while (0) #define cifs_info(fmt, ...) \ -do { \ - pr_info("CIFS: "fmt, ##__VA_ARGS__); \ -} while (0) + pr_info(fmt, ##__VA_ARGS__) #endif #endif /* _H_CIFS_DEBUG */ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 97b7497c13ef..874a551f339c 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -520,7 +520,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, rc = crypto_shash_init(&ses->server->secmech.sdeschmacmd5->shash); if (rc) { - cifs_dbg(VFS, "%s: could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); return rc; } @@ -624,7 +624,7 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) rc = crypto_shash_init(&ses->server->secmech.sdeschmacmd5->shash); if (rc) { - cifs_dbg(VFS, "%s: could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); return rc; } @@ -723,7 +723,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) /* calculate ntlmv2_hash */ rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp); if (rc) { - cifs_dbg(VFS, "could not get v2 hash rc %d\n", rc); + cifs_dbg(VFS, "Could not get v2 hash rc %d\n", rc); goto unlock; } @@ -783,7 +783,7 @@ calc_seckey(struct cifs_ses *ses) ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL); if (!ctx_arc4) { - cifs_dbg(VFS, "could not allocate arc4 context\n"); + cifs_dbg(VFS, "Could not allocate arc4 context\n"); return -ENOMEM; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c31f362fa098..889f9c71049b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -534,6 +534,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",signloosely"); if (tcon->nocase) seq_puts(s, ",nocase"); + if (tcon->nodelete) + seq_puts(s, ",nodelete"); if (tcon->local_lease) seq_puts(s, ",locallease"); if (tcon->retry) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c9e2e6bbca13..c7a311d28d3d 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -156,5 +156,5 @@ extern int cifs_truncate_page(struct address_space *mapping, loff_t from); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.26" +#define CIFS_VERSION "2.27" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 39b708d9d86d..e133bb3e172f 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -562,6 +562,7 @@ struct smb_vol { bool override_gid:1; bool dynperm:1; bool noperm:1; + bool nodelete:1; bool mode_ace:1; bool no_psx_acl:1; /* set if posix acl support should be disabled */ bool cifs_acl:1; @@ -1029,6 +1030,7 @@ struct cifs_ses { #define CIFS_MAX_CHANNELS 16 struct cifs_chan chans[CIFS_MAX_CHANNELS]; + struct cifs_chan *binding_chan; size_t chan_count; size_t chan_max; atomic_t chan_seq; /* round robin state */ @@ -1036,23 +1038,31 @@ struct cifs_ses { /* * When binding a new channel, we need to access the channel which isn't fully - * established yet (one past the established count) + * established yet. */ static inline struct cifs_chan *cifs_ses_binding_channel(struct cifs_ses *ses) { if (ses->binding) - return &ses->chans[ses->chan_count]; + return ses->binding_chan; else return NULL; } +/* + * Returns the server pointer of the session. When binding a new + * channel this returns the last channel which isn't fully established + * yet. + * + * This function should be use for negprot/sess.setup codepaths. For + * the other requests see cifs_pick_channel(). + */ static inline struct TCP_Server_Info *cifs_ses_server(struct cifs_ses *ses) { if (ses->binding) - return ses->chans[ses->chan_count].server; + return ses->binding_chan->server; else return ses->server; } @@ -1136,6 +1146,7 @@ struct cifs_tcon { bool retry:1; bool nocase:1; bool nohandlecache:1; /* if strange server resource prob can turn off */ + bool nodelete:1; bool seal:1; /* transport encryption for this mounted share */ bool unix_ext:1; /* if false disable Linux extensions to CIFS protocol for this mount even if server would support */ @@ -1333,6 +1344,7 @@ struct cifs_io_parms { __u64 offset; unsigned int length; struct cifs_tcon *tcon; + struct TCP_Server_Info *server; }; struct cifs_aio_ctx { @@ -1380,6 +1392,7 @@ struct cifs_readdata { struct cifs_readdata *rdata, struct iov_iter *iter); struct kvec iov[2]; + struct TCP_Server_Info *server; #ifdef CONFIG_CIFS_SMB_DIRECT struct smbd_mr *mr; #endif @@ -1406,6 +1419,7 @@ struct cifs_writedata { pid_t pid; unsigned int bytes; int result; + struct TCP_Server_Info *server; #ifdef CONFIG_CIFS_SMB_DIRECT struct smbd_mr *mr; #endif diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 12a895e02db4..bd92070ca30c 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -45,25 +45,25 @@ extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *, unsigned int /* length */); extern unsigned int _get_xid(void); extern void _free_xid(unsigned int); -#define get_xid() \ -({ \ +#define get_xid() \ +({ \ unsigned int __xid = _get_xid(); \ - cifs_dbg(FYI, "CIFS VFS: in %s as Xid: %u with uid: %d\n", \ + cifs_dbg(FYI, "VFS: in %s as Xid: %u with uid: %d\n", \ __func__, __xid, \ from_kuid(&init_user_ns, current_fsuid())); \ - trace_smb3_enter(__xid, __func__); \ - __xid; \ + trace_smb3_enter(__xid, __func__); \ + __xid; \ }) -#define free_xid(curr_xid) \ -do { \ - _free_xid(curr_xid); \ - cifs_dbg(FYI, "CIFS VFS: leaving %s (xid = %u) rc = %d\n", \ - __func__, curr_xid, (int)rc); \ - if (rc) \ +#define free_xid(curr_xid) \ +do { \ + _free_xid(curr_xid); \ + cifs_dbg(FYI, "VFS: leaving %s (xid = %u) rc = %d\n", \ + __func__, curr_xid, (int)rc); \ + if (rc) \ trace_smb3_exit_err(curr_xid, __func__, (int)rc); \ - else \ - trace_smb3_exit_done(curr_xid, __func__); \ + else \ + trace_smb3_exit_done(curr_xid, __func__); \ } while (0) extern int init_cifs_idmap(void); extern void exit_cifs_idmap(void); @@ -89,16 +89,20 @@ extern void cifs_mid_q_entry_release(struct mid_q_entry *midEntry); extern void cifs_wake_up_task(struct mid_q_entry *mid); extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); +extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); extern int cifs_discard_remaining_data(struct TCP_Server_Info *server); extern int cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, mid_receive_t *receive, mid_callback_t *callback, mid_handle_t *handle, void *cbdata, const int flags, const struct cifs_credits *exist_credits); +extern struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses); extern int cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, struct smb_rqst *rqst, int *resp_buf_type, const int flags, struct kvec *resp_iov); extern int compound_send_recv(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, const int flags, const int num_rqst, struct smb_rqst *rqst, int *resp_buf_type, struct kvec *resp_iov); @@ -589,6 +593,8 @@ void cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc); extern void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, unsigned int *len, unsigned int *offset); +struct cifs_chan * +cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server); int cifs_try_adding_channels(struct cifs_ses *ses); int cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface); @@ -616,6 +622,10 @@ static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses, return dfs_cache_find(xid, ses, nls_codepage, remap, old_path, referral, NULL); } + +int match_target_ip(struct TCP_Server_Info *server, + const char *share, size_t share_len, + bool *result); #endif static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options) diff --git a/fs/cifs/cifsroot.c b/fs/cifs/cifsroot.c index 37edbfb8e096..9e91a5a40aae 100644 --- a/fs/cifs/cifsroot.c +++ b/fs/cifs/cifsroot.c @@ -56,7 +56,7 @@ static int __init cifs_root_setup(char *line) /* len is strlen(unc) + '\0' */ len = s - line + 1; if (len > sizeof(root_dev)) { - printk(KERN_ERR "Root-CIFS: UNC path too long\n"); + pr_err("Root-CIFS: UNC path too long\n"); return 1; } strlcpy(root_dev, line, len); @@ -66,7 +66,7 @@ static int __init cifs_root_setup(char *line) sizeof(root_opts), "%s,%s", DEFAULT_MNT_OPTS, s + 1); if (n >= sizeof(root_opts)) { - printk(KERN_ERR "Root-CIFS: mount options string too long\n"); + pr_err("Root-CIFS: mount options string too long\n"); root_opts[sizeof(root_opts)-1] = '\0'; return 1; } @@ -83,7 +83,7 @@ __setup("cifsroot=", cifs_root_setup); int __init cifs_root_data(char **dev, char **opts) { if (!root_dev[0] || root_server_addr == htonl(INADDR_NONE)) { - printk(KERN_ERR "Root-CIFS: no SMB server address\n"); + pr_err("Root-CIFS: no SMB server address\n"); return -1; } diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 5014a82391ff..bf41ee048396 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -129,6 +129,7 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, struct cifs_tcon *tcon) { int rc; + struct TCP_Server_Info *server = tcon->ses->server; struct dfs_cache_tgt_list tl; struct dfs_cache_tgt_iterator *it = NULL; char *tree; @@ -141,15 +142,14 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, if (!tree) return -ENOMEM; - if (tcon->ipc) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", - tcon->ses->server->hostname); - rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); - goto out; - } - if (!tcon->dfs_path) { - rc = CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + if (tcon->ipc) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", + server->hostname); + rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + } else { + rc = CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + } goto out; } @@ -157,13 +157,13 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, if (rc) goto out; - extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, - &tcp_host_len); + extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); for (it = dfs_cache_get_tgt_iterator(&tl); it; it = dfs_cache_get_next_tgt(&tl, it)) { const char *share, *prefix; size_t share_len, prefix_len; + bool target_match; rc = dfs_cache_get_tgt_share(it, &share, &share_len, &prefix, &prefix_len); @@ -177,19 +177,38 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { - cifs_dbg(FYI, "%s: skipping %.*s, doesn't match %.*s", + cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, dfs_host, (int)tcp_host_len, tcp_host); - continue; - } - scnprintf(tree, MAX_TREE_SIZE, "\\%.*s", (int)share_len, share); + rc = match_target_ip(server, dfs_host, dfs_host_len, + &target_match); + if (rc) { + cifs_dbg(VFS, "%s: failed to match target ip: %d\n", + __func__, rc); + break; + } + + if (!target_match) { + cifs_dbg(FYI, "%s: skipping target\n", __func__); + continue; + } + } - rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); - if (!rc) { - rc = update_super_prepath(tcon, prefix, prefix_len); - break; + if (tcon->ipc) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%.*s\\IPC$", + (int)share_len, share); + rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + } else { + scnprintf(tree, MAX_TREE_SIZE, "\\%.*s", (int)share_len, + share); + rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + if (!rc) { + rc = update_super_prepath(tcon, prefix, + prefix_len); + break; + } } if (rc == -EREMOTE) break; @@ -262,8 +281,8 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) (server->tcpStatus != CifsNeedReconnect), 10 * HZ); if (rc < 0) { - cifs_dbg(FYI, "%s: aborting reconnect due to a received" - " signal by the process\n", __func__); + cifs_dbg(FYI, "%s: aborting reconnect due to a received signal by the process\n", + __func__); return -ERESTARTSYS; } @@ -324,7 +343,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc); if (rc) { - printk_once(KERN_WARNING "reconnect tcon failed rc = %d\n", rc); + pr_warn_once("reconnect tcon failed rc = %d\n", rc); goto out; } @@ -557,7 +576,7 @@ cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required) /* If server requires signing, does client allow it? */ if (srv_sign_required) { if (!mnt_sign_enabled) { - cifs_dbg(VFS, "Server requires signing, but it's disabled in SecurityFlags!"); + cifs_dbg(VFS, "Server requires signing, but it's disabled in SecurityFlags!\n"); return -ENOTSUPP; } server->sign = true; @@ -566,14 +585,14 @@ cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required) /* If client requires signing, does server allow it? */ if (mnt_sign_required) { if (!srv_sign_enabled) { - cifs_dbg(VFS, "Server does not support signing!"); + cifs_dbg(VFS, "Server does not support signing!\n"); return -ENOTSUPP; } server->sign = true; } if (cifs_rdma_enabled(server) && server->sign) - cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled"); + cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled\n"); return 0; } @@ -703,7 +722,7 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS); if (should_set_ext_sec_flag(ses->sectype)) { - cifs_dbg(FYI, "Requesting extended security."); + cifs_dbg(FYI, "Requesting extended security\n"); pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC; } @@ -2375,7 +2394,7 @@ int CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, struct kvec *iov, int n_vec) { - int rc = -EACCES; + int rc; WRITE_REQ *pSMB = NULL; int wct; int smb_hdr_len; @@ -3868,7 +3887,7 @@ GetExtAttrRetry: struct file_chattr_info *pfinfo; /* BB Do we need a cast or hash here ? */ if (count != 16) { - cifs_dbg(FYI, "Illegal size ret in GetExtAttr\n"); + cifs_dbg(FYI, "Invalid size ret in GetExtAttr\n"); rc = -EIO; goto GetExtAttrOut; } @@ -4244,7 +4263,7 @@ QFileInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QFileInfo = %d", rc); + cifs_dbg(FYI, "Send error in QFileInfo = %d\n", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4411,7 +4430,7 @@ UnixQFileInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in UnixQFileInfo = %d", rc); + cifs_dbg(FYI, "Send error in UnixQFileInfo = %d\n", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4493,7 +4512,7 @@ UnixQPathInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in UnixQPathInfo = %d", rc); + cifs_dbg(FYI, "Send error in UnixQPathInfo = %d\n", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4913,7 +4932,7 @@ GetInodeNumberRetry: struct file_internal_info *pfinfo; /* BB Do we need a cast or hash here ? */ if (count < 8) { - cifs_dbg(FYI, "Illegal size ret in QryIntrnlInf\n"); + cifs_dbg(FYI, "Invalid size ret in QryIntrnlInf\n"); rc = -EIO; goto GetInodeNumOut; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ad8fb53b3682..5fac34f192af 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -75,7 +75,7 @@ enum { Opt_forceuid, Opt_noforceuid, Opt_forcegid, Opt_noforcegid, Opt_noblocksend, Opt_noautotune, Opt_nolease, - Opt_hard, Opt_soft, Opt_perm, Opt_noperm, + Opt_hard, Opt_soft, Opt_perm, Opt_noperm, Opt_nodelete, Opt_mapposix, Opt_nomapposix, Opt_mapchars, Opt_nomapchars, Opt_sfu, Opt_nosfu, Opt_nodfs, Opt_posixpaths, @@ -141,6 +141,7 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_soft, "soft" }, { Opt_perm, "perm" }, { Opt_noperm, "noperm" }, + { Opt_nodelete, "nodelete" }, { Opt_mapchars, "mapchars" }, /* SFU style */ { Opt_nomapchars, "nomapchars" }, { Opt_mapposix, "mapposix" }, /* SFM style */ @@ -426,8 +427,7 @@ static void reconn_inval_dfs_target(struct TCP_Server_Info *server, } static inline int reconn_setup_dfs_targets(struct cifs_sb_info *cifs_sb, - struct dfs_cache_tgt_list *tl, - struct dfs_cache_tgt_iterator **it) + struct dfs_cache_tgt_list *tl) { if (!cifs_sb->origin_fullpath) return -EOPNOTSUPP; @@ -472,7 +472,7 @@ cifs_reconnect(struct TCP_Server_Info *server) } else { cifs_sb = CIFS_SB(sb); - rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list, &tgt_it); + rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list); if (rc && (rc != -EOPNOTSUPP)) { cifs_server_dbg(VFS, "%s: no target servers for DFS failover\n", __func__); @@ -572,26 +572,26 @@ cifs_reconnect(struct TCP_Server_Info *server) try_to_freeze(); mutex_lock(&server->srv_mutex); +#ifdef CONFIG_CIFS_DFS_UPCALL /* * Set up next DFS target server (if any) for reconnect. If DFS * feature is disabled, then we will retry last server we * connected to before. */ + reconn_inval_dfs_target(server, cifs_sb, &tgt_list, &tgt_it); +#endif + rc = reconn_set_ipaddr(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } + if (cifs_rdma_enabled(server)) rc = smbd_reconnect(server); else rc = generic_ip_connect(server); if (rc) { cifs_dbg(FYI, "reconnect error %d\n", rc); -#ifdef CONFIG_CIFS_DFS_UPCALL - reconn_inval_dfs_target(server, cifs_sb, &tgt_list, - &tgt_it); -#endif - rc = reconn_set_ipaddr(server); - if (rc) { - cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", - __func__, rc); - } mutex_unlock(&server->srv_mutex); msleep(3000); } else { @@ -879,8 +879,7 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) * function has finished processing it is a bug. */ if (mid->mid_flags & MID_DELETED) - printk_once(KERN_WARNING - "trying to dequeue a deleted mid\n"); + pr_warn_once("trying to dequeue a deleted mid\n"); else { list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; @@ -1229,9 +1228,8 @@ next_pdu: smb2_add_credits_from_hdr(bufs[i], server); cifs_dbg(FYI, "Received oplock break\n"); } else { - cifs_server_dbg(VFS, "No task to wake, unknown frame " - "received! NumMids %d\n", - atomic_read(&midCount)); + cifs_server_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n", + atomic_read(&midCount)); cifs_dump_mem("Received Data is: ", bufs[i], HEADER_SIZE(server)); smb2_add_credits_from_hdr(bufs[i], server); @@ -1476,9 +1474,7 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3) cifs_dbg(VFS, "vers=1.0 (cifs) not permitted when mounting with smb3\n"); return 1; } - cifs_dbg(VFS, "Use of the less secure dialect vers=1.0 " - "is not recommended unless required for " - "access to very old servers\n"); + cifs_dbg(VFS, "Use of the less secure dialect vers=1.0 is not recommended unless required for access to very old servers\n"); vol->ops = &smb1_operations; vol->vals = &smb1_values; break; @@ -1545,7 +1541,7 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol) size_t len; if (unlikely(!devname || !*devname)) { - cifs_dbg(VFS, "Device name not specified.\n"); + cifs_dbg(VFS, "Device name not specified\n"); return -EINVAL; } @@ -1695,13 +1691,13 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, case 0: break; case -ENOMEM: - cifs_dbg(VFS, "Unable to allocate memory for devname.\n"); + cifs_dbg(VFS, "Unable to allocate memory for devname\n"); goto cifs_parse_mount_err; case -EINVAL: - cifs_dbg(VFS, "Malformed UNC in devname.\n"); + cifs_dbg(VFS, "Malformed UNC in devname\n"); goto cifs_parse_mount_err; default: - cifs_dbg(VFS, "Unknown error parsing devname.\n"); + cifs_dbg(VFS, "Unknown error parsing devname\n"); goto cifs_parse_mount_err; } @@ -1761,6 +1757,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, case Opt_noperm: vol->noperm = 1; break; + case Opt_nodelete: + vol->nodelete = 1; + break; case Opt_mapchars: vol->sfu_remap = true; vol->remap = false; /* disable SFM mapping */ @@ -1909,7 +1908,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->seal = 1; break; case Opt_noac: - pr_warn("CIFS: Mount option noac not supported. Instead set /proc/fs/cifs/LookupCacheEnabled to 0\n"); + pr_warn("Mount option noac not supported. Instead set /proc/fs/cifs/LookupCacheEnabled to 0\n"); break; case Opt_fsc: #ifndef CONFIG_CIFS_FSCACHE @@ -1965,9 +1964,13 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, break; case Opt_multichannel: vol->multichannel = true; + /* if number of channels not specified, default to 2 */ + if (vol->max_channels < 2) + vol->max_channels = 2; break; case Opt_nomultichannel: vol->multichannel = false; + vol->max_channels = 1; break; case Opt_compress: vol->compression = UNKNOWN_TYPE; @@ -2156,7 +2159,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (strnlen(string, CIFS_MAX_USERNAME_LEN) > CIFS_MAX_USERNAME_LEN) { - pr_warn("CIFS: username too long\n"); + pr_warn("username too long\n"); goto cifs_parse_mount_err; } @@ -2222,7 +2225,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, temp_len = strlen(value); vol->password = kzalloc(temp_len+1, GFP_KERNEL); if (vol->password == NULL) { - pr_warn("CIFS: no memory for password\n"); + pr_warn("no memory for password\n"); goto cifs_parse_mount_err; } @@ -2246,7 +2249,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (!cifs_convert_address(dstaddr, string, strlen(string))) { - pr_err("CIFS: bad ip= option (%s).\n", string); + pr_err("bad ip= option (%s)\n", string); goto cifs_parse_mount_err; } got_ip = true; @@ -2258,14 +2261,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN) == CIFS_MAX_DOMAINNAME_LEN) { - pr_warn("CIFS: domain name too long\n"); + pr_warn("domain name too long\n"); goto cifs_parse_mount_err; } kfree(vol->domainname); vol->domainname = kstrdup(string, GFP_KERNEL); if (!vol->domainname) { - pr_warn("CIFS: no memory for domainname\n"); + pr_warn("no memory for domainname\n"); goto cifs_parse_mount_err; } cifs_dbg(FYI, "Domain name set\n"); @@ -2278,7 +2281,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (!cifs_convert_address( (struct sockaddr *)&vol->srcaddr, string, strlen(string))) { - pr_warn("CIFS: Could not parse srcaddr: %s\n", + pr_warn("Could not parse srcaddr: %s\n", string); goto cifs_parse_mount_err; } @@ -2289,7 +2292,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto out_nomem; if (strnlen(string, 1024) >= 65) { - pr_warn("CIFS: iocharset name too long.\n"); + pr_warn("iocharset name too long\n"); goto cifs_parse_mount_err; } @@ -2298,7 +2301,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->iocharset = kstrdup(string, GFP_KERNEL); if (!vol->iocharset) { - pr_warn("CIFS: no memory for charset\n"); + pr_warn("no memory for charset\n"); goto cifs_parse_mount_err; } } @@ -2329,7 +2332,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * set at top of the function */ if (i == RFC1001_NAME_LEN && string[i] != 0) - pr_warn("CIFS: netbiosname longer than 15 truncated.\n"); + pr_warn("netbiosname longer than 15 truncated\n"); break; case Opt_servern: /* servernetbiosname specified override *SMBSERVER */ @@ -2355,7 +2358,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* The string has 16th byte zero still from set at top of the function */ if (i == RFC1001_NAME_LEN && string[i] != 0) - pr_warn("CIFS: server netbiosname longer than 15 truncated.\n"); + pr_warn("server netbiosname longer than 15 truncated\n"); break; case Opt_ver: /* version of mount userspace tools, not dialect */ @@ -2366,17 +2369,15 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* If interface changes in mount.cifs bump to new ver */ if (strncasecmp(string, "1", 1) == 0) { if (strlen(string) > 1) { - pr_warn("Bad mount helper ver=%s. Did " - "you want SMB1 (CIFS) dialect " - "and mean to type vers=1.0 " - "instead?\n", string); + pr_warn("Bad mount helper ver=%s. Did you want SMB1 (CIFS) dialect and mean to type vers=1.0 instead?\n", + string); goto cifs_parse_mount_err; } /* This is the default */ break; } /* For all other value, error */ - pr_warn("CIFS: Invalid mount helper version specified\n"); + pr_warn("Invalid mount helper version specified\n"); goto cifs_parse_mount_err; case Opt_vers: /* protocol version (dialect) */ @@ -2419,7 +2420,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } if (!sloppy && invalid) { - pr_err("CIFS: Unknown mount option \"%s\"\n", invalid); + pr_err("Unknown mount option \"%s\"\n", invalid); goto cifs_parse_mount_err; } @@ -2455,7 +2456,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, slash = strchr(&vol->UNC[2], '\\'); len = slash - &vol->UNC[2]; if (!cifs_convert_address(dstaddr, &vol->UNC[2], len)) { - pr_err("Unable to determine destination address.\n"); + pr_err("Unable to determine destination address\n"); goto cifs_parse_mount_err; } } @@ -2466,20 +2467,15 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (uid_specified) vol->override_uid = override_uid; else if (override_uid == 1) - pr_notice("CIFS: ignoring forceuid mount option specified with no uid= option.\n"); + pr_notice("ignoring forceuid mount option specified with no uid= option\n"); if (gid_specified) vol->override_gid = override_gid; else if (override_gid == 1) - pr_notice("CIFS: ignoring forcegid mount option specified with no gid= option.\n"); + pr_notice("ignoring forcegid mount option specified with no gid= option\n"); if (got_version == false) - pr_warn_once("No dialect specified on mount. Default has changed" - " to a more secure dialect, SMB2.1 or later (e.g. " - "SMB3.1.1), from CIFS (SMB1). To use the less secure " - "SMB1 dialect to access old servers which do not " - "support SMB3.1.1 (or even SMB3 or SMB2.1) specify " - "vers=1.0 on mount.\n"); + pr_warn_once("No dialect specified on mount. Default has changed to a more secure dialect, SMB2.1 or later (e.g. SMB3.1.1), from CIFS (SMB1). To use the less secure SMB1 dialect to access old servers which do not support SMB3.1.1 (or even SMB3 or SMB2.1) specify vers=1.0 on mount.\n"); kfree(mountdata_copy); return 0; @@ -2496,8 +2492,8 @@ cifs_parse_mount_err: * specified, or if srcaddr is specified and * matches the IP address of the rhs argument. */ -static bool -srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs) +bool +cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs) { switch (srcaddr->sa_family) { case AF_UNSPEC: @@ -2588,7 +2584,7 @@ match_address(struct TCP_Server_Info *server, struct sockaddr *addr, return false; /* don't expect to be here */ } - if (!srcip_matches(srcaddr, (struct sockaddr *)&server->srcaddr)) + if (!cifs_match_ipaddr(srcaddr, (struct sockaddr *)&server->srcaddr)) return false; return true; @@ -3197,8 +3193,8 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) strlen(ses->domainName), GFP_KERNEL); if (!vol->domainname) { - cifs_dbg(FYI, "Unable to allocate %zd bytes for " - "domain\n", len); + cifs_dbg(FYI, "Unable to allocate %zd bytes for domain\n", + len); rc = -ENOMEM; kfree(vol->username); vol->username = NULL; @@ -3363,6 +3359,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info) return 0; if (tcon->no_lease != volume_info->no_lease) return 0; + if (tcon->nodelete != volume_info->nodelete) + return 0; return 1; } @@ -3519,10 +3517,9 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) if (volume_info->linux_ext) { if (ses->server->posix_ext_supported) { tcon->posix_extensions = true; - printk_once(KERN_WARNING - "SMB3.11 POSIX Extensions are experimental\n"); + pr_warn_once("SMB3.11 POSIX Extensions are experimental\n"); } else { - cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions.\n"); + cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions\n"); rc = -EOPNOTSUPP; goto out_fail; } @@ -3580,6 +3577,16 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) cifs_dbg(VFS, "cache=singleclient requested on mount but NO_CACHING flag set on share\n"); } + if (volume_info->no_lease) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "SMB2 or later required for nolease option\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } else + tcon->no_lease = volume_info->no_lease; + } + /* * We can have only one retry value for a connection to a share so for * resources mounted more than once to the same server share the last @@ -3588,8 +3595,8 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) tcon->retry = volume_info->retry; tcon->nocase = volume_info->nocase; tcon->nohandlecache = volume_info->nohandlecache; + tcon->nodelete = volume_info->nodelete; tcon->local_lease = volume_info->local_lease; - tcon->no_lease = volume_info->no_lease; INIT_LIST_HEAD(&tcon->pending_opens); spin_lock(&cifs_tcp_ses_lock); @@ -4736,8 +4743,7 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb_vol *vol, rc = cifs_are_all_path_components_accessible(server, xid, tcon, cifs_sb, full_path, tcon->Flags & SMB_SHARE_IS_IN_DFS); if (rc != 0) { - cifs_server_dbg(VFS, "cannot query dirs between root and final path, " - "enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); + cifs_server_dbg(VFS, "cannot query dirs between root and final path, enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; rc = 0; } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index a67f88bf7ae1..df81c718d2fa 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -198,7 +198,7 @@ static ssize_t dfscache_proc_write(struct file *file, const char __user *buffer, if (c != '0') return -EINVAL; - cifs_dbg(FYI, "clearing dfs cache"); + cifs_dbg(FYI, "clearing dfs cache\n"); down_write(&htable_rw_lock); flush_cache_ents(); @@ -234,8 +234,8 @@ static inline void dump_tgts(const struct cache_entry *ce) static inline void dump_ce(const struct cache_entry *ce) { - cifs_dbg(FYI, "cache entry: path=%s,type=%s,ttl=%d,etime=%ld," - "interlink=%s,path_consumed=%d,expired=%s\n", ce->path, + cifs_dbg(FYI, "cache entry: path=%s,type=%s,ttl=%d,etime=%ld,interlink=%s,path_consumed=%d,expired=%s\n", + ce->path, ce->srvtype == DFS_TYPE_ROOT ? "root" : "link", ce->ttl, ce->etime.tv_nsec, IS_INTERLINK_SET(ce->flags) ? "yes" : "no", @@ -453,11 +453,11 @@ static void remove_oldest_entry(void) } if (!to_del) { - cifs_dbg(FYI, "%s: no entry to remove", __func__); + cifs_dbg(FYI, "%s: no entry to remove\n", __func__); return; } - cifs_dbg(FYI, "%s: removing entry", __func__); + cifs_dbg(FYI, "%s: removing entry\n", __func__); dump_ce(to_del); flush_cache_ent(to_del); } @@ -696,8 +696,8 @@ static int __dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, } if (atomic_read(&cache_count) >= CACHE_MAX_ENTRIES) { - cifs_dbg(FYI, "%s: reached max cache size (%d)", __func__, - CACHE_MAX_ENTRIES); + cifs_dbg(FYI, "%s: reached max cache size (%d)\n", + __func__, CACHE_MAX_ENTRIES); down_write(&htable_rw_lock); remove_oldest_entry(); up_write(&htable_rw_lock); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 75ddce8ef456..8277859d12a3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -857,7 +857,7 @@ cifs_reopen_persistent_handles(struct cifs_tcon *tcon) tcon->need_reopen_files = false; - cifs_dbg(FYI, "Reopen persistent handles"); + cifs_dbg(FYI, "Reopen persistent handles\n"); INIT_LIST_HEAD(&tmp_list); /* list all files open on tree connection, reopen resilient handles */ @@ -1853,7 +1853,7 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data, unsigned int xid; struct dentry *dentry = open_file->dentry; struct cifsInodeInfo *cifsi = CIFS_I(d_inode(dentry)); - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; cifs_dbg(FYI, "write %zd bytes to offset %lld of %pd\n", write_size, *offset, dentry); @@ -2056,7 +2056,7 @@ find_writable_file(struct cifsInodeInfo *cifs_inode, int flags) rc = cifs_get_writable_file(cifs_inode, flags, &cfile); if (rc) - cifs_dbg(FYI, "couldn't find writable handle rc=%d", rc); + cifs_dbg(FYI, "Couldn't find writable handle rc=%d\n", rc); return cfile; } @@ -2292,8 +2292,6 @@ wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages, struct address_space *mapping, struct writeback_control *wbc) { int rc; - struct TCP_Server_Info *server = - tlink_tcon(wdata->cfile->tlink)->ses->server; wdata->sync_mode = wbc->sync_mode; wdata->nr_pages = nr_pages; @@ -2305,14 +2303,15 @@ wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages, wdata->bytes = ((nr_pages - 1) * PAGE_SIZE) + wdata->tailsz; wdata->pid = wdata->cfile->pid; - rc = adjust_credits(server, &wdata->credits, wdata->bytes); + rc = adjust_credits(wdata->server, &wdata->credits, wdata->bytes); if (rc) return rc; if (wdata->cfile->invalidHandle) rc = -EAGAIN; else - rc = server->ops->async_writev(wdata, cifs_writedata_release); + rc = wdata->server->ops->async_writev(wdata, + cifs_writedata_release); return rc; } @@ -2349,7 +2348,8 @@ static int cifs_writepages(struct address_space *mapping, range_whole = true; scanned = true; } - server = cifs_sb_master_tcon(cifs_sb)->ses->server; + server = cifs_pick_channel(cifs_sb_master_tcon(cifs_sb)->ses); + retry: while (!done && index <= end) { unsigned int i, nr_pages, found_pages, wsize; @@ -2403,6 +2403,7 @@ retry: wdata->credits = credits_on_stack; wdata->cfile = cfile; + wdata->server = server; cfile = NULL; if (!wdata->cfile) { @@ -2806,8 +2807,7 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list, unsigned int wsize; struct cifs_credits credits; int rc; - struct TCP_Server_Info *server = - tlink_tcon(wdata->cfile->tlink)->ses->server; + struct TCP_Server_Info *server = wdata->server; do { if (wdata->cfile->invalidHandle) { @@ -2893,7 +2893,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, else pid = current->tgid; - server = tlink_tcon(open_file->tlink)->ses->server; + server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); xid = get_xid(); do { @@ -2923,11 +2923,9 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, from, &pagevec, cur_len, &start); if (result < 0) { cifs_dbg(VFS, - "direct_writev couldn't get user pages " - "(rc=%zd) iter type %d iov_offset %zd " - "count %zd\n", - result, iov_iter_type(from), - from->iov_offset, from->count); + "direct_writev couldn't get user pages (rc=%zd) iter type %d iov_offset %zd count %zd\n", + result, iov_iter_type(from), + from->iov_offset, from->count); dump_stack(); rc = result; @@ -2999,6 +2997,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, wdata->nr_pages = nr_pages; wdata->offset = (__u64)offset; wdata->cfile = cifsFileInfo_get(open_file); + wdata->server = server; wdata->pid = pid; wdata->bytes = cur_len; wdata->pagesz = PAGE_SIZE; @@ -3540,8 +3539,10 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata, unsigned int rsize; struct cifs_credits credits; int rc; - struct TCP_Server_Info *server = - tlink_tcon(rdata->cfile->tlink)->ses->server; + struct TCP_Server_Info *server; + + /* XXX: should we pick a new channel here? */ + server = rdata->server; do { if (rdata->cfile->invalidHandle) { @@ -3620,7 +3621,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, size_t start; struct iov_iter direct_iov = ctx->iter; - server = tlink_tcon(open_file->tlink)->ses->server; + server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) pid = open_file->pid; @@ -3654,12 +3655,10 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, cur_len, &start); if (result < 0) { cifs_dbg(VFS, - "couldn't get user pages (rc=%zd)" - " iter type %d" - " iov_offset %zd count %zd\n", - result, iov_iter_type(&direct_iov), - direct_iov.iov_offset, - direct_iov.count); + "Couldn't get user pages (rc=%zd) iter type %d iov_offset %zd count %zd\n", + result, iov_iter_type(&direct_iov), + direct_iov.iov_offset, + direct_iov.count); dump_stack(); rc = result; @@ -3706,6 +3705,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, rdata->tailsz = PAGE_SIZE; } + rdata->server = server; rdata->cfile = cifsFileInfo_get(open_file); rdata->nr_pages = npages; rdata->offset = offset; @@ -4018,7 +4018,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) unsigned int xid; char *cur_offset; struct cifsFileInfo *open_file; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; int buf_type = CIFS_NO_BUFFER; __u32 pid; @@ -4035,7 +4035,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) } open_file = file->private_data; tcon = tlink_tcon(open_file->tlink); - server = tcon->ses->server; + server = cifs_pick_channel(tcon->ses); if (!server->ops->sync_read) { free_xid(xid); @@ -4074,6 +4074,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) io_parms.tcon = tcon; io_parms.offset = *offset; io_parms.length = current_read_size; + io_parms.server = server; rc = server->ops->sync_read(xid, &open_file->fid, &io_parms, &bytes_read, &cur_offset, &buf_type); @@ -4162,7 +4163,7 @@ cifs_readv_complete(struct work_struct *work) for (i = 0; i < rdata->nr_pages; i++) { struct page *page = rdata->pages[i]; - lru_cache_add_file(page); + lru_cache_add(page); if (rdata->result == 0 || (rdata->result == -EAGAIN && got_bytes)) { @@ -4232,7 +4233,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, * fill them until the writes are flushed. */ zero_user(page, 0, PAGE_SIZE); - lru_cache_add_file(page); + lru_cache_add(page); flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); @@ -4242,7 +4243,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, continue; } else { /* no need to hold page hostage */ - lru_cache_add_file(page); + lru_cache_add(page); unlock_page(page); put_page(page); rdata->pages[i] = NULL; @@ -4376,7 +4377,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, pid = current->tgid; rc = 0; - server = tlink_tcon(open_file->tlink)->ses->server; + server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n", __func__, file, mapping, num_pages); @@ -4437,7 +4438,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, /* best to give up if we're out of mem */ list_for_each_entry_safe(page, tpage, &tmplist, lru) { list_del(&page->lru); - lru_cache_add_file(page); + lru_cache_add(page); unlock_page(page); put_page(page); } @@ -4447,6 +4448,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } rdata->cfile = cifsFileInfo_get(open_file); + rdata->server = server; rdata->mapping = mapping; rdata->offset = offset; rdata->bytes = bytes; @@ -4475,7 +4477,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, add_credits_and_wake_if(server, &rdata->credits, 0); for (i = 0; i < rdata->nr_pages; i++) { page = rdata->pages[i]; - lru_cache_add_file(page); + lru_cache_add(page); unlock_page(page); put_page(page); } @@ -4828,7 +4830,7 @@ static int cifs_swap_activate(struct swap_info_struct *sis, } *span = sis->pages; - printk_once(KERN_WARNING "Swap support over SMB3 is experimental\n"); + pr_warn_once("Swap support over SMB3 is experimental\n"); /* * TODO: consider adding ACL (or documenting how) to prevent other diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 5d2965a23730..5072bcaf4be1 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -25,6 +25,7 @@ #include <linux/freezer.h> #include <linux/sched/signal.h> #include <linux/wait_bit.h> +#include <linux/fiemap.h> #include <asm/div64.h> #include "cifsfs.h" @@ -447,7 +448,7 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, struct cifs_tcon *tcon; struct cifs_fid fid; struct cifs_open_parms oparms; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; char buf[24]; unsigned int bytes_read; char *pbuf; @@ -1155,7 +1156,7 @@ struct inode *cifs_root_iget(struct super_block *sb) /* some servers mistakenly claim POSIX support */ if (rc != -EOPNOTSUPP) goto iget_no_retry; - cifs_dbg(VFS, "server does not support POSIX extensions"); + cifs_dbg(VFS, "server does not support POSIX extensions\n"); tcon->unix_ext = false; } @@ -1418,6 +1419,11 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) xid = get_xid(); + if (tcon->nodelete) { + rc = -EACCES; + goto unlink_out; + } + /* Unlink can be called from rename so we can not take the * sb->s_vfs_rename_mutex here */ full_path = build_path_from_dentry(dentry); @@ -1746,6 +1752,12 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) goto rmdir_exit; } + if (tcon->nodelete) { + rc = -EACCES; + cifs_put_tlink(tlink); + goto rmdir_exit; + } + rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb); cifs_put_tlink(tlink); @@ -1999,7 +2011,7 @@ cifs_invalidate_mapping(struct inode *inode) if (inode->i_mapping && inode->i_mapping->nrpages != 0) { rc = invalidate_inode_pages2(inode->i_mapping); if (rc) - cifs_dbg(VFS, "%s: could not invalidate inode %p\n", + cifs_dbg(VFS, "%s: Could not invalidate inode %p\n", __func__, inode); } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index a25ef35b023e..c381d2d03ef6 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -308,7 +308,7 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, int oplock = 0; struct cifs_fid fid; struct cifs_open_parms oparms; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; int buf_type = CIFS_NO_BUFFER; FILE_ALL_INFO file_info; @@ -352,7 +352,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, int oplock = 0; struct cifs_fid fid; struct cifs_open_parms oparms; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; @@ -389,7 +389,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, int rc; struct cifs_fid fid; struct cifs_open_parms oparms; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; int buf_type = CIFS_NO_BUFFER; __le16 *utf16_path; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; @@ -450,7 +450,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, int rc; struct cifs_fid fid; struct cifs_open_parms oparms; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; __le16 *utf16_path; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct kvec iov[2]; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 550ce9020a3e..56791a692c8b 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -32,6 +32,9 @@ #include "cifs_unicode.h" #include "smb2pdu.h" #include "cifsfs.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dns_resolve.h" +#endif extern mempool_t *cifs_sm_req_poolp; extern mempool_t *cifs_req_poolp; @@ -421,7 +424,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) if (data_offset > len - sizeof(struct file_notify_information)) { - cifs_dbg(FYI, "invalid data_offset %u\n", + cifs_dbg(FYI, "Invalid data_offset %u\n", data_offset); return true; } @@ -449,7 +452,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) large dirty files cached on the client */ if ((NT_STATUS_INVALID_HANDLE) == le32_to_cpu(pSMB->hdr.Status.CifsError)) { - cifs_dbg(FYI, "invalid handle on oplock break\n"); + cifs_dbg(FYI, "Invalid handle on oplock break\n"); return true; } else if (ERRbadfid == le16_to_cpu(pSMB->hdr.Status.DosError.Error)) { @@ -530,9 +533,9 @@ cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; cifs_sb->mnt_cifs_serverino_autodisabled = true; - cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s.\n", + cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s\n", tcon ? tcon->treeName : "new server"); - cifs_dbg(VFS, "The server doesn't seem to support them properly or the files might be on different servers (DFS).\n"); + cifs_dbg(VFS, "The server doesn't seem to support them properly or the files might be on different servers (DFS)\n"); cifs_dbg(VFS, "Hardlinks will not be recognized on this mount. Consider mounting with the \"noserverino\" option to silence this message.\n"); } @@ -874,7 +877,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) while (count && npages < max_pages) { rc = iov_iter_get_pages(iter, pages, count, max_pages, &start); if (rc < 0) { - cifs_dbg(VFS, "couldn't get user pages (rc=%zd)\n", rc); + cifs_dbg(VFS, "Couldn't get user pages (rc=%zd)\n", rc); break; } @@ -933,7 +936,7 @@ cifs_alloc_hash(const char *name, *shash = crypto_alloc_shash(name, 0, 0); if (IS_ERR(*shash)) { - cifs_dbg(VFS, "could not allocate crypto %s\n", name); + cifs_dbg(VFS, "Could not allocate crypto %s\n", name); rc = PTR_ERR(*shash); *shash = NULL; *sdesc = NULL; @@ -1083,6 +1086,51 @@ void cifs_put_tcp_super(struct super_block *sb) } #ifdef CONFIG_CIFS_DFS_UPCALL +int match_target_ip(struct TCP_Server_Info *server, + const char *share, size_t share_len, + bool *result) +{ + int rc; + char *target, *tip = NULL; + struct sockaddr tipaddr; + + *result = false; + + target = kzalloc(share_len + 3, GFP_KERNEL); + if (!target) { + rc = -ENOMEM; + goto out; + } + + scnprintf(target, share_len + 3, "\\\\%.*s", (int)share_len, share); + + cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2); + + rc = dns_resolve_server_name_to_ip(target, &tip); + if (rc < 0) + goto out; + + cifs_dbg(FYI, "%s: target ip: %s\n", __func__, tip); + + if (!cifs_convert_address(&tipaddr, tip, strlen(tip))) { + cifs_dbg(VFS, "%s: failed to convert target ip address\n", + __func__); + rc = -EINVAL; + goto out; + } + + *result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, + &tipaddr); + cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result); + rc = 0; + +out: + kfree(target); + kfree(tip); + + return rc; +} + static void tcon_super_cb(struct super_block *sb, void *arg) { struct super_cb_data *sd = arg; diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 9b41436fb8db..b7ca4960d4ca 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -957,15 +957,15 @@ struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset) sec = 2 * st->TwoSeconds; min = st->Minutes; if ((sec > 59) || (min > 59)) - cifs_dbg(VFS, "illegal time min %d sec %lld\n", min, sec); + cifs_dbg(VFS, "Invalid time min %d sec %lld\n", min, sec); sec += (min * 60); sec += 60 * 60 * st->Hours; if (st->Hours > 24) - cifs_dbg(VFS, "illegal hours %d\n", st->Hours); + cifs_dbg(VFS, "Invalid hours %d\n", st->Hours); day = sd->Day; month = sd->Month; if (day < 1 || day > 31 || month < 1 || month > 12) { - cifs_dbg(VFS, "illegal date, month %d day: %d\n", month, day); + cifs_dbg(VFS, "Invalid date, month %d day: %d\n", month, day); day = clamp(day, 1, 31); month = clamp(month, 1, 12); } diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 50f776a8d4ba..6df0922e7e30 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -53,7 +53,7 @@ static void dump_cifs_file_struct(struct file *file, char *label) return; } if (cf->invalidHandle) - cifs_dbg(FYI, "invalid handle\n"); + cifs_dbg(FYI, "Invalid handle\n"); if (cf->srch_inf.endOfSearch) cifs_dbg(FYI, "end of search\n"); if (cf->srch_inf.emptyDir) @@ -246,7 +246,7 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, */ fattr->cf_mode = le32_to_cpu(info->Mode) & ~S_IFMT; - cifs_dbg(FYI, "posix fattr: dev %d, reparse %d, mode %o", + cifs_dbg(FYI, "posix fattr: dev %d, reparse %d, mode %o\n", le32_to_cpu(info->DeviceId), le32_to_cpu(info->ReparseTag), le32_to_cpu(info->Mode)); @@ -478,7 +478,7 @@ static char *nxt_dir_entry(char *old_entry, char *end_of_smb, int level) u32 next_offset = le32_to_cpu(pDirInfo->NextEntryOffset); if (old_entry + next_offset < old_entry) { - cifs_dbg(VFS, "invalid offset %u\n", next_offset); + cifs_dbg(VFS, "Invalid offset %u\n", next_offset); return NULL; } new_entry = old_entry + next_offset; @@ -515,7 +515,7 @@ static void cifs_fill_dirent_posix(struct cifs_dirent *de, /* payload should have already been checked at this point */ if (posix_info_parse(info, NULL, &parsed) < 0) { - cifs_dbg(VFS, "invalid POSIX info payload"); + cifs_dbg(VFS, "Invalid POSIX info payload\n"); return; } @@ -968,7 +968,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) } else if (current_entry != NULL) { cifs_dbg(FYI, "entry %lld found\n", ctx->pos); } else { - cifs_dbg(FYI, "could not find entry\n"); + cifs_dbg(FYI, "Could not find entry\n"); goto rddir2_exit; } cifs_dbg(FYI, "loop through %d times filling dir for net buf %p\n", diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 43a88e26d26b..5d05bd2822d2 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -122,7 +122,7 @@ int cifs_try_adding_channels(struct cifs_ses *ses) tries++; if (tries > 3*ses->chan_max) { - cifs_dbg(FYI, "too many attempt at opening channels (%d channels left to open)\n", + cifs_dbg(FYI, "too many channel open attempts (%d channels left to open)\n", left); break; } @@ -150,6 +150,22 @@ int cifs_try_adding_channels(struct cifs_ses *ses) return ses->chan_count - old_chan_count; } +/* + * If server is a channel of ses, return the corresponding enclosing + * cifs_chan otherwise return NULL. + */ +struct cifs_chan * +cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server) +{ + int i; + + for (i = 0; i < ses->chan_count; i++) { + if (ses->chans[i].server == server) + return &ses->chans[i]; + } + return NULL; +} + int cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) { @@ -162,12 +178,14 @@ cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) int rc; unsigned int xid = get_xid(); - cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ", - ses, iface->speed, iface->rdma_capable ? "yes" : "no"); if (iface->sockaddr.ss_family == AF_INET) - cifs_dbg(FYI, "ip:%pI4)\n", &ipv4->sin_addr); + cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI4)\n", + ses, iface->speed, iface->rdma_capable ? "yes" : "no", + &ipv4->sin_addr); else - cifs_dbg(FYI, "ip:%pI6)\n", &ipv6->sin6_addr); + cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI4)\n", + ses, iface->speed, iface->rdma_capable ? "yes" : "no", + &ipv6->sin6_addr); /* * Setup a smb_vol with mostly the same info as the existing @@ -198,7 +216,7 @@ cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) vol.UNC = unc; vol.prepath = ""; - /* Re-use same version as master connection */ + /* Reuse same version as master connection */ vol.vals = ses->server->vals; vol.ops = ses->server->ops; @@ -229,7 +247,7 @@ cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) mutex_lock(&ses->session_mutex); - chan = &ses->chans[ses->chan_count]; + chan = ses->binding_chan = &ses->chans[ses->chan_count]; chan->server = cifs_get_tcp_session(&vol); if (IS_ERR(chan->server)) { rc = PTR_ERR(chan->server); @@ -261,7 +279,7 @@ cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) goto out; /* success, put it on the list - * XXX: sharing ses between 2 tcp server is not possible, the + * XXX: sharing ses between 2 tcp servers is not possible, the * way "internal" linked lists works in linux makes element * only able to belong to one list * @@ -274,6 +292,7 @@ cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) atomic_set(&ses->chan_seq, 0); out: ses->binding = false; + ses->binding_chan = NULL; mutex_unlock(&ses->session_mutex); if (rc && chan->server) @@ -569,15 +588,15 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset); tilen = le16_to_cpu(pblob->TargetInfoArray.Length); if (tioffset > blob_len || tioffset + tilen > blob_len) { - cifs_dbg(VFS, "tioffset + tilen too high %u + %u", - tioffset, tilen); + cifs_dbg(VFS, "tioffset + tilen too high %u + %u\n", + tioffset, tilen); return -EINVAL; } if (tilen) { ses->auth_key.response = kmemdup(bcc_ptr + tioffset, tilen, GFP_KERNEL); if (!ses->auth_key.response) { - cifs_dbg(VFS, "Challenge target info alloc failure"); + cifs_dbg(VFS, "Challenge target info alloc failure\n"); return -ENOMEM; } ses->auth_key.len = tilen; @@ -970,7 +989,7 @@ sess_auth_lanman(struct sess_data *sess_data) /* Calculate hash with password and copy into bcc_ptr. * Encryption Key (stored as in cryptkey) gets used if the - * security mode bit in Negottiate Protocol response states + * security mode bit in Negotiate Protocol response states * to use challenge/response method (i.e. Password bit is 1). */ rc = calc_lanman_hash(ses->password, ses->server->cryptkey, @@ -1303,9 +1322,8 @@ sess_auth_kerberos(struct sess_data *sess_data) * sending us a response in an expected form */ if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) { - cifs_dbg(VFS, - "incorrect version of cifs.upcall (expected %d but got %d)", - CIFS_SPNEGO_UPCALL_VERSION, msg->version); + cifs_dbg(VFS, "incorrect version of cifs.upcall (expected %d but got %d)\n", + CIFS_SPNEGO_UPCALL_VERSION, msg->version); rc = -EKEYREJECTED; goto out_put_spnego_key; } @@ -1313,8 +1331,8 @@ sess_auth_kerberos(struct sess_data *sess_data) ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, GFP_KERNEL); if (!ses->auth_key.response) { - cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory", - msg->sesskey_len); + cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory\n", + msg->sesskey_len); rc = -ENOMEM; goto out_put_spnego_key; } @@ -1657,8 +1675,7 @@ static int select_sec(struct cifs_ses *ses, struct sess_data *sess_data) type = cifs_select_sectype(ses->server, ses->sectype); cifs_dbg(FYI, "sess setup type %d\n", type); if (type == Unspecified) { - cifs_dbg(VFS, - "Unable to select appropriate authentication method!"); + cifs_dbg(VFS, "Unable to select appropriate authentication method!\n"); return -EINVAL; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index b130efaf8feb..197ed455e657 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -247,7 +247,7 @@ check2ndT2(char *buf) /* check for plausible wct, bcc and t2 data and parm sizes */ /* check for parm and data offset going beyond end of smb */ if (pSMB->WordCount != 10) { /* coalesce_t2 depends on this */ - cifs_dbg(FYI, "invalid transact2 word count\n"); + cifs_dbg(FYI, "Invalid transact2 word count\n"); return -EINVAL; } diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index a8c301ae00ed..0a116fc490a9 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -47,6 +47,18 @@ free_set_inf_compound(struct smb_rqst *rqst) } +struct cop_vars { + struct cifs_open_parms oparms; + struct kvec rsp_iov[3]; + struct smb_rqst rqst[3]; + struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; + struct kvec qi_iov[1]; + struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec close_iov[1]; + struct smb2_file_rename_info rename_info; + struct smb2_file_link_info link_info; +}; + static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, @@ -54,35 +66,36 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, __u32 create_options, umode_t mode, void *ptr, int command, struct cifsFileInfo *cfile) { + struct cop_vars *vars = NULL; + struct kvec *rsp_iov; + struct smb_rqst *rqst; int rc; __le16 *utf16_path = NULL; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - struct cifs_open_parms oparms; struct cifs_fid fid; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server; int num_rqst = 0; - struct smb_rqst rqst[3]; int resp_buftype[3]; - struct kvec rsp_iov[3]; - struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; - struct kvec qi_iov[1]; - struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; - struct kvec close_iov[1]; struct smb2_query_info_rsp *qi_rsp = NULL; int flags = 0; __u8 delete_pending[8] = {1, 0, 0, 0, 0, 0, 0, 0}; unsigned int size[2]; void *data[2]; - struct smb2_file_rename_info rename_info; - struct smb2_file_link_info link_info; int len; + vars = kzalloc(sizeof(*vars), GFP_ATOMIC); + if (vars == NULL) + return -ENOMEM; + rqst = &vars->rqst[0]; + rsp_iov = &vars->rsp_iov[0]; + + server = cifs_pick_channel(ses); + if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - memset(rqst, 0, sizeof(rqst)); resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; - memset(rsp_iov, 0, sizeof(rsp_iov)); /* We already have a handle so we can skip the open */ if (cfile) @@ -95,19 +108,18 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, goto finished; } - memset(&oparms, 0, sizeof(struct cifs_open_parms)); - oparms.tcon = tcon; - oparms.desired_access = desired_access; - oparms.disposition = create_disposition; - oparms.create_options = cifs_create_options(cifs_sb, create_options); - oparms.fid = &fid; - oparms.reconnect = false; - oparms.mode = mode; - - memset(&open_iov, 0, sizeof(open_iov)); - rqst[num_rqst].rq_iov = open_iov; + vars->oparms.tcon = tcon; + vars->oparms.desired_access = desired_access; + vars->oparms.disposition = create_disposition; + vars->oparms.create_options = cifs_create_options(cifs_sb, create_options); + vars->oparms.fid = &fid; + vars->oparms.reconnect = false; + vars->oparms.mode = mode; + + rqst[num_rqst].rq_iov = &vars->open_iov[0]; rqst[num_rqst].rq_nvec = SMB2_CREATE_IOV_SIZE; - rc = SMB2_open_init(tcon, &rqst[num_rqst], &oplock, &oparms, + rc = SMB2_open_init(tcon, server, + &rqst[num_rqst], &oplock, &vars->oparms, utf16_path); kfree(utf16_path); if (rc) @@ -121,12 +133,12 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, /* Operation */ switch (command) { case SMB2_OP_QUERY_INFO: - memset(&qi_iov, 0, sizeof(qi_iov)); - rqst[num_rqst].rq_iov = qi_iov; + rqst[num_rqst].rq_iov = &vars->qi_iov[0]; rqst[num_rqst].rq_nvec = 1; if (cfile) - rc = SMB2_query_info_init(tcon, &rqst[num_rqst], + rc = SMB2_query_info_init(tcon, server, + &rqst[num_rqst], cfile->fid.persistent_fid, cfile->fid.volatile_fid, FILE_ALL_INFORMATION, @@ -134,10 +146,11 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, sizeof(struct smb2_file_all_info) + PATH_MAX * 2, 0, NULL); else { - rc = SMB2_query_info_init(tcon, &rqst[num_rqst], + rc = SMB2_query_info_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, - FILE_ALL_INFORMATION, + FILE_ALL_INFORMATION, SMB2_O_INFO_FILE, 0, sizeof(struct smb2_file_all_info) + PATH_MAX * 2, 0, NULL); @@ -164,14 +177,14 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, trace_smb3_mkdir_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_RMDIR: - memset(&si_iov, 0, sizeof(si_iov)); - rqst[num_rqst].rq_iov = si_iov; + rqst[num_rqst].rq_iov = &vars->si_iov[0]; rqst[num_rqst].rq_nvec = 1; size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */ data[0] = &delete_pending[0]; - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], COMPOUND_FID, + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_DISPOSITION_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); @@ -182,14 +195,14 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, trace_smb3_rmdir_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_EOF: - memset(&si_iov, 0, sizeof(si_iov)); - rqst[num_rqst].rq_iov = si_iov; + rqst[num_rqst].rq_iov = &vars->si_iov[0]; rqst[num_rqst].rq_nvec = 1; size[0] = 8; /* sizeof __le64 */ data[0] = ptr; - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], COMPOUND_FID, + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); @@ -200,8 +213,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_INFO: - memset(&si_iov, 0, sizeof(si_iov)); - rqst[num_rqst].rq_iov = si_iov; + rqst[num_rqst].rq_iov = &vars->si_iov[0]; rqst[num_rqst].rq_nvec = 1; @@ -209,13 +221,15 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, data[0] = ptr; if (cfile) - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], cfile->fid.persistent_fid, cfile->fid.volatile_fid, current->tgid, FILE_BASIC_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); else { - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_BASIC_INFORMATION, @@ -233,30 +247,31 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, full_path); break; case SMB2_OP_RENAME: - memset(&si_iov, 0, sizeof(si_iov)); - rqst[num_rqst].rq_iov = si_iov; + rqst[num_rqst].rq_iov = &vars->si_iov[0]; rqst[num_rqst].rq_nvec = 2; len = (2 * UniStrnlen((wchar_t *)ptr, PATH_MAX)); - rename_info.ReplaceIfExists = 1; - rename_info.RootDirectory = 0; - rename_info.FileNameLength = cpu_to_le32(len); + vars->rename_info.ReplaceIfExists = 1; + vars->rename_info.RootDirectory = 0; + vars->rename_info.FileNameLength = cpu_to_le32(len); size[0] = sizeof(struct smb2_file_rename_info); - data[0] = &rename_info; + data[0] = &vars->rename_info; size[1] = len + 2 /* null */; data[1] = (__le16 *)ptr; if (cfile) - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], cfile->fid.persistent_fid, cfile->fid.volatile_fid, current->tgid, FILE_RENAME_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); else { - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_RENAME_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); @@ -271,23 +286,23 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_HARDLINK: - memset(&si_iov, 0, sizeof(si_iov)); - rqst[num_rqst].rq_iov = si_iov; + rqst[num_rqst].rq_iov = &vars->si_iov[0]; rqst[num_rqst].rq_nvec = 2; len = (2 * UniStrnlen((wchar_t *)ptr, PATH_MAX)); - link_info.ReplaceIfExists = 0; - link_info.RootDirectory = 0; - link_info.FileNameLength = cpu_to_le32(len); + vars->link_info.ReplaceIfExists = 0; + vars->link_info.RootDirectory = 0; + vars->link_info.FileNameLength = cpu_to_le32(len); size[0] = sizeof(struct smb2_file_link_info); - data[0] = &link_info; + data[0] = &vars->link_info; size[1] = len + 2 /* null */; data[1] = (__le16 *)ptr; - rc = SMB2_set_info_init(tcon, &rqst[num_rqst], COMPOUND_FID, + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_LINK_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); @@ -308,10 +323,10 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, if (cfile) goto after_close; /* Close */ - memset(&close_iov, 0, sizeof(close_iov)); - rqst[num_rqst].rq_iov = close_iov; + rqst[num_rqst].rq_iov = &vars->close_iov[0]; rqst[num_rqst].rq_nvec = 1; - rc = SMB2_close_init(tcon, &rqst[num_rqst], COMPOUND_FID, + rc = SMB2_close_init(tcon, server, + &rqst[num_rqst], COMPOUND_FID, COMPOUND_FID, false); smb2_set_related(&rqst[num_rqst]); if (rc) @@ -322,11 +337,13 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, if (cfile) { cifsFileInfo_put(cfile); cfile = NULL; - rc = compound_send_recv(xid, ses, flags, num_rqst - 2, + rc = compound_send_recv(xid, ses, server, + flags, num_rqst - 2, &rqst[1], &resp_buftype[1], &rsp_iov[1]); } else - rc = compound_send_recv(xid, ses, flags, num_rqst, + rc = compound_send_recv(xid, ses, server, + flags, num_rqst, rqst, resp_buftype, rsp_iov); @@ -336,8 +353,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_open_free(&rqst[0]); if (rc == -EREMCHG) { - printk_once(KERN_WARNING "server share %s deleted\n", - tcon->treeName); + pr_warn_once("server share %s deleted\n", tcon->treeName); tcon->need_reconnect = true; } @@ -420,6 +436,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + kfree(vars); return rc; } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 497afb0b9960..6a39451973f8 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -110,14 +110,14 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len, /* Make sure that negotiate contexts start after gss security blob */ nc_offset = le32_to_cpu(pneg_rsp->NegotiateContextOffset); if (nc_offset < non_ctxlen) { - printk_once(KERN_WARNING "invalid negotiate context offset\n"); + pr_warn_once("Invalid negotiate context offset\n"); return 0; } size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen; /* Verify that at least minimal negotiate contexts fit within frame */ if (len < nc_offset + (neg_count * sizeof(struct smb2_neg_context))) { - printk_once(KERN_WARNING "negotiate context goes beyond end\n"); + pr_warn_once("negotiate context goes beyond end\n"); return 0; } @@ -190,14 +190,14 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) return 1; if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) { - cifs_dbg(VFS, "Illegal structure size %u\n", + cifs_dbg(VFS, "Invalid structure size %u\n", le16_to_cpu(shdr->StructureSize)); return 1; } command = le16_to_cpu(shdr->Command); if (command >= NUMBER_OF_SMB2_COMMANDS) { - cifs_dbg(VFS, "Illegal SMB2 command %d\n", command); + cifs_dbg(VFS, "Invalid SMB2 command %d\n", command); return 1; } @@ -205,7 +205,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 || pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2)) { /* error packets have 9 byte structure size */ - cifs_dbg(VFS, "Illegal response size %u for command %d\n", + cifs_dbg(VFS, "Invalid response size %u for command %d\n", le16_to_cpu(pdu->StructureSize2), command); return 1; } else if (command == SMB2_OPLOCK_BREAK_HE @@ -213,7 +213,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) && (le16_to_cpu(pdu->StructureSize2) != 44) && (le16_to_cpu(pdu->StructureSize2) != 36)) { /* special case for SMB2.1 lease break message */ - cifs_dbg(VFS, "Illegal response size %d for oplock break\n", + cifs_dbg(VFS, "Invalid response size %d for oplock break\n", le16_to_cpu(pdu->StructureSize2)); return 1; } @@ -864,14 +864,14 @@ ok: d = server->secmech.sdescsha512; rc = crypto_shash_init(&d->shash); if (rc) { - cifs_dbg(VFS, "%s: could not init sha512 shash\n", __func__); + cifs_dbg(VFS, "%s: Could not init sha512 shash\n", __func__); return rc; } rc = crypto_shash_update(&d->shash, ses->preauth_sha_hash, SMB2_PREAUTH_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: could not update sha512 shash\n", __func__); + cifs_dbg(VFS, "%s: Could not update sha512 shash\n", __func__); return rc; } @@ -879,7 +879,7 @@ ok: rc = crypto_shash_update(&d->shash, iov[i].iov_base, iov[i].iov_len); if (rc) { - cifs_dbg(VFS, "%s: could not update sha512 shash\n", + cifs_dbg(VFS, "%s: Could not update sha512 shash\n", __func__); return rc; } @@ -887,7 +887,7 @@ ok: rc = crypto_shash_final(&d->shash, ses->preauth_sha_hash); if (rc) { - cifs_dbg(VFS, "%s: could not finalize sha512 shash\n", + cifs_dbg(VFS, "%s: Could not finalize sha512 shash\n", __func__); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f829f4165d38..736d86b8a910 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -12,6 +12,7 @@ #include <linux/uuid.h> #include <linux/sort.h> #include <crypto/aead.h> +#include <linux/fiemap.h> #include "cifsfs.h" #include "cifsglob.h" #include "smb2pdu.h" @@ -79,7 +80,7 @@ smb2_add_credits(struct TCP_Server_Info *server, if (*val > 65000) { *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ - printk_once(KERN_WARNING "server overflowed SMB3 credits\n"); + pr_warn_once("server overflowed SMB3 credits\n"); } server->in_flight--; if (server->in_flight == 0 && (optype & CIFS_OP_MASK) != CIFS_NEG_OP) @@ -708,7 +709,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, oparms.fid = pfid; oparms.reconnect = false; - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &utf16_path); + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, &utf16_path); if (rc) goto oshr_free; smb2_set_next_command(tcon, &rqst[0]); @@ -717,7 +719,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = qi_iov; rqst[1].rq_nvec = 1; - rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, + rc = SMB2_query_info_init(tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, FILE_ALL_INFORMATION, SMB2_O_INFO_FILE, 0, sizeof(struct smb2_file_all_info) + @@ -727,7 +730,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, smb2_set_related(&rqst[1]); - rc = compound_send_recv(xid, ses, flags, 2, rqst, + rc = compound_send_recv(xid, ses, server, + flags, 2, rqst, resp_buftype, rsp_iov); mutex_lock(&tcon->crfid.fid_mutex); @@ -767,8 +771,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, if (rc) { if (rc == -EREMCHG) { tcon->need_reconnect = true; - printk_once(KERN_WARNING "server share %s deleted\n", - tcon->treeName); + pr_warn_once("server share %s deleted\n", + tcon->treeName); } goto oshr_exit; } @@ -1102,6 +1106,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb) { struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); __le16 *utf16_path = NULL; int ea_name_len = strlen(ea_name); int flags = 0; @@ -1190,7 +1195,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto sea_exit; smb2_set_next_command(tcon, &rqst[0]); @@ -1216,7 +1222,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, size[0] = len; data[0] = ea; - rc = SMB2_set_info_init(tcon, &rqst[1], COMPOUND_FID, + rc = SMB2_set_info_init(tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); @@ -1228,10 +1235,12 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, memset(&close_iov, 0, sizeof(close_iov)); rqst[2].rq_iov = close_iov; rqst[2].rq_nvec = 1; - rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); + rc = SMB2_close_init(tcon, server, + &rqst[2], COMPOUND_FID, COMPOUND_FID, false); smb2_set_related(&rqst[2]); - rc = compound_send_recv(xid, ses, flags, 3, rqst, + rc = compound_send_recv(xid, ses, server, + flags, 3, rqst, resp_buftype, rsp_iov); /* no need to bump num_remote_opens because handle immediately closed */ @@ -1452,6 +1461,16 @@ req_res_key_exit: return rc; } +struct iqi_vars { + struct smb_rqst rqst[3]; + struct kvec rsp_iov[3]; + struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; + struct kvec qi_iov[1]; + struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; + struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec close_iov[1]; +}; + static int smb2_ioctl_query_info(const unsigned int xid, struct cifs_tcon *tcon, @@ -1459,7 +1478,11 @@ smb2_ioctl_query_info(const unsigned int xid, __le16 *path, int is_dir, unsigned long p) { + struct iqi_vars *vars; + struct smb_rqst *rqst; + struct kvec *rsp_iov; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); char __user *arg = (char __user *)p; struct smb_query_info qi; struct smb_query_info __user *pqi; @@ -1468,45 +1491,47 @@ smb2_ioctl_query_info(const unsigned int xid, struct smb2_query_info_rsp *qi_rsp = NULL; struct smb2_ioctl_rsp *io_rsp = NULL; void *buffer = NULL; - struct smb_rqst rqst[3]; int resp_buftype[3]; - struct kvec rsp_iov[3]; - struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; struct cifs_open_parms oparms; u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_fid fid; - struct kvec qi_iov[1]; - struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; - struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; - struct kvec close_iov[1]; unsigned int size[2]; void *data[2]; int create_options = is_dir ? CREATE_NOT_FILE : CREATE_NOT_DIR; - memset(rqst, 0, sizeof(rqst)); + vars = kzalloc(sizeof(*vars), GFP_ATOMIC); + if (vars == NULL) + return -ENOMEM; + rqst = &vars->rqst[0]; + rsp_iov = &vars->rsp_iov[0]; + resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; - memset(rsp_iov, 0, sizeof(rsp_iov)); if (copy_from_user(&qi, arg, sizeof(struct smb_query_info))) - return -EFAULT; + goto e_fault; - if (qi.output_buffer_length > 1024) + if (qi.output_buffer_length > 1024) { + kfree(vars); return -EINVAL; + } - if (!ses || !(ses->server)) + if (!ses || !server) { + kfree(vars); return -EIO; + } if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; buffer = memdup_user(arg + sizeof(struct smb_query_info), qi.output_buffer_length); - if (IS_ERR(buffer)) + if (IS_ERR(buffer)) { + kfree(vars); return PTR_ERR(buffer); + } /* Open */ - memset(&open_iov, 0, sizeof(open_iov)); - rqst[0].rq_iov = open_iov; + rqst[0].rq_iov = &vars->open_iov[0]; rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; memset(&oparms, 0, sizeof(oparms)); @@ -1537,7 +1562,8 @@ smb2_ioctl_query_info(const unsigned int xid, oparms.desired_access = FILE_READ_ATTRIBUTES | READ_CONTROL; } - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, path); + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, path); if (rc) goto iqinf_exit; smb2_set_next_command(tcon, &rqst[0]); @@ -1548,11 +1574,11 @@ smb2_ioctl_query_info(const unsigned int xid, if (!capable(CAP_SYS_ADMIN)) rc = -EPERM; else { - memset(&io_iov, 0, sizeof(io_iov)); - rqst[1].rq_iov = io_iov; + rqst[1].rq_iov = &vars->io_iov[0]; rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst[1], + rc = SMB2_ioctl_init(tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, qi.info_type, true, buffer, qi.output_buffer_length, @@ -1565,31 +1591,32 @@ smb2_ioctl_query_info(const unsigned int xid, if (!capable(CAP_SYS_ADMIN)) rc = -EPERM; else { - memset(&si_iov, 0, sizeof(si_iov)); - rqst[1].rq_iov = si_iov; + rqst[1].rq_iov = &vars->si_iov[0]; rqst[1].rq_nvec = 1; size[0] = 8; data[0] = buffer; - rc = SMB2_set_info_init(tcon, &rqst[1], + rc = SMB2_set_info_init(tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); } } else if (qi.flags == PASSTHRU_QUERY_INFO) { - memset(&qi_iov, 0, sizeof(qi_iov)); - rqst[1].rq_iov = qi_iov; + rqst[1].rq_iov = &vars->qi_iov[0]; rqst[1].rq_nvec = 1; - rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, + rc = SMB2_query_info_init(tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, qi.file_info_class, qi.info_type, qi.additional_information, qi.input_buffer_length, qi.output_buffer_length, buffer); } else { /* unknown flags */ - cifs_tcon_dbg(VFS, "invalid passthru query flags: 0x%x\n", qi.flags); + cifs_tcon_dbg(VFS, "Invalid passthru query flags: 0x%x\n", + qi.flags); rc = -EINVAL; } @@ -1599,16 +1626,17 @@ smb2_ioctl_query_info(const unsigned int xid, smb2_set_related(&rqst[1]); /* Close */ - memset(&close_iov, 0, sizeof(close_iov)); - rqst[2].rq_iov = close_iov; + rqst[2].rq_iov = &vars->close_iov[0]; rqst[2].rq_nvec = 1; - rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); + rc = SMB2_close_init(tcon, server, + &rqst[2], COMPOUND_FID, COMPOUND_FID, false); if (rc) goto iqinf_exit; smb2_set_related(&rqst[2]); - rc = compound_send_recv(xid, ses, flags, 3, rqst, + rc = compound_send_recv(xid, ses, server, + flags, 3, rqst, resp_buftype, rsp_iov); if (rc) goto iqinf_exit; @@ -1649,6 +1677,7 @@ smb2_ioctl_query_info(const unsigned int xid, } iqinf_exit: + kfree(vars); kfree(buffer); SMB2_open_free(&rqst[0]); if (qi.flags & PASSTHRU_FSCTL) @@ -1719,7 +1748,7 @@ smb2_copychunk_range(const unsigned int xid, if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { - cifs_tcon_dbg(VFS, "invalid cchunk response size\n"); + cifs_tcon_dbg(VFS, "Invalid cchunk response size\n"); rc = -EIO; goto cchunk_out; } @@ -1733,12 +1762,12 @@ smb2_copychunk_range(const unsigned int xid, */ if (le32_to_cpu(retbuf->TotalBytesWritten) > le32_to_cpu(pcchunk->Length)) { - cifs_tcon_dbg(VFS, "invalid copy chunk response\n"); + cifs_tcon_dbg(VFS, "Invalid copy chunk response\n"); rc = -EIO; goto cchunk_out; } if (le32_to_cpu(retbuf->ChunksWritten) != 1) { - cifs_tcon_dbg(VFS, "invalid num chunks written\n"); + cifs_tcon_dbg(VFS, "Invalid num chunks written\n"); rc = -EIO; goto cchunk_out; } @@ -2159,6 +2188,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct smb2_query_directory_rsp *qd_rsp = NULL; struct smb2_create_rsp *op_rsp = NULL; + struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) @@ -2183,7 +2213,8 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = fid; oparms.reconnect = false; - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto qdf_free; smb2_set_next_command(tcon, &rqst[0]); @@ -2196,7 +2227,8 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = qd_iov; rqst[1].rq_nvec = SMB2_QUERY_DIRECTORY_IOV_SIZE; - rc = SMB2_query_directory_init(xid, tcon, &rqst[1], + rc = SMB2_query_directory_init(xid, tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, 0, srch_inf->info_level); if (rc) @@ -2204,7 +2236,8 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, smb2_set_related(&rqst[1]); - rc = compound_send_recv(xid, tcon->ses, flags, 2, rqst, + rc = compound_send_recv(xid, tcon->ses, server, + flags, 2, rqst, resp_buftype, rsp_iov); /* If the open failed there is nothing to do */ @@ -2409,6 +2442,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb) { struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); int flags = 0; struct smb_rqst rqst[3]; int resp_buftype[3]; @@ -2439,7 +2473,8 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto qic_exit; smb2_set_next_command(tcon, &rqst[0]); @@ -2448,7 +2483,8 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = qi_iov; rqst[1].rq_nvec = 1; - rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID, + rc = SMB2_query_info_init(tcon, server, + &rqst[1], COMPOUND_FID, COMPOUND_FID, class, type, 0, output_len, 0, NULL); @@ -2461,19 +2497,21 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, rqst[2].rq_iov = close_iov; rqst[2].rq_nvec = 1; - rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); + rc = SMB2_close_init(tcon, server, + &rqst[2], COMPOUND_FID, COMPOUND_FID, false); if (rc) goto qic_exit; smb2_set_related(&rqst[2]); - rc = compound_send_recv(xid, ses, flags, 3, rqst, + rc = compound_send_recv(xid, ses, server, + flags, 3, rqst, resp_buftype, rsp_iov); if (rc) { free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); if (rc == -EREMCHG) { tcon->need_reconnect = true; - printk_once(KERN_WARNING "server share %s deleted\n", - tcon->treeName); + pr_warn_once("server share %s deleted\n", + tcon->treeName); } goto qic_exit; } @@ -2753,15 +2791,15 @@ parse_reparse_point(struct reparse_data_buffer *buf, struct cifs_sb_info *cifs_sb) { if (plen < sizeof(struct reparse_data_buffer)) { - cifs_dbg(VFS, "reparse buffer is too small. Must be " - "at least 8 bytes but was %d\n", plen); + cifs_dbg(VFS, "reparse buffer is too small. Must be at least 8 bytes but was %d\n", + plen); return -EIO; } if (plen < le16_to_cpu(buf->ReparseDataLength) + sizeof(struct reparse_data_buffer)) { - cifs_dbg(VFS, "srv returned invalid reparse buf " - "length: %d\n", plen); + cifs_dbg(VFS, "srv returned invalid reparse buf length: %d\n", + plen); return -EIO; } @@ -2776,8 +2814,8 @@ parse_reparse_point(struct reparse_data_buffer *buf, (struct reparse_symlink_data_buffer *)buf, plen, target_path, cifs_sb); default: - cifs_dbg(VFS, "srv returned unknown symlink buffer " - "tag:0x%08x\n", le32_to_cpu(buf->ReparseTag)); + cifs_dbg(VFS, "srv returned unknown symlink buffer tag:0x%08x\n", + le32_to_cpu(buf->ReparseTag)); return -EOPNOTSUPP; } } @@ -2798,6 +2836,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct kvec err_iov = {NULL, 0}; struct smb2_err_rsp *err_buf = NULL; struct smb2_symlink_err_rsp *symlink; + struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); unsigned int sub_len; unsigned int sub_offset; unsigned int print_len; @@ -2843,7 +2882,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto querty_exit; smb2_set_next_command(tcon, &rqst[0]); @@ -2854,7 +2894,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = io_iov; rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst[1], fid.persistent_fid, + rc = SMB2_ioctl_init(tcon, server, + &rqst[1], fid.persistent_fid, fid.volatile_fid, FSCTL_GET_REPARSE_POINT, true /* is_fctl */, NULL, 0, CIFSMaxBufSize - @@ -2872,13 +2913,15 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rqst[2].rq_iov = close_iov; rqst[2].rq_nvec = 1; - rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); + rc = SMB2_close_init(tcon, server, + &rqst[2], COMPOUND_FID, COMPOUND_FID, false); if (rc) goto querty_exit; smb2_set_related(&rqst[2]); - rc = compound_send_recv(xid, tcon->ses, flags, 3, rqst, + rc = compound_send_recv(xid, tcon->ses, server, + flags, 3, rqst, resp_buftype, rsp_iov); create_rsp = rsp_iov[0].iov_base; @@ -3407,8 +3450,9 @@ static int smb3_fiemap(struct cifs_tcon *tcon, int i, num, rc, flags, last_blob; u64 next; - if (fiemap_check_flags(fei, FIEMAP_FLAG_SYNC)) - return -EBADR; + rc = fiemap_prep(d_inode(cfile->dentry), fei, start, &len, 0); + if (rc) + return rc; xid = get_xid(); again: @@ -4571,7 +4615,7 @@ smb2_make_node(unsigned int xid, struct inode *inode, struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); int rc = -EPERM; FILE_ALL_INFO *buf = NULL; - struct cifs_io_parms io_parms; + struct cifs_io_parms io_parms = {0}; __u32 oplock = 0; struct cifs_fid fid; struct cifs_open_parms oparms; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b30aa3cdd845..ded96b529a4d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -85,7 +85,7 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = { int smb3_encryption_required(const struct cifs_tcon *tcon) { - if (!tcon) + if (!tcon || !tcon->ses) return 0; if ((tcon->ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) || (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)) @@ -98,14 +98,13 @@ int smb3_encryption_required(const struct cifs_tcon *tcon) static void smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd, - const struct cifs_tcon *tcon) + const struct cifs_tcon *tcon, + struct TCP_Server_Info *server) { shdr->ProtocolId = SMB2_PROTO_NUMBER; shdr->StructureSize = cpu_to_le16(64); shdr->Command = smb2_cmd; - if (tcon && tcon->ses && tcon->ses->server) { - struct TCP_Server_Info *server = tcon->ses->server; - + if (server) { spin_lock(&server->req_lock); /* Request up to 10 credits but don't go over the limit. */ if (server->credits >= server->max_credits) @@ -125,8 +124,7 @@ smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd, /* GLOBAL_CAP_LARGE_MTU will only be set if dialect > SMB2.02 */ /* See sections 2.2.4 and 3.2.4.1.5 of MS-SMB2 */ - if ((tcon->ses) && (tcon->ses->server) && - (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU)) + if (server && (server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU)) shdr->CreditCharge = cpu_to_le16(1); /* else CreditCharge MBZ */ @@ -148,8 +146,7 @@ smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd, /* if (tcon->share_flags & SHI1005_FLAGS_DFS) shdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */ - if (tcon->ses && tcon->ses->server && tcon->ses->server->sign && - !smb3_encryption_required(tcon)) + if (server && server->sign && !smb3_encryption_required(tcon)) shdr->Flags |= SMB2_FLAGS_SIGNED; out: return; @@ -160,6 +157,7 @@ static int __smb2_reconnect(const struct nls_table *nlsc, struct cifs_tcon *tcon) { int rc; + struct TCP_Server_Info *server = tcon->ses->server; struct dfs_cache_tgt_list tl; struct dfs_cache_tgt_iterator *it = NULL; char *tree; @@ -172,15 +170,15 @@ static int __smb2_reconnect(const struct nls_table *nlsc, if (!tree) return -ENOMEM; - if (tcon->ipc) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", - tcon->ses->server->hostname); - rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); - goto out; - } - if (!tcon->dfs_path) { - rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); + if (tcon->ipc) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", + server->hostname); + rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + } else { + rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, + nlsc); + } goto out; } @@ -188,13 +186,13 @@ static int __smb2_reconnect(const struct nls_table *nlsc, if (rc) goto out; - extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, - &tcp_host_len); + extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); for (it = dfs_cache_get_tgt_iterator(&tl); it; it = dfs_cache_get_next_tgt(&tl, it)) { const char *share, *prefix; size_t share_len, prefix_len; + bool target_match; rc = dfs_cache_get_tgt_share(it, &share, &share_len, &prefix, &prefix_len); @@ -208,19 +206,38 @@ static int __smb2_reconnect(const struct nls_table *nlsc, if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { - cifs_dbg(FYI, "%s: skipping %.*s, doesn't match %.*s", + cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, dfs_host, (int)tcp_host_len, tcp_host); - continue; - } - scnprintf(tree, MAX_TREE_SIZE, "\\%.*s", (int)share_len, share); + rc = match_target_ip(server, dfs_host, dfs_host_len, + &target_match); + if (rc) { + cifs_dbg(VFS, "%s: failed to match target ip: %d\n", + __func__, rc); + break; + } - rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); - if (!rc) { - rc = update_super_prepath(tcon, prefix, prefix_len); - break; + if (!target_match) { + cifs_dbg(FYI, "%s: skipping target\n", __func__); + continue; + } + } + + if (tcon->ipc) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%.*s\\IPC$", + (int)share_len, share); + rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + } else { + scnprintf(tree, MAX_TREE_SIZE, "\\%.*s", (int)share_len, + share); + rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + if (!rc) { + rc = update_super_prepath(tcon, prefix, + prefix_len); + break; + } } if (rc == -EREMOTE) break; @@ -247,12 +264,12 @@ static inline int __smb2_reconnect(const struct nls_table *nlsc, #endif static int -smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) +smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, + struct TCP_Server_Info *server) { int rc; struct nls_table *nls_codepage; struct cifs_ses *ses; - struct TCP_Server_Info *server; int retries; /* @@ -281,12 +298,10 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) } } if ((!tcon->ses) || (tcon->ses->status == CifsExiting) || - (!tcon->ses->server)) + (!tcon->ses->server) || !server) return -EIO; ses = tcon->ses; - server = ses->server; - retries = server->nr_targets; /* @@ -314,8 +329,8 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) (server->tcpStatus != CifsNeedReconnect), 10 * HZ); if (rc < 0) { - cifs_dbg(FYI, "%s: aborting reconnect due to a received" - " signal by the process\n", __func__); + cifs_dbg(FYI, "%s: aborting reconnect due to a received signal by the process\n", + __func__); return -ERESTARTSYS; } @@ -360,15 +375,31 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) goto out; } + /* + * If we are reconnecting an extra channel, bind + */ + if (server->is_channel) { + ses->binding = true; + ses->binding_chan = cifs_ses_find_chan(ses, server); + } + rc = cifs_negotiate_protocol(0, tcon->ses); if (!rc && tcon->ses->need_reconnect) { rc = cifs_setup_session(0, tcon->ses, nls_codepage); if ((rc == -EACCES) && !tcon->retry) { rc = -EHOSTDOWN; + ses->binding = false; + ses->binding_chan = NULL; mutex_unlock(&tcon->ses->session_mutex); goto failed; } } + /* + * End of channel binding + */ + ses->binding = false; + ses->binding_chan = NULL; + if (rc || !tcon->need_reconnect) { mutex_unlock(&tcon->ses->session_mutex); goto out; @@ -384,7 +415,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc); if (rc) { /* If sess reconnected but tcon didn't, something strange ... */ - printk_once(KERN_WARNING "reconnect tcon failed rc = %d\n", rc); + pr_warn_once("reconnect tcon failed rc = %d\n", rc); goto out; } @@ -419,7 +450,9 @@ failed: } static void -fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf, +fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + void *buf, unsigned int *total_len) { struct smb2_sync_pdu *spdu = (struct smb2_sync_pdu *)buf; @@ -432,7 +465,7 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf, */ memset(buf, 0, 256); - smb2_hdr_assemble(&spdu->sync_hdr, smb2_command, tcon); + smb2_hdr_assemble(&spdu->sync_hdr, smb2_command, tcon, server); spdu->StructureSize2 = cpu_to_le16(parmsize); *total_len = parmsize + sizeof(struct smb2_sync_hdr); @@ -444,7 +477,8 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf, * function must have filled in request_buf pointer. */ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, - void **request_buf, unsigned int *total_len) + struct TCP_Server_Info *server, + void **request_buf, unsigned int *total_len) { /* BB eventually switch this to SMB2 specific small buf size */ if (smb2_command == SMB2_SET_INFO) @@ -456,7 +490,7 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, return -ENOMEM; } - fill_small_buf(smb2_command, tcon, + fill_small_buf(smb2_command, tcon, server, (struct smb2_sync_hdr *)(*request_buf), total_len); @@ -470,27 +504,30 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, } static int smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, + struct TCP_Server_Info *server, void **request_buf, unsigned int *total_len) { int rc; - rc = smb2_reconnect(smb2_command, tcon); + rc = smb2_reconnect(smb2_command, tcon, server); if (rc) return rc; - return __smb2_plain_req_init(smb2_command, tcon, request_buf, + return __smb2_plain_req_init(smb2_command, tcon, server, request_buf, total_len); } static int smb2_ioctl_req_init(u32 opcode, struct cifs_tcon *tcon, + struct TCP_Server_Info *server, void **request_buf, unsigned int *total_len) { /* Skip reconnect only for FSCTL_VALIDATE_NEGOTIATE_INFO IOCTLs */ if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) { - return __smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf, - total_len); + return __smb2_plain_req_init(SMB2_IOCTL, tcon, server, + request_buf, total_len); } - return smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf, total_len); + return smb2_plain_req_init(SMB2_IOCTL, tcon, server, + request_buf, total_len); } /* For explanation of negotiate contexts see MS-SMB2 section 2.2.3.1 */ @@ -626,13 +663,13 @@ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) /* If invalid preauth context warn but use what we requested, SHA-512 */ if (len < MIN_PREAUTH_CTXT_DATA_LEN) { - printk_once(KERN_WARNING "server sent bad preauth context\n"); + pr_warn_once("server sent bad preauth context\n"); return; } if (le16_to_cpu(ctxt->HashAlgorithmCount) != 1) - printk_once(KERN_WARNING "illegal SMB3 hash algorithm count\n"); + pr_warn_once("Invalid SMB3 hash algorithm count\n"); if (ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) - printk_once(KERN_WARNING "unknown SMB3 hash algorithm\n"); + pr_warn_once("unknown SMB3 hash algorithm\n"); } static void decode_compress_ctx(struct TCP_Server_Info *server, @@ -642,15 +679,15 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, /* sizeof compress context is a one element compression capbility struct */ if (len < 10) { - printk_once(KERN_WARNING "server sent bad compression cntxt\n"); + pr_warn_once("server sent bad compression cntxt\n"); return; } if (le16_to_cpu(ctxt->CompressionAlgorithmCount) != 1) { - printk_once(KERN_WARNING "illegal SMB3 compress algorithm count\n"); + pr_warn_once("Invalid SMB3 compress algorithm count\n"); return; } if (le16_to_cpu(ctxt->CompressionAlgorithms[0]) > 3) { - printk_once(KERN_WARNING "unknown compression algorithm\n"); + pr_warn_once("unknown compression algorithm\n"); return; } server->compress_algorithm = ctxt->CompressionAlgorithms[0]; @@ -663,18 +700,18 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server, cifs_dbg(FYI, "decode SMB3.11 encryption neg context of len %d\n", len); if (len < MIN_ENCRYPT_CTXT_DATA_LEN) { - printk_once(KERN_WARNING "server sent bad crypto ctxt len\n"); + pr_warn_once("server sent bad crypto ctxt len\n"); return -EINVAL; } if (le16_to_cpu(ctxt->CipherCount) != 1) { - printk_once(KERN_WARNING "illegal SMB3.11 cipher count\n"); + pr_warn_once("Invalid SMB3.11 cipher count\n"); return -EINVAL; } cifs_dbg(FYI, "SMB311 cipher type:%d\n", le16_to_cpu(ctxt->Ciphers[0])); if ((ctxt->Ciphers[0] != SMB2_ENCRYPTION_AES128_CCM) && (ctxt->Ciphers[0] != SMB2_ENCRYPTION_AES128_GCM)) { - printk_once(KERN_WARNING "invalid SMB3.11 cipher returned\n"); + pr_warn_once("Invalid SMB3.11 cipher returned\n"); return -EINVAL; } server->cipher_type = ctxt->Ciphers[0]; @@ -774,7 +811,7 @@ create_posix_buf(umode_t mode) buf->Name[14] = 0xCD; buf->Name[15] = 0x7C; buf->Mode = cpu_to_le32(mode); - cifs_dbg(FYI, "mode on posix create 0%o", mode); + cifs_dbg(FYI, "mode on posix create 0%o\n", mode); return buf; } @@ -786,7 +823,7 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) iov[num].iov_base = create_posix_buf(mode); if (mode == ACL_NO_MODE) - cifs_dbg(FYI, "illegal mode\n"); + cifs_dbg(FYI, "Invalid mode\n"); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_posix); @@ -838,7 +875,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) return -EIO; } - rc = smb2_plain_req_init(SMB2_NEGOTIATE, NULL, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_NEGOTIATE, NULL, server, + (void **) &req, &total_len); if (rc) return rc; @@ -896,7 +934,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_negotiate_rsp *)rsp_iov.iov_base; /* @@ -904,9 +943,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]); */ if (rc == -EOPNOTSUPP) { - cifs_server_dbg(VFS, "Dialect not supported by server. Consider " - "specifying vers=1.0 or vers=2.0 on mount for accessing" - " older servers\n"); + cifs_server_dbg(VFS, "Dialect not supported by server. Consider specifying vers=1.0 or vers=2.0 on mount for accessing older servers\n"); goto neg_exit; } else if (rc != 0) goto neg_exit; @@ -939,8 +976,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (le16_to_cpu(rsp->DialectRevision) != server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ - cifs_server_dbg(VFS, "Illegal 0x%x dialect returned: not requested\n", - le16_to_cpu(rsp->DialectRevision)); + cifs_server_dbg(VFS, "Invalid 0x%x dialect returned: not requested\n", + le16_to_cpu(rsp->DialectRevision)); return -EIO; } @@ -957,8 +994,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) cifs_dbg(FYI, "negotiated smb3.1.1 dialect\n"); else { - cifs_server_dbg(VFS, "Illegal dialect returned by server 0x%x\n", - le16_to_cpu(rsp->DialectRevision)); + cifs_server_dbg(VFS, "Invalid dialect returned by server 0x%x\n", + le16_to_cpu(rsp->DialectRevision)); rc = -EIO; goto neg_exit; } @@ -1116,15 +1153,16 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) rc = 0; goto out_free_inbuf; } else if (rc != 0) { - cifs_tcon_dbg(VFS, "validate protocol negotiate failed: %d\n", rc); + cifs_tcon_dbg(VFS, "validate protocol negotiate failed: %d\n", + rc); rc = -EIO; goto out_free_inbuf; } rc = -EIO; if (rsplen != sizeof(*pneg_rsp)) { - cifs_tcon_dbg(VFS, "invalid protocol negotiate response size: %d\n", - rsplen); + cifs_tcon_dbg(VFS, "Invalid protocol negotiate response size: %d\n", + rsplen); /* relax check since Mac returns max bufsize allowed on ioctl */ if (rsplen > CIFSMaxBufSize || rsplen < sizeof(*pneg_rsp)) @@ -1208,8 +1246,9 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) struct TCP_Server_Info *server = cifs_ses_server(ses); unsigned int total_len; - rc = smb2_plain_req_init(SMB2_SESSION_SETUP, NULL, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_SESSION_SETUP, NULL, server, + (void **) &req, + &total_len); if (rc) return rc; @@ -1286,6 +1325,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) /* BB add code to build os and lm fields */ rc = cifs_send_recv(sess_data->xid, sess_data->ses, + cifs_ses_server(sess_data->ses), &rqst, &sess_data->buf0_type, CIFS_LOG_ERROR | CIFS_NEG_OP, &rsp_iov); @@ -1357,9 +1397,8 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) * sending us a response in an expected form */ if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) { - cifs_dbg(VFS, - "bad cifs.upcall version. Expected %d got %d", - CIFS_SPNEGO_UPCALL_VERSION, msg->version); + cifs_dbg(VFS, "bad cifs.upcall version. Expected %d got %d\n", + CIFS_SPNEGO_UPCALL_VERSION, msg->version); rc = -EKEYREJECTED; goto out_put_spnego_key; } @@ -1369,8 +1408,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, GFP_KERNEL); if (!ses->auth_key.response) { - cifs_dbg(VFS, - "Kerberos can't allocate (%u bytes) memory", + cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory\n", msg->sesskey_len); rc = -ENOMEM; goto out_put_spnego_key; @@ -1584,8 +1622,7 @@ SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data) type = smb2_select_sectype(cifs_ses_server(ses), ses->sectype); cifs_dbg(FYI, "sess setup type %d\n", type); if (type == Unspecified) { - cifs_dbg(VFS, - "Unable to select appropriate authentication method!"); + cifs_dbg(VFS, "Unable to select appropriate authentication method!\n"); return -EINVAL; } @@ -1673,7 +1710,8 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) if (ses->need_reconnect) goto smb2_session_already_dead; - rc = smb2_plain_req_init(SMB2_LOGOFF, NULL, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_LOGOFF, NULL, ses->server, + (void **) &req, &total_len); if (rc) return rc; @@ -1694,7 +1732,8 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, ses->server, + &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); /* * No tcon so can't do @@ -1735,7 +1774,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, __le16 *unc_path = NULL; int flags = 0; unsigned int total_len; - struct TCP_Server_Info *server = ses->server; + struct TCP_Server_Info *server; + + /* always use master channel */ + server = ses->server; cifs_dbg(FYI, "TCON\n"); @@ -1756,8 +1798,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */ tcon->tid = 0; atomic_set(&tcon->num_remote_opens, 0); - rc = smb2_plain_req_init(SMB2_TREE_CONNECT, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_TREE_CONNECT, tcon, server, + (void **) &req, &total_len); if (rc) { kfree(unc_path); return rc; @@ -1796,7 +1838,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, /* Need 64 for max size write so ask for more in case not there yet */ req->sync_hdr.CreditRequest = cpu_to_le16(64); - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base; trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc); @@ -1881,8 +1924,9 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) close_shroot_lease(&tcon->crfid); - rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, ses->server, + (void **) &req, + &total_len); if (rc) return rc; @@ -1898,7 +1942,8 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, ses->server, + &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) cifs_stats_fail_inc(tcon, SMB2_TREE_DISCONNECT_HE); @@ -2452,6 +2497,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, int flags = 0; unsigned int total_len; __le16 *utf16_path = NULL; + struct TCP_Server_Info *server = cifs_pick_channel(ses); cifs_dbg(FYI, "mkdir\n"); @@ -2460,13 +2506,14 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, if (!utf16_path) return -ENOMEM; - if (!ses || !(ses->server)) { + if (!ses || !server) { rc = -EIO; goto err_free_path; } /* resource #2: request */ - rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_CREATE, tcon, server, + (void **) &req, &total_len); if (rc) goto err_free_path; @@ -2552,7 +2599,8 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, trace_smb3_posix_mkdir_enter(xid, tcon->tid, ses->Suid, CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES); /* resource #4: response buffer */ - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_CREATE_HE); trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid, @@ -2581,10 +2629,10 @@ err_free_path: } int -SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock, +SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, + struct smb_rqst *rqst, __u8 *oplock, struct cifs_open_parms *oparms, __le16 *path) { - struct TCP_Server_Info *server = tcon->ses->server; struct smb2_create_req *req; unsigned int n_iov = 2; __u32 file_attributes = 0; @@ -2595,7 +2643,8 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock, __le16 *copy_path; int rc; - rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_CREATE, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -2767,9 +2816,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, { struct smb_rqst rqst; struct smb2_create_rsp *rsp = NULL; - struct TCP_Server_Info *server; struct cifs_tcon *tcon = oparms->tcon; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); struct kvec iov[SMB2_CREATE_IOV_SIZE]; struct kvec rsp_iov = {NULL, 0}; int resp_buftype = CIFS_NO_BUFFER; @@ -2777,9 +2826,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, int flags = 0; cifs_dbg(FYI, "create/open\n"); - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !server) return -EIO; if (smb3_encryption_required(tcon)) @@ -2790,14 +2837,16 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, rqst.rq_iov = iov; rqst.rq_nvec = SMB2_CREATE_IOV_SIZE; - rc = SMB2_open_init(tcon, &rqst, oplock, oparms, path); + rc = SMB2_open_init(tcon, server, + &rqst, oplock, oparms, path); if (rc) goto creat_exit; trace_smb3_open_enter(xid, tcon->tid, tcon->ses->Suid, oparms->create_options, oparms->desired_access); - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_create_rsp *)rsp_iov.iov_base; @@ -2812,8 +2861,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, trace_smb3_open_err(xid, tcon->tid, ses->Suid, oparms->create_options, oparms->desired_access, rc); if (rc == -EREMCHG) { - printk_once(KERN_WARNING "server share %s deleted\n", - tcon->treeName); + pr_warn_once("server share %s deleted\n", + tcon->treeName); tcon->need_reconnect = true; } goto creat_exit; @@ -2849,7 +2898,8 @@ creat_exit: } int -SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, __u32 max_response_size) @@ -2860,7 +2910,8 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, int rc; char *in_data_buf; - rc = smb2_ioctl_req_init(opcode, tcon, (void **) &req, &total_len); + rc = smb2_ioctl_req_init(opcode, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -2922,7 +2973,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, * response size smaller. */ req->MaxOutputResponse = cpu_to_le32(max_response_size); - + req->sync_hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(max_response_size, SMB2_MAX_BUFFER_SIZE)); if (is_fsctl) req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); else @@ -2960,12 +3011,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, struct smb_rqst rqst; struct smb2_ioctl_rsp *rsp = NULL; struct cifs_ses *ses; + struct TCP_Server_Info *server; struct kvec iov[SMB2_IOCTL_IOV_SIZE]; struct kvec rsp_iov = {NULL, 0}; int resp_buftype = CIFS_NO_BUFFER; int rc = 0; int flags = 0; - struct TCP_Server_Info *server; cifs_dbg(FYI, "SMB2 IOCTL\n"); @@ -2976,14 +3027,14 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, if (plen) *plen = 0; - if (tcon) - ses = tcon->ses; - else + if (!tcon) return -EIO; + ses = tcon->ses; if (!ses) return -EIO; - server = ses->server; + + server = cifs_pick_channel(ses); if (!server) return -EIO; @@ -2995,12 +3046,14 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rqst.rq_iov = iov; rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, opcode, + rc = SMB2_ioctl_init(tcon, server, + &rqst, persistent_fid, volatile_fid, opcode, is_fsctl, in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base; @@ -3088,7 +3141,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, } int -SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +SMB2_close_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, bool query_attrs) { struct smb2_close_req *req; @@ -3096,7 +3150,8 @@ SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, unsigned int total_len; int rc; - rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_CLOSE, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -3127,6 +3182,7 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, struct smb_rqst rqst; struct smb2_close_rsp *rsp = NULL; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); struct kvec iov[1]; struct kvec rsp_iov; int resp_buftype = CIFS_NO_BUFFER; @@ -3136,7 +3192,7 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, cifs_dbg(FYI, "Close\n"); - if (!ses || !(ses->server)) + if (!ses || !server) return -EIO; if (smb3_encryption_required(tcon)) @@ -3152,12 +3208,14 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, query_attrs = true; trace_smb3_close_enter(xid, persistent_fid, tcon->tid, ses->Suid); - rc = SMB2_close_init(tcon, &rqst, persistent_fid, volatile_fid, + rc = SMB2_close_init(tcon, server, + &rqst, persistent_fid, volatile_fid, query_attrs); if (rc) goto close_exit; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_close_rsp *)rsp_iov.iov_base; if (rc != 0) { @@ -3225,7 +3283,7 @@ smb2_validate_iov(unsigned int offset, unsigned int buffer_length, } if ((begin_of_buf > end_of_smb) || (end_of_buf > end_of_smb)) { - cifs_dbg(VFS, "illegal server response, bad offset to data\n"); + cifs_dbg(VFS, "Invalid server response, bad offset to data\n"); return -EINVAL; } @@ -3257,7 +3315,8 @@ smb2_validate_and_copy_iov(unsigned int offset, unsigned int buffer_length, } int -SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type, u32 additional_info, size_t output_len, size_t input_len, void *input) @@ -3267,8 +3326,8 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, unsigned int total_len; int rc; - rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -3320,7 +3379,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, if (!ses) return -EIO; - server = ses->server; + server = cifs_pick_channel(ses); if (!server) return -EIO; @@ -3332,7 +3391,8 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = SMB2_query_info_init(tcon, &rqst, persistent_fid, volatile_fid, + rc = SMB2_query_info_init(tcon, server, + &rqst, persistent_fid, volatile_fid, info_class, info_type, additional_info, output_len, 0, NULL); if (rc) @@ -3341,7 +3401,8 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, trace_smb3_query_info_enter(xid, persistent_fid, tcon->tid, ses->Suid, info_class, (__u32)info_type); - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base; if (rc) { @@ -3426,15 +3487,17 @@ SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, static int SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst, - struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, - u32 completion_filter, bool watch_tree) + struct cifs_tcon *tcon, struct TCP_Server_Info *server, + u64 persistent_fid, u64 volatile_fid, + u32 completion_filter, bool watch_tree) { struct smb2_change_notify_req *req; struct kvec *iov = rqst->rq_iov; unsigned int total_len; int rc; - rc = smb2_plain_req_init(SMB2_CHANGE_NOTIFY, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_CHANGE_NOTIFY, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -3461,6 +3524,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, u32 completion_filter) { struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); struct smb_rqst rqst; struct kvec iov[1]; struct kvec rsp_iov = {NULL, 0}; @@ -3469,7 +3533,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; cifs_dbg(FYI, "change notify\n"); - if (!ses || !(ses->server)) + if (!ses || !server) return -EIO; if (smb3_encryption_required(tcon)) @@ -3480,14 +3544,16 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = SMB2_notify_init(xid, &rqst, tcon, persistent_fid, volatile_fid, + rc = SMB2_notify_init(xid, &rqst, tcon, server, + persistent_fid, volatile_fid, completion_filter, watch_tree); if (rc) goto cnotify_exit; trace_smb3_notify_enter(xid, persistent_fid, tcon->tid, ses->Suid, (u8)watch_tree, completion_filter); - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); if (rc != 0) { cifs_stats_fail_inc(tcon, SMB2_CHANGE_NOTIFY_HE); @@ -3577,7 +3643,7 @@ void smb2_reconnect_server(struct work_struct *work) spin_unlock(&cifs_tcp_ses_lock); list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) { - rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon); + rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server); if (!rc) cifs_reopen_persistent_handles(tcon); else @@ -3617,7 +3683,8 @@ SMB2_echo(struct TCP_Server_Info *server) return rc; } - rc = smb2_plain_req_init(SMB2_ECHO, NULL, (void **)&req, &total_len); + rc = smb2_plain_req_init(SMB2_ECHO, NULL, server, + (void **)&req, &total_len); if (rc) return rc; @@ -3644,14 +3711,16 @@ SMB2_flush_free(struct smb_rqst *rqst) int SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst, - struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid) + struct cifs_tcon *tcon, struct TCP_Server_Info *server, + u64 persistent_fid, u64 volatile_fid) { struct smb2_flush_req *req; struct kvec *iov = rqst->rq_iov; unsigned int total_len; int rc; - rc = smb2_plain_req_init(SMB2_FLUSH, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_FLUSH, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -3672,6 +3741,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, struct smb_rqst rqst; struct kvec iov[1]; struct kvec rsp_iov = {NULL, 0}; + struct TCP_Server_Info *server = cifs_pick_channel(ses); int resp_buftype = CIFS_NO_BUFFER; int flags = 0; int rc = 0; @@ -3688,12 +3758,14 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = SMB2_flush_init(xid, &rqst, tcon, persistent_fid, volatile_fid); + rc = SMB2_flush_init(xid, &rqst, tcon, server, + persistent_fid, volatile_fid); if (rc) goto flush_exit; trace_smb3_flush_enter(xid, persistent_fid, tcon->tid, ses->Suid); - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); if (rc != 0) { cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE); @@ -3721,14 +3793,13 @@ smb2_new_read_req(void **buf, unsigned int *total_len, int rc = -EACCES; struct smb2_read_plain_req *req = NULL; struct smb2_sync_hdr *shdr; - struct TCP_Server_Info *server; + struct TCP_Server_Info *server = io_parms->server; - rc = smb2_plain_req_init(SMB2_READ, io_parms->tcon, (void **) &req, - total_len); + rc = smb2_plain_req_init(SMB2_READ, io_parms->tcon, server, + (void **) &req, total_len); if (rc) return rc; - server = io_parms->tcon->ses->server; if (server == NULL) return -ECONNABORTED; @@ -3757,8 +3828,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len, rdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) { struct smbd_buffer_descriptor_v1 *v1; - bool need_invalidate = - io_parms->tcon->ses->server->dialect == SMB30_PROT_ID; + bool need_invalidate = server->dialect == SMB30_PROT_ID; rdata->mr = smbd_register_mr( server->smbd_conn, rdata->pages, @@ -3815,7 +3885,7 @@ smb2_readv_callback(struct mid_q_entry *mid) { struct cifs_readdata *rdata = mid->callback_data; struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; + struct TCP_Server_Info *server = rdata->server; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)rdata->iov[0].iov_base; struct cifs_credits credits = { .value = 0, .instance = 0 }; @@ -3827,6 +3897,10 @@ smb2_readv_callback(struct mid_q_entry *mid) .rq_pagesz = rdata->pagesz, .rq_tailsz = rdata->tailsz }; + WARN_ONCE(rdata->server != mid->server, + "rdata server %p != mid server %p", + rdata->server, mid->server); + cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n", __func__, mid->mid, mid->mid_state, rdata->result, rdata->bytes); @@ -3904,20 +3978,23 @@ smb2_async_readv(struct cifs_readdata *rdata) struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 1 }; struct TCP_Server_Info *server; + struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); unsigned int total_len; cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n", __func__, rdata->offset, rdata->bytes); + if (!rdata->server) + rdata->server = cifs_pick_channel(tcon->ses); + io_parms.tcon = tlink_tcon(rdata->cfile->tlink); + io_parms.server = server = rdata->server; io_parms.offset = rdata->offset; io_parms.length = rdata->bytes; io_parms.persistent_fid = rdata->cfile->fid.persistent_fid; io_parms.volatile_fid = rdata->cfile->fid.volatile_fid; io_parms.pid = rdata->pid; - server = io_parms.tcon->ses->server; - rc = smb2_new_read_req( (void **) &buf, &total_len, &io_parms, rdata, 0, 0); if (rc) @@ -3945,7 +4022,7 @@ smb2_async_readv(struct cifs_readdata *rdata) } kref_get(&rdata->refcount); - rc = cifs_call_async(io_parms.tcon->ses->server, &rqst, + rc = cifs_call_async(server, &rqst, cifs_readv_receive, smb2_readv_callback, smb3_handle_read_data, rdata, flags, &rdata->credits); @@ -3977,6 +4054,9 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, int flags = CIFS_LOG_ERROR; struct cifs_ses *ses = io_parms->tcon->ses; + if (!io_parms->server) + io_parms->server = cifs_pick_channel(io_parms->tcon->ses); + *nbytes = 0; rc = smb2_new_read_req((void **)&req, &total_len, io_parms, NULL, 0, 0); if (rc) @@ -3992,7 +4072,8 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, io_parms->server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; if (rc) { @@ -4048,11 +4129,15 @@ smb2_writev_callback(struct mid_q_entry *mid) { struct cifs_writedata *wdata = mid->callback_data; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; + struct TCP_Server_Info *server = wdata->server; unsigned int written; struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf; struct cifs_credits credits = { .value = 0, .instance = 0 }; + WARN_ONCE(wdata->server != mid->server, + "wdata server %p != mid server %p", + wdata->server, mid->server); + switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: credits.value = le16_to_cpu(rsp->sync_hdr.CreditRequest); @@ -4108,8 +4193,8 @@ smb2_writev_callback(struct mid_q_entry *mid) tcon->tid, tcon->ses->Suid, wdata->offset, wdata->bytes, wdata->result); if (wdata->result == -ENOSPC) - printk_once(KERN_WARNING "Out of space writing to %s\n", - tcon->treeName); + pr_warn_once("Out of space writing to %s\n", + tcon->treeName); } else trace_smb3_write_done(0 /* no xid */, wdata->cfile->fid.persistent_fid, @@ -4130,12 +4215,16 @@ smb2_async_writev(struct cifs_writedata *wdata, struct smb2_write_req *req = NULL; struct smb2_sync_hdr *shdr; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; + struct TCP_Server_Info *server = wdata->server; struct kvec iov[1]; struct smb_rqst rqst = { }; unsigned int total_len; - rc = smb2_plain_req_init(SMB2_WRITE, tcon, (void **) &req, &total_len); + if (!wdata->server) + server = wdata->server = cifs_pick_channel(tcon->ses); + + rc = smb2_plain_req_init(SMB2_WRITE, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -4274,20 +4363,24 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, struct kvec rsp_iov; int flags = 0; unsigned int total_len; + struct TCP_Server_Info *server; *nbytes = 0; if (n_vec < 1) return rc; - rc = smb2_plain_req_init(SMB2_WRITE, io_parms->tcon, (void **) &req, - &total_len); + if (!io_parms->server) + io_parms->server = cifs_pick_channel(io_parms->tcon->ses); + server = io_parms->server; + if (server == NULL) + return -ECONNABORTED; + + rc = smb2_plain_req_init(SMB2_WRITE, io_parms->tcon, server, + (void **) &req, &total_len); if (rc) return rc; - if (io_parms->tcon->ses->server == NULL) - return -ECONNABORTED; - if (smb3_encryption_required(io_parms->tcon)) flags |= CIFS_TRANSFORM_REQ; @@ -4316,7 +4409,8 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_iov = iov; rqst.rq_nvec = n_vec + 1; - rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, + rc = cifs_send_recv(xid, io_parms->tcon->ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; @@ -4490,11 +4584,12 @@ num_entries(int infotype, char *bufstart, char *end_of_buf, char **lastentry, * Readdir/FindFirst */ int SMB2_query_directory_init(const unsigned int xid, - struct cifs_tcon *tcon, struct smb_rqst *rqst, + struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, int index, int info_level) { - struct TCP_Server_Info *server = tcon->ses->server; struct smb2_query_directory_req *req; unsigned char *bufptr; __le16 asteriks = cpu_to_le16('*'); @@ -4505,8 +4600,8 @@ int SMB2_query_directory_init(const unsigned int xid, struct kvec *iov = rqst->rq_iov; int len, rc; - rc = smb2_plain_req_init(SMB2_QUERY_DIRECTORY, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_QUERY_DIRECTORY, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -4632,7 +4727,7 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, else if (resp_buftype == CIFS_SMALL_BUFFER) srch_inf->smallBuf = true; else - cifs_tcon_dbg(VFS, "illegal search buffer type\n"); + cifs_tcon_dbg(VFS, "Invalid search buffer type\n"); return 0; } @@ -4649,6 +4744,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, struct kvec rsp_iov; int rc = 0; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); int flags = 0; if (!ses || !(ses->server)) @@ -4662,13 +4758,15 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = SMB2_QUERY_DIRECTORY_IOV_SIZE; - rc = SMB2_query_directory_init(xid, tcon, &rqst, persistent_fid, + rc = SMB2_query_directory_init(xid, tcon, server, + &rqst, persistent_fid, volatile_fid, index, srch_inf->info_level); if (rc) goto qdir_exit; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base; if (rc) { @@ -4705,17 +4803,19 @@ qdir_exit: } int -SMB2_set_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, - u64 persistent_fid, u64 volatile_fid, u32 pid, u8 info_class, - u8 info_type, u32 additional_info, - void **data, unsigned int *size) +SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, + struct smb_rqst *rqst, + u64 persistent_fid, u64 volatile_fid, u32 pid, + u8 info_class, u8 info_type, u32 additional_info, + void **data, unsigned int *size) { struct smb2_set_info_req *req; struct kvec *iov = rqst->rq_iov; unsigned int i, total_len; int rc; - rc = smb2_plain_req_init(SMB2_SET_INFO, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_SET_INFO, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -4766,9 +4866,10 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int resp_buftype; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); int flags = 0; - if (!ses || !(ses->server)) + if (!ses || !server) return -EIO; if (!num) @@ -4785,7 +4886,8 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = num; - rc = SMB2_set_info_init(tcon, &rqst, persistent_fid, volatile_fid, pid, + rc = SMB2_set_info_init(tcon, server, + &rqst, persistent_fid, volatile_fid, pid, info_class, info_type, additional_info, data, size); if (rc) { @@ -4794,7 +4896,8 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, } - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); SMB2_set_info_free(&rqst); rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base; @@ -4857,6 +4960,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, int rc; struct smb2_oplock_break *req = NULL; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); int flags = CIFS_OBREAK_OP; unsigned int total_len; struct kvec iov[1]; @@ -4864,8 +4968,8 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, int resp_buf_type; cifs_dbg(FYI, "SMB2_oplock_break\n"); - rc = smb2_plain_req_init(SMB2_OPLOCK_BREAK, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_OPLOCK_BREAK, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -4886,7 +4990,8 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) { @@ -4929,8 +5034,10 @@ copy_posix_fs_info_to_kstatfs(FILE_SYSTEM_POSIX_INFO *response_data, } static int -build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level, - int outbuf_len, u64 persistent_fid, u64 volatile_fid) +build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + int level, int outbuf_len, u64 persistent_fid, + u64 volatile_fid) { int rc; struct smb2_query_info_req *req; @@ -4938,11 +5045,11 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level, cifs_dbg(FYI, "Query FSInfo level %d\n", level); - if ((tcon->ses == NULL) || (tcon->ses->server == NULL)) + if ((tcon->ses == NULL) || server == NULL) return -EIO; - rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -4972,10 +5079,12 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int resp_buftype; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); FILE_SYSTEM_POSIX_INFO *info = NULL; int flags = 0; - rc = build_qfs_info_req(&iov, tcon, FS_POSIX_INFORMATION, + rc = build_qfs_info_req(&iov, tcon, server, + FS_POSIX_INFORMATION, sizeof(FILE_SYSTEM_POSIX_INFO), persistent_fid, volatile_fid); if (rc) @@ -4988,7 +5097,8 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = &iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(iov.iov_base); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); @@ -5020,10 +5130,12 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int resp_buftype; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); struct smb2_fs_full_size_info *info = NULL; int flags = 0; - rc = build_qfs_info_req(&iov, tcon, FS_FULL_SIZE_INFORMATION, + rc = build_qfs_info_req(&iov, tcon, server, + FS_FULL_SIZE_INFORMATION, sizeof(struct smb2_fs_full_size_info), persistent_fid, volatile_fid); if (rc) @@ -5036,7 +5148,8 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = &iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(iov.iov_base); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); @@ -5068,6 +5181,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int resp_buftype, max_len, min_len; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = cifs_pick_channel(ses); unsigned int rsp_len, offset; int flags = 0; @@ -5088,7 +5202,8 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, return -EINVAL; } - rc = build_qfs_info_req(&iov, tcon, level, max_len, + rc = build_qfs_info_req(&iov, tcon, server, + level, max_len, persistent_fid, volatile_fid); if (rc) return rc; @@ -5100,7 +5215,8 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = &iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(iov.iov_base); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); @@ -5153,10 +5269,12 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, unsigned int count; int flags = CIFS_NO_RSP_BUF; unsigned int total_len; + struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); cifs_dbg(FYI, "smb2_lockv num lock %d\n", num_lock); - rc = smb2_plain_req_init(SMB2_LOCK, tcon, (void **) &req, &total_len); + rc = smb2_plain_req_init(SMB2_LOCK, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -5182,7 +5300,8 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = 2; - rc = cifs_send_recv(xid, tcon->ses, &rqst, &resp_buf_type, flags, + rc = cifs_send_recv(xid, tcon->ses, server, + &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); if (rc) { @@ -5227,10 +5346,11 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, int resp_buf_type; __u64 *please_key_high; __u64 *please_key_low; + struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); cifs_dbg(FYI, "SMB2_lease_break\n"); - rc = smb2_plain_req_init(SMB2_OPLOCK_BREAK, tcon, (void **) &req, - &total_len); + rc = smb2_plain_req_init(SMB2_OPLOCK_BREAK, tcon, server, + (void **) &req, &total_len); if (rc) return rc; @@ -5253,7 +5373,8 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); + rc = cifs_send_recv(xid, ses, server, + &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); please_key_low = (__u64 *)lease_key; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 10acf90f858d..3b0e6acf9d7d 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -143,8 +143,17 @@ struct smb2_transform_hdr { __u64 SessionId; } __packed; +/* See MS-SMB2 2.2.42 */ +struct smb2_compression_transform_hdr { + __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */ + __le32 OriginalCompressedSegmentSize; + __le16 CompressionAlgorithm; + __le16 Flags; + __le16 Length; /* if chained it is length, else offset */ +} __packed; + /* See MS-SMB2 2.2.42.1 */ -struct compression_playload_header { +struct compression_payload_header { __le16 AlgorithmId; __le16 Reserved; __le32 Length; @@ -333,7 +342,7 @@ struct smb2_encryption_neg_context { #define SMB3_COMPRESS_LZ77 cpu_to_le16(0x0002) #define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003) /* Pattern scanning algorithm See MS-SMB2 3.1.4.4.1 */ -#define SMB3_COMPRESS_PATTERN cpu_to_le16(0x0004) +#define SMB3_COMPRESS_PATTERN cpu_to_le16(0x0004) /* Pattern_V1 */ /* Compression Flags */ #define SMB2_COMPRESSION_CAPABILITIES_FLAG_NONE cpu_to_le32(0x00000000) diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 087d5f14320b..71ba74792c9e 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -143,7 +143,9 @@ extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, struct smb2_file_all_info *buf, struct create_posix_rsp *posix, struct kvec *err_iov, int *resp_buftype); -extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +extern int SMB2_open_init(struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + struct smb_rqst *rqst, __u8 *oplock, struct cifs_open_parms *oparms, __le16 *path); extern void SMB2_open_free(struct smb_rqst *rqst); @@ -151,7 +153,9 @@ extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); -extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +extern int SMB2_ioctl_init(struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, __u32 max_response_size); @@ -165,19 +169,25 @@ extern int __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, struct smb2_file_network_open_info *pbuf); extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); -extern int SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, - u64 persistent_fid, u64 volatile_fid, bool query_attrs); +extern int SMB2_close_init(struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + struct smb_rqst *rqst, + u64 persistent_fid, u64 volatile_fid, + bool query_attrs); extern void SMB2_close_free(struct smb_rqst *rqst); extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); extern int SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst, struct cifs_tcon *tcon, + struct TCP_Server_Info *server, u64 persistent_file_id, u64 volatile_file_id); extern void SMB2_flush_free(struct smb_rqst *rqst); extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct smb2_file_all_info *data); -extern int SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +extern int SMB2_query_info_init(struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type, u32 additional_info, size_t output_len, @@ -201,6 +211,7 @@ extern int SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, int index, struct cifs_search_info *srch_inf); extern int SMB2_query_directory_init(unsigned int xid, struct cifs_tcon *tcon, + struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, int index, int info_level); @@ -208,7 +219,9 @@ extern void SMB2_query_directory_free(struct smb_rqst *rqst); extern int SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 pid, __le64 *eof); -extern int SMB2_set_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, +extern int SMB2_set_info_init(struct cifs_tcon *tcon, + struct TCP_Server_Info *server, + struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 pid, u8 info_class, u8 info_type, u32 additional_info, void **data, unsigned int *size); diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 1a5834a5d597..b029ed31ef91 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -294,15 +294,12 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) static void dump_smbd_negotiate_resp(struct smbd_negotiate_resp *resp) { - log_rdma_event(INFO, "resp message min_version %u max_version %u " - "negotiated_version %u credits_requested %u " - "credits_granted %u status %u max_readwrite_size %u " - "preferred_send_size %u max_receive_size %u " - "max_fragmented_size %u\n", - resp->min_version, resp->max_version, resp->negotiated_version, - resp->credits_requested, resp->credits_granted, resp->status, - resp->max_readwrite_size, resp->preferred_send_size, - resp->max_receive_size, resp->max_fragmented_size); + log_rdma_event(INFO, "resp message min_version %u max_version %u negotiated_version %u credits_requested %u credits_granted %u status %u max_readwrite_size %u preferred_send_size %u max_receive_size %u max_fragmented_size %u\n", + resp->min_version, resp->max_version, + resp->negotiated_version, resp->credits_requested, + resp->credits_granted, resp->status, + resp->max_readwrite_size, resp->preferred_send_size, + resp->max_receive_size, resp->max_fragmented_size); } /* @@ -450,10 +447,9 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) struct smbd_connection *info = response->info; int data_length = 0; - log_rdma_recv(INFO, "response=%p type=%d wc status=%d wc opcode %d " - "byte_len=%d pkey_index=%x\n", - response, response->type, wc->status, wc->opcode, - wc->byte_len, wc->pkey_index); + log_rdma_recv(INFO, "response=%p type=%d wc status=%d wc opcode %d byte_len=%d pkey_index=%x\n", + response, response->type, wc->status, wc->opcode, + wc->byte_len, wc->pkey_index); if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) { log_rdma_recv(INFO, "wc->status=%d opcode=%d\n", @@ -519,12 +515,11 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) wake_up_interruptible(&info->wait_send_queue); } - log_incoming(INFO, "data flags %d data_offset %d " - "data_length %d remaining_data_length %d\n", - le16_to_cpu(data_transfer->flags), - le32_to_cpu(data_transfer->data_offset), - le32_to_cpu(data_transfer->data_length), - le32_to_cpu(data_transfer->remaining_data_length)); + log_incoming(INFO, "data flags %d data_offset %d data_length %d remaining_data_length %d\n", + le16_to_cpu(data_transfer->flags), + le32_to_cpu(data_transfer->data_offset), + le32_to_cpu(data_transfer->data_length), + le32_to_cpu(data_transfer->remaining_data_length)); /* Send a KEEP_ALIVE response right away if requested */ info->keep_alive_requested = KEEP_ALIVE_NONE; @@ -632,14 +627,10 @@ static int smbd_ia_open( } if (!frwr_is_supported(&info->id->device->attrs)) { - log_rdma_event(ERR, - "Fast Registration Work Requests " - "(FRWR) is not supported\n"); - log_rdma_event(ERR, - "Device capability flags = %llx " - "max_fast_reg_page_list_len = %u\n", - info->id->device->attrs.device_cap_flags, - info->id->device->attrs.max_fast_reg_page_list_len); + log_rdma_event(ERR, "Fast Registration Work Requests (FRWR) is not supported\n"); + log_rdma_event(ERR, "Device capability flags = %llx max_fast_reg_page_list_len = %u\n", + info->id->device->attrs.device_cap_flags, + info->id->device->attrs.max_fast_reg_page_list_len); rc = -EPROTONOSUPPORT; goto out2; } @@ -898,13 +889,12 @@ wait_send_queue: packet->remaining_data_length = cpu_to_le32(remaining_data_length); packet->padding = 0; - log_outgoing(INFO, "credits_requested=%d credits_granted=%d " - "data_offset=%d data_length=%d remaining_data_length=%d\n", - le16_to_cpu(packet->credits_requested), - le16_to_cpu(packet->credits_granted), - le32_to_cpu(packet->data_offset), - le32_to_cpu(packet->data_length), - le32_to_cpu(packet->remaining_data_length)); + log_outgoing(INFO, "credits_requested=%d credits_granted=%d data_offset=%d data_length=%d remaining_data_length=%d\n", + le16_to_cpu(packet->credits_requested), + le16_to_cpu(packet->credits_granted), + le32_to_cpu(packet->data_offset), + le32_to_cpu(packet->data_length), + le32_to_cpu(packet->remaining_data_length)); /* Map the packet to DMA */ header_length = sizeof(struct smbd_data_transfer); @@ -1078,11 +1068,9 @@ static int smbd_negotiate(struct smbd_connection *info) response->type = SMBD_NEGOTIATE_RESP; rc = smbd_post_recv(info, response); - log_rdma_event(INFO, - "smbd_post_recv rc=%d iov.addr=%llx iov.length=%x " - "iov.lkey=%x\n", - rc, response->sge.addr, - response->sge.length, response->sge.lkey); + log_rdma_event(INFO, "smbd_post_recv rc=%d iov.addr=%llx iov.length=%x iov.lkey=%x\n", + rc, response->sge.addr, + response->sge.length, response->sge.lkey); if (rc) return rc; @@ -1540,25 +1528,19 @@ static struct smbd_connection *_smbd_get_connection( if (smbd_send_credit_target > info->id->device->attrs.max_cqe || smbd_send_credit_target > info->id->device->attrs.max_qp_wr) { - log_rdma_event(ERR, - "consider lowering send_credit_target = %d. " - "Possible CQE overrun, device " - "reporting max_cpe %d max_qp_wr %d\n", - smbd_send_credit_target, - info->id->device->attrs.max_cqe, - info->id->device->attrs.max_qp_wr); + log_rdma_event(ERR, "consider lowering send_credit_target = %d. Possible CQE overrun, device reporting max_cpe %d max_qp_wr %d\n", + smbd_send_credit_target, + info->id->device->attrs.max_cqe, + info->id->device->attrs.max_qp_wr); goto config_failed; } if (smbd_receive_credit_max > info->id->device->attrs.max_cqe || smbd_receive_credit_max > info->id->device->attrs.max_qp_wr) { - log_rdma_event(ERR, - "consider lowering receive_credit_max = %d. " - "Possible CQE overrun, device " - "reporting max_cpe %d max_qp_wr %d\n", - smbd_receive_credit_max, - info->id->device->attrs.max_cqe, - info->id->device->attrs.max_qp_wr); + log_rdma_event(ERR, "consider lowering receive_credit_max = %d. Possible CQE overrun, device reporting max_cpe %d max_qp_wr %d\n", + smbd_receive_credit_max, + info->id->device->attrs.max_cqe, + info->id->device->attrs.max_qp_wr); goto config_failed; } @@ -1865,11 +1847,9 @@ again: to_read -= to_copy; data_read += to_copy; - log_read(INFO, "_get_first_reassembly memcpy %d bytes " - "data_transfer_length-offset=%d after that " - "to_read=%d data_read=%d offset=%d\n", - to_copy, data_length - offset, - to_read, data_read, offset); + log_read(INFO, "_get_first_reassembly memcpy %d bytes data_transfer_length-offset=%d after that to_read=%d data_read=%d offset=%d\n", + to_copy, data_length - offset, + to_read, data_read, offset); } spin_lock_irq(&info->reassembly_queue_lock); @@ -1878,10 +1858,9 @@ again: spin_unlock_irq(&info->reassembly_queue_lock); info->first_entry_offset = offset; - log_read(INFO, "returning to thread data_read=%d " - "reassembly_data_length=%d first_entry_offset=%d\n", - data_read, info->reassembly_data_length, - info->first_entry_offset); + log_read(INFO, "returning to thread data_read=%d reassembly_data_length=%d first_entry_offset=%d\n", + data_read, info->reassembly_data_length, + info->first_entry_offset); read_rfc1002_done: return data_read; } @@ -1952,7 +1931,7 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) if (iov_iter_rw(&msg->msg_iter) == WRITE) { /* It's a bug in upper layer to get there */ - cifs_dbg(VFS, "CIFS: invalid msg iter dir %u\n", + cifs_dbg(VFS, "Invalid msg iter dir %u\n", iov_iter_rw(&msg->msg_iter)); rc = -EINVAL; goto out; @@ -1974,7 +1953,7 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) default: /* It's a bug in upper layer to get there */ - cifs_dbg(VFS, "CIFS: invalid msg type %d\n", + cifs_dbg(VFS, "Invalid msg type %d\n", iov_iter_type(&msg->msg_iter)); rc = -EINVAL; } @@ -2043,10 +2022,9 @@ next_rqst: dump_smb(iov[i].iov_base, iov[i].iov_len); - log_write(INFO, "rqst_idx=%d nvec=%d rqst->rq_npages=%d rq_pagesz=%d " - "rq_tailsz=%d buflen=%lu\n", - rqst_idx, rqst->rq_nvec, rqst->rq_npages, rqst->rq_pagesz, - rqst->rq_tailsz, smb_rqst_len(server, rqst)); + log_write(INFO, "rqst_idx=%d nvec=%d rqst->rq_npages=%d rq_pagesz=%d rq_tailsz=%d buflen=%lu\n", + rqst_idx, rqst->rq_nvec, rqst->rq_npages, rqst->rq_pagesz, + rqst->rq_tailsz, smb_rqst_len(server, rqst)); start = i = 0; buflen = 0; @@ -2056,11 +2034,9 @@ next_rqst: if (i > start) { remaining_data_length -= (buflen-iov[i].iov_len); - log_write(INFO, "sending iov[] from start=%d " - "i=%d nvecs=%d " - "remaining_data_length=%d\n", - start, i, i-start, - remaining_data_length); + log_write(INFO, "sending iov[] from start=%d i=%d nvecs=%d remaining_data_length=%d\n", + start, i, i - start, + remaining_data_length); rc = smbd_post_send_data( info, &iov[start], i-start, remaining_data_length); @@ -2069,10 +2045,9 @@ next_rqst: } else { /* iov[start] is too big, break it */ nvecs = (buflen+max_iov_size-1)/max_iov_size; - log_write(INFO, "iov[%d] iov_base=%p buflen=%d" - " break to %d vectors\n", - start, iov[start].iov_base, - buflen, nvecs); + log_write(INFO, "iov[%d] iov_base=%p buflen=%d break to %d vectors\n", + start, iov[start].iov_base, + buflen, nvecs); for (j = 0; j < nvecs; j++) { vec.iov_base = (char *)iov[start].iov_base + @@ -2084,11 +2059,9 @@ next_rqst: max_iov_size*(nvecs-1); remaining_data_length -= vec.iov_len; log_write(INFO, - "sending vec j=%d iov_base=%p" - " iov_len=%zu " - "remaining_data_length=%d\n", - j, vec.iov_base, vec.iov_len, - remaining_data_length); + "sending vec j=%d iov_base=%p iov_len=%zu remaining_data_length=%d\n", + j, vec.iov_base, vec.iov_len, + remaining_data_length); rc = smbd_post_send_data( info, &vec, 1, remaining_data_length); @@ -2106,11 +2079,9 @@ next_rqst: if (i == rqst->rq_nvec) { /* send out all remaining vecs */ remaining_data_length -= buflen; - log_write(INFO, - "sending iov[] from start=%d i=%d " - "nvecs=%d remaining_data_length=%d\n", - start, i, i-start, - remaining_data_length); + log_write(INFO, "sending iov[] from start=%d i=%d nvecs=%d remaining_data_length=%d\n", + start, i, i - start, + remaining_data_length); rc = smbd_post_send_data(info, &iov[start], i-start, remaining_data_length); if (rc) @@ -2134,10 +2105,9 @@ next_rqst: if (j == nvecs-1) size = buflen - j*max_iov_size; remaining_data_length -= size; - log_write(INFO, "sending pages i=%d offset=%d size=%d" - " remaining_data_length=%d\n", - i, j*max_iov_size+offset, size, - remaining_data_length); + log_write(INFO, "sending pages i=%d offset=%d size=%d remaining_data_length=%d\n", + i, j * max_iov_size + offset, size, + remaining_data_length); rc = smbd_post_send_page( info, rqst->rq_pages[i], j*max_iov_size + offset, @@ -2211,11 +2181,9 @@ static void smbd_mr_recovery_work(struct work_struct *work) info->pd, info->mr_type, info->max_frmr_depth); if (IS_ERR(smbdirect_mr->mr)) { - log_rdma_mr(ERR, - "ib_alloc_mr failed mr_type=%x " - "max_frmr_depth=%x\n", - info->mr_type, - info->max_frmr_depth); + log_rdma_mr(ERR, "ib_alloc_mr failed mr_type=%x max_frmr_depth=%x\n", + info->mr_type, + info->max_frmr_depth); smbd_disconnect_rdma_connection(info); continue; } @@ -2278,9 +2246,8 @@ static int allocate_mr_list(struct smbd_connection *info) smbdirect_mr->mr = ib_alloc_mr(info->pd, info->mr_type, info->max_frmr_depth); if (IS_ERR(smbdirect_mr->mr)) { - log_rdma_mr(ERR, "ib_alloc_mr failed mr_type=%x " - "max_frmr_depth=%x\n", - info->mr_type, info->max_frmr_depth); + log_rdma_mr(ERR, "ib_alloc_mr failed mr_type=%x max_frmr_depth=%x\n", + info->mr_type, info->max_frmr_depth); goto out; } smbdirect_mr->sgl = kcalloc( diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 99760063e000..d11e31064679 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -112,7 +112,7 @@ static void _cifs_mid_q_entry_release(struct kref *refcount) #ifdef CONFIG_CIFS_STATS2 now = jiffies; if (now < midEntry->when_alloc) - cifs_server_dbg(VFS, "invalid mid allocation time\n"); + cifs_server_dbg(VFS, "Invalid mid allocation time\n"); roundtrip_time = now - midEntry->when_alloc; if (smb_cmd < NUMBER_OF_SMB2_COMMANDS) { @@ -151,12 +151,12 @@ static void _cifs_mid_q_entry_release(struct kref *refcount) trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { - pr_debug(" CIFS slow rsp: cmd %d mid %llu", - midEntry->command, midEntry->mid); - cifs_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n", - now - midEntry->when_alloc, - now - midEntry->when_sent, - now - midEntry->when_received); + pr_debug("slow rsp: cmd %d mid %llu", + midEntry->command, midEntry->mid); + cifs_info("A: 0x%lx S: 0x%lx R: 0x%lx\n", + now - midEntry->when_alloc, + now - midEntry->when_sent, + now - midEntry->when_received); } } #endif @@ -473,8 +473,7 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -ENOMEM; if (!server->ops->init_transform_rq) { - cifs_server_dbg(VFS, "Encryption requested but transform " - "callback is missing\n"); + cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n"); return -EIO; } @@ -989,8 +988,35 @@ cifs_cancelled_callback(struct mid_q_entry *mid) DeleteMidQEntry(mid); } +/* + * Return a channel (master if none) of @ses that can be used to send + * regular requests. + * + * If we are currently binding a new channel (negprot/sess.setup), + * return the new incomplete channel. + */ +struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) +{ + uint index = 0; + + if (!ses) + return NULL; + + if (!ses->binding) { + /* round robin */ + if (ses->chan_count > 1) { + index = (uint)atomic_inc_return(&ses->chan_seq); + index %= ses->chan_count; + } + return ses->chans[index].server; + } else { + return cifs_ses_server(ses); + } +} + int compound_send_recv(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, const int flags, const int num_rqst, struct smb_rqst *rqst, int *resp_buf_type, struct kvec *resp_iov) { @@ -1002,30 +1028,17 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, }; unsigned int instance; char *buf; - struct TCP_Server_Info *server; optype = flags & CIFS_OP_MASK; for (i = 0; i < num_rqst; i++) resp_buf_type[i] = CIFS_NO_BUFFER; /* no response buf yet */ - if ((ses == NULL) || (ses->server == NULL)) { + if (!ses || !ses->server || !server) { cifs_dbg(VFS, "Null session\n"); return -EIO; } - if (!ses->binding) { - uint index = 0; - - if (ses->chan_count > 1) { - index = (uint)atomic_inc_return(&ses->chan_seq); - index %= ses->chan_count; - } - server = ses->chans[index].server; - } else { - server = cifs_ses_server(ses); - } - if (server->tcpStatus == CifsExiting) return -ENOENT; @@ -1220,11 +1233,12 @@ out: int cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, struct smb_rqst *rqst, int *resp_buf_type, const int flags, struct kvec *resp_iov) { - return compound_send_recv(xid, ses, flags, 1, rqst, resp_buf_type, - resp_iov); + return compound_send_recv(xid, ses, server, flags, 1, + rqst, resp_buf_type, resp_iov); } int @@ -1259,7 +1273,8 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, rqst.rq_iov = new_iov; rqst.rq_nvec = n_vec + 1; - rc = cifs_send_recv(xid, ses, &rqst, resp_buf_type, flags, resp_iov); + rc = cifs_send_recv(xid, ses, ses->server, + &rqst, resp_buf_type, flags, resp_iov); if (n_vec + 1 > CIFS_MAX_IOV_SIZE) kfree(new_iov); return rc; @@ -1296,8 +1311,8 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, use ses->maxReq */ if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) { - cifs_server_dbg(VFS, "Illegal length, greater than maximum frame, %d\n", - len); + cifs_server_dbg(VFS, "Invalid length, greater than maximum frame, %d\n", + len); return -EIO; } @@ -1437,8 +1452,8 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, use ses->maxReq */ if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) { - cifs_tcon_dbg(VFS, "Illegal length, greater than maximum frame, %d\n", - len); + cifs_tcon_dbg(VFS, "Invalid length, greater than maximum frame, %d\n", + len); return -EIO; } diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index e61f3fe8e32a..2d24c765cbd7 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -117,6 +117,11 @@ #define arch_setup_additional_pages compat_arch_setup_additional_pages #endif +#ifdef compat_elf_read_implies_exec +#undef elf_read_implies_exec +#define elf_read_implies_exec compat_elf_read_implies_exec +#endif + /* * Rename a few of the symbols that binfmt_elf.c will define. * These are all local so the names don't really matter, but it diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index f0d73d86cc1a..034e6973cead 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * internal.h - declarations internal to debugfs * diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 416d9de35679..04fe9f525ac7 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -97,7 +97,6 @@ do { \ __LINE__, __FILE__, #x, jiffies); \ {do} \ printk("\n"); \ - BUG(); \ panic("DLM: Record message above and reboot.\n"); \ } \ } @@ -421,7 +420,7 @@ struct dlm_message { int m_bastmode; int m_asts; int m_result; /* 0 or -EXXX */ - char m_extra[0]; /* name or lvb */ + char m_extra[]; /* name or lvb */ }; @@ -450,7 +449,7 @@ struct dlm_rcom { uint64_t rc_id; /* match reply with request */ uint64_t rc_seq; /* sender's ls_recover_seq */ uint64_t rc_seq_reply; /* remote ls_recover_seq */ - char rc_buf[0]; + char rc_buf[]; }; union dlm_packet { @@ -506,7 +505,7 @@ struct rcom_lock { __le16 rl_wait_type; __le16 rl_namelen; char rl_name[DLM_RESNAME_MAXLEN]; - char rl_lvb[0]; + char rl_lvb[]; }; /* diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index afb8340918b8..e93670ecfae5 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -197,8 +197,6 @@ static struct kset *dlm_kset; static int do_uevent(struct dlm_ls *ls, int in) { - int error; - if (in) kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE); else @@ -209,20 +207,12 @@ static int do_uevent(struct dlm_ls *ls, int in) /* dlm_controld will see the uevent, do the necessary group management and then write to sysfs to wake us */ - error = wait_event_interruptible(ls->ls_uevent_wait, - test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags)); + wait_event(ls->ls_uevent_wait, + test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags)); - log_rinfo(ls, "group event done %d %d", error, ls->ls_uevent_result); - - if (error) - goto out; + log_rinfo(ls, "group event done %d", ls->ls_uevent_result); - error = ls->ls_uevent_result; - out: - if (error) - log_error(ls, "group %s failed %d %d", in ? "join" : "leave", - error, ls->ls_uevent_result); - return error; + return ls->ls_uevent_result; } static int dlm_uevent(struct kset *kset, struct kobject *kobj, diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index e3d9f72c640d..4daf5dc2b51c 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -563,7 +563,7 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) lock = 1; reply = 1; break; - }; + } spin_lock(&ls->ls_recover_lock); status = ls->ls_recover_status; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 5264bac75115..e5cefa90b1ce 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -46,7 +46,7 @@ struct dlm_lock_params32 { __u32 bastaddr; __u32 lksb; char lvb[DLM_USER_LVB_LEN]; - char name[0]; + char name[]; }; struct dlm_write_request32 { diff --git a/fs/exec.c b/fs/exec.c index 2c465119affc..93ff1c4c7ebb 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -72,6 +72,8 @@ #include <trace/events/sched.h> +static int bprm_creds_from_file(struct linux_binprm *bprm); + int suid_dumpable = 0; static LIST_HEAD(formats); @@ -588,24 +590,48 @@ out: } /* - * Like copy_strings, but get argv and its values from kernel memory. + * Copy and argument/environment string from the kernel to the processes stack. */ -int copy_strings_kernel(int argc, const char *const *__argv, - struct linux_binprm *bprm) +int copy_string_kernel(const char *arg, struct linux_binprm *bprm) { - int r; - mm_segment_t oldfs = get_fs(); - struct user_arg_ptr argv = { - .ptr.native = (const char __user *const __user *)__argv, - }; + int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */; + unsigned long pos = bprm->p; + + if (len == 0) + return -EFAULT; + if (!valid_arg_len(bprm, len)) + return -E2BIG; + + /* We're going to work our way backwards. */ + arg += len; + bprm->p -= len; + if (IS_ENABLED(CONFIG_MMU) && bprm->p < bprm->argmin) + return -E2BIG; - set_fs(KERNEL_DS); - r = copy_strings(argc, argv, bprm); - set_fs(oldfs); + while (len > 0) { + unsigned int bytes_to_copy = min_t(unsigned int, len, + min_not_zero(offset_in_page(pos), PAGE_SIZE)); + struct page *page; + char *kaddr; + + pos -= bytes_to_copy; + arg -= bytes_to_copy; + len -= bytes_to_copy; + + page = get_arg_page(bprm, pos, 1); + if (!page) + return -E2BIG; + kaddr = kmap_atomic(page); + flush_arg_page(bprm, pos & PAGE_MASK, page); + memcpy(kaddr + offset_in_page(pos), arg, bytes_to_copy); + flush_kernel_dcache_page(page); + kunmap_atomic(kaddr); + put_arg_page(page); + } - return r; + return 0; } -EXPORT_SYMBOL(copy_strings_kernel); +EXPORT_SYMBOL(copy_string_kernel); #ifdef CONFIG_MMU @@ -1051,13 +1077,14 @@ static int exec_mmap(struct mm_struct *mm) tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); + if (old_mm) + sync_mm_rss(old_mm); ret = mutex_lock_killable(&tsk->signal->exec_update_mutex); if (ret) return ret; if (old_mm) { - sync_mm_rss(old_mm); /* * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going @@ -1093,12 +1120,6 @@ static int exec_mmap(struct mm_struct *mm) return 0; } -/* - * This function makes sure the current process has its own signal table, - * so that flush_signal_handlers can later reset the handlers without - * disturbing other processes. (Other processes might share the signal - * table via the CLONE_SIGHAND option to clone().) - */ static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; @@ -1176,7 +1197,6 @@ static int de_thread(struct task_struct *tsk) tsk->start_boottime = leader->start_boottime; BUG_ON(!same_thread_group(leader, tsk)); - BUG_ON(has_group_leader_pid(tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the @@ -1186,11 +1206,8 @@ static int de_thread(struct task_struct *tsk) /* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. - * Note: The old leader also uses this pid until release_task - * is called. Odd but simple and correct. */ - tsk->pid = leader->pid; - change_pid(tsk, PIDTYPE_PID, task_pid(leader)); + exchange_tids(tsk, leader); transfer_pid(leader, tsk, PIDTYPE_TGID); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); @@ -1240,6 +1257,12 @@ killed: } +/* + * This function makes sure the current process has its own signal table, + * so that flush_signal_handlers can later reset the handlers without + * disturbing other processes. (Other processes might share the signal + * table via the CLONE_SIGHAND option to clone().) + */ static int unshare_sighand(struct task_struct *me) { struct sighand_struct *oldsighand = me->sighand; @@ -1296,13 +1319,23 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal * signal (via de_thread() or coredump), or will have SEGV raised - * (after exec_mmap()) by search_binary_handlers (see below). + * (after exec_mmap()) by search_binary_handler (see below). */ -int flush_old_exec(struct linux_binprm * bprm) +int begin_new_exec(struct linux_binprm * bprm) { struct task_struct *me = current; int retval; + /* Once we are committed compute the creds */ + retval = bprm_creds_from_file(bprm); + if (retval) + return retval; + + /* + * Ensure all future errors are fatal. + */ + bprm->point_of_no_return = true; + /* * Make this the only thread in the thread group. */ @@ -1317,7 +1350,10 @@ int flush_old_exec(struct linux_binprm * bprm) */ set_mm_exe_file(bprm->mm, bprm->file); + /* If the binary is not readable then enforce mm->dumpable=0 */ would_dump(bprm, bprm->file); + if (bprm->have_execfd) + would_dump(bprm, bprm->executable); /* * Release all of the old mmap stuff @@ -1327,13 +1363,6 @@ int flush_old_exec(struct linux_binprm * bprm) if (retval) goto out; - /* - * After setting bprm->called_exec_mmap (to mark that current is - * using the prepared mm now), we have nothing left of the original - * process. If anything from here on returns an error, the check - * in search_binary_handler() will SEGV current. - */ - bprm->called_exec_mmap = 1; bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS @@ -1346,7 +1375,7 @@ int flush_old_exec(struct linux_binprm * bprm) */ retval = unshare_sighand(me); if (retval) - goto out; + goto out_unlock; set_fs(USER_DS); me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | @@ -1361,12 +1390,84 @@ int flush_old_exec(struct linux_binprm * bprm) * undergoing exec(2). */ do_close_on_exec(me->files); + + if (bprm->secureexec) { + /* Make sure parent cannot signal privileged process. */ + me->pdeath_signal = 0; + + /* + * For secureexec, reset the stack limit to sane default to + * avoid bad behavior from the prior rlimits. This has to + * happen before arch_pick_mmap_layout(), which examines + * RLIMIT_STACK, but after the point of no return to avoid + * needing to clean up the change on failure. + */ + if (bprm->rlim_stack.rlim_cur > _STK_LIM) + bprm->rlim_stack.rlim_cur = _STK_LIM; + } + + me->sas_ss_sp = me->sas_ss_size = 0; + + /* + * Figure out dumpability. Note that this checking only of current + * is wrong, but userspace depends on it. This should be testing + * bprm->secureexec instead. + */ + if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || + !(uid_eq(current_euid(), current_uid()) && + gid_eq(current_egid(), current_gid()))) + set_dumpable(current->mm, suid_dumpable); + else + set_dumpable(current->mm, SUID_DUMP_USER); + + perf_event_exec(); + __set_task_comm(me, kbasename(bprm->filename), true); + + /* An exec changes our domain. We are no longer part of the thread + group */ + WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); + flush_signal_handlers(me, 0); + + /* + * install the new credentials for this executable + */ + security_bprm_committing_creds(bprm); + + commit_creds(bprm->cred); + bprm->cred = NULL; + + /* + * Disable monitoring for regular users + * when executing setuid binaries. Must + * wait until new credentials are committed + * by commit_creds() above + */ + if (get_dumpable(me->mm) != SUID_DUMP_USER) + perf_event_exit_task(me); + /* + * cred_guard_mutex must be held at least to this point to prevent + * ptrace_attach() from altering our determination of the task's + * credentials; any time after this it may be unlocked. + */ + security_bprm_committed_creds(bprm); + + /* Pass the opened binary to the interpreter. */ + if (bprm->have_execfd) { + retval = get_unused_fd_flags(0); + if (retval < 0) + goto out_unlock; + fd_install(retval, bprm->executable); + bprm->executable = NULL; + bprm->execfd = retval; + } return 0; +out_unlock: + mutex_unlock(&me->signal->exec_update_mutex); out: return retval; } -EXPORT_SYMBOL(flush_old_exec); +EXPORT_SYMBOL(begin_new_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { @@ -1391,58 +1492,20 @@ EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { - /* - * Once here, prepare_binrpm() will not be called any more, so - * the final state of setuid/setgid/fscaps can be merged into the - * secureexec flag. - */ - bprm->secureexec |= bprm->cap_elevated; - - if (bprm->secureexec) { - /* Make sure parent cannot signal privileged process. */ - current->pdeath_signal = 0; - - /* - * For secureexec, reset the stack limit to sane default to - * avoid bad behavior from the prior rlimits. This has to - * happen before arch_pick_mmap_layout(), which examines - * RLIMIT_STACK, but after the point of no return to avoid - * needing to clean up the change on failure. - */ - if (bprm->rlim_stack.rlim_cur > _STK_LIM) - bprm->rlim_stack.rlim_cur = _STK_LIM; - } - - arch_pick_mmap_layout(current->mm, &bprm->rlim_stack); - - current->sas_ss_sp = current->sas_ss_size = 0; + /* Setup things that can depend upon the personality */ + struct task_struct *me = current; - /* - * Figure out dumpability. Note that this checking only of current - * is wrong, but userspace depends on it. This should be testing - * bprm->secureexec instead. - */ - if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || - !(uid_eq(current_euid(), current_uid()) && - gid_eq(current_egid(), current_gid()))) - set_dumpable(current->mm, suid_dumpable); - else - set_dumpable(current->mm, SUID_DUMP_USER); + arch_pick_mmap_layout(me->mm, &bprm->rlim_stack); arch_setup_new_exec(); - perf_event_exec(); - __set_task_comm(current, kbasename(bprm->filename), true); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on * some architectures like powerpc */ - current->mm->task_size = TASK_SIZE; - - /* An exec changes our domain. We are no longer part of the thread - group */ - WRITE_ONCE(current->self_exec_id, current->self_exec_id + 1); - flush_signal_handlers(current, 0); + me->mm->task_size = TASK_SIZE; + mutex_unlock(&me->signal->exec_update_mutex); + mutex_unlock(&me->signal->cred_guard_mutex); } EXPORT_SYMBOL(setup_new_exec); @@ -1458,7 +1521,7 @@ EXPORT_SYMBOL(finalize_exec); /* * Prepare credentials and lock ->cred_guard_mutex. - * install_exec_creds() commits the new creds and drops the lock. + * setup_new_exec() commits the new creds and drops the lock. * Or, if exec fails before, free_bprm() should release ->cred and * and unlock. */ @@ -1479,8 +1542,6 @@ static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { - if (bprm->called_exec_mmap) - mutex_unlock(¤t->signal->exec_update_mutex); mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } @@ -1488,6 +1549,8 @@ static void free_bprm(struct linux_binprm *bprm) allow_write_access(bprm->file); fput(bprm->file); } + if (bprm->executable) + fput(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); @@ -1507,35 +1570,6 @@ int bprm_change_interp(const char *interp, struct linux_binprm *bprm) EXPORT_SYMBOL(bprm_change_interp); /* - * install the new credentials for this executable - */ -void install_exec_creds(struct linux_binprm *bprm) -{ - security_bprm_committing_creds(bprm); - - commit_creds(bprm->cred); - bprm->cred = NULL; - - /* - * Disable monitoring for regular users - * when executing setuid binaries. Must - * wait until new credentials are committed - * by commit_creds() above - */ - if (get_dumpable(current->mm) != SUID_DUMP_USER) - perf_event_exit_task(current); - /* - * cred_guard_mutex must be held at least to this point to prevent - * ptrace_attach() from altering our determination of the task's - * credentials; any time after this it may be unlocked. - */ - security_bprm_committed_creds(bprm); - mutex_unlock(¤t->signal->exec_update_mutex); - mutex_unlock(¤t->signal->cred_guard_mutex); -} -EXPORT_SYMBOL(install_exec_creds); - -/* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH or seccomp thread-sync @@ -1572,29 +1606,21 @@ static void check_unsafe_exec(struct linux_binprm *bprm) spin_unlock(&p->fs->lock); } -static void bprm_fill_uid(struct linux_binprm *bprm) +static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) { + /* Handle suid and sgid on files */ struct inode *inode; unsigned int mode; kuid_t uid; kgid_t gid; - /* - * Since this can be called multiple times (via prepare_binprm), - * we must clear any previous work done when setting set[ug]id - * bits from any earlier bprm->file uses (for example when run - * first for a setuid script then again for its interpreter). - */ - bprm->cred->euid = current_euid(); - bprm->cred->egid = current_egid(); - - if (!mnt_may_suid(bprm->file->f_path.mnt)) + if (!mnt_may_suid(file->f_path.mnt)) return; if (task_no_new_privs(current)) return; - inode = bprm->file->f_path.dentry->d_inode; + inode = file->f_path.dentry->d_inode; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; @@ -1625,30 +1651,31 @@ static void bprm_fill_uid(struct linux_binprm *bprm) } /* + * Compute brpm->cred based upon the final binary. + */ +static int bprm_creds_from_file(struct linux_binprm *bprm) +{ + /* Compute creds based on which file? */ + struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file; + + bprm_fill_uid(bprm, file); + return security_bprm_creds_from_file(bprm, file); +} + +/* * Fill the binprm structure from the inode. - * Check permissions, then read the first BINPRM_BUF_SIZE bytes + * Read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */ -int prepare_binprm(struct linux_binprm *bprm) +static int prepare_binprm(struct linux_binprm *bprm) { - int retval; loff_t pos = 0; - bprm_fill_uid(bprm); - - /* fill in binprm security blob */ - retval = security_bprm_set_creds(bprm); - if (retval) - return retval; - bprm->called_set_creds = 1; - memset(bprm->buf, 0, BINPRM_BUF_SIZE); return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos); } -EXPORT_SYMBOL(prepare_binprm); - /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after @@ -1694,15 +1721,15 @@ EXPORT_SYMBOL(remove_arg_zero); /* * cycle the list of binary formats handler, until one recognizes the image */ -int search_binary_handler(struct linux_binprm *bprm) +static int search_binary_handler(struct linux_binprm *bprm) { bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; - /* This allows 4 levels of binfmt rewrites before failing hard. */ - if (bprm->recursion_depth > 5) - return -ELOOP; + retval = prepare_binprm(bprm); + if (retval < 0) + return retval; retval = security_bprm_check(bprm); if (retval) @@ -1716,19 +1743,11 @@ int search_binary_handler(struct linux_binprm *bprm) continue; read_unlock(&binfmt_lock); - bprm->recursion_depth++; retval = fmt->load_binary(bprm); - bprm->recursion_depth--; read_lock(&binfmt_lock); put_binfmt(fmt); - if (retval < 0 && bprm->called_exec_mmap) { - /* we got to flush_old_exec() and failed after it */ - read_unlock(&binfmt_lock); - force_sigsegv(SIGSEGV); - return retval; - } - if (retval != -ENOEXEC || !bprm->file) { + if (bprm->point_of_no_return || (retval != -ENOEXEC)) { read_unlock(&binfmt_lock); return retval; } @@ -1747,12 +1766,11 @@ int search_binary_handler(struct linux_binprm *bprm) return retval; } -EXPORT_SYMBOL(search_binary_handler); static int exec_binprm(struct linux_binprm *bprm) { pid_t old_pid, old_vpid; - int ret; + int ret, depth; /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; @@ -1760,15 +1778,38 @@ static int exec_binprm(struct linux_binprm *bprm) old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); - ret = search_binary_handler(bprm); - if (ret >= 0) { - audit_bprm(bprm); - trace_sched_process_exec(current, old_pid, bprm); - ptrace_event(PTRACE_EVENT_EXEC, old_vpid); - proc_exec_connector(current); + /* This allows 4 levels of binfmt rewrites before failing hard. */ + for (depth = 0;; depth++) { + struct file *exec; + if (depth > 5) + return -ELOOP; + + ret = search_binary_handler(bprm); + if (ret < 0) + return ret; + if (!bprm->interpreter) + break; + + exec = bprm->file; + bprm->file = bprm->interpreter; + bprm->interpreter = NULL; + + allow_write_access(exec); + if (unlikely(bprm->have_execfd)) { + if (bprm->executable) { + fput(exec); + return -ENOEXEC; + } + bprm->executable = exec; + } else + fput(exec); } - return ret; + audit_bprm(bprm); + trace_sched_process_exec(current, old_pid, bprm); + ptrace_event(PTRACE_EVENT_EXEC, old_vpid); + proc_exec_connector(current); + return 0; } /* @@ -1861,11 +1902,12 @@ static int __do_execve_file(int fd, struct filename *filename, if (retval < 0) goto out; - retval = prepare_binprm(bprm); - if (retval < 0) + /* Set the unchanging part of bprm->cred */ + retval = security_bprm_creds_for_exec(bprm); + if (retval) goto out; - retval = copy_strings_kernel(1, &bprm->filename, bprm); + retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out; @@ -1897,6 +1939,14 @@ static int __do_execve_file(int fd, struct filename *filename, return retval; out: + /* + * If past the point of no return ensure the the code never + * returns to the userspace process. Use an existing fatal + * signal if present otherwise terminate the process with + * SIGSEGV. + */ + if (bprm->point_of_no_return && !fatal_signal_pending(current)) + force_sigsegv(SIGSEGV); if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 39c4772e96c9..b4de9a0f170d 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -196,9 +196,7 @@ const struct file_operations ext2_file_operations = { }; const struct inode_operations ext2_file_inode_operations = { -#ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, -#endif .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 2875c0a705b5..c8b371c82b4f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -36,6 +36,7 @@ #include <linux/iomap.h> #include <linux/namei.h> #include <linux/uio.h> +#include <linux/fiemap.h> #include "ext2.h" #include "acl.h" #include "xattr.h" diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index ccfbbf59e2fc..ba3e3e075891 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -136,9 +136,7 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); -#ifdef CONFIG_EXT2_FS_XATTR inode->i_op = &ext2_special_inode_operations; -#endif mark_inode_dirty(inode); err = ext2_add_nondir(dentry, inode); } @@ -413,9 +411,7 @@ const struct inode_operations ext2_dir_inode_operations = { .rmdir = ext2_rmdir, .mknod = ext2_mknod, .rename = ext2_rename, -#ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, -#endif .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, @@ -424,9 +420,7 @@ const struct inode_operations ext2_dir_inode_operations = { }; const struct inode_operations ext2_special_inode_operations = { -#ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, -#endif .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c index 00cdb8679486..948d3a441403 100644 --- a/fs/ext2/symlink.c +++ b/fs/ext2/symlink.c @@ -25,16 +25,12 @@ const struct inode_operations ext2_symlink_inode_operations = { .get_link = page_get_link, .getattr = ext2_getattr, .setattr = ext2_setattr, -#ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, -#endif }; const struct inode_operations ext2_fast_symlink_inode_operations = { .get_link = simple_get_link, .getattr = ext2_getattr, .setattr = ext2_setattr, -#ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, -#endif }; diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h index 16272e6ddcf4..7925f596e8e2 100644 --- a/fs/ext2/xattr.h +++ b/fs/ext2/xattr.h @@ -100,6 +100,7 @@ static inline void ext2_xattr_destroy_cache(struct mb_cache *cache) } #define ext2_xattr_handlers NULL +#define ext2_listxattr NULL # endif /* CONFIG_EXT2_FS_XATTR */ diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 2a592e38cdfe..cf9e430514c4 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -99,8 +99,7 @@ config EXT4_DEBUG Enables run-time debugging support for the ext4 filesystem. If you select Y here, then you will be able to turn on debugging - with a command such as: - echo 1 > /sys/module/ext4/parameters/mballoc_debug + using dynamic debug control for mb_debug() / ext_debug() msgs. config EXT4_KUNIT_TESTS tristate "KUnit tests for ext4" diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 8c7bbf3e566d..76f634d185f1 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -215,9 +215,8 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, value, size, xattr_flags); kfree(value); - if (!error) { + if (!error) set_cached_acl(inode, type, acl); - } return error; } @@ -256,7 +255,7 @@ retry: if (!error && update_mode) { inode->i_mode = mode; inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + error = ext4_mark_inode_dirty(handle, inode); } out_stop: ext4_journal_stop(handle); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index a32e5f7b5385..1ba46d87cdf1 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -903,10 +903,11 @@ ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode) return bg_start; if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) - colour = (current->pid % 16) * + colour = (task_pid_nr(current) % 16) * (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); else - colour = (current->pid % 16) * ((last_block - bg_start) / 16); + colour = (task_pid_nr(current) % 16) * + ((last_block - bg_start) / 16); return bg_start + colour; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 15b062efcff1..b08841f70b69 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -36,6 +36,7 @@ #include <crypto/hash.h> #include <linux/falloc.h> #include <linux/percpu-rwsem.h> +#include <linux/fiemap.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -80,14 +81,22 @@ #define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif + /* + * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c + */ +#define EXT_DEBUG__ + /* - * Turn on EXT_DEBUG to get lots of info about extents operations. + * Dynamic printk for controlled extents debugging. */ -#define EXT_DEBUG__ -#ifdef EXT_DEBUG -#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) +#ifdef CONFIG_EXT4_DEBUG +#define ext_debug(ino, fmt, ...) \ + pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt, \ + current->comm, task_pid_nr(current), \ + ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__, \ + __func__, ##__VA_ARGS__) #else -#define ext_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif /* data type for block offset of block group */ @@ -142,6 +151,8 @@ enum SHIFT_DIRECTION { #define EXT4_MB_USE_ROOT_BLOCKS 0x1000 /* Use blocks from reserved pool */ #define EXT4_MB_USE_RESERVED 0x2000 +/* Do strict check for free blocks while retrying block allocation */ +#define EXT4_MB_STRICT_CHECK 0x4000 struct ext4_allocation_request { /* target inode for block we're allocating */ @@ -171,10 +182,10 @@ struct ext4_allocation_request { * well as to store the information returned by ext4_map_blocks(). It * takes less room on the stack than a struct buffer_head. */ -#define EXT4_MAP_NEW (1 << BH_New) -#define EXT4_MAP_MAPPED (1 << BH_Mapped) -#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten) -#define EXT4_MAP_BOUNDARY (1 << BH_Boundary) +#define EXT4_MAP_NEW BIT(BH_New) +#define EXT4_MAP_MAPPED BIT(BH_Mapped) +#define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten) +#define EXT4_MAP_BOUNDARY BIT(BH_Boundary) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY) @@ -417,7 +428,7 @@ struct flex_groups { /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ -#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded file */ +#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x705BDFFF /* User visible flags */ @@ -490,6 +501,7 @@ enum { /* 22 was formerly EXT4_INODE_EOFBLOCKS */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ + EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ }; @@ -535,6 +547,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(INLINE_DATA); CHECK_FLAG_VALUE(PROJINHERIT); + CHECK_FLAG_VALUE(CASEFOLD); CHECK_FLAG_VALUE(RESERVED); } @@ -609,8 +622,6 @@ enum { #define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 - /* Request will not result in inode size update (user for fallocate) */ -#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 /* Convert written extents to unwritten */ #define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100 /* Write zeros to newly created written extents */ @@ -632,6 +643,7 @@ enum { */ #define EXT4_EX_NOCACHE 0x40000000 #define EXT4_EX_FORCE_CACHE 0x20000000 +#define EXT4_EX_NOFAIL 0x10000000 /* * Flags used by ext4_free_blocks @@ -2051,7 +2063,7 @@ struct ext4_dir_entry_2 { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __u8 name_len; /* Name length */ - __u8 file_type; + __u8 file_type; /* See file type macros EXT4_FT_* below */ char name[EXT4_NAME_LEN]; /* File name */ }; @@ -3354,7 +3366,7 @@ struct ext4_extent; */ #define EXT_MAX_BLOCKS 0xffffffff -extern int ext4_ext_tree_init(handle_t *handle, struct inode *); +extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode); extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents); extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 1c216fcc202a..44e59881a1f0 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -170,10 +170,13 @@ struct partial_cluster { (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) #define EXT_LAST_INDEX(__hdr__) \ (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) -#define EXT_MAX_EXTENT(__hdr__) \ - (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) +#define EXT_MAX_EXTENT(__hdr__) \ + ((le16_to_cpu((__hdr__)->eh_max)) ? \ + ((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \ + : 0) #define EXT_MAX_INDEX(__hdr__) \ - (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) + ((le16_to_cpu((__hdr__)->eh_max)) ? \ + ((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0) static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 4b9002f0e84c..00dc668e052b 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -222,7 +222,10 @@ ext4_mark_iloc_dirty(handle_t *handle, int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); -int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); +#define ext4_mark_inode_dirty(__h, __i) \ + __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) +int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, + const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, @@ -335,12 +338,6 @@ static inline handle_t *__ext4_journal_start(struct inode *inode, handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); -static inline void ext4_journal_free_reserved(handle_t *handle) -{ - if (ext4_handle_valid(handle)) - jbd2_journal_free_reserved(handle); -} - static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2b4b94542e34..7d088ff1e902 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -297,11 +297,14 @@ ext4_force_split_extent_at(handle_t *handle, struct inode *inode, { struct ext4_ext_path *path = *ppath; int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext); + int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO; + + if (nofail) + flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL; return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ? EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0, - EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO | - (nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0)); + flags); } static int @@ -487,8 +490,12 @@ __read_extent_tree_block(const char *function, unsigned int line, { struct buffer_head *bh; int err; + gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; + + if (flags & EXT4_EX_NOFAIL) + gfp_flags |= __GFP_NOFAIL; - bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS); + bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); @@ -600,22 +607,22 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { int k, l = path->p_depth; - ext_debug("path:"); + ext_debug(inode, "path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { - ext_debug(" %d->%llu", + ext_debug(inode, " %d->%llu", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { - ext_debug(" %d:[%d]%d:%llu ", + ext_debug(inode, " %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext4_ext_pblock(path->p_ext)); } else - ext_debug(" []"); + ext_debug(inode, " []"); } - ext_debug("\n"); + ext_debug(inode, "\n"); } static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) @@ -631,14 +638,14 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); - ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino); + ext_debug(inode, "Displaying leaf extents\n"); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { - ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), + ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } - ext_debug("\n"); + ext_debug(inode, "\n"); } static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, @@ -651,10 +658,9 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent_idx *idx; idx = path[level].p_idx; while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) { - ext_debug("%d: move %d:%llu in new index %llu\n", level, - le32_to_cpu(idx->ei_block), - ext4_idx_pblock(idx), - newblock); + ext_debug(inode, "%d: move %d:%llu in new index %llu\n", + level, le32_to_cpu(idx->ei_block), + ext4_idx_pblock(idx), newblock); idx++; } @@ -663,7 +669,7 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, ex = path[depth].p_ext; while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) { - ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n", + ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex), @@ -707,7 +713,7 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_extent_idx *r, *l, *m; - ext_debug("binsearch for %u(idx): ", block); + ext_debug(inode, "binsearch for %u(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; r = EXT_LAST_INDEX(eh); @@ -717,13 +723,13 @@ ext4_ext_binsearch_idx(struct inode *inode, r = m - 1; else l = m + 1; - ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), - m, le32_to_cpu(m->ei_block), - r, le32_to_cpu(r->ei_block)); + ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, + le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), + r, le32_to_cpu(r->ei_block)); } path->p_idx = l - 1; - ext_debug(" -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), + ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH @@ -774,7 +780,7 @@ ext4_ext_binsearch(struct inode *inode, return; } - ext_debug("binsearch for %u: ", block); + ext_debug(inode, "binsearch for %u: ", block); l = EXT_FIRST_EXTENT(eh) + 1; r = EXT_LAST_EXTENT(eh); @@ -785,13 +791,13 @@ ext4_ext_binsearch(struct inode *inode, r = m - 1; else l = m + 1; - ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), - m, le32_to_cpu(m->ee_block), - r, le32_to_cpu(r->ee_block)); + ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, + le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), + r, le32_to_cpu(r->ee_block)); } path->p_ext = l - 1; - ext_debug(" -> %d:%llu:[%d]%d ", + ext_debug(inode, " -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_pblock(path->p_ext), ext4_ext_is_unwritten(path->p_ext), @@ -816,7 +822,7 @@ ext4_ext_binsearch(struct inode *inode, } -int ext4_ext_tree_init(handle_t *handle, struct inode *inode) +void ext4_ext_tree_init(handle_t *handle, struct inode *inode) { struct ext4_extent_header *eh; @@ -826,7 +832,6 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode) eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); ext4_mark_inode_dirty(handle, inode); - return 0; } struct ext4_ext_path * @@ -838,6 +843,10 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, struct ext4_ext_path *path = orig_path ? *orig_path : NULL; short int depth, i, ppos = 0; int ret; + gfp_t gfp_flags = GFP_NOFS; + + if (flags & EXT4_EX_NOFAIL) + gfp_flags |= __GFP_NOFAIL; eh = ext_inode_hdr(inode); depth = ext_depth(inode); @@ -858,7 +867,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, if (!path) { /* account possible depth increase */ path = kcalloc(depth + 2, sizeof(struct ext4_ext_path), - GFP_NOFS); + gfp_flags); if (unlikely(!path)) return ERR_PTR(-ENOMEM); path[0].p_maxdepth = depth + 1; @@ -871,7 +880,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { - ext_debug("depth %d: num %d, max %d\n", + ext_debug(inode, "depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); @@ -948,18 +957,20 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ - ext_debug("insert new index %d after: %llu\n", logical, ptr); + ext_debug(inode, "insert new index %d after: %llu\n", + logical, ptr); ix = curp->p_idx + 1; } else { /* insert before */ - ext_debug("insert new index %d before: %llu\n", logical, ptr); + ext_debug(inode, "insert new index %d before: %llu\n", + logical, ptr); ix = curp->p_idx; } len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { - ext_debug("insert new index %d: " + ext_debug(inode, "insert new index %d: " "move %d indices from 0x%p to 0x%p\n", logical, len, ix, ix + 1); memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); @@ -1008,9 +1019,13 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock, oldblock; __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ + gfp_t gfp_flags = GFP_NOFS; int err = 0; size_t ext_size = 0; + if (flags & EXT4_EX_NOFAIL) + gfp_flags |= __GFP_NOFAIL; + /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ @@ -1022,12 +1037,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; - ext_debug("leaf will be split." + ext_debug(inode, "leaf will be split." " next leaf starts at %d\n", le32_to_cpu(border)); } else { border = newext->ee_block; - ext_debug("leaf will be added." + ext_debug(inode, "leaf will be added." " next leaf starts at %d\n", le32_to_cpu(border)); } @@ -1044,12 +1059,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, * We need this to handle errors and free blocks * upon them. */ - ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), GFP_NOFS); + ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags); if (!ablocks) return -ENOMEM; /* allocate all needed blocks */ - ext_debug("allocate %d blocks for indexes/leaf\n", depth - at); + ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at); for (a = 0; a < depth - at; a++) { newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err, flags); @@ -1135,7 +1150,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, goto cleanup; } if (k) - ext_debug("create %d intermediate indices\n", k); + ext_debug(inode, "create %d intermediate indices\n", k); /* insert new index into current index block */ /* current depth stored in i var */ i = depth - 1; @@ -1162,7 +1177,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); - ext_debug("int.index at %d (block %llu): %u -> %llu\n", + ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n", i, newblock, le32_to_cpu(border), oldblock); /* move remainder of path[i] to the new index block */ @@ -1176,7 +1191,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, } /* start copy indexes */ m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++; - ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx, + ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx, EXT_MAX_INDEX(path[i].p_hdr)); ext4_ext_show_move(inode, path, newblock, i); if (m) { @@ -1313,13 +1328,13 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, EXT_FIRST_INDEX(neh)->ei_block = EXT_FIRST_EXTENT(neh)->ee_block; } - ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n", + ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); le16_add_cpu(&neh->eh_depth, 1); - ext4_mark_inode_dirty(handle, inode); + err = ext4_mark_inode_dirty(handle, inode); out: brelse(bh); @@ -1955,7 +1970,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, /* Try to append newex to the ex */ if (ext4_can_extents_be_merged(inode, ex, newext)) { - ext_debug("append [%d]%d block to %u:[%d]%d" + ext_debug(inode, "append [%d]%d block to %u:[%d]%d" "(from %llu)\n", ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), @@ -1980,7 +1995,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, prepend: /* Try to prepend newex to the ex */ if (ext4_can_extents_be_merged(inode, newext, ex)) { - ext_debug("prepend %u[%d]%d block to %u:[%d]%d" + ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d" "(from %llu)\n", le32_to_cpu(newext->ee_block), ext4_ext_is_unwritten(newext), @@ -2018,20 +2033,20 @@ prepend: if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) next = ext4_ext_next_leaf_block(path); if (next != EXT_MAX_BLOCKS) { - ext_debug("next leaf block - %u\n", next); + ext_debug(inode, "next leaf block - %u\n", next); BUG_ON(npath != NULL); - npath = ext4_find_extent(inode, next, NULL, 0); + npath = ext4_find_extent(inode, next, NULL, gb_flags); if (IS_ERR(npath)) return PTR_ERR(npath); BUG_ON(npath->p_depth != path->p_depth); eh = npath[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { - ext_debug("next leaf isn't full(%d)\n", + ext_debug(inode, "next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); path = npath; goto has_space; } - ext_debug("next leaf has no free space(%d,%d)\n", + ext_debug(inode, "next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); } @@ -2057,7 +2072,7 @@ has_space: if (!nearex) { /* there is no extent in this leaf, create first one */ - ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n", + ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), @@ -2067,7 +2082,7 @@ has_space: if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { /* Insert after */ - ext_debug("insert %u:%llu:[%d]%d before: " + ext_debug(inode, "insert %u:%llu:[%d]%d before: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), @@ -2078,7 +2093,7 @@ has_space: } else { /* Insert before */ BUG_ON(newext->ee_block == nearex->ee_block); - ext_debug("insert %u:%llu:[%d]%d after: " + ext_debug(inode, "insert %u:%llu:[%d]%d after: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), @@ -2088,7 +2103,7 @@ has_space: } len = EXT_LAST_EXTENT(eh) - nearex + 1; if (len > 0) { - ext_debug("insert %u:%llu:[%d]%d: " + ext_debug(inode, "insert %u:%llu:[%d]%d: " "move %d extents from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), @@ -2232,7 +2247,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, return; hole_len = min(es.es_lblk - hole_start, hole_len); } - ext_debug(" -> %u:%u\n", hole_start, hole_len); + ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); ext4_es_insert_extent(inode, hole_start, hole_len, ~0, EXTENT_STATUS_HOLE); } @@ -2269,7 +2284,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, err = ext4_ext_dirty(handle, inode, path); if (err) return err; - ext_debug("index is empty, remove it, free block %llu\n", leaf); + ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf); trace_ext4_ext_rm_idx(inode, leaf); ext4_free_blocks(handle, inode, NULL, leaf, 1, @@ -2548,7 +2563,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ - ext_debug("truncate since %u in leaf to %u\n", start, end); + ext_debug(inode, "truncate since %u in leaf to %u\n", start, end); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; @@ -2574,7 +2589,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, else unwritten = 0; - ext_debug("remove ext %u:[%d]%d\n", ex_ee_block, + ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block, unwritten, ex_ee_len); path[depth].p_ext = ex; @@ -2582,7 +2597,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, b = ex_ee_block+ex_ee_len - 1 < end ? ex_ee_block+ex_ee_len - 1 : end; - ext_debug(" border %u:%u\n", a, b); + ext_debug(inode, " border %u:%u\n", a, b); /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { @@ -2691,7 +2706,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, if (err) goto out; - ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num, + ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num, ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); @@ -2768,7 +2783,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, partial.lblk = 0; partial.state = initial; - ext_debug("truncate since %u to %u\n", start, end); + ext_debug(inode, "truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, @@ -2793,7 +2808,8 @@ again: ext4_fsblk_t pblk; /* find extent for or closest extent to this block */ - path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE); + path = ext4_find_extent(inode, end, NULL, + EXT4_EX_NOCACHE | EXT4_EX_NOFAIL); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); @@ -2879,7 +2895,7 @@ again: le16_to_cpu(path[k].p_hdr->eh_entries)+1; } else { path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), - GFP_NOFS); + GFP_NOFS | __GFP_NOFAIL); if (path == NULL) { ext4_journal_stop(handle); return -ENOMEM; @@ -2909,7 +2925,7 @@ again: /* this is index block */ if (!path[i].p_hdr) { - ext_debug("initialize header\n"); + ext_debug(inode, "initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); } @@ -2917,7 +2933,7 @@ again: /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; - ext_debug("init index ptr: hdr 0x%p, num %d\n", + ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n", path[i].p_hdr, le16_to_cpu(path[i].p_hdr->eh_entries)); } else { @@ -2925,13 +2941,13 @@ again: path[i].p_idx--; } - ext_debug("level %d - index, first 0x%p, cur 0x%p\n", + ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n", i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { struct buffer_head *bh; /* go to the next level */ - ext_debug("move to level %d (block %llu)\n", + ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); bh = read_extent_tree_block(inode, @@ -2967,7 +2983,7 @@ again: brelse(path[i].p_bh); path[i].p_bh = NULL; i--; - ext_debug("return to level %d\n", i); + ext_debug(inode, "return to level %d\n", i); } } @@ -3135,8 +3151,7 @@ static int ext4_split_extent_at(handle_t *handle, BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); - ext_debug("ext4_split_extents_at: inode %lu, logical" - "block %llu\n", inode->i_ino, (unsigned long long)split); + ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); @@ -3244,6 +3259,10 @@ out: fix_extent_len: ex->ee_len = orig_ex.ee_len; + /* + * Ignore ext4_ext_dirty return value since we are already in error path + * and err is a non-zero error code. + */ ext4_ext_dirty(handle, inode, path + path->p_depth); return err; } @@ -3300,7 +3319,7 @@ static int ext4_split_extent(handle_t *handle, * Update path is required because previous ext4_split_extent_at() may * result in split of original leaf or extent zeroout. */ - path = ext4_find_extent(inode, map->m_lblk, ppath, 0); + path = ext4_find_extent(inode, map->m_lblk, ppath, flags); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); @@ -3369,9 +3388,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, int err = 0; int split_flag = EXT4_EXT_DATA_VALID2; - ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" - "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)map->m_lblk, map_len); + ext_debug(inode, "logical block %llu, max_blocks %u\n", + (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) @@ -3503,7 +3521,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, } if (allocated) { /* Mark the block containing both extents as dirty */ - ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + depth); /* Update path to point to the right extent */ path[depth].p_ext = abut_ex; @@ -3623,8 +3641,7 @@ static int ext4_split_convert_extents(handle_t *handle, unsigned int ee_len; int split_flag = 0, depth; - ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n", - __func__, inode->i_ino, + ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map->m_len); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) @@ -3670,8 +3687,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical" - "block %llu, max_blocks %u\n", inode->i_ino, + ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); /* If extent is larger than requested it is a clear sign that we still @@ -3741,8 +3757,7 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - ext_debug("%s: inode %lu, logical" - "block %llu, max_blocks %u\n", __func__, inode->i_ino, + ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); if (ee_block != map->m_lblk || ee_len > map->m_len) { @@ -3794,16 +3809,13 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, int flags, unsigned int allocated, ext4_fsblk_t newblock) { -#ifdef EXT_DEBUG - struct ext4_ext_path *path = *ppath; -#endif + struct ext4_ext_path __maybe_unused *path = *ppath; int ret = 0; int err = 0; - ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical " - "block %llu, max_blocks %u, flags %x, allocated %u\n", - inode->i_ino, (unsigned long long)map->m_lblk, map->m_len, - flags, allocated); + ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n", + (unsigned long long)map->m_lblk, map->m_len, flags, + allocated); ext4_ext_show_leaf(inode, path); /* @@ -3815,39 +3827,38 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, trace_ext4_ext_handle_unwritten_extents(inode, map, flags, allocated, newblock); - /* get_block() before submit the IO, split the extent */ + /* get_block() before submitting IO, split the extent */ if (flags & EXT4_GET_BLOCKS_PRE_IO) { ret = ext4_split_convert_extents(handle, inode, map, ppath, flags | EXT4_GET_BLOCKS_CONVERT); - if (ret <= 0) - goto out; + if (ret < 0) { + err = ret; + goto out2; + } + /* + * shouldn't get a 0 return when splitting an extent unless + * m_len is 0 (bug) or extent has been corrupted + */ + if (unlikely(ret == 0)) { + EXT4_ERROR_INODE(inode, + "unexpected ret == 0, m_len = %u", + map->m_len); + err = -EFSCORRUPTED; + goto out2; + } map->m_flags |= EXT4_MAP_UNWRITTEN; goto out; } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { - if (flags & EXT4_GET_BLOCKS_ZERO) { - if (allocated > map->m_len) - allocated = map->m_len; - err = ext4_issue_zeroout(inode, map->m_lblk, newblock, - allocated); - if (err < 0) - goto out2; - } - ret = ext4_convert_unwritten_extents_endio(handle, inode, map, + err = ext4_convert_unwritten_extents_endio(handle, inode, map, ppath); - if (ret >= 0) - ext4_update_inode_fsync_trans(handle, inode, 1); - else - err = ret; - map->m_flags |= EXT4_MAP_MAPPED; - map->m_pblk = newblock; - if (allocated > map->m_len) - allocated = map->m_len; - map->m_len = allocated; - goto out2; + if (err < 0) + goto out2; + ext4_update_inode_fsync_trans(handle, inode, 1); + goto map_out; } - /* buffered IO case */ + /* buffered IO cases */ /* * repeat fallocate creation request * we already have an unwritten extent @@ -3870,29 +3881,39 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, goto out1; } - /* buffered write, writepage time, convert*/ + /* + * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1. + * For buffered writes, at writepage time, etc. Convert a + * discovered unwritten extent to written. + */ ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags); - if (ret >= 0) - ext4_update_inode_fsync_trans(handle, inode, 1); -out: - if (ret <= 0) { + if (ret < 0) { err = ret; goto out2; - } else - allocated = ret; - map->m_flags |= EXT4_MAP_NEW; - if (allocated > map->m_len) - allocated = map->m_len; - map->m_len = allocated; + } + ext4_update_inode_fsync_trans(handle, inode, 1); + /* + * shouldn't get a 0 return when converting an unwritten extent + * unless m_len is 0 (bug) or extent has been corrupted + */ + if (unlikely(ret == 0)) { + EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u", + map->m_len); + err = -EFSCORRUPTED; + goto out2; + } +out: + allocated = ret; + map->m_flags |= EXT4_MAP_NEW; map_out: map->m_flags |= EXT4_MAP_MAPPED; out1: + map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; - ext4_ext_show_leaf(inode, path); - map->m_pblk = newblock; map->m_len = allocated; + ext4_ext_show_leaf(inode, path); out2: return err ? err : allocated; } @@ -4024,15 +4045,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_ext_path *path = NULL; struct ext4_extent newex, *ex, *ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - ext4_fsblk_t newblock = 0; + ext4_fsblk_t newblock = 0, pblk; int err = 0, depth, ret; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; - ext_debug("blocks %u/%u requested for inode %lu\n", - map->m_lblk, map->m_len, inode->i_ino); + ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len); trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ @@ -4040,7 +4060,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, if (IS_ERR(path)) { err = PTR_ERR(path); path = NULL; - goto out2; + goto out; } depth = ext_depth(inode); @@ -4056,7 +4076,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, (unsigned long) map->m_lblk, depth, path[depth].p_block); err = -EFSCORRUPTED; - goto out2; + goto out; } ex = path[depth].p_ext; @@ -4079,8 +4099,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, newblock = map->m_lblk - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (map->m_lblk - ee_block); - ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk, - ee_block, ee_len, newblock); + ext_debug(inode, "%u fit into %u:%d -> %llu\n", + map->m_lblk, ee_block, ee_len, newblock); /* * If the extent is initialized check whether the @@ -4090,8 +4110,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { err = convert_initialized_extent(handle, inode, map, &path, &allocated); - goto out2; + goto out; } else if (!ext4_ext_is_unwritten(ex)) { + map->m_flags |= EXT4_MAP_MAPPED; + map->m_pblk = newblock; + if (allocated > map->m_len) + allocated = map->m_len; + map->m_len = allocated; + ext4_ext_show_leaf(inode, path); goto out; } @@ -4102,7 +4128,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, err = ret; else allocated = ret; - goto out2; + goto out; } } @@ -4127,7 +4153,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, hole_len); - goto out2; + goto out; } /* @@ -4151,12 +4177,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ar.lleft = map->m_lblk; err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft); if (err) - goto out2; + goto out; ar.lright = map->m_lblk; ex2 = NULL; err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2); if (err) - goto out2; + goto out; /* Check if the extent after searching to the right implies a * cluster we can use. */ @@ -4217,17 +4243,18 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ar.flags |= EXT4_MB_USE_RESERVED; newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) - goto out2; - ext_debug("allocate new block: goal %llu, found %llu/%u\n", - ar.goal, newblock, allocated); + goto out; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; + ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n", + ar.goal, newblock, ar.len, allocated); if (ar.len > allocated) ar.len = allocated; got_allocated_blocks: /* try to insert new extent into found leaf and return */ - ext4_ext_store_pblock(&newex, newblock + offset); + pblk = newblock + offset; + ext4_ext_store_pblock(&newex, pblk); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { @@ -4252,16 +4279,9 @@ got_allocated_blocks: EXT4_C2B(sbi, allocated_clusters), fb_flags); } - goto out2; + goto out; } - /* previous routine could use block we allocated */ - newblock = ext4_ext_pblock(&newex); - allocated = ext4_ext_get_actual_len(&newex); - if (allocated > map->m_len) - allocated = map->m_len; - map->m_flags |= EXT4_MAP_NEW; - /* * Reduce the reserved cluster count to reflect successful deferred * allocation of delayed allocated clusters or direct allocation of @@ -4307,14 +4327,14 @@ got_allocated_blocks: ext4_update_inode_fsync_trans(handle, inode, 1); else ext4_update_inode_fsync_trans(handle, inode, 0); -out: - if (allocated > map->m_len) - allocated = map->m_len; + + map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED); + map->m_pblk = pblk; + map->m_len = ar.len; + allocated = map->m_len; ext4_ext_show_leaf(inode, path); - map->m_flags |= EXT4_MAP_MAPPED; - map->m_pblk = newblock; - map->m_len = allocated; -out2: + +out: ext4_ext_drop_refs(path); kfree(path); @@ -4353,7 +4373,14 @@ retry: } if (err) return err; - return ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); +retry_remove_space: + err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); + if (err == -ENOMEM) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry_remove_space; + } + return err; } static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, @@ -4363,7 +4390,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, struct inode *inode = file_inode(file); handle_t *handle; int ret = 0; - int ret2 = 0; + int ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; @@ -4423,10 +4450,11 @@ retry: if (ext4_update_inode_size(inode, epos) & 0x1) inode->i_mtime = inode->i_ctime; } - ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); - ret2 = ext4_journal_stop(handle); - if (ret2) + ret3 = ext4_journal_stop(handle); + ret2 = ret3 ? ret3 : ret2; + if (unlikely(ret2)) break; } if (ret == -ENOSPC && @@ -4490,7 +4518,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, inode_lock(inode); /* - * Indirect files do not support unwritten extnets + * Indirect files do not support unwritten extents */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; @@ -4507,8 +4535,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, } flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode); @@ -4577,7 +4603,9 @@ static long ext4_zero_range(struct file *file, loff_t offset, inode->i_mtime = inode->i_ctime = current_time(inode); if (new_size) ext4_update_inode_size(inode, new_size); - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret)) + goto out_handle; /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); @@ -4587,6 +4615,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (file->f_flags & O_SYNC) ext4_handle_sync(handle); +out_handle: ext4_journal_stop(handle); out_mutex: inode_unlock(inode); @@ -4647,8 +4676,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; inode_lock(inode); @@ -4700,8 +4727,7 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; - int ret = 0; - int ret2 = 0; + int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; @@ -4734,9 +4760,13 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); - ext4_mark_inode_dirty(handle, inode); - if (credits) - ret2 = ext4_journal_stop(handle); + ret2 = ext4_mark_inode_dirty(handle, inode); + if (credits) { + ret3 = ext4_journal_stop(handle); + if (unlikely(ret3)) + ret2 = ret3; + } + if (ret <= 0 || ret2) break; } @@ -4854,11 +4884,9 @@ static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) return 0; } -static int _ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len, bool from_es_cache) +int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) { - ext4_lblk_t start_blk; - u32 ext4_fiemap_flags = FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR; int error = 0; if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { @@ -4868,12 +4896,6 @@ static int _ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } - if (from_es_cache) - ext4_fiemap_flags &= FIEMAP_FLAG_XATTR; - - if (fiemap_check_flags(fieinfo, ext4_fiemap_flags)) - return -EBADR; - /* * For bitmap files the maximum size limit could be smaller than * s_maxbytes, so check len here manually instead of just relying on the @@ -4885,40 +4907,20 @@ static int _ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; - error = iomap_fiemap(inode, fieinfo, start, len, - &ext4_iomap_xattr_ops); - } else if (!from_es_cache) { - error = iomap_fiemap(inode, fieinfo, start, len, - &ext4_iomap_report_ops); - } else { - ext4_lblk_t len_blks; - __u64 last_blk; - - start_blk = start >> inode->i_sb->s_blocksize_bits; - last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; - if (last_blk >= EXT_MAX_BLOCKS) - last_blk = EXT_MAX_BLOCKS-1; - len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; - - /* - * Walk the extent tree gathering extent information - * and pushing extents back to the user. - */ - error = ext4_fill_es_cache_info(inode, start_blk, len_blks, - fieinfo); + return iomap_fiemap(inode, fieinfo, start, len, + &ext4_iomap_xattr_ops); } - return error; -} -int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len) -{ - return _ext4_fiemap(inode, fieinfo, start, len, false); + return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops); } int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { + ext4_lblk_t start_blk, len_blks; + __u64 last_blk; + int error = 0; + if (ext4_has_inline_data(inode)) { int has_inline; @@ -4929,9 +4931,33 @@ int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, return 0; } - return _ext4_fiemap(inode, fieinfo, start, len, true); -} + if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { + error = ext4_ext_precache(inode); + if (error) + return error; + fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; + } + + error = fiemap_prep(inode, fieinfo, start, &len, 0); + if (error) + return error; + + error = ext4_fiemap_check_ranges(inode, start, &len); + if (error) + return error; + start_blk = start >> inode->i_sb->s_blocksize_bits; + last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; + if (last_blk >= EXT_MAX_BLOCKS) + last_blk = EXT_MAX_BLOCKS-1; + len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; + + /* + * Walk the extent tree gathering extent information + * and pushing extents back to the user. + */ + return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo); +} /* * ext4_access_path: @@ -5304,7 +5330,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (IS_SYNC(inode)) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index d996b44d2265..e75171535375 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1054,7 +1054,7 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; /* record the first block of the first delonly extent seen */ - if (rc->first_do_lblk_found == false) { + if (!rc->first_do_lblk_found) { rc->first_do_lblk = i; rc->first_do_lblk_found = true; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0d624250a62b..2a01e31a032c 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -287,6 +287,7 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, bool truncate = false; u8 blkbits = inode->i_blkbits; ext4_lblk_t written_blk, end_blk; + int ret; /* * Note that EXT4_I(inode)->i_disksize can get extended up to @@ -327,8 +328,14 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, goto truncate; } - if (ext4_update_inode_size(inode, offset + written)) - ext4_mark_inode_dirty(handle, inode); + if (ext4_update_inode_size(inode, offset + written)) { + ret = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret)) { + written = ret; + ext4_journal_stop(handle); + goto truncate; + } + } /* * We may need to truncate allocated but not written blocks beyond EOF. @@ -495,6 +502,12 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret <= 0) return ret; + /* if we're going to block and IOCB_NOWAIT is set, return -EAGAIN */ + if ((iocb->ki_flags & IOCB_NOWAIT) && (unaligned_io || extend)) { + ret = -EAGAIN; + goto out; + } + offset = iocb->ki_pos; count = ret; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 35ff9a56db67..1d668c8f131f 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -44,30 +44,28 @@ */ static int ext4_sync_parent(struct inode *inode) { - struct dentry *dentry = NULL; - struct inode *next; + struct dentry *dentry, *next; int ret = 0; if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) return 0; - inode = igrab(inode); + dentry = d_find_any_alias(inode); + if (!dentry) + return 0; while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); - dentry = d_find_any_alias(inode); - if (!dentry) - break; - next = igrab(d_inode(dentry->d_parent)); + + next = dget_parent(dentry); dput(dentry); - if (!next) - break; - iput(inode); - inode = next; + dentry = next; + inode = dentry->d_inode; + /* * The directory inode may have gone through rmdir by now. But * the inode itself and its blocks are still allocated (we hold - * a reference to the inode so it didn't go through - * ext4_evict_inode()) and so we are safe to flush metadata - * blocks and the inode. + * a reference to the inode via its dentry), so it didn't go + * through ext4_evict_inode()) and so we are safe to flush + * metadata blocks and the inode. */ ret = sync_mapping_buffers(inode->i_mapping); if (ret) @@ -76,7 +74,7 @@ static int ext4_sync_parent(struct inode *inode) if (ret) break; } - iput(inode); + dput(dentry); return ret; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 499f08d8522e..54d324e80fe5 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1246,6 +1246,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) ext4_error_err(sb, -err, "couldn't read orphan inode %lu (err %d)", ino, err); + brelse(bitmap_bh); return inode; } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 107f0043f67f..be2b66eb65f7 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -467,7 +467,9 @@ static int ext4_splice_branch(handle_t *handle, /* * OK, we spliced it into the inode itself on a direct block. */ - ext4_mark_inode_dirty(handle, ar->inode); + err = ext4_mark_inode_dirty(handle, ar->inode); + if (unlikely(err)) + goto err_out; jbd_debug(5, "splicing direct\n"); } return err; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f35e289e17aa..c3a1ad2db122 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1260,7 +1260,7 @@ out: int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode) { - int ret, inline_size, no_expand; + int ret, ret2, inline_size, no_expand; void *inline_start; struct ext4_iloc iloc; @@ -1314,7 +1314,9 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, out: ext4_write_unlock_xattr(dir, &no_expand); - ext4_mark_inode_dirty(handle, dir); + ret2 = ext4_mark_inode_dirty(handle, dir); + if (unlikely(ret2 && !ret)) + ret = ret2; brelse(iloc.bh); return ret; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 52be85f96159..40ec5c7ef0d3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -221,6 +221,16 @@ void ext4_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); /* + * For inodes with journalled data, transaction commit could have + * dirtied the inode. Flush worker is ignoring it because of I_FREEING + * flag but we still need to remove the inode from the writeback lists. + */ + if (!list_empty_careful(&inode->i_io_list)) { + WARN_ON_ONCE(!ext4_should_journal_data(inode)); + inode_io_list_del(inode); + } + + /* * Protect us against freezing - iput() caller didn't have to have any * protection against it */ @@ -432,11 +442,9 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); + retval = ext4_ext_map_blocks(handle, inode, map, 0); } else { - retval = ext4_ind_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); + retval = ext4_ind_map_blocks(handle, inode, map, 0); } up_read((&EXT4_I(inode)->i_data_sem)); @@ -493,9 +501,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, #endif map->m_flags = 0; - ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u," - "logical block %lu\n", inode->i_ino, flags, map->m_len, - (unsigned long) map->m_lblk); + ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n", + flags, map->m_len, (unsigned long) map->m_lblk); /* * ext4_map_blocks returns an int, and m_len is an unsigned int @@ -541,11 +548,9 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); + retval = ext4_ext_map_blocks(handle, inode, map, 0); } else { - retval = ext4_ind_map_blocks(handle, inode, map, flags & - EXT4_GET_BLOCKS_KEEP_SIZE); + retval = ext4_ind_map_blocks(handle, inode, map, 0); } if (retval > 0) { unsigned int status; @@ -726,6 +731,9 @@ out_sem: return ret; } } + + if (retval < 0) + ext_debug(inode, "failed with err %d\n", retval); return retval; } @@ -1296,7 +1304,7 @@ static int ext4_write_end(struct file *file, * filesystems. */ if (i_size_changed || inline_data) - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied @@ -1526,6 +1534,7 @@ struct mpage_da_data { struct ext4_map_blocks map; struct ext4_io_submit io_submit; /* IO submission data */ unsigned int do_map:1; + unsigned int scanned_until_end:1; }; static void mpage_release_unused_pages(struct mpage_da_data *mpd, @@ -1541,6 +1550,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, if (mpd->first_page >= mpd->next_page) return; + mpd->scanned_until_end = 0; index = mpd->first_page; end = mpd->next_page - 1; if (invalidate) { @@ -1681,8 +1691,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, invalid_block = ~0; map->m_flags = 0; - ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u," - "logical block %lu\n", inode->i_ino, map->m_len, + ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len, (unsigned long) map->m_lblk); /* Lookup extent status tree firstly */ @@ -2078,7 +2087,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) return err; } -#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay)) +#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay)) /* * mballoc gives us at most this number of blocks... @@ -2188,7 +2197,11 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd, if (err < 0) return err; } - return lblk < blocks; + if (lblk >= blocks) { + mpd->scanned_until_end = 1; + return 0; + } + return 1; } /* @@ -2311,7 +2324,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) * mapping, or maybe the page was submitted for IO. * So we return to call further extent mapping. */ - if (err < 0 || map_bh == true) + if (err < 0 || map_bh) goto out; /* Page fully mapped - let IO run! */ err = mpage_submit_page(mpd, page); @@ -2358,7 +2371,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) dioread_nolock = ext4_should_dioread_nolock(inode); if (dioread_nolock) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; - if (map->m_flags & (1 << BH_Delay)) + if (map->m_flags & BIT(BH_Delay)) get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; err = ext4_map_blocks(handle, inode, map, get_blocks_flags); @@ -2546,7 +2559,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, tag); if (nr_pages == 0) - goto out; + break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -2601,6 +2614,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) pagevec_release(&pvec); cond_resched(); } + mpd->scanned_until_end = 1; return 0; out: pagevec_release(&pvec); @@ -2619,7 +2633,6 @@ static int ext4_writepages(struct address_space *mapping, struct inode *inode = mapping->host; int needed_blocks, rsv_blocks = 0, ret = 0; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); - bool done; struct blk_plug plug; bool give_up_on_write = false; @@ -2705,7 +2718,6 @@ static int ext4_writepages(struct address_space *mapping, retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page); - done = false; blk_start_plug(&plug); /* @@ -2715,6 +2727,7 @@ retry: * started. */ mpd.do_map = 0; + mpd.scanned_until_end = 0; mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); if (!mpd.io_submit.io_end) { ret = -ENOMEM; @@ -2730,7 +2743,7 @@ retry: if (ret < 0) goto unplug; - while (!done && mpd.first_page <= mpd.last_page) { + while (!mpd.scanned_until_end && wbc->nr_to_write > 0) { /* For each extent of pages we use new io_end */ mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); if (!mpd.io_submit.io_end) { @@ -2765,20 +2778,9 @@ retry: trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc); ret = mpage_prepare_extent_to_map(&mpd); - if (!ret) { - if (mpd.map.m_len) - ret = mpage_map_and_submit_extent(handle, &mpd, + if (!ret && mpd.map.m_len) + ret = mpage_map_and_submit_extent(handle, &mpd, &give_up_on_write); - else { - /* - * We scanned the whole range (or exhausted - * nr_to_write), submitted what was mapped and - * didn't find anything needing mapping. We are - * done. - */ - done = true; - } - } /* * Caution: If the handle is synchronous, * ext4_journal_stop() can wait for transaction commit @@ -3077,7 +3079,7 @@ static int ext4_da_write_end(struct file *file, * new_i_size is less that inode->i_size * bu greater than i_disksize.(hint delalloc) */ - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); } } @@ -3094,7 +3096,7 @@ static int ext4_da_write_end(struct file *file, if (ret2 < 0) ret = ret2; ret2 = ext4_journal_stop(handle); - if (!ret) + if (unlikely(ret2 && !ret)) ret = ret2; return ret ? ret : copied; @@ -3883,6 +3885,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, loff_t len) { handle_t *handle; + int ret; + loff_t size = i_size_read(inode); WARN_ON(!inode_is_locked(inode)); @@ -3896,10 +3900,10 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, if (IS_ERR(handle)) return PTR_ERR(handle); ext4_update_i_disksize(inode, size); - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); - return 0; + return ret; } static void ext4_wait_dax_page(struct ext4_inode_info *ei) @@ -3951,7 +3955,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) loff_t first_block_offset, last_block_offset; handle_t *handle; unsigned int credits; - int ret = 0; + int ret = 0, ret2 = 0; trace_ext4_punch_hole(inode, offset, length, 0); @@ -4074,7 +4078,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret2)) + ret = ret2; if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: @@ -4143,7 +4149,7 @@ int ext4_truncate(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int credits; - int err = 0; + int err = 0, err2; handle_t *handle; struct address_space *mapping = inode->i_mapping; @@ -4231,7 +4237,9 @@ out_stop: ext4_orphan_del(handle, inode); inode->i_mtime = inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + err2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(err2 && !err)) + err = err2; ext4_journal_stop(handle); trace_ext4_truncate_exit(inode); @@ -4857,21 +4865,22 @@ static int ext4_inode_blocks_set(handle_t *handle, return 0; } -struct other_inode { - unsigned long orig_ino; - struct ext4_inode *raw_inode; -}; - -static int other_inode_match(struct inode * inode, unsigned long ino, - void *data) +static void __ext4_update_other_inode_time(struct super_block *sb, + unsigned long orig_ino, + unsigned long ino, + struct ext4_inode *raw_inode) { - struct other_inode *oi = (struct other_inode *) data; + struct inode *inode; + + inode = find_inode_by_ino_rcu(sb, ino); + if (!inode) + return; - if ((inode->i_ino != ino) || - (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | + if ((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | I_DIRTY_INODE)) || ((inode->i_state & I_DIRTY_TIME) == 0)) - return 0; + return; + spin_lock(&inode->i_lock); if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | I_DIRTY_INODE)) == 0) && @@ -4882,16 +4891,15 @@ static int other_inode_match(struct inode * inode, unsigned long ino, spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); - EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode); - ext4_inode_csum_set(inode, oi->raw_inode, ei); + EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); + EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); + EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); - trace_ext4_other_inode_update_time(inode, oi->orig_ino); - return -1; + trace_ext4_other_inode_update_time(inode, orig_ino); + return; } spin_unlock(&inode->i_lock); - return -1; } /* @@ -4901,24 +4909,24 @@ static int other_inode_match(struct inode * inode, unsigned long ino, static void ext4_update_other_inodes_time(struct super_block *sb, unsigned long orig_ino, char *buf) { - struct other_inode oi; unsigned long ino; int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; int inode_size = EXT4_INODE_SIZE(sb); - oi.orig_ino = orig_ino; /* * Calculate the first inode in the inode table block. Inode * numbers are one-based. That is, the first inode in a block * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1). */ ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1; + rcu_read_lock(); for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { if (ino == orig_ino) continue; - oi.raw_inode = (struct ext4_inode *) buf; - (void) find_inode_nowait(sb, ino, other_inode_match, &oi); + __ext4_update_other_inode_time(sb, orig_ino, ino, + (struct ext4_inode *)buf); } + rcu_read_unlock(); } /* @@ -5289,6 +5297,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) inode->i_gid = attr->ia_gid; error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); + if (unlikely(error)) + return error; } if (attr->ia_valid & ATTR_SIZE) { @@ -5774,7 +5784,8 @@ out_unlock: * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. */ -int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) +int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, + const char *func, unsigned int line) { struct ext4_iloc iloc; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -5784,13 +5795,18 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) - return err; + goto out; if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize) ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize, iloc, handle); - return ext4_mark_iloc_dirty(handle, inode, &iloc); + err = ext4_mark_iloc_dirty(handle, inode, &iloc); +out: + if (unlikely(err)) + ext4_error_inode_err(inode, func, line, 0, err, + "mark_inode_dirty error"); + return err; } /* diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0746532ba463..2162db0c747d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -754,14 +754,6 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg) fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; - if (fiemap.fm_extent_count != 0 && - !access_ok(fieinfo.fi_extents_start, - fieinfo.fi_extents_max * sizeof(struct fiemap_extent))) - return -EFAULT; - - if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) - filemap_write_and_wait(inode->i_mapping); - error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 30d5d97548c4..a9083113a8c0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -18,13 +18,6 @@ #include <linux/backing-dev.h> #include <trace/events/ext4.h> -#ifdef CONFIG_EXT4_DEBUG -ushort ext4_mballoc_debug __read_mostly; - -module_param_named(mballoc_debug, ext4_mballoc_debug, ushort, 0644); -MODULE_PARM_DESC(mballoc_debug, "Debugging level for ext4's mballoc"); -#endif - /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() @@ -356,6 +349,36 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); +static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); + +/* + * The algorithm using this percpu seq counter goes below: + * 1. We sample the percpu discard_pa_seq counter before trying for block + * allocation in ext4_mb_new_blocks(). + * 2. We increment this percpu discard_pa_seq counter when we either allocate + * or free these blocks i.e. while marking those blocks as used/free in + * mb_mark_used()/mb_free_blocks(). + * 3. We also increment this percpu seq counter when we successfully identify + * that the bb_prealloc_list is not empty and hence proceed for discarding + * of those PAs inside ext4_mb_discard_group_preallocations(). + * + * Now to make sure that the regular fast path of block allocation is not + * affected, as a small optimization we only sample the percpu seq counter + * on that cpu. Only when the block allocation fails and when freed blocks + * found were 0, that is when we sample percpu seq counter for all cpus using + * below function ext4_get_discard_pa_seq_sum(). This happens after making + * sure that all the PAs on grp->bb_prealloc_list got freed or if it's empty. + */ +static DEFINE_PER_CPU(u64, discard_pa_seq); +static inline u64 ext4_get_discard_pa_seq_sum(void) +{ + int __cpu; + u64 __seq = 0; + + for_each_possible_cpu(__cpu) + __seq += per_cpu(discard_pa_seq, __cpu); + return __seq; +} static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { @@ -493,6 +516,8 @@ static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { + if (unlikely(e4b->bd_info->bb_bitmap == NULL)) + return; if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) { unsigned char *b1, *b2; int i; @@ -511,6 +536,31 @@ static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) } } +static void mb_group_bb_bitmap_alloc(struct super_block *sb, + struct ext4_group_info *grp, ext4_group_t group) +{ + struct buffer_head *bh; + + grp->bb_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS); + if (!grp->bb_bitmap) + return; + + bh = ext4_read_block_bitmap(sb, group); + if (IS_ERR_OR_NULL(bh)) { + kfree(grp->bb_bitmap); + grp->bb_bitmap = NULL; + return; + } + + memcpy(grp->bb_bitmap, bh->b_data, sb->s_blocksize); + put_bh(bh); +} + +static void mb_group_bb_bitmap_free(struct ext4_group_info *grp) +{ + kfree(grp->bb_bitmap); +} + #else static inline void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) @@ -526,6 +576,17 @@ static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { return; } + +static inline void mb_group_bb_bitmap_alloc(struct super_block *sb, + struct ext4_group_info *grp, ext4_group_t group) +{ + return; +} + +static inline void mb_group_bb_bitmap_free(struct ext4_group_info *grp) +{ + return; +} #endif #ifdef AGGRESSIVE_CHECK @@ -820,14 +881,14 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) char *bitmap; struct ext4_group_info *grinfo; - mb_debug(1, "init page %lu\n", page->index); - inode = page->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = i_blocksize(inode); blocks_per_page = PAGE_SIZE / blocksize; + mb_debug(sb, "init page %lu\n", page->index); + groups_per_page = blocks_per_page >> 1; if (groups_per_page == 0) groups_per_page = 1; @@ -867,7 +928,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) bh[i] = NULL; goto out; } - mb_debug(1, "read bitmap for group %u\n", group); + mb_debug(sb, "read bitmap for group %u\n", group); } /* wait for I/O completion */ @@ -912,7 +973,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); - mb_debug(1, "put buddy for group %u in page %lu/%x\n", + mb_debug(sb, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo = ext4_get_group_info(sb, group); @@ -932,7 +993,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) } else { /* this is block of bitmap */ BUG_ON(incore != NULL); - mb_debug(1, "put bitmap for group %u in page %lu/%x\n", + mb_debug(sb, "put bitmap for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_bitmap_load(sb, group); @@ -1038,7 +1099,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) int ret = 0; might_sleep(); - mb_debug(1, "init group %u\n", group); + mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); /* * This ensures that we don't reinit the buddy cache @@ -1110,7 +1171,7 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, struct inode *inode = sbi->s_buddy_cache; might_sleep(); - mb_debug(1, "load group %u\n", group); + mb_debug(sb, "load group %u\n", group); blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); @@ -1430,6 +1491,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); + this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free += count; if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; @@ -1571,6 +1633,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); + this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free -= len; if (e4b->bd_info->bb_first_free == start) e4b->bd_info->bb_first_free += len; @@ -1670,6 +1733,14 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, sbi->s_mb_last_start = ac->ac_f_ex.fe_start; spin_unlock(&sbi->s_md_lock); } + /* + * As we've just preallocated more space than + * user requested originally, we store allocated + * space in a special descriptor. + */ + if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) + ext4_mb_new_preallocation(ac); + } /* @@ -1918,7 +1989,7 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); - BUG_ON(ac->ac_b_ex.fe_len != ac->ac_g_ex.fe_len); + BUG_ON(ac->ac_f_ex.fe_len != ac->ac_g_ex.fe_len); if (EXT4_SB(sb)->s_mb_stats) atomic_inc(&EXT4_SB(sb)->s_bal_2orders); @@ -2035,15 +2106,14 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, } /* - * This is now called BEFORE we load the buddy bitmap. + * This is also called BEFORE we load the buddy bitmap. * Returns either 1 or 0 indicating that the group is either suitable - * for the allocation or not. In addition it can also return negative - * error code when something goes wrong. + * for the allocation or not. */ -static int ext4_mb_good_group(struct ext4_allocation_context *ac, +static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, int cr) { - unsigned free, fragments; + ext4_grpblk_t free, fragments; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); @@ -2051,23 +2121,16 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, free = grp->bb_free; if (free == 0) - return 0; + return false; if (cr <= 2 && free < ac->ac_g_ex.fe_len) - return 0; + return false; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) - return 0; - - /* We only do this if the grp has never been initialized */ - if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { - int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS); - if (ret) - return ret; - } + return false; fragments = grp->bb_fragments; if (fragments == 0) - return 0; + return false; switch (cr) { case 0: @@ -2077,38 +2140,80 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, if ((ac->ac_flags & EXT4_MB_HINT_DATA) && (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) && ((group % flex_size) == 0)) - return 0; + return false; if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) || (free / fragments) >= ac->ac_g_ex.fe_len) - return 1; + return true; if (grp->bb_largest_free_order < ac->ac_2order) - return 0; + return false; - return 1; + return true; case 1: if ((free / fragments) >= ac->ac_g_ex.fe_len) - return 1; + return true; break; case 2: if (free >= ac->ac_g_ex.fe_len) - return 1; + return true; break; case 3: - return 1; + return true; default: BUG(); } - return 0; + return false; +} + +/* + * This could return negative error code if something goes wrong + * during ext4_mb_init_group(). This should not be called with + * ext4_lock_group() held. + */ +static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, + ext4_group_t group, int cr) +{ + struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); + struct super_block *sb = ac->ac_sb; + bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; + ext4_grpblk_t free; + int ret = 0; + + if (should_lock) + ext4_lock_group(sb, group); + free = grp->bb_free; + if (free == 0) + goto out; + if (cr <= 2 && free < ac->ac_g_ex.fe_len) + goto out; + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + goto out; + if (should_lock) + ext4_unlock_group(sb, group); + + /* We only do this if the grp has never been initialized */ + if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { + ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS); + if (ret) + return ret; + } + + if (should_lock) + ext4_lock_group(sb, group); + ret = ext4_mb_good_group(ac, group, cr); +out: + if (should_lock) + ext4_unlock_group(sb, group); + return ret; } static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t ngroups, group, i; - int cr; + int cr = -1; int err = 0, first_err = 0; struct ext4_sb_info *sbi; struct super_block *sb; @@ -2189,7 +2294,7 @@ repeat: group = 0; /* This now checks without needing the buddy page */ - ret = ext4_mb_good_group(ac, group, cr); + ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!first_err) first_err = ret; @@ -2207,11 +2312,9 @@ repeat: * block group */ ret = ext4_mb_good_group(ac, group, cr); - if (ret <= 0) { + if (ret == 0) { ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); - if (!first_err) - first_err = ret; continue; } @@ -2260,6 +2363,10 @@ repeat: out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = first_err; + + mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", + ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, + ac->ac_flags, cr, err); return err; } @@ -2452,20 +2559,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, meta_group_info[i]->bb_free_root = RB_ROOT; meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ -#ifdef DOUBLE_CHECK - { - struct buffer_head *bh; - meta_group_info[i]->bb_bitmap = - kmalloc(sb->s_blocksize, GFP_NOFS); - BUG_ON(meta_group_info[i]->bb_bitmap == NULL); - bh = ext4_read_block_bitmap(sb, group); - BUG_ON(IS_ERR_OR_NULL(bh)); - memcpy(meta_group_info[i]->bb_bitmap, bh->b_data, - sb->s_blocksize); - put_bh(bh); - } -#endif - + mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; exit_group_info: @@ -2702,7 +2796,7 @@ out: } /* need to called with the ext4 group lock held */ -static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) +static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; struct list_head *cur, *tmp; @@ -2714,9 +2808,7 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) count++; kmem_cache_free(ext4_pspace_cachep, pa); } - if (count) - mb_debug(1, "mballoc: %u PAs left\n", count); - + return count; } int ext4_mb_release(struct super_block *sb) @@ -2727,16 +2819,18 @@ int ext4_mb_release(struct super_block *sb) struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); + int count; if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); -#ifdef DOUBLE_CHECK - kfree(grinfo->bb_bitmap); -#endif + mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); - ext4_mb_cleanup_pa(grinfo); + count = ext4_mb_cleanup_pa(grinfo); + if (count) + mb_debug(sb, "mballoc: %d PAs left\n", + count); ext4_unlock_group(sb, i); kmem_cache_free(cachep, grinfo); } @@ -2809,7 +2903,7 @@ static void ext4_free_data_in_buddy(struct super_block *sb, struct ext4_group_info *db; int err, count = 0, count2 = 0; - mb_debug(1, "gonna free %u blocks in group %u (0x%p):", + mb_debug(sb, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); @@ -2849,7 +2943,8 @@ static void ext4_free_data_in_buddy(struct super_block *sb, kmem_cache_free(ext4_free_data_cachep, entry); ext4_mb_unload_buddy(&e4b); - mb_debug(1, "freed %u blocks in %u structures\n", count, count2); + mb_debug(sb, "freed %d blocks in %d structures\n", count, + count2); } /* @@ -2909,23 +3004,26 @@ int __init ext4_init_mballoc(void) ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) - return -ENOMEM; + goto out; ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, SLAB_RECLAIM_ACCOUNT); - if (ext4_ac_cachep == NULL) { - kmem_cache_destroy(ext4_pspace_cachep); - return -ENOMEM; - } + if (ext4_ac_cachep == NULL) + goto out_pa_free; ext4_free_data_cachep = KMEM_CACHE(ext4_free_data, SLAB_RECLAIM_ACCOUNT); - if (ext4_free_data_cachep == NULL) { - kmem_cache_destroy(ext4_pspace_cachep); - kmem_cache_destroy(ext4_ac_cachep); - return -ENOMEM; - } + if (ext4_free_data_cachep == NULL) + goto out_ac_free; + return 0; + +out_ac_free: + kmem_cache_destroy(ext4_ac_cachep); +out_pa_free: + kmem_cache_destroy(ext4_pspace_cachep); +out: + return -ENOMEM; } void ext4_exit_mballoc(void) @@ -3077,8 +3175,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) BUG_ON(lg == NULL); ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; - mb_debug(1, "#%u: goal %u blocks for locality group\n", - current->pid, ac->ac_g_ex.fe_len); + mb_debug(sb, "goal %u blocks for locality group\n", ac->ac_g_ex.fe_len); } /* @@ -3276,8 +3373,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } - mb_debug(1, "goal: %u(was %u) blocks at %u\n", (unsigned) size, - (unsigned) orig_size, (unsigned) start); + mb_debug(ac->ac_sb, "goal: %lld(was %lld) blocks at %u\n", size, + orig_size, start); } static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) @@ -3366,7 +3463,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, BUG_ON(pa->pa_free < len); pa->pa_free -= len; - mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa); + mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); } /* @@ -3390,7 +3487,8 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ - mb_debug(1, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); + mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n", + pa->pa_lstart-len, len, pa); } /* @@ -3425,7 +3523,7 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block, /* * search goal blocks in preallocated space */ -static noinline_for_stack int +static noinline_for_stack bool ext4_mb_use_preallocated(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); @@ -3437,7 +3535,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) /* only data can be preallocated */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) - return 0; + return false; /* first, try per-file preallocation */ rcu_read_lock(); @@ -3464,7 +3562,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) spin_unlock(&pa->pa_lock); ac->ac_criteria = 10; rcu_read_unlock(); - return 1; + return true; } spin_unlock(&pa->pa_lock); } @@ -3472,12 +3570,12 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) /* can we use group allocation? */ if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)) - return 0; + return false; /* inode may have no locality group for some reason */ lg = ac->ac_lg; if (lg == NULL) - return 0; + return false; order = fls(ac->ac_o_ex.fe_len) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ @@ -3506,9 +3604,9 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) if (cpa) { ext4_mb_use_group_pa(ac, cpa); ac->ac_criteria = 20; - return 1; + return true; } - return 0; + return false; } /* @@ -3573,7 +3671,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_set_bits(bitmap, start, len); preallocated += len; } - mb_debug(1, "preallocated %u for group %u\n", preallocated, group); + mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } static void ext4_mb_pa_callback(struct rcu_head *head) @@ -3649,7 +3747,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, /* * creates new preallocated space for given inode */ -static noinline_for_stack int +static noinline_for_stack void ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; @@ -3662,10 +3760,9 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); + BUG_ON(ac->ac_pa == NULL); - pa = kmem_cache_alloc(ext4_pspace_cachep, GFP_NOFS); - if (pa == NULL) - return -ENOMEM; + pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { int winl; @@ -3709,15 +3806,14 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; - atomic_set(&pa->pa_count, 1); spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_inode_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; - mb_debug(1, "new inode pa %p: %llu/%u for %u\n", pa, - pa->pa_pstart, pa->pa_len, pa->pa_lstart); + mb_debug(sb, "new inode pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, + pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); ext4_mb_use_inode_pa(ac, pa); @@ -3729,21 +3825,17 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa->pa_obj_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; - ext4_lock_group(sb, ac->ac_b_ex.fe_group); list_add(&pa->pa_group_list, &grp->bb_prealloc_list); - ext4_unlock_group(sb, ac->ac_b_ex.fe_group); spin_lock(pa->pa_obj_lock); list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); - - return 0; } /* * creates new preallocated space for locality group inodes belongs to */ -static noinline_for_stack int +static noinline_for_stack void ext4_mb_new_group_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; @@ -3755,11 +3847,9 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); + BUG_ON(ac->ac_pa == NULL); - BUG_ON(ext4_pspace_cachep == NULL); - pa = kmem_cache_alloc(ext4_pspace_cachep, GFP_NOFS); - if (pa == NULL) - return -ENOMEM; + pa = ac->ac_pa; /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ @@ -3769,15 +3859,14 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) pa->pa_lstart = pa->pa_pstart; pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; - atomic_set(&pa->pa_count, 1); spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_inode_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; - mb_debug(1, "new group pa %p: %llu/%u for %u\n", pa, - pa->pa_pstart, pa->pa_len, pa->pa_lstart); + mb_debug(sb, "new group pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, + pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); @@ -3790,26 +3879,20 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) pa->pa_obj_lock = &lg->lg_prealloc_lock; pa->pa_inode = NULL; - ext4_lock_group(sb, ac->ac_b_ex.fe_group); list_add(&pa->pa_group_list, &grp->bb_prealloc_list); - ext4_unlock_group(sb, ac->ac_b_ex.fe_group); /* * We will later add the new pa to the right bucket * after updating the pa_free in ext4_mb_release_context */ - return 0; } -static int ext4_mb_new_preallocation(struct ext4_allocation_context *ac) +static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) { - int err; - if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) - err = ext4_mb_new_group_pa(ac); + ext4_mb_new_group_pa(ac); else - err = ext4_mb_new_inode_pa(ac); - return err; + ext4_mb_new_inode_pa(ac); } /* @@ -3844,7 +3927,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, if (bit >= end) break; next = mb_find_next_bit(bitmap_bh->b_data, end, bit); - mb_debug(1, " free preallocated %u/%u in group %u\n", + mb_debug(sb, "free preallocated %u/%u in group %u\n", (unsigned) ext4_group_first_block_no(sb, group) + bit, (unsigned) next - bit, (unsigned) group); free += next - bit; @@ -3858,10 +3941,10 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, } if (free != pa->pa_free) { ext4_msg(e4b->bd_sb, KERN_CRIT, - "pa %p: logic %lu, phys. %lu, len %lu", + "pa %p: logic %lu, phys. %lu, len %d", pa, (unsigned long) pa->pa_lstart, (unsigned long) pa->pa_pstart, - (unsigned long) pa->pa_len); + pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* @@ -3915,10 +3998,9 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, int busy = 0; int free = 0; - mb_debug(1, "discard preallocation for group %u\n", group); - + mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) - return 0; + goto out_dbg; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { @@ -3926,7 +4008,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); - return 0; + goto out_dbg; } err = ext4_mb_load_buddy(sb, group, &e4b); @@ -3934,7 +4016,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_warning(sb, "Error %d loading buddy information for %u", err, group); put_bh(bitmap_bh); - return 0; + goto out_dbg; } if (needed == 0) @@ -3943,6 +4025,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, INIT_LIST_HEAD(&list); repeat: ext4_lock_group(sb, group); + this_cpu_inc(discard_pa_seq); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); @@ -3979,6 +4062,8 @@ repeat: /* found anything to free? */ if (list_empty(&list)) { BUG_ON(free != 0); + mb_debug(sb, "Someone else may have freed PA for this group %u\n", + group); goto out; } @@ -4003,6 +4088,9 @@ out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); +out_dbg: + mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", + free, group, grp->bb_free); return free; } @@ -4031,7 +4119,8 @@ void ext4_discard_preallocations(struct inode *inode) return; } - mb_debug(1, "discard preallocation for inode %lu\n", inode->i_ino); + mb_debug(sb, "discard preallocation for inode %lu\n", + inode->i_ino); trace_ext4_discard_preallocations(inode); INIT_LIST_HEAD(&list); @@ -4119,22 +4208,74 @@ repeat: } } +static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac) +{ + struct ext4_prealloc_space *pa; + + BUG_ON(ext4_pspace_cachep == NULL); + pa = kmem_cache_zalloc(ext4_pspace_cachep, GFP_NOFS); + if (!pa) + return -ENOMEM; + atomic_set(&pa->pa_count, 1); + ac->ac_pa = pa; + return 0; +} + +static void ext4_mb_pa_free(struct ext4_allocation_context *ac) +{ + struct ext4_prealloc_space *pa = ac->ac_pa; + + BUG_ON(!pa); + ac->ac_pa = NULL; + WARN_ON(!atomic_dec_and_test(&pa->pa_count)); + kmem_cache_free(ext4_pspace_cachep, pa); +} + #ifdef CONFIG_EXT4_DEBUG +static inline void ext4_mb_show_pa(struct super_block *sb) +{ + ext4_group_t i, ngroups; + + if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + return; + + ngroups = ext4_get_groups_count(sb); + mb_debug(sb, "groups: "); + for (i = 0; i < ngroups; i++) { + struct ext4_group_info *grp = ext4_get_group_info(sb, i); + struct ext4_prealloc_space *pa; + ext4_grpblk_t start; + struct list_head *cur; + ext4_lock_group(sb, i); + list_for_each(cur, &grp->bb_prealloc_list) { + pa = list_entry(cur, struct ext4_prealloc_space, + pa_group_list); + spin_lock(&pa->pa_lock); + ext4_get_group_no_and_offset(sb, pa->pa_pstart, + NULL, &start); + spin_unlock(&pa->pa_lock); + mb_debug(sb, "PA:%u:%d:%d\n", i, start, + pa->pa_len); + } + ext4_unlock_group(sb, i); + mb_debug(sb, "%u: %d/%d\n", i, grp->bb_free, + grp->bb_fragments); + } +} + static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - ext4_group_t ngroups, i; - if (!ext4_mballoc_debug || - (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) + if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) return; - ext4_msg(ac->ac_sb, KERN_ERR, "Can't allocate:" + mb_debug(sb, "Can't allocate:" " Allocation context details:"); - ext4_msg(ac->ac_sb, KERN_ERR, "status %d flags %d", + mb_debug(sb, "status %u flags 0x%x", ac->ac_status, ac->ac_flags); - ext4_msg(ac->ac_sb, KERN_ERR, "orig %lu/%lu/%lu@%lu, " - "goal %lu/%lu/%lu@%lu, " + mb_debug(sb, "orig %lu/%lu/%lu@%lu, " + "goal %lu/%lu/%lu@%lu, " "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, @@ -4149,37 +4290,17 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); - ext4_msg(ac->ac_sb, KERN_ERR, "%d found", ac->ac_found); - ext4_msg(ac->ac_sb, KERN_ERR, "groups: "); - ngroups = ext4_get_groups_count(sb); - for (i = 0; i < ngroups; i++) { - struct ext4_group_info *grp = ext4_get_group_info(sb, i); - struct ext4_prealloc_space *pa; - ext4_grpblk_t start; - struct list_head *cur; - ext4_lock_group(sb, i); - list_for_each(cur, &grp->bb_prealloc_list) { - pa = list_entry(cur, struct ext4_prealloc_space, - pa_group_list); - spin_lock(&pa->pa_lock); - ext4_get_group_no_and_offset(sb, pa->pa_pstart, - NULL, &start); - spin_unlock(&pa->pa_lock); - printk(KERN_ERR "PA:%u:%d:%u \n", i, - start, pa->pa_len); - } - ext4_unlock_group(sb, i); - - if (grp->bb_free == 0) - continue; - printk(KERN_ERR "%u: %d/%d \n", - i, grp->bb_free, grp->bb_fragments); - } - printk(KERN_ERR "\n"); + mb_debug(sb, "%u found", ac->ac_found); + ext4_mb_show_pa(sb); } #else +static inline void ext4_mb_show_pa(struct super_block *sb) +{ + return; +} static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { + ext4_mb_show_pa(ac->ac_sb); return; } #endif @@ -4282,7 +4403,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); - mb_debug(1, "init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, " + mb_debug(sb, "init ac: %u blocks @ %u, goal %u, flags 0x%x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, @@ -4303,7 +4424,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, struct list_head discard_list; struct ext4_prealloc_space *pa, *tmp; - mb_debug(1, "discard locality group preallocation\n"); + mb_debug(sb, "discard locality group preallocation\n"); INIT_LIST_HEAD(&discard_list); @@ -4486,6 +4607,30 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) return freed; } +static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb, + struct ext4_allocation_context *ac, u64 *seq) +{ + int freed; + u64 seq_retry = 0; + bool ret = false; + + freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); + if (freed) { + ret = true; + goto out_dbg; + } + seq_retry = ext4_get_discard_pa_seq_sum(); + if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) { + ac->ac_flags |= EXT4_MB_STRICT_CHECK; + *seq = seq_retry; + ret = true; + } + +out_dbg: + mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no"); + return ret; +} + /* * Main entry point into mballoc to allocate blocks * it tries to use preallocation first, then falls back @@ -4494,13 +4639,13 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { - int freed; struct ext4_allocation_context *ac = NULL; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + u64 seq; might_sleep(); sb = ar->inode->i_sb; @@ -4525,6 +4670,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ar->len = ar->len >> 1; } if (!ar->len) { + ext4_mb_show_pa(sb); *errp = -ENOSPC; return 0; } @@ -4562,26 +4708,32 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, } ac->ac_op = EXT4_MB_HISTORY_PREALLOC; + seq = *this_cpu_ptr(&discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); + + *errp = ext4_mb_pa_alloc(ac); + if (*errp) + goto errout; repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); - if (*errp) - goto discard_and_exit; - - /* as we've just preallocated more space than - * user requested originally, we store allocated - * space in a special descriptor */ - if (ac->ac_status == AC_STATUS_FOUND && - ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) - *errp = ext4_mb_new_preallocation(ac); + /* + * pa allocated above is added to grp->bb_prealloc_list only + * when we were able to allocate some block i.e. when + * ac->ac_status == AC_STATUS_FOUND. + * And error from above mean ac->ac_status != AC_STATUS_FOUND + * So we have to free this pa here itself. + */ if (*errp) { - discard_and_exit: + ext4_mb_pa_free(ac); ext4_discard_allocated_blocks(ac); goto errout; } + if (ac->ac_status == AC_STATUS_FOUND && + ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len) + ext4_mb_pa_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); @@ -4593,9 +4745,13 @@ repeat: ar->len = ac->ac_b_ex.fe_len; } } else { - freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); - if (freed) + if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; + /* + * If block allocation fails then the pa allocated above + * needs to be freed here itself. + */ + ext4_mb_pa_free(ac); *errp = -ENOSPC; } diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 88c98f17e3d9..6b4d17c2935d 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -24,19 +24,15 @@ #include "ext4.h" /* + * mb_debug() dynamic printk msgs could be used to debug mballoc code. */ #ifdef CONFIG_EXT4_DEBUG -extern ushort ext4_mballoc_debug; - -#define mb_debug(n, fmt, ...) \ -do { \ - if ((n) <= ext4_mballoc_debug) { \ - printk(KERN_DEBUG "(%s, %d): %s: " fmt, \ - __FILE__, __LINE__, __func__, ##__VA_ARGS__); \ - } \ -} while (0) +#define mb_debug(sb, fmt, ...) \ + pr_debug("[%s/%d] EXT4-fs (%s): (%s, %d): %s: " fmt, \ + current->comm, task_pid_nr(current), sb->s_id, \ + __FILE__, __LINE__, __func__, ##__VA_ARGS__) #else -#define mb_debug(n, fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#define mb_debug(sb, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define EXT4_MB_HISTORY_ALLOC 1 /* allocation */ diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index fb6520f37135..c5e3fc998211 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -287,7 +287,7 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data) static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode, struct inode *tmp_inode) { - int retval; + int retval, retval2 = 0; __le32 i_data[3]; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode); @@ -342,7 +342,9 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode, * i_blocks when freeing the indirect meta-data blocks */ retval = free_ind_block(handle, inode, i_data); - ext4_mark_inode_dirty(handle, inode); + retval2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(retval2 && !retval)) + retval = retval2; err_out: return retval; @@ -601,7 +603,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_lblk_t start, end; ext4_fsblk_t blk; handle_t *handle; - int ret; + int ret, ret2 = 0; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) @@ -655,7 +657,9 @@ int ext4_ind_migrate(struct inode *inode) memset(ei->i_data, 0, sizeof(ei->i_data)); for (i = start; i <= end; i++) ei->i_data[i] = cpu_to_le32(blk++); - ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret2 && !ret)) + ret = ret2; errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a8aca4772aaa..56738b538ddf 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1993,7 +1993,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, { unsigned int blocksize = dir->i_sb->s_blocksize; int csum_size = 0; - int err; + int err, err2; if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); @@ -2028,12 +2028,12 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, dir->i_mtime = dir->i_ctime = current_time(dir); ext4_update_dx_flag(dir); inode_inc_iversion(dir); - ext4_mark_inode_dirty(handle, dir); + err2 = ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_dirblock(handle, dir, bh); if (err) ext4_std_error(dir->i_sb, err); - return 0; + return err ? err : err2; } /* @@ -2223,7 +2223,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; - ext4_mark_inode_dirty(handle, dir); + retval = ext4_mark_inode_dirty(handle, dir); + if (unlikely(retval)) + goto out; } blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { @@ -2576,12 +2578,12 @@ static int ext4_add_nondir(handle_t *handle, struct inode *inode = *inodep; int err = ext4_add_entry(handle, dentry, inode); if (!err) { - ext4_mark_inode_dirty(handle, inode); + err = ext4_mark_inode_dirty(handle, inode); if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); d_instantiate_new(dentry, inode); *inodep = NULL; - return 0; + return err; } drop_nlink(inode); ext4_orphan_add(handle, inode); @@ -2775,7 +2777,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { handle_t *handle; struct inode *inode; - int err, credits, retries = 0; + int err, err2 = 0, credits, retries = 0; if (EXT4_DIR_LINK_MAX(dir)) return -EMLINK; @@ -2808,7 +2810,9 @@ out_clear_inode: clear_nlink(inode); ext4_orphan_add(handle, inode); unlock_new_inode(inode); - ext4_mark_inode_dirty(handle, inode); + err2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(err2)) + err = err2; ext4_journal_stop(handle); iput(inode); goto out_retry; @@ -3148,10 +3152,12 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) inode->i_size = 0; ext4_orphan_add(handle, inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + retval = ext4_mark_inode_dirty(handle, inode); + if (retval) + goto end_rmdir; ext4_dec_count(handle, dir); ext4_update_dx_flag(dir); - ext4_mark_inode_dirty(handle, dir); + retval = ext4_mark_inode_dirty(handle, dir); #ifdef CONFIG_UNICODE /* VFS negative dentries are incompatible with Encoding and @@ -3221,7 +3227,9 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) goto end_unlink; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); - ext4_mark_inode_dirty(handle, dir); + retval = ext4_mark_inode_dirty(handle, dir); + if (retval) + goto end_unlink; if (inode->i_nlink == 0) ext4_warning_inode(inode, "Deleting file '%.*s' with no links", dentry->d_name.len, dentry->d_name.name); @@ -3230,7 +3238,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (!inode->i_nlink) ext4_orphan_add(handle, inode); inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + retval = ext4_mark_inode_dirty(handle, inode); #ifdef CONFIG_UNICODE /* VFS negative dentries are incompatible with Encoding and @@ -3419,7 +3427,7 @@ retry: err = ext4_add_entry(handle, dentry, inode); if (!err) { - ext4_mark_inode_dirty(handle, inode); + err = ext4_mark_inode_dirty(handle, inode); /* this can happen only for tmpfile being * linked the first time */ @@ -3531,7 +3539,7 @@ static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent, static int ext4_setent(handle_t *handle, struct ext4_renament *ent, unsigned ino, unsigned file_type) { - int retval; + int retval, retval2; BUFFER_TRACE(ent->bh, "get write access"); retval = ext4_journal_get_write_access(handle, ent->bh); @@ -3543,19 +3551,19 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, inode_inc_iversion(ent->dir); ent->dir->i_ctime = ent->dir->i_mtime = current_time(ent->dir); - ext4_mark_inode_dirty(handle, ent->dir); + retval = ext4_mark_inode_dirty(handle, ent->dir); BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata"); if (!ent->inlined) { - retval = ext4_handle_dirty_dirblock(handle, ent->dir, ent->bh); - if (unlikely(retval)) { - ext4_std_error(ent->dir->i_sb, retval); - return retval; + retval2 = ext4_handle_dirty_dirblock(handle, ent->dir, ent->bh); + if (unlikely(retval2)) { + ext4_std_error(ent->dir->i_sb, retval2); + return retval2; } } brelse(ent->bh); ent->bh = NULL; - return 0; + return retval; } static int ext4_find_delete_entry(handle_t *handle, struct inode *dir, @@ -3790,7 +3798,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_FT_CHRDEV); if (retval) goto end_rename; - ext4_mark_inode_dirty(handle, whiteout); + retval = ext4_mark_inode_dirty(handle, whiteout); + if (unlikely(retval)) + goto end_rename; } if (!new.bh) { retval = ext4_add_entry(handle, new.dentry, old.inode); @@ -3811,7 +3821,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, * rename. */ old.inode->i_ctime = current_time(old.inode); - ext4_mark_inode_dirty(handle, old.inode); + retval = ext4_mark_inode_dirty(handle, old.inode); + if (unlikely(retval)) + goto end_rename; if (!whiteout) { /* @@ -3840,12 +3852,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, } else { ext4_inc_count(handle, new.dir); ext4_update_dx_flag(new.dir); - ext4_mark_inode_dirty(handle, new.dir); + retval = ext4_mark_inode_dirty(handle, new.dir); + if (unlikely(retval)) + goto end_rename; } } - ext4_mark_inode_dirty(handle, old.dir); + retval = ext4_mark_inode_dirty(handle, old.dir); + if (unlikely(retval)) + goto end_rename; if (new.inode) { - ext4_mark_inode_dirty(handle, new.inode); + retval = ext4_mark_inode_dirty(handle, new.inode); + if (unlikely(retval)) + goto end_rename; if (!new.inode->i_nlink) ext4_orphan_add(handle, new.inode); } @@ -3979,8 +3997,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, ctime = current_time(old.inode); old.inode->i_ctime = ctime; new.inode->i_ctime = ctime; - ext4_mark_inode_dirty(handle, old.inode); - ext4_mark_inode_dirty(handle, new.inode); + retval = ext4_mark_inode_dirty(handle, old.inode); + if (unlikely(retval)) + goto end_rename; + retval = ext4_mark_inode_dirty(handle, new.inode); + if (unlikely(retval)) + goto end_rename; if (old.dir_bh) { retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9824cd8203e8..a29e8ea1a7ab 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3718,7 +3718,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) int blocksize, clustersize; unsigned int db_count; unsigned int i; - int needs_recovery, has_huge_files, has_bigalloc; + int needs_recovery, has_huge_files; __u64 blocks_count; int err = 0; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; @@ -4010,17 +4010,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n"); + /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); goto failed_mount; } - if (test_opt(sb, DIOREAD_NOLOCK)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and dioread_nolock"); - goto failed_mount; - } if (test_opt(sb, DAX)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dax"); @@ -4237,8 +4233,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Handle clustersize */ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); - has_bigalloc = ext4_has_feature_bigalloc(sb); - if (has_bigalloc) { + if (ext4_has_feature_bigalloc(sb)) { if (clustersize < blocksize) { ext4_msg(sb, KERN_ERR, "cluster size (%d) smaller than " @@ -5925,7 +5920,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL; inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, S_NOATIME | S_IMMUTABLE); - ext4_mark_inode_dirty(handle, inode); + err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); @@ -6027,12 +6022,14 @@ static int ext4_quota_off(struct super_block *sb, int type) * this is not a hard failure and quotas are already disabled. */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); - if (IS_ERR(handle)) + if (IS_ERR(handle)) { + err = PTR_ERR(handle); goto out_unlock; + } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); inode->i_mtime = inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); + err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: inode_unlock(inode); @@ -6090,7 +6087,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); - int err, offset = off & (sb->s_blocksize - 1); + int err = 0, err2 = 0, offset = off & (sb->s_blocksize - 1); int retries = 0; struct buffer_head *bh; handle_t *handle = journal_current_handle(); @@ -6138,9 +6135,11 @@ out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; - ext4_mark_inode_dirty(handle, inode); + err2 = ext4_mark_inode_dirty(handle, inode); + if (unlikely(err2 && !err)) + err = err2; } - return len; + return err ? err : len; } #endif diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 21df43a25328..9b29a40738ac 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1327,7 +1327,7 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, int blocksize = ea_inode->i_sb->s_blocksize; int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits; int csize, wsize = 0; - int ret = 0; + int ret = 0, ret2 = 0; int retries = 0; retry: @@ -1385,7 +1385,9 @@ retry: ext4_update_i_disksize(ea_inode, wsize); inode_unlock(ea_inode); - ext4_mark_inode_dirty(handle, ea_inode); + ret2 = ext4_mark_inode_dirty(handle, ea_inode); + if (unlikely(ret2 && !ret)) + ret = ret2; out: brelse(bh); @@ -1800,8 +1802,11 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, if (EXT4_I(inode)->i_file_acl) { /* The inode already has an extended attribute block. */ bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); - if (IS_ERR(bs->bh)) - return PTR_ERR(bs->bh); + if (IS_ERR(bs->bh)) { + error = PTR_ERR(bs->bh); + bs->bh = NULL; + return error; + } ea_bdebug(bs->bh, "b_count=%d, refcount=%d", atomic_read(&(bs->bh->b_count)), le32_to_cpu(BHDR(bs->bh)->h_refcount)); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 03ec97f28235..072fb19555a8 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -19,6 +19,7 @@ #include <linux/uio.h> #include <linux/cleancache.h> #include <linux/sched/signal.h> +#include <linux/fiemap.h> #include "f2fs.h" #include "node.h" @@ -1824,7 +1825,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return ret; } - ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR); + ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_XATTR); if (ret) return ret; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 4167e5408151..9686ffea177e 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -8,6 +8,7 @@ #include <linux/fs.h> #include <linux/f2fs_fs.h> +#include <linux/fiemap.h> #include "f2fs.h" #include "node.h" diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 3647c65a0f48..bbfe18c07417 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -632,20 +632,80 @@ error: } EXPORT_SYMBOL_GPL(fat_free_clusters); -/* 128kb is the whole sectors for FAT12 and FAT16 */ -#define FAT_READA_SIZE (128 * 1024) +struct fatent_ra { + sector_t cur; + sector_t limit; + + unsigned int ra_blocks; + sector_t ra_advance; + sector_t ra_next; + sector_t ra_limit; +}; -static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent, - unsigned long reada_blocks) +static void fat_ra_init(struct super_block *sb, struct fatent_ra *ra, + struct fat_entry *fatent, int ent_limit) { - const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; - sector_t blocknr; - int i, offset; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + sector_t blocknr, block_end; + int offset; + /* + * This is the sequential read, so ra_pages * 2 (but try to + * align the optimal hardware IO size). + * [BTW, 128kb covers the whole sectors for FAT12 and FAT16] + */ + unsigned long ra_pages = sb->s_bdi->ra_pages; + unsigned int reada_blocks; + if (ra_pages > sb->s_bdi->io_pages) + ra_pages = rounddown(ra_pages, sb->s_bdi->io_pages); + reada_blocks = ra_pages << (PAGE_SHIFT - sb->s_blocksize_bits + 1); + + /* Initialize the range for sequential read */ ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + ops->ent_blocknr(sb, ent_limit - 1, &offset, &block_end); + ra->cur = 0; + ra->limit = (block_end + 1) - blocknr; - for (i = 0; i < reada_blocks; i++) - sb_breadahead(sb, blocknr + i); + /* Advancing the window at half size */ + ra->ra_blocks = reada_blocks >> 1; + ra->ra_advance = ra->cur; + ra->ra_next = ra->cur; + ra->ra_limit = ra->cur + min_t(sector_t, reada_blocks, ra->limit); +} + +/* Assuming to be called before reading a new block (increments ->cur). */ +static void fat_ent_reada(struct super_block *sb, struct fatent_ra *ra, + struct fat_entry *fatent) +{ + if (ra->ra_next >= ra->ra_limit) + return; + + if (ra->cur >= ra->ra_advance) { + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + struct blk_plug plug; + sector_t blocknr, diff; + int offset; + + ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + + diff = blocknr - ra->cur; + blk_start_plug(&plug); + /* + * FIXME: we would want to directly use the bio with + * pages to reduce the number of segments. + */ + for (; ra->ra_next < ra->ra_limit; ra->ra_next++) + sb_breadahead(sb, ra->ra_next + diff); + blk_finish_plug(&plug); + + /* Advance the readahead window */ + ra->ra_advance += ra->ra_blocks; + ra->ra_limit += min_t(sector_t, + ra->ra_blocks, ra->limit - ra->ra_limit); + } + ra->cur++; } int fat_count_free_clusters(struct super_block *sb) @@ -653,27 +713,20 @@ int fat_count_free_clusters(struct super_block *sb) struct msdos_sb_info *sbi = MSDOS_SB(sb); const struct fatent_operations *ops = sbi->fatent_ops; struct fat_entry fatent; - unsigned long reada_blocks, reada_mask, cur_block; + struct fatent_ra fatent_ra; int err = 0, free; lock_fat(sbi); if (sbi->free_clusters != -1 && sbi->free_clus_valid) goto out; - reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; - reada_mask = reada_blocks - 1; - cur_block = 0; - free = 0; fatent_init(&fatent); fatent_set_entry(&fatent, FAT_START_ENT); + fat_ra_init(sb, &fatent_ra, &fatent, sbi->max_cluster); while (fatent.entry < sbi->max_cluster) { /* readahead of fat blocks */ - if ((cur_block & reada_mask) == 0) { - unsigned long rest = sbi->fat_length - cur_block; - fat_ent_reada(sb, &fatent, min(reada_blocks, rest)); - } - cur_block++; + fat_ent_reada(sb, &fatent_ra, &fatent); err = fat_ent_read_block(sb, &fatent); if (err) @@ -707,9 +760,9 @@ int fat_trim_fs(struct inode *inode, struct fstrim_range *range) struct msdos_sb_info *sbi = MSDOS_SB(sb); const struct fatent_operations *ops = sbi->fatent_ops; struct fat_entry fatent; + struct fatent_ra fatent_ra; u64 ent_start, ent_end, minlen, trimmed = 0; u32 free = 0; - unsigned long reada_blocks, reada_mask, cur_block = 0; int err = 0; /* @@ -727,19 +780,13 @@ int fat_trim_fs(struct inode *inode, struct fstrim_range *range) if (ent_end >= sbi->max_cluster) ent_end = sbi->max_cluster - 1; - reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; - reada_mask = reada_blocks - 1; - fatent_init(&fatent); lock_fat(sbi); fatent_set_entry(&fatent, ent_start); + fat_ra_init(sb, &fatent_ra, &fatent, ent_end + 1); while (fatent.entry <= ent_end) { /* readahead of fat blocks */ - if ((cur_block & reada_mask) == 0) { - unsigned long rest = sbi->fat_length - cur_block; - fat_ent_reada(sb, &fatent, min(reada_blocks, rest)); - } - cur_block++; + fat_ent_reada(sb, &fatent_ra, &fatent); err = fat_ent_read_block(sb, &fatent); if (err) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index e6e68b2274a5..a0cf99debb1e 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1519,6 +1519,12 @@ static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, goto out; } + if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of FAT sectors"); + goto out; + } + error = 0; out: diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a750381d554a..a605c3dddabc 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1125,6 +1125,7 @@ void inode_io_list_del(struct inode *inode) inode_io_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); } +EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4907e3d1f56c..8ccc97356cb5 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -840,7 +840,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) get_page(newpage); if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add_file(newpage); + lru_cache_add(newpage); err = 0; spin_lock(&cs->req->waitq.lock); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5acd3ce30759..a1337bf31e49 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -17,6 +17,7 @@ #include <linux/crc32.h> #include <linux/iomap.h> #include <linux/security.h> +#include <linux/fiemap.h> #include <linux/uaccess.h> #include "gfs2.h" diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c index e285d6b3bba4..d39246865c51 100644 --- a/fs/hpfs/buffer.c +++ b/fs/hpfs/buffer.c @@ -53,7 +53,7 @@ void hpfs_prefetch_sectors(struct super_block *s, unsigned secno, int n) return; } brelse(bh); - }; + } blk_start_plug(&plug); while (n > 0) { diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 2de0d3492d15..077c25128eb7 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -9,6 +9,7 @@ #include "hpfs_fn.h" #include <linux/mpage.h> +#include <linux/fiemap.h> #define BLOCKS(size) (((size) + 511) >> 9) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 991c60c7ffe0..f3420a643b4f 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -38,6 +38,7 @@ #include <linux/uio.h> #include <linux/uaccess.h> +#include <linux/sched/mm.h> static const struct super_operations hugetlbfs_ops; static const struct address_space_operations hugetlbfs_aops; @@ -191,13 +192,60 @@ out: #ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA static unsigned long +hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + struct vm_unmapped_area_info info; + + info.flags = 0; + info.length = len; + info.low_limit = current->mm->mmap_base; + info.high_limit = TASK_SIZE; + info.align_mask = PAGE_MASK & ~huge_page_mask(h); + info.align_offset = 0; + return vm_unmapped_area(&info); +} + +static unsigned long +hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + struct vm_unmapped_area_info info; + + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.high_limit = current->mm->mmap_base; + info.align_mask = PAGE_MASK & ~huge_page_mask(h); + info.align_offset = 0; + addr = vm_unmapped_area(&info); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + if (unlikely(offset_in_page(addr))) { + VM_BUG_ON(addr != -ENOMEM); + info.flags = 0; + info.low_limit = current->mm->mmap_base; + info.high_limit = TASK_SIZE; + addr = vm_unmapped_area(&info); + } + + return addr; +} + +static unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; if (len & ~huge_page_mask(h)) return -EINVAL; @@ -218,13 +266,16 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return addr; } - info.flags = 0; - info.length = len; - info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = TASK_SIZE; - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; - return vm_unmapped_area(&info); + /* + * Use mm->get_unmapped_area value as a hint to use topdown routine. + * If architectures have special needs, they should define their own + * version of hugetlb_get_unmapped_area. + */ + if (mm->get_unmapped_area == arch_get_unmapped_area_topdown) + return hugetlb_get_unmapped_area_topdown(file, addr, len, + pgoff, flags); + return hugetlb_get_unmapped_area_bottomup(file, addr, len, + pgoff, flags); } #endif diff --git a/fs/inode.c b/fs/inode.c index 9fcec07a9d7c..72c4c347afb7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -497,7 +497,7 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval) spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); - hlist_add_head(&inode->i_hash, b); + hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } @@ -513,7 +513,7 @@ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); - hlist_del_init(&inode->i_hash); + hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } @@ -1107,7 +1107,7 @@ again: */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; - hlist_add_head(&inode->i_hash, head); + hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); if (!creating) inode_sb_list_add(inode); @@ -1201,7 +1201,7 @@ again: inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; - hlist_add_head(&inode->i_hash, head); + hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); @@ -1244,15 +1244,10 @@ static int test_inode_iunique(struct super_block *sb, unsigned long ino) struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; - spin_lock(&inode_hash_lock); - hlist_for_each_entry(inode, b, i_hash) { - if (inode->i_ino == ino && inode->i_sb == sb) { - spin_unlock(&inode_hash_lock); + hlist_for_each_entry_rcu(inode, b, i_hash) { + if (inode->i_ino == ino && inode->i_sb == sb) return 0; - } } - spin_unlock(&inode_hash_lock); - return 1; } @@ -1281,6 +1276,7 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) static unsigned int counter; ino_t res; + rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) @@ -1288,6 +1284,7 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); + rcu_read_unlock(); return res; } @@ -1456,6 +1453,84 @@ out: } EXPORT_SYMBOL(find_inode_nowait); +/** + * find_inode_rcu - find an inode in the inode cache + * @sb: Super block of file system to search + * @hashval: Key to hash + * @test: Function to test match on an inode + * @data: Data for test function + * + * Search for the inode specified by @hashval and @data in the inode cache, + * where the helper function @test will return 0 if the inode does not match + * and 1 if it does. The @test function must be responsible for taking the + * i_lock spin_lock and checking i_state for an inode being freed or being + * initialized. + * + * If successful, this will return the inode for which the @test function + * returned 1 and NULL otherwise. + * + * The @test function is not permitted to take a ref on any inode presented. + * It is also not permitted to sleep. + * + * The caller must hold the RCU read lock. + */ +struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, + int (*test)(struct inode *, void *), void *data) +{ + struct hlist_head *head = inode_hashtable + hash(sb, hashval); + struct inode *inode; + + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), + "suspicious find_inode_rcu() usage"); + + hlist_for_each_entry_rcu(inode, head, i_hash) { + if (inode->i_sb == sb && + !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && + test(inode, data)) + return inode; + } + return NULL; +} +EXPORT_SYMBOL(find_inode_rcu); + +/** + * find_inode_by_rcu - Find an inode in the inode cache + * @sb: Super block of file system to search + * @ino: The inode number to match + * + * Search for the inode specified by @hashval and @data in the inode cache, + * where the helper function @test will return 0 if the inode does not match + * and 1 if it does. The @test function must be responsible for taking the + * i_lock spin_lock and checking i_state for an inode being freed or being + * initialized. + * + * If successful, this will return the inode for which the @test function + * returned 1 and NULL otherwise. + * + * The @test function is not permitted to take a ref on any inode presented. + * It is also not permitted to sleep. + * + * The caller must hold the RCU read lock. + */ +struct inode *find_inode_by_ino_rcu(struct super_block *sb, + unsigned long ino) +{ + struct hlist_head *head = inode_hashtable + hash(sb, ino); + struct inode *inode; + + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), + "suspicious find_inode_by_ino_rcu() usage"); + + hlist_for_each_entry_rcu(inode, head, i_hash) { + if (inode->i_ino == ino && + inode->i_sb == sb && + !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) + return inode; + } + return NULL; +} +EXPORT_SYMBOL(find_inode_by_ino_rcu); + int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -1480,7 +1555,7 @@ int insert_inode_locked(struct inode *inode) if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; - hlist_add_head(&inode->i_hash, head); + hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; @@ -1540,6 +1615,7 @@ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; + unsigned long state; int drop; WARN_ON(inode->i_state & I_NEW); @@ -1555,16 +1631,20 @@ static void iput_final(struct inode *inode) return; } + state = inode->i_state; if (!drop) { - inode->i_state |= I_WILL_FREE; + WRITE_ONCE(inode->i_state, state | I_WILL_FREE); spin_unlock(&inode->i_lock); + write_inode_now(inode, 1); + spin_lock(&inode->i_lock); - WARN_ON(inode->i_state & I_NEW); - inode->i_state &= ~I_WILL_FREE; + state = inode->i_state; + WARN_ON(state & I_NEW); + state &= ~I_WILL_FREE; } - inode->i_state |= I_FREEING; + WRITE_ONCE(inode->i_state, state | I_FREEING); if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); diff --git a/fs/internal.h b/fs/internal.h index b89d78f10396..9b863a7bd708 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -142,8 +142,6 @@ extern int dentry_needs_remove_privs(struct dentry *dentry); /* * fs-writeback.c */ -extern void inode_io_list_del(struct inode *inode); - extern long get_nr_dirty_inodes(void); extern int invalidate_inodes(struct super_block *, bool); diff --git a/fs/ioctl.c b/fs/ioctl.c index 5e80b40bc1b5..d69786d1dd91 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -18,6 +18,7 @@ #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> +#include <linux/fiemap.h> #include "internal.h" @@ -148,61 +149,55 @@ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, EXPORT_SYMBOL(fiemap_fill_next_extent); /** - * fiemap_check_flags - check validity of requested flags for fiemap + * fiemap_prep - check validity of requested flags for fiemap + * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap - * @fs_flags: Set of fiemap flags that the file system understands + * @start: Start of the mapped range + * @len: Length of the mapped range, can be truncated by this function. + * @supported_flags: Set of fiemap flags that the file system understands * - * Called from file system ->fiemap callback. This will compute the - * intersection of valid fiemap flags and those that the fs supports. That - * value is then compared against the user supplied flags. In case of bad user - * flags, the invalid values will be written into the fieinfo structure, and - * -EBADR is returned, which tells ioctl_fiemap() to return those values to - * userspace. For this reason, a return code of -EBADR should be preserved. + * This function must be called from each ->fiemap instance to validate the + * fiemap request against the file system parameters. * - * Returns 0 on success, -EBADR on bad flags. + * Returns 0 on success, or a negative error on failure. */ -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags) +int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 *len, u32 supported_flags) { + u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; + int ret = 0; - incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags); - if (incompat_flags) { - fieinfo->fi_flags = incompat_flags; - return -EBADR; - } - return 0; -} -EXPORT_SYMBOL(fiemap_check_flags); - -static int fiemap_check_ranges(struct super_block *sb, - u64 start, u64 len, u64 *new_len) -{ - u64 maxbytes = (u64) sb->s_maxbytes; - - *new_len = len; - - if (len == 0) + if (*len == 0) return -EINVAL; - if (start > maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ - if (len > maxbytes || (maxbytes - len) < start) - *new_len = maxbytes - start; + if (*len > maxbytes || (maxbytes - *len) < start) + *len = maxbytes - start; + + supported_flags |= FIEMAP_FLAG_SYNC; + supported_flags &= FIEMAP_FLAGS_COMPAT; + incompat_flags = fieinfo->fi_flags & ~supported_flags; + if (incompat_flags) { + fieinfo->fi_flags = incompat_flags; + return -EBADR; + } - return 0; + if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) + ret = filemap_write_and_wait(inode->i_mapping); + return ret; } +EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); - struct super_block *sb = inode->i_sb; - u64 len; int error; if (!inode->i_op->fiemap) @@ -214,24 +209,13 @@ static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; - error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length, - &len); - if (error) - return error; - fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; - if (fiemap.fm_extent_count != 0 && - !access_ok(fieinfo.fi_extents_start, - fieinfo.fi_extents_max * sizeof(struct fiemap_extent))) - return -EFAULT; - - if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) - filemap_write_and_wait(inode->i_mapping); + error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, + fiemap.fm_length); - error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) @@ -307,8 +291,7 @@ static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) * If you use this function directly, you need to do your own locking. Use * generic_block_fiemap if you want the locking done for you. */ - -int __generic_block_fiemap(struct inode *inode, +static int __generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, get_block_t *get_block) { @@ -320,7 +303,7 @@ int __generic_block_fiemap(struct inode *inode, bool past_eof = false, whole_file = false; int ret = 0; - ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); + ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_SYNC); if (ret) return ret; @@ -453,7 +436,6 @@ int __generic_block_fiemap(struct inode *inode, return ret; } -EXPORT_SYMBOL(__generic_block_fiemap); /** * generic_block_fiemap - FIEMAP for block based inodes diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c index d55e8f491a5e..aab070df4a21 100644 --- a/fs/iomap/fiemap.c +++ b/fs/iomap/fiemap.c @@ -6,6 +6,7 @@ #include <linux/compiler.h> #include <linux/fs.h> #include <linux/iomap.h> +#include <linux/fiemap.h> struct fiemap_ctx { struct fiemap_extent_info *fi; @@ -65,7 +66,7 @@ iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, - loff_t start, loff_t len, const struct iomap_ops *ops) + u64 start, u64 len, const struct iomap_ops *ops) { struct fiemap_ctx ctx; loff_t ret; @@ -74,16 +75,10 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, ctx.fi = fi; ctx.prev.type = IOMAP_HOLE; - ret = fiemap_check_flags(fi, FIEMAP_FLAG_SYNC); + ret = fiemap_prep(inode, fi, start, &len, 0); if (ret) return ret; - if (fi->fi_flags & FIEMAP_FLAG_SYNC) { - ret = filemap_write_and_wait(inode->i_mapping); - if (ret) - return ret; - } - while (len > 0) { ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx, iomap_fiemap_actor); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 3dccc23cf010..e91aad3637a2 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -541,17 +541,24 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) } EXPORT_SYMBOL(jbd2_journal_start); -static void __jbd2_journal_unreserve_handle(handle_t *handle) +static void __jbd2_journal_unreserve_handle(handle_t *handle, transaction_t *t) { journal_t *journal = handle->h_journal; WARN_ON(!handle->h_reserved); sub_reserved_credits(journal, handle->h_total_credits); + if (t) + atomic_sub(handle->h_total_credits, &t->t_outstanding_credits); } void jbd2_journal_free_reserved(handle_t *handle) { - __jbd2_journal_unreserve_handle(handle); + journal_t *journal = handle->h_journal; + + /* Get j_state_lock to pin running transaction if it exists */ + read_lock(&journal->j_state_lock); + __jbd2_journal_unreserve_handle(handle, journal->j_running_transaction); + read_unlock(&journal->j_state_lock); jbd2_free_handle(handle); } EXPORT_SYMBOL(jbd2_journal_free_reserved); @@ -722,7 +729,8 @@ static void stop_this_handle(handle_t *handle) atomic_sub(handle->h_total_credits, &transaction->t_outstanding_credits); if (handle->h_rsv_handle) - __jbd2_journal_unreserve_handle(handle->h_rsv_handle); + __jbd2_journal_unreserve_handle(handle->h_rsv_handle, + transaction); if (atomic_dec_and_test(&transaction->t_updates)) wake_up(&journal->j_wait_updates); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 34366db3620d..fd6ddfe4cd94 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -1010,7 +1010,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { - lockdep_init_map(&kn->dep_map, "kn->count", key, 0); + lockdep_init_map(&kn->dep_map, "kn->active", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif diff --git a/fs/locks.c b/fs/locks.c index 1d4f4d5da704..6fd1f6e83178 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2823,7 +2823,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, { struct inode *inode = NULL; unsigned int fl_pid; - struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; + struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); fl_pid = locks_translate_pid(fl, proc_pidns); /* @@ -2901,7 +2901,7 @@ static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock *fl, *bfl; - struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; + struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); fl = hlist_entry(v, struct file_lock, fl_link); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index ceeb3b441844..28009ec54420 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/uio.h> +#include <linux/fiemap.h> #include "nilfs.h" #include "btnode.h" #include "segment.h" @@ -996,7 +997,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, unsigned int blkbits = inode->i_blkbits; int ret, n; - ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); + ret = fiemap_prep(inode, fieinfo, start, &len, 0); if (ret) return ret; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index c18459cea6f4..85eda539b35f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -70,7 +70,7 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1, return !memcmp(fne1->name, fne2->name, fne1->name_len); } -static bool should_merge(struct fsnotify_event *old_fsn, +static bool fanotify_should_merge(struct fsnotify_event *old_fsn, struct fsnotify_event *new_fsn) { struct fanotify_event *old, *new; @@ -129,7 +129,7 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) return 0; list_for_each_entry_reverse(test_event, list, list) { - if (should_merge(test_event, event)) { + if (fanotify_should_merge(test_event, event)) { FANOTIFY_E(test_event)->mask |= new->mask; return 1; } @@ -232,6 +232,10 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, if (!fsnotify_iter_should_report_type(iter_info, type)) continue; mark = iter_info->marks[type]; + + /* Apply ignore mask regardless of ISDIR and ON_CHILD flags */ + marks_ignored_mask |= mark->ignored_mask; + /* * If the event is on dir and this mark doesn't care about * events on dir, don't send it! @@ -249,7 +253,6 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, continue; marks_mask |= mark->mask; - marks_ignored_mask |= mark->ignored_mask; } test_mask = event_mask & marks_mask & ~marks_ignored_mask; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 35bfbf4a7aac..8ce7ccfc4b0d 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -89,7 +89,7 @@ struct fanotify_name_event { __kernel_fsid_t fsid; struct fanotify_fh dir_fh; u8 name_len; - char name[0]; + char name[]; }; static inline struct fanotify_name_event * diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 42cb794c62ac..63b5dffdca9e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -328,7 +328,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, ret = -EFAULT; /* * Sanity check copy size in case get_one_event() and - * fill_event_metadata() event_len sizes ever get out of sync. + * event_len sizes ever get out of sync. */ if (WARN_ON_ONCE(metadata.event_len > count)) goto out_close_fd; @@ -487,8 +487,10 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t group = file->private_data; - if (count > sizeof(response)) - count = sizeof(response); + if (count < sizeof(response)) + return -EINVAL; + + count = sizeof(response); pr_debug("%s: group=%p count=%zu\n", __func__, group, count); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index ef83f4020554..f0d6b54be412 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -11,7 +11,6 @@ #include <linux/sched.h> #include <linux/types.h> #include <linux/seq_file.h> -#include <linux/proc_fs.h> #include <linux/exportfs.h> #include "inotify/inotify.h" diff --git a/fs/notify/group.c b/fs/notify/group.c index 133f723aca07..a4a4b1c64d32 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -25,6 +25,7 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) group->ops->free_group_priv(group); mem_cgroup_put(group->memcg); + mutex_destroy(&group->mark_mutex); kfree(group); } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 81ffc8629fc4..f88bbcc9efeb 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -764,20 +764,18 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd) struct fsnotify_group *group; struct inotify_inode_mark *i_mark; struct fd f; - int ret = 0; + int ret = -EINVAL; f = fdget(fd); if (unlikely(!f.file)) return -EBADF; /* verify that this is indeed an inotify instance */ - ret = -EINVAL; if (unlikely(f.file->f_op != &inotify_fops)) goto out; group = f.file->private_data; - ret = -EINVAL; i_mark = inotify_idr_find(group, wd); if (unlikely(!i_mark)) goto out; diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 1d96216dffd1..8387937b9d01 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -325,13 +325,16 @@ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) + __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_obj_type(type) { /* This can fail if mark is being removed */ - if (!fsnotify_get_mark_safe(iter_info->marks[type])) + if (!fsnotify_get_mark_safe(iter_info->marks[type])) { + __release(&fsnotify_mark_srcu); goto fail; + } } /* @@ -350,6 +353,7 @@ fail: } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) + __acquires(&fsnotify_mark_srcu) { int type; diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index e3e2d1b2af51..a94852af5510 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -733,8 +733,6 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, return 0; } -#define OCFS2_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC) - int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 map_start, u64 map_len) { @@ -746,7 +744,7 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, struct buffer_head *di_bh = NULL; struct ocfs2_extent_rec rec; - ret = fiemap_check_flags(fieinfo, OCFS2_FIEMAP_FLAGS); + ret = fiemap_prep(inode, fieinfo, map_start, &map_len, 0); if (ret) return ret; diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 2bb916d68576..538e839590ef 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -168,10 +168,7 @@ static DEFINE_SPINLOCK(orangefs_bufmap_lock); static void orangefs_bufmap_unmap(struct orangefs_bufmap *bufmap) { - int i; - - for (i = 0; i < bufmap->page_count; i++) - put_page(bufmap->page_array[i]); + unpin_user_pages(bufmap->page_array, bufmap->page_count); } static void @@ -268,7 +265,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap, int offset = 0, ret, i; /* map the pages */ - ret = get_user_pages_fast((unsigned long)user_desc->ptr, + ret = pin_user_pages_fast((unsigned long)user_desc->ptr, bufmap->page_count, FOLL_WRITE, bufmap->page_array); if (ret < 0) @@ -280,7 +277,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap, for (i = 0; i < ret; i++) { SetPageError(bufmap->page_array[i]); - put_page(bufmap->page_array[i]); + unpin_user_page(bufmap->page_array[i]); } return -ENOMEM; } diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index c010c1fddafc..289b648ae196 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -79,7 +79,7 @@ DECLARE_WAIT_QUEUE_HEAD(orangefs_request_list_waitq); static int __init orangefs_init(void) { - int ret = -1; + int ret; __u32 i = 0; if (op_timeout_secs < 0) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 981f11ec51bc..7af76b9004eb 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -10,6 +10,7 @@ #include <linux/xattr.h> #include <linux/posix_acl.h> #include <linux/ratelimit.h> +#include <linux/fiemap.h> #include "overlayfs.h" @@ -479,10 +480,6 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return -EOPNOTSUPP; old_cred = ovl_override_creds(inode->i_sb); - - if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) - filemap_write_and_wait(realinode->i_mapping); - err = realinode->i_op->fiemap(realinode, fieinfo, start, len); revert_creds(old_cred); diff --git a/fs/proc/array.c b/fs/proc/array.c index 8e16f14bb05a..713ffac59bbb 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -248,8 +248,8 @@ void render_sigset_t(struct seq_file *m, const char *header, seq_putc(m, '\n'); } -static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, - sigset_t *catch) +static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *sigign, + sigset_t *sigcatch) { struct k_sigaction *k; int i; @@ -257,9 +257,9 @@ static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, k = p->sighand->action; for (i = 1; i <= _NSIG; ++i, ++k) { if (k->sa.sa_handler == SIG_IGN) - sigaddset(ign, i); + sigaddset(sigign, i); else if (k->sa.sa_handler != SIG_DFL) - sigaddset(catch, i); + sigaddset(sigcatch, i); } } @@ -728,7 +728,7 @@ static int children_seq_show(struct seq_file *seq, void *v) { struct inode *inode = file_inode(seq->file); - seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode))); + seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode->i_sb))); return 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index eb2255e95f62..066d9c0f4664 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -697,13 +697,21 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) * May current process learn task's sched/cmdline info (for hide_pid_min=1) * or euid/egid (for hide_pid_min=2)? */ -static bool has_pid_permissions(struct pid_namespace *pid, +static bool has_pid_permissions(struct proc_fs_info *fs_info, struct task_struct *task, - int hide_pid_min) + enum proc_hidepid hide_pid_min) { - if (pid->hide_pid < hide_pid_min) + /* + * If 'hidpid' mount option is set force a ptrace check, + * we indicate that we are using a filesystem syscall + * by passing PTRACE_MODE_READ_FSCREDS + */ + if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) + return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); + + if (fs_info->hide_pid < hide_pid_min) return true; - if (in_group_p(pid->pid_gid)) + if (in_group_p(fs_info->pid_gid)) return true; return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } @@ -711,18 +719,18 @@ static bool has_pid_permissions(struct pid_namespace *pid, static int proc_pid_permission(struct inode *inode, int mask) { - struct pid_namespace *pid = proc_pid_ns(inode); + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; bool has_perms; task = get_proc_task(inode); if (!task) return -ESRCH; - has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS); + has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { - if (pid->hide_pid == HIDEPID_INVISIBLE) { + if (fs_info->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process @@ -746,7 +754,7 @@ static const struct inode_operations proc_def_inode_operations = { static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct pid_namespace *ns = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; @@ -1415,7 +1423,7 @@ static const struct file_operations proc_fail_nth_operations = { static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct pid_namespace *ns = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct task_struct *p; p = get_proc_task(inode); @@ -1909,7 +1917,7 @@ int pid_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); - struct pid_namespace *pid = proc_pid_ns(inode); + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; generic_fillattr(inode, stat); @@ -1919,7 +1927,7 @@ int pid_getattr(const struct path *path, struct kstat *stat, rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { - if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) { + if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, @@ -2470,7 +2478,7 @@ static int proc_timers_open(struct inode *inode, struct file *file) return -ENOMEM; tp->pid = proc_pid(inode); - tp->ns = proc_pid_ns(inode); + tp->ns = proc_pid_ns(inode->i_sb); return 0; } @@ -2770,6 +2778,15 @@ static const struct pid_entry smack_attr_dir_stuff[] = { LSM_DIR_OPS(smack); #endif +#ifdef CONFIG_SECURITY_APPARMOR +static const struct pid_entry apparmor_attr_dir_stuff[] = { + ATTR("apparmor", "current", 0666), + ATTR("apparmor", "prev", 0444), + ATTR("apparmor", "exec", 0666), +}; +LSM_DIR_OPS(apparmor); +#endif + static const struct pid_entry attr_dir_stuff[] = { ATTR(NULL, "current", 0666), ATTR(NULL, "prev", 0444), @@ -2781,6 +2798,10 @@ static const struct pid_entry attr_dir_stuff[] = { DIR("smack", 0555, proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), #endif +#ifdef CONFIG_SECURITY_APPARMOR + DIR("apparmor", 0555, + proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops), +#endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) @@ -3312,6 +3333,7 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; + struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); @@ -3319,7 +3341,8 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) if (tgid == ~0U) goto out; - ns = dentry->d_sb->s_fs_info; + fs_info = proc_sb_info(dentry->d_sb); + ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tgid, ns); if (task) @@ -3328,7 +3351,14 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) if (!task) goto out; + /* Limit procfs to only ptraceable tasks */ + if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) { + if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS)) + goto out_put_task; + } + result = proc_pid_instantiate(dentry, task, NULL); +out_put_task: put_task_struct(task); out: return result; @@ -3354,20 +3384,8 @@ retry: pid = find_ge_pid(iter.tgid, ns); if (pid) { iter.tgid = pid_nr_ns(pid, ns); - iter.task = pid_task(pid, PIDTYPE_PID); - /* What we to know is if the pid we have find is the - * pid of a thread_group_leader. Testing for task - * being a thread_group_leader is the obvious thing - * todo but there is a window when it fails, due to - * the pid transfer logic in de_thread. - * - * So we perform the straight forward test of seeing - * if the pid we have found is the pid of a thread - * group leader, and don't worry if the task we have - * found doesn't happen to be a thread group leader. - * As we don't care in the case of readdir. - */ - if (!iter.task || !has_group_leader_pid(iter.task)) { + iter.task = pid_task(pid, PIDTYPE_TGID); + if (!iter.task) { iter.tgid += 1; goto retry; } @@ -3383,20 +3401,21 @@ retry: int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; - struct pid_namespace *ns = proc_pid_ns(file_inode(file)); + struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb); + struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; if (pos == TGID_OFFSET - 2) { - struct inode *inode = d_inode(ns->proc_self); + struct inode *inode = d_inode(fs_info->proc_self); if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } if (pos == TGID_OFFSET - 1) { - struct inode *inode = d_inode(ns->proc_thread_self); + struct inode *inode = d_inode(fs_info->proc_thread_self); if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; @@ -3410,7 +3429,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) unsigned int len; cond_resched(); - if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE)) + if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%u", iter.tgid); @@ -3610,6 +3629,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; + struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); @@ -3620,7 +3640,8 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry if (tid == ~0U) goto out; - ns = dentry->d_sb->s_fs_info; + fs_info = proc_sb_info(dentry->d_sb); + ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tid, ns); if (task) @@ -3734,7 +3755,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - ns = proc_pid_ns(inode); + ns = proc_pid_ns(inode->i_sb); tid = (int)file->f_version; file->f_version = 0; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 4ed6dabdf6ff..2f9fa179194d 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -269,6 +269,11 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { + struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb); + + if (fs_info->pidonly == PROC_PIDONLY_ON) + return ERR_PTR(-ENOENT); + return proc_lookup_de(dir, dentry, PDE(dir)); } @@ -325,6 +330,10 @@ int proc_readdir_de(struct file *file, struct dir_context *ctx, int proc_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); + + if (fs_info->pidonly == PROC_PIDONLY_ON) + return 1; return proc_readdir_de(file, ctx, PDE(inode)); } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index fb4cace9ea41..f40c2532c057 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -24,6 +24,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/mount.h> +#include <linux/bug.h> #include <linux/uaccess.h> @@ -165,15 +166,28 @@ void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock deactivate_super(old_sb); } +static inline const char *hidepid2str(enum proc_hidepid v) +{ + switch (v) { + case HIDEPID_OFF: return "off"; + case HIDEPID_NO_ACCESS: return "noaccess"; + case HIDEPID_INVISIBLE: return "invisible"; + case HIDEPID_NOT_PTRACEABLE: return "ptraceable"; + } + WARN_ONCE(1, "bad hide_pid value: %d\n", v); + return "unknown"; +} + static int proc_show_options(struct seq_file *seq, struct dentry *root) { - struct super_block *sb = root->d_sb; - struct pid_namespace *pid = sb->s_fs_info; + struct proc_fs_info *fs_info = proc_sb_info(root->d_sb); - if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID)) - seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid)); - if (pid->hide_pid != HIDEPID_OFF) - seq_printf(seq, ",hidepid=%u", pid->hide_pid); + if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid)); + if (fs_info->hide_pid != HIDEPID_OFF) + seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid)); + if (fs_info->pidonly != PROC_PIDONLY_OFF) + seq_printf(seq, ",subset=pid"); return 0; } @@ -464,6 +478,7 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, static int proc_reg_open(struct inode *inode, struct file *file) { + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct proc_dir_entry *pde = PDE(inode); int rv = 0; typeof_member(struct proc_ops, proc_open) open; @@ -477,6 +492,9 @@ static int proc_reg_open(struct inode *inode, struct file *file) return rv; } + if (fs_info->pidonly == PROC_PIDONLY_ON) + return -ENOENT; + /* * Ensure that * 1) PDE's ->release hook will be called no matter what diff --git a/fs/proc/root.c b/fs/proc/root.c index cdbe9293ea55..ffebed1999e5 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -32,21 +32,86 @@ struct proc_fs_context { struct pid_namespace *pid_ns; unsigned int mask; - int hidepid; + enum proc_hidepid hidepid; int gid; + enum proc_pidonly pidonly; }; enum proc_param { Opt_gid, Opt_hidepid, + Opt_subset, }; static const struct fs_parameter_spec proc_fs_parameters[] = { fsparam_u32("gid", Opt_gid), - fsparam_u32("hidepid", Opt_hidepid), + fsparam_string("hidepid", Opt_hidepid), + fsparam_string("subset", Opt_subset), {} }; +static inline int valid_hidepid(unsigned int value) +{ + return (value == HIDEPID_OFF || + value == HIDEPID_NO_ACCESS || + value == HIDEPID_INVISIBLE || + value == HIDEPID_NOT_PTRACEABLE); +} + +static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct proc_fs_context *ctx = fc->fs_private; + struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid); + struct fs_parse_result result; + int base = (unsigned long)hidepid_u32_spec.data; + + if (param->type != fs_value_is_string) + return invalf(fc, "proc: unexpected type of hidepid value\n"); + + if (!kstrtouint(param->string, base, &result.uint_32)) { + if (!valid_hidepid(result.uint_32)) + return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); + ctx->hidepid = result.uint_32; + return 0; + } + + if (!strcmp(param->string, "off")) + ctx->hidepid = HIDEPID_OFF; + else if (!strcmp(param->string, "noaccess")) + ctx->hidepid = HIDEPID_NO_ACCESS; + else if (!strcmp(param->string, "invisible")) + ctx->hidepid = HIDEPID_INVISIBLE; + else if (!strcmp(param->string, "ptraceable")) + ctx->hidepid = HIDEPID_NOT_PTRACEABLE; + else + return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); + + return 0; +} + +static int proc_parse_subset_param(struct fs_context *fc, char *value) +{ + struct proc_fs_context *ctx = fc->fs_private; + + while (value) { + char *ptr = strchr(value, ','); + + if (ptr != NULL) + *ptr++ = '\0'; + + if (*value != '\0') { + if (!strcmp(value, "pid")) { + ctx->pidonly = PROC_PIDONLY_ON; + } else { + return invalf(fc, "proc: unsupported subset option - %s\n", value); + } + } + value = ptr; + } + + return 0; +} + static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; @@ -63,10 +128,13 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_hidepid: - ctx->hidepid = result.uint_32; - if (ctx->hidepid < HIDEPID_OFF || - ctx->hidepid > HIDEPID_INVISIBLE) - return invalfc(fc, "hidepid value must be between 0 and 2.\n"); + if (proc_parse_hidepid_param(fc, param)) + return -EINVAL; + break; + + case Opt_subset: + if (proc_parse_subset_param(fc, param->string) < 0) + return -EINVAL; break; default: @@ -77,26 +145,33 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) return 0; } -static void proc_apply_options(struct super_block *s, +static void proc_apply_options(struct proc_fs_info *fs_info, struct fs_context *fc, - struct pid_namespace *pid_ns, struct user_namespace *user_ns) { struct proc_fs_context *ctx = fc->fs_private; if (ctx->mask & (1 << Opt_gid)) - pid_ns->pid_gid = make_kgid(user_ns, ctx->gid); + fs_info->pid_gid = make_kgid(user_ns, ctx->gid); if (ctx->mask & (1 << Opt_hidepid)) - pid_ns->hide_pid = ctx->hidepid; + fs_info->hide_pid = ctx->hidepid; + if (ctx->mask & (1 << Opt_subset)) + fs_info->pidonly = ctx->pidonly; } static int proc_fill_super(struct super_block *s, struct fs_context *fc) { - struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info); + struct proc_fs_context *ctx = fc->fs_private; struct inode *root_inode; + struct proc_fs_info *fs_info; int ret; - proc_apply_options(s, fc, pid_ns, current_user_ns()); + fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL); + if (!fs_info) + return -ENOMEM; + + fs_info->pid_ns = get_pid_ns(ctx->pid_ns); + proc_apply_options(fs_info, fc, current_user_ns()); /* User space would break if executables or devices appear on proc */ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV; @@ -106,6 +181,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) s->s_magic = PROC_SUPER_MAGIC; s->s_op = &proc_sops; s->s_time_gran = 1; + s->s_fs_info = fs_info; /* * procfs isn't actually a stacking filesystem; however, there is @@ -113,7 +189,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) * top of it */ s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; - + /* procfs dentries and inodes don't require IO to create */ s->s_shrink.seeks = 0; @@ -140,19 +216,17 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) static int proc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; - struct pid_namespace *pid = sb->s_fs_info; + struct proc_fs_info *fs_info = proc_sb_info(sb); sync_filesystem(sb); - proc_apply_options(sb, fc, pid, current_user_ns()); + proc_apply_options(fs_info, fc, current_user_ns()); return 0; } static int proc_get_tree(struct fs_context *fc) { - struct proc_fs_context *ctx = fc->fs_private; - - return get_tree_keyed(fc, proc_fill_super, ctx->pid_ns); + return get_tree_nodev(fc, proc_fill_super); } static void proc_fs_context_free(struct fs_context *fc) @@ -188,22 +262,17 @@ static int proc_init_fs_context(struct fs_context *fc) static void proc_kill_sb(struct super_block *sb) { - struct pid_namespace *ns; + struct proc_fs_info *fs_info = proc_sb_info(sb); - ns = (struct pid_namespace *)sb->s_fs_info; - if (ns->proc_self) - dput(ns->proc_self); - if (ns->proc_thread_self) - dput(ns->proc_thread_self); - kill_anon_super(sb); + if (fs_info->proc_self) + dput(fs_info->proc_self); - /* Make the pid namespace safe for the next mount of proc */ - ns->proc_self = NULL; - ns->proc_thread_self = NULL; - ns->pid_gid = GLOBAL_ROOT_GID; - ns->hide_pid = 0; + if (fs_info->proc_thread_self) + dput(fs_info->proc_thread_self); - put_pid_ns(ns); + kill_anon_super(sb); + put_pid_ns(fs_info->pid_ns); + kfree(fs_info); } static struct file_system_type proc_fs_type = { diff --git a/fs/proc/self.c b/fs/proc/self.c index 57c0a1047250..ca5158fa561c 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -12,7 +12,7 @@ static const char *proc_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct pid_namespace *ns = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); char *name; @@ -36,10 +36,10 @@ static unsigned self_inum __ro_after_init; int proc_setup_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); - struct pid_namespace *ns = proc_pid_ns(root_inode); + struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *self; int ret = -ENOMEM; - + inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); if (self) { @@ -62,7 +62,7 @@ int proc_setup_self(struct super_block *s) if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); else - ns->proc_self = self; + fs_info->proc_self = self; return ret; } diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index f61ae53533f5..ac284f409568 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -12,7 +12,7 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct pid_namespace *ns = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; @@ -36,7 +36,7 @@ static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); - struct pid_namespace *ns = proc_pid_ns(root_inode); + struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *thread_self; int ret = -ENOMEM; @@ -60,9 +60,9 @@ int proc_setup_thread_self(struct super_block *s) inode_unlock(root_inode); if (ret) - pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); + pr_err("proc_fill_super: can't allocate /proc/thread-self\n"); else - ns->proc_thread_self = thread_self; + fs_info->proc_thread_self = thread_self; return ret; } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index e4d70c0dffe9..3059a9394c2d 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -37,23 +37,23 @@ static __poll_t mounts_poll(struct file *file, poll_table *wait) return res; } -struct proc_fs_info { +struct proc_fs_opts { int flag; const char *str; }; static int show_sb_opts(struct seq_file *m, struct super_block *sb) { - static const struct proc_fs_info fs_info[] = { + static const struct proc_fs_opts fs_opts[] = { { SB_SYNCHRONOUS, ",sync" }, { SB_DIRSYNC, ",dirsync" }, { SB_MANDLOCK, ",mand" }, { SB_LAZYTIME, ",lazytime" }, { 0, NULL } }; - const struct proc_fs_info *fs_infop; + const struct proc_fs_opts *fs_infop; - for (fs_infop = fs_info; fs_infop->flag; fs_infop++) { + for (fs_infop = fs_opts; fs_infop->flag; fs_infop++) { if (sb->s_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } @@ -63,7 +63,7 @@ static int show_sb_opts(struct seq_file *m, struct super_block *sb) static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) { - static const struct proc_fs_info mnt_info[] = { + static const struct proc_fs_opts mnt_opts[] = { { MNT_NOSUID, ",nosuid" }, { MNT_NODEV, ",nodev" }, { MNT_NOEXEC, ",noexec" }, @@ -72,9 +72,9 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) { MNT_RELATIME, ",relatime" }, { 0, NULL } }; - const struct proc_fs_info *fs_infop; + const struct proc_fs_opts *fs_infop; - for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) { + for (fs_infop = mnt_opts; fs_infop->flag; fs_infop++) { if (mnt->mnt_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 0031070b3692..1509775da040 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1066,7 +1066,7 @@ research: } else { /* paste hole to the indirect item */ /* - * If kmalloc failed, max_to_insert becomes + * If kcalloc failed, max_to_insert becomes * zero and it means we only have space for * one block */ diff --git a/fs/seq_file.c b/fs/seq_file.c index 70f5fdf99bf6..4e6239f33c06 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -6,6 +6,8 @@ * initial implementation -- AV, Oct 2001. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/cache.h> #include <linux/fs.h> #include <linux/export.h> @@ -233,9 +235,8 @@ Fill: p = m->op->next(m, p, &m->index); if (pos == m->index) { - pr_info_ratelimited("buggy seq_file .next function %ps " - "did not updated position index\n", - m->op->next); + pr_info_ratelimited("buggy .next function %ps did not update position index\n", + m->op->next); m->index++; } if (!p || IS_ERR(p)) { diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index f275fcda62fb..eb6897ab78e7 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -492,6 +492,7 @@ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) kernfs_put(kn); return ret; } +EXPORT_SYMBOL_GPL(sysfs_remove_file_self); void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index d66528fa3657..202b2c0a9e9d 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -25,6 +25,7 @@ #include <linux/posix_acl.h> #include <linux/security.h> #include <linux/iversion.h> +#include <linux/fiemap.h> /* * Directories have different lock order w.r.t. mmap_sem compared to regular diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index d79b821ed1c7..07bc42d62673 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1330,7 +1330,7 @@ static int zonefs_read_super(struct super_block *sb) goto unmap; } - uuid_copy(&sbi->s_uuid, (uuid_t *)super->s_uuid); + import_uuid(&sbi->s_uuid, super->s_uuid); ret = 0; unmap: |