diff options
Diffstat (limited to 'fs/nfsd/nfs4xdr.c')
| -rw-r--r-- | fs/nfsd/nfs4xdr.c | 3771 |
1 files changed, 2504 insertions, 1267 deletions
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 0e6a179ecca..944275c8f56 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1,6 +1,4 @@ /* - * fs/nfs/nfs4xdr.c - * * Server-side XDR for NFSv4 * * Copyright (c) 2002 The Regents of the University of Michigan. @@ -42,23 +40,26 @@ * at the end of nfs4svc_decode_compoundargs. */ -#include <linux/param.h> -#include <linux/smp.h> -#include <linux/fs.h> +#include <linux/slab.h> #include <linux/namei.h> -#include <linux/vfs.h> -#include <linux/sunrpc/xdr.h> -#include <linux/sunrpc/svc.h> -#include <linux/sunrpc/clnt.h> -#include <linux/nfsd/nfsd.h> -#include <linux/nfsd/state.h> -#include <linux/nfsd/xdr4.h> -#include <linux/nfsd_idmap.h> -#include <linux/nfs4.h> -#include <linux/nfs4_acl.h> -#include <linux/sunrpc/gss_api.h> +#include <linux/statfs.h> +#include <linux/utsname.h> +#include <linux/pagemap.h> #include <linux/sunrpc/svcauth_gss.h> +#include "idmap.h" +#include "acl.h" +#include "xdr4.h" +#include "vfs.h" +#include "state.h" +#include "cache.h" +#include "netns.h" + +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL +#include <linux/security.h> +#endif + + #define NFSDDBG_FACILITY NFSDDBG_XDR /* @@ -70,30 +71,20 @@ #define NFS4_REFERRAL_FSID_MINOR 0x8000000ULL static __be32 -check_filename(char *str, int len, __be32 err) +check_filename(char *str, int len) { int i; if (len == 0) return nfserr_inval; if (isdotent(str, len)) - return err; + return nfserr_badname; for (i = 0; i < len; i++) if (str[i] == '/') - return err; + return nfserr_badname; return 0; } -/* - * START OF "GENERIC" DECODE ROUTINES. - * These may look a little ugly since they are imported from a "generic" - * set of XDR encode/decode routines which are intended to be shared by - * all of our NFSv4 implementations (OpenBSD, MacOS X...). - * - * If the pain of reading these is too great, it should be a straightforward - * task to translate them into Linux-specific versions which are more - * consistent with the style used in NFSv2/v3... - */ #define DECODE_HEAD \ __be32 *p; \ __be32 status @@ -107,16 +98,6 @@ xdr_error: \ status = nfserr_bad_xdr; \ goto out -#define READ32(x) (x) = ntohl(*p++) -#define READ64(x) do { \ - (x) = (u64)ntohl(*p++) << 32; \ - (x) |= ntohl(*p++); \ -} while (0) -#define READTIME(x) do { \ - p++; \ - (x) = ntohl(*p++); \ - p++; \ -} while (0) #define READMEM(x,nbytes) do { \ x = (char *)p; \ p += XDR_QUADLEN(nbytes); \ @@ -148,6 +129,19 @@ xdr_error: \ } \ } while (0) +static void next_decode_page(struct nfsd4_compoundargs *argp) +{ + argp->p = page_address(argp->pagelist[0]); + argp->pagelist++; + if (argp->pagelen < PAGE_SIZE) { + argp->end = argp->p + (argp->pagelen>>2); + argp->pagelen = 0; + } else { + argp->end = argp->p + (PAGE_SIZE>>2); + argp->pagelen -= PAGE_SIZE; + } +} + static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes) { /* We want more bytes than seem to be available. @@ -175,21 +169,26 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes) * guarantee p points to at least nbytes bytes. */ memcpy(p, argp->p, avail); - /* step to next page */ - argp->p = page_address(argp->pagelist[0]); - argp->pagelist++; - if (argp->pagelen < PAGE_SIZE) { - argp->end = p + (argp->pagelen>>2); - argp->pagelen = 0; - } else { - argp->end = p + (PAGE_SIZE>>2); - argp->pagelen -= PAGE_SIZE; - } + next_decode_page(argp); memcpy(((char*)p)+avail, argp->p, (nbytes - avail)); argp->p += XDR_QUADLEN(nbytes - avail); return p; } +static int zero_clientid(clientid_t *clid) +{ + return (clid->cl_boot == 0) && (clid->cl_id == 0); +} + +/** + * defer_free - mark an allocation as deferred freed + * @argp: NFSv4 compound argument structure to be freed with + * @release: release callback to free @p, typically kfree() + * @p: pointer to be freed + * + * Marks @p to be freed when processing the compound operation + * described in @argp finishes. + */ static int defer_free(struct nfsd4_compoundargs *argp, void (*release)(const void *), void *p) @@ -206,13 +205,22 @@ defer_free(struct nfsd4_compoundargs *argp, return 0; } +/** + * savemem - duplicate a chunk of memory for later processing + * @argp: NFSv4 compound argument structure to be freed with + * @p: pointer to be duplicated + * @nbytes: length to be duplicated + * + * Returns a pointer to a copy of @nbytes bytes of memory at @p + * that are preserved until processing of the NFSv4 compound + * operation described by @argp finishes. + */ static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes) { if (p == argp->tmp) { - p = kmalloc(nbytes, GFP_KERNEL); + p = kmemdup(argp->tmp, nbytes, GFP_KERNEL); if (!p) return NULL; - memcpy(p, argp->tmp, nbytes); } else { BUG_ON(p != argp->tmpp); argp->tmpp = NULL; @@ -232,139 +240,131 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval) bmval[0] = 0; bmval[1] = 0; + bmval[2] = 0; READ_BUF(4); - READ32(bmlen); + bmlen = be32_to_cpup(p++); if (bmlen > 1000) goto xdr_error; READ_BUF(bmlen << 2); if (bmlen > 0) - READ32(bmval[0]); + bmval[0] = be32_to_cpup(p++); if (bmlen > 1) - READ32(bmval[1]); + bmval[1] = be32_to_cpup(p++); + if (bmlen > 2) + bmval[2] = be32_to_cpup(p++); DECODE_TAIL; } static __be32 -nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *iattr, - struct nfs4_acl **acl) +nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, + struct iattr *iattr, struct nfs4_acl **acl, + struct xdr_netobj *label) { int expected_len, len = 0; u32 dummy32; + u64 sec; char *buf; - int host_err; DECODE_HEAD; iattr->ia_valid = 0; if ((status = nfsd4_decode_bitmap(argp, bmval))) return status; - /* - * According to spec, unsupported attributes return ERR_ATTRNOTSUPP; - * read-only attributes return ERR_INVAL. - */ - if ((bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0) || (bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1)) - return nfserr_attrnotsupp; - if ((bmval[0] & ~NFSD_WRITEABLE_ATTRS_WORD0) || (bmval[1] & ~NFSD_WRITEABLE_ATTRS_WORD1)) - return nfserr_inval; - READ_BUF(4); - READ32(expected_len); + expected_len = be32_to_cpup(p++); if (bmval[0] & FATTR4_WORD0_SIZE) { READ_BUF(8); len += 8; - READ64(iattr->ia_size); + p = xdr_decode_hyper(p, &iattr->ia_size); iattr->ia_valid |= ATTR_SIZE; } if (bmval[0] & FATTR4_WORD0_ACL) { - int nace; + u32 nace; struct nfs4_ace *ace; READ_BUF(4); len += 4; - READ32(nace); + nace = be32_to_cpup(p++); if (nace > NFS4_ACL_MAX) - return nfserr_resource; + return nfserr_fbig; *acl = nfs4_acl_new(nace); - if (*acl == NULL) { - host_err = -ENOMEM; - goto out_nfserr; - } + if (*acl == NULL) + return nfserr_jukebox; + defer_free(argp, kfree, *acl); (*acl)->naces = nace; for (ace = (*acl)->aces; ace < (*acl)->aces + nace; ace++) { READ_BUF(16); len += 16; - READ32(ace->type); - READ32(ace->flag); - READ32(ace->access_mask); - READ32(dummy32); + ace->type = be32_to_cpup(p++); + ace->flag = be32_to_cpup(p++); + ace->access_mask = be32_to_cpup(p++); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); len += XDR_QUADLEN(dummy32) << 2; READMEM(buf, dummy32); ace->whotype = nfs4_acl_get_whotype(buf, dummy32); - host_err = 0; + status = nfs_ok; if (ace->whotype != NFS4_ACL_WHO_NAMED) - ace->who = 0; + ; else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) - host_err = nfsd_map_name_to_gid(argp->rqstp, - buf, dummy32, &ace->who); + status = nfsd_map_name_to_gid(argp->rqstp, + buf, dummy32, &ace->who_gid); else - host_err = nfsd_map_name_to_uid(argp->rqstp, - buf, dummy32, &ace->who); - if (host_err) - goto out_nfserr; + status = nfsd_map_name_to_uid(argp->rqstp, + buf, dummy32, &ace->who_uid); + if (status) + return status; } } else *acl = NULL; if (bmval[1] & FATTR4_WORD1_MODE) { READ_BUF(4); len += 4; - READ32(iattr->ia_mode); + iattr->ia_mode = be32_to_cpup(p++); iattr->ia_mode &= (S_IFMT | S_IALLUGO); iattr->ia_valid |= ATTR_MODE; } if (bmval[1] & FATTR4_WORD1_OWNER) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); - if ((host_err = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid))) - goto out_nfserr; + if ((status = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid))) + return status; iattr->ia_valid |= ATTR_UID; } if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); - if ((host_err = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid))) - goto out_nfserr; + if ((status = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid))) + return status; iattr->ia_valid |= ATTR_GID; } if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: /* We require the high 32 bits of 'seconds' to be 0, and we ignore all 32 bits of 'nseconds'. */ READ_BUF(12); len += 12; - READ32(dummy32); - if (dummy32) - return nfserr_inval; - READ32(iattr->ia_atime.tv_sec); - READ32(iattr->ia_atime.tv_nsec); + p = xdr_decode_hyper(p, &sec); + iattr->ia_atime.tv_sec = (time_t)sec; + iattr->ia_atime.tv_nsec = be32_to_cpup(p++); if (iattr->ia_atime.tv_nsec >= (u32)1000000000) return nfserr_inval; iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); @@ -376,35 +376,19 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *ia goto xdr_error; } } - if (bmval[1] & FATTR4_WORD1_TIME_METADATA) { - /* We require the high 32 bits of 'seconds' to be 0, and we ignore - all 32 bits of 'nseconds'. */ - READ_BUF(12); - len += 12; - READ32(dummy32); - if (dummy32) - return nfserr_inval; - READ32(iattr->ia_ctime.tv_sec); - READ32(iattr->ia_ctime.tv_nsec); - if (iattr->ia_ctime.tv_nsec >= (u32)1000000000) - return nfserr_inval; - iattr->ia_valid |= ATTR_CTIME; - } if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: /* We require the high 32 bits of 'seconds' to be 0, and we ignore all 32 bits of 'nseconds'. */ READ_BUF(12); len += 12; - READ32(dummy32); - if (dummy32) - return nfserr_inval; - READ32(iattr->ia_mtime.tv_sec); - READ32(iattr->ia_mtime.tv_nsec); + p = xdr_decode_hyper(p, &sec); + iattr->ia_mtime.tv_sec = sec; + iattr->ia_mtime.tv_nsec = be32_to_cpup(p++); if (iattr->ia_mtime.tv_nsec >= (u32)1000000000) return nfserr_inval; iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); @@ -416,14 +400,53 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *ia goto xdr_error; } } - if (len != expected_len) + + label->len = 0; +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { + READ_BUF(4); + len += 4; + dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */ + READ_BUF(4); + len += 4; + dummy32 = be32_to_cpup(p++); /* pi: we don't use it either */ + READ_BUF(4); + len += 4; + dummy32 = be32_to_cpup(p++); + READ_BUF(dummy32); + if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN) + return nfserr_badlabel; + len += (XDR_QUADLEN(dummy32) << 2); + READMEM(buf, dummy32); + label->data = kzalloc(dummy32 + 1, GFP_KERNEL); + if (!label->data) + return nfserr_jukebox; + label->len = dummy32; + defer_free(argp, kfree, label->data); + memcpy(label->data, buf, dummy32); + } +#endif + + if (bmval[0] & ~NFSD_WRITEABLE_ATTRS_WORD0 + || bmval[1] & ~NFSD_WRITEABLE_ATTRS_WORD1 + || bmval[2] & ~NFSD_WRITEABLE_ATTRS_WORD2) + READ_BUF(expected_len - len); + else if (len != expected_len) goto xdr_error; DECODE_TAIL; +} -out_nfserr: - status = nfserrno(host_err); - goto out; +static __be32 +nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid) +{ + DECODE_HEAD; + + READ_BUF(sizeof(stateid_t)); + sid->si_generation = be32_to_cpup(p++); + COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); + + DECODE_TAIL; } static __be32 @@ -432,21 +455,122 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access DECODE_HEAD; READ_BUF(4); - READ32(access->ac_req_access); + access->ac_req_access = be32_to_cpup(p++); DECODE_TAIL; } +static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) +{ + DECODE_HEAD; + u32 dummy, uid, gid; + char *machine_name; + int i; + int nr_secflavs; + + /* callback_sec_params4 */ + READ_BUF(4); + nr_secflavs = be32_to_cpup(p++); + if (nr_secflavs) + cbs->flavor = (u32)(-1); + else + /* Is this legal? Be generous, take it to mean AUTH_NONE: */ + cbs->flavor = 0; + for (i = 0; i < nr_secflavs; ++i) { + READ_BUF(4); + dummy = be32_to_cpup(p++); + switch (dummy) { + case RPC_AUTH_NULL: + /* Nothing to read */ + if (cbs->flavor == (u32)(-1)) + cbs->flavor = RPC_AUTH_NULL; + break; + case RPC_AUTH_UNIX: + READ_BUF(8); + /* stamp */ + dummy = be32_to_cpup(p++); + + /* machine name */ + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + SAVEMEM(machine_name, dummy); + + /* uid, gid */ + READ_BUF(8); + uid = be32_to_cpup(p++); + gid = be32_to_cpup(p++); + + /* more gids */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy * 4); + if (cbs->flavor == (u32)(-1)) { + kuid_t kuid = make_kuid(&init_user_ns, uid); + kgid_t kgid = make_kgid(&init_user_ns, gid); + if (uid_valid(kuid) && gid_valid(kgid)) { + cbs->uid = kuid; + cbs->gid = kgid; + cbs->flavor = RPC_AUTH_UNIX; + } else { + dprintk("RPC_AUTH_UNIX with invalid" + "uid or gid ignoring!\n"); + } + } + break; + case RPC_AUTH_GSS: + dprintk("RPC_AUTH_GSS callback secflavor " + "not supported!\n"); + READ_BUF(8); + /* gcbp_service */ + dummy = be32_to_cpup(p++); + /* gcbp_handle_from_server */ + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + /* gcbp_handle_from_client */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + break; + default: + dprintk("Illegal callback secflavor\n"); + return nfserr_inval; + } + } + DECODE_TAIL; +} + +static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) +{ + DECODE_HEAD; + + READ_BUF(4); + bc->bc_cb_program = be32_to_cpup(p++); + nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); + + DECODE_TAIL; +} + +static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts) +{ + DECODE_HEAD; + + READ_BUF(NFS4_MAX_SESSIONID_LEN + 8); + COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN); + bcts->dir = be32_to_cpup(p++); + /* XXX: skipping ctsa_use_conn_in_rdma_mode. Perhaps Tom Tucker + * could help us figure out we should be using it. */ + DECODE_TAIL; +} + static __be32 nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) { DECODE_HEAD; - close->cl_stateowner = NULL; - READ_BUF(4 + sizeof(stateid_t)); - READ32(close->cl_seqid); - READ32(close->cl_stateid.si_generation); - COPYMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t)); + READ_BUF(4); + close->cl_seqid = be32_to_cpup(p++); + return nfsd4_decode_stateid(argp, &close->cl_stateid); DECODE_TAIL; } @@ -458,8 +582,8 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit DECODE_HEAD; READ_BUF(12); - READ64(commit->co_offset); - READ32(commit->co_count); + p = xdr_decode_hyper(p, &commit->co_offset); + commit->co_count = be32_to_cpup(p++); DECODE_TAIL; } @@ -470,19 +594,30 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create DECODE_HEAD; READ_BUF(4); - READ32(create->cr_type); + create->cr_type = be32_to_cpup(p++); switch (create->cr_type) { case NF4LNK: READ_BUF(4); - READ32(create->cr_linklen); + create->cr_linklen = be32_to_cpup(p++); READ_BUF(create->cr_linklen); - SAVEMEM(create->cr_linkname, create->cr_linklen); + /* + * The VFS will want a null-terminated string, and + * null-terminating in place isn't safe since this might + * end on a page boundary: + */ + create->cr_linkname = + kmalloc(create->cr_linklen + 1, GFP_KERNEL); + if (!create->cr_linkname) + return nfserr_jukebox; + memcpy(create->cr_linkname, p, create->cr_linklen); + create->cr_linkname[create->cr_linklen] = '\0'; + defer_free(argp, kfree, create->cr_linkname); break; case NF4BLK: case NF4CHR: READ_BUF(8); - READ32(create->cr_specdata1); - READ32(create->cr_specdata2); + create->cr_specdata1 = be32_to_cpup(p++); + create->cr_specdata2 = be32_to_cpup(p++); break; case NF4SOCK: case NF4FIFO: @@ -492,13 +627,15 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create } READ_BUF(4); - READ32(create->cr_namelen); + create->cr_namelen = be32_to_cpup(p++); READ_BUF(create->cr_namelen); SAVEMEM(create->cr_name, create->cr_namelen); - if ((status = check_filename(create->cr_name, create->cr_namelen, nfserr_inval))) + if ((status = check_filename(create->cr_name, create->cr_namelen))) return status; - if ((status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr, &create->cr_acl))) + status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr, + &create->cr_acl, &create->cr_label); + if (status) goto out; DECODE_TAIL; @@ -507,13 +644,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create static inline __be32 nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr) { - DECODE_HEAD; - - READ_BUF(sizeof(stateid_t)); - READ32(dr->dr_stateid.si_generation); - COPYMEM(&dr->dr_stateid.si_opaque, sizeof(stateid_opaque_t)); - - DECODE_TAIL; + return nfsd4_decode_stateid(argp, &dr->dr_stateid); } static inline __be32 @@ -528,10 +659,10 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) DECODE_HEAD; READ_BUF(4); - READ32(link->li_namelen); + link->li_namelen = be32_to_cpup(p++); READ_BUF(link->li_namelen); SAVEMEM(link->li_name, link->li_namelen); - if ((status = check_filename(link->li_name, link->li_namelen, nfserr_inval))) + if ((status = check_filename(link->li_name, link->li_namelen))) return status; DECODE_TAIL; @@ -542,35 +673,36 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) { DECODE_HEAD; - lock->lk_replay_owner = NULL; /* * type, reclaim(boolean), offset, length, new_lock_owner(boolean) */ READ_BUF(28); - READ32(lock->lk_type); + lock->lk_type = be32_to_cpup(p++); if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT)) goto xdr_error; - READ32(lock->lk_reclaim); - READ64(lock->lk_offset); - READ64(lock->lk_length); - READ32(lock->lk_is_new); + lock->lk_reclaim = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &lock->lk_offset); + p = xdr_decode_hyper(p, &lock->lk_length); + lock->lk_is_new = be32_to_cpup(p++); if (lock->lk_is_new) { - READ_BUF(36); - READ32(lock->lk_new_open_seqid); - READ32(lock->lk_new_open_stateid.si_generation); - - COPYMEM(&lock->lk_new_open_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ32(lock->lk_new_lock_seqid); + READ_BUF(4); + lock->lk_new_open_seqid = be32_to_cpup(p++); + status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid); + if (status) + return status; + READ_BUF(8 + sizeof(clientid_t)); + lock->lk_new_lock_seqid = be32_to_cpup(p++); COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t)); - READ32(lock->lk_new_owner.len); + lock->lk_new_owner.len = be32_to_cpup(p++); READ_BUF(lock->lk_new_owner.len); READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len); } else { - READ_BUF(20); - READ32(lock->lk_old_lock_stateid.si_generation); - COPYMEM(&lock->lk_old_lock_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ32(lock->lk_old_lock_seqid); + status = nfsd4_decode_stateid(argp, &lock->lk_old_lock_stateid); + if (status) + return status; + READ_BUF(4); + lock->lk_old_lock_seqid = be32_to_cpup(p++); } DECODE_TAIL; @@ -582,13 +714,13 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) DECODE_HEAD; READ_BUF(32); - READ32(lockt->lt_type); + lockt->lt_type = be32_to_cpup(p++); if((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT)) goto xdr_error; - READ64(lockt->lt_offset); - READ64(lockt->lt_length); + p = xdr_decode_hyper(p, &lockt->lt_offset); + p = xdr_decode_hyper(p, &lockt->lt_length); COPYMEM(&lockt->lt_clientid, 8); - READ32(lockt->lt_owner.len); + lockt->lt_owner.len = be32_to_cpup(p++); READ_BUF(lockt->lt_owner.len); READMEM(lockt->lt_owner.data, lockt->lt_owner.len); @@ -600,16 +732,17 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) { DECODE_HEAD; - locku->lu_stateowner = NULL; - READ_BUF(24 + sizeof(stateid_t)); - READ32(locku->lu_type); + READ_BUF(8); + locku->lu_type = be32_to_cpup(p++); if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT)) goto xdr_error; - READ32(locku->lu_seqid); - READ32(locku->lu_stateid.si_generation); - COPYMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ64(locku->lu_offset); - READ64(locku->lu_length); + locku->lu_seqid = be32_to_cpup(p++); + status = nfsd4_decode_stateid(argp, &locku->lu_stateid); + if (status) + return status; + READ_BUF(16); + p = xdr_decode_hyper(p, &locku->lu_offset); + p = xdr_decode_hyper(p, &locku->lu_length); DECODE_TAIL; } @@ -620,51 +753,155 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup DECODE_HEAD; READ_BUF(4); - READ32(lookup->lo_len); + lookup->lo_len = be32_to_cpup(p++); READ_BUF(lookup->lo_len); SAVEMEM(lookup->lo_name, lookup->lo_len); - if ((status = check_filename(lookup->lo_name, lookup->lo_len, nfserr_noent))) + if ((status = check_filename(lookup->lo_name, lookup->lo_len))) return status; DECODE_TAIL; } +static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *share_access, u32 *deleg_want, u32 *deleg_when) +{ + __be32 *p; + u32 w; + + READ_BUF(4); + w = be32_to_cpup(p++); + *share_access = w & NFS4_SHARE_ACCESS_MASK; + *deleg_want = w & NFS4_SHARE_WANT_MASK; + if (deleg_when) + *deleg_when = w & NFS4_SHARE_WHEN_MASK; + + switch (w & NFS4_SHARE_ACCESS_MASK) { + case NFS4_SHARE_ACCESS_READ: + case NFS4_SHARE_ACCESS_WRITE: + case NFS4_SHARE_ACCESS_BOTH: + break; + default: + return nfserr_bad_xdr; + } + w &= ~NFS4_SHARE_ACCESS_MASK; + if (!w) + return nfs_ok; + if (!argp->minorversion) + return nfserr_bad_xdr; + switch (w & NFS4_SHARE_WANT_MASK) { + case NFS4_SHARE_WANT_NO_PREFERENCE: + case NFS4_SHARE_WANT_READ_DELEG: + case NFS4_SHARE_WANT_WRITE_DELEG: + case NFS4_SHARE_WANT_ANY_DELEG: + case NFS4_SHARE_WANT_NO_DELEG: + case NFS4_SHARE_WANT_CANCEL: + break; + default: + return nfserr_bad_xdr; + } + w &= ~NFS4_SHARE_WANT_MASK; + if (!w) + return nfs_ok; + + if (!deleg_when) /* open_downgrade */ + return nfserr_inval; + switch (w) { + case NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL: + case NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED: + case (NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL | + NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED): + return nfs_ok; + } +xdr_error: + return nfserr_bad_xdr; +} + +static __be32 nfsd4_decode_share_deny(struct nfsd4_compoundargs *argp, u32 *x) +{ + __be32 *p; + + READ_BUF(4); + *x = be32_to_cpup(p++); + /* Note: unlinke access bits, deny bits may be zero. */ + if (*x & ~NFS4_SHARE_DENY_BOTH) + return nfserr_bad_xdr; + return nfs_ok; +xdr_error: + return nfserr_bad_xdr; +} + +static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_netobj *o) +{ + __be32 *p; + + READ_BUF(4); + o->len = be32_to_cpup(p++); + + if (o->len == 0 || o->len > NFS4_OPAQUE_LIMIT) + return nfserr_bad_xdr; + + READ_BUF(o->len); + SAVEMEM(o->data, o->len); + return nfs_ok; +xdr_error: + return nfserr_bad_xdr; +} + static __be32 nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) { DECODE_HEAD; + u32 dummy; memset(open->op_bmval, 0, sizeof(open->op_bmval)); open->op_iattr.ia_valid = 0; - open->op_stateowner = NULL; + open->op_openowner = NULL; + open->op_xdr_error = 0; /* seqid, share_access, share_deny, clientid, ownerlen */ - READ_BUF(16 + sizeof(clientid_t)); - READ32(open->op_seqid); - READ32(open->op_share_access); - READ32(open->op_share_deny); + READ_BUF(4); + open->op_seqid = be32_to_cpup(p++); + /* decode, yet ignore deleg_when until supported */ + status = nfsd4_decode_share_access(argp, &open->op_share_access, + &open->op_deleg_want, &dummy); + if (status) + goto xdr_error; + status = nfsd4_decode_share_deny(argp, &open->op_share_deny); + if (status) + goto xdr_error; + READ_BUF(sizeof(clientid_t)); COPYMEM(&open->op_clientid, sizeof(clientid_t)); - READ32(open->op_owner.len); - - /* owner, open_flag */ - READ_BUF(open->op_owner.len + 4); - SAVEMEM(open->op_owner.data, open->op_owner.len); - READ32(open->op_create); + status = nfsd4_decode_opaque(argp, &open->op_owner); + if (status) + goto xdr_error; + READ_BUF(4); + open->op_create = be32_to_cpup(p++); switch (open->op_create) { case NFS4_OPEN_NOCREATE: break; case NFS4_OPEN_CREATE: READ_BUF(4); - READ32(open->op_createmode); + open->op_createmode = be32_to_cpup(p++); switch (open->op_createmode) { case NFS4_CREATE_UNCHECKED: case NFS4_CREATE_GUARDED: - if ((status = nfsd4_decode_fattr(argp, open->op_bmval, &open->op_iattr, &open->op_acl))) + status = nfsd4_decode_fattr(argp, open->op_bmval, + &open->op_iattr, &open->op_acl, &open->op_label); + if (status) goto out; break; case NFS4_CREATE_EXCLUSIVE: - READ_BUF(8); - COPYMEM(open->op_verf.data, 8); + READ_BUF(NFS4_VERIFIER_SIZE); + COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE); + break; + case NFS4_CREATE_EXCLUSIVE4_1: + if (argp->minorversion < 1) + goto xdr_error; + READ_BUF(NFS4_VERIFIER_SIZE); + COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE); + status = nfsd4_decode_fattr(argp, open->op_bmval, + &open->op_iattr, &open->op_acl, &open->op_label); + if (status) + goto out; break; default: goto xdr_error; @@ -676,28 +913,43 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) /* open_claim */ READ_BUF(4); - READ32(open->op_claim_type); + open->op_claim_type = be32_to_cpup(p++); switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_NULL: case NFS4_OPEN_CLAIM_DELEGATE_PREV: READ_BUF(4); - READ32(open->op_fname.len); + open->op_fname.len = be32_to_cpup(p++); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); - if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval))) + if ((status = check_filename(open->op_fname.data, open->op_fname.len))) return status; break; case NFS4_OPEN_CLAIM_PREVIOUS: READ_BUF(4); - READ32(open->op_delegate_type); + open->op_delegate_type = be32_to_cpup(p++); break; case NFS4_OPEN_CLAIM_DELEGATE_CUR: - READ_BUF(sizeof(stateid_t) + 4); - COPYMEM(&open->op_delegate_stateid, sizeof(stateid_t)); - READ32(open->op_fname.len); + status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid); + if (status) + return status; + READ_BUF(4); + open->op_fname.len = be32_to_cpup(p++); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); - if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval))) + if ((status = check_filename(open->op_fname.data, open->op_fname.len))) + return status; + break; + case NFS4_OPEN_CLAIM_FH: + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + if (argp->minorversion < 1) + goto xdr_error; + /* void */ + break; + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + if (argp->minorversion < 1) + goto xdr_error; + status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid); + if (status) return status; break; default: @@ -711,13 +963,16 @@ static __be32 nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_confirm *open_conf) { DECODE_HEAD; - - open_conf->oc_stateowner = NULL; - READ_BUF(4 + sizeof(stateid_t)); - READ32(open_conf->oc_req_stateid.si_generation); - COPYMEM(&open_conf->oc_req_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ32(open_conf->oc_seqid); - + + if (argp->minorversion >= 1) + return nfserr_notsupp; + + status = nfsd4_decode_stateid(argp, &open_conf->oc_req_stateid); + if (status) + return status; + READ_BUF(4); + open_conf->oc_seqid = be32_to_cpup(p++); + DECODE_TAIL; } @@ -726,14 +981,18 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d { DECODE_HEAD; - open_down->od_stateowner = NULL; - READ_BUF(12 + sizeof(stateid_t)); - READ32(open_down->od_stateid.si_generation); - COPYMEM(&open_down->od_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ32(open_down->od_seqid); - READ32(open_down->od_share_access); - READ32(open_down->od_share_deny); - + status = nfsd4_decode_stateid(argp, &open_down->od_stateid); + if (status) + return status; + READ_BUF(4); + open_down->od_seqid = be32_to_cpup(p++); + status = nfsd4_decode_share_access(argp, &open_down->od_share_access, + &open_down->od_deleg_want, NULL); + if (status) + return status; + status = nfsd4_decode_share_deny(argp, &open_down->od_share_deny); + if (status) + return status; DECODE_TAIL; } @@ -743,7 +1002,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) DECODE_HEAD; READ_BUF(4); - READ32(putfh->pf_fhlen); + putfh->pf_fhlen = be32_to_cpup(p++); if (putfh->pf_fhlen > NFS4_FHSIZE) goto xdr_error; READ_BUF(putfh->pf_fhlen); @@ -753,15 +1012,24 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) } static __be32 +nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) +{ + if (argp->minorversion == 0) + return nfs_ok; + return nfserr_notsupp; +} + +static __be32 nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) { DECODE_HEAD; - READ_BUF(sizeof(stateid_t) + 12); - READ32(read->rd_stateid.si_generation); - COPYMEM(&read->rd_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ64(read->rd_offset); - READ32(read->rd_length); + status = nfsd4_decode_stateid(argp, &read->rd_stateid); + if (status) + return status; + READ_BUF(12); + p = xdr_decode_hyper(p, &read->rd_offset); + read->rd_length = be32_to_cpup(p++); DECODE_TAIL; } @@ -772,10 +1040,10 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read DECODE_HEAD; READ_BUF(24); - READ64(readdir->rd_cookie); + p = xdr_decode_hyper(p, &readdir->rd_cookie); COPYMEM(readdir->rd_verf.data, sizeof(readdir->rd_verf.data)); - READ32(readdir->rd_dircount); /* just in case you needed a useless field... */ - READ32(readdir->rd_maxcount); + readdir->rd_dircount = be32_to_cpup(p++); + readdir->rd_maxcount = be32_to_cpup(p++); if ((status = nfsd4_decode_bitmap(argp, readdir->rd_bmval))) goto out; @@ -788,10 +1056,10 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove DECODE_HEAD; READ_BUF(4); - READ32(remove->rm_namelen); + remove->rm_namelen = be32_to_cpup(p++); READ_BUF(remove->rm_namelen); SAVEMEM(remove->rm_name, remove->rm_namelen); - if ((status = check_filename(remove->rm_name, remove->rm_namelen, nfserr_noent))) + if ((status = check_filename(remove->rm_name, remove->rm_namelen))) return status; DECODE_TAIL; @@ -803,15 +1071,15 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename DECODE_HEAD; READ_BUF(4); - READ32(rename->rn_snamelen); + rename->rn_snamelen = be32_to_cpup(p++); READ_BUF(rename->rn_snamelen + 4); SAVEMEM(rename->rn_sname, rename->rn_snamelen); - READ32(rename->rn_tnamelen); + rename->rn_tnamelen = be32_to_cpup(p++); READ_BUF(rename->rn_tnamelen); SAVEMEM(rename->rn_tname, rename->rn_tnamelen); - if ((status = check_filename(rename->rn_sname, rename->rn_snamelen, nfserr_noent))) + if ((status = check_filename(rename->rn_sname, rename->rn_snamelen))) return status; - if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen, nfserr_inval))) + if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen))) return status; DECODE_TAIL; @@ -822,6 +1090,9 @@ nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid) { DECODE_HEAD; + if (argp->minorversion >= 1) + return nfserr_notsupp; + READ_BUF(sizeof(clientid_t)); COPYMEM(clientid, sizeof(clientid_t)); @@ -835,51 +1106,63 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, DECODE_HEAD; READ_BUF(4); - READ32(secinfo->si_namelen); + secinfo->si_namelen = be32_to_cpup(p++); READ_BUF(secinfo->si_namelen); SAVEMEM(secinfo->si_name, secinfo->si_namelen); - status = check_filename(secinfo->si_name, secinfo->si_namelen, - nfserr_noent); + status = check_filename(secinfo->si_name, secinfo->si_namelen); if (status) return status; DECODE_TAIL; } static __be32 -nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) +nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, + struct nfsd4_secinfo_no_name *sin) { DECODE_HEAD; - READ_BUF(sizeof(stateid_t)); - READ32(setattr->sa_stateid.si_generation); - COPYMEM(&setattr->sa_stateid.si_opaque, sizeof(stateid_opaque_t)); - if ((status = nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr, &setattr->sa_acl))) - goto out; - + READ_BUF(4); + sin->sin_style = be32_to_cpup(p++); DECODE_TAIL; } static __be32 +nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) +{ + __be32 status; + + status = nfsd4_decode_stateid(argp, &setattr->sa_stateid); + if (status) + return status; + return nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr, + &setattr->sa_acl, &setattr->sa_label); +} + +static __be32 nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid *setclientid) { DECODE_HEAD; - READ_BUF(12); - COPYMEM(setclientid->se_verf.data, 8); - READ32(setclientid->se_namelen); + if (argp->minorversion >= 1) + return nfserr_notsupp; - READ_BUF(setclientid->se_namelen + 8); - SAVEMEM(setclientid->se_name, setclientid->se_namelen); - READ32(setclientid->se_callback_prog); - READ32(setclientid->se_callback_netid_len); + READ_BUF(NFS4_VERIFIER_SIZE); + COPYMEM(setclientid->se_verf.data, NFS4_VERIFIER_SIZE); + + status = nfsd4_decode_opaque(argp, &setclientid->se_name); + if (status) + return nfserr_bad_xdr; + READ_BUF(8); + setclientid->se_callback_prog = be32_to_cpup(p++); + setclientid->se_callback_netid_len = be32_to_cpup(p++); READ_BUF(setclientid->se_callback_netid_len + 4); SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len); - READ32(setclientid->se_callback_addr_len); + setclientid->se_callback_addr_len = be32_to_cpup(p++); READ_BUF(setclientid->se_callback_addr_len + 4); SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len); - READ32(setclientid->se_callback_ident); + setclientid->se_callback_ident = be32_to_cpup(p++); DECODE_TAIL; } @@ -889,9 +1172,12 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s { DECODE_HEAD; - READ_BUF(8 + sizeof(nfs4_verifier)); + if (argp->minorversion >= 1) + return nfserr_notsupp; + + READ_BUF(8 + NFS4_VERIFIER_SIZE); COPYMEM(&scd_c->sc_clientid, 8); - COPYMEM(&scd_c->sc_confirm, sizeof(nfs4_verifier)); + COPYMEM(&scd_c->sc_confirm, NFS4_VERIFIER_SIZE); DECODE_TAIL; } @@ -900,33 +1186,16 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s static __be32 nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify) { -#if 0 - struct nfsd4_compoundargs save = { - .p = argp->p, - .end = argp->end, - .rqstp = argp->rqstp, - }; - u32 ve_bmval[2]; - struct iattr ve_iattr; /* request */ - struct nfs4_acl *ve_acl; /* request */ -#endif DECODE_HEAD; if ((status = nfsd4_decode_bitmap(argp, verify->ve_bmval))) goto out; /* For convenience's sake, we compare raw xdr'd attributes in - * nfsd4_proc_verify; however we still decode here just to return - * correct error in case of bad xdr. */ -#if 0 - status = nfsd4_decode_fattr(ve_bmval, &ve_iattr, &ve_acl); - if (status == nfserr_inval) { - status = nfserrno(status); - goto out; - } -#endif + * nfsd4_proc_verify */ + READ_BUF(4); - READ32(verify->ve_attrlen); + verify->ve_attrlen = be32_to_cpup(p++); READ_BUF(verify->ve_attrlen); SAVEMEM(verify->ve_attrval, verify->ve_attrlen); @@ -937,18 +1206,18 @@ static __be32 nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) { int avail; - int v; int len; DECODE_HEAD; - READ_BUF(sizeof(stateid_opaque_t) + 20); - READ32(write->wr_stateid.si_generation); - COPYMEM(&write->wr_stateid.si_opaque, sizeof(stateid_opaque_t)); - READ64(write->wr_offset); - READ32(write->wr_stable_how); + status = nfsd4_decode_stateid(argp, &write->wr_stateid); + if (status) + return status; + READ_BUF(16); + p = xdr_decode_hyper(p, &write->wr_offset); + write->wr_stable_how = be32_to_cpup(p++); if (write->wr_stable_how > 2) goto xdr_error; - READ32(write->wr_buflen); + write->wr_buflen = be32_to_cpup(p++); /* Sorry .. no magic macros for this.. * * READ_BUF(write->wr_buflen); @@ -960,27 +1229,26 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) __FILE__, __LINE__); goto xdr_error; } - argp->rqstp->rq_vec[0].iov_base = p; - argp->rqstp->rq_vec[0].iov_len = avail; - v = 0; - len = write->wr_buflen; - while (len > argp->rqstp->rq_vec[v].iov_len) { - len -= argp->rqstp->rq_vec[v].iov_len; - v++; - argp->rqstp->rq_vec[v].iov_base = page_address(argp->pagelist[0]); + write->wr_head.iov_base = p; + write->wr_head.iov_len = avail; + write->wr_pagelist = argp->pagelist; + + len = XDR_QUADLEN(write->wr_buflen) << 2; + if (len >= avail) { + int pages; + + len -= avail; + + pages = len >> PAGE_SHIFT; + argp->pagelist += pages; + argp->pagelen -= pages * PAGE_SIZE; + len -= pages * PAGE_SIZE; + + argp->p = (__be32 *)page_address(argp->pagelist[0]); argp->pagelist++; - if (argp->pagelen >= PAGE_SIZE) { - argp->rqstp->rq_vec[v].iov_len = PAGE_SIZE; - argp->pagelen -= PAGE_SIZE; - } else { - argp->rqstp->rq_vec[v].iov_len = argp->pagelen; - argp->pagelen -= len; - } + argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE); } - argp->end = (__be32*) (argp->rqstp->rq_vec[v].iov_base + argp->rqstp->rq_vec[v].iov_len); - argp->p = (__be32*) (argp->rqstp->rq_vec[v].iov_base + (XDR_QUADLEN(len) << 2)); - argp->rqstp->rq_vec[v].iov_len = len; - write->wr_vlen = v+1; + argp->p += XDR_QUADLEN(len); DECODE_TAIL; } @@ -990,34 +1258,381 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel { DECODE_HEAD; + if (argp->minorversion >= 1) + return nfserr_notsupp; + READ_BUF(12); COPYMEM(&rlockowner->rl_clientid, sizeof(clientid_t)); - READ32(rlockowner->rl_owner.len); + rlockowner->rl_owner.len = be32_to_cpup(p++); READ_BUF(rlockowner->rl_owner.len); READMEM(rlockowner->rl_owner.data, rlockowner->rl_owner.len); + if (argp->minorversion && !zero_clientid(&rlockowner->rl_clientid)) + return nfserr_inval; DECODE_TAIL; } static __be32 +nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, + struct nfsd4_exchange_id *exid) +{ + int dummy, tmp; + DECODE_HEAD; + + READ_BUF(NFS4_VERIFIER_SIZE); + COPYMEM(exid->verifier.data, NFS4_VERIFIER_SIZE); + + status = nfsd4_decode_opaque(argp, &exid->clname); + if (status) + return nfserr_bad_xdr; + + READ_BUF(4); + exid->flags = be32_to_cpup(p++); + + /* Ignore state_protect4_a */ + READ_BUF(4); + exid->spa_how = be32_to_cpup(p++); + switch (exid->spa_how) { + case SP4_NONE: + break; + case SP4_MACH_CRED: + /* spo_must_enforce */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy * 4); + p += dummy; + + /* spo_must_allow */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy * 4); + p += dummy; + break; + case SP4_SSV: + /* ssp_ops */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy * 4); + p += dummy; + + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy * 4); + p += dummy; + + /* ssp_hash_algs<> */ + READ_BUF(4); + tmp = be32_to_cpup(p++); + while (tmp--) { + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + } + + /* ssp_encr_algs<> */ + READ_BUF(4); + tmp = be32_to_cpup(p++); + while (tmp--) { + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + } + + /* ssp_window and ssp_num_gss_handles */ + READ_BUF(8); + dummy = be32_to_cpup(p++); + dummy = be32_to_cpup(p++); + break; + default: + goto xdr_error; + } + + /* Ignore Implementation ID */ + READ_BUF(4); /* nfs_impl_id4 array length */ + dummy = be32_to_cpup(p++); + + if (dummy > 1) + goto xdr_error; + + if (dummy == 1) { + /* nii_domain */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + + /* nii_name */ + READ_BUF(4); + dummy = be32_to_cpup(p++); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + + /* nii_date */ + READ_BUF(12); + p += 3; + } + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, + struct nfsd4_create_session *sess) +{ + DECODE_HEAD; + u32 dummy; + + READ_BUF(16); + COPYMEM(&sess->clientid, 8); + sess->seqid = be32_to_cpup(p++); + sess->flags = be32_to_cpup(p++); + + /* Fore channel attrs */ + READ_BUF(28); + dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */ + sess->fore_channel.maxreq_sz = be32_to_cpup(p++); + sess->fore_channel.maxresp_sz = be32_to_cpup(p++); + sess->fore_channel.maxresp_cached = be32_to_cpup(p++); + sess->fore_channel.maxops = be32_to_cpup(p++); + sess->fore_channel.maxreqs = be32_to_cpup(p++); + sess->fore_channel.nr_rdma_attrs = be32_to_cpup(p++); + if (sess->fore_channel.nr_rdma_attrs == 1) { + READ_BUF(4); + sess->fore_channel.rdma_attrs = be32_to_cpup(p++); + } else if (sess->fore_channel.nr_rdma_attrs > 1) { + dprintk("Too many fore channel attr bitmaps!\n"); + goto xdr_error; + } + + /* Back channel attrs */ + READ_BUF(28); + dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */ + sess->back_channel.maxreq_sz = be32_to_cpup(p++); + sess->back_channel.maxresp_sz = be32_to_cpup(p++); + sess->back_channel.maxresp_cached = be32_to_cpup(p++); + sess->back_channel.maxops = be32_to_cpup(p++); + sess->back_channel.maxreqs = be32_to_cpup(p++); + sess->back_channel.nr_rdma_attrs = be32_to_cpup(p++); + if (sess->back_channel.nr_rdma_attrs == 1) { + READ_BUF(4); + sess->back_channel.rdma_attrs = be32_to_cpup(p++); + } else if (sess->back_channel.nr_rdma_attrs > 1) { + dprintk("Too many back channel attr bitmaps!\n"); + goto xdr_error; + } + + READ_BUF(4); + sess->callback_prog = be32_to_cpup(p++); + nfsd4_decode_cb_sec(argp, &sess->cb_sec); + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, + struct nfsd4_destroy_session *destroy_session) +{ + DECODE_HEAD; + READ_BUF(NFS4_MAX_SESSIONID_LEN); + COPYMEM(destroy_session->sessionid.data, NFS4_MAX_SESSIONID_LEN); + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, + struct nfsd4_free_stateid *free_stateid) +{ + DECODE_HEAD; + + READ_BUF(sizeof(stateid_t)); + free_stateid->fr_stateid.si_generation = be32_to_cpup(p++); + COPYMEM(&free_stateid->fr_stateid.si_opaque, sizeof(stateid_opaque_t)); + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, + struct nfsd4_sequence *seq) +{ + DECODE_HEAD; + + READ_BUF(NFS4_MAX_SESSIONID_LEN + 16); + COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); + seq->seqid = be32_to_cpup(p++); + seq->slotid = be32_to_cpup(p++); + seq->maxslots = be32_to_cpup(p++); + seq->cachethis = be32_to_cpup(p++); + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid) +{ + int i; + __be32 *p, status; + struct nfsd4_test_stateid_id *stateid; + + READ_BUF(4); + test_stateid->ts_num_ids = ntohl(*p++); + + INIT_LIST_HEAD(&test_stateid->ts_stateid_list); + + for (i = 0; i < test_stateid->ts_num_ids; i++) { + stateid = kmalloc(sizeof(struct nfsd4_test_stateid_id), GFP_KERNEL); + if (!stateid) { + status = nfserrno(-ENOMEM); + goto out; + } + + defer_free(argp, kfree, stateid); + INIT_LIST_HEAD(&stateid->ts_id_list); + list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list); + + status = nfsd4_decode_stateid(argp, &stateid->ts_id_stateid); + if (status) + goto out; + } + + status = 0; +out: + return status; +xdr_error: + dprintk("NFSD: xdr error (%s:%d)\n", __FILE__, __LINE__); + status = nfserr_bad_xdr; + goto out; +} + +static __be32 nfsd4_decode_destroy_clientid(struct nfsd4_compoundargs *argp, struct nfsd4_destroy_clientid *dc) +{ + DECODE_HEAD; + + READ_BUF(8); + COPYMEM(&dc->clientid, 8); + + DECODE_TAIL; +} + +static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, struct nfsd4_reclaim_complete *rc) +{ + DECODE_HEAD; + + READ_BUF(4); + rc->rca_one_fs = be32_to_cpup(p++); + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) +{ + return nfs_ok; +} + +static __be32 +nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) +{ + return nfserr_notsupp; +} + +typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); + +static nfsd4_dec nfsd4_dec_ops[] = { + [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, + [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, + [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, + [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create, + [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn, + [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr, + [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_LINK] = (nfsd4_dec)nfsd4_decode_link, + [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock, + [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt, + [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku, + [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup, + [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop, + [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify, + [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open, + [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade, + [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh, + [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_putpubfh, + [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_READ] = (nfsd4_dec)nfsd4_decode_read, + [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir, + [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop, + [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove, + [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename, + [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew, + [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo, + [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr, + [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm, + [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify, + [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, + + /* new operations for NFSv4.1 */ + [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl, + [OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session, + [OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id, + [OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session, + [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, + [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, + [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, + [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, + [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_TEST_STATEID] = (nfsd4_dec)nfsd4_decode_test_stateid, + [OP_WANT_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_DESTROY_CLIENTID] = (nfsd4_dec)nfsd4_decode_destroy_clientid, + [OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete, +}; + +static inline bool +nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op) +{ + if (op->opnum < FIRST_NFS4_OP) + return false; + else if (argp->minorversion == 0 && op->opnum > LAST_NFS40_OP) + return false; + else if (argp->minorversion == 1 && op->opnum > LAST_NFS41_OP) + return false; + else if (argp->minorversion == 2 && op->opnum > LAST_NFS42_OP) + return false; + return true; +} + +static __be32 nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { DECODE_HEAD; struct nfsd4_op *op; + bool cachethis = false; + int auth_slack= argp->rqstp->rq_auth_slack; + int max_reply = auth_slack + 8; /* opcnt, status */ + int readcount = 0; + int readbytes = 0; int i; - /* - * XXX: According to spec, we should check the tag - * for UTF-8 compliance. I'm postponing this for - * now because it seems that some clients do use - * binary tags. - */ READ_BUF(4); - READ32(argp->taglen); + argp->taglen = be32_to_cpup(p++); READ_BUF(argp->taglen + 8); SAVEMEM(argp->tag, argp->taglen); - READ32(argp->minorversion); - READ32(argp->opcnt); + argp->minorversion = be32_to_cpup(p++); + argp->opcnt = be32_to_cpup(p++); + max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2); if (argp->taglen > NFSD4_MAX_TAGLEN) goto xdr_error; @@ -1033,399 +1648,330 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) } } + if (argp->minorversion > NFSD_SUPPORTED_MINOR_VERSION) + argp->opcnt = 0; + for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; - /* - * We can't use READ_BUF() here because we need to handle - * a missing opcode as an OP_WRITE + 1. So we need to check - * to see if we're truly at the end of our buffer or if there - * is another page we need to flip to. - */ - - if (argp->p == argp->end) { - if (argp->pagelen < 4) { - /* There isn't an opcode still on the wire */ - op->opnum = OP_WRITE + 1; - op->status = nfserr_bad_xdr; - argp->opcnt = i+1; - break; - } - - /* - * False alarm. We just hit a page boundary, but there - * is still data available. Move pointer across page - * boundary. *snip from READ_BUF* - */ - argp->p = page_address(argp->pagelist[0]); - argp->pagelist++; - if (argp->pagelen < PAGE_SIZE) { - argp->end = p + (argp->pagelen>>2); - argp->pagelen = 0; - } else { - argp->end = p + (PAGE_SIZE>>2); - argp->pagelen -= PAGE_SIZE; - } - } - op->opnum = ntohl(*argp->p++); + READ_BUF(4); + op->opnum = be32_to_cpup(p++); - switch (op->opnum) { - case 2: /* Reserved operation */ - op->opnum = OP_ILLEGAL; - if (argp->minorversion == 0) - op->status = nfserr_op_illegal; - else - op->status = nfserr_minor_vers_mismatch; - break; - case OP_ACCESS: - op->status = nfsd4_decode_access(argp, &op->u.access); - break; - case OP_CLOSE: - op->status = nfsd4_decode_close(argp, &op->u.close); - break; - case OP_COMMIT: - op->status = nfsd4_decode_commit(argp, &op->u.commit); - break; - case OP_CREATE: - op->status = nfsd4_decode_create(argp, &op->u.create); - break; - case OP_DELEGRETURN: - op->status = nfsd4_decode_delegreturn(argp, &op->u.delegreturn); - break; - case OP_GETATTR: - op->status = nfsd4_decode_getattr(argp, &op->u.getattr); - break; - case OP_GETFH: - op->status = nfs_ok; - break; - case OP_LINK: - op->status = nfsd4_decode_link(argp, &op->u.link); - break; - case OP_LOCK: - op->status = nfsd4_decode_lock(argp, &op->u.lock); - break; - case OP_LOCKT: - op->status = nfsd4_decode_lockt(argp, &op->u.lockt); - break; - case OP_LOCKU: - op->status = nfsd4_decode_locku(argp, &op->u.locku); - break; - case OP_LOOKUP: - op->status = nfsd4_decode_lookup(argp, &op->u.lookup); - break; - case OP_LOOKUPP: - op->status = nfs_ok; - break; - case OP_NVERIFY: - op->status = nfsd4_decode_verify(argp, &op->u.nverify); - break; - case OP_OPEN: - op->status = nfsd4_decode_open(argp, &op->u.open); - break; - case OP_OPEN_CONFIRM: - op->status = nfsd4_decode_open_confirm(argp, &op->u.open_confirm); - break; - case OP_OPEN_DOWNGRADE: - op->status = nfsd4_decode_open_downgrade(argp, &op->u.open_downgrade); - break; - case OP_PUTFH: - op->status = nfsd4_decode_putfh(argp, &op->u.putfh); - break; - case OP_PUTROOTFH: - op->status = nfs_ok; - break; - case OP_READ: - op->status = nfsd4_decode_read(argp, &op->u.read); - break; - case OP_READDIR: - op->status = nfsd4_decode_readdir(argp, &op->u.readdir); - break; - case OP_READLINK: - op->status = nfs_ok; - break; - case OP_REMOVE: - op->status = nfsd4_decode_remove(argp, &op->u.remove); - break; - case OP_RENAME: - op->status = nfsd4_decode_rename(argp, &op->u.rename); - break; - case OP_RESTOREFH: - op->status = nfs_ok; - break; - case OP_RENEW: - op->status = nfsd4_decode_renew(argp, &op->u.renew); - break; - case OP_SAVEFH: - op->status = nfs_ok; - break; - case OP_SECINFO: - op->status = nfsd4_decode_secinfo(argp, &op->u.secinfo); - break; - case OP_SETATTR: - op->status = nfsd4_decode_setattr(argp, &op->u.setattr); - break; - case OP_SETCLIENTID: - op->status = nfsd4_decode_setclientid(argp, &op->u.setclientid); - break; - case OP_SETCLIENTID_CONFIRM: - op->status = nfsd4_decode_setclientid_confirm(argp, &op->u.setclientid_confirm); - break; - case OP_VERIFY: - op->status = nfsd4_decode_verify(argp, &op->u.verify); - break; - case OP_WRITE: - op->status = nfsd4_decode_write(argp, &op->u.write); - break; - case OP_RELEASE_LOCKOWNER: - op->status = nfsd4_decode_release_lockowner(argp, &op->u.release_lockowner); - break; - default: + if (nfsd4_opnum_in_range(argp, op)) + op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); + else { op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; - break; } + /* + * We'll try to cache the result in the DRC if any one + * op in the compound wants to be cached: + */ + cachethis |= nfsd4_cache_this_op(op); + + if (op->opnum == OP_READ) { + readcount++; + readbytes += nfsd4_max_reply(argp->rqstp, op); + } else + max_reply += nfsd4_max_reply(argp->rqstp, op); if (op->status) { argp->opcnt = i+1; break; } } + /* Sessions make the DRC unnecessary: */ + if (argp->minorversion) + cachethis = false; + svc_reserve(argp->rqstp, max_reply + readbytes); + argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; + + if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) + argp->rqstp->rq_splice_ok = false; DECODE_TAIL; } -/* - * END OF "GENERIC" DECODE ROUTINES. - */ - -/* - * START OF "GENERIC" ENCODE ROUTINES. - * These may look a little ugly since they are imported from a "generic" - * set of XDR encode/decode routines which are intended to be shared by - * all of our NFSv4 implementations (OpenBSD, MacOS X...). - * - * If the pain of reading these is too great, it should be a straightforward - * task to translate them into Linux-specific versions which are more - * consistent with the style used in NFSv2/v3... - */ -#define ENCODE_HEAD __be32 *p - -#define WRITE32(n) *p++ = htonl(n) -#define WRITE64(n) do { \ - *p++ = htonl((u32)((n) >> 32)); \ - *p++ = htonl((u32)(n)); \ -} while (0) -#define WRITEMEM(ptr,nbytes) do { \ - *(p + XDR_QUADLEN(nbytes) -1) = 0; \ - memcpy(p, ptr, nbytes); \ - p += XDR_QUADLEN(nbytes); \ -} while (0) -#define WRITECINFO(c) do { \ - *p++ = htonl(c.atomic); \ - *p++ = htonl(c.before_ctime_sec); \ - *p++ = htonl(c.before_ctime_nsec); \ - *p++ = htonl(c.after_ctime_sec); \ - *p++ = htonl(c.after_ctime_nsec); \ -} while (0) - -#define RESERVE_SPACE(nbytes) do { \ - p = resp->p; \ - BUG_ON(p + XDR_QUADLEN(nbytes) > resp->end); \ -} while (0) -#define ADJUST_ARGS() resp->p = p - -/* - * Header routine to setup seqid operation replay cache - */ -#define ENCODE_SEQID_OP_HEAD \ - __be32 *p; \ - __be32 *save; \ - \ - save = resp->p; -/* - * Routine for encoding the result of a "seqid-mutating" NFSv4 operation. This - * is where sequence id's are incremented, and the replay cache is filled. - * Note that we increment sequence id's here, at the last moment, so we're sure - * we know whether the error to be returned is a sequence id mutating error. - */ +static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode) +{ + if (IS_I_VERSION(inode)) { + p = xdr_encode_hyper(p, inode->i_version); + } else { + *p++ = cpu_to_be32(stat->ctime.tv_sec); + *p++ = cpu_to_be32(stat->ctime.tv_nsec); + } + return p; +} -#define ENCODE_SEQID_OP_TAIL(stateowner) do { \ - if (seqid_mutating_err(nfserr) && stateowner) { \ - stateowner->so_seqid++; \ - stateowner->so_replay.rp_status = nfserr; \ - stateowner->so_replay.rp_buflen = \ - (((char *)(resp)->p - (char *)save)); \ - memcpy(stateowner->so_replay.rp_buf, save, \ - stateowner->so_replay.rp_buflen); \ - } } while (0); +static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c) +{ + *p++ = cpu_to_be32(c->atomic); + if (c->change_supported) { + p = xdr_encode_hyper(p, c->before_change); + p = xdr_encode_hyper(p, c->after_change); + } else { + *p++ = cpu_to_be32(c->before_ctime_sec); + *p++ = cpu_to_be32(c->before_ctime_nsec); + *p++ = cpu_to_be32(c->after_ctime_sec); + *p++ = cpu_to_be32(c->after_ctime_nsec); + } + return p; +} /* Encode as an array of strings the string given with components - * seperated @sep. + * separated @sep, escaped with esc_enter and esc_exit. */ -static __be32 nfsd4_encode_components(char sep, char *components, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, + char *components, char esc_enter, + char esc_exit) { - __be32 *p = *pp; - __be32 *countp = p; + __be32 *p; + __be32 pathlen; + int pathlen_offset; int strlen, count=0; - char *str, *end; + char *str, *end, *next; dprintk("nfsd4_encode_components(%s)\n", components); - if ((*buflen -= 4) < 0) + + pathlen_offset = xdr->buf->len; + p = xdr_reserve_space(xdr, 4); + if (!p) return nfserr_resource; - WRITE32(0); /* We will fill this in with @count later */ + p++; /* We will fill this in with @count later */ + end = str = components; while (*end) { - for (; *end && (*end != sep); end++) - ; /* Point to end of component */ + bool found_esc = false; + + /* try to parse as esc_start, ..., esc_end, sep */ + if (*str == esc_enter) { + for (; *end && (*end != esc_exit); end++) + /* find esc_exit or end of string */; + next = end + 1; + if (*end && (!*next || *next == sep)) { + str++; + found_esc = true; + } + } + + if (!found_esc) + for (; *end && (*end != sep); end++) + /* find sep or end of string */; + strlen = end - str; if (strlen) { - if ((*buflen -= ((XDR_QUADLEN(strlen) << 2) + 4)) < 0) + p = xdr_reserve_space(xdr, strlen + 4); + if (!p) return nfserr_resource; - WRITE32(strlen); - WRITEMEM(str, strlen); + p = xdr_encode_opaque(p, str, strlen); count++; } else end++; str = end; } - *pp = p; - p = countp; - WRITE32(count); + pathlen = htonl(xdr->buf->len - pathlen_offset); + write_bytes_to_xdr_buf(xdr->buf, pathlen_offset, &pathlen, 4); return 0; } +/* Encode as an array of strings the string given with components + * separated @sep. + */ +static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep, + char *components) +{ + return nfsd4_encode_components_esc(xdr, sep, components, 0, 0); +} + /* * encode a location element of a fs_locations structure */ -static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr, + struct nfsd4_fs_location *location) { __be32 status; - __be32 *p = *pp; - status = nfsd4_encode_components(':', location->hosts, &p, buflen); + status = nfsd4_encode_components_esc(xdr, ':', location->hosts, + '[', ']'); if (status) return status; - status = nfsd4_encode_components('/', location->path, &p, buflen); + status = nfsd4_encode_components(xdr, '/', location->path); if (status) return status; - *pp = p; return 0; } /* - * Return the path to an export point in the pseudo filesystem namespace - * Returned string is safe to use as long as the caller holds a reference - * to @exp. + * Encode a path in RFC3530 'pathname4' format */ -static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 *stat) +static __be32 nfsd4_encode_path(struct xdr_stream *xdr, + const struct path *root, + const struct path *path) { - struct svc_fh tmp_fh; - char *path, *rootpath; - - fh_init(&tmp_fh, NFS4_FHSIZE); - *stat = exp_pseudoroot(rqstp, &tmp_fh); - if (*stat) - return NULL; - rootpath = tmp_fh.fh_export->ex_pathname; + struct path cur = *path; + __be32 *p; + struct dentry **components = NULL; + unsigned int ncomponents = 0; + __be32 err = nfserr_jukebox; - path = exp->ex_pathname; + dprintk("nfsd4_encode_components("); - if (strncmp(path, rootpath, strlen(rootpath))) { - dprintk("nfsd: fs_locations failed;" - "%s is not contained in %s\n", path, rootpath); - *stat = nfserr_notsupp; - return NULL; + path_get(&cur); + /* First walk the path up to the nfsd root, and store the + * dentries/path components in an array. + */ + for (;;) { + if (cur.dentry == root->dentry && cur.mnt == root->mnt) + break; + if (cur.dentry == cur.mnt->mnt_root) { + if (follow_up(&cur)) + continue; + goto out_free; + } + if ((ncomponents & 15) == 0) { + struct dentry **new; + new = krealloc(components, + sizeof(*new) * (ncomponents + 16), + GFP_KERNEL); + if (!new) + goto out_free; + components = new; + } + components[ncomponents++] = cur.dentry; + cur.dentry = dget_parent(cur.dentry); + } + err = nfserr_resource; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_free; + *p++ = cpu_to_be32(ncomponents); + + while (ncomponents) { + struct dentry *dentry = components[ncomponents - 1]; + unsigned int len; + + spin_lock(&dentry->d_lock); + len = dentry->d_name.len; + p = xdr_reserve_space(xdr, len + 4); + if (!p) { + spin_unlock(&dentry->d_lock); + goto out_free; + } + p = xdr_encode_opaque(p, dentry->d_name.name, len); + dprintk("/%s", dentry->d_name.name); + spin_unlock(&dentry->d_lock); + dput(dentry); + ncomponents--; } - return path + strlen(rootpath); + err = 0; +out_free: + dprintk(")\n"); + while (ncomponents) + dput(components[--ncomponents]); + kfree(components); + path_put(&cur); + return err; +} + +static __be32 nfsd4_encode_fsloc_fsroot(struct xdr_stream *xdr, + struct svc_rqst *rqstp, const struct path *path) +{ + struct svc_export *exp_ps; + __be32 res; + + exp_ps = rqst_find_fsidzero_export(rqstp); + if (IS_ERR(exp_ps)) + return nfserrno(PTR_ERR(exp_ps)); + res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path); + exp_put(exp_ps); + return res; } /* * encode a fs_locations structure */ -static __be32 nfsd4_encode_fs_locations(struct svc_rqst *rqstp, - struct svc_export *exp, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_fs_locations(struct xdr_stream *xdr, + struct svc_rqst *rqstp, struct svc_export *exp) { __be32 status; int i; - __be32 *p = *pp; + __be32 *p; struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs; - char *root = nfsd4_path(rqstp, exp, &status); + status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path); if (status) return status; - status = nfsd4_encode_components('/', root, &p, buflen); - if (status) - return status; - if ((*buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) return nfserr_resource; - WRITE32(fslocs->locations_count); + *p++ = cpu_to_be32(fslocs->locations_count); for (i=0; i<fslocs->locations_count; i++) { - status = nfsd4_encode_fs_location4(&fslocs->locations[i], - &p, buflen); + status = nfsd4_encode_fs_location4(xdr, &fslocs->locations[i]); if (status) return status; } - *pp = p; return 0; } -static u32 nfs4_ftypes[16] = { - NF4BAD, NF4FIFO, NF4CHR, NF4BAD, - NF4DIR, NF4BAD, NF4BLK, NF4BAD, - NF4REG, NF4BAD, NF4LNK, NF4BAD, - NF4SOCK, NF4BAD, NF4LNK, NF4BAD, -}; - -static __be32 -nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, uid_t id, int group, - __be32 **p, int *buflen) +static u32 nfs4_file_type(umode_t mode) { - int status; - - if (*buflen < (XDR_QUADLEN(IDMAP_NAMESZ) << 2) + 4) - return nfserr_resource; - if (whotype != NFS4_ACL_WHO_NAMED) - status = nfs4_acl_write_who(whotype, (u8 *)(*p + 1)); - else if (group) - status = nfsd_map_gid_to_name(rqstp, id, (u8 *)(*p + 1)); - else - status = nfsd_map_uid_to_name(rqstp, id, (u8 *)(*p + 1)); - if (status < 0) - return nfserrno(status); - *p = xdr_encode_opaque(*p, NULL, status); - *buflen -= (XDR_QUADLEN(status) << 2) + 4; - BUG_ON(*buflen < 0); - return 0; + switch (mode & S_IFMT) { + case S_IFIFO: return NF4FIFO; + case S_IFCHR: return NF4CHR; + case S_IFDIR: return NF4DIR; + case S_IFBLK: return NF4BLK; + case S_IFLNK: return NF4LNK; + case S_IFREG: return NF4REG; + case S_IFSOCK: return NF4SOCK; + default: return NF4BAD; + }; } static inline __be32 -nfsd4_encode_user(struct svc_rqst *rqstp, uid_t uid, __be32 **p, int *buflen) +nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, + struct nfs4_ace *ace) { - return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, uid, 0, p, buflen); + if (ace->whotype != NFS4_ACL_WHO_NAMED) + return nfs4_acl_write_who(xdr, ace->whotype); + else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) + return nfsd4_encode_group(xdr, rqstp, ace->who_gid); + else + return nfsd4_encode_user(xdr, rqstp, ace->who_uid); } -static inline __be32 -nfsd4_encode_group(struct svc_rqst *rqstp, uid_t gid, __be32 **p, int *buflen) -{ - return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, gid, 1, p, buflen); -} +#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ + FATTR4_WORD0_RDATTR_ERROR) +#define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 -nfsd4_encode_aclname(struct svc_rqst *rqstp, int whotype, uid_t id, int group, - __be32 **p, int *buflen) +nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, + void *context, int len) { - return nfsd4_encode_name(rqstp, whotype, id, group, p, buflen); -} + __be32 *p; -#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ - FATTR4_WORD0_RDATTR_ERROR) -#define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID + p = xdr_reserve_space(xdr, len + 4 + 4 + 4); + if (!p) + return nfserr_resource; + + /* + * For now we use a 0 here to indicate the null translation; in + * the future we may place a call to translation code here. + */ + *p++ = cpu_to_be32(0); /* lfs */ + *p++ = cpu_to_be32(0); /* pi */ + p = xdr_encode_opaque(p, context, len); + return 0; +} +#else +static inline __be32 +nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, + void *context, int len) +{ return 0; } +#endif static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) { @@ -1443,61 +1989,93 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) return 0; } + +static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) +{ + struct path path = exp->ex_path; + int err; + + path_get(&path); + while (follow_up(&path)) { + if (path.dentry != path.mnt->mnt_root) + break; + } + err = vfs_getattr(&path, stat); + path_put(&path); + return err; +} + /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. - * - * @countp is the buffer size in _words_; upon successful return this becomes - * replaced with the number of words written. */ -__be32 -nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval, +static __be32 +nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, + struct svc_export *exp, + struct dentry *dentry, u32 *bmval, struct svc_rqst *rqstp, int ignore_crossmnt) { u32 bmval0 = bmval[0]; u32 bmval1 = bmval[1]; + u32 bmval2 = bmval[2]; struct kstat stat; - struct svc_fh tempfh; + struct svc_fh *tempfh = NULL; struct kstatfs statfs; - int buflen = *countp << 2; - __be32 *attrlenp; + __be32 *p; + int starting_len = xdr->buf->len; + int attrlen_offset; + __be32 attrlen; u32 dummy; u64 dummy64; u32 rdattr_err = 0; - __be32 *p = buffer; __be32 status; int err; int aclsupport = 0; struct nfs4_acl *acl = NULL; + void *context = NULL; + int contextlen; + bool contextsupport = false; + struct nfsd4_compoundres *resp = rqstp->rq_resp; + u32 minorversion = resp->cstate.minorversion; + struct path path = { + .mnt = exp->ex_path.mnt, + .dentry = dentry, + }; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1); - BUG_ON(bmval0 & ~NFSD_SUPPORTED_ATTRS_WORD0); - BUG_ON(bmval1 & ~NFSD_SUPPORTED_ATTRS_WORD1); + BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion)); + BUG_ON(bmval1 & ~nfsd_suppattrs1(minorversion)); + BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion)); if (exp->ex_fslocs.migrated) { + BUG_ON(bmval[2]); status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err); if (status) goto out; } - err = vfs_getattr(exp->ex_path.mnt, dentry, &stat); + err = vfs_getattr(&path, &stat); if (err) goto out_nfserr; - if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | - FATTR4_WORD0_MAXNAME)) || + if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { - err = vfs_statfs(dentry, &statfs); + err = vfs_statfs(&path, &statfs); if (err) goto out_nfserr; } if ((bmval0 & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { - fh_init(&tempfh, NFS4_FHSIZE); - status = fh_compose(&tempfh, exp, dentry, NULL); + tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); + status = nfserr_jukebox; + if (!tempfh) + goto out; + fh_init(tempfh, NFS4_FHSIZE); + status = fh_compose(tempfh, exp, dentry, NULL); if (status) goto out; - fhp = &tempfh; + fhp = tempfh; } if (bmval0 & (FATTR4_WORD0_ACL | FATTR4_WORD0_ACLSUPPORT | FATTR4_WORD0_SUPPORTED_ATTRS)) { @@ -1513,363 +2091,492 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, goto out_nfserr; } } - if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) { - if (exp->ex_fslocs.locations == NULL) { - bmval0 &= ~FATTR4_WORD0_FS_LOCATIONS; + +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) || + bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + err = security_inode_getsecctx(dentry->d_inode, + &context, &contextlen); + contextsupport = (err == 0); + if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { + if (err == -EOPNOTSUPP) + bmval2 &= ~FATTR4_WORD2_SECURITY_LABEL; + else if (err) + goto out_nfserr; } } - if ((buflen -= 16) < 0) - goto out_resource; +#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ - WRITE32(2); - WRITE32(bmval0); - WRITE32(bmval1); - attrlenp = p++; /* to be backfilled later */ + 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); + } + + attrlen_offset = xdr->buf->len; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + p++; /* to be backfilled later */ if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { - u32 word0 = NFSD_SUPPORTED_ATTRS_WORD0; - if ((buflen -= 12) < 0) - goto out_resource; + u32 word0 = nfsd_suppattrs0(minorversion); + u32 word1 = nfsd_suppattrs1(minorversion); + u32 word2 = nfsd_suppattrs2(minorversion); + if (!aclsupport) word0 &= ~FATTR4_WORD0_ACL; - if (!exp->ex_fslocs.locations) - word0 &= ~FATTR4_WORD0_FS_LOCATIONS; - WRITE32(2); - WRITE32(word0); - WRITE32(NFSD_SUPPORTED_ATTRS_WORD1); + if (!contextsupport) + word2 &= ~FATTR4_WORD2_SECURITY_LABEL; + if (!word2) { + p = xdr_reserve_space(xdr, 12); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(word0); + *p++ = cpu_to_be32(word1); + } else { + p = xdr_reserve_space(xdr, 16); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(word0); + *p++ = cpu_to_be32(word1); + *p++ = cpu_to_be32(word2); + } } if (bmval0 & FATTR4_WORD0_TYPE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - dummy = nfs4_ftypes[(stat.mode & S_IFMT) >> 12]; - if (dummy == NF4BAD) - goto out_serverfault; - WRITE32(dummy); + dummy = nfs4_file_type(stat.mode); + if (dummy == NF4BAD) { + status = nfserr_serverfault; + goto out; + } + *p++ = cpu_to_be32(dummy); } if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) - WRITE32(NFS4_FH_PERSISTENT); + *p++ = cpu_to_be32(NFS4_FH_PERSISTENT); else - WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME); + *p++ = cpu_to_be32(NFS4_FH_PERSISTENT| + NFS4_FH_VOL_RENAME); } if (bmval0 & FATTR4_WORD0_CHANGE) { - /* - * Note: This _must_ be consistent with the scheme for writing - * change_info, so any changes made here must be reflected there - * as well. (See xdr4.h:set_change_info() and the WRITECINFO() - * macro above.) - */ - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE32(stat.ctime.tv_sec); - WRITE32(stat.ctime.tv_nsec); + p = encode_change(p, &stat, dentry->d_inode); } if (bmval0 & FATTR4_WORD0_SIZE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64(stat.size); + p = xdr_encode_hyper(p, stat.size); } if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_NAMED_ATTR) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); } if (bmval0 & FATTR4_WORD0_FSID) { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; if (exp->ex_fslocs.migrated) { - WRITE64(NFS4_REFERRAL_FSID_MAJOR); - WRITE64(NFS4_REFERRAL_FSID_MINOR); + p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR); + p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR); } else switch(fsid_source(fhp)) { case FSIDSOURCE_FSID: - WRITE64((u64)exp->ex_fsid); - WRITE64((u64)0); + p = xdr_encode_hyper(p, (u64)exp->ex_fsid); + p = xdr_encode_hyper(p, (u64)0); break; case FSIDSOURCE_DEV: - WRITE32(0); - WRITE32(MAJOR(stat.dev)); - WRITE32(0); - WRITE32(MINOR(stat.dev)); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(MAJOR(stat.dev)); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(MINOR(stat.dev)); break; case FSIDSOURCE_UUID: - WRITEMEM(exp->ex_uuid, 16); + p = xdr_encode_opaque_fixed(p, exp->ex_uuid, + EX_UUID_LEN); break; } } if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); } if (bmval0 & FATTR4_WORD0_LEASE_TIME) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(NFSD_LEASE_TIME); + *p++ = cpu_to_be32(nn->nfsd4_lease); } if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(rdattr_err); + *p++ = cpu_to_be32(rdattr_err); } if (bmval0 & FATTR4_WORD0_ACL) { struct nfs4_ace *ace; if (acl == NULL) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(0); + *p++ = cpu_to_be32(0); goto out_acl; } - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(acl->naces); + *p++ = cpu_to_be32(acl->naces); for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) { - if ((buflen -= 4*3) < 0) - goto out_resource; - WRITE32(ace->type); - WRITE32(ace->flag); - WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL); - status = nfsd4_encode_aclname(rqstp, ace->whotype, - ace->who, ace->flag & NFS4_ACE_IDENTIFIER_GROUP, - &p, &buflen); - if (status == nfserr_resource) + p = xdr_reserve_space(xdr, 4*3); + if (!p) goto out_resource; + *p++ = cpu_to_be32(ace->type); + *p++ = cpu_to_be32(ace->flag); + *p++ = cpu_to_be32(ace->access_mask & + NFS4_ACE_MASK_ALL); + status = nfsd4_encode_aclname(xdr, rqstp, ace); if (status) goto out; } } out_acl: if (bmval0 & FATTR4_WORD0_ACLSUPPORT) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(aclsupport ? + *p++ = cpu_to_be32(aclsupport ? ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0); } if (bmval0 & FATTR4_WORD0_CANSETTIME) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(0); } if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_FILEHANDLE) { - buflen -= (XDR_QUADLEN(fhp->fh_handle.fh_size) << 2) + 4; - if (buflen < 0) + p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4); + if (!p) goto out_resource; - WRITE32(fhp->fh_handle.fh_size); - WRITEMEM(&fhp->fh_handle.fh_base, fhp->fh_handle.fh_size); + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, + fhp->fh_handle.fh_size); } if (bmval0 & FATTR4_WORD0_FILEID) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64(stat.ino); + p = xdr_encode_hyper(p, stat.ino); } if (bmval0 & FATTR4_WORD0_FILES_AVAIL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) statfs.f_ffree); + p = xdr_encode_hyper(p, (u64) statfs.f_ffree); } if (bmval0 & FATTR4_WORD0_FILES_FREE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) statfs.f_ffree); + p = xdr_encode_hyper(p, (u64) statfs.f_ffree); } if (bmval0 & FATTR4_WORD0_FILES_TOTAL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) statfs.f_files); + p = xdr_encode_hyper(p, (u64) statfs.f_files); } if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) { - status = nfsd4_encode_fs_locations(rqstp, exp, &p, &buflen); - if (status == nfserr_resource) - goto out_resource; + status = nfsd4_encode_fs_locations(xdr, rqstp, exp); if (status) goto out; } if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval0 & FATTR4_WORD0_MAXFILESIZE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64(~(u64)0); + p = xdr_encode_hyper(p, exp->ex_path.mnt->mnt_sb->s_maxbytes); } if (bmval0 & FATTR4_WORD0_MAXLINK) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(255); + *p++ = cpu_to_be32(255); } if (bmval0 & FATTR4_WORD0_MAXNAME) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(statfs.f_namelen); + *p++ = cpu_to_be32(statfs.f_namelen); } if (bmval0 & FATTR4_WORD0_MAXREAD) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) svc_max_payload(rqstp)); + p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); } if (bmval0 & FATTR4_WORD0_MAXWRITE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE64((u64) svc_max_payload(rqstp)); + p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); } if (bmval1 & FATTR4_WORD1_MODE) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(stat.mode & S_IALLUGO); + *p++ = cpu_to_be32(stat.mode & S_IALLUGO); } if (bmval1 & FATTR4_WORD1_NO_TRUNC) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(1); + *p++ = cpu_to_be32(1); } if (bmval1 & FATTR4_WORD1_NUMLINKS) { - if ((buflen -= 4) < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_resource; - WRITE32(stat.nlink); + *p++ = cpu_to_be32(stat.nlink); } if (bmval1 & FATTR4_WORD1_OWNER) { - status = nfsd4_encode_user(rqstp, stat.uid, &p, &buflen); - if (status == nfserr_resource) - goto out_resource; + status = nfsd4_encode_user(xdr, rqstp, stat.uid); if (status) goto out; } if (bmval1 & FATTR4_WORD1_OWNER_GROUP) { - status = nfsd4_encode_group(rqstp, stat.gid, &p, &buflen); - if (status == nfserr_resource) - goto out_resource; + status = nfsd4_encode_group(xdr, rqstp, stat.gid); if (status) goto out; } if (bmval1 & FATTR4_WORD1_RAWDEV) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE32((u32) MAJOR(stat.rdev)); - WRITE32((u32) MINOR(stat.rdev)); + *p++ = cpu_to_be32((u32) MAJOR(stat.rdev)); + *p++ = cpu_to_be32((u32) MINOR(stat.rdev)); } if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_SPACE_FREE) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_SPACE_USED) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; dummy64 = (u64)stat.blocks << 9; - WRITE64(dummy64); + p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(0); - WRITE32(stat.atime.tv_sec); - WRITE32(stat.atime.tv_nsec); + p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); + *p++ = cpu_to_be32(stat.atime.tv_nsec); } if (bmval1 & FATTR4_WORD1_TIME_DELTA) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(0); - WRITE32(1); - WRITE32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(0); } if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(0); - WRITE32(stat.ctime.tv_sec); - WRITE32(stat.ctime.tv_nsec); + p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); + *p++ = cpu_to_be32(stat.ctime.tv_nsec); } if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(0); - WRITE32(stat.mtime.tv_sec); - WRITE32(stat.mtime.tv_nsec); + p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); + *p++ = cpu_to_be32(stat.mtime.tv_nsec); } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; /* * Get parent's attributes if not ignoring crossmount * and this is the root of a cross-mounted filesystem. */ if (ignore_crossmnt == 0 && - exp->ex_path.mnt->mnt_root->d_inode == dentry->d_inode) { - err = vfs_getattr(exp->ex_path.mnt->mnt_parent, - exp->ex_path.mnt->mnt_mountpoint, &stat); - if (err) - goto out_nfserr; - } - WRITE64(stat.ino); + dentry == exp->ex_path.mnt->mnt_root) + get_parent_attributes(exp, &stat); + p = xdr_encode_hyper(p, stat.ino); + } + if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { + status = nfsd4_encode_security_label(xdr, rqstp, context, + contextlen); + if (status) + goto out; } - *attrlenp = htonl((char *)p - (char *)attrlenp - 4); - *countp = p - buffer; + 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); status = nfs_ok; out: +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + if (context) + security_release_secctx(context, contextlen); +#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ kfree(acl); - if (fhp == &tempfh) - fh_put(&tempfh); + if (tempfh) { + fh_put(tempfh); + kfree(tempfh); + } + if (status) + xdr_truncate_encode(xdr, starting_len); return status; out_nfserr: status = nfserrno(err); goto out; out_resource: - *countp = 0; status = nfserr_resource; goto out; -out_serverfault: - status = nfserr_serverfault; - goto out; +} + +static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr, + struct xdr_buf *buf, __be32 *p, int bytes) +{ + xdr->scratch.iov_len = 0; + memset(buf, 0, sizeof(struct xdr_buf)); + buf->head[0].iov_base = p; + buf->head[0].iov_len = 0; + buf->len = 0; + xdr->buf = buf; + xdr->iov = buf->head; + xdr->p = p; + xdr->end = (void *)p + bytes; + buf->buflen = bytes; +} + +__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, + struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, u32 *bmval, + struct svc_rqst *rqstp, int ignore_crossmnt) +{ + struct xdr_buf dummy; + struct xdr_stream xdr; + __be32 ret; + + svcxdr_init_encode_from_buffer(&xdr, &dummy, *p, words << 2); + ret = nfsd4_encode_fattr(&xdr, fhp, exp, dentry, bmval, rqstp, + ignore_crossmnt); + *p = xdr.p; + return ret; +} + +static inline int attributes_need_mount(u32 *bmval) +{ + if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME)) + return 1; + if (bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID) + return 1; + return 0; } static __be32 -nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, - const char *name, int namlen, __be32 *p, int *buflen) +nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, + const char *name, int namlen) { struct svc_export *exp = cd->rd_fhp->fh_export; struct dentry *dentry; @@ -1879,6 +2586,15 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); + if (!dentry->d_inode) { + /* + * nfsd_buffered_readdir drops the i_mutex between + * readdir and calling this callback, leaving a window + * where this directory entry could have gone away. + */ + dput(dentry); + return nfserr_noent; + } exp_get(exp); /* @@ -1888,13 +2604,14 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, * we will not follow the cross mount and will fill the attribtutes * directly from the mountpoint dentry. */ - if (d_mountpoint(dentry) && - (cd->rd_bmval[0] & ~FATTR4_WORD0_RDATTR_ERROR) == 0 && - (cd->rd_bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID) == 0) - ignore_crossmnt = 1; - else if (d_mountpoint(dentry)) { + if (nfsd_mountpoint(dentry, exp)) { int err; + if (!(exp->ex_flags & NFSEXP_V4ROOT) + && !attributes_need_mount(cd->rd_bmval)) { + ignore_crossmnt = 1; + goto out_encode; + } /* * Why the heck aren't we just using nfsd_lookup?? * Different "."/".." handling? Something else? @@ -1910,7 +2627,8 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, goto out_put; } - nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, +out_encode: + nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval, cd->rd_rqstp, ignore_crossmnt); out_put: dput(dentry); @@ -1919,19 +2637,19 @@ out_put: } static __be32 * -nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr) +nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) { - __be32 *attrlenp; + __be32 *p; - if (buflen < 6) + p = xdr_reserve_space(xdr, 20); + if (!p) return NULL; *p++ = htonl(2); *p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */ *p++ = htonl(0); /* bmval1 */ - attrlenp = p++; + *p++ = htonl(4); /* attribute length */ *p++ = nfserr; /* no htonl */ - *attrlenp = htonl((char *)p - (char *)attrlenp - 4); return p; } @@ -1941,9 +2659,13 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, { struct readdir_cd *ccd = ccdv; struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common); - int buflen; - __be32 *p = cd->buffer; + struct xdr_stream *xdr = cd->xdr; + int start_offset = xdr->buf->len; + int cookie_offset; + int entry_bytes; __be32 nfserr = nfserr_toosmall; + __be64 wire_offset; + __be32 *p; /* In nfsv4, "." and ".." never make it onto the wire.. */ if (name && isdotent(name, namlen)) { @@ -1951,28 +2673,33 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, return 0; } - if (cd->offset) - xdr_encode_hyper(cd->offset, (u64) offset); + if (cd->cookie_offset) { + wire_offset = cpu_to_be64(offset); + write_bytes_to_xdr_buf(xdr->buf, cd->cookie_offset, + &wire_offset, 8); + } - buflen = cd->buflen - 4 - XDR_QUADLEN(namlen); - if (buflen < 0) + p = xdr_reserve_space(xdr, 4); + if (!p) goto fail; - *p++ = xdr_one; /* mark entry present */ - cd->offset = p; /* remember pointer */ + cookie_offset = xdr->buf->len; + p = xdr_reserve_space(xdr, 3*4 + namlen); + if (!p) + goto fail; p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */ p = xdr_encode_array(p, name, namlen); /* name length & name */ - nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, p, &buflen); + nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); switch (nfserr) { case nfs_ok: - p += buflen; break; case nfserr_resource: nfserr = nfserr_toosmall; goto fail; - case nfserr_dropit: - goto fail; + case nfserr_noent: + xdr_truncate_encode(xdr, start_offset); + goto skip_entry; default: /* * If the client requested the RDATTR_ERROR attribute, @@ -1983,391 +2710,580 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, */ if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)) goto fail; - p = nfsd4_encode_rdattr_error(p, buflen, nfserr); + p = nfsd4_encode_rdattr_error(xdr, nfserr); if (p == NULL) { nfserr = nfserr_toosmall; goto fail; } } - cd->buflen -= (p - cd->buffer); - cd->buffer = p; + nfserr = nfserr_toosmall; + entry_bytes = xdr->buf->len - start_offset; + if (entry_bytes > cd->rd_maxcount) + goto fail; + cd->rd_maxcount -= entry_bytes; + if (!cd->rd_dircount) + goto fail; + cd->rd_dircount--; + cd->cookie_offset = cookie_offset; +skip_entry: cd->common.err = nfs_ok; return 0; fail: + xdr_truncate_encode(xdr, start_offset); cd->common.err = nfserr; return -EINVAL; } -static void +static __be32 +nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, sizeof(stateid_t)); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sid->si_generation); + p = xdr_encode_opaque_fixed(p, &sid->si_opaque, + sizeof(stateid_opaque_t)); + return 0; +} + +static __be32 nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(8); - WRITE32(access->ac_supported); - WRITE32(access->ac_resp_access); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(access->ac_supported); + *p++ = cpu_to_be32(access->ac_resp_access); } + return nfserr; } -static void -nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) +static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) { - ENCODE_SEQID_OP_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(close->cl_stateid.si_generation); - WRITEMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, bcts->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(bcts->dir); + /* Sorry, we do not yet support RDMA over 4.1: */ + *p++ = cpu_to_be32(0); } - ENCODE_SEQID_OP_TAIL(close->cl_stateowner); + return nfserr; +} + +static __be32 +nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) +{ + struct xdr_stream *xdr = &resp->xdr; + + if (!nfserr) + nfserr = nfsd4_encode_stateid(xdr, &close->cl_stateid); + + return nfserr; } -static void +static __be32 nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(8); - WRITEMEM(commit->co_verf.data, 8); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, commit->co_verf.data, + NFS4_VERIFIER_SIZE); } + return nfserr; } -static void +static __be32 nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(32); - WRITECINFO(create->cr_cinfo); - WRITE32(2); - WRITE32(create->cr_bmval[0]); - WRITE32(create->cr_bmval[1]); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 32); + 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]); } + return nfserr; } static __be32 nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr) { struct svc_fh *fhp = getattr->ga_fhp; - int buflen; + struct xdr_stream *xdr = &resp->xdr; if (nfserr) return nfserr; - buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2); - nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry, - resp->p, &buflen, getattr->ga_bmval, + nfserr = nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry, + getattr->ga_bmval, resp->rqstp, 0); - if (!nfserr) - resp->p += buflen; return nfserr; } -static void -nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh *fhp) +static __be32 +nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) { + struct xdr_stream *xdr = &resp->xdr; + struct svc_fh *fhp = *fhpp; unsigned int len; - ENCODE_HEAD; + __be32 *p; if (!nfserr) { len = fhp->fh_handle.fh_size; - RESERVE_SPACE(len + 4); - WRITE32(len); - WRITEMEM(&fhp->fh_handle.fh_base, len); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, len + 4); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len); } + return nfserr; } /* * Including all fields other than the name, a LOCK4denied structure requires * 8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes. */ -static void -nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denied *ld) -{ - ENCODE_HEAD; - - RESERVE_SPACE(32 + XDR_LEN(ld->ld_sop ? ld->ld_sop->so_owner.len : 0)); - WRITE64(ld->ld_start); - WRITE64(ld->ld_length); - WRITE32(ld->ld_type); - if (ld->ld_sop) { - WRITEMEM(&ld->ld_clientid, 8); - WRITE32(ld->ld_sop->so_owner.len); - WRITEMEM(ld->ld_sop->so_owner.data, ld->ld_sop->so_owner.len); - kref_put(&ld->ld_sop->so_ref, nfs4_free_stateowner); +static __be32 +nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld) +{ + struct xdr_netobj *conf = &ld->ld_owner; + __be32 *p; + +again: + p = xdr_reserve_space(xdr, 32 + XDR_LEN(conf->len)); + if (!p) { + /* + * Don't fail to return the result just because we can't + * return the conflicting open: + */ + if (conf->len) { + kfree(conf->data); + conf->len = 0; + conf->data = NULL; + goto again; + } + return nfserr_resource; + } + p = xdr_encode_hyper(p, ld->ld_start); + p = xdr_encode_hyper(p, ld->ld_length); + *p++ = cpu_to_be32(ld->ld_type); + if (conf->len) { + p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8); + p = xdr_encode_opaque(p, conf->data, conf->len); + kfree(conf->data); } else { /* non - nfsv4 lock in conflict, no clientid nor owner */ - WRITE64((u64)0); /* clientid */ - WRITE32(0); /* length of owner name */ + p = xdr_encode_hyper(p, (u64)0); /* clientid */ + *p++ = cpu_to_be32(0); /* length of owner name */ } - ADJUST_ARGS(); + return nfserr_denied; } -static void +static __be32 nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) { - ENCODE_SEQID_OP_HEAD; + struct xdr_stream *xdr = &resp->xdr; - if (!nfserr) { - RESERVE_SPACE(4 + sizeof(stateid_t)); - WRITE32(lock->lk_resp_stateid.si_generation); - WRITEMEM(&lock->lk_resp_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } else if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(resp, &lock->lk_denied); + if (!nfserr) + nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid); + else if (nfserr == nfserr_denied) + nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied); - ENCODE_SEQID_OP_TAIL(lock->lk_replay_owner); + return nfserr; } -static void +static __be32 nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) { + struct xdr_stream *xdr = &resp->xdr; + if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(resp, &lockt->lt_denied); + nfsd4_encode_lock_denied(xdr, &lockt->lt_denied); + return nfserr; } -static void +static __be32 nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) { - ENCODE_SEQID_OP_HEAD; + struct xdr_stream *xdr = &resp->xdr; - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(locku->lu_stateid.si_generation); - WRITEMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } - - ENCODE_SEQID_OP_TAIL(locku->lu_stateowner); + if (!nfserr) + nfserr = nfsd4_encode_stateid(xdr, &locku->lu_stateid); + + return nfserr; } -static void +static __be32 nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(20); - WRITECINFO(link->li_cinfo); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &link->li_cinfo); } + return nfserr; } -static void +static __be32 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) { - ENCODE_SEQID_OP_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (nfserr) goto out; - RESERVE_SPACE(36 + sizeof(stateid_t)); - WRITE32(open->op_stateid.si_generation); - WRITEMEM(&open->op_stateid.si_opaque, sizeof(stateid_opaque_t)); - WRITECINFO(open->op_cinfo); - WRITE32(open->op_rflags); - WRITE32(2); - WRITE32(open->op_bmval[0]); - WRITE32(open->op_bmval[1]); - WRITE32(open->op_delegate_type); - ADJUST_ARGS(); + nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); + if (nfserr) + goto out; + p = xdr_reserve_space(xdr, 40); + 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); switch (open->op_delegate_type) { case NFS4_OPEN_DELEGATE_NONE: break; case NFS4_OPEN_DELEGATE_READ: - RESERVE_SPACE(20 + sizeof(stateid_t)); - WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t)); - WRITE32(open->op_recall); + nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); + if (nfserr) + return nfserr; + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_recall); /* * TODO: ACE's in delegations */ - WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - WRITE32(0); - WRITE32(0); - WRITE32(0); /* XXX: is NULL principal ok? */ - ADJUST_ARGS(); + *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ break; case NFS4_OPEN_DELEGATE_WRITE: - RESERVE_SPACE(32 + sizeof(stateid_t)); - WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t)); - WRITE32(0); + nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); + if (nfserr) + return nfserr; + p = xdr_reserve_space(xdr, 32); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); /* * TODO: space_limit's in delegations */ - WRITE32(NFS4_LIMIT_SIZE); - WRITE32(~(u32)0); - WRITE32(~(u32)0); + *p++ = cpu_to_be32(NFS4_LIMIT_SIZE); + *p++ = cpu_to_be32(~(u32)0); + *p++ = cpu_to_be32(~(u32)0); /* * TODO: ACE's in delegations */ - WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - WRITE32(0); - WRITE32(0); - WRITE32(0); /* XXX: is NULL principal ok? */ - ADJUST_ARGS(); + *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ + break; + case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */ + switch (open->op_why_no_deleg) { + case WND4_CONTENTION: + case WND4_RESOURCE: + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_why_no_deleg); + /* deleg signaling not supported yet: */ + *p++ = cpu_to_be32(0); + break; + default: + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_why_no_deleg); + } break; default: BUG(); } /* XXX save filehandle here */ out: - ENCODE_SEQID_OP_TAIL(open->op_stateowner); + return nfserr; } -static void +static __be32 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) { - ENCODE_SEQID_OP_HEAD; - - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(oc->oc_resp_stateid.si_generation); - WRITEMEM(&oc->oc_resp_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } + struct xdr_stream *xdr = &resp->xdr; - ENCODE_SEQID_OP_TAIL(oc->oc_stateowner); + if (!nfserr) + nfserr = nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); + + return nfserr; } -static void +static __be32 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) { - ENCODE_SEQID_OP_HEAD; - - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(od->od_stateid.si_generation); - WRITEMEM(&od->od_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } + struct xdr_stream *xdr = &resp->xdr; + + if (!nfserr) + nfserr = nfsd4_encode_stateid(xdr, &od->od_stateid); - ENCODE_SEQID_OP_TAIL(od->od_stateowner); + return nfserr; } -static __be32 -nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) +static __be32 nfsd4_encode_splice_read( + struct nfsd4_compoundres *resp, + struct nfsd4_read *read, + struct file *file, unsigned long maxcount) { + struct xdr_stream *xdr = &resp->xdr; + struct xdr_buf *buf = xdr->buf; u32 eof; - int v, pn; - unsigned long maxcount; - long len; - ENCODE_HEAD; + int space_left; + __be32 nfserr; + __be32 *p = xdr->p - 2; - if (nfserr) - return nfserr; - if (resp->xbuf->page_len) + /* + * Don't inline pages unless we know there's room for eof, + * count, and possible padding: + */ + if (xdr->end - xdr->p < 3) return nfserr_resource; - RESERVE_SPACE(8); /* eof flag and byte count */ + nfserr = nfsd_splice_read(read->rd_rqstp, file, + read->rd_offset, &maxcount); + if (nfserr) { + /* + * nfsd_splice_actor may have already messed with the + * page length; reset it so as not to confuse + * xdr_truncate_encode: + */ + buf->page_len = 0; + return nfserr; + } - maxcount = svc_max_payload(resp->rqstp); - if (maxcount > read->rd_length) - maxcount = read->rd_length; + eof = (read->rd_offset + maxcount >= + read->rd_fhp->fh_dentry->d_inode->i_size); + + *(p++) = htonl(eof); + *(p++) = htonl(maxcount); + + buf->page_len = maxcount; + buf->len += maxcount; + xdr->page_ptr += (maxcount + PAGE_SIZE - 1) / PAGE_SIZE; + + /* Use rest of head for padding and remaining ops: */ + buf->tail[0].iov_base = xdr->p; + buf->tail[0].iov_len = 0; + xdr->iov = buf->tail; + if (maxcount&3) { + int pad = 4 - (maxcount&3); + + *(xdr->p++) = 0; + + buf->tail[0].iov_base += maxcount&3; + buf->tail[0].iov_len = pad; + buf->len += pad; + } + + space_left = min_t(int, (void *)xdr->end - (void *)xdr->p, + buf->buflen - buf->len); + buf->buflen = buf->len + space_left; + xdr->end = (__be32 *)((void *)xdr->end + space_left); + + return 0; +} + +static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, + struct nfsd4_read *read, + struct file *file, unsigned long maxcount) +{ + struct xdr_stream *xdr = &resp->xdr; + u32 eof; + int v; + int starting_len = xdr->buf->len - 8; + long len; + int thislen; + __be32 nfserr; + __be32 tmp; + __be32 *p; + u32 zzz = 0; + int pad; len = maxcount; v = 0; - while (len > 0) { - pn = resp->rqstp->rq_resused++; - resp->rqstp->rq_vec[v].iov_base = - page_address(resp->rqstp->rq_respages[pn]); - resp->rqstp->rq_vec[v].iov_len = - len < PAGE_SIZE ? len : PAGE_SIZE; + + thislen = (void *)xdr->end - (void *)xdr->p; + if (len < thislen) + thislen = len; + p = xdr_reserve_space(xdr, (thislen+3)&~3); + WARN_ON_ONCE(!p); + resp->rqstp->rq_vec[v].iov_base = p; + resp->rqstp->rq_vec[v].iov_len = thislen; + v++; + len -= thislen; + + while (len) { + thislen = min_t(long, len, PAGE_SIZE); + p = xdr_reserve_space(xdr, (thislen+3)&~3); + WARN_ON_ONCE(!p); + resp->rqstp->rq_vec[v].iov_base = p; + resp->rqstp->rq_vec[v].iov_len = thislen; v++; - len -= PAGE_SIZE; + len -= thislen; } read->rd_vlen = v; - nfserr = nfsd_read(read->rd_rqstp, read->rd_fhp, read->rd_filp, - read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen, - &maxcount); - - if (nfserr == nfserr_symlink) - nfserr = nfserr_inval; + nfserr = nfsd_readv(file, read->rd_offset, resp->rqstp->rq_vec, + read->rd_vlen, &maxcount); if (nfserr) return nfserr; + xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3)); + eof = (read->rd_offset + maxcount >= read->rd_fhp->fh_dentry->d_inode->i_size); - WRITE32(eof); - WRITE32(maxcount); - ADJUST_ARGS(); - resp->xbuf->head[0].iov_len = (char*)p - - (char*)resp->xbuf->head[0].iov_base; - resp->xbuf->page_len = maxcount; + tmp = htonl(eof); + write_bytes_to_xdr_buf(xdr->buf, starting_len , &tmp, 4); + tmp = htonl(maxcount); + write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); - /* Use rest of head for padding and remaining ops: */ - resp->xbuf->tail[0].iov_base = p; - resp->xbuf->tail[0].iov_len = 0; - if (maxcount&3) { - RESERVE_SPACE(4); - WRITE32(0); - resp->xbuf->tail[0].iov_base += maxcount&3; - resp->xbuf->tail[0].iov_len = 4 - (maxcount&3); - ADJUST_ARGS(); - } + pad = (maxcount&3) ? 4 - (maxcount&3) : 0; + write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount, + &zzz, pad); return 0; + } static __be32 -nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_read *read) { - int maxcount; - char *page; - ENCODE_HEAD; + unsigned long maxcount; + struct xdr_stream *xdr = &resp->xdr; + struct file *file = read->rd_filp; + int starting_len = xdr->buf->len; + struct raparms *ra; + __be32 *p; + __be32 err; if (nfserr) return nfserr; - if (resp->xbuf->page_len) + + p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ + if (!p) { + WARN_ON_ONCE(resp->rqstp->rq_splice_ok); return nfserr_resource; + } + if (resp->xdr.buf->page_len && resp->rqstp->rq_splice_ok) { + WARN_ON_ONCE(1); + return nfserr_resource; + } + xdr_commit_encode(xdr); + + maxcount = svc_max_payload(resp->rqstp); + if (maxcount > xdr->buf->buflen - xdr->buf->len) + maxcount = xdr->buf->buflen - xdr->buf->len; + if (maxcount > read->rd_length) + maxcount = read->rd_length; + + if (!read->rd_filp) { + err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp, + &file, &ra); + if (err) + goto err_truncate; + } + + if (file->f_op->splice_read && resp->rqstp->rq_splice_ok) + err = nfsd4_encode_splice_read(resp, read, file, maxcount); + else + err = nfsd4_encode_readv(resp, read, file, maxcount); - page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]); + if (!read->rd_filp) + nfsd_put_tmp_read_open(file, ra); +err_truncate: + if (err) + xdr_truncate_encode(xdr, starting_len); + return err; +} + +static __be32 +nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +{ + int maxcount; + __be32 wire_count; + int zero = 0; + struct xdr_stream *xdr = &resp->xdr; + int length_offset = xdr->buf->len; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; maxcount = PAGE_SIZE; - RESERVE_SPACE(4); + p = xdr_reserve_space(xdr, maxcount); + if (!p) + return nfserr_resource; /* * XXX: By default, the ->readlink() VFS op will truncate symlinks * if they would overflow the buffer. Is this kosher in NFSv4? If * not, one easy fix is: if ->readlink() precisely fills the buffer, * assume that truncation occurred, and return NFS4ERR_RESOURCE. */ - nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, page, &maxcount); + nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, + (char *)p, &maxcount); if (nfserr == nfserr_isdir) - return nfserr_inval; - if (nfserr) + nfserr = nfserr_inval; + if (nfserr) { + xdr_truncate_encode(xdr, length_offset); return nfserr; - - WRITE32(maxcount); - ADJUST_ARGS(); - resp->xbuf->head[0].iov_len = (char*)p - - (char*)resp->xbuf->head[0].iov_base; - resp->xbuf->page_len = maxcount; - - /* Use rest of head for padding and remaining ops: */ - resp->xbuf->tail[0].iov_base = p; - resp->xbuf->tail[0].iov_len = 0; - if (maxcount&3) { - RESERVE_SPACE(4); - WRITE32(0); - resp->xbuf->tail[0].iov_base += maxcount&3; - resp->xbuf->tail[0].iov_len = 4 - (maxcount&3); - ADJUST_ARGS(); } + + wire_count = htonl(maxcount); + write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4); + xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4)); + if (maxcount & 3) + write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, + &zero, 4 - (maxcount&3)); return 0; } @@ -2375,45 +3291,52 @@ static __be32 nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir) { int maxcount; + int bytes_left; loff_t offset; - __be32 *page, *savep, *tailbase; - ENCODE_HEAD; + __be64 wire_offset; + struct xdr_stream *xdr = &resp->xdr; + int starting_len = xdr->buf->len; + __be32 *p; if (nfserr) return nfserr; - if (resp->xbuf->page_len) - return nfserr_resource; - RESERVE_SPACE(8); /* verifier */ - savep = p; + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; /* XXX: Following NFSv3, we ignore the READDIR verifier for now. */ - WRITE32(0); - WRITE32(0); - ADJUST_ARGS(); - resp->xbuf->head[0].iov_len = ((char*)resp->p) - (char*)resp->xbuf->head[0].iov_base; - tailbase = p; - - maxcount = PAGE_SIZE; - if (maxcount > readdir->rd_maxcount) - maxcount = readdir->rd_maxcount; + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + resp->xdr.buf->head[0].iov_len = ((char *)resp->xdr.p) + - (char *)resp->xdr.buf->head[0].iov_base; /* - * Convert from bytes to words, account for the two words already - * written, make sure to leave two words at the end for the next - * pointer and eof field. + * Number of bytes left for directory entries allowing for the + * final 8 bytes of the readdir and a following failed op: + */ + bytes_left = xdr->buf->buflen - xdr->buf->len + - COMPOUND_ERR_SLACK_SPACE - 8; + if (bytes_left < 0) { + nfserr = nfserr_resource; + goto err_no_verf; + } + maxcount = min_t(u32, readdir->rd_maxcount, INT_MAX); + /* + * Note the rfc defines rd_maxcount as the size of the + * READDIR4resok structure, which includes the verifier above + * and the 8 bytes encoded at the end of this function: */ - maxcount = (maxcount >> 2) - 4; - if (maxcount < 0) { - nfserr = nfserr_toosmall; + if (maxcount < 16) { + nfserr = nfserr_toosmall; goto err_no_verf; } + maxcount = min_t(int, maxcount-16, bytes_left); - page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]); + readdir->xdr = xdr; + readdir->rd_maxcount = maxcount; readdir->common.err = 0; - readdir->buflen = maxcount; - readdir->buffer = page; - readdir->offset = NULL; + readdir->cookie_offset = 0; offset = readdir->rd_cookie; nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp, @@ -2421,73 +3344,82 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 &readdir->common, nfsd4_encode_dirent); if (nfserr == nfs_ok && readdir->common.err == nfserr_toosmall && - readdir->buffer == page) - nfserr = nfserr_toosmall; - if (nfserr == nfserr_symlink) - nfserr = nfserr_notdir; + xdr->buf->len == starting_len + 8) { + /* nothing encoded; which limit did we hit?: */ + if (maxcount - 16 < bytes_left) + /* It was the fault of rd_maxcount: */ + nfserr = nfserr_toosmall; + else + /* We ran out of buffer space: */ + nfserr = nfserr_resource; + } if (nfserr) goto err_no_verf; - if (readdir->offset) - xdr_encode_hyper(readdir->offset, offset); + if (readdir->cookie_offset) { + wire_offset = cpu_to_be64(offset); + write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset, + &wire_offset, 8); + } - p = readdir->buffer; + p = xdr_reserve_space(xdr, 8); + if (!p) { + WARN_ON_ONCE(1); + goto err_no_verf; + } *p++ = 0; /* no more entries */ *p++ = htonl(readdir->common.err == nfserr_eof); - resp->xbuf->page_len = ((char*)p) - (char*)page_address( - resp->rqstp->rq_respages[resp->rqstp->rq_resused-1]); - - /* Use rest of head for padding and remaining ops: */ - resp->xbuf->tail[0].iov_base = tailbase; - resp->xbuf->tail[0].iov_len = 0; - resp->p = resp->xbuf->tail[0].iov_base; - resp->end = resp->p + (PAGE_SIZE - resp->xbuf->head[0].iov_len)/4; return 0; err_no_verf: - p = savep; - ADJUST_ARGS(); + xdr_truncate_encode(xdr, starting_len); return nfserr; } -static void +static __be32 nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(20); - WRITECINFO(remove->rm_cinfo); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &remove->rm_cinfo); } + return nfserr; } -static void +static __be32 nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(40); - WRITECINFO(rename->rn_sinfo); - WRITECINFO(rename->rn_tinfo); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 40); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &rename->rn_sinfo); + p = encode_cinfo(p, &rename->rn_tinfo); } + return nfserr; } -static void -nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo *secinfo) +static __be32 +nfsd4_do_encode_secinfo(struct xdr_stream *xdr, + __be32 nfserr, struct svc_export *exp) { - int i = 0; - struct svc_export *exp = secinfo->si_exp; - u32 nflavs; + u32 i, nflavs, supported; struct exp_flavor_info *flavs; struct exp_flavor_info def_flavs[2]; - ENCODE_HEAD; + __be32 *p, *flavorsp; + static bool report = true; if (nfserr) goto out; + nfserr = nfserr_resource; if (exp->ex_nflavors) { flavs = exp->ex_flavors; nflavs = exp->ex_nflavors; @@ -2508,206 +3440,496 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, } } - RESERVE_SPACE(4); - WRITE32(nflavs); - ADJUST_ARGS(); + supported = 0; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + flavorsp = p++; /* to be backfilled later */ + for (i = 0; i < nflavs; i++) { - u32 flav = flavs[i].pseudoflavor; - struct gss_api_mech *gm = gss_mech_get_by_pseudoflavor(flav); - - if (gm) { - RESERVE_SPACE(4); - WRITE32(RPC_AUTH_GSS); - ADJUST_ARGS(); - RESERVE_SPACE(4 + gm->gm_oid.len); - WRITE32(gm->gm_oid.len); - WRITEMEM(gm->gm_oid.data, gm->gm_oid.len); - ADJUST_ARGS(); - RESERVE_SPACE(4); - WRITE32(0); /* qop */ - ADJUST_ARGS(); - RESERVE_SPACE(4); - WRITE32(gss_pseudoflavor_to_service(gm, flav)); - ADJUST_ARGS(); - gss_mech_put(gm); + rpc_authflavor_t pf = flavs[i].pseudoflavor; + struct rpcsec_gss_info info; + + if (rpcauth_get_gssinfo(pf, &info) == 0) { + supported++; + p = xdr_reserve_space(xdr, 4 + 4 + + XDR_LEN(info.oid.len) + 4 + 4); + if (!p) + goto out; + *p++ = cpu_to_be32(RPC_AUTH_GSS); + p = xdr_encode_opaque(p, info.oid.data, info.oid.len); + *p++ = cpu_to_be32(info.qop); + *p++ = cpu_to_be32(info.service); + } else if (pf < RPC_AUTH_MAXFLAVOR) { + supported++; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + *p++ = cpu_to_be32(pf); } else { - RESERVE_SPACE(4); - WRITE32(flav); - ADJUST_ARGS(); + if (report) + pr_warn("NFS: SECINFO: security flavor %u " + "is not supported\n", pf); } } + + if (nflavs != supported) + report = false; + *flavorsp = htonl(supported); + nfserr = 0; out: if (exp) exp_put(exp); + return nfserr; +} + +static __be32 +nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_secinfo *secinfo) +{ + struct xdr_stream *xdr = &resp->xdr; + + return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->si_exp); +} + +static __be32 +nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_secinfo_no_name *secinfo) +{ + struct xdr_stream *xdr = &resp->xdr; + + return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->sin_exp); } /* * The SETATTR encode routine is special -- it always encodes a bitmap, * regardless of the error status. */ -static void +static __be32 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; - RESERVE_SPACE(12); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; if (nfserr) { - WRITE32(2); - WRITE32(0); - WRITE32(0); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); } else { - WRITE32(2); - WRITE32(setattr->sa_bmval[0]); - WRITE32(setattr->sa_bmval[1]); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(setattr->sa_bmval[0]); + *p++ = cpu_to_be32(setattr->sa_bmval[1]); + *p++ = cpu_to_be32(setattr->sa_bmval[2]); } - ADJUST_ARGS(); + return nfserr; } -static void +static __be32 nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(8 + sizeof(nfs4_verifier)); - WRITEMEM(&scd->se_clientid, 8); - WRITEMEM(&scd->se_confirm, sizeof(nfs4_verifier)); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8 + NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, &scd->se_clientid, 8); + p = xdr_encode_opaque_fixed(p, &scd->se_confirm, + NFS4_VERIFIER_SIZE); } else if (nfserr == nfserr_clid_inuse) { - RESERVE_SPACE(8); - WRITE32(0); - WRITE32(0); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(0); } + return nfserr; } -static void +static __be32 nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) { - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; if (!nfserr) { - RESERVE_SPACE(16); - WRITE32(write->wr_bytes_written); - WRITE32(write->wr_how_written); - WRITEMEM(write->wr_verifier.data, 8); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(write->wr_bytes_written); + *p++ = cpu_to_be32(write->wr_how_written); + p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, + NFS4_VERIFIER_SIZE); } + return nfserr; } -void -nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) +static const u32 nfs4_minimal_spo_must_enforce[2] = { + [1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) | + 1 << (OP_EXCHANGE_ID - 32) | + 1 << (OP_CREATE_SESSION - 32) | + 1 << (OP_DESTROY_SESSION - 32) | + 1 << (OP_DESTROY_CLIENTID - 32) +}; + +static __be32 +nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_exchange_id *exid) { - __be32 *statp; - ENCODE_HEAD; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + char *major_id; + char *server_scope; + int major_id_sz; + int server_scope_sz; + uint64_t minor_id = 0; - RESERVE_SPACE(8); - WRITE32(op->opnum); - statp = p++; /* to be backfilled at the end */ - ADJUST_ARGS(); + if (nfserr) + return nfserr; - switch (op->opnum) { - case OP_ACCESS: - nfsd4_encode_access(resp, op->status, &op->u.access); - break; - case OP_CLOSE: - nfsd4_encode_close(resp, op->status, &op->u.close); - break; - case OP_COMMIT: - nfsd4_encode_commit(resp, op->status, &op->u.commit); - break; - case OP_CREATE: - nfsd4_encode_create(resp, op->status, &op->u.create); - break; - case OP_DELEGRETURN: - break; - case OP_GETATTR: - op->status = nfsd4_encode_getattr(resp, op->status, &op->u.getattr); - break; - case OP_GETFH: - nfsd4_encode_getfh(resp, op->status, op->u.getfh); - break; - case OP_LINK: - nfsd4_encode_link(resp, op->status, &op->u.link); - break; - case OP_LOCK: - nfsd4_encode_lock(resp, op->status, &op->u.lock); - break; - case OP_LOCKT: - nfsd4_encode_lockt(resp, op->status, &op->u.lockt); - break; - case OP_LOCKU: - nfsd4_encode_locku(resp, op->status, &op->u.locku); - break; - case OP_LOOKUP: - break; - case OP_LOOKUPP: - break; - case OP_NVERIFY: - break; - case OP_OPEN: - nfsd4_encode_open(resp, op->status, &op->u.open); - break; - case OP_OPEN_CONFIRM: - nfsd4_encode_open_confirm(resp, op->status, &op->u.open_confirm); - break; - case OP_OPEN_DOWNGRADE: - nfsd4_encode_open_downgrade(resp, op->status, &op->u.open_downgrade); - break; - case OP_PUTFH: - break; - case OP_PUTROOTFH: - break; - case OP_READ: - op->status = nfsd4_encode_read(resp, op->status, &op->u.read); - break; - case OP_READDIR: - op->status = nfsd4_encode_readdir(resp, op->status, &op->u.readdir); - break; - case OP_READLINK: - op->status = nfsd4_encode_readlink(resp, op->status, &op->u.readlink); - break; - case OP_REMOVE: - nfsd4_encode_remove(resp, op->status, &op->u.remove); - break; - case OP_RENAME: - nfsd4_encode_rename(resp, op->status, &op->u.rename); - break; - case OP_RENEW: - break; - case OP_RESTOREFH: - break; - case OP_SAVEFH: - break; - case OP_SECINFO: - nfsd4_encode_secinfo(resp, op->status, &op->u.secinfo); - break; - case OP_SETATTR: - nfsd4_encode_setattr(resp, op->status, &op->u.setattr); - break; - case OP_SETCLIENTID: - nfsd4_encode_setclientid(resp, op->status, &op->u.setclientid); - break; - case OP_SETCLIENTID_CONFIRM: - break; - case OP_VERIFY: - break; - case OP_WRITE: - nfsd4_encode_write(resp, op->status, &op->u.write); + major_id = utsname()->nodename; + major_id_sz = strlen(major_id); + server_scope = utsname()->nodename; + server_scope_sz = strlen(server_scope); + + p = xdr_reserve_space(xdr, + 8 /* eir_clientid */ + + 4 /* eir_sequenceid */ + + 4 /* eir_flags */ + + 4 /* spr_how */); + if (!p) + return nfserr_resource; + + p = xdr_encode_opaque_fixed(p, &exid->clientid, 8); + *p++ = cpu_to_be32(exid->seqid); + *p++ = cpu_to_be32(exid->flags); + + *p++ = cpu_to_be32(exid->spa_how); + + switch (exid->spa_how) { + case SP4_NONE: break; - case OP_RELEASE_LOCKOWNER: + case SP4_MACH_CRED: + /* spo_must_enforce, spo_must_allow */ + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; + + /* spo_must_enforce bitmap: */ + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[0]); + *p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[1]); + /* empty spo_must_allow bitmap: */ + *p++ = cpu_to_be32(0); + break; default: - break; + WARN_ON_ONCE(1); } - /* - * Note: We write the status directly, instead of using WRITE32(), - * since it is already in network byte order. - */ - *statp = op->status; + p = xdr_reserve_space(xdr, + 8 /* so_minor_id */ + + 4 /* so_major_id.len */ + + (XDR_QUADLEN(major_id_sz) * 4) + + 4 /* eir_server_scope.len */ + + (XDR_QUADLEN(server_scope_sz) * 4) + + 4 /* eir_server_impl_id.count (0) */); + if (!p) + return nfserr_resource; + + /* The server_owner struct */ + p = xdr_encode_hyper(p, minor_id); /* Minor id */ + /* major id */ + p = xdr_encode_opaque(p, major_id, major_id_sz); + + /* Server scope */ + p = xdr_encode_opaque(p, server_scope, server_scope_sz); + + /* Implementation id */ + *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */ + return 0; +} + +static __be32 +nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_create_session *sess) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 24); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, sess->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(sess->seqid); + *p++ = cpu_to_be32(sess->flags); + + p = xdr_reserve_space(xdr, 28); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); /* headerpadsz */ + *p++ = cpu_to_be32(sess->fore_channel.maxreq_sz); + *p++ = cpu_to_be32(sess->fore_channel.maxresp_sz); + *p++ = cpu_to_be32(sess->fore_channel.maxresp_cached); + *p++ = cpu_to_be32(sess->fore_channel.maxops); + *p++ = cpu_to_be32(sess->fore_channel.maxreqs); + *p++ = cpu_to_be32(sess->fore_channel.nr_rdma_attrs); + + if (sess->fore_channel.nr_rdma_attrs) { + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sess->fore_channel.rdma_attrs); + } + + p = xdr_reserve_space(xdr, 28); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(0); /* headerpadsz */ + *p++ = cpu_to_be32(sess->back_channel.maxreq_sz); + *p++ = cpu_to_be32(sess->back_channel.maxresp_sz); + *p++ = cpu_to_be32(sess->back_channel.maxresp_cached); + *p++ = cpu_to_be32(sess->back_channel.maxops); + *p++ = cpu_to_be32(sess->back_channel.maxreqs); + *p++ = cpu_to_be32(sess->back_channel.nr_rdma_attrs); + + if (sess->back_channel.nr_rdma_attrs) { + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sess->back_channel.rdma_attrs); + } + return 0; +} + +static __be32 +nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_sequence *seq) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, seq->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(seq->seqid); + *p++ = cpu_to_be32(seq->slotid); + /* Note slotid's are numbered from zero: */ + *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_highest_slotid */ + *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_target_highest_slotid */ + *p++ = cpu_to_be32(seq->status_flags); + + resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */ + return 0; +} + +static __be32 +nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_test_stateid *test_stateid) +{ + struct xdr_stream *xdr = &resp->xdr; + struct nfsd4_test_stateid_id *stateid, *next; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids)); + if (!p) + return nfserr_resource; + *p++ = htonl(test_stateid->ts_num_ids); + + list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) { + *p++ = stateid->ts_id_status; + } + + return nfserr; +} + +static __be32 +nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) +{ + return nfserr; +} + +typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); + +/* + * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 + * since we don't need to filter out obsolete ops as this is + * done in the decoding phase. + */ +static nfsd4_enc nfsd4_enc_ops[] = { + [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, + [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, + [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, + [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create, + [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr, + [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh, + [OP_LINK] = (nfsd4_enc)nfsd4_encode_link, + [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock, + [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt, + [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku, + [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, + [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, + [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, + [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop, + [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, + [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_READ] = (nfsd4_enc)nfsd4_encode_read, + [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir, + [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink, + [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove, + [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename, + [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop, + [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo, + [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr, + [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop, + [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, + [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, + + /* NFSv4.1 operations */ + [OP_BACKCHANNEL_CTL] = (nfsd4_enc)nfsd4_encode_noop, + [OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session, + [OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id, + [OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session, + [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, + [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, + [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, + [OP_TEST_STATEID] = (nfsd4_enc)nfsd4_encode_test_stateid, + [OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop, + [OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop, +}; + +/* + * Calculate whether we still have space to encode repsize bytes. + * There are two considerations: + * - For NFS versions >=4.1, the size of the reply must stay within + * session limits + * - For all NFS versions, we must stay within limited preallocated + * buffer space. + * + * This is called before the operation is processed, so can only provide + * an upper estimate. For some nonidempotent operations (such as + * getattr), it's not necessarily a problem if that estimate is wrong, + * as we can fail it after processing without significant side effects. + */ +__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize) +{ + struct xdr_buf *buf = &resp->rqstp->rq_res; + struct nfsd4_slot *slot = resp->cstate.slot; + + if (buf->len + respsize <= buf->buflen) + return nfs_ok; + if (!nfsd4_has_session(&resp->cstate)) + return nfserr_resource; + if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) { + WARN_ON_ONCE(1); + return nfserr_rep_too_big_to_cache; + } + return nfserr_rep_too_big; +} + +void +nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) +{ + struct xdr_stream *xdr = &resp->xdr; + struct nfs4_stateowner *so = resp->cstate.replay_owner; + struct svc_rqst *rqstp = resp->rqstp; + int post_err_offset; + nfsd4_enc encoder; + __be32 *p; + + p = xdr_reserve_space(xdr, 8); + if (!p) { + WARN_ON_ONCE(1); + return; + } + *p++ = cpu_to_be32(op->opnum); + post_err_offset = xdr->buf->len; + + if (op->opnum == OP_ILLEGAL) + goto status; + BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) || + !nfsd4_enc_ops[op->opnum]); + encoder = nfsd4_enc_ops[op->opnum]; + op->status = encoder(resp, op->status, &op->u); + xdr_commit_encode(xdr); + + /* nfsd4_check_resp_size guarantees enough room for error status */ + if (!op->status) { + int space_needed = 0; + if (!nfsd4_last_compound_op(rqstp)) + space_needed = COMPOUND_ERR_SLACK_SPACE; + op->status = nfsd4_check_resp_size(resp, space_needed); + } + if (op->status == nfserr_resource && nfsd4_has_session(&resp->cstate)) { + struct nfsd4_slot *slot = resp->cstate.slot; + + if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) + op->status = nfserr_rep_too_big_to_cache; + else + op->status = nfserr_rep_too_big; + } + if (op->status == nfserr_resource || + op->status == nfserr_rep_too_big || + op->status == nfserr_rep_too_big_to_cache) { + /* + * The operation may have already been encoded or + * partially encoded. No op returns anything additional + * in the case of one of these three errors, so we can + * just truncate back to after the status. But it's a + * bug if we had to do this on a non-idempotent op: + */ + warn_on_nonidempotent_op(op); + xdr_truncate_encode(xdr, post_err_offset); + } + if (so) { + int len = xdr->buf->len - post_err_offset; + + so->so_replay.rp_status = op->status; + so->so_replay.rp_buflen = len; + read_bytes_from_xdr_buf(xdr->buf, post_err_offset, + so->so_replay.rp_buf, len); + } +status: + /* Note that op->status is already in network byte order: */ + write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4); } /* @@ -2719,35 +3941,35 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) * called with nfs4_lock_state() held */ void -nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op) +nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) { - ENCODE_HEAD; + __be32 *p; struct nfs4_replay *rp = op->replay; BUG_ON(!rp); - RESERVE_SPACE(8); - WRITE32(op->opnum); + p = xdr_reserve_space(xdr, 8 + rp->rp_buflen); + if (!p) { + WARN_ON_ONCE(1); + return; + } + *p++ = cpu_to_be32(op->opnum); *p++ = rp->rp_status; /* already xdr'ed */ - ADJUST_ARGS(); - RESERVE_SPACE(rp->rp_buflen); - WRITEMEM(rp->rp_buf, rp->rp_buflen); - ADJUST_ARGS(); + p = xdr_encode_opaque_fixed(p, rp->rp_buf, rp->rp_buflen); } -/* - * END OF "GENERIC" ENCODE ROUTINES. - */ - int nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) { return xdr_ressize_check(rqstp, p); } -void nfsd4_release_compoundargs(struct nfsd4_compoundargs *args) +int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) { + struct svc_rqst *rqstp = rq; + struct nfsd4_compoundargs *args = rqstp->rq_argp; + if (args->ops != args->iops) { kfree(args->ops); args->ops = args->iops; @@ -2760,13 +3982,18 @@ void nfsd4_release_compoundargs(struct nfsd4_compoundargs *args) tb->release(tb->buf); kfree(tb); } + return 1; } int nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args) { - __be32 status; - + if (rqstp->rq_arg.head[0].iov_len % 4) { + /* client is nuts */ + dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)", + __func__, svc_addr(rqstp), be32_to_cpu(rqstp->rq_xid)); + return 0; + } args->p = p; args->end = rqstp->rq_arg.head[0].iov_base + rqstp->rq_arg.head[0].iov_len; args->pagelist = rqstp->rq_arg.pages; @@ -2776,11 +4003,7 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_comp args->ops = args->iops; args->rqstp = rqstp; - status = nfsd4_decode_compound(args); - if (status) { - nfsd4_release_compoundargs(args); - } - return !status; + return !nfsd4_decode_compound(args); } int @@ -2789,19 +4012,33 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo /* * All that remains is to write the tag and operation count... */ - struct kvec *iov; + struct nfsd4_compound_state *cs = &resp->cstate; + struct xdr_buf *buf = resp->xdr.buf; + + WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + + buf->tail[0].iov_len); + + rqstp->rq_next_page = resp->xdr.page_ptr + 1; + p = resp->tagp; *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); p += XDR_QUADLEN(resp->taglen); *p++ = htonl(resp->opcnt); - if (rqstp->rq_res.page_len) - iov = &rqstp->rq_res.tail[0]; - else - iov = &rqstp->rq_res.head[0]; - iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base; - BUG_ON(iov->iov_len > PAGE_SIZE); + if (nfsd4_has_session(cs)) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfs4_client *clp = cs->session->se_client; + if (cs->status != nfserr_replay_cache) { + nfsd4_store_cache_entry(resp); + cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE; + } + /* Renew the clientid on success and on replay */ + spin_lock(&nn->client_lock); + nfsd4_put_session(cs->session); + spin_unlock(&nn->client_lock); + put_client_renew(clp); + } return 1; } |