diff options
53 files changed, 2265 insertions, 1999 deletions
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt index b930ad0..c49cd7e 100644 --- a/Documentation/filesystems/nfs/nfs41-server.txt +++ b/Documentation/filesystems/nfs/nfs41-server.txt @@ -176,7 +176,5 @@ Nonstandard compound limitations: ca_maxrequestsize request and a ca_maxresponsesize reply, so we may fail to live up to the promise we made in CREATE_SESSION fore channel negotiation. -* No more than one read-like operation allowed per compound; encoding - replies that cross page boundaries (except for read data) not handled. See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues. diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 00ec0b9..d3e40db 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -14,6 +14,8 @@ #include <linux/sunrpc/stats.h> #include <linux/lockd/lockd.h> +#include <uapi/linux/nfs3.h> + #define NLMDBG_FACILITY NLMDBG_XDR #if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ) diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 9a55797..3e9f787 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -15,6 +15,8 @@ #include <linux/sunrpc/stats.h> #include <linux/lockd/lockd.h> +#include <uapi/linux/nfs2.h> + #define NLMDBG_FACILITY NLMDBG_XDR #if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index de051cb1..8f27c93 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -622,8 +622,8 @@ static int __init init_nlm(void) err_pernet: #ifdef CONFIG_SYSCTL unregister_sysctl_table(nlm_sysctl_table); -#endif err_sysctl: +#endif return err; } diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index dc5c759..b6f3b84 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -14,12 +14,11 @@ #include <linux/mutex.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/addr.h> -#include <linux/nfsd/nfsfh.h> -#include <linux/nfsd/export.h> #include <linux/lockd/lockd.h> #include <linux/lockd/share.h> #include <linux/module.h> #include <linux/mount.h> +#include <uapi/linux/nfs2.h> #define NLMDBG_FACILITY NLMDBG_SVCSUBS diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 964666c..9340e7e 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -16,6 +16,8 @@ #include <linux/sunrpc/stats.h> #include <linux/lockd/lockd.h> +#include <uapi/linux/nfs2.h> + #define NLMDBG_FACILITY NLMDBG_XDR diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 397be39..7f55fed 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2750,7 +2750,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL) #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) -#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_CHANGE_SECURITY_LABEL - 1UL) +#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_SECURITY_LABEL - 1UL) static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h index b481e1f..a986ceb 100644 --- a/fs/nfsd/acl.h +++ b/fs/nfsd/acl.h @@ -49,7 +49,7 @@ struct svc_rqst; struct nfs4_acl *nfs4_acl_new(int); int nfs4_acl_get_whotype(char *, u32); -__be32 nfs4_acl_write_who(int who, __be32 **p, int *len); +__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who); int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 2645be4..72f4482 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -1,7 +1,6 @@ /* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ #include <linux/sched.h> -#include <linux/user_namespace.h> #include "nfsd.h" #include "auth.h" @@ -25,7 +24,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) struct cred *new; int i; int flags = nfsexp_flags(rqstp, exp); - int ret; validate_process_creds(); @@ -86,8 +84,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) return 0; oom: - ret = -ENOMEM; abort_creds(new); - return ret; + return -ENOMEM; } diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 8513c59..13b85f9 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -17,17 +17,12 @@ #include <linux/exportfs.h> #include <linux/sunrpc/svc_xprt.h> -#include <net/ipv6.h> - #include "nfsd.h" #include "nfsfh.h" #include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT -typedef struct auth_domain svc_client; -typedef struct svc_export svc_export; - /* * We have two caches. * One maps client+vfsmnt+dentry to export options - the export map @@ -73,7 +68,7 @@ static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) { - /* client fsidtype fsid [path] */ + /* client fsidtype fsid expiry [path] */ char *buf; int len; struct auth_domain *dom = NULL; @@ -295,13 +290,19 @@ svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) { + struct nfsd4_fs_location *locations = fsloc->locations; int i; + if (!locations) + return; + for (i = 0; i < fsloc->locations_count; i++) { - kfree(fsloc->locations[i].path); - kfree(fsloc->locations[i].hosts); + kfree(locations[i].path); + kfree(locations[i].hosts); } - kfree(fsloc->locations); + + kfree(locations); + fsloc->locations = NULL; } static void svc_export_put(struct kref *ref) @@ -388,6 +389,10 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc) int len; int migrated, i, err; + /* more than one fsloc */ + if (fsloc->locations) + return -EINVAL; + /* listsize */ err = get_uint(mesg, &fsloc->locations_count); if (err) @@ -437,13 +442,18 @@ out_free_all: static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { - int listsize, err; struct exp_flavor_info *f; + u32 listsize; + int err; + + /* more than one secinfo */ + if (exp->ex_nflavors) + return -EINVAL; - err = get_int(mesg, &listsize); + err = get_uint(mesg, &listsize); if (err) return err; - if (listsize < 0 || listsize > MAX_SECINFO_LIST) + if (listsize > MAX_SECINFO_LIST) return -EINVAL; for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) { @@ -474,6 +484,27 @@ static inline int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif +static inline int +uuid_parse(char **mesg, char *buf, unsigned char **puuid) +{ + int len; + + /* more than one uuid */ + if (*puuid) + return -EINVAL; + + /* expect a 16 byte uuid encoded as \xXXXX... */ + len = qword_get(mesg, buf, PAGE_SIZE); + if (len != EX_UUID_LEN) + return -EINVAL; + + *puuid = kmemdup(buf, EX_UUID_LEN, GFP_KERNEL); + if (*puuid == NULL) + return -ENOMEM; + + return 0; +} + static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) { /* client path expiry [flags anonuid anongid fsid] */ @@ -552,18 +583,9 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) { if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); - else if (strcmp(buf, "uuid") == 0) { - /* expect a 16 byte uuid encoded as \xXXXX... */ - len = qword_get(&mesg, buf, PAGE_SIZE); - if (len != 16) - err = -EINVAL; - else { - exp.ex_uuid = - kmemdup(buf, 16, GFP_KERNEL); - if (exp.ex_uuid == NULL) - err = -ENOMEM; - } - } else if (strcmp(buf, "secinfo") == 0) + else if (strcmp(buf, "uuid") == 0) + err = uuid_parse(&mesg, buf, &exp.ex_uuid); + else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); else /* quietly ignore unknown words and anything @@ -649,7 +671,7 @@ static int svc_export_show(struct seq_file *m, if (exp->ex_uuid) { int i; seq_puts(m, ",uuid="); - for (i=0; i<16; i++) { + for (i = 0; i < EX_UUID_LEN; i++) { if ((i&3) == 0 && i) seq_putc(m, ':'); seq_printf(m, "%02x", exp->ex_uuid[i]); @@ -771,7 +793,7 @@ svc_export_update(struct svc_export *new, struct svc_export *old) static struct svc_expkey * -exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type, +exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) { struct svc_expkey key, *ek; @@ -793,9 +815,9 @@ exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type, return ek; } - -static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp, - const struct path *path, struct cache_req *reqp) +static struct svc_export * +exp_get_by_name(struct cache_detail *cd, struct auth_domain *clp, + const struct path *path, struct cache_req *reqp) { struct svc_export *exp, key; int err; @@ -819,11 +841,11 @@ static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp, /* * Find the export entry for a given dentry. */ -static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp, - struct path *path) +static struct svc_export * +exp_parent(struct cache_detail *cd, struct auth_domain *clp, struct path *path) { struct dentry *saved = dget(path->dentry); - svc_export *exp = exp_get_by_name(cd, clp, path, NULL); + struct svc_export *exp = exp_get_by_name(cd, clp, path, NULL); while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) { struct dentry *parent = dget_parent(path->dentry); @@ -844,7 +866,7 @@ static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp, * since its harder to fool a kernel module than a user space program. */ int -exp_rootfh(struct net *net, svc_client *clp, char *name, +exp_rootfh(struct net *net, struct auth_domain *clp, char *name, struct knfsd_fh *f, int maxsize) { struct svc_export *exp; diff --git a/include/linux/nfsd/export.h b/fs/nfsd/export.h index 7898c99..cfeea85 100644 --- a/include/linux/nfsd/export.h +++ b/fs/nfsd/export.h @@ -1,17 +1,16 @@ /* - * include/linux/nfsd/export.h - * - * Public declarations for NFS exports. The definitions for the - * syscall interface are in nfsctl.h - * * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de> */ #ifndef NFSD_EXPORT_H #define NFSD_EXPORT_H -# include <linux/nfsd/nfsfh.h> +#include <linux/sunrpc/cache.h> #include <uapi/linux/nfsd/export.h> +struct knfsd_fh; +struct svc_fh; +struct svc_rqst; + /* * FS Locations */ @@ -38,6 +37,7 @@ struct nfsd4_fs_locations { * spkm3i, and spkm3p (and using all 8 at once should be rare). */ #define MAX_SECINFO_LIST 8 +#define EX_UUID_LEN 16 struct exp_flavor_info { u32 pseudoflavor; @@ -54,7 +54,7 @@ struct svc_export { int ex_fsid; unsigned char * ex_uuid; /* 16 byte fsid */ struct nfsd4_fs_locations ex_fslocs; - int ex_nflavors; + uint32_t ex_nflavors; struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST]; struct cache_detail *cd; }; diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c index d620e7f..2ed05c3 100644 --- a/fs/nfsd/fault_inject.c +++ b/fs/nfsd/fault_inject.c @@ -97,25 +97,14 @@ static ssize_t fault_inject_read(struct file *file, char __user *buf, { static u64 val; char read_buf[25]; - size_t size, ret; + size_t size; loff_t pos = *ppos; if (!pos) nfsd_inject_get(file_inode(file)->i_private, &val); size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val); - if (pos < 0) - return -EINVAL; - if (pos >= size || !len) - return 0; - if (len > size - pos) - len = size - pos; - ret = copy_to_user(buf, read_buf + pos, len); - if (ret == len) - return -EFAULT; - len -= ret; - *ppos = pos + len; - return len; + return simple_read_from_buffer(buf, len, ppos, read_buf, size); } static ssize_t fault_inject_write(struct file *file, const char __user *buf, diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h index 66e58db..a3f3490 100644 --- a/fs/nfsd/idmap.h +++ b/fs/nfsd/idmap.h @@ -56,7 +56,7 @@ static inline void nfsd_idmap_shutdown(struct net *net) __be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *); __be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *); -__be32 nfsd4_encode_user(struct svc_rqst *, kuid_t, __be32 **, int *); -__be32 nfsd4_encode_group(struct svc_rqst *, kgid_t, __be32 **, int *); +__be32 nfsd4_encode_user(struct xdr_stream *, struct svc_rqst *, kuid_t); +__be32 nfsd4_encode_group(struct xdr_stream *, struct svc_rqst *, kgid_t); #endif /* LINUX_NFSD_IDMAP_H */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 11c1fba..12b023a 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -182,7 +182,8 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclargs *argp) { - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; argp->mask = ntohl(*p); p++; @@ -197,7 +198,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, unsigned int base; int n; - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; argp->mask = ntohl(*p++); if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) || @@ -218,7 +220,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *argp) { - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; return xdr_argsize_check(rqstp, p); } @@ -226,7 +229,8 @@ static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_accessargs *argp) { - if (!(p = nfs2svc_decode_fh(p, &argp->fh))) + p = nfs2svc_decode_fh(p, &argp->fh); + if (!p) return 0; argp->access = ntohl(*p++); diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index adc5f1b..2a514e2 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -128,7 +128,8 @@ out: static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclargs *args) { - if (!(p = nfs3svc_decode_fh(p, &args->fh))) + p = nfs3svc_decode_fh(p, &args->fh); + if (!p) return 0; args->mask = ntohl(*p); p++; @@ -143,7 +144,8 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, unsigned int base; int n; - if (!(p = nfs3svc_decode_fh(p, &args->fh))) + p = nfs3svc_decode_fh(p, &args->fh); + if (!p) return 0; args->mask = ntohl(*p++); if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) || diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index de6e39e..e6c01e8 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -278,7 +278,8 @@ void fill_post_wcc(struct svc_fh *fhp) int nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; return xdr_argsize_check(rqstp, p); } @@ -287,7 +288,8 @@ int nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_sattrargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = decode_sattr3(p, &args->attrs); @@ -315,7 +317,8 @@ int nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_accessargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->access = ntohl(*p++); @@ -330,7 +333,8 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, int v; u32 max_blocksize = svc_max_payload(rqstp); - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); @@ -360,7 +364,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); @@ -535,7 +540,8 @@ int nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_readlinkargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); @@ -558,7 +564,8 @@ int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_readdirargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->cookie); args->verf = p; p += 2; @@ -580,7 +587,8 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, int len; u32 max_blocksize = svc_max_payload(rqstp); - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->cookie); args->verf = p; p += 2; @@ -605,7 +613,8 @@ int nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_commitargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); args->count = ntohl(*p++); diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index f66c66b..d714156 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -36,7 +36,6 @@ #include <linux/slab.h> #include <linux/nfs_fs.h> -#include <linux/export.h> #include "nfsfh.h" #include "nfsd.h" #include "acl.h" @@ -920,20 +919,19 @@ nfs4_acl_get_whotype(char *p, u32 len) return NFS4_ACL_WHO_NAMED; } -__be32 nfs4_acl_write_who(int who, __be32 **p, int *len) +__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who) { + __be32 *p; int i; - int bytes; for (i = 0; i < ARRAY_SIZE(s2t_map); i++) { if (s2t_map[i].type != who) continue; - bytes = 4 + (XDR_QUADLEN(s2t_map[i].stringlen) << 2); - if (bytes > *len) + p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4); + if (!p) return nfserr_resource; - *p = xdr_encode_opaque(*p, s2t_map[i].string, + p = xdr_encode_opaque(p, s2t_map[i].string, s2t_map[i].stringlen); - *len -= bytes; return 0; } WARN_ON_ONCE(1); diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index c0dfde6..a0ab0a8 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -551,44 +551,43 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen return 0; } -static __be32 encode_ascii_id(u32 id, __be32 **p, int *buflen) +static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id) { char buf[11]; int len; - int bytes; + __be32 *p; len = sprintf(buf, "%u", id); - bytes = 4 + (XDR_QUADLEN(len) << 2); - if (bytes > *buflen) + p = xdr_reserve_space(xdr, len + 4); + if (!p) return nfserr_resource; - *p = xdr_encode_opaque(*p, buf, len); - *buflen -= bytes; + p = xdr_encode_opaque(p, buf, len); return 0; } -static __be32 idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen) +static __be32 idmap_id_to_name(struct xdr_stream *xdr, + struct svc_rqst *rqstp, int type, u32 id) { struct ent *item, key = { .id = id, .type = type, }; + __be32 *p; int ret; - int bytes; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item); if (ret == -ENOENT) - return encode_ascii_id(id, p, buflen); + return encode_ascii_id(xdr, id); if (ret) return nfserrno(ret); ret = strlen(item->name); WARN_ON_ONCE(ret > IDMAP_NAMESZ); - bytes = 4 + (XDR_QUADLEN(ret) << 2); - if (bytes > *buflen) + p = xdr_reserve_space(xdr, ret + 4); + if (!p) return nfserr_resource; - *p = xdr_encode_opaque(*p, item->name, ret); - *buflen -= bytes; + p = xdr_encode_opaque(p, item->name, ret); cache_put(&item->h, nn->idtoname_cache); return 0; } @@ -622,11 +621,12 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u return idmap_name_to_id(rqstp, type, name, namelen, id); } -static __be32 encode_name_from_id(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen) +static __be32 encode_name_from_id(struct xdr_stream *xdr, + struct svc_rqst *rqstp, int type, u32 id) { if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS) - return encode_ascii_id(id, p, buflen); - return idmap_id_to_name(rqstp, type, id, p, buflen); + return encode_ascii_id(xdr, id); + return idmap_id_to_name(xdr, rqstp, type, id); } __be32 @@ -655,14 +655,16 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, return status; } -__be32 nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t uid, __be32 **p, int *buflen) +__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp, + kuid_t uid) { u32 id = from_kuid(&init_user_ns, uid); - return encode_name_from_id(rqstp, IDMAP_TYPE_USER, id, p, buflen); + return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id); } -__be32 nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t gid, __be32 **p, int *buflen) +__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp, + kgid_t gid) { u32 id = from_kgid(&init_user_ns, gid); - return encode_name_from_id(rqstp, IDMAP_TYPE_GROUP, id, p, buflen); + return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index d543222..6851b00 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -430,12 +430,12 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; break; case NFS4_OPEN_CLAIM_PREVIOUS: - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion, nn); if (status) goto out; + open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; case NFS4_OPEN_CLAIM_FH: case NFS4_OPEN_CLAIM_DELEG_CUR_FH: status = do_open_fhandle(rqstp, cstate, open); @@ -445,7 +445,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, break; case NFS4_OPEN_CLAIM_DELEG_PREV_FH: case NFS4_OPEN_CLAIM_DELEGATE_PREV: - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; dprintk("NFSD: unsupported OPEN claim type %d\n", open->op_claim_type); status = nfserr_notsupp; @@ -786,7 +785,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!nfsd4_last_compound_op(rqstp)) rqstp->rq_splice_ok = false; - nfs4_lock_state(); /* check stateid */ if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, &read->rd_stateid, @@ -794,11 +792,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; } - if (read->rd_filp) - get_file(read->rd_filp); status = nfs_ok; out: - nfs4_unlock_state(); read->rd_rqstp = rqstp; read->rd_fhp = &cstate->current_fh; return status; @@ -937,10 +932,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int err; if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { - nfs4_lock_state(); status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, &setattr->sa_stateid, WR_STATE, NULL); - nfs4_unlock_state(); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -1006,17 +999,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (write->wr_offset >= OFFSET_MAX) return nfserr_inval; - nfs4_lock_state(); status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, stateid, WR_STATE, &filp); if (status) { - nfs4_unlock_state(); dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; } - if (filp) - get_file(filp); - nfs4_unlock_state(); cnt = write->wr_buflen; write->wr_how_written = write->wr_stable_how; @@ -1072,10 +1060,10 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_jukebox; p = buf; - status = nfsd4_encode_fattr(&cstate->current_fh, + status = nfsd4_encode_fattr_to_buf(&p, count, &cstate->current_fh, cstate->current_fh.fh_export, - cstate->current_fh.fh_dentry, &p, - count, verify->ve_bmval, + cstate->current_fh.fh_dentry, + verify->ve_bmval, rqstp, 0); /* * If nfsd4_encode_fattr() ran out of space, assume that's because @@ -1182,9 +1170,7 @@ struct nfsd4_operation { static struct nfsd4_operation nfsd4_ops[]; -#ifdef NFSD_DEBUG static const char *nfsd4_op_name(unsigned opnum); -#endif /* * Enforce NFSv4.1 COMPOUND ordering rules: @@ -1226,6 +1212,8 @@ static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op) bool nfsd4_cache_this_op(struct nfsd4_op *op) { + if (op->opnum == OP_ILLEGAL) + return false; return OPDESC(op)->op_flags & OP_CACHEME; } @@ -1262,6 +1250,25 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) return !(nextd->op_flags & OP_HANDLES_WRONGSEC); } +static void svcxdr_init_encode(struct svc_rqst *rqstp, + struct nfsd4_compoundres *resp) +{ + struct xdr_stream *xdr = &resp->xdr; + struct xdr_buf *buf = &rqstp->rq_res; + struct kvec *head = buf->head; + + xdr->buf = buf; + xdr->iov = head; + xdr->p = head->iov_base + head->iov_len; + xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack; + /* Tail and page_len should be zero at this point: */ + buf->len = buf->head[0].iov_len; + xdr->scratch.iov_len = 0; + xdr->page_ptr = buf->pages - 1; + buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages) + - rqstp->rq_auth_slack; +} + /* * COMPOUND call. */ @@ -1275,24 +1282,16 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; - int slack_bytes; - u32 plen = 0; __be32 status; - resp->xbuf = &rqstp->rq_res; - resp->p = rqstp->rq_res.head[0].iov_base + - rqstp->rq_res.head[0].iov_len; - resp->tagp = resp->p; + svcxdr_init_encode(rqstp, resp); + resp->tagp = resp->xdr.p; /* reserve space for: taglen, tag, and opcnt */ - resp->p += 2 + XDR_QUADLEN(args->taglen); - resp->end = rqstp->rq_res.head[0].iov_base + PAGE_SIZE; + xdr_reserve_space(&resp->xdr, 8 + args->taglen); resp->taglen = args->taglen; resp->tag = args->tag; - resp->opcnt = 0; resp->rqstp = rqstp; cstate->minorversion = args->minorversion; - cstate->replay_owner = NULL; - cstate->session = NULL; fh_init(current_fh, NFS4_FHSIZE); fh_init(save_fh, NFS4_FHSIZE); /* @@ -1332,19 +1331,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, goto encode_op; } - /* We must be able to encode a successful response to - * this operation, with enough room left over to encode a - * failed response to the next operation. If we don't - * have enough room, fail with ERR_RESOURCE. - */ - slack_bytes = (char *)resp->end - (char *)resp->p; - if (slack_bytes < COMPOUND_SLACK_SPACE - + COMPOUND_ERR_SLACK_SPACE) { - BUG_ON(slack_bytes < COMPOUND_ERR_SLACK_SPACE); - op->status = nfserr_resource; - goto encode_op; - } - opdesc = OPDESC(op); if (!current_fh->fh_dentry) { @@ -1362,9 +1348,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, /* If op is non-idempotent */ if (opdesc->op_flags & OP_MODIFIES_SOMETHING) { - plen = opdesc->op_rsize_bop(rqstp, op); /* - * If there's still another operation, make sure + * Don't execute this op if we couldn't encode a + * succesful reply: + */ + u32 plen = opdesc->op_rsize_bop(rqstp, op); + /* + * Plus if there's another operation, make sure * we'll have space to at least encode an error: */ if (resp->opcnt < args->opcnt) @@ -1399,7 +1389,7 @@ encode_op: } if (op->status == nfserr_replay_me) { op->replay = &cstate->replay_owner->so_replay; - nfsd4_encode_replay(resp, op); + nfsd4_encode_replay(&resp->xdr, op); status = op->status = op->replay->rp_status; } else { nfsd4_encode_operation(resp, op); @@ -1438,7 +1428,8 @@ out: #define op_encode_change_info_maxsz (5) #define nfs4_fattr_bitmap_maxsz (4) -#define op_encode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +/* We'll fall back on returning no lockowner if run out of space: */ +#define op_encode_lockowner_maxsz (0) #define op_encode_lock_denied_maxsz (8 + op_encode_lockowner_maxsz) #define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) @@ -1470,6 +1461,49 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); } +/* + * Note since this is an idempotent operation we won't insist on failing + * the op prematurely if the estimate is too large. We may turn off splice + * reads unnecessarily. + */ +static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + u32 *bmap = op->u.getattr.ga_bmval; + u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2]; + u32 ret = 0; + + if (bmap0 & FATTR4_WORD0_ACL) + return svc_max_payload(rqstp); + if (bmap0 & FATTR4_WORD0_FS_LOCATIONS) + return svc_max_payload(rqstp); + + if (bmap1 & FATTR4_WORD1_OWNER) { + ret += IDMAP_NAMESZ + 4; + bmap1 &= ~FATTR4_WORD1_OWNER; + } + if (bmap1 & FATTR4_WORD1_OWNER_GROUP) { + ret += IDMAP_NAMESZ + 4; + bmap1 &= ~FATTR4_WORD1_OWNER_GROUP; + } + if (bmap0 & FATTR4_WORD0_FILEHANDLE) { + ret += NFS4_FHSIZE + 4; + bmap0 &= ~FATTR4_WORD0_FILEHANDLE; + } + if (bmap2 & FATTR4_WORD2_SECURITY_LABEL) { + ret += NFSD4_MAX_SEC_LABEL_LEN + 12; + bmap2 &= ~FATTR4_WORD2_SECURITY_LABEL; + } + /* + * Largest of remaining attributes are 16 bytes (e.g., + * supported_attributes) + */ + ret += 16 * (hweight32(bmap0) + hweight32(bmap1) + hweight32(bmap2)); + /* bitmask, length */ + ret += 20; + return ret; +} + static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) @@ -1500,18 +1534,19 @@ static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) if (rlen > maxcount) rlen = maxcount; - return (op_encode_hdr_size + 2) * sizeof(__be32) + rlen; + return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32); } static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { + u32 maxcount = svc_max_payload(rqstp); u32 rlen = op->u.readdir.rd_maxcount; - if (rlen > PAGE_SIZE) - rlen = PAGE_SIZE; + if (rlen > maxcount) + rlen = maxcount; - return (op_encode_hdr_size + op_encode_verifier_maxsz) - * sizeof(__be32) + rlen; + return (op_encode_hdr_size + op_encode_verifier_maxsz + + XDR_QUADLEN(rlen)) * sizeof(__be32); } static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) @@ -1526,6 +1561,12 @@ static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op + op_encode_change_info_maxsz) * sizeof(__be32); } +static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + return NFS4_MAX_SESSIONID_LEN + 20; +} + static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); @@ -1539,7 +1580,7 @@ static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_o static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { - return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32); + return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32); } static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) @@ -1607,6 +1648,7 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_GETATTR] = { .op_func = (nfsd4op_func)nfsd4_getattr, .op_flags = ALLOWED_ON_ABSENT_FS, + .op_rsize_bop = nfsd4_getattr_rsize, .op_name = "OP_GETATTR", }, [OP_GETFH] = { @@ -1676,37 +1718,32 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_PUTFH] = { .op_func = (nfsd4op_func)nfsd4_putfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING - | OP_CLEAR_STATEID, + | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING - | OP_CLEAR_STATEID, + | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING - | OP_CLEAR_STATEID, + | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, [OP_READ] = { .op_func = (nfsd4op_func)nfsd4_read, - .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_READ", .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, .op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid, }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, - .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_READDIR", .op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize, }, @@ -1864,14 +1901,33 @@ static struct nfsd4_operation nfsd4_ops[] = { }, }; -#ifdef NFSD_DEBUG +int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + struct nfsd4_operation *opdesc; + nfsd4op_rsize estimator; + + if (op->opnum == OP_ILLEGAL) + return op_encode_hdr_size * sizeof(__be32); + opdesc = OPDESC(op); + estimator = opdesc->op_rsize_bop; + return estimator ? estimator(rqstp, op) : PAGE_SIZE; +} + +void warn_on_nonidempotent_op(struct nfsd4_op *op) +{ + if (OPDESC(op)->op_flags & OP_MODIFIES_SOMETHING) { + pr_err("unable to encode reply to nonidempotent op %d (%s)\n", + op->opnum, nfsd4_op_name(op->opnum)); + WARN_ON_ONCE(1); + } +} + static const char *nfsd4_op_name(unsigned opnum) { if (opnum < ARRAY_SIZE(nfsd4_ops)) return nfsd4_ops[opnum].op_name; return "unknown_operation"; } -#endif #define nfsd4_voidres nfsd4_voidargs struct nfsd4_voidargs { int dummy; }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9a77a5a..c0d45ce 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -81,13 +81,13 @@ static DEFINE_MUTEX(client_mutex); * effort to decrease the scope of the client_mutex, this spinlock may * eventually cover more: */ -static DEFINE_SPINLOCK(recall_lock); +static DEFINE_SPINLOCK(state_lock); -static struct kmem_cache *openowner_slab = NULL; -static struct kmem_cache *lockowner_slab = NULL; -static struct kmem_cache *file_slab = NULL; -static struct kmem_cache *stateid_slab = NULL; -static struct kmem_cache *deleg_slab = NULL; +static struct kmem_cache *openowner_slab; +static struct kmem_cache *lockowner_slab; +static struct kmem_cache *file_slab; +static struct kmem_cache *stateid_slab; +static struct kmem_cache *deleg_slab; void nfs4_lock_state(void) @@ -235,9 +235,9 @@ static void nfsd4_free_file(struct nfs4_file *f) static inline void put_nfs4_file(struct nfs4_file *fi) { - if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) { + if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) { hlist_del(&fi->fi_hash); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); iput(fi->fi_inode); nfsd4_free_file(fi); } @@ -375,7 +375,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); if (dp == NULL) return dp; - dp->dl_stid.sc_type = NFS4_DELEG_STID; /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid @@ -418,6 +417,8 @@ nfs4_put_delegation(struct nfs4_delegation *dp) static void nfs4_put_deleg_lease(struct nfs4_file *fp) { + if (!fp->fi_lease) + return; if (atomic_dec_and_test(&fp->fi_delegees)) { vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease); fp->fi_lease = NULL; @@ -431,18 +432,30 @@ static void unhash_stid(struct nfs4_stid *s) s->sc_type = 0; } +static void +hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) +{ + lockdep_assert_held(&state_lock); + + dp->dl_stid.sc_type = NFS4_DELEG_STID; + list_add(&dp->dl_perfile, &fp->fi_delegations); + list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); +} + /* Called under the state lock. */ static void unhash_delegation(struct nfs4_delegation *dp) { + spin_lock(&state_lock); list_del_init(&dp->dl_perclnt); - spin_lock(&recall_lock); list_del_init(&dp->dl_perfile); list_del_init(&dp->dl_recall_lru); - spin_unlock(&recall_lock); - nfs4_put_deleg_lease(dp->dl_file); - put_nfs4_file(dp->dl_file); - dp->dl_file = NULL; + spin_unlock(&state_lock); + if (dp->dl_file) { + nfs4_put_deleg_lease(dp->dl_file); + put_nfs4_file(dp->dl_file); + dp->dl_file = NULL; + } } @@ -645,6 +658,12 @@ static void unhash_lockowner(struct nfs4_lockowner *lo) } } +static void nfs4_free_lockowner(struct nfs4_lockowner *lo) +{ + kfree(lo->lo_owner.so_owner.data); + kmem_cache_free(lockowner_slab, lo); +} + static void release_lockowner(struct nfs4_lockowner *lo) { unhash_lockowner(lo); @@ -699,6 +718,12 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo) } } +static void nfs4_free_openowner(struct nfs4_openowner *oo) +{ + kfree(oo->oo_owner.so_owner.data); + kmem_cache_free(openowner_slab, oo); +} + static void release_openowner(struct nfs4_openowner *oo) { unhash_openowner(oo); @@ -1093,7 +1118,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) return clp; } -static inline void +static void free_client(struct nfs4_client *clp) { struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id); @@ -1136,13 +1161,13 @@ destroy_client(struct nfs4_client *clp) struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); INIT_LIST_HEAD(&reaplist); - spin_lock(&recall_lock); + spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); list_del_init(&dp->dl_perclnt); list_move(&dp->dl_recall_lru, &reaplist); } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); while (!list_empty(&reaplist)) { dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru); destroy_delegation(dp); @@ -1544,6 +1569,7 @@ out_err: void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) { + struct xdr_buf *buf = resp->xdr.buf; struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; @@ -1557,11 +1583,9 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) slot->sl_datalen = 0; return; } - slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap; - base = (char *)resp->cstate.datap - - (char *)resp->xbuf->head[0].iov_base; - if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data, - slot->sl_datalen)) + base = resp->cstate.data_offset; + slot->sl_datalen = buf->len - base; + if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) WARN("%s: sessions DRC could not cache compound\n", __func__); return; } @@ -1602,6 +1626,8 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { struct nfsd4_slot *slot = resp->cstate.slot; + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; __be32 status; dprintk("--> %s slot %p\n", __func__, slot); @@ -1610,14 +1636,16 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, if (status) return status; - /* The sequence operation has been encoded, cstate->datap set. */ - memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen); + p = xdr_reserve_space(xdr, slot->sl_datalen); + if (!p) { + WARN_ON_ONCE(1); + return nfserr_serverfault; + } + xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen); + xdr_commit_encode(xdr); resp->opcnt = slot->sl_opcnt; - resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen); - status = slot->sl_status; - - return status; + return slot->sl_status; } /* @@ -2189,11 +2217,13 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_sequence *seq) { struct nfsd4_compoundres *resp = rqstp->rq_resp; + struct xdr_stream *xdr = &resp->xdr; struct nfsd4_session *session; struct nfs4_client *clp; struct nfsd4_slot *slot; struct nfsd4_conn *conn; __be32 status; + int buflen; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (resp->opcnt != 1) @@ -2262,6 +2292,16 @@ nfsd4_sequence(struct svc_rqst *rqstp, if (status) goto out_put_session; + buflen = (seq->cachethis) ? + session->se_fchannel.maxresp_cached : + session->se_fchannel.maxresp_sz; + status = (seq->cachethis) ? nfserr_rep_too_big_to_cache : + nfserr_rep_too_big; + if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) + goto out_put_session; + svc_reserve(rqstp, buflen); + + status = nfs_ok; /* Success! bump slot seqid */ slot->sl_seqid = seq->seqid; slot->sl_flags |= NFSD4_SLOT_INUSE; @@ -2499,28 +2539,19 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino) fp->fi_lease = NULL; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); - spin_lock(&recall_lock); + spin_lock(&state_lock); hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]); - spin_unlock(&recall_lock); -} - -static void -nfsd4_free_slab(struct kmem_cache **slab) -{ - if (*slab == NULL) - return; - kmem_cache_destroy(*slab); - *slab = NULL; + spin_unlock(&state_lock); } void nfsd4_free_slabs(void) { - nfsd4_free_slab(&openowner_slab); - nfsd4_free_slab(&lockowner_slab); - nfsd4_free_slab(&file_slab); - nfsd4_free_slab(&stateid_slab); - nfsd4_free_slab(&deleg_slab); + kmem_cache_destroy(openowner_slab); + kmem_cache_destroy(lockowner_slab); + kmem_cache_destroy(file_slab); + kmem_cache_destroy(stateid_slab); + kmem_cache_destroy(deleg_slab); } int @@ -2529,42 +2560,38 @@ nfsd4_init_slabs(void) openowner_slab = kmem_cache_create("nfsd4_openowners", sizeof(struct nfs4_openowner), 0, 0, NULL); if (openowner_slab == NULL) - goto out_nomem; + goto out; lockowner_slab = kmem_cache_create("nfsd4_lockowners", sizeof(struct nfs4_lockowner), 0, 0, NULL); if (lockowner_slab == NULL) - goto out_nomem; + goto out_free_openowner_slab; file_slab = kmem_cache_create("nfsd4_files", sizeof(struct nfs4_file), 0, 0, NULL); if (file_slab == NULL) - goto out_nomem; + goto out_free_lockowner_slab; stateid_slab = kmem_cache_create("nfsd4_stateids", sizeof(struct nfs4_ol_stateid), 0, 0, NULL); if (stateid_slab == NULL) - goto out_nomem; + goto out_free_file_slab; deleg_slab = kmem_cache_create("nfsd4_delegations", sizeof(struct nfs4_delegation), 0, 0, NULL); if (deleg_slab == NULL) - goto out_nomem; + goto out_free_stateid_slab; return 0; -out_nomem: - nfsd4_free_slabs(); + +out_free_stateid_slab: + kmem_cache_destroy(stateid_slab); +out_free_file_slab: + kmem_cache_destroy(file_slab); +out_free_lockowner_slab: + kmem_cache_destroy(lockowner_slab); +out_free_openowner_slab: + kmem_cache_destroy(openowner_slab); +out: dprintk("nfsd4: out of memory while initializing nfsv4\n"); return -ENOMEM; } -void nfs4_free_openowner(struct nfs4_openowner *oo) -{ - kfree(oo->oo_owner.so_owner.data); - kmem_cache_free(openowner_slab, oo); -} - -void nfs4_free_lockowner(struct nfs4_lockowner *lo) -{ - kfree(lo->lo_owner.so_owner.data); - kmem_cache_free(lockowner_slab, lo); -} - static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; @@ -2685,15 +2712,15 @@ find_file(struct inode *ino) unsigned int hashval = file_hashval(ino); struct nfs4_file *fp; - spin_lock(&recall_lock); + spin_lock(&state_lock); hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) { if (fp->fi_inode == ino) { get_nfs4_file(fp); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); return fp; } } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); return NULL; } @@ -2730,6 +2757,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) struct nfs4_client *clp = dp->dl_stid.sc_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + lockdep_assert_held(&state_lock); /* We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the kernel @@ -2766,11 +2794,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&recall_lock); + spin_lock(&state_lock); fp->fi_had_conflict = true; list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) nfsd_break_one_deleg(dp); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); } static @@ -3047,11 +3075,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp) status = vfs_setlease(fl->fl_file, fl->fl_type, &fl); if (status) goto out_free; - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); fp->fi_lease = fl; fp->fi_deleg_file = get_file(fl->fl_file); atomic_set(&fp->fi_delegees, 1); - list_add(&dp->dl_perfile, &fp->fi_delegations); + spin_lock(&state_lock); + hash_delegation_locked(dp, fp); + spin_unlock(&state_lock); return 0; out_free: locks_free_lock(fl); @@ -3060,33 +3089,21 @@ out_free: static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp) { - int status; - if (fp->fi_had_conflict) return -EAGAIN; get_nfs4_file(fp); dp->dl_file = fp; - if (!fp->fi_lease) { - status = nfs4_setlease(dp); - if (status) - goto out_free; - return 0; - } - spin_lock(&recall_lock); + if (!fp->fi_lease) + return nfs4_setlease(dp); + spin_lock(&state_lock); + atomic_inc(&fp->fi_delegees); if (fp->fi_had_conflict) { - spin_unlock(&recall_lock); - status = -EAGAIN; - goto out_free; + spin_unlock(&state_lock); + return -EAGAIN; } - atomic_inc(&fp->fi_delegees); - list_add(&dp->dl_perfile, &fp->fi_delegations); - spin_unlock(&recall_lock); - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); + hash_delegation_locked(dp, fp); + spin_unlock(&state_lock); return 0; -out_free: - put_nfs4_file(fp); - dp->dl_file = fp; - return status; } static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) @@ -3173,8 +3190,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh, open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; return; out_free: - remove_stid(&dp->dl_stid); - nfs4_put_delegation(dp); + destroy_delegation(dp); out_no_deleg: open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && @@ -3391,8 +3407,7 @@ nfs4_laundromat(struct nfsd_net *nn) struct nfs4_delegation *dp; struct list_head *pos, *next, reaplist; time_t cutoff = get_seconds() - nn->nfsd4_lease; - time_t t, clientid_val = nn->nfsd4_lease; - time_t u, test_val = nn->nfsd4_lease; + time_t t, new_timeo = nn->nfsd4_lease; nfs4_lock_state(); @@ -3404,8 +3419,7 @@ nfs4_laundromat(struct nfsd_net *nn) clp = list_entry(pos, struct nfs4_client, cl_lru); if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) { t = clp->cl_time - cutoff; - if (clientid_val > t) - clientid_val = t; + new_timeo = min(new_timeo, t); break; } if (mark_client_expired_locked(clp)) { @@ -3422,39 +3436,35 @@ nfs4_laundromat(struct nfsd_net *nn) clp->cl_clientid.cl_id); expire_client(clp); } - spin_lock(&recall_lock); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn) continue; if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) { - u = dp->dl_time - cutoff; - if (test_val > u) - test_val = u; + t = dp->dl_time - cutoff; + new_timeo = min(new_timeo, t); break; } list_move(&dp->dl_recall_lru, &reaplist); } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); list_for_each_safe(pos, next, &reaplist) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); revoke_delegation(dp); } - test_val = nn->nfsd4_lease; list_for_each_safe(pos, next, &nn->close_lru) { oo = container_of(pos, struct nfs4_openowner, oo_close_lru); if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) { - u = oo->oo_time - cutoff; - if (test_val > u) - test_val = u; + t = oo->oo_time - cutoff; + new_timeo = min(new_timeo, t); break; } release_openowner(oo); } - if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT) - clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT; + new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); nfs4_unlock_state(); - return clientid_val; + return new_timeo; } static struct workqueue_struct *laundry_wq; @@ -3654,6 +3664,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, struct svc_fh *current_fh = &cstate->current_fh; struct inode *ino = current_fh->fh_dentry->d_inode; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct file *file = NULL; __be32 status; if (filpp) @@ -3665,10 +3676,12 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) return check_special_stateids(net, current_fh, stateid, flags); + nfs4_lock_state(); + status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, cstate->minorversion, nn); if (status) - return status; + goto out; status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate)); if (status) goto out; @@ -3679,8 +3692,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, if (status) goto out; if (filpp) { - *filpp = dp->dl_file->fi_deleg_file; - if (!*filpp) { + file = dp->dl_file->fi_deleg_file; + if (!file) { WARN_ON_ONCE(1); status = nfserr_serverfault; goto out; @@ -3701,16 +3714,20 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, goto out; if (filpp) { if (flags & RD_STATE) - *filpp = find_readable_file(stp->st_file); + file = find_readable_file(stp->st_file); else - *filpp = find_writeable_file(stp->st_file); + file = find_writeable_file(stp->st_file); } break; default: - return nfserr_bad_stateid; + status = nfserr_bad_stateid; + goto out; } status = nfs_ok; + if (file) + *filpp = get_file(file); out: + nfs4_unlock_state(); return status; } @@ -3726,7 +3743,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp) * correspondance, and we have to delete the lockowner when we * delete the lock stateid: */ - unhash_lockowner(lo); + release_lockowner(lo); return nfs_ok; } @@ -4896,6 +4913,7 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max, struct nfs4_delegation *dp, *next; u64 count = 0; + lockdep_assert_held(&state_lock); list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) { if (victims) list_move(&dp->dl_recall_lru, victims); @@ -4911,9 +4929,9 @@ u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max) LIST_HEAD(victims); u64 count; - spin_lock(&recall_lock); + spin_lock(&state_lock); count = nfsd_find_all_delegations(clp, max, &victims); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); list_for_each_entry_safe(dp, next, &victims, dl_recall_lru) revoke_delegation(dp); @@ -4927,11 +4945,11 @@ u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max) LIST_HEAD(victims); u64 count; - spin_lock(&recall_lock); + spin_lock(&state_lock); count = nfsd_find_all_delegations(clp, max, &victims); list_for_each_entry_safe(dp, next, &victims, dl_recall_lru) nfsd_break_one_deleg(dp); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); return count; } @@ -4940,9 +4958,9 @@ u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max) { u64 count = 0; - spin_lock(&recall_lock); + spin_lock(&state_lock); count = nfsd_find_all_delegations(clp, max, NULL); - spin_unlock(&recall_lock); + spin_unlock(&state_lock); nfsd_print_count(clp, count, "delegations"); return count; @@ -4983,13 +5001,6 @@ struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_ #endif /* CONFIG_NFSD_FAULT_INJECTION */ -/* initialization to perform at module load time: */ - -void -nfs4_state_init(void) -{ -} - /* * Since the lifetime of a delegation isn't limited to that of an open, a * client may quite reasonably hang on to a delegation as long as it has @@ -5160,12 +5171,12 @@ nfs4_state_shutdown_net(struct net *net) nfs4_lock_state(); INIT_LIST_HEAD(&reaplist); - spin_lock(&recall_lock); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); list_move(&dp->dl_recall_lru, &reaplist); } - spin_unlock(&recall_lock); + spin_unlock(&state_lock); list_for_each_safe(pos, next, &reaplist) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); destroy_delegation(dp); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 18881f3..2d305a1 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -98,11 +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 READMEM(x,nbytes) do { \ x = (char *)p; \ p += XDR_QUADLEN(nbytes); \ @@ -248,17 +243,17 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval) 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) - READ32(bmval[2]); + bmval[2] = be32_to_cpup(p++); DECODE_TAIL; } @@ -270,6 +265,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, { int expected_len, len = 0; u32 dummy32; + u64 sec; char *buf; DECODE_HEAD; @@ -278,12 +274,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, return status; 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) { @@ -291,7 +287,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct nfs4_ace *ace; READ_BUF(4); len += 4; - READ32(nace); + nace = be32_to_cpup(p++); if (nace > NFS4_ACL_MAX) return nfserr_fbig; @@ -305,10 +301,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, (*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); @@ -330,14 +326,14 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, 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); @@ -348,7 +344,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, 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); @@ -359,15 +355,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, 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; - READ64(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); @@ -382,15 +379,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, 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; - READ64(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); @@ -408,13 +406,13 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { READ_BUF(4); len += 4; - READ32(dummy32); /* lfs: we don't use it */ + dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */ READ_BUF(4); len += 4; - READ32(dummy32); /* pi: we don't use it either */ + dummy32 = be32_to_cpup(p++); /* pi: we don't use it either */ READ_BUF(4); len += 4; - READ32(dummy32); + dummy32 = be32_to_cpup(p++); READ_BUF(dummy32); if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN) return nfserr_badlabel; @@ -445,7 +443,7 @@ nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid) DECODE_HEAD; READ_BUF(sizeof(stateid_t)); - READ32(sid->si_generation); + sid->si_generation = be32_to_cpup(p++); COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); DECODE_TAIL; @@ -457,7 +455,7 @@ 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; } @@ -472,7 +470,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ /* callback_sec_params4 */ READ_BUF(4); - READ32(nr_secflavs); + nr_secflavs = be32_to_cpup(p++); if (nr_secflavs) cbs->flavor = (u32)(-1); else @@ -480,7 +478,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ cbs->flavor = 0; for (i = 0; i < nr_secflavs; ++i) { READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); switch (dummy) { case RPC_AUTH_NULL: /* Nothing to read */ @@ -490,21 +488,21 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ case RPC_AUTH_UNIX: READ_BUF(8); /* stamp */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* machine name */ - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); SAVEMEM(machine_name, dummy); /* uid, gid */ READ_BUF(8); - READ32(uid); - READ32(gid); + uid = be32_to_cpup(p++); + gid = be32_to_cpup(p++); /* more gids */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); if (cbs->flavor == (u32)(-1)) { kuid_t kuid = make_kuid(&init_user_ns, uid); @@ -524,14 +522,14 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ "not supported!\n"); READ_BUF(8); /* gcbp_service */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* gcbp_handle_from_server */ - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); /* gcbp_handle_from_client */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); break; default: @@ -547,7 +545,7 @@ static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, stru DECODE_HEAD; READ_BUF(4); - READ32(bc->bc_cb_program); + bc->bc_cb_program = be32_to_cpup(p++); nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); DECODE_TAIL; @@ -559,7 +557,7 @@ static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, READ_BUF(NFS4_MAX_SESSIONID_LEN + 8); COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN); - READ32(bcts->dir); + 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; @@ -571,7 +569,7 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) DECODE_HEAD; READ_BUF(4); - READ32(close->cl_seqid); + close->cl_seqid = be32_to_cpup(p++); return nfsd4_decode_stateid(argp, &close->cl_stateid); DECODE_TAIL; @@ -584,8 +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; } @@ -596,19 +594,19 @@ 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); 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: @@ -618,7 +616,7 @@ 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))) @@ -650,7 +648,7 @@ 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))) @@ -668,24 +666,24 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) * 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(4); - READ32(lock->lk_new_open_seqid); + 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)); - READ32(lock->lk_new_lock_seqid); + 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 { @@ -693,7 +691,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) if (status) return status; READ_BUF(4); - READ32(lock->lk_old_lock_seqid); + lock->lk_old_lock_seqid = be32_to_cpup(p++); } DECODE_TAIL; @@ -705,13 +703,13 @@ 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); @@ -724,16 +722,16 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) DECODE_HEAD; READ_BUF(8); - READ32(locku->lu_type); + 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); + locku->lu_seqid = be32_to_cpup(p++); status = nfsd4_decode_stateid(argp, &locku->lu_stateid); if (status) return status; READ_BUF(16); - READ64(locku->lu_offset); - READ64(locku->lu_length); + p = xdr_decode_hyper(p, &locku->lu_offset); + p = xdr_decode_hyper(p, &locku->lu_length); DECODE_TAIL; } @@ -744,7 +742,7 @@ 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))) @@ -759,7 +757,7 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh u32 w; READ_BUF(4); - READ32(w); + w = be32_to_cpup(p++); *share_access = w & NFS4_SHARE_ACCESS_MASK; *deleg_want = w & NFS4_SHARE_WANT_MASK; if (deleg_when) @@ -811,7 +809,7 @@ static __be32 nfsd4_decode_share_deny(struct nfsd4_compoundargs *argp, u32 *x) __be32 *p; READ_BUF(4); - READ32(*x); + *x = be32_to_cpup(p++); /* Note: unlinke access bits, deny bits may be zero. */ if (*x & ~NFS4_SHARE_DENY_BOTH) return nfserr_bad_xdr; @@ -825,7 +823,7 @@ static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_ne __be32 *p; READ_BUF(4); - READ32(o->len); + o->len = be32_to_cpup(p++); if (o->len == 0 || o->len > NFS4_OPAQUE_LIMIT) return nfserr_bad_xdr; @@ -850,7 +848,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) open->op_xdr_error = 0; /* seqid, share_access, share_deny, clientid, ownerlen */ READ_BUF(4); - READ32(open->op_seqid); + 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); @@ -865,13 +863,13 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) if (status) goto xdr_error; READ_BUF(4); - READ32(open->op_create); + 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: @@ -904,12 +902,12 @@ 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))) @@ -917,14 +915,14 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) 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: status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid); if (status) return status; 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))) @@ -962,7 +960,7 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con if (status) return status; READ_BUF(4); - READ32(open_conf->oc_seqid); + open_conf->oc_seqid = be32_to_cpup(p++); DECODE_TAIL; } @@ -976,7 +974,7 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d if (status) return status; READ_BUF(4); - READ32(open_down->od_seqid); + 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) @@ -993,7 +991,7 @@ 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); @@ -1019,8 +1017,8 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) if (status) return status; READ_BUF(12); - READ64(read->rd_offset); - READ32(read->rd_length); + p = xdr_decode_hyper(p, &read->rd_offset); + read->rd_length = be32_to_cpup(p++); DECODE_TAIL; } @@ -1031,10 +1029,10 @@ 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; @@ -1047,7 +1045,7 @@ 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))) @@ -1062,10 +1060,10 @@ 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))) @@ -1097,7 +1095,7 @@ 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); @@ -1113,7 +1111,7 @@ nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, DECODE_HEAD; READ_BUF(4); - READ32(sin->sin_style); + sin->sin_style = be32_to_cpup(p++); DECODE_TAIL; } @@ -1144,16 +1142,16 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient if (status) return nfserr_bad_xdr; READ_BUF(8); - READ32(setclientid->se_callback_prog); - READ32(setclientid->se_callback_netid_len); + 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; } @@ -1186,7 +1184,7 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify * 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); @@ -1204,11 +1202,11 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) if (status) return status; READ_BUF(16); - READ64(write->wr_offset); - READ32(write->wr_stable_how); + 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); @@ -1254,7 +1252,7 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel 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); @@ -1278,63 +1276,63 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, return nfserr_bad_xdr; READ_BUF(4); - READ32(exid->flags); + exid->flags = be32_to_cpup(p++); /* Ignore state_protect4_a */ READ_BUF(4); - READ32(exid->spa_how); + 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); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; /* spo_must_allow */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; break; case SP4_SSV: /* ssp_ops */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); p += dummy; /* ssp_hash_algs<> */ READ_BUF(4); - READ32(tmp); + tmp = be32_to_cpup(p++); while (tmp--) { READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); } /* ssp_encr_algs<> */ READ_BUF(4); - READ32(tmp); + tmp = be32_to_cpup(p++); while (tmp--) { READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); } /* ssp_window and ssp_num_gss_handles */ READ_BUF(8); - READ32(dummy); - READ32(dummy); + dummy = be32_to_cpup(p++); + dummy = be32_to_cpup(p++); break; default: goto xdr_error; @@ -1342,7 +1340,7 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, /* Ignore Implementation ID */ READ_BUF(4); /* nfs_impl_id4 array length */ - READ32(dummy); + dummy = be32_to_cpup(p++); if (dummy > 1) goto xdr_error; @@ -1350,13 +1348,13 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, if (dummy == 1) { /* nii_domain */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); /* nii_name */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); p += XDR_QUADLEN(dummy); @@ -1376,21 +1374,21 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, READ_BUF(16); COPYMEM(&sess->clientid, 8); - READ32(sess->seqid); - READ32(sess->flags); + sess->seqid = be32_to_cpup(p++); + sess->flags = be32_to_cpup(p++); /* Fore channel attrs */ READ_BUF(28); - READ32(dummy); /* headerpadsz is always 0 */ - READ32(sess->fore_channel.maxreq_sz); - READ32(sess->fore_channel.maxresp_sz); - READ32(sess->fore_channel.maxresp_cached); - READ32(sess->fore_channel.maxops); - READ32(sess->fore_channel.maxreqs); - READ32(sess->fore_channel.nr_rdma_attrs); + 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); - READ32(sess->fore_channel.rdma_attrs); + 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; @@ -1398,23 +1396,23 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, /* Back channel attrs */ READ_BUF(28); - READ32(dummy); /* headerpadsz is always 0 */ - READ32(sess->back_channel.maxreq_sz); - READ32(sess->back_channel.maxresp_sz); - READ32(sess->back_channel.maxresp_cached); - READ32(sess->back_channel.maxops); - READ32(sess->back_channel.maxreqs); - READ32(sess->back_channel.nr_rdma_attrs); + 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); - READ32(sess->back_channel.rdma_attrs); + 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); - READ32(sess->callback_prog); + sess->callback_prog = be32_to_cpup(p++); nfsd4_decode_cb_sec(argp, &sess->cb_sec); DECODE_TAIL; } @@ -1437,7 +1435,7 @@ nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, DECODE_HEAD; READ_BUF(sizeof(stateid_t)); - READ32(free_stateid->fr_stateid.si_generation); + free_stateid->fr_stateid.si_generation = be32_to_cpup(p++); COPYMEM(&free_stateid->fr_stateid.si_opaque, sizeof(stateid_opaque_t)); DECODE_TAIL; @@ -1451,10 +1449,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, READ_BUF(NFS4_MAX_SESSIONID_LEN + 16); COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); - READ32(seq->seqid); - READ32(seq->slotid); - READ32(seq->maxslots); - READ32(seq->cachethis); + 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; } @@ -1511,7 +1509,7 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str DECODE_HEAD; READ_BUF(4); - READ32(rc->rca_one_fs); + rc->rca_one_fs = be32_to_cpup(p++); DECODE_TAIL; } @@ -1605,47 +1603,25 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op) return true; } -/* - * Return a rough estimate of the maximum possible reply size. Note the - * estimate includes rpc headers so is meant to be passed to - * svc_reserve, not svc_reserve_auth. - * - * Also note the current compound encoding permits only one operation to - * use pages beyond the first one, so the maximum possible length is the - * maximum over these values, not the sum. - */ -static int nfsd4_max_reply(u32 opnum) -{ - switch (opnum) { - case OP_READLINK: - case OP_READDIR: - /* - * Both of these ops take a single page for data and put - * the head and tail in another page: - */ - return 2 * PAGE_SIZE; - case OP_READ: - return INT_MAX; - default: - return PAGE_SIZE; - } -} - static __be32 nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { DECODE_HEAD; struct nfsd4_op *op; bool cachethis = false; - int max_reply = PAGE_SIZE; + int auth_slack= argp->rqstp->rq_auth_slack; + int max_reply = auth_slack + 8; /* opcnt, status */ + int readcount = 0; + int readbytes = 0; int i; 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; @@ -1669,7 +1645,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->replay = NULL; READ_BUF(4); - READ32(op->opnum); + op->opnum = be32_to_cpup(p++); if (nfsd4_opnum_in_range(argp, op)) op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); @@ -1677,97 +1653,82 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } - - if (op->status) { - argp->opcnt = i+1; - 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); - max_reply = max(max_reply, nfsd4_max_reply(op->opnum)); + 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; - if (max_reply != INT_MAX) - svc_reserve(argp->rqstp, max_reply); + svc_reserve(argp->rqstp, max_reply + readbytes); argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; - DECODE_TAIL; -} - -#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 { if (nbytes > 0) { \ - *(p + XDR_QUADLEN(nbytes) -1) = 0; \ - memcpy(p, ptr, nbytes); \ - p += XDR_QUADLEN(nbytes); \ -}} while (0) - -static void write32(__be32 **p, u32 n) -{ - *(*p)++ = htonl(n); -} + if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) + argp->rqstp->rq_splice_ok = false; -static void write64(__be32 **p, u64 n) -{ - write32(p, (n >> 32)); - write32(p, (u32)n); + DECODE_TAIL; } -static void write_change(__be32 **p, struct kstat *stat, struct inode *inode) +static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode) { if (IS_I_VERSION(inode)) { - write64(p, inode->i_version); + p = xdr_encode_hyper(p, inode->i_version); } else { - write32(p, stat->ctime.tv_sec); - write32(p, stat->ctime.tv_nsec); + *p++ = cpu_to_be32(stat->ctime.tv_sec); + *p++ = cpu_to_be32(stat->ctime.tv_nsec); } + return p; } -static void write_cinfo(__be32 **p, struct nfsd4_change_info *c) +static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c) { - write32(p, c->atomic); + *p++ = cpu_to_be32(c->atomic); if (c->change_supported) { - write64(p, c->before_change); - write64(p, c->after_change); + p = xdr_encode_hyper(p, c->before_change); + p = xdr_encode_hyper(p, c->after_change); } else { - write32(p, c->before_ctime_sec); - write32(p, c->before_ctime_nsec); - write32(p, c->after_ctime_sec); - write32(p, c->after_ctime_nsec); + *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; } -#define RESERVE_SPACE(nbytes) do { \ - p = resp->p; \ - BUG_ON(p + XDR_QUADLEN(nbytes) > resp->end); \ -} while (0) -#define ADJUST_ARGS() resp->p = p - /* Encode as an array of strings the string given with components * separated @sep, escaped with esc_enter and esc_exit. */ -static __be32 nfsd4_encode_components_esc(char sep, char *components, - __be32 **pp, int *buflen, - char esc_enter, char esc_exit) +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, *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) { bool found_esc = false; @@ -1789,59 +1750,57 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components, 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(char sep, char *components, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep, + char *components) { - return nfsd4_encode_components_esc(sep, components, pp, buflen, 0, 0); + 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_esc(':', 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; } /* * Encode a path in RFC3530 'pathname4' format */ -static __be32 nfsd4_encode_path(const struct path *root, - const struct path *path, __be32 **pp, int *buflen) +static __be32 nfsd4_encode_path(struct xdr_stream *xdr, + const struct path *root, + const struct path *path) { struct path cur = *path; - __be32 *p = *pp; + __be32 *p; struct dentry **components = NULL; unsigned int ncomponents = 0; __be32 err = nfserr_jukebox; @@ -1872,11 +1831,11 @@ static __be32 nfsd4_encode_path(const struct path *root, components[ncomponents++] = cur.dentry; cur.dentry = dget_parent(cur.dentry); } - - *buflen -= 4; - if (*buflen < 0) + err = nfserr_resource; + p = xdr_reserve_space(xdr, 4); + if (!p) goto out_free; - WRITE32(ncomponents); + *p++ = cpu_to_be32(ncomponents); while (ncomponents) { struct dentry *dentry = components[ncomponents - 1]; @@ -1884,20 +1843,18 @@ static __be32 nfsd4_encode_path(const struct path *root, spin_lock(&dentry->d_lock); len = dentry->d_name.len; - *buflen -= 4 + (XDR_QUADLEN(len) << 2); - if (*buflen < 0) { + p = xdr_reserve_space(xdr, len + 4); + if (!p) { spin_unlock(&dentry->d_lock); goto out_free; } - WRITE32(len); - WRITEMEM(dentry->d_name.name, len); + p = xdr_encode_opaque(p, dentry->d_name.name, len); dprintk("/%s", dentry->d_name.name); spin_unlock(&dentry->d_lock); dput(dentry); ncomponents--; } - *pp = p; err = 0; out_free: dprintk(")\n"); @@ -1908,8 +1865,8 @@ out_free: return err; } -static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp, - const struct path *path, __be32 **pp, int *buflen) +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; @@ -1917,7 +1874,7 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp, exp_ps = rqst_find_fsidzero_export(rqstp); if (IS_ERR(exp_ps)) return nfserrno(PTR_ERR(exp_ps)); - res = nfsd4_encode_path(&exp_ps->ex_path, path, pp, buflen); + res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path); exp_put(exp_ps); return res; } @@ -1925,28 +1882,26 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp, /* * 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; - status = nfsd4_encode_fsloc_fsroot(rqstp, &exp->ex_path, &p, buflen); + status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path); 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; } @@ -1965,15 +1920,15 @@ static u32 nfs4_file_type(umode_t mode) } static inline __be32 -nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace, - __be32 **p, int *buflen) +nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, + struct nfs4_ace *ace) { if (ace->whotype != NFS4_ACL_WHO_NAMED) - return nfs4_acl_write_who(ace->whotype, p, buflen); + return nfs4_acl_write_who(xdr, ace->whotype); else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) - return nfsd4_encode_group(rqstp, ace->who_gid, p, buflen); + return nfsd4_encode_group(xdr, rqstp, ace->who_gid); else - return nfsd4_encode_user(rqstp, ace->who_uid, p, buflen); + return nfsd4_encode_user(xdr, rqstp, ace->who_uid); } #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ @@ -1982,31 +1937,28 @@ nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace, #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 -nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen) +nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, + void *context, int len) { - __be32 *p = *pp; + __be32 *p; - if (*buflen < ((XDR_QUADLEN(len) << 2) + 4 + 4 + 4)) + 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. */ - if ((*buflen -= 8) < 0) - return nfserr_resource; - - WRITE32(0); /* lfs */ - WRITE32(0); /* pi */ + *p++ = cpu_to_be32(0); /* lfs */ + *p++ = cpu_to_be32(0); /* pi */ p = xdr_encode_opaque(p, context, len); - *buflen -= (XDR_QUADLEN(len) << 2) + 4; - - *pp = p; return 0; } #else static inline __be32 -nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen) +nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, + void *context, int len) { return 0; } #endif @@ -2045,12 +1997,11 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. - * - * countp is the buffer size in _words_ */ -__be32 -nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, __be32 **buffer, int count, 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]; @@ -2059,12 +2010,13 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, struct kstat stat; struct svc_fh *tempfh = NULL; struct kstatfs statfs; - int buflen = count << 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; @@ -2095,8 +2047,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, 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(&path, &statfs); @@ -2145,25 +2097,33 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ if (bmval2) { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; - WRITE32(3); - WRITE32(bmval0); - WRITE32(bmval1); - WRITE32(bmval2); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bmval0); + *p++ = cpu_to_be32(bmval1); + *p++ = cpu_to_be32(bmval2); } else if (bmval1) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(2); - WRITE32(bmval0); - WRITE32(bmval1); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bmval0); + *p++ = cpu_to_be32(bmval1); } else { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - WRITE32(1); - WRITE32(bmval0); + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(bmval0); } - attrlenp = p++; /* to be backfilled later */ + + 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_suppattrs0(minorversion); @@ -2175,296 +2135,343 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, if (!contextsupport) word2 &= ~FATTR4_WORD2_SECURITY_LABEL; if (!word2) { - if ((buflen -= 12) < 0) + p = xdr_reserve_space(xdr, 12); + if (!p) goto out_resource; - WRITE32(2); - WRITE32(word0); - WRITE32(word1); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(word0); + *p++ = cpu_to_be32(word1); } else { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; - WRITE32(3); - WRITE32(word0); - WRITE32(word1); - WRITE32(word2); + *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_file_type(stat.mode); if (dummy == NF4BAD) { status = nfserr_serverfault; goto out; } - WRITE32(dummy); + *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) { - if ((buflen -= 8) < 0) + p = xdr_reserve_space(xdr, 8); + if (!p) goto out_resource; - write_change(&p, &stat, dentry->d_inode); + 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(nn->nfsd4_lease); + *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) + p = xdr_reserve_space(xdr, 4*3); + if (!p) goto out_resource; - WRITE32(ace->type); - WRITE32(ace->flag); - WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL); - status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen); + *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(0); + *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); + 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(exp->ex_path.mnt->mnt_sb->s_maxbytes); + 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); + 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); + 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; - WRITE64((s64)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; - WRITE64((s64)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; - WRITE64((s64)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 @@ -2473,25 +2480,26 @@ out_acl: if (ignore_crossmnt == 0 && dentry == exp->ex_path.mnt->mnt_root) get_parent_attributes(exp, &stat); - WRITE64(stat.ino); + p = xdr_encode_hyper(p, stat.ino); } if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { - status = nfsd4_encode_security_label(rqstp, context, - contextlen, &p, &buflen); + status = nfsd4_encode_security_label(xdr, rqstp, context, + contextlen); if (status) goto out; } if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - if ((buflen -= 16) < 0) + p = xdr_reserve_space(xdr, 16); + if (!p) goto out_resource; - WRITE32(3); - WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0); - WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1); - WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD2); + *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); } - *attrlenp = htonl((char *)p - (char *)attrlenp - 4); - *buffer = p; + attrlen = htonl(xdr->buf->len - attrlen_offset - 4); + write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); status = nfs_ok; out: @@ -2504,6 +2512,8 @@ out: fh_put(tempfh); kfree(tempfh); } + if (status) + xdr_truncate_encode(xdr, starting_len); return status; out_nfserr: status = nfserrno(err); @@ -2513,6 +2523,37 @@ out_resource: 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)) @@ -2523,8 +2564,8 @@ static inline int attributes_need_mount(u32 *bmval) } 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; @@ -2576,7 +2617,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, } out_encode: - nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, + nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval, cd->rd_rqstp, ignore_crossmnt); out_put: dput(dentry); @@ -2585,9 +2626,12 @@ out_put: } static __be32 * -nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr) +nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) { - if (buflen < 6) + __be32 *p; + + p = xdr_reserve_space(xdr, 6); + if (!p) return NULL; *p++ = htonl(2); *p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */ @@ -2604,10 +2648,13 @@ 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; - __be32 *cookiep; + 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)) { @@ -2615,19 +2662,24 @@ 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 */ - cookiep = p; + 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: break; @@ -2646,59 +2698,74 @@ 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; - cd->offset = cookiep; + 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 -nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid) +static __be32 +nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) { __be32 *p; - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(sid->si_generation); - WRITEMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); + 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) { + 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 __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8); - WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(bcts->dir); + 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: */ - WRITE32(0); - ADJUST_ARGS(); + *p++ = cpu_to_be32(0); } return nfserr; } @@ -2706,8 +2773,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, static __be32 nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &close->cl_stateid); + nfserr = nfsd4_encode_stateid(xdr, &close->cl_stateid); return nfserr; } @@ -2716,12 +2785,15 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c static __be32 nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(NFS4_VERIFIER_SIZE); - WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE); - 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; } @@ -2729,15 +2801,17 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ static __be32 nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(32); - write_cinfo(&p, &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; } @@ -2746,14 +2820,13 @@ 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); return nfserr; } @@ -2761,16 +2834,17 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 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; __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; } @@ -2779,52 +2853,69 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh * 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) +static __be32 +nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld) { struct xdr_netobj *conf = &ld->ld_owner; __be32 *p; - RESERVE_SPACE(32 + XDR_LEN(conf->len)); - WRITE64(ld->ld_start); - WRITE64(ld->ld_length); - WRITE32(ld->ld_type); +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) { + 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) { - WRITEMEM(&ld->ld_clientid, 8); - WRITE32(conf->len); - WRITEMEM(conf->data, conf->len); - kfree(conf->data); + p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8); + p = xdr_encode_opaque(p, conf->data, conf->len); } 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 __be32 nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &lock->lk_resp_stateid); + nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid); else if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(resp, &lock->lk_denied); - + nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied); + kfree(lock->lk_denied.ld_owner.data); return nfserr; } 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 __be32 nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &locku->lu_stateid); + nfserr = nfsd4_encode_stateid(xdr, &locku->lu_stateid); return nfserr; } @@ -2833,12 +2924,14 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l static __be32 nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(20); - write_cinfo(&p, &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; } @@ -2847,72 +2940,86 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li static __be32 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (nfserr) goto out; - nfsd4_encode_stateid(resp, &open->op_stateid); - RESERVE_SPACE(40); - write_cinfo(&p, &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: - nfsd4_encode_stateid(resp, &open->op_delegate_stateid); - RESERVE_SPACE(20); - 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: - nfsd4_encode_stateid(resp, &open->op_delegate_stateid); - RESERVE_SPACE(32); - 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: - RESERVE_SPACE(8); - WRITE32(open->op_why_no_deleg); - WRITE32(0); /* deleg signaling not supported yet */ + 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: - RESERVE_SPACE(4); - WRITE32(open->op_why_no_deleg); + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(open->op_why_no_deleg); } - ADJUST_ARGS(); break; default: BUG(); @@ -2925,8 +3032,10 @@ out: static __be32 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &oc->oc_resp_stateid); + nfserr = nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); return nfserr; } @@ -2934,127 +3043,233 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct static __be32 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) { + struct xdr_stream *xdr = &resp->xdr; + if (!nfserr) - nfsd4_encode_stateid(resp, &od->od_stateid); + nfserr = nfsd4_encode_stateid(xdr, &od->od_stateid); 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; - struct page *page; - unsigned long maxcount; - long len; - __be32 *p; + 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) { - page = *(resp->rqstp->rq_next_page); - if (!page) { /* ran out of pages */ - maxcount -= len; - break; - } - resp->rqstp->rq_vec[v].iov_base = page_address(page); - resp->rqstp->rq_vec[v].iov_len = - len < PAGE_SIZE ? len : PAGE_SIZE; - resp->rqstp->rq_next_page++; + + 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_file(read->rd_rqstp, read->rd_fhp, read->rd_filp, - read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen, - &maxcount); - + 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; + 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->rqstp->rq_next_page) + } + 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); + + 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; - page = page_address(*(resp->rqstp->rq_next_page++)); + 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 + maxcount); + if (maxcount & 3) + write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, + &zero, 4 - (maxcount&3)); return 0; } @@ -3062,47 +3277,52 @@ 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; + __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; - if (!*resp->rqstp->rq_next_page) - return nfserr_resource; - RESERVE_SPACE(NFS4_VERIFIER_SIZE); - 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_next_page++)); + 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, @@ -3110,42 +3330,49 @@ 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; + 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_next_page-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 __be32 nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(20); - write_cinfo(&p, &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; } @@ -3153,19 +3380,21 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ static __be32 nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(40); - write_cinfo(&p, &rename->rn_sinfo); - write_cinfo(&p, &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 __be32 -nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, +nfsd4_do_encode_secinfo(struct xdr_stream *xdr, __be32 nfserr, struct svc_export *exp) { u32 i, nflavs, supported; @@ -3176,6 +3405,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, if (nfserr) goto out; + nfserr = nfserr_resource; if (exp->ex_nflavors) { flavs = exp->ex_flavors; nflavs = exp->ex_nflavors; @@ -3197,9 +3427,10 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, } supported = 0; - RESERVE_SPACE(4); + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; flavorsp = p++; /* to be backfilled later */ - ADJUST_ARGS(); for (i = 0; i < nflavs; i++) { rpc_authflavor_t pf = flavs[i].pseudoflavor; @@ -3207,18 +3438,20 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, if (rpcauth_get_gssinfo(pf, &info) == 0) { supported++; - RESERVE_SPACE(4 + 4 + XDR_LEN(info.oid.len) + 4 + 4); - WRITE32(RPC_AUTH_GSS); - WRITE32(info.oid.len); - WRITEMEM(info.oid.data, info.oid.len); - WRITE32(info.qop); - WRITE32(info.service); - ADJUST_ARGS(); + 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++; - RESERVE_SPACE(4); - WRITE32(pf); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + *p++ = cpu_to_be32(pf); } else { if (report) pr_warn("NFS: SECINFO: security flavor %u " @@ -3229,7 +3462,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, if (nflavs != supported) report = false; *flavorsp = htonl(supported); - + nfserr = 0; out: if (exp) exp_put(exp); @@ -3240,14 +3473,18 @@ static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo *secinfo) { - return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->si_exp); + 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) { - return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->sin_exp); + struct xdr_stream *xdr = &resp->xdr; + + return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->sin_exp); } /* @@ -3257,41 +3494,47 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; - RESERVE_SPACE(16); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; if (nfserr) { - WRITE32(3); - WRITE32(0); - 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(3); - WRITE32(setattr->sa_bmval[0]); - WRITE32(setattr->sa_bmval[1]); - WRITE32(setattr->sa_bmval[2]); + *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 __be32 nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; if (!nfserr) { - RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE); - WRITEMEM(&scd->se_clientid, 8); - WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE); - 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; } @@ -3299,14 +3542,17 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n static __be32 nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) { + 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, NFS4_VERIFIER_SIZE); - 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; } @@ -3323,6 +3569,7 @@ static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_exchange_id *exid) { + struct xdr_stream *xdr = &resp->xdr; __be32 *p; char *major_id; char *server_scope; @@ -3338,60 +3585,61 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, server_scope = utsname()->nodename; server_scope_sz = strlen(server_scope); - RESERVE_SPACE( + p = xdr_reserve_space(xdr, 8 /* eir_clientid */ + 4 /* eir_sequenceid */ + 4 /* eir_flags */ + 4 /* spr_how */); + if (!p) + return nfserr_resource; - WRITEMEM(&exid->clientid, 8); - WRITE32(exid->seqid); - WRITE32(exid->flags); + p = xdr_encode_opaque_fixed(p, &exid->clientid, 8); + *p++ = cpu_to_be32(exid->seqid); + *p++ = cpu_to_be32(exid->flags); - WRITE32(exid->spa_how); - ADJUST_ARGS(); + *p++ = cpu_to_be32(exid->spa_how); switch (exid->spa_how) { case SP4_NONE: break; case SP4_MACH_CRED: /* spo_must_enforce, spo_must_allow */ - RESERVE_SPACE(16); + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; /* spo_must_enforce bitmap: */ - WRITE32(2); - WRITE32(nfs4_minimal_spo_must_enforce[0]); - WRITE32(nfs4_minimal_spo_must_enforce[1]); + *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: */ - WRITE32(0); + *p++ = cpu_to_be32(0); - ADJUST_ARGS(); break; default: WARN_ON_ONCE(1); } - RESERVE_SPACE( + 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 */ - WRITE64(minor_id); /* Minor id */ + p = xdr_encode_hyper(p, minor_id); /* Minor id */ /* major id */ - WRITE32(major_id_sz); - WRITEMEM(major_id, major_id_sz); + p = xdr_encode_opaque(p, major_id, major_id_sz); /* Server scope */ - WRITE32(server_scope_sz); - WRITEMEM(server_scope, server_scope_sz); + p = xdr_encode_opaque(p, server_scope, server_scope_sz); /* Implementation id */ - WRITE32(0); /* zero length nfs_impl_id4 array */ - ADJUST_ARGS(); + *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */ return 0; } @@ -3399,47 +3647,54 @@ 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; - RESERVE_SPACE(24); - WRITEMEM(sess->sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(sess->seqid); - WRITE32(sess->flags); - ADJUST_ARGS(); - - RESERVE_SPACE(28); - WRITE32(0); /* headerpadsz */ - WRITE32(sess->fore_channel.maxreq_sz); - WRITE32(sess->fore_channel.maxresp_sz); - WRITE32(sess->fore_channel.maxresp_cached); - WRITE32(sess->fore_channel.maxops); - WRITE32(sess->fore_channel.maxreqs); - WRITE32(sess->fore_channel.nr_rdma_attrs); - ADJUST_ARGS(); + 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) { - RESERVE_SPACE(4); - WRITE32(sess->fore_channel.rdma_attrs); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sess->fore_channel.rdma_attrs); } - RESERVE_SPACE(28); - WRITE32(0); /* headerpadsz */ - WRITE32(sess->back_channel.maxreq_sz); - WRITE32(sess->back_channel.maxresp_sz); - WRITE32(sess->back_channel.maxresp_cached); - WRITE32(sess->back_channel.maxops); - WRITE32(sess->back_channel.maxreqs); - WRITE32(sess->back_channel.nr_rdma_attrs); - ADJUST_ARGS(); + 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) { - RESERVE_SPACE(4); - WRITE32(sess->back_channel.rdma_attrs); - ADJUST_ARGS(); + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(sess->back_channel.rdma_attrs); } return 0; } @@ -3448,22 +3703,25 @@ 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; - RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 20); - WRITEMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(seq->seqid); - WRITE32(seq->slotid); + 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: */ - WRITE32(seq->maxslots - 1); /* sr_highest_slotid */ - WRITE32(seq->maxslots - 1); /* sr_target_highest_slotid */ - WRITE32(seq->status_flags); + *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); - ADJUST_ARGS(); - resp->cstate.datap = p; /* DRC cache data pointer */ + resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */ return 0; } @@ -3471,20 +3729,22 @@ 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; - RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids)); + 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; } - ADJUST_ARGS(); return nfserr; } @@ -3563,81 +3823,99 @@ static nfsd4_enc nfsd4_enc_ops[] = { }; /* - * Calculate the total amount of memory that the compound response has taken - * after encoding the current operation with pad. - * - * pad: if operation is non-idempotent, pad was calculate by op_rsize_bop() - * which was specified at nfsd4_operation, else pad is zero. - * - * Compare this length to the session se_fmaxresp_sz and se_fmaxresp_cached. + * 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. * - * Our se_fmaxresp_cached will always be a multiple of PAGE_SIZE, and so - * will be at least a page and will therefore hold the xdr_buf head. + * 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 pad) +__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize) { - struct xdr_buf *xb = &resp->rqstp->rq_res; - struct nfsd4_session *session = NULL; + struct xdr_buf *buf = &resp->rqstp->rq_res; struct nfsd4_slot *slot = resp->cstate.slot; - u32 length, tlen = 0; + if (buf->len + respsize <= buf->buflen) + return nfs_ok; if (!nfsd4_has_session(&resp->cstate)) - return 0; - - session = resp->cstate.session; - - if (xb->page_len == 0) { - length = (char *)resp->p - (char *)xb->head[0].iov_base + pad; - } else { - if (xb->tail[0].iov_base && xb->tail[0].iov_len > 0) - tlen = (char *)resp->p - (char *)xb->tail[0].iov_base; - - length = xb->head[0].iov_len + xb->page_len + tlen + pad; - } - dprintk("%s length %u, xb->page_len %u tlen %u pad %u\n", __func__, - length, xb->page_len, tlen, pad); - - if (length > session->se_fchannel.maxresp_sz) - return nfserr_rep_too_big; - - if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) && - length > session->se_fchannel.maxresp_cached) + return nfserr_resource; + if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) { + WARN_ON_ONCE(1); return nfserr_rep_too_big_to_cache; - - return 0; + } + 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; - __be32 *statp; + struct svc_rqst *rqstp = resp->rqstp; + int post_err_offset; + nfsd4_enc encoder; __be32 *p; - RESERVE_SPACE(8); - WRITE32(op->opnum); - statp = p++; /* to be backfilled at the end */ - ADJUST_ARGS(); + 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]); - op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u); + 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) - op->status = nfsd4_check_resp_size(resp, 0); + 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 = (char *)resp->p - (char *)(statp+1); - memcpy(so->so_replay.rp_buf, statp+1, so->so_replay.rp_buflen); + so->so_replay.rp_buflen = len; + read_bytes_from_xdr_buf(xdr->buf, post_err_offset, + so->so_replay.rp_buf, len); } status: - /* - * Note: We write the status directly, instead of using WRITE32(), - * since it is already in network byte order. - */ - *statp = op->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); } /* @@ -3649,21 +3927,22 @@ status: * 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) { __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); } int @@ -3720,19 +3999,19 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo * All that remains is to write the tag and operation count... */ struct nfsd4_compound_state *cs = &resp->cstate; - struct kvec *iov; + 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; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index f8f060f..6040da8 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp) hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits)); } -static inline bool -nfsd_cache_entry_expired(struct svc_cacherep *rp) -{ - return rp->c_state != RC_INPROG && - time_after(jiffies, rp->c_timestamp + RC_EXPIRE); -} - /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -242,8 +235,14 @@ prune_cache_entries(void) long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { - if (!nfsd_cache_entry_expired(rp) && - num_drc_entries <= max_drc_entries) + /* + * Don't free entries attached to calls that are still + * in-progress, but do keep scanning the list. + */ + if (rp->c_state == RC_INPROG) + continue; + if (num_drc_entries <= max_drc_entries && + time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(rp); freed++; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f34d9de..5184404 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1179,7 +1179,6 @@ static int __init init_nfsd(void) retval = nfsd4_init_slabs(); if (retval) goto out_unregister_pernet; - nfs4_state_init(); retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ if (retval) goto out_free_slabs; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 479eb68..847daf3 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -15,11 +15,20 @@ #include <linux/nfs2.h> #include <linux/nfs3.h> #include <linux/nfs4.h> +#include <linux/sunrpc/svc.h> #include <linux/sunrpc/msg_prot.h> -#include <linux/nfsd/debug.h> -#include <linux/nfsd/export.h> -#include <linux/nfsd/stats.h> +#include <uapi/linux/nfsd/debug.h> + +#include "stats.h" +#include "export.h" + +#undef ifdebug +#ifdef NFSD_DEBUG +# define ifdebug(flag) if (nfsd_debug & NFSDDBG_##flag) +#else +# define ifdebug(flag) if (0) +#endif /* * nfsd version @@ -106,7 +115,6 @@ static inline int nfsd_v4client(struct svc_rqst *rq) */ #ifdef CONFIG_NFSD_V4 extern unsigned long max_delegations; -void nfs4_state_init(void); int nfsd4_init_slabs(void); void nfsd4_free_slabs(void); int nfs4_state_start(void); @@ -117,7 +125,6 @@ void nfs4_reset_lease(time_t leasetime); int nfs4_reset_recoverydir(char *recdir); char * nfs4_recoverydir(void); #else -static inline void nfs4_state_init(void) { } static inline int nfsd4_init_slabs(void) { return 0; } static inline void nfsd4_free_slabs(void) { } static inline int nfs4_state_start(void) { return 0; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 3c37b16..ec83934 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -88,9 +88,8 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, /* Check if the request originated from a secure port. */ if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) { RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); - dprintk(KERN_WARNING - "nfsd: request from insecure port %s!\n", - svc_print_addr(rqstp, buf, sizeof(buf))); + dprintk("nfsd: request from insecure port %s!\n", + svc_print_addr(rqstp, buf, sizeof(buf))); return nfserr_perm; } @@ -169,8 +168,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) data_left -= len; if (data_left < 0) return error; - exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_auth); - fid = (struct fid *)(fh->fh_auth + len); + exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); + fid = (struct fid *)(fh->fh_fsid + len); } else { __u32 tfh[2]; dev_t xdev; @@ -385,7 +384,7 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp, { if (dentry != exp->ex_path.dentry) { struct fid *fid = (struct fid *) - (fhp->fh_handle.fh_auth + fhp->fh_handle.fh_size/4 - 1); + (fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1); int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4; int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK); @@ -513,7 +512,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, */ struct inode * inode = dentry->d_inode; - __u32 *datap; dev_t ex_dev = exp_sb(exp)->s_dev; dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %pd2, ino=%ld)\n", @@ -557,17 +555,16 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, if (inode) _fh_update_old(dentry, exp, &fhp->fh_handle); } else { - int len; + fhp->fh_handle.fh_size = + key_len(fhp->fh_handle.fh_fsid_type) + 4; fhp->fh_handle.fh_auth_type = 0; - datap = fhp->fh_handle.fh_auth+0; - mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev, + + mk_fsid(fhp->fh_handle.fh_fsid_type, + fhp->fh_handle.fh_fsid, + ex_dev, exp->ex_path.dentry->d_inode->i_ino, exp->ex_fsid, exp->ex_uuid); - len = key_len(fhp->fh_handle.fh_fsid_type); - datap += len/4; - fhp->fh_handle.fh_size = 4 + len; - if (inode) _fh_update(fhp, exp, dentry); if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index ad67964..2e89e70 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -1,9 +1,58 @@ -/* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ +/* + * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> + * + * This file describes the layout of the file handles as passed + * over the wire. + */ +#ifndef _LINUX_NFSD_NFSFH_H +#define _LINUX_NFSD_NFSFH_H + +#include <linux/sunrpc/svc.h> +#include <uapi/linux/nfsd/nfsfh.h> + +static inline __u32 ino_t_to_u32(ino_t ino) +{ + return (__u32) ino; +} + +static inline ino_t u32_to_ino_t(__u32 uino) +{ + return (ino_t) uino; +} -#ifndef _LINUX_NFSD_FH_INT_H -#define _LINUX_NFSD_FH_INT_H +/* + * This is the internal representation of an NFS handle used in knfsd. + * pre_mtime/post_version will be used to support wcc_attr's in NFSv3. + */ +typedef struct svc_fh { + struct knfsd_fh fh_handle; /* FH data */ + struct dentry * fh_dentry; /* validated dentry */ + struct svc_export * fh_export; /* export pointer */ + int fh_maxsize; /* max size for fh_handle */ + + unsigned char fh_locked; /* inode locked by us */ + unsigned char fh_want_write; /* remount protection taken */ + +#ifdef CONFIG_NFSD_V3 + unsigned char fh_post_saved; /* post-op attrs saved */ + unsigned char fh_pre_saved; /* pre-op attrs saved */ + + /* Pre-op attributes saved during fh_lock */ + __u64 fh_pre_size; /* size before operation */ + struct timespec fh_pre_mtime; /* mtime before oper */ + struct timespec fh_pre_ctime; /* ctime before oper */ + /* + * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode) + * to find out if it is valid. + */ + u64 fh_pre_change; + + /* Post-op attributes saved in fh_unlock */ + struct kstat fh_post_attr; /* full attrs after operation */ + u64 fh_post_change; /* nfsv4 change; see above */ +#endif /* CONFIG_NFSD_V3 */ -#include <linux/nfsd/nfsfh.h> +} svc_fh; enum nfsd_fsid { FSID_DEV = 0, @@ -215,4 +264,4 @@ fh_unlock(struct svc_fh *fhp) } } -#endif /* _LINUX_NFSD_FH_INT_H */ +#endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9a4a5f9..1879e43 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -591,12 +591,6 @@ nfsd(void *vrqstp) nfsdstats.th_cnt++; mutex_unlock(&nfsd_mutex); - /* - * We want less throttling in balance_dirty_pages() so that nfs to - * localhost doesn't cause nfsd to lock up due to all the client's - * dirty pages. - */ - current->flags |= PF_LESS_THROTTLE; set_freezable(); /* diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 9c769a4..1ac306b 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -214,7 +214,8 @@ nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) int nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; return xdr_argsize_check(rqstp, p); } @@ -248,7 +249,8 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, { unsigned int len; int v; - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->offset = ntohl(*p++); @@ -281,7 +283,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, unsigned int len, hdr, dlen; int v; - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; p++; /* beginoffset */ @@ -355,7 +358,8 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, int nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); @@ -391,7 +395,8 @@ int nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readdirargs *args) { - if (!(p = decode_fh(p, &args->fh))) + p = decode_fh(p, &args->fh); + if (!p) return 0; args->cookie = ntohl(*p++); args->count = ntohl(*p++); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 424d8f5..374c662 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -37,7 +37,6 @@ #include <linux/idr.h> #include <linux/sunrpc/svc_xprt.h> -#include <linux/nfsd/nfsfh.h> #include "nfsfh.h" typedef struct { @@ -123,7 +122,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) /* Maximum number of operations per session compound */ #define NFSD_MAX_OPS_PER_COMPOUND 16 /* Maximum session per slot cache size */ -#define NFSD_SLOT_CACHE_SIZE 1024 +#define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ #define NFSD_CACHE_SIZE_SLOTS_PER_SESSION 32 #define NFSD_MAX_MEM_PER_SESSION \ @@ -464,8 +463,6 @@ extern void nfs4_release_reclaim(struct nfsd_net *); extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn); extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn); -extern void nfs4_free_openowner(struct nfs4_openowner *); -extern void nfs4_free_lockowner(struct nfs4_lockowner *); extern int set_callback_cred(void); extern void nfsd4_init_callback(struct nfsd4_callback *); extern void nfsd4_probe_callback(struct nfs4_client *clp); diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 6d4521f..cd90878 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -24,7 +24,6 @@ #include <linux/seq_file.h> #include <linux/module.h> #include <linux/sunrpc/stats.h> -#include <linux/nfsd/stats.h> #include <net/net_namespace.h> #include "nfsd.h" diff --git a/include/linux/nfsd/stats.h b/fs/nfsd/stats.h index e75b254..a5c944b 100644 --- a/include/linux/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -1,12 +1,10 @@ /* - * linux/include/linux/nfsd/stats.h - * * Statistics for NFS server. * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ -#ifndef LINUX_NFSD_STATS_H -#define LINUX_NFSD_STATS_H +#ifndef _NFSD_STATS_H +#define _NFSD_STATS_H #include <uapi/linux/nfsd/stats.h> @@ -42,4 +40,4 @@ extern struct svc_stat nfsd_svcstats; void nfsd_stat_init(void); void nfsd_stat_shutdown(void); -#endif /* LINUX_NFSD_STATS_H */ +#endif /* _NFSD_STATS_H */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 16f0673..140c496 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -820,55 +820,54 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe, return __splice_from_pipe(pipe, sd, nfsd_splice_actor); } -static __be32 -nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +__be32 nfsd_finish_read(struct file *file, unsigned long *count, int host_err) { - mm_segment_t oldfs; - __be32 err; - int host_err; - - err = nfserr_perm; - - if (file->f_op->splice_read && rqstp->rq_splice_ok) { - struct splice_desc sd = { - .len = 0, - .total_len = *count, - .pos = offset, - .u.data = rqstp, - }; - - rqstp->rq_next_page = rqstp->rq_respages + 1; - host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); - } else { - oldfs = get_fs(); - set_fs(KERNEL_DS); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); - set_fs(oldfs); - } - if (host_err >= 0) { nfsdstats.io_read += host_err; *count = host_err; - err = 0; fsnotify_access(file); + return 0; } else - err = nfserrno(host_err); - return err; + return nfserrno(host_err); +} + +int nfsd_splice_read(struct svc_rqst *rqstp, + struct file *file, loff_t offset, unsigned long *count) +{ + struct splice_desc sd = { + .len = 0, + .total_len = *count, + .pos = offset, + .u.data = rqstp, + }; + int host_err; + + rqstp->rq_next_page = rqstp->rq_respages + 1; + host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); + return nfsd_finish_read(file, count, host_err); } -static void kill_suid(struct dentry *dentry) +int nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, + unsigned long *count) { - struct iattr ia; - ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; + mm_segment_t oldfs; + int host_err; - mutex_lock(&dentry->d_inode->i_mutex); - /* - * Note we call this on write, so notify_change will not - * encounter any conflicting delegations: - */ - notify_change(dentry, &ia, NULL); - mutex_unlock(&dentry->d_inode->i_mutex); + oldfs = get_fs(); + set_fs(KERNEL_DS); + host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); + set_fs(oldfs); + return nfsd_finish_read(file, count, host_err); +} + +static __be32 +nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file, + loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +{ + if (file->f_op->splice_read && rqstp->rq_splice_ok) + return nfsd_splice_read(rqstp, file, offset, count); + else + return nfsd_readv(file, offset, vec, vlen, count); } /* @@ -922,6 +921,16 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, int stable = *stablep; int use_wgather; loff_t pos = offset; + unsigned int pflags = current->flags; + + if (rqstp->rq_local) + /* + * We want less throttling in balance_dirty_pages() + * and shrink_inactive_list() so that nfs to + * localhost doesn't cause nfsd to lock up due to all + * the client's dirty pages or its congested queue. + */ + current->flags |= PF_LESS_THROTTLE; dentry = file->f_path.dentry; inode = dentry->d_inode; @@ -942,10 +951,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, nfsdstats.io_write += host_err; fsnotify_modify(file); - /* clear setuid/setgid flag after write */ - if (inode->i_mode & (S_ISUID | S_ISGID)) - kill_suid(dentry); - if (stable) { if (use_wgather) host_err = wait_for_concurrent_writes(file); @@ -959,36 +964,33 @@ out_nfserr: err = 0; else err = nfserrno(host_err); + if (rqstp->rq_local) + tsk_restore_flags(current, pflags, PF_LESS_THROTTLE); return err; } -/* - * Read data from a file. count must contain the requested read count - * on entry. On return, *count contains the number of bytes actually read. - * N.B. After this call fhp needs an fh_put - */ -__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file **file, struct raparms **ra) { - struct file *file; struct inode *inode; - struct raparms *ra; __be32 err; - err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file); if (err) return err; - inode = file_inode(file); + inode = file_inode(*file); /* Get readahead parameters */ - ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); + *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); - if (ra && ra->p_set) - file->f_ra = ra->p_ra; - - err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); + if (*ra && (*ra)->p_set) + (*file)->f_ra = (*ra)->p_ra; + return nfs_ok; +} +void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra) +{ /* Write back readahead params */ if (ra) { struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex]; @@ -998,28 +1000,29 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ra->p_count--; spin_unlock(&rab->pb_lock); } - nfsd_close(file); - return err; } -/* As above, but use the provided file descriptor. */ -__be32 -nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, - unsigned long *count) +/* + * Read data from a file. count must contain the requested read count + * on entry. On return, *count contains the number of bytes actually read. + * N.B. After this call fhp needs an fh_put + */ +__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + loff_t offset, struct kvec *vec, int vlen, unsigned long *count) { - __be32 err; + struct file *file; + struct raparms *ra; + __be32 err; + + err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra); + if (err) + return err; + + err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); + + nfsd_put_tmp_read_open(file, ra); - if (file) { - err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, - NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); - if (err) - goto out; - err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); - } else /* Note file may still be NULL in NFSv4 special stateid case: */ - err = nfsd_read(rqstp, fhp, offset, vec, vlen, count); -out: return err; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fbe90bd..91b6ae3 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -70,10 +70,16 @@ __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); void nfsd_close(struct file *); +struct raparms; +__be32 nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *, + struct file **, struct raparms **); +void nfsd_put_tmp_read_open(struct file *, struct raparms *); +int nfsd_splice_read(struct svc_rqst *, + struct file *, loff_t, unsigned long *); +int nfsd_readv(struct file *, loff_t, struct kvec *, int, + unsigned long *); __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, loff_t, struct kvec *, int, unsigned long *); -__be32 nfsd_read_file(struct svc_rqst *, struct svc_fh *, struct file *, - loff_t, struct kvec *, int, unsigned long *); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, loff_t, struct kvec *,int, unsigned long *, int *); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 5ea7df3..18cbb6d 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -58,7 +58,7 @@ struct nfsd4_compound_state { /* For sessions DRC */ struct nfsd4_session *session; struct nfsd4_slot *slot; - __be32 *datap; + int data_offset; size_t iovlen; u32 minorversion; __be32 status; @@ -287,9 +287,8 @@ struct nfsd4_readdir { struct svc_fh * rd_fhp; /* response */ struct readdir_cd common; - __be32 * buffer; - int buflen; - __be32 * offset; + struct xdr_stream *xdr; + int cookie_offset; }; struct nfsd4_release_lockowner { @@ -506,9 +505,7 @@ struct nfsd4_compoundargs { struct nfsd4_compoundres { /* scratch variables for XDR encode */ - __be32 * p; - __be32 * end; - struct xdr_buf * xbuf; + struct xdr_stream xdr; struct svc_rqst * rqstp; u32 taglen; @@ -538,6 +535,9 @@ static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp) return argp->opcnt == resp->opcnt; } +int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op); +void warn_on_nonidempotent_op(struct nfsd4_op *op); + #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) static inline void @@ -563,10 +563,11 @@ int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); -void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); -__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, __be32 **buffer, int countp, - u32 *bmval, struct svc_rqst *, int ignore_crossmnt); +void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); +__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 *, int ignore_crossmnt); extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid *setclid); diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index dcaad79..219d796 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -17,13 +17,13 @@ #include <linux/fs.h> #include <linux/kref.h> #include <linux/utsname.h> -#include <linux/nfsd/nfsfh.h> #include <linux/lockd/bind.h> #include <linux/lockd/xdr.h> #ifdef CONFIG_LOCKD_V4 #include <linux/lockd/xdr4.h> #endif #include <linux/lockd/debug.h> +#include <linux/sunrpc/svc.h> /* * Version string diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 12c2cb9..a1e3064 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -399,8 +399,6 @@ enum lock_type4 { #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) -#define FATTR4_WORD2_CHANGE_SECURITY_LABEL \ - (1UL << 17) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) diff --git a/include/linux/nfsd/debug.h b/include/linux/nfsd/debug.h deleted file mode 100644 index 19ef837..0000000 --- a/include/linux/nfsd/debug.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * linux/include/linux/nfsd/debug.h - * - * Debugging-related stuff for nfsd - * - * Copyright (C) 1995 Olaf Kirch <okir@monad.swb.de> - */ -#ifndef LINUX_NFSD_DEBUG_H -#define LINUX_NFSD_DEBUG_H - -#include <uapi/linux/nfsd/debug.h> - -# undef ifdebug -# ifdef NFSD_DEBUG -# define ifdebug(flag) if (nfsd_debug & NFSDDBG_##flag) -# else -# define ifdebug(flag) if (0) -# endif -#endif /* LINUX_NFSD_DEBUG_H */ diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h deleted file mode 100644 index a93593f1..0000000 --- a/include/linux/nfsd/nfsfh.h +++ /dev/null @@ -1,63 +0,0 @@ -/* - * include/linux/nfsd/nfsfh.h - * - * This file describes the layout of the file handles as passed - * over the wire. - * - * Earlier versions of knfsd used to sign file handles using keyed MD5 - * or SHA. I've removed this code, because it doesn't give you more - * security than blocking external access to port 2049 on your firewall. - * - * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> - */ -#ifndef _LINUX_NFSD_FH_H -#define _LINUX_NFSD_FH_H - -# include <linux/sunrpc/svc.h> -#include <uapi/linux/nfsd/nfsfh.h> - -static inline __u32 ino_t_to_u32(ino_t ino) -{ - return (__u32) ino; -} - -static inline ino_t u32_to_ino_t(__u32 uino) -{ - return (ino_t) uino; -} - -/* - * This is the internal representation of an NFS handle used in knfsd. - * pre_mtime/post_version will be used to support wcc_attr's in NFSv3. - */ -typedef struct svc_fh { - struct knfsd_fh fh_handle; /* FH data */ - struct dentry * fh_dentry; /* validated dentry */ - struct svc_export * fh_export; /* export pointer */ - int fh_maxsize; /* max size for fh_handle */ - - unsigned char fh_locked; /* inode locked by us */ - unsigned char fh_want_write; /* remount protection taken */ - -#ifdef CONFIG_NFSD_V3 - unsigned char fh_post_saved; /* post-op attrs saved */ - unsigned char fh_pre_saved; /* pre-op attrs saved */ - - /* Pre-op attributes saved during fh_lock */ - __u64 fh_pre_size; /* size before operation */ - struct timespec fh_pre_mtime; /* mtime before oper */ - struct timespec fh_pre_ctime; /* ctime before oper */ - /* - * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode) - * to find out if it is valid. - */ - u64 fh_pre_change; - - /* Post-op attributes saved in fh_unlock */ - struct kstat fh_post_attr; /* full attrs after operation */ - u64 fh_post_change; /* nfsv4 change; see above */ -#endif /* CONFIG_NFSD_V3 */ - -} svc_fh; - -#endif /* _LINUX_NFSD_FH_H */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 04e7632..1bc7cd0 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -244,6 +244,7 @@ struct svc_rqst { struct page * rq_pages[RPCSVC_MAXPAGES]; struct page * *rq_respages; /* points into rq_pages */ struct page * *rq_next_page; /* next reply page to use */ + struct page * *rq_page_end; /* one past the last page */ struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ @@ -254,11 +255,15 @@ struct svc_rqst { u32 rq_prot; /* IP protocol */ unsigned short rq_secure : 1; /* secure port */ + unsigned short rq_local : 1; /* local request */ void * rq_argp; /* decoded arguments */ void * rq_resp; /* xdr'd results */ void * rq_auth_data; /* flavor-specific data */ - + int rq_auth_slack; /* extra space xdr code + * should leave in head + * for krb5i, krb5p. + */ int rq_reserved; /* space on socket outq * reserved for this request */ @@ -454,11 +459,7 @@ char * svc_print_addr(struct svc_rqst *, char *, size_t); */ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space) { - int added_space = 0; - - if (rqstp->rq_authop->flavour) - added_space = RPC_MAX_AUTH_SIZE; - svc_reserve(rqstp, space + added_space); + svc_reserve(rqstp, space + rqstp->rq_auth_slack); } #endif /* SUNRPC_SVC_H */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 0b8e3e6..5cf99a0 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -115,14 +115,13 @@ struct svc_rdma_fastreg_mr { struct list_head frmr_list; }; struct svc_rdma_req_map { - struct svc_rdma_fastreg_mr *frmr; unsigned long count; union { struct kvec sge[RPCSVC_MAXPAGES]; struct svc_rdma_chunk_sge ch[RPCSVC_MAXPAGES]; + unsigned long lkey[RPCSVC_MAXPAGES]; }; }; -#define RDMACTXT_F_FAST_UNREG 1 #define RDMACTXT_F_LAST_CTXT 2 #define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index b05963f..7235040 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -24,6 +24,7 @@ struct svc_xprt_ops { void (*xpo_release_rqst)(struct svc_rqst *); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); + int (*xpo_secure_port)(struct svc_rqst *); }; struct svc_xprt_class { @@ -63,6 +64,7 @@ struct svc_xprt { #define XPT_DETACHED 10 /* detached from tempsocks list */ #define XPT_LISTENER 11 /* listening endpoint */ #define XPT_CACHE_AUTH 12 /* cache auth info */ +#define XPT_LOCAL 13 /* connection from loopback interface */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 15f9204..70c6b92 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -215,6 +215,9 @@ typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); +extern void xdr_commit_encode(struct xdr_stream *xdr); +extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); +extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr); diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h index 616e3b3..2039123 100644 --- a/include/uapi/linux/nfsd/nfsfh.h +++ b/include/uapi/linux/nfsd/nfsfh.h @@ -1,13 +1,7 @@ /* - * include/linux/nfsd/nfsfh.h - * * This file describes the layout of the file handles as passed * over the wire. * - * Earlier versions of knfsd used to sign file handles using keyed MD5 - * or SHA. I've removed this code, because it doesn't give you more - * security than blocking external access to port 2049 on your firewall. - * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ @@ -37,7 +31,7 @@ struct nfs_fhbase_old { }; /* - * This is the new flexible, extensible style NFSv2/v3 file handle. + * This is the new flexible, extensible style NFSv2/v3/v4 file handle. * by Neil Brown <neilb@cse.unsw.edu.au> - March 2000 * * The file handle starts with a sequence of four-byte words. @@ -47,14 +41,7 @@ struct nfs_fhbase_old { * * All four-byte values are in host-byte-order. * - * The auth_type field specifies how the filehandle can be authenticated - * This might allow a file to be confirmed to be in a writable part of a - * filetree without checking the path from it up to the root. - * Current values: - * 0 - No authentication. fb_auth is 0 bytes long - * Possible future values: - * 1 - 4 bytes taken from MD5 hash of the remainer of the file handle - * prefixed by a secret and with the important export flags. + * The auth_type field is deprecated and must be set to 0. * * The fsid_type identifies how the filesystem (or export point) is * encoded. @@ -71,14 +58,9 @@ struct nfs_fhbase_old { * 7 - 8 byte inode number and 16 byte uuid * * The fileid_type identified how the file within the filesystem is encoded. - * This is (will be) passed to, and set by, the underlying filesystem if it supports - * filehandle operations. The filesystem must not use the value '0' or '0xff' and may - * only use the values 1 and 2 as defined below: - * Current values: - * 0 - The root, or export point, of the filesystem. fb_fileid is 0 bytes. - * 1 - 32bit inode number, 32 bit generation number. - * 2 - 32bit inode number, 32 bit generation number, 32 bit parent directory inode number. - * + * The values for this field are filesystem specific, exccept that + * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' + * in include/linux/exportfs.h for currently registered values. */ struct nfs_fhbase_new { __u8 fb_version; /* == 1, even => nfs_fhbase_old */ @@ -114,9 +96,9 @@ struct knfsd_fh { #define fh_fsid_type fh_base.fh_new.fb_fsid_type #define fh_auth_type fh_base.fh_new.fb_auth_type #define fh_fileid_type fh_base.fh_new.fb_fileid_type -#define fh_auth fh_base.fh_new.fb_auth #define fh_fsid fh_base.fh_new.fb_auth - +/* Do not use, provided for userspace compatiblity. */ +#define fh_auth fh_base.fh_new.fb_auth #endif /* _UAPI_LINUX_NFSD_FH_H */ diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 0f73f45..4ce5ecce 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1503,6 +1503,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) if (unwrap_integ_data(rqstp, &rqstp->rq_arg, gc->gc_seq, rsci->mechctx)) goto garbage_args; + rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE; break; case RPC_GSS_SVC_PRIVACY: /* placeholders for length and seq. number: */ @@ -1511,6 +1512,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) if (unwrap_priv_data(rqstp, &rqstp->rq_arg, gc->gc_seq, rsci->mechctx)) goto garbage_args; + rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE * 2; break; default: goto auth_err; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index ae333c1..0663621 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -374,7 +374,7 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd) } return; out: - printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name); + printk(KERN_ERR "RPC: failed to unregister %s cache\n", cd->name); } EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail); diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index 14c9f6d..f2b7cb5 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -43,6 +43,19 @@ static inline int rpc_reply_expected(struct rpc_task *task) (task->tk_msg.rpc_proc->p_decode != NULL); } +static inline int sock_is_loopback(struct sock *sk) +{ + struct dst_entry *dst; + int loopback = 0; + rcu_read_lock(); + dst = rcu_dereference(sk->sk_dst_cache); + if (dst && dst->dev && + (dst->dev->features & NETIF_F_LOOPBACK)) + loopback = 1; + rcu_read_unlock(); + return loopback; +} + int svc_send_common(struct socket *sock, struct xdr_buf *xdr, struct page *headpage, unsigned long headoffset, struct page *tailpage, unsigned long tailoffset); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 06c6ff0..b4737fb 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -597,6 +597,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) } rqstp->rq_pages[i] = p; } + rqstp->rq_page_end = &rqstp->rq_pages[i]; rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */ /* Make arg->head point to first page and arg->pages point to rest */ @@ -730,6 +731,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) svc_add_new_temp_xprt(serv, newxpt); + else + module_put(xprt->xpt_class->xcl_owner); } else if (xprt->xpt_ops->xpo_has_wspace(xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", @@ -793,7 +796,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) clear_bit(XPT_OLD, &xprt->xpt_flags); - rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp)); + rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp); rqstp->rq_chandle.defer = svc_defer; if (serv->sv_stats) diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 2af7b0c..79c0f34 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -54,6 +54,8 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) } spin_unlock(&authtab_lock); + rqstp->rq_auth_slack = 0; + rqstp->rq_authop = aops; return aops->accept(rqstp, authp); } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 43bcb46..b507cd3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -400,6 +400,12 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, release_sock(sock->sk); #endif } + +static int svc_sock_secure_port(struct svc_rqst *rqstp) +{ + return svc_port_is_privileged(svc_addr(rqstp)); +} + /* * INET callback when data has been received on the socket. */ @@ -678,6 +684,7 @@ static struct svc_xprt_ops svc_udp_ops = { .xpo_prep_reply_hdr = svc_udp_prep_reply_hdr, .xpo_has_wspace = svc_udp_has_wspace, .xpo_accept = svc_udp_accept, + .xpo_secure_port = svc_sock_secure_port, }; static struct svc_xprt_class svc_udp_class = { @@ -842,8 +849,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) * tell us anything. For now just warn about unpriv connections. */ if (!svc_port_is_privileged(sin)) { - dprintk(KERN_WARNING - "%s: connect from unprivileged port: %s\n", + dprintk("%s: connect from unprivileged port: %s\n", serv->sv_name, __svc_print_addr(sin, buf, sizeof(buf))); } @@ -867,6 +873,10 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) } svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen); + if (sock_is_loopback(newsock->sk)) + set_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags); + else + clear_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags); if (serv->sv_stats) serv->sv_stats->nettcpconn++; @@ -1112,6 +1122,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; + rqstp->rq_local = !!test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags); p = (__be32 *)rqstp->rq_arg.head[0].iov_base; calldir = p[1]; @@ -1234,6 +1245,7 @@ static struct svc_xprt_ops svc_tcp_bc_ops = { .xpo_detach = svc_bc_tcp_sock_detach, .xpo_free = svc_bc_sock_free, .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, + .xpo_secure_port = svc_sock_secure_port, }; static struct svc_xprt_class svc_tcp_bc_class = { @@ -1272,6 +1284,7 @@ static struct svc_xprt_ops svc_tcp_ops = { .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, + .xpo_secure_port = svc_sock_secure_port, }; static struct svc_xprt_class svc_tcp_class = { diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index dd97ba3..23fb4e7 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -462,6 +462,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) struct kvec *iov = buf->head; int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len; + xdr_set_scratch_buffer(xdr, NULL, 0); BUG_ON(scratch_len < 0); xdr->buf = buf; xdr->iov = iov; @@ -482,6 +483,73 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) EXPORT_SYMBOL_GPL(xdr_init_encode); /** + * xdr_commit_encode - Ensure all data is written to buffer + * @xdr: pointer to xdr_stream + * + * We handle encoding across page boundaries by giving the caller a + * temporary location to write to, then later copying the data into + * place; xdr_commit_encode does that copying. + * + * Normally the caller doesn't need to call this directly, as the + * following xdr_reserve_space will do it. But an explicit call may be + * required at the end of encoding, or any other time when the xdr_buf + * data might be read. + */ +void xdr_commit_encode(struct xdr_stream *xdr) +{ + int shift = xdr->scratch.iov_len; + void *page; + + if (shift == 0) + return; + page = page_address(*xdr->page_ptr); + memcpy(xdr->scratch.iov_base, page, shift); + memmove(page, page + shift, (void *)xdr->p - page); + xdr->scratch.iov_len = 0; +} +EXPORT_SYMBOL_GPL(xdr_commit_encode); + +__be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, size_t nbytes) +{ + static __be32 *p; + int space_left; + int frag1bytes, frag2bytes; + + if (nbytes > PAGE_SIZE) + return NULL; /* Bigger buffers require special handling */ + if (xdr->buf->len + nbytes > xdr->buf->buflen) + return NULL; /* Sorry, we're totally out of space */ + frag1bytes = (xdr->end - xdr->p) << 2; + frag2bytes = nbytes - frag1bytes; + if (xdr->iov) + xdr->iov->iov_len += frag1bytes; + else + xdr->buf->page_len += frag1bytes; + xdr->page_ptr++; + xdr->iov = NULL; + /* + * If the last encode didn't end exactly on a page boundary, the + * next one will straddle boundaries. Encode into the next + * page, then copy it back later in xdr_commit_encode. We use + * the "scratch" iov to track any temporarily unused fragment of + * space at the end of the previous buffer: + */ + xdr->scratch.iov_base = xdr->p; + xdr->scratch.iov_len = frag1bytes; + p = page_address(*xdr->page_ptr); + /* + * Note this is where the next encode will start after we've + * shifted this one back: + */ + xdr->p = (void *)p + frag2bytes; + space_left = xdr->buf->buflen - xdr->buf->len; + xdr->end = (void *)p + min_t(int, space_left, PAGE_SIZE); + xdr->buf->page_len += frag2bytes; + xdr->buf->len += nbytes; + return p; +} + +/** * xdr_reserve_space - Reserve buffer space for sending * @xdr: pointer to xdr_stream * @nbytes: number of bytes to reserve @@ -495,20 +563,122 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes) __be32 *p = xdr->p; __be32 *q; + xdr_commit_encode(xdr); /* align nbytes on the next 32-bit boundary */ nbytes += 3; nbytes &= ~3; q = p + (nbytes >> 2); if (unlikely(q > xdr->end || q < p)) - return NULL; + return xdr_get_next_encode_buffer(xdr, nbytes); xdr->p = q; - xdr->iov->iov_len += nbytes; + if (xdr->iov) + xdr->iov->iov_len += nbytes; + else + xdr->buf->page_len += nbytes; xdr->buf->len += nbytes; return p; } EXPORT_SYMBOL_GPL(xdr_reserve_space); /** + * xdr_truncate_encode - truncate an encode buffer + * @xdr: pointer to xdr_stream + * @len: new length of buffer + * + * Truncates the xdr stream, so that xdr->buf->len == len, + * and xdr->p points at offset len from the start of the buffer, and + * head, tail, and page lengths are adjusted to correspond. + * + * If this means moving xdr->p to a different buffer, we assume that + * that the end pointer should be set to the end of the current page, + * except in the case of the head buffer when we assume the head + * buffer's current length represents the end of the available buffer. + * + * This is *not* safe to use on a buffer that already has inlined page + * cache pages (as in a zero-copy server read reply), except for the + * simple case of truncating from one position in the tail to another. + * + */ +void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) +{ + struct xdr_buf *buf = xdr->buf; + struct kvec *head = buf->head; + struct kvec *tail = buf->tail; + int fraglen; + int new, old; + + if (len > buf->len) { + WARN_ON_ONCE(1); + return; + } + xdr_commit_encode(xdr); + + fraglen = min_t(int, buf->len - len, tail->iov_len); + tail->iov_len -= fraglen; + buf->len -= fraglen; + if (tail->iov_len && buf->len == len) { + xdr->p = tail->iov_base + tail->iov_len; + /* xdr->end, xdr->iov should be set already */ + return; + } + WARN_ON_ONCE(fraglen); + fraglen = min_t(int, buf->len - len, buf->page_len); + buf->page_len -= fraglen; + buf->len -= fraglen; + + new = buf->page_base + buf->page_len; + old = new + fraglen; + xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT); + + if (buf->page_len && buf->len == len) { + xdr->p = page_address(*xdr->page_ptr); + xdr->end = (void *)xdr->p + PAGE_SIZE; + xdr->p = (void *)xdr->p + (new % PAGE_SIZE); + /* xdr->iov should already be NULL */ + return; + } + if (fraglen) { + xdr->end = head->iov_base + head->iov_len; + xdr->page_ptr--; + } + /* (otherwise assume xdr->end is already set) */ + head->iov_len = len; + buf->len = len; + xdr->p = head->iov_base + head->iov_len; + xdr->iov = buf->head; +} +EXPORT_SYMBOL(xdr_truncate_encode); + +/** + * xdr_restrict_buflen - decrease available buffer space + * @xdr: pointer to xdr_stream + * @newbuflen: new maximum number of bytes available + * + * Adjust our idea of how much space is available in the buffer. + * If we've already used too much space in the buffer, returns -1. + * If the available space is already smaller than newbuflen, returns 0 + * and does nothing. Otherwise, adjusts xdr->buf->buflen to newbuflen + * and ensures xdr->end is set at most offset newbuflen from the start + * of the buffer. + */ +int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen) +{ + struct xdr_buf *buf = xdr->buf; + int left_in_this_buf = (void *)xdr->end - (void *)xdr->p; + int end_offset = buf->len + left_in_this_buf; + + if (newbuflen < 0 || newbuflen < buf->len) + return -1; + if (newbuflen > buf->buflen) + return 0; + if (newbuflen < end_offset) + xdr->end = (void *)xdr->end + newbuflen - end_offset; + buf->buflen = newbuflen; + return 0; +} +EXPORT_SYMBOL(xdr_restrict_buflen); + +/** * xdr_write_pages - Insert a list of pages into an XDR buffer for sending * @xdr: pointer to xdr_stream * @pages: list of pages diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 8d904e4..8f92a61 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved. * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -69,7 +70,8 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, /* Set up the XDR head */ rqstp->rq_arg.head[0].iov_base = page_address(page); - rqstp->rq_arg.head[0].iov_len = min(byte_count, ctxt->sge[0].length); + rqstp->rq_arg.head[0].iov_len = + min_t(size_t, byte_count, ctxt->sge[0].length); rqstp->rq_arg.len = byte_count; rqstp->rq_arg.buflen = byte_count; @@ -85,7 +87,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, page = ctxt->pages[sge_no]; put_page(rqstp->rq_pages[sge_no]); rqstp->rq_pages[sge_no] = page; - bc -= min(bc, ctxt->sge[sge_no].length); + bc -= min_t(u32, bc, ctxt->sge[sge_no].length); rqstp->rq_arg.buflen += ctxt->sge[sge_no].length; sge_no++; } @@ -113,291 +115,265 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -/* Encode a read-chunk-list as an array of IB SGE - * - * Assumptions: - * - chunk[0]->position points to pages[0] at an offset of 0 - * - pages[] is not physically or virtually contiguous and consists of - * PAGE_SIZE elements. - * - * Output: - * - sge array pointing into pages[] array. - * - chunk_sge array specifying sge index and count for each - * chunk in the read list - * - */ -static int map_read_chunks(struct svcxprt_rdma *xprt, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head, - struct rpcrdma_msg *rmsgp, - struct svc_rdma_req_map *rpl_map, - struct svc_rdma_req_map *chl_map, - int ch_count, - int byte_count) +static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) { - int sge_no; - int sge_bytes; - int page_off; - int page_no; - int ch_bytes; - int ch_no; - struct rpcrdma_read_chunk *ch; + if (rdma_node_get_transport(xprt->sc_cm_id->device->node_type) == + RDMA_TRANSPORT_IWARP) + return 1; + else + return min_t(int, sge_count, xprt->sc_max_sge); +} - sge_no = 0; - page_no = 0; - page_off = 0; - ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; - ch_no = 0; - ch_bytes = ntohl(ch->rc_target.rs_length); - head->arg.head[0] = rqstp->rq_arg.head[0]; - head->arg.tail[0] = rqstp->rq_arg.tail[0]; - head->arg.pages = &head->pages[head->count]; - head->hdr_count = head->count; /* save count of hdr pages */ - head->arg.page_base = 0; - head->arg.page_len = ch_bytes; - head->arg.len = rqstp->rq_arg.len + ch_bytes; - head->arg.buflen = rqstp->rq_arg.buflen + ch_bytes; - head->count++; - chl_map->ch[0].start = 0; - while (byte_count) { - rpl_map->sge[sge_no].iov_base = - page_address(rqstp->rq_arg.pages[page_no]) + page_off; - sge_bytes = min_t(int, PAGE_SIZE-page_off, ch_bytes); - rpl_map->sge[sge_no].iov_len = sge_bytes; - /* - * Don't bump head->count here because the same page - * may be used by multiple SGE. - */ - head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no]; - rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1]; +typedef int (*rdma_reader_fn)(struct svcxprt_rdma *xprt, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, + int *page_no, + u32 *page_offset, + u32 rs_handle, + u32 rs_length, + u64 rs_offset, + int last); + +/* Issue an RDMA_READ using the local lkey to map the data sink */ +static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, + int *page_no, + u32 *page_offset, + u32 rs_handle, + u32 rs_length, + u64 rs_offset, + int last) +{ + struct ib_send_wr read_wr; + int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT; + struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt); + int ret, read, pno; + u32 pg_off = *page_offset; + u32 pg_no = *page_no; + + ctxt->direction = DMA_FROM_DEVICE; + ctxt->read_hdr = head; + pages_needed = + min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed)); + read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + + for (pno = 0; pno < pages_needed; pno++) { + int len = min_t(int, rs_length, PAGE_SIZE - pg_off); + + head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; + head->arg.page_len += len; + head->arg.len += len; + if (!pg_off) + head->count++; + rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1]; rqstp->rq_next_page = rqstp->rq_respages + 1; + ctxt->sge[pno].addr = + ib_dma_map_page(xprt->sc_cm_id->device, + head->arg.pages[pg_no], pg_off, + PAGE_SIZE - pg_off, + DMA_FROM_DEVICE); + ret = ib_dma_mapping_error(xprt->sc_cm_id->device, + ctxt->sge[pno].addr); + if (ret) + goto err; + atomic_inc(&xprt->sc_dma_used); - byte_count -= sge_bytes; - ch_bytes -= sge_bytes; - sge_no++; - /* - * If all bytes for this chunk have been mapped to an - * SGE, move to the next SGE - */ - if (ch_bytes == 0) { - chl_map->ch[ch_no].count = - sge_no - chl_map->ch[ch_no].start; - ch_no++; - ch++; - chl_map->ch[ch_no].start = sge_no; - ch_bytes = ntohl(ch->rc_target.rs_length); - /* If bytes remaining account for next chunk */ - if (byte_count) { - head->arg.page_len += ch_bytes; - head->arg.len += ch_bytes; - head->arg.buflen += ch_bytes; - } + /* The lkey here is either a local dma lkey or a dma_mr lkey */ + ctxt->sge[pno].lkey = xprt->sc_dma_lkey; + ctxt->sge[pno].length = len; + ctxt->count++; + + /* adjust offset and wrap to next page if needed */ + pg_off += len; + if (pg_off == PAGE_SIZE) { + pg_off = 0; + pg_no++; } - /* - * If this SGE consumed all of the page, move to the - * next page - */ - if ((sge_bytes + page_off) == PAGE_SIZE) { - page_no++; - page_off = 0; - /* - * If there are still bytes left to map, bump - * the page count - */ - if (byte_count) - head->count++; - } else - page_off += sge_bytes; + rs_length -= len; } - BUG_ON(byte_count != 0); - return sge_no; + + if (last && rs_length == 0) + set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); + else + clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); + + memset(&read_wr, 0, sizeof(read_wr)); + read_wr.wr_id = (unsigned long)ctxt; + read_wr.opcode = IB_WR_RDMA_READ; + ctxt->wr_op = read_wr.opcode; + read_wr.send_flags = IB_SEND_SIGNALED; + read_wr.wr.rdma.rkey = rs_handle; + read_wr.wr.rdma.remote_addr = rs_offset; + read_wr.sg_list = ctxt->sge; + read_wr.num_sge = pages_needed; + + ret = svc_rdma_send(xprt, &read_wr); + if (ret) { + pr_err("svcrdma: Error %d posting RDMA_READ\n", ret); + set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + goto err; + } + + /* return current location in page array */ + *page_no = pg_no; + *page_offset = pg_off; + ret = read; + atomic_inc(&rdma_stat_read); + return ret; + err: + svc_rdma_unmap_dma(ctxt); + svc_rdma_put_context(ctxt, 0); + return ret; } -/* Map a read-chunk-list to an XDR and fast register the page-list. - * - * Assumptions: - * - chunk[0] position points to pages[0] at an offset of 0 - * - pages[] will be made physically contiguous by creating a one-off memory - * region using the fastreg verb. - * - byte_count is # of bytes in read-chunk-list - * - ch_count is # of chunks in read-chunk-list - * - * Output: - * - sge array pointing into pages[] array. - * - chunk_sge array specifying sge index and count for each - * chunk in the read list - */ -static int fast_reg_read_chunks(struct svcxprt_rdma *xprt, +/* Issue an RDMA_READ using an FRMR to map the data sink */ +static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head, - struct rpcrdma_msg *rmsgp, - struct svc_rdma_req_map *rpl_map, - struct svc_rdma_req_map *chl_map, - int ch_count, - int byte_count) + int *page_no, + u32 *page_offset, + u32 rs_handle, + u32 rs_length, + u64 rs_offset, + int last) { - int page_no; - int ch_no; - u32 offset; - struct rpcrdma_read_chunk *ch; - struct svc_rdma_fastreg_mr *frmr; - int ret = 0; + struct ib_send_wr read_wr; + struct ib_send_wr inv_wr; + struct ib_send_wr fastreg_wr; + u8 key; + int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT; + struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt); + struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt); + int ret, read, pno; + u32 pg_off = *page_offset; + u32 pg_no = *page_no; - frmr = svc_rdma_get_frmr(xprt); if (IS_ERR(frmr)) return -ENOMEM; - head->frmr = frmr; - head->arg.head[0] = rqstp->rq_arg.head[0]; - head->arg.tail[0] = rqstp->rq_arg.tail[0]; - head->arg.pages = &head->pages[head->count]; - head->hdr_count = head->count; /* save count of hdr pages */ - head->arg.page_base = 0; - head->arg.page_len = byte_count; - head->arg.len = rqstp->rq_arg.len + byte_count; - head->arg.buflen = rqstp->rq_arg.buflen + byte_count; + ctxt->direction = DMA_FROM_DEVICE; + ctxt->frmr = frmr; + pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len); + read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); - /* Fast register the page list */ - frmr->kva = page_address(rqstp->rq_arg.pages[0]); + frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]); frmr->direction = DMA_FROM_DEVICE; frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE); - frmr->map_len = byte_count; - frmr->page_list_len = PAGE_ALIGN(byte_count) >> PAGE_SHIFT; - for (page_no = 0; page_no < frmr->page_list_len; page_no++) { - frmr->page_list->page_list[page_no] = + frmr->map_len = pages_needed << PAGE_SHIFT; + frmr->page_list_len = pages_needed; + + for (pno = 0; pno < pages_needed; pno++) { + int len = min_t(int, rs_length, PAGE_SIZE - pg_off); + + head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; + head->arg.page_len += len; + head->arg.len += len; + if (!pg_off) + head->count++; + rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1]; + rqstp->rq_next_page = rqstp->rq_respages + 1; + frmr->page_list->page_list[pno] = ib_dma_map_page(xprt->sc_cm_id->device, - rqstp->rq_arg.pages[page_no], 0, + head->arg.pages[pg_no], 0, PAGE_SIZE, DMA_FROM_DEVICE); - if (ib_dma_mapping_error(xprt->sc_cm_id->device, - frmr->page_list->page_list[page_no])) - goto fatal_err; + ret = ib_dma_mapping_error(xprt->sc_cm_id->device, + frmr->page_list->page_list[pno]); + if (ret) + goto err; atomic_inc(&xprt->sc_dma_used); - head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no]; - } - head->count += page_no; - - /* rq_respages points one past arg pages */ - rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - /* Create the reply and chunk maps */ - offset = 0; - ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; - for (ch_no = 0; ch_no < ch_count; ch_no++) { - int len = ntohl(ch->rc_target.rs_length); - rpl_map->sge[ch_no].iov_base = frmr->kva + offset; - rpl_map->sge[ch_no].iov_len = len; - chl_map->ch[ch_no].count = 1; - chl_map->ch[ch_no].start = ch_no; - offset += len; - ch++; + /* adjust offset and wrap to next page if needed */ + pg_off += len; + if (pg_off == PAGE_SIZE) { + pg_off = 0; + pg_no++; + } + rs_length -= len; } - ret = svc_rdma_fastreg(xprt, frmr); - if (ret) - goto fatal_err; - - return ch_no; - - fatal_err: - printk("svcrdma: error fast registering xdr for xprt %p", xprt); - svc_rdma_put_frmr(xprt, frmr); - return -EIO; -} - -static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, - struct svc_rdma_op_ctxt *ctxt, - struct svc_rdma_fastreg_mr *frmr, - struct kvec *vec, - u64 *sgl_offset, - int count) -{ - int i; - unsigned long off; + if (last && rs_length == 0) + set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); + else + clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - ctxt->count = count; - ctxt->direction = DMA_FROM_DEVICE; - for (i = 0; i < count; i++) { - ctxt->sge[i].length = 0; /* in case map fails */ - if (!frmr) { - BUG_ON(!virt_to_page(vec[i].iov_base)); - off = (unsigned long)vec[i].iov_base & ~PAGE_MASK; - ctxt->sge[i].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - virt_to_page(vec[i].iov_base), - off, - vec[i].iov_len, - DMA_FROM_DEVICE); - if (ib_dma_mapping_error(xprt->sc_cm_id->device, - ctxt->sge[i].addr)) - return -EINVAL; - ctxt->sge[i].lkey = xprt->sc_dma_lkey; - atomic_inc(&xprt->sc_dma_used); - } else { - ctxt->sge[i].addr = (unsigned long)vec[i].iov_base; - ctxt->sge[i].lkey = frmr->mr->lkey; - } - ctxt->sge[i].length = vec[i].iov_len; - *sgl_offset = *sgl_offset + vec[i].iov_len; + /* Bump the key */ + key = (u8)(frmr->mr->lkey & 0x000000FF); + ib_update_fast_reg_key(frmr->mr, ++key); + + ctxt->sge[0].addr = (unsigned long)frmr->kva + *page_offset; + ctxt->sge[0].lkey = frmr->mr->lkey; + ctxt->sge[0].length = read; + ctxt->count = 1; + ctxt->read_hdr = head; + + /* Prepare FASTREG WR */ + memset(&fastreg_wr, 0, sizeof(fastreg_wr)); + fastreg_wr.opcode = IB_WR_FAST_REG_MR; + fastreg_wr.send_flags = IB_SEND_SIGNALED; + fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva; + fastreg_wr.wr.fast_reg.page_list = frmr->page_list; + fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len; + fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; + fastreg_wr.wr.fast_reg.length = frmr->map_len; + fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags; + fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey; + fastreg_wr.next = &read_wr; + + /* Prepare RDMA_READ */ + memset(&read_wr, 0, sizeof(read_wr)); + read_wr.send_flags = IB_SEND_SIGNALED; + read_wr.wr.rdma.rkey = rs_handle; + read_wr.wr.rdma.remote_addr = rs_offset; + read_wr.sg_list = ctxt->sge; + read_wr.num_sge = 1; + if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) { + read_wr.opcode = IB_WR_RDMA_READ_WITH_INV; + read_wr.wr_id = (unsigned long)ctxt; + read_wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey; + } else { + read_wr.opcode = IB_WR_RDMA_READ; + read_wr.next = &inv_wr; + /* Prepare invalidate */ + memset(&inv_wr, 0, sizeof(inv_wr)); + inv_wr.wr_id = (unsigned long)ctxt; + inv_wr.opcode = IB_WR_LOCAL_INV; + inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE; + inv_wr.ex.invalidate_rkey = frmr->mr->lkey; + } + ctxt->wr_op = read_wr.opcode; + + /* Post the chain */ + ret = svc_rdma_send(xprt, &fastreg_wr); + if (ret) { + pr_err("svcrdma: Error %d posting RDMA_READ\n", ret); + set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + goto err; } - return 0; -} -static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) -{ - if ((rdma_node_get_transport(xprt->sc_cm_id->device->node_type) == - RDMA_TRANSPORT_IWARP) && - sge_count > 1) - return 1; - else - return min_t(int, sge_count, xprt->sc_max_sge); + /* return current location in page array */ + *page_no = pg_no; + *page_offset = pg_off; + ret = read; + atomic_inc(&rdma_stat_read); + return ret; + err: + svc_rdma_unmap_dma(ctxt); + svc_rdma_put_context(ctxt, 0); + svc_rdma_put_frmr(xprt, frmr); + return ret; } -/* - * Use RDMA_READ to read data from the advertised client buffer into the - * XDR stream starting at rq_arg.head[0].iov_base. - * Each chunk in the array - * contains the following fields: - * discrim - '1', This isn't used for data placement - * position - The xdr stream offset (the same for every chunk) - * handle - RMR for client memory region - * length - data transfer length - * offset - 64 bit tagged offset in remote memory region - * - * On our side, we need to read into a pagelist. The first page immediately - * follows the RPC header. - * - * This function returns: - * 0 - No error and no read-list found. - * - * 1 - Successful read-list processing. The data is not yet in - * the pagelist and therefore the RPC request must be deferred. The - * I/O completion will enqueue the transport again and - * svc_rdma_recvfrom will complete the request. - * - * <0 - Error processing/posting read-list. - * - * NOTE: The ctxt must not be touched after the last WR has been posted - * because the I/O completion processing may occur on another - * processor and free / modify the context. Ne touche pas! - */ -static int rdma_read_xdr(struct svcxprt_rdma *xprt, - struct rpcrdma_msg *rmsgp, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *hdr_ctxt) +static int rdma_read_chunks(struct svcxprt_rdma *xprt, + struct rpcrdma_msg *rmsgp, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head) { - struct ib_send_wr read_wr; - struct ib_send_wr inv_wr; - int err = 0; - int ch_no; - int ch_count; - int byte_count; - int sge_count; - u64 sgl_offset; + int page_no, ch_count, ret; struct rpcrdma_read_chunk *ch; - struct svc_rdma_op_ctxt *ctxt = NULL; - struct svc_rdma_req_map *rpl_map; - struct svc_rdma_req_map *chl_map; + u32 page_offset, byte_count; + u64 rs_offset; + rdma_reader_fn reader; /* If no read list is present, return 0 */ ch = svc_rdma_get_read_chunk(rmsgp); @@ -408,122 +384,55 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt, if (ch_count > RPCSVC_MAXPAGES) return -EINVAL; - /* Allocate temporary reply and chunk maps */ - rpl_map = svc_rdma_get_req_map(); - chl_map = svc_rdma_get_req_map(); + /* The request is completed when the RDMA_READs complete. The + * head context keeps all the pages that comprise the + * request. + */ + head->arg.head[0] = rqstp->rq_arg.head[0]; + head->arg.tail[0] = rqstp->rq_arg.tail[0]; + head->arg.pages = &head->pages[head->count]; + head->hdr_count = head->count; + head->arg.page_base = 0; + head->arg.page_len = 0; + head->arg.len = rqstp->rq_arg.len; + head->arg.buflen = rqstp->rq_arg.buflen; - if (!xprt->sc_frmr_pg_list_len) - sge_count = map_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp, - rpl_map, chl_map, ch_count, - byte_count); + /* Use FRMR if supported */ + if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG) + reader = rdma_read_chunk_frmr; else - sge_count = fast_reg_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp, - rpl_map, chl_map, ch_count, - byte_count); - if (sge_count < 0) { - err = -EIO; - goto out; - } - - sgl_offset = 0; - ch_no = 0; + reader = rdma_read_chunk_lcl; + page_no = 0; page_offset = 0; for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; - ch->rc_discrim != 0; ch++, ch_no++) { - u64 rs_offset; -next_sge: - ctxt = svc_rdma_get_context(xprt); - ctxt->direction = DMA_FROM_DEVICE; - ctxt->frmr = hdr_ctxt->frmr; - ctxt->read_hdr = NULL; - clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags); + ch->rc_discrim != 0; ch++) { - /* Prepare READ WR */ - memset(&read_wr, 0, sizeof read_wr); - read_wr.wr_id = (unsigned long)ctxt; - read_wr.opcode = IB_WR_RDMA_READ; - ctxt->wr_op = read_wr.opcode; - read_wr.send_flags = IB_SEND_SIGNALED; - read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle); xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset, &rs_offset); - read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset; - read_wr.sg_list = ctxt->sge; - read_wr.num_sge = - rdma_read_max_sge(xprt, chl_map->ch[ch_no].count); - err = rdma_set_ctxt_sge(xprt, ctxt, hdr_ctxt->frmr, - &rpl_map->sge[chl_map->ch[ch_no].start], - &sgl_offset, - read_wr.num_sge); - if (err) { - svc_rdma_unmap_dma(ctxt); - svc_rdma_put_context(ctxt, 0); - goto out; - } - if (((ch+1)->rc_discrim == 0) && - (read_wr.num_sge == chl_map->ch[ch_no].count)) { - /* - * Mark the last RDMA_READ with a bit to - * indicate all RPC data has been fetched from - * the client and the RPC needs to be enqueued. - */ - set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - if (hdr_ctxt->frmr) { - set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags); - /* - * Invalidate the local MR used to map the data - * sink. - */ - if (xprt->sc_dev_caps & - SVCRDMA_DEVCAP_READ_W_INV) { - read_wr.opcode = - IB_WR_RDMA_READ_WITH_INV; - ctxt->wr_op = read_wr.opcode; - read_wr.ex.invalidate_rkey = - ctxt->frmr->mr->lkey; - } else { - /* Prepare INVALIDATE WR */ - memset(&inv_wr, 0, sizeof inv_wr); - inv_wr.opcode = IB_WR_LOCAL_INV; - inv_wr.send_flags = IB_SEND_SIGNALED; - inv_wr.ex.invalidate_rkey = - hdr_ctxt->frmr->mr->lkey; - read_wr.next = &inv_wr; - } - } - ctxt->read_hdr = hdr_ctxt; - } - /* Post the read */ - err = svc_rdma_send(xprt, &read_wr); - if (err) { - printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n", - err); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - svc_rdma_unmap_dma(ctxt); - svc_rdma_put_context(ctxt, 0); - goto out; + byte_count = ntohl(ch->rc_target.rs_length); + + while (byte_count > 0) { + ret = reader(xprt, rqstp, head, + &page_no, &page_offset, + ntohl(ch->rc_target.rs_handle), + byte_count, rs_offset, + ((ch+1)->rc_discrim == 0) /* last */ + ); + if (ret < 0) + goto err; + byte_count -= ret; + rs_offset += ret; + head->arg.buflen += ret; } - atomic_inc(&rdma_stat_read); - - if (read_wr.num_sge < chl_map->ch[ch_no].count) { - chl_map->ch[ch_no].count -= read_wr.num_sge; - chl_map->ch[ch_no].start += read_wr.num_sge; - goto next_sge; - } - sgl_offset = 0; - err = 1; } - - out: - svc_rdma_put_req_map(rpl_map); - svc_rdma_put_req_map(chl_map); - + ret = 1; + err: /* Detach arg pages. svc_recv will replenish them */ - for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++) - rqstp->rq_pages[ch_no] = NULL; + for (page_no = 0; + &rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++) + rqstp->rq_pages[page_no] = NULL; - return err; + return ret; } static int rdma_read_complete(struct svc_rqst *rqstp, @@ -595,13 +504,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) struct svc_rdma_op_ctxt, dto_q); list_del_init(&ctxt->dto_q); - } - if (ctxt) { spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock); return rdma_read_complete(rqstp, ctxt); - } - - if (!list_empty(&rdma_xprt->sc_rq_dto_q)) { + } else if (!list_empty(&rdma_xprt->sc_rq_dto_q)) { ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next, struct svc_rdma_op_ctxt, dto_q); @@ -621,7 +526,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) goto close_out; - BUG_ON(ret); goto out; } dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n", @@ -644,12 +548,11 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) } /* Read read-list data. */ - ret = rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt); + ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt); if (ret > 0) { /* read-list posted, defer until data received from client. */ goto defer; - } - if (ret < 0) { + } else if (ret < 0) { /* Post of read-list failed, free context. */ svc_rdma_put_context(ctxt, 1); return 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 7e024a5..49fd21a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved. * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -49,152 +50,6 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT -/* Encode an XDR as an array of IB SGE - * - * Assumptions: - * - head[0] is physically contiguous. - * - tail[0] is physically contiguous. - * - pages[] is not physically or virtually contiguous and consists of - * PAGE_SIZE elements. - * - * Output: - * SGE[0] reserved for RCPRDMA header - * SGE[1] data from xdr->head[] - * SGE[2..sge_count-2] data from xdr->pages[] - * SGE[sge_count-1] data from xdr->tail. - * - * The max SGE we need is the length of the XDR / pagesize + one for - * head + one for tail + one for RPCRDMA header. Since RPCSVC_MAXPAGES - * reserves a page for both the request and the reply header, and this - * array is only concerned with the reply we are assured that we have - * on extra page for the RPCRMDA header. - */ -static int fast_reg_xdr(struct svcxprt_rdma *xprt, - struct xdr_buf *xdr, - struct svc_rdma_req_map *vec) -{ - int sge_no; - u32 sge_bytes; - u32 page_bytes; - u32 page_off; - int page_no = 0; - u8 *frva; - struct svc_rdma_fastreg_mr *frmr; - - frmr = svc_rdma_get_frmr(xprt); - if (IS_ERR(frmr)) - return -ENOMEM; - vec->frmr = frmr; - - /* Skip the RPCRDMA header */ - sge_no = 1; - - /* Map the head. */ - frva = (void *)((unsigned long)(xdr->head[0].iov_base) & PAGE_MASK); - vec->sge[sge_no].iov_base = xdr->head[0].iov_base; - vec->sge[sge_no].iov_len = xdr->head[0].iov_len; - vec->count = 2; - sge_no++; - - /* Map the XDR head */ - frmr->kva = frva; - frmr->direction = DMA_TO_DEVICE; - frmr->access_flags = 0; - frmr->map_len = PAGE_SIZE; - frmr->page_list_len = 1; - page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK; - frmr->page_list->page_list[page_no] = - ib_dma_map_page(xprt->sc_cm_id->device, - virt_to_page(xdr->head[0].iov_base), - page_off, - PAGE_SIZE - page_off, - DMA_TO_DEVICE); - if (ib_dma_mapping_error(xprt->sc_cm_id->device, - frmr->page_list->page_list[page_no])) - goto fatal_err; - atomic_inc(&xprt->sc_dma_used); - - /* Map the XDR page list */ - page_off = xdr->page_base; - page_bytes = xdr->page_len + page_off; - if (!page_bytes) - goto encode_tail; - - /* Map the pages */ - vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off; - vec->sge[sge_no].iov_len = page_bytes; - sge_no++; - while (page_bytes) { - struct page *page; - - page = xdr->pages[page_no++]; - sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off)); - page_bytes -= sge_bytes; - - frmr->page_list->page_list[page_no] = - ib_dma_map_page(xprt->sc_cm_id->device, - page, page_off, - sge_bytes, DMA_TO_DEVICE); - if (ib_dma_mapping_error(xprt->sc_cm_id->device, - frmr->page_list->page_list[page_no])) - goto fatal_err; - - atomic_inc(&xprt->sc_dma_used); - page_off = 0; /* reset for next time through loop */ - frmr->map_len += PAGE_SIZE; - frmr->page_list_len++; - } - vec->count++; - - encode_tail: - /* Map tail */ - if (0 == xdr->tail[0].iov_len) - goto done; - - vec->count++; - vec->sge[sge_no].iov_len = xdr->tail[0].iov_len; - - if (((unsigned long)xdr->tail[0].iov_base & PAGE_MASK) == - ((unsigned long)xdr->head[0].iov_base & PAGE_MASK)) { - /* - * If head and tail use the same page, we don't need - * to map it again. - */ - vec->sge[sge_no].iov_base = xdr->tail[0].iov_base; - } else { - void *va; - - /* Map another page for the tail */ - page_off = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK; - va = (void *)((unsigned long)xdr->tail[0].iov_base & PAGE_MASK); - vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off; - - frmr->page_list->page_list[page_no] = - ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va), - page_off, - PAGE_SIZE, - DMA_TO_DEVICE); - if (ib_dma_mapping_error(xprt->sc_cm_id->device, - frmr->page_list->page_list[page_no])) - goto fatal_err; - atomic_inc(&xprt->sc_dma_used); - frmr->map_len += PAGE_SIZE; - frmr->page_list_len++; - } - - done: - if (svc_rdma_fastreg(xprt, frmr)) - goto fatal_err; - - return 0; - - fatal_err: - printk("svcrdma: Error fast registering memory for xprt %p\n", xprt); - vec->frmr = NULL; - svc_rdma_put_frmr(xprt, frmr); - return -EIO; -} - static int map_xdr(struct svcxprt_rdma *xprt, struct xdr_buf *xdr, struct svc_rdma_req_map *vec) @@ -208,9 +63,6 @@ static int map_xdr(struct svcxprt_rdma *xprt, BUG_ON(xdr->len != (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)); - if (xprt->sc_frmr_pg_list_len) - return fast_reg_xdr(xprt, xdr, vec); - /* Skip the first sge, this is for the RPCRDMA header */ sge_no = 1; @@ -282,8 +134,6 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt, } /* Assumptions: - * - We are using FRMR - * - or - * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE */ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, @@ -327,23 +177,16 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, sge_bytes = min_t(size_t, bc, vec->sge[xdr_sge_no].iov_len-sge_off); sge[sge_no].length = sge_bytes; - if (!vec->frmr) { - sge[sge_no].addr = - dma_map_xdr(xprt, &rqstp->rq_res, xdr_off, - sge_bytes, DMA_TO_DEVICE); - xdr_off += sge_bytes; - if (ib_dma_mapping_error(xprt->sc_cm_id->device, - sge[sge_no].addr)) - goto err; - atomic_inc(&xprt->sc_dma_used); - sge[sge_no].lkey = xprt->sc_dma_lkey; - } else { - sge[sge_no].addr = (unsigned long) - vec->sge[xdr_sge_no].iov_base + sge_off; - sge[sge_no].lkey = vec->frmr->mr->lkey; - } + sge[sge_no].addr = + dma_map_xdr(xprt, &rqstp->rq_res, xdr_off, + sge_bytes, DMA_TO_DEVICE); + xdr_off += sge_bytes; + if (ib_dma_mapping_error(xprt->sc_cm_id->device, + sge[sge_no].addr)) + goto err; + atomic_inc(&xprt->sc_dma_used); + sge[sge_no].lkey = xprt->sc_dma_lkey; ctxt->count++; - ctxt->frmr = vec->frmr; sge_off = 0; sge_no++; xdr_sge_no++; @@ -369,7 +212,6 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, return 0; err: svc_rdma_unmap_dma(ctxt); - svc_rdma_put_frmr(xprt, vec->frmr); svc_rdma_put_context(ctxt, 0); /* Fatal error, close transport */ return -EIO; @@ -397,10 +239,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, res_ary = (struct rpcrdma_write_array *) &rdma_resp->rm_body.rm_chunks[1]; - if (vec->frmr) - max_write = vec->frmr->map_len; - else - max_write = xprt->sc_max_sge * PAGE_SIZE; + max_write = xprt->sc_max_sge * PAGE_SIZE; /* Write chunks start at the pagelist */ for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0; @@ -472,10 +311,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, res_ary = (struct rpcrdma_write_array *) &rdma_resp->rm_body.rm_chunks[2]; - if (vec->frmr) - max_write = vec->frmr->map_len; - else - max_write = xprt->sc_max_sge * PAGE_SIZE; + max_write = xprt->sc_max_sge * PAGE_SIZE; /* xdr offset starts at RPC message */ nchunks = ntohl(arg_ary->wc_nchunks); @@ -545,7 +381,6 @@ static int send_reply(struct svcxprt_rdma *rdma, int byte_count) { struct ib_send_wr send_wr; - struct ib_send_wr inv_wr; int sge_no; int sge_bytes; int page_no; @@ -559,7 +394,6 @@ static int send_reply(struct svcxprt_rdma *rdma, "svcrdma: could not post a receive buffer, err=%d." "Closing transport %p.\n", ret, rdma); set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); - svc_rdma_put_frmr(rdma, vec->frmr); svc_rdma_put_context(ctxt, 0); return -ENOTCONN; } @@ -567,11 +401,6 @@ static int send_reply(struct svcxprt_rdma *rdma, /* Prepare the context */ ctxt->pages[0] = page; ctxt->count = 1; - ctxt->frmr = vec->frmr; - if (vec->frmr) - set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags); - else - clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags); /* Prepare the SGE for the RPCRDMA Header */ ctxt->sge[0].lkey = rdma->sc_dma_lkey; @@ -590,21 +419,15 @@ static int send_reply(struct svcxprt_rdma *rdma, int xdr_off = 0; sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; - if (!vec->frmr) { - ctxt->sge[sge_no].addr = - dma_map_xdr(rdma, &rqstp->rq_res, xdr_off, - sge_bytes, DMA_TO_DEVICE); - xdr_off += sge_bytes; - if (ib_dma_mapping_error(rdma->sc_cm_id->device, - ctxt->sge[sge_no].addr)) - goto err; - atomic_inc(&rdma->sc_dma_used); - ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey; - } else { - ctxt->sge[sge_no].addr = (unsigned long) - vec->sge[sge_no].iov_base; - ctxt->sge[sge_no].lkey = vec->frmr->mr->lkey; - } + ctxt->sge[sge_no].addr = + dma_map_xdr(rdma, &rqstp->rq_res, xdr_off, + sge_bytes, DMA_TO_DEVICE); + xdr_off += sge_bytes; + if (ib_dma_mapping_error(rdma->sc_cm_id->device, + ctxt->sge[sge_no].addr)) + goto err; + atomic_inc(&rdma->sc_dma_used); + ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey; ctxt->sge[sge_no].length = sge_bytes; } BUG_ON(byte_count != 0); @@ -627,6 +450,7 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[page_no+1].length = 0; } rqstp->rq_next_page = rqstp->rq_respages + 1; + BUG_ON(sge_no > rdma->sc_max_sge); memset(&send_wr, 0, sizeof send_wr); ctxt->wr_op = IB_WR_SEND; @@ -635,15 +459,6 @@ static int send_reply(struct svcxprt_rdma *rdma, send_wr.num_sge = sge_no; send_wr.opcode = IB_WR_SEND; send_wr.send_flags = IB_SEND_SIGNALED; - if (vec->frmr) { - /* Prepare INVALIDATE WR */ - memset(&inv_wr, 0, sizeof inv_wr); - inv_wr.opcode = IB_WR_LOCAL_INV; - inv_wr.send_flags = IB_SEND_SIGNALED; - inv_wr.ex.invalidate_rkey = - vec->frmr->mr->lkey; - send_wr.next = &inv_wr; - } ret = svc_rdma_send(rdma, &send_wr); if (ret) @@ -653,7 +468,6 @@ static int send_reply(struct svcxprt_rdma *rdma, err: svc_rdma_unmap_dma(ctxt); - svc_rdma_put_frmr(rdma, vec->frmr); svc_rdma_put_context(ctxt, 1); return -EIO; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 25688fa..e7323fb 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved. * Copyright (c) 2005-2007 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -65,6 +66,7 @@ static void dto_tasklet_func(unsigned long data); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); +static int svc_rdma_secure_port(struct svc_rqst *); static void rq_cq_reap(struct svcxprt_rdma *xprt); static void sq_cq_reap(struct svcxprt_rdma *xprt); @@ -82,6 +84,7 @@ static struct svc_xprt_ops svc_rdma_ops = { .xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr, .xpo_has_wspace = svc_rdma_has_wspace, .xpo_accept = svc_rdma_accept, + .xpo_secure_port = svc_rdma_secure_port, }; struct svc_xprt_class svc_rdma_class = { @@ -160,7 +163,6 @@ struct svc_rdma_req_map *svc_rdma_get_req_map(void) schedule_timeout_uninterruptible(msecs_to_jiffies(500)); } map->count = 0; - map->frmr = NULL; return map; } @@ -336,22 +338,21 @@ static void process_context(struct svcxprt_rdma *xprt, switch (ctxt->wr_op) { case IB_WR_SEND: - if (test_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags)) - svc_rdma_put_frmr(xprt, ctxt->frmr); + BUG_ON(ctxt->frmr); svc_rdma_put_context(ctxt, 1); break; case IB_WR_RDMA_WRITE: + BUG_ON(ctxt->frmr); svc_rdma_put_context(ctxt, 0); break; case IB_WR_RDMA_READ: case IB_WR_RDMA_READ_WITH_INV: + svc_rdma_put_frmr(xprt, ctxt->frmr); if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr; BUG_ON(!read_hdr); - if (test_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags)) - svc_rdma_put_frmr(xprt, ctxt->frmr); spin_lock_bh(&xprt->sc_rq_dto_lock); set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); list_add_tail(&read_hdr->dto_q, @@ -363,6 +364,7 @@ static void process_context(struct svcxprt_rdma *xprt, break; default: + BUG_ON(1); printk(KERN_ERR "svcrdma: unexpected completion type, " "opcode=%d\n", ctxt->wr_op); @@ -378,29 +380,42 @@ static void process_context(struct svcxprt_rdma *xprt, static void sq_cq_reap(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt = NULL; - struct ib_wc wc; + struct ib_wc wc_a[6]; + struct ib_wc *wc; struct ib_cq *cq = xprt->sc_sq_cq; int ret; + memset(wc_a, 0, sizeof(wc_a)); + if (!test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags)) return; ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP); atomic_inc(&rdma_stat_sq_poll); - while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) { - if (wc.status != IB_WC_SUCCESS) - /* Close the transport */ - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + while ((ret = ib_poll_cq(cq, ARRAY_SIZE(wc_a), wc_a)) > 0) { + int i; - /* Decrement used SQ WR count */ - atomic_dec(&xprt->sc_sq_count); - wake_up(&xprt->sc_send_wait); + for (i = 0; i < ret; i++) { + wc = &wc_a[i]; + if (wc->status != IB_WC_SUCCESS) { + dprintk("svcrdma: sq wc err status %d\n", + wc->status); - ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id; - if (ctxt) - process_context(xprt, ctxt); + /* Close the transport */ + set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + } - svc_xprt_put(&xprt->sc_xprt); + /* Decrement used SQ WR count */ + atomic_dec(&xprt->sc_sq_count); + wake_up(&xprt->sc_send_wait); + + ctxt = (struct svc_rdma_op_ctxt *) + (unsigned long)wc->wr_id; + if (ctxt) + process_context(xprt, ctxt); + + svc_xprt_put(&xprt->sc_xprt); + } } if (ctxt) @@ -993,7 +1008,11 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) need_dma_mr = 0; break; case RDMA_TRANSPORT_IB: - if (!(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) { + if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) { + need_dma_mr = 1; + dma_mr_acc = IB_ACCESS_LOCAL_WRITE; + } else if (!(devattr.device_cap_flags & + IB_DEVICE_LOCAL_DMA_LKEY)) { need_dma_mr = 1; dma_mr_acc = IB_ACCESS_LOCAL_WRITE; } else @@ -1190,14 +1209,7 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt) container_of(xprt, struct svcxprt_rdma, sc_xprt); /* - * If there are fewer SQ WR available than required to send a - * simple response, return false. - */ - if ((rdma->sc_sq_depth - atomic_read(&rdma->sc_sq_count) < 3)) - return 0; - - /* - * ...or there are already waiters on the SQ, + * If there are already waiters on the SQ, * return false. */ if (waitqueue_active(&rdma->sc_send_wait)) @@ -1207,6 +1219,11 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt) return 1; } +static int svc_rdma_secure_port(struct svc_rqst *rqstp) +{ + return 1; +} + /* * Attempt to register the kvec representing the RPC memory with the * device. |
