diff options
author | José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-11 10:41:07 +0300 |
---|---|---|
committer | José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-13 08:17:18 +0300 |
commit | e09b41010ba33a20a87472ee821fa407a5b8da36 (patch) | |
tree | d10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/fs/nfsd | |
parent | f93b97fd65072de626c074dbe099a1fff05ce060 (diff) |
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page.
During the rebasing, the following patch collided:
Force tick interrupt and get rid of softirq magic(I70131fb85).
Collisions have been removed because its logic was found on the
source already.
Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/fs/nfsd')
29 files changed, 741 insertions, 629 deletions
diff --git a/kernel/fs/nfsd/blocklayout.c b/kernel/fs/nfsd/blocklayout.c index cdefaa331..c29d9421b 100644 --- a/kernel/fs/nfsd/blocklayout.c +++ b/kernel/fs/nfsd/blocklayout.c @@ -56,14 +56,6 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, u32 device_generation = 0; int error; - /* - * We do not attempt to support I/O smaller than the fs block size, - * or not aligned to it. - */ - if (args->lg_minlength < block_size) { - dprintk("pnfsd: I/O too small\n"); - goto out_layoutunavailable; - } if (seg->offset & (block_size - 1)) { dprintk("pnfsd: I/O misaligned\n"); goto out_layoutunavailable; diff --git a/kernel/fs/nfsd/blocklayoutxdr.c b/kernel/fs/nfsd/blocklayoutxdr.c index 9aa2796da..6d834dc9b 100644 --- a/kernel/fs/nfsd/blocklayoutxdr.c +++ b/kernel/fs/nfsd/blocklayoutxdr.c @@ -101,7 +101,7 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, } nr_iomaps = be32_to_cpup(p++); - expected = sizeof(__be32) + nr_iomaps * NFS4_BLOCK_EXTENT_SIZE; + expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE; if (len != expected) { dprintk("%s: extent array size mismatch: %u/%u\n", __func__, len, expected); diff --git a/kernel/fs/nfsd/blocklayoutxdr.h b/kernel/fs/nfsd/blocklayoutxdr.h index fdc79037c..6de925fe8 100644 --- a/kernel/fs/nfsd/blocklayoutxdr.h +++ b/kernel/fs/nfsd/blocklayoutxdr.h @@ -7,13 +7,6 @@ struct iomap; struct xdr_stream; -enum pnfs_block_extent_state { - PNFS_BLOCK_READWRITE_DATA = 0, - PNFS_BLOCK_READ_DATA = 1, - PNFS_BLOCK_INVALID_DATA = 2, - PNFS_BLOCK_NONE_DATA = 3, -}; - struct pnfs_block_extent { struct nfsd4_deviceid vol_id; u64 foff; @@ -21,14 +14,6 @@ struct pnfs_block_extent { u64 soff; enum pnfs_block_extent_state es; }; -#define NFS4_BLOCK_EXTENT_SIZE 44 - -enum pnfs_block_volume_type { - PNFS_BLOCK_VOLUME_SIMPLE = 0, - PNFS_BLOCK_VOLUME_SLICE = 1, - PNFS_BLOCK_VOLUME_CONCAT = 2, - PNFS_BLOCK_VOLUME_STRIPE = 3, -}; /* * Random upper cap for the uuid length to avoid unbounded allocation. diff --git a/kernel/fs/nfsd/export.c b/kernel/fs/nfsd/export.c index f79521a59..b4d84b579 100644 --- a/kernel/fs/nfsd/export.c +++ b/kernel/fs/nfsd/export.c @@ -1075,73 +1075,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) return rv; } -/* Iterator */ - -static void *e_start(struct seq_file *m, loff_t *pos) - __acquires(((struct cache_detail *)m->private)->hash_lock) -{ - loff_t n = *pos; - unsigned hash, export; - struct cache_head *ch; - struct cache_detail *cd = m->private; - struct cache_head **export_table = cd->hash_table; - - read_lock(&cd->hash_lock); - if (!n--) - return SEQ_START_TOKEN; - hash = n >> 32; - export = n & ((1LL<<32) - 1); - - - for (ch=export_table[hash]; ch; ch=ch->next) - if (!export--) - return ch; - n &= ~((1LL<<32) - 1); - do { - hash++; - n += 1LL<<32; - } while(hash < EXPORT_HASHMAX && export_table[hash]==NULL); - if (hash >= EXPORT_HASHMAX) - return NULL; - *pos = n+1; - return export_table[hash]; -} - -static void *e_next(struct seq_file *m, void *p, loff_t *pos) -{ - struct cache_head *ch = p; - int hash = (*pos >> 32); - struct cache_detail *cd = m->private; - struct cache_head **export_table = cd->hash_table; - - if (p == SEQ_START_TOKEN) - hash = 0; - else if (ch->next == NULL) { - hash++; - *pos += 1LL<<32; - } else { - ++*pos; - return ch->next; - } - *pos &= ~((1LL<<32) - 1); - while (hash < EXPORT_HASHMAX && export_table[hash] == NULL) { - hash++; - *pos += 1LL<<32; - } - if (hash >= EXPORT_HASHMAX) - return NULL; - ++*pos; - return export_table[hash]; -} - -static void e_stop(struct seq_file *m, void *p) - __releases(((struct cache_detail *)m->private)->hash_lock) -{ - struct cache_detail *cd = m->private; - - read_unlock(&cd->hash_lock); -} - static struct flags { int flag; char *name[2]; @@ -1270,9 +1203,9 @@ static int e_show(struct seq_file *m, void *p) } const struct seq_operations nfs_exports_op = { - .start = e_start, - .next = e_next, - .stop = e_stop, + .start = cache_seq_start, + .next = cache_seq_next, + .stop = cache_seq_stop, .show = e_show, }; diff --git a/kernel/fs/nfsd/export.h b/kernel/fs/nfsd/export.h index 1f52bfcc4..2e315072b 100644 --- a/kernel/fs/nfsd/export.h +++ b/kernel/fs/nfsd/export.h @@ -6,6 +6,7 @@ #include <linux/sunrpc/cache.h> #include <uapi/linux/nfsd/export.h> +#include <linux/nfs4.h> struct knfsd_fh; struct svc_fh; diff --git a/kernel/fs/nfsd/idmap.h b/kernel/fs/nfsd/idmap.h index a3f349000..23cc85d1e 100644 --- a/kernel/fs/nfsd/idmap.h +++ b/kernel/fs/nfsd/idmap.h @@ -37,9 +37,7 @@ #include <linux/in.h> #include <linux/sunrpc/svc.h> - -/* XXX from linux/nfs_idmap.h */ -#define IDMAP_NAMESZ 128 +#include <linux/nfs_idmap.h> #ifdef CONFIG_NFSD_V4 int nfsd_idmap_init(struct net *); diff --git a/kernel/fs/nfsd/netns.h b/kernel/fs/nfsd/netns.h index ea6749a32..d8b16c256 100644 --- a/kernel/fs/nfsd/netns.h +++ b/kernel/fs/nfsd/netns.h @@ -110,6 +110,7 @@ struct nfsd_net { unsigned int max_connections; u32 clientid_counter; + u32 clverifier_counter; struct svc_serv *nfsd_serv; }; diff --git a/kernel/fs/nfsd/nfs2acl.c b/kernel/fs/nfsd/nfs2acl.c index d54701f6d..1580ea6fd 100644 --- a/kernel/fs/nfsd/nfs2acl.c +++ b/kernel/fs/nfsd/nfs2acl.c @@ -44,13 +44,13 @@ static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp, inode = d_inode(fh->fh_dentry); - if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT)) + if (argp->mask & ~NFS_ACL_MASK) RETURN_STATUS(nfserr_inval); resp->mask = argp->mask; nfserr = fh_getattr(fh, &resp->stat); if (nfserr) - goto fail; + RETURN_STATUS(nfserr); if (resp->mask & (NFS_ACL|NFS_ACLCNT)) { acl = get_acl(inode, ACL_TYPE_ACCESS); @@ -202,7 +202,7 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, if (!p) return 0; argp->mask = ntohl(*p++); - if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) || + if (argp->mask & ~NFS_ACL_MASK || !xdr_argsize_check(rqstp, p)) return 0; @@ -293,9 +293,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, resp->acl_default, resp->mask & NFS_DFACL, NFS_ACL_DEFAULT); - if (n <= 0) - return 0; - return 1; + return (n > 0); } static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p, diff --git a/kernel/fs/nfsd/nfs3acl.c b/kernel/fs/nfsd/nfs3acl.c index 882b1a14b..01df4cd7c 100644 --- a/kernel/fs/nfsd/nfs3acl.c +++ b/kernel/fs/nfsd/nfs3acl.c @@ -41,7 +41,7 @@ static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp, inode = d_inode(fh->fh_dentry); - if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT)) + if (argp->mask & ~NFS_ACL_MASK) RETURN_STATUS(nfserr_inval); resp->mask = argp->mask; @@ -148,7 +148,7 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, if (!p) return 0; args->mask = ntohl(*p++); - if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) || + if (args->mask & ~NFS_ACL_MASK || !xdr_argsize_check(rqstp, p)) return 0; diff --git a/kernel/fs/nfsd/nfs3xdr.c b/kernel/fs/nfsd/nfs3xdr.c index e4b2b4322..00575d776 100644 --- a/kernel/fs/nfsd/nfs3xdr.c +++ b/kernel/fs/nfsd/nfs3xdr.c @@ -262,11 +262,11 @@ void fill_post_wcc(struct svc_fh *fhp) err = fh_getattr(fhp, &fhp->fh_post_attr); fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version; if (err) { - fhp->fh_post_saved = 0; + fhp->fh_post_saved = false; /* Grab the ctime anyway - set_change_info might use it */ fhp->fh_post_attr.ctime = d_inode(fhp->fh_dentry)->i_ctime; } else - fhp->fh_post_saved = 1; + fhp->fh_post_saved = true; } /* @@ -805,7 +805,7 @@ encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, static __be32 compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, - const char *name, int namlen) + const char *name, int namlen, u64 ino) { struct svc_export *exp; struct dentry *dparent, *dchild; @@ -830,19 +830,21 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, goto out; if (d_really_is_negative(dchild)) goto out; + if (dchild->d_inode->i_ino != ino) + goto out; rv = fh_compose(fhp, exp, dchild, &cd->fh); out: dput(dchild); return rv; } -static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen) +static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen, u64 ino) { struct svc_fh *fh = &cd->scratch; __be32 err; fh_init(fh, NFS3_FHSIZE); - err = compose_entry_fh(cd, fh, name, namlen); + err = compose_entry_fh(cd, fh, name, namlen, ino); if (err) { *p++ = 0; *p++ = 0; @@ -927,7 +929,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, p = encode_entry_baggage(cd, p, name, namlen, ino); if (plus) - p = encode_entryplus_baggage(cd, p, name, namlen); + p = encode_entryplus_baggage(cd, p, name, namlen, ino); num_entry_words = p - cd->buffer; } else if (*(page+1) != NULL) { /* temporarily encode entry into next page, then move back to @@ -941,7 +943,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, p1 = encode_entry_baggage(cd, p1, name, namlen, ino); if (plus) - p1 = encode_entryplus_baggage(cd, p1, name, namlen); + p1 = encode_entryplus_baggage(cd, p1, name, namlen, ino); /* determine entry word length and lengths to go in pages */ num_entry_words = p1 - tmp; diff --git a/kernel/fs/nfsd/nfs4acl.c b/kernel/fs/nfsd/nfs4acl.c index 67242bf7c..6adabd604 100644 --- a/kernel/fs/nfsd/nfs4acl.c +++ b/kernel/fs/nfsd/nfs4acl.c @@ -34,8 +34,10 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/fs.h> #include <linux/slab.h> -#include <linux/nfs_fs.h> +#include <linux/posix_acl.h> + #include "nfsfh.h" #include "nfsd.h" #include "acl.h" @@ -52,10 +54,6 @@ #define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE) #define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL) -/* We don't support these bits; insist they be neither allowed nor denied */ -#define NFS4_MASK_UNSUPP (NFS4_ACE_DELETE | NFS4_ACE_WRITE_OWNER \ - | NFS4_ACE_READ_NAMED_ATTRS | NFS4_ACE_WRITE_NAMED_ATTRS) - /* flags used to simulate posix default ACLs */ #define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \ | NFS4_ACE_DIRECTORY_INHERIT_ACE) @@ -64,9 +62,6 @@ | NFS4_ACE_INHERIT_ONLY_ACE \ | NFS4_ACE_IDENTIFIER_GROUP) -#define MASK_EQUAL(mask1, mask2) \ - ( ((mask1) & NFS4_ACE_MASK_ALL) == ((mask2) & NFS4_ACE_MASK_ALL) ) - static u32 mask_from_posix(unsigned short perm, unsigned int flags) { @@ -107,7 +102,7 @@ deny_mask_from_posix(unsigned short perm, u32 flags) /* We only map from NFSv4 to POSIX ACLs when setting ACLs, when we err on the * side of being more restrictive, so the mode bit mapping below is * pessimistic. An optimistic version would be needed to handle DENY's, - * but we espect to coalesce all ALLOWs and DENYs before mapping to mode + * but we expect to coalesce all ALLOWs and DENYs before mapping to mode * bits. */ static void @@ -126,11 +121,6 @@ low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags) *mode |= ACL_EXECUTE; } -struct ace_container { - struct nfs4_ace *ace; - struct list_head ace_l; -}; - static short ace2type(struct nfs4_ace *); static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *, unsigned int); @@ -384,7 +374,6 @@ pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2) static void sort_pacl_range(struct posix_acl *pacl, int start, int end) { int sorted = 0, i; - struct posix_acl_entry tmp; /* We just do a bubble sort; easy to do in place, and we're not * expecting acl's to be long enough to justify anything more. */ @@ -394,9 +383,8 @@ sort_pacl_range(struct posix_acl *pacl, int start, int end) { if (pace_gt(&pacl->a_entries[i], &pacl->a_entries[i+1])) { sorted = 0; - tmp = pacl->a_entries[i]; - pacl->a_entries[i] = pacl->a_entries[i+1]; - pacl->a_entries[i+1] = tmp; + swap(pacl->a_entries[i], + pacl->a_entries[i + 1]); } } } @@ -472,7 +460,7 @@ init_state(struct posix_acl_state *state, int cnt) state->empty = 1; /* * In the worst case, each individual acl could be for a distinct - * named user or group, but we don't no which, so we allocate + * named user or group, but we don't know which, so we allocate * enough space for either: */ alloc = sizeof(struct posix_ace_state_array) diff --git a/kernel/fs/nfsd/nfs4callback.c b/kernel/fs/nfsd/nfs4callback.c index 5694cfb7a..e7f50c408 100644 --- a/kernel/fs/nfsd/nfs4callback.c +++ b/kernel/fs/nfsd/nfs4callback.c @@ -435,12 +435,12 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, */ status = 0; out: - if (status) - nfsd4_mark_cb_fault(cb->cb_clp, status); + cb->cb_seq_status = status; return status; out_overflow: print_overflow_msg(__func__, xdr); - return -EIO; + status = -EIO; + goto out; } static int decode_cb_sequence4res(struct xdr_stream *xdr, @@ -451,8 +451,8 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr, if (cb->cb_minorversion == 0) return 0; - status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_status); - if (unlikely(status || cb->cb_status)) + status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_seq_status); + if (unlikely(status || cb->cb_seq_status)) return status; return decode_cb_sequence4resok(xdr, cb); @@ -526,7 +526,7 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, if (cb != NULL) { status = decode_cb_sequence4res(xdr, cb); - if (unlikely(status || cb->cb_status)) + if (unlikely(status || cb->cb_seq_status)) return status; } @@ -616,7 +616,7 @@ static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp, if (cb) { status = decode_cb_sequence4res(xdr, cb); - if (unlikely(status || cb->cb_status)) + if (unlikely(status || cb->cb_seq_status)) return status; } return decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &cb->cb_status); @@ -875,6 +875,12 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) u32 minorversion = clp->cl_minorversion; cb->cb_minorversion = minorversion; + /* + * cb_seq_status is only set in decode_cb_sequence4res, + * and so will remain 1 if an rpc level failure occurs. + */ + cb->cb_seq_status = 1; + cb->cb_status = 0; if (minorversion) { if (!nfsd41_cb_get_slot(clp, task)) return; @@ -882,6 +888,84 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) rpc_call_start(task); } +static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + struct nfsd4_session *session = clp->cl_cb_session; + bool ret = true; + + if (!clp->cl_minorversion) { + /* + * If the backchannel connection was shut down while this + * task was queued, we need to resubmit it after setting up + * a new backchannel connection. + * + * Note that if we lost our callback connection permanently + * the submission code will error out, so we don't need to + * handle that case here. + */ + if (task->tk_flags & RPC_TASK_KILLED) + goto need_restart; + + return true; + } + + switch (cb->cb_seq_status) { + case 0: + /* + * No need for lock, access serialized in nfsd4_cb_prepare + * + * RFC5661 20.9.3 + * If CB_SEQUENCE returns an error, then the state of the slot + * (sequence ID, cached reply) MUST NOT change. + */ + ++session->se_cb_seq_nr; + break; + case -ESERVERFAULT: + ++session->se_cb_seq_nr; + case 1: + case -NFS4ERR_BADSESSION: + nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status); + ret = false; + break; + case -NFS4ERR_DELAY: + if (!rpc_restart_call(task)) + goto out; + + rpc_delay(task, 2 * HZ); + return false; + case -NFS4ERR_BADSLOT: + goto retry_nowait; + case -NFS4ERR_SEQ_MISORDERED: + if (session->se_cb_seq_nr != 1) { + session->se_cb_seq_nr = 1; + goto retry_nowait; + } + break; + default: + dprintk("%s: unprocessed error %d\n", __func__, + cb->cb_seq_status); + } + + clear_bit(0, &clp->cl_cb_slot_busy); + rpc_wake_up_next(&clp->cl_cb_waitq); + dprintk("%s: freed slot, new seqid=%d\n", __func__, + clp->cl_cb_session->se_cb_seq_nr); + + if (task->tk_flags & RPC_TASK_KILLED) + goto need_restart; +out: + return ret; +retry_nowait: + if (rpc_restart_call_prepare(task)) + ret = false; + goto out; +need_restart: + task->tk_status = 0; + cb->cb_need_restart = true; + return false; +} + static void nfsd4_cb_done(struct rpc_task *task, void *calldata) { struct nfsd4_callback *cb = calldata; @@ -890,30 +974,8 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) dprintk("%s: minorversion=%d\n", __func__, clp->cl_minorversion); - if (clp->cl_minorversion) { - /* No need for lock, access serialized in nfsd4_cb_prepare */ - if (!task->tk_status) - ++clp->cl_cb_session->se_cb_seq_nr; - clear_bit(0, &clp->cl_cb_slot_busy); - rpc_wake_up_next(&clp->cl_cb_waitq); - dprintk("%s: freed slot, new seqid=%d\n", __func__, - clp->cl_cb_session->se_cb_seq_nr); - } - - /* - * If the backchannel connection was shut down while this - * task was queued, we need to resubmit it after setting up - * a new backchannel connection. - * - * Note that if we lost our callback connection permanently - * the submission code will error out, so we don't need to - * handle that case here. - */ - if (task->tk_flags & RPC_TASK_KILLED) { - task->tk_status = 0; - cb->cb_need_restart = true; + if (!nfsd4_cb_sequence_done(task, cb)) return; - } if (cb->cb_status) { WARN_ON_ONCE(task->tk_status); @@ -1089,6 +1151,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_msg.rpc_resp = cb; cb->cb_ops = ops; INIT_WORK(&cb->cb_work, nfsd4_run_cb_work); + cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; } diff --git a/kernel/fs/nfsd/nfs4idmap.c b/kernel/fs/nfsd/nfs4idmap.c index e1b3d3d47..5b20577dc 100644 --- a/kernel/fs/nfsd/nfs4idmap.c +++ b/kernel/fs/nfsd/nfs4idmap.c @@ -59,9 +59,6 @@ MODULE_PARM_DESC(nfs4_disable_idmapping, * that. */ -#define IDMAP_TYPE_USER 0 -#define IDMAP_TYPE_GROUP 1 - struct ent { struct cache_head h; int type; /* User / Group */ diff --git a/kernel/fs/nfsd/nfs4layouts.c b/kernel/fs/nfsd/nfs4layouts.c index 6904213a4..c9d6c715c 100644 --- a/kernel/fs/nfsd/nfs4layouts.c +++ b/kernel/fs/nfsd/nfs4layouts.c @@ -201,6 +201,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, INIT_LIST_HEAD(&ls->ls_perfile); spin_lock_init(&ls->ls_lock); INIT_LIST_HEAD(&ls->ls_layouts); + mutex_init(&ls->ls_mutex); ls->ls_layout_type = layout_type; nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, NFSPROC4_CLNT_CB_LAYOUT); @@ -212,6 +213,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, BUG_ON(!ls->ls_file); if (nfsd4_layout_setlease(ls)) { + fput(ls->ls_file); put_nfs4_file(fp); kmem_cache_free(nfs4_layout_stateid_cache, ls); return NULL; @@ -261,19 +263,23 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, status = nfserr_jukebox; if (!ls) goto out; + mutex_lock(&ls->ls_mutex); } else { ls = container_of(stid, struct nfs4_layout_stateid, ls_stid); status = nfserr_bad_stateid; + mutex_lock(&ls->ls_mutex); if (stateid->si_generation > stid->sc_stateid.si_generation) - goto out_put_stid; + goto out_unlock_stid; if (layout_type != ls->ls_layout_type) - goto out_put_stid; + goto out_unlock_stid; } *lsp = ls; return 0; +out_unlock_stid: + mutex_unlock(&ls->ls_mutex); out_put_stid: nfs4_put_stid(stid); out: @@ -295,8 +301,6 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) trace_layout_recall(&ls->ls_stid.sc_stateid); atomic_inc(&ls->ls_stid.sc_count); - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); nfsd4_run_cb(&ls->ls_recall); out_unlock: @@ -405,8 +409,7 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) list_add_tail(&new->lo_perstate, &ls->ls_layouts); new = NULL; done: - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&lgp->lg_sid, &ls->ls_stid); spin_unlock(&ls->ls_lock); out: spin_unlock(&fp->fi_lock); @@ -480,11 +483,8 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } } if (!list_empty(&ls->ls_layouts)) { - if (found) { - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid, - sizeof(stateid_t)); - } + if (found) + nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid); lrp->lrs_present = 1; } else { trace_layoutstate_unhash(&ls->ls_stid.sc_stateid); @@ -493,6 +493,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } spin_unlock(&ls->ls_lock); + mutex_unlock(&ls->ls_mutex); nfs4_put_stid(&ls->ls_stid); nfsd4_free_layouts(&reaplist); return nfs_ok; @@ -607,6 +608,17 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) } } +static void +nfsd4_cb_layout_prepare(struct nfsd4_callback *cb) +{ + struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + + mutex_lock(&ls->ls_mutex); + nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid); + mutex_unlock(&ls->ls_mutex); +} + static int nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -654,6 +666,7 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) } static struct nfsd4_callback_ops nfsd4_cb_layout_ops = { + .prepare = nfsd4_cb_layout_prepare, .done = nfsd4_cb_layout_done, .release = nfsd4_cb_layout_release, }; diff --git a/kernel/fs/nfsd/nfs4proc.c b/kernel/fs/nfsd/nfs4proc.c index 864e2003e..a9f096c7e 100644 --- a/kernel/fs/nfsd/nfs4proc.c +++ b/kernel/fs/nfsd/nfs4proc.c @@ -276,13 +276,13 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval); /* - * Following rfc 3530 14.2.16, use the returned bitmask - * to indicate which attributes we used to store the - * verifier: + * Following rfc 3530 14.2.16, and rfc 5661 18.16.4 + * use the returned bitmask to indicate which attributes + * we used to store the verifier: */ - if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0) - open->op_bmval[1] = (FATTR4_WORD1_TIME_ACCESS | - FATTR4_WORD1_TIME_MODIFY); + if (nfsd_create_is_exclusive(open->op_createmode) && status == 0) + open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS | + FATTR4_WORD1_TIME_MODIFY); } else /* * Note this may exit with the parent still locked. @@ -362,7 +362,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; struct svc_fh *resfh = NULL; - struct nfsd4_compoundres *resp; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -389,8 +388,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy_clientid(&open->op_clientid, cstate->session); /* check seqid for replay. set nfs4_owner */ - resp = rqstp->rq_resp; - status = nfsd4_process_open1(&resp->cstate, open, nn); + status = nfsd4_process_open1(cstate, open, nn); if (status == nfserr_replay_me) { struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay; fh_put(&cstate->current_fh); @@ -417,10 +415,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Openowner is now set, so sequence id will get bumped. Now we need * these checks before we do any creates: */ status = nfserr_grace; - if (locks_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS) + if (opens_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS) goto out; status = nfserr_no_grace; - if (!locks_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) + if (!opens_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) goto out; switch (open->op_claim_type) { @@ -760,8 +758,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; - /* no need to check permission - this will be done in nfsd_read() */ - read->rd_filp = NULL; if (read->rd_offset >= OFFSET_MAX) return nfserr_inval; @@ -778,9 +774,9 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ - if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), - cstate, &read->rd_stateid, - RD_STATE, &read->rd_filp))) { + status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid, + RD_STATE, &read->rd_filp, &read->rd_tmp_file); + if (status) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; } @@ -831,7 +827,7 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; - if (locks_in_grace(SVC_NET(rqstp))) + if (opens_in_grace(SVC_NET(rqstp))) return nfserr_grace; status = nfsd_unlink(rqstp, &cstate->current_fh, 0, remove->rm_name, remove->rm_namelen); @@ -850,7 +846,7 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!cstate->save_fh.fh_dentry) return status; - if (locks_in_grace(SVC_NET(rqstp)) && + if (opens_in_grace(SVC_NET(rqstp)) && !(cstate->save_fh.fh_export->ex_flags & NFSEXP_NOSUBTREECHECK)) return nfserr_grace; status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname, @@ -924,8 +920,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int err; if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, - &setattr->sa_stateid, WR_STATE, NULL); + status = nfs4_preprocess_stateid_op(rqstp, cstate, + &setattr->sa_stateid, WR_STATE, NULL, NULL); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -986,13 +982,11 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned long cnt; int nvecs; - /* no need to check permission - this will be done in nfsd_write() */ - if (write->wr_offset >= OFFSET_MAX) return nfserr_inval; - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), - cstate, stateid, WR_STATE, &filp); + status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE, + &filp, NULL); if (status) { dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; @@ -1005,11 +999,10 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nvecs = fill_in_write_vector(rqstp->rq_vec, write); WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); - status = nfsd_write(rqstp, &cstate->current_fh, filp, - write->wr_offset, rqstp->rq_vec, nvecs, - &cnt, &write->wr_how_written); - if (filp) - fput(filp); + status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp, + write->wr_offset, rqstp->rq_vec, nvecs, &cnt, + &write->wr_how_written); + fput(filp); write->wr_bytes_written = cnt; @@ -1023,15 +1016,13 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status = nfserr_notsupp; struct file *file; - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &fallocate->falloc_stateid, - WR_STATE, &file); + WR_STATE, &file, NULL); if (status != nfs_ok) { dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); return status; } - if (!file) - return nfserr_bad_stateid; status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file, fallocate->falloc_offset, @@ -1064,15 +1055,13 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct file *file; - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &seek->seek_stateid, - RD_STATE, &file); + RD_STATE, &file, NULL); if (status) { dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); return status; } - if (!file) - return nfserr_bad_stateid; switch (seek->seek_whence) { case NFS4_CONTENT_DATA: @@ -1320,6 +1309,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp, nfserr = nfsd4_insert_layout(lgp, ls); out_put_stid: + mutex_unlock(&ls->ls_mutex); nfs4_put_stid(&ls->ls_stid); out: return nfserr; @@ -1373,9 +1363,8 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, goto out; } - nfserr = ops->proc_layoutcommit(inode, lcp); - if (nfserr) - goto out_put_stid; + /* LAYOUTCOMMIT does not require any serialization */ + mutex_unlock(&ls->ls_mutex); if (new_size > i_size_read(inode)) { lcp->lc_size_chg = 1; @@ -1384,7 +1373,7 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, lcp->lc_size_chg = 0; } -out_put_stid: + nfserr = ops->proc_layoutcommit(inode, lcp); nfs4_put_stid(&ls->ls_stid); out: return nfserr; @@ -1732,10 +1721,6 @@ encode_op: be32_to_cpu(status)); nfsd4_cstate_clear_replay(cstate); - /* XXX Ugh, we need to get rid of this kind of special case: */ - if (op->opnum == OP_READ && op->u.read.rd_filp) - fput(op->u.read.rd_filp); - nfsd4_increment_op_stats(op->opnum); } diff --git a/kernel/fs/nfsd/nfs4recover.c b/kernel/fs/nfsd/nfs4recover.c index d88ea7b9a..e3d47091b 100644 --- a/kernel/fs/nfsd/nfs4recover.c +++ b/kernel/fs/nfsd/nfs4recover.c @@ -272,6 +272,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) .ctx.actor = nfsd4_build_namelist, .names = LIST_HEAD_INIT(ctx.names) }; + struct name_list *entry, *tmp; int status; status = nfs4_save_creds(&original_cred); @@ -286,9 +287,8 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) status = iterate_dir(nn->rec_file, &ctx.ctx); mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT); - while (!list_empty(&ctx.names)) { - struct name_list *entry; - entry = list_entry(ctx.names.next, struct name_list, list); + + list_for_each_entry_safe(entry, tmp, &ctx.names, list) { if (!status) { struct dentry *dentry; dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1); @@ -304,6 +304,12 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) } mutex_unlock(&d_inode(dir)->i_mutex); nfs4_reset_creds(original_cred); + + list_for_each_entry_safe(entry, tmp, &ctx.names, list) { + dprintk("NFSD: %s. Left entry %s\n", __func__, entry->name); + list_del(&entry->list); + kfree(entry); + } return status; } @@ -541,8 +547,7 @@ nfsd4_legacy_tracking_init(struct net *net) /* XXX: The legacy code won't work in a container */ if (net != &init_net) { - WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client " - "tracking in a container!\n"); + pr_warn("NFSD: attempt to initialize legacy client tracking in a container ignored.\n"); return -EINVAL; } @@ -1254,8 +1259,7 @@ nfsd4_umh_cltrack_init(struct net *net) /* XXX: The usermode helper s not working in container yet. */ if (net != &init_net) { - WARN(1, KERN_ERR "NFSD: attempt to initialize umh client " - "tracking in a container!\n"); + pr_warn("NFSD: attempt to initialize umh client tracking in a container ignored.\n"); return -EINVAL; } diff --git a/kernel/fs/nfsd/nfs4state.c b/kernel/fs/nfsd/nfs4state.c index 397798368..6b800b5b8 100644 --- a/kernel/fs/nfsd/nfs4state.c +++ b/kernel/fs/nfsd/nfs4state.c @@ -575,6 +575,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; /* Will be incremented before return to client: */ atomic_set(&stid->sc_count, 1); + spin_lock_init(&stid->sc_lock); /* * It shouldn't be a problem to reuse an opaque stateid value. @@ -745,6 +746,18 @@ nfs4_put_stid(struct nfs4_stid *s) put_nfs4_file(fp); } +void +nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) +{ + stateid_t *src = &stid->sc_stateid; + + spin_lock(&stid->sc_lock); + if (unlikely(++src->si_generation == 0)) + src->si_generation = 1; + memcpy(dst, src, sizeof(*dst)); + spin_unlock(&stid->sc_lock); +} + static void nfs4_put_deleg_lease(struct nfs4_file *fp) { struct file *filp = NULL; @@ -765,16 +778,68 @@ void nfs4_unhash_stid(struct nfs4_stid *s) s->sc_type = 0; } -static void +/** + * nfs4_get_existing_delegation - Discover if this delegation already exists + * @clp: a pointer to the nfs4_client we're granting a delegation to + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if an existing delegation was not found. + * + * On error: -EAGAIN if one was previously granted to this nfs4_client + * for this nfs4_file. + * + */ + +static int +nfs4_get_existing_delegation(struct nfs4_client *clp, struct nfs4_file *fp) +{ + struct nfs4_delegation *searchdp = NULL; + struct nfs4_client *searchclp = NULL; + + lockdep_assert_held(&state_lock); + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) { + searchclp = searchdp->dl_stid.sc_client; + if (clp == searchclp) { + return -EAGAIN; + } + } + return 0; +} + +/** + * hash_delegation_locked - Add a delegation to the appropriate lists + * @dp: a pointer to the nfs4_delegation we are adding. + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if the delegation was successfully hashed. + * + * On error: -EAGAIN if one was previously granted to this + * nfs4_client for this nfs4_file. Delegation is not hashed. + * + */ + +static int hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) { + int status; + struct nfs4_client *clp = dp->dl_stid.sc_client; + lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + if (status) + return status; + ++fp->fi_delegees; atomic_inc(&dp->dl_stid.sc_count); dp->dl_stid.sc_type = NFS4_DELEG_STID; list_add(&dp->dl_perfile, &fp->fi_delegations); - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); + list_add(&dp->dl_perclnt, &clp->cl_delegations); + return 0; } static bool @@ -998,6 +1063,12 @@ release_all_access(struct nfs4_ol_stateid *stp) } } +static inline void nfs4_free_stateowner(struct nfs4_stateowner *sop) +{ + kfree(sop->so_owner.data); + sop->so_ops->so_free(sop); +} + static void nfs4_put_stateowner(struct nfs4_stateowner *sop) { struct nfs4_client *clp = sop->so_client; @@ -1008,8 +1079,7 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop) return; sop->so_ops->so_unhash(sop); spin_unlock(&clp->cl_lock); - kfree(sop->so_owner.data); - sop->so_ops->so_free(sop); + nfs4_free_stateowner(sop); } static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) @@ -1913,7 +1983,7 @@ static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn) * __force to keep sparse happy */ verf[0] = (__force __be32)get_seconds(); - verf[1] = (__force __be32)nn->clientid_counter; + verf[1] = (__force __be32)nn->clverifier_counter++; memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data)); } @@ -2251,15 +2321,23 @@ nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) clid->flags = new->cl_exchange_flags; } +static bool client_has_openowners(struct nfs4_client *clp) +{ + struct nfs4_openowner *oo; + + list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) { + if (!list_empty(&oo->oo_owner.so_stateids)) + return true; + } + return false; +} + static bool client_has_state(struct nfs4_client *clp) { - /* - * Note clp->cl_openowners check isn't quite right: there's no - * need to count owners without stateid's. - * - * Also note we should probably be using this in 4.0 case too. - */ - return !list_empty(&clp->cl_openowners) + return client_has_openowners(clp) +#ifdef CONFIG_NFSD_PNFS + || !list_empty(&clp->cl_lo_states) +#endif || !list_empty(&clp->cl_delegations) || !list_empty(&clp->cl_sessions); } @@ -2566,11 +2644,9 @@ nfsd4_create_session(struct svc_rqst *rqstp, goto out_free_conn; cs_slot = &conf->cl_cs_slot; status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); - if (status == nfserr_replay_cache) { - status = nfsd4_replay_create_session(cr_ses, cs_slot); - goto out_free_conn; - } else if (cr_ses->seqid != cs_slot->sl_seqid + 1) { - status = nfserr_seq_misordered; + if (status) { + if (status == nfserr_replay_cache) + status = nfsd4_replay_create_session(cr_ses, cs_slot); goto out_free_conn; } } else if (unconf) { @@ -3043,7 +3119,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Cases below refer to rfc 3530 section 14.2.33: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&clname, nn); - if (conf) { + if (conf && client_has_state(conf)) { /* case 0: */ status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) @@ -3060,10 +3136,11 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) unhash_client_locked(unconf); - if (conf && same_verf(&conf->cl_verifier, &clverifier)) + if (conf && same_verf(&conf->cl_verifier, &clverifier)) { /* case 1: probable callback update */ copy_clid(new, conf); - else /* case 4 (new client) or cases 2, 3 (client reboot): */ + gen_confirm(new, nn); + } else /* case 4 (new client) or cases 2, 3 (client reboot): */ gen_clid(new, nn); new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); @@ -3104,10 +3181,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, /* * We try hard to give out unique clientid's, so if we get an * attempt to confirm the same clientid with a different cred, - * there's a bug somewhere. Let's charitably assume it's our - * bug. + * the client may be buggy; this should never happen. + * + * Nevertheless, RFC 7530 recommends INUSE for this case: */ - status = nfserr_serverfault; + status = nfserr_clid_inuse; if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred)) goto out; if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred)) @@ -3128,6 +3206,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } else { /* case 3: normal case; new or rebooted client */ old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { + status = nfserr_clid_inuse; + if (client_has_state(old) + && !same_creds(&unconf->cl_cred, + &old->cl_cred)) + goto out; status = mark_client_expired_locked(old); if (status) { old = NULL; @@ -3309,6 +3392,27 @@ static const struct nfs4_stateowner_operations openowner_ops = { .so_free = nfs4_free_openowner, }; +static struct nfs4_ol_stateid * +nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) +{ + struct nfs4_ol_stateid *local, *ret = NULL; + struct nfs4_openowner *oo = open->op_openowner; + + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(local, &fp->fi_stateids, st_perfile) { + /* ignore lock owners */ + if (local->st_stateowner->so_is_open_owner == 0) + continue; + if (local->st_stateowner == &oo->oo_owner) { + ret = local; + atomic_inc(&ret->st_stid.sc_count); + break; + } + } + return ret; +} + static struct nfs4_openowner * alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, struct nfsd4_compound_state *cstate) @@ -3334,14 +3438,26 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, hash_openowner(oo, clp, strhashval); ret = oo; } else - nfs4_free_openowner(&oo->oo_owner); + nfs4_free_stateowner(&oo->oo_owner); + spin_unlock(&clp->cl_lock); return ret; } -static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) { +static struct nfs4_ol_stateid * +init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, + struct nfsd4_open *open) +{ + struct nfs4_openowner *oo = open->op_openowner; + struct nfs4_ol_stateid *retstp = NULL; + + spin_lock(&oo->oo_owner.so_client->cl_lock); + spin_lock(&fp->fi_lock); + retstp = nfsd4_find_existing_open(fp, open); + if (retstp) + goto out_unlock; atomic_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_OPEN_STID; INIT_LIST_HEAD(&stp->st_locks); @@ -3351,12 +3467,14 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; - spin_lock(&oo->oo_owner.so_client->cl_lock); + init_rwsem(&stp->st_rwsem); list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); - spin_lock(&fp->fi_lock); list_add(&stp->st_perfile, &fp->fi_stateids); + +out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); + return retstp; } /* @@ -3501,6 +3619,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, { struct nfs4_delegation *dp = cb_to_delegation(cb); + if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID) + return 1; + switch (task->tk_status) { case 0: return 1; @@ -3764,27 +3885,6 @@ out: return nfs_ok; } -static struct nfs4_ol_stateid * -nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) -{ - struct nfs4_ol_stateid *local, *ret = NULL; - struct nfs4_openowner *oo = open->op_openowner; - - spin_lock(&fp->fi_lock); - list_for_each_entry(local, &fp->fi_stateids, st_perfile) { - /* ignore lock owners */ - if (local->st_stateowner->so_is_open_owner == 0) - continue; - if (local->st_stateowner == &oo->oo_owner) { - ret = local; - atomic_inc(&ret->st_stid.sc_count); - break; - } - } - spin_unlock(&fp->fi_lock); - return ret; -} - static inline int nfs4_access_to_access(u32 nfs4_access) { int flags = 0; @@ -3880,7 +3980,7 @@ static __be32 nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) { __be32 status; - unsigned char old_deny_bmap; + unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open); @@ -3889,7 +3989,6 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *c spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); if (status == nfs_ok) { - old_deny_bmap = stp->st_deny_bmap; set_deny(open->op_share_deny, stp); fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH); @@ -3905,12 +4004,6 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *c return status; } -static void -nfs4_set_claim_prev(struct nfsd4_open *open, bool has_session) -{ - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; -} - /* Should we give out recallable state?: */ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) { @@ -3940,10 +4033,22 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag) return fl; } +/** + * nfs4_setlease - Obtain a delegation by requesting lease from vfs layer + * @dp: a pointer to the nfs4_delegation we're adding. + * + * Return: + * On success: Return code will be 0 on success. + * + * On error: -EAGAIN if there was an existing delegation. + * nonzero if there is an error in other cases. + * + */ + static int nfs4_setlease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; - struct file_lock *fl, *ret; + struct file_lock *fl; struct file *filp; int status = 0; @@ -3954,10 +4059,10 @@ static int nfs4_setlease(struct nfs4_delegation *dp) if (!filp) { /* We should always have a readable file here */ WARN_ON_ONCE(1); + locks_free_lock(fl); return -EBADF; } fl->fl_file = filp; - ret = fl; status = vfs_setlease(filp, fl->fl_type, &fl, NULL); if (fl) locks_free_lock(fl); @@ -3971,16 +4076,19 @@ static int nfs4_setlease(struct nfs4_delegation *dp) goto out_unlock; /* Race breaker */ if (fp->fi_deleg_file) { - status = 0; - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); goto out_unlock; } fp->fi_deleg_file = filp; - fp->fi_delegees = 1; - hash_delegation_locked(dp, fp); + fp->fi_delegees = 0; + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); + if (status) { + /* Should never happen, this is a new fi_deleg_file */ + WARN_ON_ONCE(1); + goto out_fput; + } return 0; out_unlock: spin_unlock(&fp->fi_lock); @@ -4000,6 +4108,15 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) + return ERR_PTR(status); + dp = alloc_init_deleg(clp, fh, odstate); if (!dp) return ERR_PTR(-ENOMEM); @@ -4018,9 +4135,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, status = -EAGAIN; goto out_unlock; } - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); - status = 0; + status = hash_delegation_locked(dp, fp); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -4083,7 +4198,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's - * had the chance to reclaim theirs.... + * had the chance to reclaim theirs, *and* until + * NLM locks have all been reclaimed: */ if (locks_in_grace(clp->net)) goto out_no_deleg; @@ -4154,6 +4270,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf struct nfs4_client *cl = open->op_openowner->oo_owner.so_client; struct nfs4_file *fp = NULL; struct nfs4_ol_stateid *stp = NULL; + struct nfs4_ol_stateid *swapstp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; @@ -4167,7 +4284,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; + spin_lock(&fp->fi_lock); stp = nfsd4_find_existing_open(fp, open); + spin_unlock(&fp->fi_lock); } else { open->op_file = NULL; status = nfserr_bad_stateid; @@ -4181,15 +4300,32 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf */ if (stp) { /* Stateid was found, this is an OPEN upgrade */ + down_read(&stp->st_rwsem); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); - if (status) + if (status) { + up_read(&stp->st_rwsem); goto out; + } } else { stp = open->op_stp; open->op_stp = NULL; - init_open_stateid(stp, fp, open); + swapstp = init_open_stateid(stp, fp, open); + if (swapstp) { + nfs4_put_stid(&stp->st_stid); + stp = swapstp; + down_read(&stp->st_rwsem); + status = nfs4_upgrade_open(rqstp, fp, current_fh, + stp, open); + if (status) { + up_read(&stp->st_rwsem); + goto out; + } + goto upgrade_out; + } + down_read(&stp->st_rwsem); status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { + up_read(&stp->st_rwsem); release_open_stateid(stp); goto out; } @@ -4199,8 +4335,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (stp->st_clnt_odstate == open->op_odstate) open->op_odstate = NULL; } - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); +upgrade_out: + nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); + up_read(&stp->st_rwsem); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { @@ -4229,7 +4366,7 @@ out: if (fp) put_nfs4_file(fp); if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) - nfs4_set_claim_prev(open, nfsd4_has_session(&resp->cstate)); + open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; /* * To finish the open response, we just need to set the rflags. */ @@ -4358,8 +4495,6 @@ nfs4_laundromat(struct nfsd_net *nn) spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); - if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn) - continue; if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) { t = dp->dl_time - cutoff; new_timeo = min(new_timeo, t); @@ -4460,7 +4595,7 @@ check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, { if (ONE_STATEID(stateid) && (flags & RD_STATE)) return nfs_ok; - else if (locks_in_grace(net)) { + else if (opens_in_grace(net)) { /* Answer in remaining cases depends on existence of * conflicting state; so we must wait out the grace period. */ return nfserr_grace; @@ -4479,7 +4614,7 @@ check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, static inline int grace_disallows_io(struct net *net, struct inode *inode) { - return locks_in_grace(net) && mandatory_lock(inode); + return opens_in_grace(net) && mandatory_lock(inode); } /* Returns true iff a is later than b: */ @@ -4596,6 +4731,9 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, static struct file * nfs4_find_file(struct nfs4_stid *s, int flags) { + if (!s) + return NULL; + switch (s->sc_type) { case NFS4_DELEG_STID: if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file)) @@ -4624,27 +4762,63 @@ nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags) return nfs4_check_openmode(ols, flags); } +static __be32 +nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, + struct file **filpp, bool *tmp_file, int flags) +{ + int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE; + struct file *file; + __be32 status; + + file = nfs4_find_file(s, flags); + if (file) { + status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, + acc | NFSD_MAY_OWNER_OVERRIDE); + if (status) { + fput(file); + return status; + } + + *filpp = file; + } else { + status = nfsd_open(rqstp, fhp, S_IFREG, acc, filpp); + if (status) + return status; + + if (tmp_file) + *tmp_file = true; + } + + return 0; +} + /* * Checks for stateid operations */ __be32 -nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, - stateid_t *stateid, int flags, struct file **filpp) +nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + int flags, struct file **filpp, bool *tmp_file) { struct svc_fh *fhp = &cstate->current_fh; struct inode *ino = d_inode(fhp->fh_dentry); + struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfs4_stid *s; + struct nfs4_stid *s = NULL; __be32 status; if (filpp) *filpp = NULL; + if (tmp_file) + *tmp_file = false; if (grace_disallows_io(net, ino)) return nfserr_grace; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) - return check_special_stateids(net, fhp, stateid, flags); + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { + status = check_special_stateids(net, fhp, stateid, flags); + goto done; + } status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, @@ -4672,13 +4846,12 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, goto out; status = nfs4_check_fh(fhp, s); - if (!status && filpp) { - *filpp = nfs4_find_file(s, flags); - if (!*filpp) - status = nfserr_serverfault; - } +done: + if (!status && filpp) + status = nfs4_check_file(rqstp, fhp, s, filpp, tmp_file, flags); out: - nfs4_put_stid(s); + if (s) + nfs4_put_stid(s); return status; } @@ -4777,10 +4950,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * revoked delegations are kept only for free_stateid. */ return nfserr_bad_stateid; + down_write(&stp->st_rwsem); status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); - if (status) - return status; - return nfs4_check_fh(current_fh, &stp->st_stid); + if (status == nfs_ok) + status = nfs4_check_fh(current_fh, &stp->st_stid); + if (status != nfs_ok) + up_write(&stp->st_rwsem); + return status; } /* @@ -4827,6 +5003,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } @@ -4857,11 +5034,13 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; - if (oo->oo_flags & NFS4_OO_CONFIRMED) + if (oo->oo_flags & NFS4_OO_CONFIRMED) { + up_write(&stp->st_rwsem); goto put_stateid; + } oo->oo_flags |= NFS4_OO_CONFIRMED; - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); + up_write(&stp->st_rwsem); dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); @@ -4933,13 +5112,11 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, goto put_stateid; } nfs4_stateid_downgrade(stp, od->od_share_access); - reset_union_bmap_deny(od->od_share_deny, stp); - - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid); status = nfs_ok; put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -4991,8 +5168,8 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd4_bump_seqid(cstate, status); if (status) goto out; - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); + up_write(&stp->st_rwsem); nfsd4_close_open_stateid(stp); @@ -5030,9 +5207,6 @@ out: return status; } - -#define LOFF_OVERFLOW(start, len) ((u64)(len) > ~(u64)(start)) - static inline u64 end_offset(u64 start, u64 len) { @@ -5124,8 +5298,7 @@ nevermind: } static struct nfs4_lockowner * -find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner, - struct nfs4_client *clp) +find_lockowner_str_locked(struct nfs4_client *clp, struct xdr_netobj *owner) { unsigned int strhashval = ownerstr_hashval(owner); struct nfs4_stateowner *so; @@ -5143,13 +5316,12 @@ find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner, } static struct nfs4_lockowner * -find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner, - struct nfs4_client *clp) +find_lockowner_str(struct nfs4_client *clp, struct xdr_netobj *owner) { struct nfs4_lockowner *lo; spin_lock(&clp->cl_lock); - lo = find_lockowner_str_locked(clid, owner, clp); + lo = find_lockowner_str_locked(clp, owner); spin_unlock(&clp->cl_lock); return lo; } @@ -5193,14 +5365,14 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, lo->lo_owner.so_seqid = lock->lk_new_lock_seqid; lo->lo_owner.so_ops = &lockowner_ops; spin_lock(&clp->cl_lock); - ret = find_lockowner_str_locked(&clp->cl_clientid, - &lock->lk_new_owner, clp); + ret = find_lockowner_str_locked(clp, &lock->lk_new_owner); if (ret == NULL) { list_add(&lo->lo_owner.so_strhash, &clp->cl_ownerstr_hashtbl[strhashval]); ret = lo; } else - nfs4_free_lockowner(&lo->lo_owner); + nfs4_free_stateowner(&lo->lo_owner); + spin_unlock(&clp->cl_lock); return ret; } @@ -5223,6 +5395,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + init_rwsem(&stp->st_rwsem); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -5283,8 +5456,8 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, static int check_lock_length(u64 offset, u64 length) { - return ((length == 0) || ((length != NFS4_MAX_UINT64) && - LOFF_OVERFLOW(offset, length))); + return ((length == 0) || ((length != NFS4_MAX_UINT64) && + (length > ~offset))); } static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access) @@ -5313,9 +5486,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_lockowner *lo; unsigned int strhashval; - lo = find_lockowner_str(&cl->cl_clientid, &lock->v.new.owner, cl); + lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { - strhashval = ownerstr_hashval(&lock->v.new.owner); + strhashval = ownerstr_hashval(&lock->lk_new_owner); lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock); if (lo == NULL) return nfserr_jukebox; @@ -5376,7 +5549,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) /* See rfc 5661 18.10.3: given clientid is ignored: */ - memcpy(&lock->v.new.clientid, + memcpy(&lock->lk_new_clientid, &cstate->session->se_client->cl_clientid, sizeof(clientid_t)); @@ -5391,13 +5564,16 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &open_stp, nn); if (status) goto out; + up_write(&open_stp->st_rwsem); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, - &lock->v.new.clientid)) + &lock->lk_new_clientid)) goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); + if (status == nfs_ok) + down_write(&lock_stp->st_rwsem); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, @@ -5475,9 +5651,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, err = vfs_lock_file(filp, F_SETLK, file_lock, conflock); switch (-err) { case 0: /* success! */ - update_stateid(&lock_stp->st_stid.sc_stateid); - memcpy(&lock->lk_resp_stateid, &lock_stp->st_stid.sc_stateid, - sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); status = 0; break; case (EAGAIN): /* conflock holds conflicting lock */ @@ -5503,6 +5677,8 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; + up_write(&lock_stp->st_rwsem); + /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. @@ -5534,7 +5710,7 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct __be32 err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); if (!err) { err = nfserrno(vfs_test_lock(file, lock)); - nfsd_close(file); + fput(file); } return err; } @@ -5588,8 +5764,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - lo = find_lockowner_str(&lockt->lt_clientid, &lockt->lt_owner, - cstate->clp); + lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); if (lo) file_lock->fl_owner = (fl_owner_t)lo; file_lock->fl_pid = current->tgid; @@ -5668,11 +5843,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid); fput: fput(filp); put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -6569,6 +6744,7 @@ nfs4_state_start_net(struct net *net) return ret; nn->boot_time = get_seconds(); nn->grace_ended = false; + nn->nfsd4_manager.block_opens = true; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); printk(KERN_INFO "NFSD: starting %ld-second grace period (net %p)\n", @@ -6587,7 +6763,7 @@ nfs4_state_start(void) ret = set_callback_cred(); if (ret) return -ENOMEM; - laundry_wq = create_singlethread_workqueue("nfsd4"); + laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); if (laundry_wq == NULL) { ret = -ENOMEM; goto out_recovery; diff --git a/kernel/fs/nfsd/nfs4xdr.c b/kernel/fs/nfsd/nfs4xdr.c index 3dd1b616b..51c9e9ca3 100644 --- a/kernel/fs/nfsd/nfs4xdr.c +++ b/kernel/fs/nfsd/nfs4xdr.c @@ -33,6 +33,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/file.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/statfs.h> @@ -2225,6 +2226,39 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) return err; } +static __be32 +nfsd4_encode_bitmap(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) +{ + __be32 *p; + + if (bmval2) { + p = xdr_reserve_space(xdr, 16); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bmval0); + *p++ = cpu_to_be32(bmval1); + *p++ = cpu_to_be32(bmval2); + } else if (bmval1) { + p = xdr_reserve_space(xdr, 12); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bmval0); + *p++ = cpu_to_be32(bmval1); + } else { + p = xdr_reserve_space(xdr, 8); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(bmval0); + } + + return 0; +out_resource: + return nfserr_resource; +} + /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. @@ -2250,7 +2284,6 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, u32 rdattr_err = 0; __be32 status; int err; - int aclsupport = 0; struct nfs4_acl *acl = NULL; void *context = NULL; int contextlen; @@ -2296,19 +2329,15 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; fhp = tempfh; } - if (bmval0 & (FATTR4_WORD0_ACL | FATTR4_WORD0_ACLSUPPORT - | FATTR4_WORD0_SUPPORTED_ATTRS)) { + if (bmval0 & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &acl); - aclsupport = (err == 0); - if (bmval0 & FATTR4_WORD0_ACL) { - if (err == -EOPNOTSUPP) - bmval0 &= ~FATTR4_WORD0_ACL; - else if (err == -EINVAL) { - status = nfserr_attrnotsupp; - goto out; - } else if (err != 0) - goto out_nfserr; - } + if (err == -EOPNOTSUPP) + bmval0 &= ~FATTR4_WORD0_ACL; + else if (err == -EINVAL) { + status = nfserr_attrnotsupp; + goto out; + } else if (err != 0) + goto out_nfserr; } #ifdef CONFIG_NFSD_V4_SECURITY_LABEL @@ -2326,28 +2355,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, } #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ - if (bmval2) { - p = xdr_reserve_space(xdr, 16); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(bmval0); - *p++ = cpu_to_be32(bmval1); - *p++ = cpu_to_be32(bmval2); - } else if (bmval1) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(2); - *p++ = cpu_to_be32(bmval0); - *p++ = cpu_to_be32(bmval1); - } else { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - *p++ = cpu_to_be32(bmval0); - } + status = nfsd4_encode_bitmap(xdr, bmval0, bmval1, bmval2); + if (status) + goto out; attrlen_offset = xdr->buf->len; p = xdr_reserve_space(xdr, 4); @@ -2360,7 +2370,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, u32 word1 = nfsd_suppattrs1(minorversion); u32 word2 = nfsd_suppattrs2(minorversion); - if (!aclsupport) + if (!IS_POSIXACL(dentry->d_inode)) word0 &= ~FATTR4_WORD0_ACL; if (!contextsupport) word2 &= ~FATTR4_WORD2_SECURITY_LABEL; @@ -2508,7 +2518,7 @@ out_acl: p = xdr_reserve_space(xdr, 4); if (!p) goto out_resource; - *p++ = cpu_to_be32(aclsupport ? + *p++ = cpu_to_be32(IS_POSIXACL(dentry->d_inode) ? ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0); } if (bmval0 & FATTR4_WORD0_CANSETTIME) { @@ -2700,6 +2710,9 @@ out_acl: *p++ = cpu_to_be32(stat.mtime.tv_nsec); } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { + struct kstat parent_stat; + u64 ino = stat.ino; + p = xdr_reserve_space(xdr, 8); if (!p) goto out_resource; @@ -2708,9 +2721,13 @@ out_acl: * and this is the root of a cross-mounted filesystem. */ if (ignore_crossmnt == 0 && - dentry == exp->ex_path.mnt->mnt_root) - get_parent_attributes(exp, &stat); - p = xdr_encode_hyper(p, stat.ino); + dentry == exp->ex_path.mnt->mnt_root) { + err = get_parent_attributes(exp, &parent_stat); + if (err) + goto out_nfserr; + ino = parent_stat.ino; + } + p = xdr_encode_hyper(p, ino); } #ifdef CONFIG_NFSD_PNFS if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) { @@ -2732,21 +2749,20 @@ out_acl: *p++ = cpu_to_be32(stat.blksize); } #endif /* CONFIG_NFSD_PNFS */ + if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { + status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0, + NFSD_SUPPATTR_EXCLCREAT_WORD1, + NFSD_SUPPATTR_EXCLCREAT_WORD2); + if (status) + goto out; + } + if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { status = nfsd4_encode_security_label(xdr, rqstp, context, contextlen); if (status) goto out; } - if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - p = xdr_reserve_space(xdr, 16); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD0); - *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD1); - *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD2); - } attrlen = htonl(xdr->buf->len - attrlen_offset - 4); write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); @@ -3065,13 +3081,12 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ __be32 *p; if (!nfserr) { - p = xdr_reserve_space(xdr, 32); + p = xdr_reserve_space(xdr, 20); if (!p) return nfserr_resource; - p = encode_cinfo(p, &create->cr_cinfo); - *p++ = cpu_to_be32(2); - *p++ = cpu_to_be32(create->cr_bmval[0]); - *p++ = cpu_to_be32(create->cr_bmval[1]); + encode_cinfo(p, &create->cr_cinfo); + nfserr = nfsd4_encode_bitmap(xdr, create->cr_bmval[0], + create->cr_bmval[1], create->cr_bmval[2]); } return nfserr; } @@ -3211,16 +3226,22 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); if (nfserr) goto out; - p = xdr_reserve_space(xdr, 40); + p = xdr_reserve_space(xdr, 24); if (!p) return nfserr_resource; p = encode_cinfo(p, &open->op_cinfo); *p++ = cpu_to_be32(open->op_rflags); - *p++ = cpu_to_be32(2); - *p++ = cpu_to_be32(open->op_bmval[0]); - *p++ = cpu_to_be32(open->op_bmval[1]); - *p++ = cpu_to_be32(open->op_delegate_type); + nfserr = nfsd4_encode_bitmap(xdr, open->op_bmval[0], open->op_bmval[1], + open->op_bmval[2]); + if (nfserr) + goto out; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + + *p++ = cpu_to_be32(open->op_delegate_type); switch (open->op_delegate_type) { case NFS4_OPEN_DELEGATE_NONE: break; @@ -3440,52 +3461,51 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, unsigned long maxcount; struct xdr_stream *xdr = &resp->xdr; struct file *file = read->rd_filp; - struct svc_fh *fhp = read->rd_fhp; int starting_len = xdr->buf->len; - struct raparms *ra; + struct raparms *ra = NULL; __be32 *p; - __be32 err; if (nfserr) - return nfserr; + goto out; p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); - return nfserr_resource; + nfserr = nfserr_resource; + goto out; } - if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { + if (resp->xdr.buf->page_len && + test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { WARN_ON_ONCE(1); - return nfserr_resource; + nfserr = nfserr_resource; + goto out; } xdr_commit_encode(xdr); maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, (xdr->buf->buflen - xdr->buf->len)); + maxcount = min_t(unsigned long, maxcount, + (xdr->buf->buflen - xdr->buf->len)); maxcount = min_t(unsigned long, maxcount, read->rd_length); - if (read->rd_filp) - err = nfsd_permission(resp->rqstp, fhp->fh_export, - fhp->fh_dentry, - NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); - else - err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp, - &file, &ra); - if (err) - goto err_truncate; + if (read->rd_tmp_file) + ra = nfsd_init_raparms(file); - if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) - err = nfsd4_encode_splice_read(resp, read, file, maxcount); + if (file->f_op->splice_read && + test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) + nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); else - err = nfsd4_encode_readv(resp, read, file, maxcount); + nfserr = nfsd4_encode_readv(resp, read, file, maxcount); - if (!read->rd_filp) - nfsd_put_tmp_read_open(file, ra); + if (ra) + nfsd_put_raparams(file, ra); -err_truncate: - if (err) + if (nfserr) xdr_truncate_encode(xdr, starting_len); - return err; + +out: + if (file) + fput(file); + return nfserr; } static __be32 diff --git a/kernel/fs/nfsd/nfscache.c b/kernel/fs/nfsd/nfscache.c index 46ec934f5..54cde9a58 100644 --- a/kernel/fs/nfsd/nfscache.c +++ b/kernel/fs/nfsd/nfscache.c @@ -63,7 +63,6 @@ static unsigned int longest_chain; static unsigned int longest_chain_cachesize; static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); -static void cache_cleaner_func(struct work_struct *unused); static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, @@ -76,13 +75,6 @@ static struct shrinker nfsd_reply_cache_shrinker = { }; /* - * locking for the reply cache: - * A cache entry is "single use" if c_state == RC_INPROG - * Otherwise, it when accessing _prev or _next, the lock must be held. - */ -static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func); - -/* * Put a cap on the size of the DRC based on the amount of available * low memory in the machine. * @@ -203,7 +195,6 @@ void nfsd_reply_cache_shutdown(void) unsigned int i; unregister_shrinker(&nfsd_reply_cache_shrinker); - cancel_delayed_work_sync(&cache_cleaner); for (i = 0; i < drc_hashsize; i++) { struct list_head *head = &drc_hashtbl[i].lru_head; @@ -217,10 +208,8 @@ void nfsd_reply_cache_shutdown(void) drc_hashtbl = NULL; drc_hashsize = 0; - if (drc_slab) { - kmem_cache_destroy(drc_slab); - drc_slab = NULL; - } + kmem_cache_destroy(drc_slab); + drc_slab = NULL; } /* @@ -232,7 +221,6 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) { rp->c_timestamp = jiffies; list_move_tail(&rp->c_lru, &b->lru_head); - schedule_delayed_work(&cache_cleaner, RC_EXPIRE); } static long @@ -266,7 +254,6 @@ prune_cache_entries(void) { unsigned int i; long freed = 0; - bool cancel = true; for (i = 0; i < drc_hashsize; i++) { struct nfsd_drc_bucket *b = &drc_hashtbl[i]; @@ -275,26 +262,11 @@ prune_cache_entries(void) continue; spin_lock(&b->cache_lock); freed += prune_bucket(b); - if (!list_empty(&b->lru_head)) - cancel = false; spin_unlock(&b->cache_lock); } - - /* - * Conditionally rearm the job to run in RC_EXPIRE since we just - * ran the pruner. - */ - if (!cancel) - mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE); return freed; } -static void -cache_cleaner_func(struct work_struct *unused) -{ - prune_cache_entries(); -} - static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { diff --git a/kernel/fs/nfsd/nfsfh.c b/kernel/fs/nfsd/nfsfh.c index 350041a40..c1681ce89 100644 --- a/kernel/fs/nfsd/nfsfh.c +++ b/kernel/fs/nfsd/nfsfh.c @@ -631,10 +631,7 @@ fh_put(struct svc_fh *fhp) fh_unlock(fhp); fhp->fh_dentry = NULL; dput(dentry); -#ifdef CONFIG_NFSD_V3 - fhp->fh_pre_saved = 0; - fhp->fh_post_saved = 0; -#endif + fh_clear_wcc(fhp); } fh_drop_write(fhp); if (exp) { diff --git a/kernel/fs/nfsd/nfsfh.h b/kernel/fs/nfsd/nfsfh.h index 1e90dad49..2087bae17 100644 --- a/kernel/fs/nfsd/nfsfh.h +++ b/kernel/fs/nfsd/nfsfh.h @@ -26,16 +26,16 @@ static inline ino_t u32_to_ino_t(__u32 uino) */ typedef struct svc_fh { struct knfsd_fh fh_handle; /* FH data */ + int fh_maxsize; /* max size for fh_handle */ struct dentry * fh_dentry; /* validated dentry */ struct svc_export * fh_export; /* export pointer */ - int fh_maxsize; /* max size for fh_handle */ - unsigned char fh_locked; /* inode locked by us */ - unsigned char fh_want_write; /* remount protection taken */ + bool fh_locked; /* inode locked by us */ + bool fh_want_write; /* remount protection taken */ #ifdef CONFIG_NFSD_V3 - unsigned char fh_post_saved; /* post-op attrs saved */ - unsigned char fh_pre_saved; /* pre-op attrs saved */ + bool fh_post_saved; /* post-op attrs saved */ + bool fh_pre_saved; /* pre-op attrs saved */ /* Pre-op attributes saved during fh_lock */ __u64 fh_pre_size; /* size before operation */ @@ -213,8 +213,8 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) static inline void fh_clear_wcc(struct svc_fh *fhp) { - fhp->fh_post_saved = 0; - fhp->fh_pre_saved = 0; + fhp->fh_post_saved = false; + fhp->fh_pre_saved = false; } /* @@ -231,7 +231,7 @@ fill_pre_wcc(struct svc_fh *fhp) fhp->fh_pre_ctime = inode->i_ctime; fhp->fh_pre_size = inode->i_size; fhp->fh_pre_change = inode->i_version; - fhp->fh_pre_saved = 1; + fhp->fh_pre_saved = true; } } @@ -267,7 +267,7 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) inode = d_inode(dentry); mutex_lock_nested(&inode->i_mutex, subclass); fill_pre_wcc(fhp); - fhp->fh_locked = 1; + fhp->fh_locked = true; } static inline void @@ -285,7 +285,7 @@ fh_unlock(struct svc_fh *fhp) if (fhp->fh_locked) { fill_post_wcc(fhp); mutex_unlock(&d_inode(fhp->fh_dentry)->i_mutex); - fhp->fh_locked = 0; + fhp->fh_locked = false; } } diff --git a/kernel/fs/nfsd/nfsproc.c b/kernel/fs/nfsd/nfsproc.c index aecbcd34d..4cd78ef4c 100644 --- a/kernel/fs/nfsd/nfsproc.c +++ b/kernel/fs/nfsd/nfsproc.c @@ -59,13 +59,61 @@ static __be32 nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, struct nfsd_attrstat *resp) { + struct iattr *iap = &argp->attrs; + struct svc_fh *fhp; __be32 nfserr; + dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", SVCFH_fmt(&argp->fh), argp->attrs.ia_valid, (long) argp->attrs.ia_size); - fh_copy(&resp->fh, &argp->fh); - nfserr = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,0, (time_t)0); + fhp = fh_copy(&resp->fh, &argp->fh); + + /* + * NFSv2 does not differentiate between "set-[ac]time-to-now" + * which only requires access, and "set-[ac]time-to-X" which + * requires ownership. + * So if it looks like it might be "set both to the same time which + * is close to now", and if inode_change_ok fails, then we + * convert to "set to now" instead of "set to explicit time" + * + * We only call inode_change_ok as the last test as technically + * it is not an interface that we should be using. + */ +#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) +#define MAX_TOUCH_TIME_ERROR (30*60) + if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && + iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { + /* + * Looks probable. + * + * Now just make sure time is in the right ballpark. + * Solaris, at least, doesn't seem to care what the time + * request is. We require it be within 30 minutes of now. + */ + time_t delta = iap->ia_atime.tv_sec - get_seconds(); + struct inode *inode; + + nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); + if (nfserr) + goto done; + inode = d_inode(fhp->fh_dentry); + + if (delta < 0) + delta = -delta; + if (delta < MAX_TOUCH_TIME_ERROR && + inode_change_ok(inode, iap) != 0) { + /* + * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. + * This will cause notify_change to set these times + * to "now" + */ + iap->ia_valid &= ~BOTH_TIME_SET; + } + } + + nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0); +done: return nfsd_return_attrs(nfserr, resp); } diff --git a/kernel/fs/nfsd/nfssvc.c b/kernel/fs/nfsd/nfssvc.c index 9277cc91c..ad4e2377d 100644 --- a/kernel/fs/nfsd/nfssvc.c +++ b/kernel/fs/nfsd/nfssvc.c @@ -391,6 +391,14 @@ static int nfsd_get_default_max_blksize(void) return ret; } +static struct svc_serv_ops nfsd_thread_sv_ops = { + .svo_shutdown = nfsd_last_thread, + .svo_function = nfsd, + .svo_enqueue_xprt = svc_xprt_do_enqueue, + .svo_setup = svc_set_num_threads, + .svo_module = THIS_MODULE, +}; + int nfsd_create_serv(struct net *net) { int error; @@ -405,7 +413,7 @@ int nfsd_create_serv(struct net *net) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(); nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, - nfsd_last_thread, nfsd, THIS_MODULE); + &nfsd_thread_sv_ops); if (nn->nfsd_serv == NULL) return -ENOMEM; @@ -500,8 +508,8 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) /* apply the new numbers */ svc_get(nn->nfsd_serv); for (i = 0; i < n; i++) { - err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], - nthreads[i]); + err = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, + &nn->nfsd_serv->sv_pools[i], nthreads[i]); if (err) break; } @@ -540,7 +548,8 @@ nfsd_svc(int nrservs, struct net *net) error = nfsd_startup_net(nrservs, net); if (error) goto out_destroy; - error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs); + error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, + NULL, nrservs); if (error) goto out_shutdown; /* We are holding a reference to nn->nfsd_serv which diff --git a/kernel/fs/nfsd/state.h b/kernel/fs/nfsd/state.h index dbc4f85a5..77fdf4de9 100644 --- a/kernel/fs/nfsd/state.h +++ b/kernel/fs/nfsd/state.h @@ -67,6 +67,7 @@ struct nfsd4_callback { struct rpc_message cb_msg; struct nfsd4_callback_ops *cb_ops; struct work_struct cb_work; + int cb_seq_status; int cb_status; bool cb_need_restart; }; @@ -83,7 +84,7 @@ struct nfsd4_callback_ops { * fields that are of general use to any stateid. */ struct nfs4_stid { - atomic_t sc_count; + atomic_t sc_count; #define NFS4_OPEN_STID 1 #define NFS4_LOCK_STID 2 #define NFS4_DELEG_STID 4 @@ -93,11 +94,12 @@ struct nfs4_stid { #define NFS4_REVOKED_DELEG_STID 16 #define NFS4_CLOSED_DELEG_STID 32 #define NFS4_LAYOUT_STID 64 - unsigned char sc_type; - stateid_t sc_stateid; - struct nfs4_client *sc_client; - struct nfs4_file *sc_file; - void (*sc_free)(struct nfs4_stid *); + unsigned char sc_type; + stateid_t sc_stateid; + spinlock_t sc_lock; + struct nfs4_client *sc_client; + struct nfs4_file *sc_file; + void (*sc_free)(struct nfs4_stid *); }; /* @@ -363,15 +365,6 @@ struct nfs4_client_reclaim { char cr_recdir[HEXDIR_LEN]; /* recover dir */ }; -static inline void -update_stateid(stateid_t *stateid) -{ - stateid->si_generation++; - /* Wraparound recommendation from 3530bis-13 9.1.3.2: */ - if (stateid->si_generation == 0) - stateid->si_generation = 1; -} - /* A reasonable value for REPLAY_ISIZE was estimated as follows: * The OPEN response, typically the largest, requires * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) + @@ -533,15 +526,16 @@ struct nfs4_file { * Better suggestions welcome. */ struct nfs4_ol_stateid { - struct nfs4_stid st_stid; /* must be first field */ - struct list_head st_perfile; - struct list_head st_perstateowner; - struct list_head st_locks; - struct nfs4_stateowner * st_stateowner; - struct nfs4_clnt_odstate * st_clnt_odstate; - unsigned char st_access_bmap; - unsigned char st_deny_bmap; - struct nfs4_ol_stateid * st_openstp; + struct nfs4_stid st_stid; + struct list_head st_perfile; + struct list_head st_perstateowner; + struct list_head st_locks; + struct nfs4_stateowner *st_stateowner; + struct nfs4_clnt_odstate *st_clnt_odstate; + unsigned char st_access_bmap; + unsigned char st_deny_bmap; + struct nfs4_ol_stateid *st_openstp; + struct rw_semaphore st_rwsem; }; static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) @@ -560,6 +554,7 @@ struct nfs4_layout_stateid { struct nfsd4_callback ls_recall; stateid_t ls_recall_sid; bool ls_recalled; + struct mutex ls_mutex; }; static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) @@ -582,9 +577,9 @@ enum nfsd4_cb_op { struct nfsd4_compound_state; struct nfsd_net; -extern __be32 nfs4_preprocess_stateid_op(struct net *net, - struct nfsd4_compound_state *cstate, - stateid_t *stateid, int flags, struct file **filp); +extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + int flags, struct file **filp, bool *tmp_file); __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); @@ -592,6 +587,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); +void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); extern void nfs4_release_reclaim(struct nfsd_net *); extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, diff --git a/kernel/fs/nfsd/trace.c b/kernel/fs/nfsd/trace.c index 82f890705..90967466a 100644 --- a/kernel/fs/nfsd/trace.c +++ b/kernel/fs/nfsd/trace.c @@ -1,5 +1,3 @@ -#include "state.h" - #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/kernel/fs/nfsd/trace.h b/kernel/fs/nfsd/trace.h index c668520c3..0befe7627 100644 --- a/kernel/fs/nfsd/trace.h +++ b/kernel/fs/nfsd/trace.h @@ -9,6 +9,8 @@ #include <linux/tracepoint.h> +#include "state.h" + DECLARE_EVENT_CLASS(nfsd_stateid_class, TP_PROTO(stateid_t *stp), TP_ARGS(stp), diff --git a/kernel/fs/nfsd/vfs.c b/kernel/fs/nfsd/vfs.c index 84d770be0..994d66fbb 100644 --- a/kernel/fs/nfsd/vfs.c +++ b/kernel/fs/nfsd/vfs.c @@ -302,42 +302,6 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { - /* - * NFSv2 does not differentiate between "set-[ac]time-to-now" - * which only requires access, and "set-[ac]time-to-X" which - * requires ownership. - * So if it looks like it might be "set both to the same time which - * is close to now", and if inode_change_ok fails, then we - * convert to "set to now" instead of "set to explicit time" - * - * We only call inode_change_ok as the last test as technically - * it is not an interface that we should be using. - */ -#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) -#define MAX_TOUCH_TIME_ERROR (30*60) - if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && - iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { - /* - * Looks probable. - * - * Now just make sure time is in the right ballpark. - * Solaris, at least, doesn't seem to care what the time - * request is. We require it be within 30 minutes of now. - */ - time_t delta = iap->ia_atime.tv_sec - get_seconds(); - if (delta < 0) - delta = -delta; - if (delta < MAX_TOUCH_TIME_ERROR && - inode_change_ok(inode, iap) != 0) { - /* - * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. - * This will cause notify_change to set these times - * to "now" - */ - iap->ia_valid &= ~BOTH_TIME_SET; - } - } - /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; @@ -538,16 +502,11 @@ __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, loff_t len, int flags) { - __be32 err; int error; if (!S_ISREG(file_inode(file)->i_mode)) return nfserr_inval; - err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, NFSD_MAY_WRITE); - if (err) - return err; - error = vfs_fallocate(file, flags, offset, len); if (!error) error = commit_metadata(fhp); @@ -744,7 +703,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, host_err = ima_file_check(file, may_flags, 0); if (host_err) { - nfsd_close(file); + fput(file); goto out_nfserr; } @@ -761,23 +720,12 @@ out: return err; } -/* - * Close a file. - */ -void -nfsd_close(struct file *filp) -{ - fput(filp); -} - -/* - * Obtain the readahead parameters for the file - * specified by (dev, ino). - */ - -static inline struct raparms * -nfsd_get_raparms(dev_t dev, ino_t ino) +struct raparms * +nfsd_init_raparms(struct file *file) { + struct inode *inode = file_inode(file); + dev_t dev = inode->i_sb->s_dev; + ino_t ino = inode->i_ino; struct raparms *ra, **rap, **frap = NULL; int depth = 0; unsigned int hash; @@ -814,9 +762,23 @@ found: ra->p_count++; nfsdstats.ra_depth[depth*10/nfsdstats.ra_size]++; spin_unlock(&rab->pb_lock); + + if (ra->p_set) + file->f_ra = ra->p_ra; return ra; } +void nfsd_put_raparams(struct file *file, struct raparms *ra) +{ + struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex]; + + spin_lock(&rab->pb_lock); + ra->p_ra = file->f_ra; + ra->p_set = 1; + ra->p_count--; + spin_unlock(&rab->pb_lock); +} + /* * Grab and keep cached pages associated with a file in the svc_rqst * so that they can be passed to the network sendmsg/sendpage routines @@ -945,7 +907,7 @@ static int wait_for_concurrent_writes(struct file *file) return err; } -static __be32 +__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt, int *stablep) @@ -1009,40 +971,6 @@ out_nfserr: return err; } -__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct file **file, struct raparms **ra) -{ - struct inode *inode; - __be32 err; - - err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file); - if (err) - return err; - - inode = file_inode(*file); - - /* Get readahead parameters */ - *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); - - if (*ra && (*ra)->p_set) - (*file)->f_ra = (*ra)->p_ra; - return nfs_ok; -} - -void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra) -{ - /* Write back readahead params */ - if (ra) { - struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex]; - spin_lock(&rab->pb_lock); - ra->p_ra = file->f_ra; - ra->p_set = 1; - ra->p_count--; - spin_unlock(&rab->pb_lock); - } - nfsd_close(file); -} - /* * Read data from a file. count must contain the requested read count * on entry. On return, *count contains the number of bytes actually read. @@ -1055,13 +983,15 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct raparms *ra; __be32 err; - err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); if (err) return err; + ra = nfsd_init_raparms(file); err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); - - nfsd_put_tmp_read_open(file, ra); + if (ra) + nfsd_put_raparams(file, ra); + fput(file); return err; } @@ -1093,7 +1023,7 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (cnt) err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt, stablep); - nfsd_close(file); + fput(file); } out: return err; @@ -1138,7 +1068,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfserr_notsupp; } - nfsd_close(file); + fput(file); out: return err; } @@ -1319,12 +1249,6 @@ out_nfserr: #ifdef CONFIG_NFSD_V3 -static inline int nfsd_create_is_exclusive(int createmode) -{ - return createmode == NFS3_CREATE_EXCLUSIVE - || createmode == NFS4_CREATE_EXCLUSIVE4_1; -} - /* * NFSv3 and NFSv4 version of nfsd_create */ @@ -1707,7 +1631,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, /* cannot use fh_lock as we need deadlock protective ordering * so do it by hand */ trap = lock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = 1; + ffhp->fh_locked = tfhp->fh_locked = true; fill_pre_wcc(ffhp); fill_pre_wcc(tfhp); @@ -1757,7 +1681,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, fill_post_wcc(ffhp); fill_post_wcc(tfhp); unlock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = 0; + ffhp->fh_locked = tfhp->fh_locked = false; fh_drop_write(ffhp); out: @@ -1977,7 +1901,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, if (err == nfserr_eof || err == nfserr_toosmall) err = nfs_ok; /* can still be found in ->err */ out_close: - nfsd_close(file); + fput(file); out: return err; } diff --git a/kernel/fs/nfsd/vfs.h b/kernel/fs/nfsd/vfs.h index 2050cb016..fcfc48cbe 100644 --- a/kernel/fs/nfsd/vfs.h +++ b/kernel/fs/nfsd/vfs.h @@ -71,11 +71,7 @@ __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, #endif /* CONFIG_NFSD_V3 */ __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); -void nfsd_close(struct file *); struct raparms; -__be32 nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *, - struct file **, struct raparms **); -void nfsd_put_tmp_read_open(struct file *, struct raparms *); __be32 nfsd_splice_read(struct svc_rqst *, struct file *, loff_t, unsigned long *); __be32 nfsd_readv(struct file *, loff_t, struct kvec *, int, @@ -84,6 +80,10 @@ __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, loff_t, struct kvec *, int, unsigned long *); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, loff_t, struct kvec *,int, unsigned long *, int *); +__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file *file, loff_t offset, + struct kvec *vec, int vlen, unsigned long *cnt, + int *stablep); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, @@ -104,19 +104,22 @@ __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, __be32 nfsd_permission(struct svc_rqst *, struct svc_export *, struct dentry *, int); +struct raparms *nfsd_init_raparms(struct file *file); +void nfsd_put_raparams(struct file *file, struct raparms *ra); + static inline int fh_want_write(struct svc_fh *fh) { int ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) - fh->fh_want_write = 1; + fh->fh_want_write = true; return ret; } static inline void fh_drop_write(struct svc_fh *fh) { if (fh->fh_want_write) { - fh->fh_want_write = 0; + fh->fh_want_write = false; mnt_drop_write(fh->fh_export->ex_path.mnt); } } @@ -128,4 +131,10 @@ static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat) return nfserrno(vfs_getattr(&p, stat)); } +static inline int nfsd_create_is_exclusive(int createmode) +{ + return createmode == NFS3_CREATE_EXCLUSIVE + || createmode == NFS4_CREATE_EXCLUSIVE4_1; +} + #endif /* LINUX_NFSD_VFS_H */ diff --git a/kernel/fs/nfsd/xdr4.h b/kernel/fs/nfsd/xdr4.h index 2f8c092be..ce7362c88 100644 --- a/kernel/fs/nfsd/xdr4.h +++ b/kernel/fs/nfsd/xdr4.h @@ -273,6 +273,7 @@ struct nfsd4_read { u32 rd_length; /* request */ int rd_vlen; struct file *rd_filp; + bool rd_tmp_file; struct svc_rqst *rd_rqstp; /* response */ struct svc_fh * rd_fhp; /* response */ @@ -631,7 +632,7 @@ static inline void set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) { BUG_ON(!fhp->fh_pre_saved); - cinfo->atomic = fhp->fh_post_saved; + cinfo->atomic = (u32)fhp->fh_post_saved; cinfo->change_supported = IS_I_VERSION(d_inode(fhp->fh_dentry)); cinfo->before_change = fhp->fh_pre_change; |