summaryrefslogtreecommitdiffstats
path: root/net/sunrpc
diff options
context:
space:
mode:
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/auth.c12
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c40
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_crypto.c95
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_mech.c24
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_seal.c2
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_seqnum.c4
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_wrap.c8
-rw-r--r--net/sunrpc/auth_gss/gss_spkm3_mech.c29
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c82
-rw-r--r--net/sunrpc/auth_null.c8
-rw-r--r--net/sunrpc/auth_unix.c10
-rw-r--r--net/sunrpc/clnt.c221
-rw-r--r--net/sunrpc/pmap_clnt.c266
-rw-r--r--net/sunrpc/rpc_pipe.c56
-rw-r--r--net/sunrpc/sched.c107
-rw-r--r--net/sunrpc/socklib.c2
-rw-r--r--net/sunrpc/sunrpc_syms.c5
-rw-r--r--net/sunrpc/svc.c509
-rw-r--r--net/sunrpc/svcauth.c4
-rw-r--r--net/sunrpc/svcauth_unix.c43
-rw-r--r--net/sunrpc/svcsock.c427
-rw-r--r--net/sunrpc/timer.c2
-rw-r--r--net/sunrpc/xdr.c54
-rw-r--r--net/sunrpc/xprt.c90
-rw-r--r--net/sunrpc/xprtsock.c124
25 files changed, 1465 insertions, 759 deletions
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 55163af3dca..993ff1a5d94 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -331,8 +331,8 @@ rpcauth_unbindcred(struct rpc_task *task)
task->tk_msg.rpc_cred = NULL;
}
-u32 *
-rpcauth_marshcred(struct rpc_task *task, u32 *p)
+__be32 *
+rpcauth_marshcred(struct rpc_task *task, __be32 *p)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
@@ -342,8 +342,8 @@ rpcauth_marshcred(struct rpc_task *task, u32 *p)
return cred->cr_ops->crmarshal(task, p);
}
-u32 *
-rpcauth_checkverf(struct rpc_task *task, u32 *p)
+__be32 *
+rpcauth_checkverf(struct rpc_task *task, __be32 *p)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
@@ -355,7 +355,7 @@ rpcauth_checkverf(struct rpc_task *task, u32 *p)
int
rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp,
- u32 *data, void *obj)
+ __be32 *data, void *obj)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
@@ -369,7 +369,7 @@ rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp,
int
rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
- u32 *data, void *obj)
+ __be32 *data, void *obj)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index ef1cf5b476c..a6ed2d22a6e 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -88,7 +88,6 @@ struct gss_auth {
struct list_head upcalls;
struct rpc_clnt *client;
struct dentry *dentry;
- char path[48];
spinlock_t lock;
};
@@ -690,10 +689,8 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
if (err)
goto err_put_mech;
- snprintf(gss_auth->path, sizeof(gss_auth->path), "%s/%s",
- clnt->cl_pathname,
- gss_auth->mech->gm_name);
- gss_auth->dentry = rpc_mkpipe(gss_auth->path, clnt, &gss_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
+ gss_auth->dentry = rpc_mkpipe(clnt->cl_dentry, gss_auth->mech->gm_name,
+ clnt, &gss_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
if (IS_ERR(gss_auth->dentry)) {
err = PTR_ERR(gss_auth->dentry);
goto err_put_mech;
@@ -829,14 +826,14 @@ out:
* Marshal credentials.
* Maybe we should keep a cached credential for performance reasons.
*/
-static u32 *
-gss_marshal(struct rpc_task *task, u32 *p)
+static __be32 *
+gss_marshal(struct rpc_task *task, __be32 *p)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
- u32 *cred_len;
+ __be32 *cred_len;
struct rpc_rqst *req = task->tk_rqstp;
u32 maj_stat = 0;
struct xdr_netobj mic;
@@ -897,12 +894,12 @@ gss_refresh(struct rpc_task *task)
return 0;
}
-static u32 *
-gss_validate(struct rpc_task *task, u32 *p)
+static __be32 *
+gss_validate(struct rpc_task *task, __be32 *p)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
- u32 seq;
+ __be32 seq;
struct kvec iov;
struct xdr_buf verf_buf;
struct xdr_netobj mic;
@@ -943,13 +940,14 @@ out_bad:
static inline int
gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
- kxdrproc_t encode, struct rpc_rqst *rqstp, u32 *p, void *obj)
+ kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj)
{
struct xdr_buf *snd_buf = &rqstp->rq_snd_buf;
struct xdr_buf integ_buf;
- u32 *integ_len = NULL;
+ __be32 *integ_len = NULL;
struct xdr_netobj mic;
- u32 offset, *q;
+ u32 offset;
+ __be32 *q;
struct kvec *iov;
u32 maj_stat = 0;
int status = -EIO;
@@ -1035,13 +1033,13 @@ out:
static inline int
gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
- kxdrproc_t encode, struct rpc_rqst *rqstp, u32 *p, void *obj)
+ kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj)
{
struct xdr_buf *snd_buf = &rqstp->rq_snd_buf;
u32 offset;
u32 maj_stat;
int status;
- u32 *opaque_len;
+ __be32 *opaque_len;
struct page **inpages;
int first;
int pad;
@@ -1098,7 +1096,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
static int
gss_wrap_req(struct rpc_task *task,
- kxdrproc_t encode, void *rqstp, u32 *p, void *obj)
+ kxdrproc_t encode, void *rqstp, __be32 *p, void *obj)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
@@ -1135,7 +1133,7 @@ out:
static inline int
gss_unwrap_resp_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
- struct rpc_rqst *rqstp, u32 **p)
+ struct rpc_rqst *rqstp, __be32 **p)
{
struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf;
struct xdr_buf integ_buf;
@@ -1172,7 +1170,7 @@ gss_unwrap_resp_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
static inline int
gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
- struct rpc_rqst *rqstp, u32 **p)
+ struct rpc_rqst *rqstp, __be32 **p)
{
struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf;
u32 offset;
@@ -1201,13 +1199,13 @@ gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
static int
gss_unwrap_resp(struct rpc_task *task,
- kxdrproc_t decode, void *rqstp, u32 *p, void *obj)
+ kxdrproc_t decode, void *rqstp, __be32 *p, void *obj)
{
struct rpc_cred *cred = task->tk_msg.rpc_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
- u32 *savedp = p;
+ __be32 *savedp = p;
struct kvec *head = ((struct rpc_rqst *)rqstp)->rq_rcv_buf.head;
int savedlen = head->iov_len;
int status = -EIO;
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 76b969e6904..e11a40b25cc 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -34,6 +34,7 @@
* WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
*/
+#include <linux/err.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/slab.h>
@@ -49,7 +50,7 @@
u32
krb5_encrypt(
- struct crypto_tfm *tfm,
+ struct crypto_blkcipher *tfm,
void * iv,
void * in,
void * out,
@@ -58,26 +59,27 @@ krb5_encrypt(
u32 ret = -EINVAL;
struct scatterlist sg[1];
u8 local_iv[16] = {0};
+ struct blkcipher_desc desc = { .tfm = tfm, .info = local_iv };
dprintk("RPC: krb5_encrypt: input data:\n");
print_hexl((u32 *)in, length, 0);
- if (length % crypto_tfm_alg_blocksize(tfm) != 0)
+ if (length % crypto_blkcipher_blocksize(tfm) != 0)
goto out;
- if (crypto_tfm_alg_ivsize(tfm) > 16) {
+ if (crypto_blkcipher_ivsize(tfm) > 16) {
dprintk("RPC: gss_k5encrypt: tfm iv size to large %d\n",
- crypto_tfm_alg_ivsize(tfm));
+ crypto_blkcipher_ivsize(tfm));
goto out;
}
if (iv)
- memcpy(local_iv, iv, crypto_tfm_alg_ivsize(tfm));
+ memcpy(local_iv, iv, crypto_blkcipher_ivsize(tfm));
memcpy(out, in, length);
sg_set_buf(sg, out, length);
- ret = crypto_cipher_encrypt_iv(tfm, sg, sg, length, local_iv);
+ ret = crypto_blkcipher_encrypt_iv(&desc, sg, sg, length);
dprintk("RPC: krb5_encrypt: output data:\n");
print_hexl((u32 *)out, length, 0);
@@ -90,7 +92,7 @@ EXPORT_SYMBOL(krb5_encrypt);
u32
krb5_decrypt(
- struct crypto_tfm *tfm,
+ struct crypto_blkcipher *tfm,
void * iv,
void * in,
void * out,
@@ -99,25 +101,26 @@ krb5_decrypt(
u32 ret = -EINVAL;
struct scatterlist sg[1];
u8 local_iv[16] = {0};
+ struct blkcipher_desc desc = { .tfm = tfm, .info = local_iv };
dprintk("RPC: krb5_decrypt: input data:\n");
print_hexl((u32 *)in, length, 0);
- if (length % crypto_tfm_alg_blocksize(tfm) != 0)
+ if (length % crypto_blkcipher_blocksize(tfm) != 0)
goto out;
- if (crypto_tfm_alg_ivsize(tfm) > 16) {
+ if (crypto_blkcipher_ivsize(tfm) > 16) {
dprintk("RPC: gss_k5decrypt: tfm iv size to large %d\n",
- crypto_tfm_alg_ivsize(tfm));
+ crypto_blkcipher_ivsize(tfm));
goto out;
}
if (iv)
- memcpy(local_iv,iv, crypto_tfm_alg_ivsize(tfm));
+ memcpy(local_iv,iv, crypto_blkcipher_ivsize(tfm));
memcpy(out, in, length);
sg_set_buf(sg, out, length);
- ret = crypto_cipher_decrypt_iv(tfm, sg, sg, length, local_iv);
+ ret = crypto_blkcipher_decrypt_iv(&desc, sg, sg, length);
dprintk("RPC: krb5_decrypt: output_data:\n");
print_hexl((u32 *)out, length, 0);
@@ -197,11 +200,9 @@ out:
static int
checksummer(struct scatterlist *sg, void *data)
{
- struct crypto_tfm *tfm = (struct crypto_tfm *)data;
+ struct hash_desc *desc = data;
- crypto_digest_update(tfm, sg, 1);
-
- return 0;
+ return crypto_hash_update(desc, sg, sg->length);
}
/* checksum the plaintext data and hdrlen bytes of the token header */
@@ -210,8 +211,9 @@ make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body,
int body_offset, struct xdr_netobj *cksum)
{
char *cksumname;
- struct crypto_tfm *tfm = NULL; /* XXX add to ctx? */
+ struct hash_desc desc; /* XXX add to ctx? */
struct scatterlist sg[1];
+ int err;
switch (cksumtype) {
case CKSUMTYPE_RSA_MD5:
@@ -222,25 +224,35 @@ make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body,
" unsupported checksum %d", cksumtype);
return GSS_S_FAILURE;
}
- if (!(tfm = crypto_alloc_tfm(cksumname, CRYPTO_TFM_REQ_MAY_SLEEP)))
+ desc.tfm = crypto_alloc_hash(cksumname, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(desc.tfm))
return GSS_S_FAILURE;
- cksum->len = crypto_tfm_alg_digestsize(tfm);
+ cksum->len = crypto_hash_digestsize(desc.tfm);
+ desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- crypto_digest_init(tfm);
+ err = crypto_hash_init(&desc);
+ if (err)
+ goto out;
sg_set_buf(sg, header, hdrlen);
- crypto_digest_update(tfm, sg, 1);
- process_xdr_buf(body, body_offset, body->len - body_offset,
- checksummer, tfm);
- crypto_digest_final(tfm, cksum->data);
- crypto_free_tfm(tfm);
- return 0;
+ err = crypto_hash_update(&desc, sg, hdrlen);
+ if (err)
+ goto out;
+ err = process_xdr_buf(body, body_offset, body->len - body_offset,
+ checksummer, &desc);
+ if (err)
+ goto out;
+ err = crypto_hash_final(&desc, cksum->data);
+
+out:
+ crypto_free_hash(desc.tfm);
+ return err ? GSS_S_FAILURE : 0;
}
EXPORT_SYMBOL(make_checksum);
struct encryptor_desc {
u8 iv[8]; /* XXX hard-coded blocksize */
- struct crypto_tfm *tfm;
+ struct blkcipher_desc desc;
int pos;
struct xdr_buf *outbuf;
struct page **pages;
@@ -285,8 +297,8 @@ encryptor(struct scatterlist *sg, void *data)
if (thislen == 0)
return 0;
- ret = crypto_cipher_encrypt_iv(desc->tfm, desc->outfrags, desc->infrags,
- thislen, desc->iv);
+ ret = crypto_blkcipher_encrypt_iv(&desc->desc, desc->outfrags,
+ desc->infrags, thislen);
if (ret)
return ret;
if (fraglen) {
@@ -305,16 +317,18 @@ encryptor(struct scatterlist *sg, void *data)
}
int
-gss_encrypt_xdr_buf(struct crypto_tfm *tfm, struct xdr_buf *buf, int offset,
- struct page **pages)
+gss_encrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf,
+ int offset, struct page **pages)
{
int ret;
struct encryptor_desc desc;
- BUG_ON((buf->len - offset) % crypto_tfm_alg_blocksize(tfm) != 0);
+ BUG_ON((buf->len - offset) % crypto_blkcipher_blocksize(tfm) != 0);
memset(desc.iv, 0, sizeof(desc.iv));
- desc.tfm = tfm;
+ desc.desc.tfm = tfm;
+ desc.desc.info = desc.iv;
+ desc.desc.flags = 0;
desc.pos = offset;
desc.outbuf = buf;
desc.pages = pages;
@@ -329,7 +343,7 @@ EXPORT_SYMBOL(gss_encrypt_xdr_buf);
struct decryptor_desc {
u8 iv[8]; /* XXX hard-coded blocksize */
- struct crypto_tfm *tfm;
+ struct blkcipher_desc desc;
struct scatterlist frags[4];
int fragno;
int fraglen;
@@ -355,8 +369,8 @@ decryptor(struct scatterlist *sg, void *data)
if (thislen == 0)
return 0;
- ret = crypto_cipher_decrypt_iv(desc->tfm, desc->frags, desc->frags,
- thislen, desc->iv);
+ ret = crypto_blkcipher_decrypt_iv(&desc->desc, desc->frags,
+ desc->frags, thislen);
if (ret)
return ret;
if (fraglen) {
@@ -373,15 +387,18 @@ decryptor(struct scatterlist *sg, void *data)
}
int
-gss_decrypt_xdr_buf(struct crypto_tfm *tfm, struct xdr_buf *buf, int offset)
+gss_decrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf,
+ int offset)
{
struct decryptor_desc desc;
/* XXXJBF: */
- BUG_ON((buf->len - offset) % crypto_tfm_alg_blocksize(tfm) != 0);
+ BUG_ON((buf->len - offset) % crypto_blkcipher_blocksize(tfm) != 0);
memset(desc.iv, 0, sizeof(desc.iv));
- desc.tfm = tfm;
+ desc.desc.tfm = tfm;
+ desc.desc.info = desc.iv;
+ desc.desc.flags = 0;
desc.fragno = 0;
desc.fraglen = 0;
return process_xdr_buf(buf, offset, buf->len - offset, decryptor, &desc);
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 70e1e53a632..325e72e4fd3 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -34,6 +34,7 @@
*
*/
+#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
@@ -78,10 +79,10 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
}
static inline const void *
-get_key(const void *p, const void *end, struct crypto_tfm **res)
+get_key(const void *p, const void *end, struct crypto_blkcipher **res)
{
struct xdr_netobj key;
- int alg, alg_mode;
+ int alg;
char *alg_name;
p = simple_get_bytes(p, end, &alg, sizeof(alg));
@@ -93,18 +94,19 @@ get_key(const void *p, const void *end, struct crypto_tfm **res)
switch (alg) {
case ENCTYPE_DES_CBC_RAW:
- alg_name = "des";
- alg_mode = CRYPTO_TFM_MODE_CBC;
+ alg_name = "cbc(des)";
break;
default:
printk("gss_kerberos_mech: unsupported algorithm %d\n", alg);
goto out_err_free_key;
}
- if (!(*res = crypto_alloc_tfm(alg_name, alg_mode))) {
+ *res = crypto_alloc_blkcipher(alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(*res)) {
printk("gss_kerberos_mech: unable to initialize crypto algorithm %s\n", alg_name);
+ *res = NULL;
goto out_err_free_key;
}
- if (crypto_cipher_setkey(*res, key.data, key.len)) {
+ if (crypto_blkcipher_setkey(*res, key.data, key.len)) {
printk("gss_kerberos_mech: error setting key for crypto algorithm %s\n", alg_name);
goto out_err_free_tfm;
}
@@ -113,7 +115,7 @@ get_key(const void *p, const void *end, struct crypto_tfm **res)
return p;
out_err_free_tfm:
- crypto_free_tfm(*res);
+ crypto_free_blkcipher(*res);
out_err_free_key:
kfree(key.data);
p = ERR_PTR(-EINVAL);
@@ -172,9 +174,9 @@ gss_import_sec_context_kerberos(const void *p,
return 0;
out_err_free_key2:
- crypto_free_tfm(ctx->seq);
+ crypto_free_blkcipher(ctx->seq);
out_err_free_key1:
- crypto_free_tfm(ctx->enc);
+ crypto_free_blkcipher(ctx->enc);
out_err_free_mech:
kfree(ctx->mech_used.data);
out_err_free_ctx:
@@ -187,8 +189,8 @@ static void
gss_delete_sec_context_kerberos(void *internal_ctx) {
struct krb5_ctx *kctx = internal_ctx;
- crypto_free_tfm(kctx->seq);
- crypto_free_tfm(kctx->enc);
+ crypto_free_blkcipher(kctx->seq);
+ crypto_free_blkcipher(kctx->enc);
kfree(kctx->mech_used.data);
kfree(kctx);
}
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index 2f312164d6d..08601ee4cd7 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -115,7 +115,7 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text,
krb5_hdr = ptr - 2;
msg_start = krb5_hdr + 24;
- *(u16 *)(krb5_hdr + 2) = htons(ctx->signalg);
+ *(__be16 *)(krb5_hdr + 2) = htons(ctx->signalg);
memset(krb5_hdr + 4, 0xff, 4);
if (make_checksum(checksum_type, krb5_hdr, 8, text, 0, &md5cksum))
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index c53ead39118..c604baf3a5f 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -41,7 +41,7 @@
#endif
s32
-krb5_make_seq_num(struct crypto_tfm *key,
+krb5_make_seq_num(struct crypto_blkcipher *key,
int direction,
s32 seqnum,
unsigned char *cksum, unsigned char *buf)
@@ -62,7 +62,7 @@ krb5_make_seq_num(struct crypto_tfm *key,
}
s32
-krb5_get_seq_num(struct crypto_tfm *key,
+krb5_get_seq_num(struct crypto_blkcipher *key,
unsigned char *cksum,
unsigned char *buf,
int *direction, s32 * seqnum)
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 89d1f3e1412..cc45c1605f8 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -149,7 +149,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset,
goto out_err;
}
- blocksize = crypto_tfm_alg_blocksize(kctx->enc);
+ blocksize = crypto_blkcipher_blocksize(kctx->enc);
gss_krb5_add_padding(buf, offset, blocksize);
BUG_ON((buf->len - offset) % blocksize);
plainlen = blocksize + buf->len - offset;
@@ -177,9 +177,9 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset,
msg_start = krb5_hdr + 24;
/* XXXJBF: */ BUG_ON(buf->head[0].iov_base + offset + headlen != msg_start + blocksize);
- *(u16 *)(krb5_hdr + 2) = htons(kctx->signalg);
+ *(__be16 *)(krb5_hdr + 2) = htons(kctx->signalg);
memset(krb5_hdr + 4, 0xff, 4);
- *(u16 *)(krb5_hdr + 4) = htons(kctx->sealalg);
+ *(__be16 *)(krb5_hdr + 4) = htons(kctx->sealalg);
make_confounder(msg_start, blocksize);
@@ -346,7 +346,7 @@ gss_unwrap_kerberos(struct gss_ctx *ctx, int offset, struct xdr_buf *buf)
/* Copy the data back to the right position. XXX: Would probably be
* better to copy and encrypt at the same time. */
- blocksize = crypto_tfm_alg_blocksize(kctx->enc);
+ blocksize = crypto_blkcipher_blocksize(kctx->enc);
data_start = ptr + 22 + blocksize;
orig_start = buf->head[0].iov_base + offset;
data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start;
diff --git a/net/sunrpc/auth_gss/gss_spkm3_mech.c b/net/sunrpc/auth_gss/gss_spkm3_mech.c
index 88dcb52d171..bdedf456bc1 100644
--- a/net/sunrpc/auth_gss/gss_spkm3_mech.c
+++ b/net/sunrpc/auth_gss/gss_spkm3_mech.c
@@ -34,6 +34,7 @@
*
*/
+#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
@@ -83,10 +84,11 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
}
static inline const void *
-get_key(const void *p, const void *end, struct crypto_tfm **res, int *resalg)
+get_key(const void *p, const void *end, struct crypto_blkcipher **res,
+ int *resalg)
{
struct xdr_netobj key = { 0 };
- int alg_mode,setkey = 0;
+ int setkey = 0;
char *alg_name;
p = simple_get_bytes(p, end, resalg, sizeof(*resalg));
@@ -98,14 +100,12 @@ get_key(const void *p, const void *end, struct crypto_tfm **res, int *resalg)
switch (*resalg) {
case NID_des_cbc:
- alg_name = "des";
- alg_mode = CRYPTO_TFM_MODE_CBC;
+ alg_name = "cbc(des)";
setkey = 1;
break;
case NID_cast5_cbc:
/* XXXX here in name only, not used */
- alg_name = "cast5";
- alg_mode = CRYPTO_TFM_MODE_CBC;
+ alg_name = "cbc(cast5)";
setkey = 0; /* XXX will need to set to 1 */
break;
case NID_md5:
@@ -113,19 +113,20 @@ get_key(const void *p, const void *end, struct crypto_tfm **res, int *resalg)
dprintk("RPC: SPKM3 get_key: NID_md5 zero Key length\n");
}
alg_name = "md5";
- alg_mode = 0;
setkey = 0;
break;
default:
dprintk("gss_spkm3_mech: unsupported algorithm %d\n", *resalg);
goto out_err_free_key;
}
- if (!(*res = crypto_alloc_tfm(alg_name, alg_mode))) {
+ *res = crypto_alloc_blkcipher(alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(*res)) {
printk("gss_spkm3_mech: unable to initialize crypto algorthm %s\n", alg_name);
+ *res = NULL;
goto out_err_free_key;
}
if (setkey) {
- if (crypto_cipher_setkey(*res, key.data, key.len)) {
+ if (crypto_blkcipher_setkey(*res, key.data, key.len)) {
printk("gss_spkm3_mech: error setting key for crypto algorthm %s\n", alg_name);
goto out_err_free_tfm;
}
@@ -136,7 +137,7 @@ get_key(const void *p, const void *end, struct crypto_tfm **res, int *resalg)
return p;
out_err_free_tfm:
- crypto_free_tfm(*res);
+ crypto_free_blkcipher(*res);
out_err_free_key:
if(key.len > 0)
kfree(key.data);
@@ -204,9 +205,9 @@ gss_import_sec_context_spkm3(const void *p, size_t len,
return 0;
out_err_free_key2:
- crypto_free_tfm(ctx->derived_integ_key);
+ crypto_free_blkcipher(ctx->derived_integ_key);
out_err_free_key1:
- crypto_free_tfm(ctx->derived_conf_key);
+ crypto_free_blkcipher(ctx->derived_conf_key);
out_err_free_s_key:
kfree(ctx->share_key.data);
out_err_free_mech:
@@ -223,8 +224,8 @@ static void
gss_delete_sec_context_spkm3(void *internal_ctx) {
struct spkm3_ctx *sctx = internal_ctx;
- crypto_free_tfm(sctx->derived_integ_key);
- crypto_free_tfm(sctx->derived_conf_key);
+ crypto_free_blkcipher(sctx->derived_integ_key);
+ crypto_free_blkcipher(sctx->derived_conf_key);
kfree(sctx->share_key.data);
kfree(sctx->mech_used.data);
kfree(sctx);
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 94217ec9e2d..638c0b57620 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -607,7 +607,7 @@ svc_safe_getnetobj(struct kvec *argv, struct xdr_netobj *o)
if (argv->iov_len < 4)
return -1;
- o->len = ntohl(svc_getu32(argv));
+ o->len = svc_getnl(argv);
l = round_up_to_quad(o->len);
if (argv->iov_len < l)
return -1;
@@ -620,17 +620,17 @@ svc_safe_getnetobj(struct kvec *argv, struct xdr_netobj *o)
static inline int
svc_safe_putnetobj(struct kvec *resv, struct xdr_netobj *o)
{
- u32 *p;
+ u8 *p;
if (resv->iov_len + 4 > PAGE_SIZE)
return -1;
- svc_putu32(resv, htonl(o->len));
+ svc_putnl(resv, o->len);
p = resv->iov_base + resv->iov_len;
resv->iov_len += round_up_to_quad(o->len);
if (resv->iov_len > PAGE_SIZE)
return -1;
memcpy(p, o->data, o->len);
- memset((u8 *)p + o->len, 0, round_up_to_quad(o->len) - o->len);
+ memset(p + o->len, 0, round_up_to_quad(o->len) - o->len);
return 0;
}
@@ -640,7 +640,7 @@ svc_safe_putnetobj(struct kvec *resv, struct xdr_netobj *o)
*/
static int
gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci,
- u32 *rpcstart, struct rpc_gss_wire_cred *gc, u32 *authp)
+ __be32 *rpcstart, struct rpc_gss_wire_cred *gc, __be32 *authp)
{
struct gss_ctx *ctx_id = rsci->mechctx;
struct xdr_buf rpchdr;
@@ -657,7 +657,7 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci,
*authp = rpc_autherr_badverf;
if (argv->iov_len < 4)
return SVC_DENIED;
- flavor = ntohl(svc_getu32(argv));
+ flavor = svc_getnl(argv);
if (flavor != RPC_AUTH_GSS)
return SVC_DENIED;
if (svc_safe_getnetobj(argv, &checksum))
@@ -687,9 +687,9 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci,
static int
gss_write_null_verf(struct svc_rqst *rqstp)
{
- u32 *p;
+ __be32 *p;
- svc_putu32(rqstp->rq_res.head, htonl(RPC_AUTH_NULL));
+ svc_putnl(rqstp->rq_res.head, RPC_AUTH_NULL);
p = rqstp->rq_res.head->iov_base + rqstp->rq_res.head->iov_len;
/* don't really need to check if head->iov_len > PAGE_SIZE ... */
*p++ = 0;
@@ -701,14 +701,14 @@ gss_write_null_verf(struct svc_rqst *rqstp)
static int
gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq)
{
- u32 xdr_seq;
+ __be32 xdr_seq;
u32 maj_stat;
struct xdr_buf verf_data;
struct xdr_netobj mic;
- u32 *p;
+ __be32 *p;
struct kvec iov;
- svc_putu32(rqstp->rq_res.head, htonl(RPC_AUTH_GSS));
+ svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS);
xdr_seq = htonl(seq);
iov.iov_base = &xdr_seq;
@@ -782,7 +782,7 @@ EXPORT_SYMBOL(svcauth_gss_register_pseudoflavor);
static inline int
read_u32_from_xdr_buf(struct xdr_buf *buf, int base, u32 *obj)
{
- u32 raw;
+ __be32 raw;
int status;
status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj));
@@ -805,7 +805,7 @@ unwrap_integ_data(struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx)
struct xdr_netobj mic;
struct xdr_buf integ_buf;
- integ_len = ntohl(svc_getu32(&buf->head[0]));
+ integ_len = svc_getnl(&buf->head[0]);
if (integ_len & 3)
goto out;
if (integ_len > buf->len)
@@ -825,7 +825,7 @@ unwrap_integ_data(struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx)
maj_stat = gss_verify_mic(ctx, &integ_buf, &mic);
if (maj_stat != GSS_S_COMPLETE)
goto out;
- if (ntohl(svc_getu32(&buf->head[0])) != seq)
+ if (svc_getnl(&buf->head[0]) != seq)
goto out;
stat = 0;
out:
@@ -857,7 +857,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
rqstp->rq_sendfile_ok = 0;
- priv_len = ntohl(svc_getu32(&buf->head[0]));
+ priv_len = svc_getnl(&buf->head[0]);
if (rqstp->rq_deferred) {
/* Already decrypted last time through! The sequence number
* check at out_seq is unnecessary but harmless: */
@@ -895,7 +895,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
if (maj_stat != GSS_S_COMPLETE)
return -EINVAL;
out_seq:
- if (ntohl(svc_getu32(&buf->head[0])) != seq)
+ if (svc_getnl(&buf->head[0]) != seq)
return -EINVAL;
return 0;
}
@@ -905,7 +905,7 @@ struct gss_svc_data {
struct rpc_gss_wire_cred clcred;
/* pointer to the beginning of the procedure-specific results,
* which may be encrypted/checksummed in svcauth_gss_release: */
- u32 *body_start;
+ __be32 *body_start;
struct rsc *rsci;
};
@@ -946,7 +946,7 @@ gss_write_init_verf(struct svc_rqst *rqstp, struct rsi *rsip)
* response here and return SVC_COMPLETE.
*/
static int
-svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
+svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
{
struct kvec *argv = &rqstp->rq_arg.head[0];
struct kvec *resv = &rqstp->rq_res.head[0];
@@ -956,8 +956,8 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
struct rpc_gss_wire_cred *gc;
struct rsc *rsci = NULL;
struct rsi *rsip, rsikey;
- u32 *rpcstart;
- u32 *reject_stat = resv->iov_base + resv->iov_len;
+ __be32 *rpcstart;
+ __be32 *reject_stat = resv->iov_base + resv->iov_len;
int ret;
dprintk("RPC: svcauth_gss: argv->iov_len = %zd\n",argv->iov_len);
@@ -985,12 +985,12 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
if (argv->iov_len < 5 * 4)
goto auth_err;
- crlen = ntohl(svc_getu32(argv));
- if (ntohl(svc_getu32(argv)) != RPC_GSS_VERSION)
+ crlen = svc_getnl(argv);
+ if (svc_getnl(argv) != RPC_GSS_VERSION)
goto auth_err;
- gc->gc_proc = ntohl(svc_getu32(argv));
- gc->gc_seq = ntohl(svc_getu32(argv));
- gc->gc_svc = ntohl(svc_getu32(argv));
+ gc->gc_proc = svc_getnl(argv);
+ gc->gc_seq = svc_getnl(argv);
+ gc->gc_svc = svc_getnl(argv);
if (svc_safe_getnetobj(argv, &gc->gc_ctx))
goto auth_err;
if (crlen != round_up_to_quad(gc->gc_ctx.len) + 5 * 4)
@@ -1016,9 +1016,9 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
case RPC_GSS_PROC_CONTINUE_INIT:
if (argv->iov_len < 2 * 4)
goto auth_err;
- if (ntohl(svc_getu32(argv)) != RPC_AUTH_NULL)
+ if (svc_getnl(argv) != RPC_AUTH_NULL)
goto auth_err;
- if (ntohl(svc_getu32(argv)) != 0)
+ if (svc_getnl(argv) != 0)
goto auth_err;
break;
case RPC_GSS_PROC_DATA:
@@ -1076,14 +1076,14 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
goto drop;
if (resv->iov_len + 4 > PAGE_SIZE)
goto drop;
- svc_putu32(resv, rpc_success);
+ svc_putnl(resv, RPC_SUCCESS);
if (svc_safe_putnetobj(resv, &rsip->out_handle))
goto drop;
if (resv->iov_len + 3 * 4 > PAGE_SIZE)
goto drop;
- svc_putu32(resv, htonl(rsip->major_status));
- svc_putu32(resv, htonl(rsip->minor_status));
- svc_putu32(resv, htonl(GSS_SEQ_WIN));
+ svc_putnl(resv, rsip->major_status);
+ svc_putnl(resv, rsip->minor_status);
+ svc_putnl(resv, GSS_SEQ_WIN);
if (svc_safe_putnetobj(resv, &rsip->out_token))
goto drop;
rqstp->rq_client = NULL;
@@ -1093,7 +1093,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
set_bit(CACHE_NEGATIVE, &rsci->h.flags);
if (resv->iov_len + 4 > PAGE_SIZE)
goto drop;
- svc_putu32(resv, rpc_success);
+ svc_putnl(resv, RPC_SUCCESS);
goto complete;
case RPC_GSS_PROC_DATA:
*authp = rpcsec_gsserr_ctxproblem;
@@ -1111,8 +1111,8 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
goto auth_err;
/* placeholders for length and seq. number: */
svcdata->body_start = resv->iov_base + resv->iov_len;
- svc_putu32(resv, 0);
- svc_putu32(resv, 0);
+ svc_putnl(resv, 0);
+ svc_putnl(resv, 0);
break;
case RPC_GSS_SVC_PRIVACY:
if (unwrap_priv_data(rqstp, &rqstp->rq_arg,
@@ -1120,8 +1120,8 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
goto auth_err;
/* placeholders for length and seq. number: */
svcdata->body_start = resv->iov_base + resv->iov_len;
- svc_putu32(resv, 0);
- svc_putu32(resv, 0);
+ svc_putnl(resv, 0);
+ svc_putnl(resv, 0);
break;
default:
goto auth_err;
@@ -1156,7 +1156,7 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp)
struct xdr_buf integ_buf;
struct xdr_netobj mic;
struct kvec *resv;
- u32 *p;
+ __be32 *p;
int integ_offset, integ_len;
int stat = -EINVAL;
@@ -1199,7 +1199,7 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp)
mic.data = (u8 *)resv->iov_base + resv->iov_len + 4;
if (gss_get_mic(gsd->rsci->mechctx, &integ_buf, &mic))
goto out_err;
- svc_putu32(resv, htonl(mic.len));
+ svc_putnl(resv, mic.len);
memset(mic.data + mic.len, 0,
round_up_to_quad(mic.len) - mic.len);
resv->iov_len += XDR_QUADLEN(mic.len) << 2;
@@ -1219,8 +1219,8 @@ svcauth_gss_wrap_resp_priv(struct svc_rqst *rqstp)
struct rpc_gss_wire_cred *gc = &gsd->clcred;
struct xdr_buf *resbuf = &rqstp->rq_res;
struct page **inpages = NULL;
- u32 *p;
- int offset, *len;
+ __be32 *p, *len;
+ int offset;
int pad;
p = gsd->body_start;
@@ -1264,7 +1264,7 @@ svcauth_gss_wrap_resp_priv(struct svc_rqst *rqstp)
return -ENOMEM;
*len = htonl(resbuf->len - offset);
pad = 3 - ((resbuf->len - offset - 1)&3);
- p = (u32 *)(resbuf->tail[0].iov_base + resbuf->tail[0].iov_len);
+ p = (__be32 *)(resbuf->tail[0].iov_base + resbuf->tail[0].iov_len);
memset(p, 0, pad);
resbuf->tail[0].iov_len += pad;
resbuf->len += pad;
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 2eccffa96ba..3be257dc32b 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -60,8 +60,8 @@ nul_match(struct auth_cred *acred, struct rpc_cred *cred, int taskflags)
/*
* Marshal credential.
*/
-static u32 *
-nul_marshal(struct rpc_task *task, u32 *p)
+static __be32 *
+nul_marshal(struct rpc_task *task, __be32 *p)
{
*p++ = htonl(RPC_AUTH_NULL);
*p++ = 0;
@@ -81,8 +81,8 @@ nul_refresh(struct rpc_task *task)
return 0;
}
-static u32 *
-nul_validate(struct rpc_task *task, u32 *p)
+static __be32 *
+nul_validate(struct rpc_task *task, __be32 *p)
{
rpc_authflavor_t flavor;
u32 size;
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 74c7406a105..f7f990c9afe 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -137,12 +137,12 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags)
* Marshal credentials.
* Maybe we should keep a cached credential for performance reasons.
*/
-static u32 *
-unx_marshal(struct rpc_task *task, u32 *p)
+static __be32 *
+unx_marshal(struct rpc_task *task, __be32 *p)
{
struct rpc_clnt *clnt = task->tk_client;
struct unx_cred *cred = (struct unx_cred *) task->tk_msg.rpc_cred;
- u32 *base, *hold;
+ __be32 *base, *hold;
int i;
*p++ = htonl(RPC_AUTH_UNIX);
@@ -178,8 +178,8 @@ unx_refresh(struct rpc_task *task)
return 0;
}
-static u32 *
-unx_validate(struct rpc_task *task, u32 *p)
+static __be32 *
+unx_validate(struct rpc_task *task, __be32 *p)
{
rpc_authflavor_t flavor;
u32 size;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 3e19d321067..78696f2dc7d 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -60,8 +60,8 @@ static void call_refreshresult(struct rpc_task *task);
static void call_timeout(struct rpc_task *task);
static void call_connect(struct rpc_task *task);
static void call_connect_status(struct rpc_task *task);
-static u32 * call_header(struct rpc_task *task);
-static u32 * call_verify(struct rpc_task *task);
+static __be32 * call_header(struct rpc_task *task);
+static __be32 * call_verify(struct rpc_task *task);
static int
@@ -97,17 +97,7 @@ rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name)
}
}
-/*
- * Create an RPC client
- * FIXME: This should also take a flags argument (as in task->tk_flags).
- * It's called (among others) from pmap_create_client, which may in
- * turn be called by an async task. In this case, rpciod should not be
- * made to sleep too long.
- */
-struct rpc_clnt *
-rpc_new_client(struct rpc_xprt *xprt, char *servname,
- struct rpc_program *program, u32 vers,
- rpc_authflavor_t flavor)
+static struct rpc_clnt * rpc_new_client(struct rpc_xprt *xprt, char *servname, struct rpc_program *program, u32 vers, rpc_authflavor_t flavor)
{
struct rpc_version *version;
struct rpc_clnt *clnt = NULL;
@@ -147,16 +137,12 @@ rpc_new_client(struct rpc_xprt *xprt, char *servname,
clnt->cl_procinfo = version->procs;
clnt->cl_maxproc = version->nrprocs;
clnt->cl_protname = program->name;
- clnt->cl_pmap = &clnt->cl_pmap_default;
- clnt->cl_port = xprt->addr.sin_port;
clnt->cl_prog = program->number;
clnt->cl_vers = version->number;
- clnt->cl_prot = xprt->prot;
clnt->cl_stats = program->stats;
clnt->cl_metrics = rpc_alloc_iostats(clnt);
- rpc_init_wait_queue(&clnt->cl_pmap_default.pm_bindwait, "bindwait");
- if (!clnt->cl_port)
+ if (!xprt_bound(clnt->cl_xprt))
clnt->cl_autobind = 1;
clnt->cl_rtt = &clnt->cl_rtt_default;
@@ -175,10 +161,10 @@ rpc_new_client(struct rpc_xprt *xprt, char *servname,
}
/* save the nodename */
- clnt->cl_nodelen = strlen(system_utsname.nodename);
+ clnt->cl_nodelen = strlen(utsname()->nodename);
if (clnt->cl_nodelen > UNX_MAXNODENAME)
clnt->cl_nodelen = UNX_MAXNODENAME;
- memcpy(clnt->cl_nodename, system_utsname.nodename, clnt->cl_nodelen);
+ memcpy(clnt->cl_nodename, utsname()->nodename, clnt->cl_nodelen);
return clnt;
out_no_auth:
@@ -191,40 +177,71 @@ out_no_path:
kfree(clnt->cl_server);
kfree(clnt);
out_err:
- xprt_destroy(xprt);
+ xprt_put(xprt);
out_no_xprt:
return ERR_PTR(err);
}
-/**
- * Create an RPC client
- * @xprt - pointer to xprt struct
- * @servname - name of server
- * @info - rpc_program
- * @version - rpc_program version
- * @authflavor - rpc_auth flavour to use
+/*
+ * rpc_create - create an RPC client and transport with one call
+ * @args: rpc_clnt create argument structure
*
- * Creates an RPC client structure, then pings the server in order to
- * determine if it is up, and if it supports this program and version.
+ * Creates and initializes an RPC transport and an RPC client.
*
- * This function should never be called by asynchronous tasks such as
- * the portmapper.
+ * It can ping the server in order to determine if it is up, and to see if
+ * it supports this program and version. RPC_CLNT_CREATE_NOPING disables
+ * this behavior so asynchronous tasks can also use rpc_create.
*/
-struct rpc_clnt *rpc_create_client(struct rpc_xprt *xprt, char *servname,
- struct rpc_program *info, u32 version, rpc_authflavor_t authflavor)
+struct rpc_clnt *rpc_create(struct rpc_create_args *args)
{
+ struct rpc_xprt *xprt;
struct rpc_clnt *clnt;
- int err;
-
- clnt = rpc_new_client(xprt, servname, info, version, authflavor);
+
+ xprt = xprt_create_transport(args->protocol, args->address,
+ args->addrsize, args->timeout);
+ if (IS_ERR(xprt))
+ return (struct rpc_clnt *)xprt;
+
+ /*
+ * By default, kernel RPC client connects from a reserved port.
+ * CAP_NET_BIND_SERVICE will not be set for unprivileged requesters,
+ * but it is always enabled for rpciod, which handles the connect
+ * operation.
+ */
+ xprt->resvport = 1;
+ if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT)
+ xprt->resvport = 0;
+
+ dprintk("RPC: creating %s client for %s (xprt %p)\n",
+ args->program->name, args->servername, xprt);
+
+ clnt = rpc_new_client(xprt, args->servername, args->program,
+ args->version, args->authflavor);
if (IS_ERR(clnt))
return clnt;
- err = rpc_ping(clnt, RPC_TASK_SOFT|RPC_TASK_NOINTR);
- if (err == 0)
- return clnt;
- rpc_shutdown_client(clnt);
- return ERR_PTR(err);
+
+ if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
+ int err = rpc_ping(clnt, RPC_TASK_SOFT|RPC_TASK_NOINTR);
+ if (err != 0) {
+ rpc_shutdown_client(clnt);
+ return ERR_PTR(err);
+ }
+ }
+
+ clnt->cl_softrtry = 1;
+ if (args->flags & RPC_CLNT_CREATE_HARDRTRY)
+ clnt->cl_softrtry = 0;
+
+ if (args->flags & RPC_CLNT_CREATE_INTR)
+ clnt->cl_intr = 1;
+ if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
+ clnt->cl_autobind = 1;
+ if (args->flags & RPC_CLNT_CREATE_ONESHOT)
+ clnt->cl_oneshot = 1;
+
+ return clnt;
}
+EXPORT_SYMBOL_GPL(rpc_create);
/*
* This function clones the RPC client structure. It allows us to share the
@@ -244,8 +261,7 @@ rpc_clone_client(struct rpc_clnt *clnt)
atomic_set(&new->cl_users, 0);
new->cl_parent = clnt;
atomic_inc(&clnt->cl_count);
- /* Duplicate portmapper */
- rpc_init_wait_queue(&new->cl_pmap_default.pm_bindwait, "bindwait");
+ new->cl_xprt = xprt_get(clnt->cl_xprt);
/* Turn off autobind on clones */
new->cl_autobind = 0;
new->cl_oneshot = 0;
@@ -255,8 +271,7 @@ rpc_clone_client(struct rpc_clnt *clnt)
rpc_init_rtt(&new->cl_rtt_default, clnt->cl_xprt->timeout.to_initval);
if (new->cl_auth)
atomic_inc(&new->cl_auth->au_count);
- new->cl_pmap = &new->cl_pmap_default;
- new->cl_metrics = rpc_alloc_iostats(clnt);
+ new->cl_metrics = rpc_alloc_iostats(clnt);
return new;
out_no_clnt:
printk(KERN_INFO "RPC: out of memory in %s\n", __FUNCTION__);
@@ -323,15 +338,12 @@ rpc_destroy_client(struct rpc_clnt *clnt)
rpc_rmdir(clnt->cl_dentry);
rpc_put_mount();
}
- if (clnt->cl_xprt) {
- xprt_destroy(clnt->cl_xprt);
- clnt->cl_xprt = NULL;
- }
if (clnt->cl_server != clnt->cl_inline_name)
kfree(clnt->cl_server);
out_free:
rpc_free_iostats(clnt->cl_metrics);
clnt->cl_metrics = NULL;
+ xprt_put(clnt->cl_xprt);
kfree(clnt);
return 0;
}
@@ -540,6 +552,40 @@ rpc_call_setup(struct rpc_task *task, struct rpc_message *msg, int flags)
task->tk_action = rpc_exit_task;
}
+/**
+ * rpc_peeraddr - extract remote peer address from clnt's xprt
+ * @clnt: RPC client structure
+ * @buf: target buffer
+ * @size: length of target buffer
+ *
+ * Returns the number of bytes that are actually in the stored address.
+ */
+size_t rpc_peeraddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t bufsize)
+{
+ size_t bytes;
+ struct rpc_xprt *xprt = clnt->cl_xprt;
+
+ bytes = sizeof(xprt->addr);
+ if (bytes > bufsize)
+ bytes = bufsize;
+ memcpy(buf, &clnt->cl_xprt->addr, bytes);
+ return xprt->addrlen;
+}
+EXPORT_SYMBOL_GPL(rpc_peeraddr);
+
+/**
+ * rpc_peeraddr2str - return remote peer address in printable format
+ * @clnt: RPC client structure
+ * @format: address format
+ *
+ */
+char *rpc_peeraddr2str(struct rpc_clnt *clnt, enum rpc_display_format_t format)
+{
+ struct rpc_xprt *xprt = clnt->cl_xprt;
+ return xprt->ops->print_addr(xprt, format);
+}
+EXPORT_SYMBOL_GPL(rpc_peeraddr2str);
+
void
rpc_setbufsize(struct rpc_clnt *clnt, unsigned int sndsize, unsigned int rcvsize)
{
@@ -560,7 +606,7 @@ size_t rpc_max_payload(struct rpc_clnt *clnt)
{
return clnt->cl_xprt->max_payload;
}
-EXPORT_SYMBOL(rpc_max_payload);
+EXPORT_SYMBOL_GPL(rpc_max_payload);
/**
* rpc_force_rebind - force transport to check that remote port is unchanged
@@ -570,9 +616,9 @@ EXPORT_SYMBOL(rpc_max_payload);
void rpc_force_rebind(struct rpc_clnt *clnt)
{
if (clnt->cl_autobind)
- clnt->cl_port = 0;
+ xprt_clear_bound(clnt->cl_xprt);
}
-EXPORT_SYMBOL(rpc_force_rebind);
+EXPORT_SYMBOL_GPL(rpc_force_rebind);
/*
* Restart an (async) RPC call. Usually called from within the
@@ -736,7 +782,7 @@ call_encode(struct rpc_task *task)
struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
unsigned int bufsiz;
kxdrproc_t encode;
- u32 *p;
+ __be32 *p;
dprintk("RPC: %4d call_encode (status %d)\n",
task->tk_pid, task->tk_status);
@@ -781,16 +827,16 @@ call_encode(struct rpc_task *task)
static void
call_bind(struct rpc_task *task)
{
- struct rpc_clnt *clnt = task->tk_client;
+ struct rpc_xprt *xprt = task->tk_xprt;
dprintk("RPC: %4d call_bind (status %d)\n",
task->tk_pid, task->tk_status);
task->tk_action = call_connect;
- if (!clnt->cl_port) {
+ if (!xprt_bound(xprt)) {
task->tk_action = call_bind_status;
- task->tk_timeout = task->tk_xprt->bind_timeout;
- rpc_getport(task, clnt);
+ task->tk_timeout = xprt->bind_timeout;
+ xprt->ops->rpcbind(task);
}
}
@@ -815,15 +861,11 @@ call_bind_status(struct rpc_task *task)
dprintk("RPC: %4d remote rpcbind: RPC program/version unavailable\n",
task->tk_pid);
rpc_delay(task, 3*HZ);
- goto retry_bind;
+ goto retry_timeout;
case -ETIMEDOUT:
dprintk("RPC: %4d rpcbind request timed out\n",
task->tk_pid);
- if (RPC_IS_SOFT(task)) {
- status = -EIO;
- break;
- }
- goto retry_bind;
+ goto retry_timeout;
case -EPFNOSUPPORT:
dprintk("RPC: %4d remote rpcbind service unavailable\n",
task->tk_pid);
@@ -836,16 +878,13 @@ call_bind_status(struct rpc_task *task)
dprintk("RPC: %4d unrecognized rpcbind error (%d)\n",
task->tk_pid, -task->tk_status);
status = -EIO;
- break;
}
rpc_exit(task, status);
return;
-retry_bind:
- task->tk_status = 0;
- task->tk_action = call_bind;
- return;
+retry_timeout:
+ task->tk_action = call_timeout;
}
/*
@@ -893,14 +932,16 @@ call_connect_status(struct rpc_task *task)
switch (status) {
case -ENOTCONN:
- case -ETIMEDOUT:
case -EAGAIN:
task->tk_action = call_bind;
- break;
- default:
- rpc_exit(task, -EIO);
- break;
+ if (!RPC_IS_SOFT(task))
+ return;
+ /* if soft mounted, test if we've timed out */
+ case -ETIMEDOUT:
+ task->tk_action = call_timeout;
+ return;
}
+ rpc_exit(task, -EIO);
}
/*
@@ -982,6 +1023,14 @@ call_status(struct rpc_task *task)
task->tk_status = 0;
switch(status) {
+ case -EHOSTDOWN:
+ case -EHOSTUNREACH:
+ case -ENETUNREACH:
+ /*
+ * Delay any retries for 3 seconds, then handle as if it
+ * were a timeout.
+ */
+ rpc_delay(task, 3*HZ);
case -ETIMEDOUT:
task->tk_action = call_timeout;
break;
@@ -1001,7 +1050,6 @@ call_status(struct rpc_task *task)
printk("%s: RPC call returned error %d\n",
clnt->cl_protname, -status);
rpc_exit(task, status);
- break;
}
}
@@ -1052,7 +1100,7 @@ call_decode(struct rpc_task *task)
struct rpc_clnt *clnt = task->tk_client;
struct rpc_rqst *req = task->tk_rqstp;
kxdrproc_t decode = task->tk_msg.rpc_proc->p_decode;
- u32 *p;
+ __be32 *p;
dprintk("RPC: %4d call_decode (status %d)\n",
task->tk_pid, task->tk_status);
@@ -1069,10 +1117,10 @@ call_decode(struct rpc_task *task)
clnt->cl_stats->rpcretrans++;
goto out_retry;
}
- printk(KERN_WARNING "%s: too small RPC reply size (%d bytes)\n",
+ dprintk("%s: too small RPC reply size (%d bytes)\n",
clnt->cl_protname, task->tk_status);
- rpc_exit(task, -EIO);
- return;
+ task->tk_action = call_timeout;
+ goto out_retry;
}
/*
@@ -1149,12 +1197,12 @@ call_refreshresult(struct rpc_task *task)
/*
* Call header serialization
*/
-static u32 *
+static __be32 *
call_header(struct rpc_task *task)
{
struct rpc_clnt *clnt = task->tk_client;
struct rpc_rqst *req = task->tk_rqstp;
- u32 *p = req->rq_svec[0].iov_base;
+ __be32 *p = req->rq_svec[0].iov_base;
/* FIXME: check buffer size? */
@@ -1173,12 +1221,13 @@ call_header(struct rpc_task *task)
/*
* Reply header verification
*/
-static u32 *
+static __be32 *
call_verify(struct rpc_task *task)
{
struct kvec *iov = &task->tk_rqstp->rq_rcv_buf.head[0];
int len = task->tk_rqstp->rq_rcv_buf.len >> 2;
- u32 *p = iov->iov_base, n;
+ __be32 *p = iov->iov_base;
+ u32 n;
int error = -EACCES;
if ((task->tk_rqstp->rq_rcv_buf.len & 3) != 0) {
@@ -1255,7 +1304,7 @@ call_verify(struct rpc_task *task)
printk(KERN_WARNING "call_verify: auth check failed\n");
goto out_garbage; /* bad verifier, retry */
}
- len = p - (u32 *)iov->iov_base - 1;
+ len = p - (__be32 *)iov->iov_base - 1;
if (len < 0)
goto out_overflow;
switch ((n = ntohl(*p++))) {
@@ -1310,12 +1359,12 @@ out_overflow:
goto out_garbage;
}
-static int rpcproc_encode_null(void *rqstp, u32 *data, void *obj)
+static int rpcproc_encode_null(void *rqstp, __be32 *data, void *obj)
{
return 0;
}
-static int rpcproc_decode_null(void *rqstp, u32 *data, void *obj)
+static int rpcproc_decode_null(void *rqstp, __be32 *data, void *obj)
{
return 0;
}
diff --git a/net/sunrpc/pmap_clnt.c b/net/sunrpc/pmap_clnt.c
index 623180f224c..919d5ba7ca0 100644
--- a/net/sunrpc/pmap_clnt.c
+++ b/net/sunrpc/pmap_clnt.c
@@ -1,7 +1,9 @@
/*
- * linux/net/sunrpc/pmap.c
+ * linux/net/sunrpc/pmap_clnt.c
*
- * Portmapper client.
+ * In-kernel RPC portmapper client.
+ *
+ * Portmapper supports version 2 of the rpcbind protocol (RFC 1833).
*
* Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
*/
@@ -13,7 +15,6 @@
#include <linux/uio.h>
#include <linux/in.h>
#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/sched.h>
#ifdef RPC_DEBUG
@@ -24,80 +25,141 @@
#define PMAP_UNSET 2
#define PMAP_GETPORT 3
+struct portmap_args {
+ u32 pm_prog;
+ u32 pm_vers;
+ u32 pm_prot;
+ unsigned short pm_port;
+ struct rpc_xprt * pm_xprt;
+};
+
static struct rpc_procinfo pmap_procedures[];
static struct rpc_clnt * pmap_create(char *, struct sockaddr_in *, int, int);
-static void pmap_getport_done(struct rpc_task *);
+static void pmap_getport_done(struct rpc_task *, void *);
static struct rpc_program pmap_program;
-static DEFINE_SPINLOCK(pmap_lock);
-/*
- * Obtain the port for a given RPC service on a given host. This one can
- * be called for an ongoing RPC request.
- */
-void
-rpc_getport(struct rpc_task *task, struct rpc_clnt *clnt)
+static void pmap_getport_prepare(struct rpc_task *task, void *calldata)
{
- struct rpc_portmap *map = clnt->cl_pmap;
- struct sockaddr_in *sap = &clnt->cl_xprt->addr;
+ struct portmap_args *map = calldata;
struct rpc_message msg = {
.rpc_proc = &pmap_procedures[PMAP_GETPORT],
.rpc_argp = map,
- .rpc_resp = &clnt->cl_port,
- .rpc_cred = NULL
+ .rpc_resp = &map->pm_port,
};
+
+ rpc_call_setup(task, &msg, 0);
+}
+
+static inline struct portmap_args *pmap_map_alloc(void)
+{
+ return kmalloc(sizeof(struct portmap_args), GFP_NOFS);
+}
+
+static inline void pmap_map_free(struct portmap_args *map)
+{
+ kfree(map);
+}
+
+static void pmap_map_release(void *data)
+{
+ pmap_map_free(data);
+}
+
+static const struct rpc_call_ops pmap_getport_ops = {
+ .rpc_call_prepare = pmap_getport_prepare,
+ .rpc_call_done = pmap_getport_done,
+ .rpc_release = pmap_map_release,
+};
+
+static inline void pmap_wake_portmap_waiters(struct rpc_xprt *xprt, int status)
+{
+ xprt_clear_binding(xprt);
+ rpc_wake_up_status(&xprt->binding, status);
+}
+
+/**
+ * rpc_getport - obtain the port for a given RPC service on a given host
+ * @task: task that is waiting for portmapper request
+ *
+ * This one can be called for an ongoing RPC request, and can be used in
+ * an async (rpciod) context.
+ */
+void rpc_getport(struct rpc_task *task)
+{
+ struct rpc_clnt *clnt = task->tk_client;
+ struct rpc_xprt *xprt = task->tk_xprt;
+ struct sockaddr_in addr;
+ struct portmap_args *map;
struct rpc_clnt *pmap_clnt;
- struct rpc_task *child;
+ struct rpc_task *child;
+ int status;
- dprintk("RPC: %4d rpc_getport(%s, %d, %d, %d)\n",
+ dprintk("RPC: %4d rpc_getport(%s, %u, %u, %d)\n",
task->tk_pid, clnt->cl_server,
- map->pm_prog, map->pm_vers, map->pm_prot);
+ clnt->cl_prog, clnt->cl_vers, xprt->prot);
/* Autobind on cloned rpc clients is discouraged */
BUG_ON(clnt->cl_parent != clnt);
- spin_lock(&pmap_lock);
- if (map->pm_binding) {
- rpc_sleep_on(&map->pm_bindwait, task, NULL, NULL);
- spin_unlock(&pmap_lock);
+ if (xprt_test_and_set_binding(xprt)) {
+ task->tk_status = -EACCES; /* tell caller to check again */
+ rpc_sleep_on(&xprt->binding, task, NULL, NULL);
return;
}
- map->pm_binding = 1;
- spin_unlock(&pmap_lock);
- pmap_clnt = pmap_create(clnt->cl_server, sap, map->pm_prot, 0);
- if (IS_ERR(pmap_clnt)) {
- task->tk_status = PTR_ERR(pmap_clnt);
+ /* Someone else may have bound if we slept */
+ status = 0;
+ if (xprt_bound(xprt))
+ goto bailout_nofree;
+
+ status = -ENOMEM;
+ map = pmap_map_alloc();
+ if (!map)
+ goto bailout_nofree;
+ map->pm_prog = clnt->cl_prog;
+ map->pm_vers = clnt->cl_vers;
+ map->pm_prot = xprt->prot;
+ map->pm_port = 0;
+ map->pm_xprt = xprt_get(xprt);
+
+ rpc_peeraddr(clnt, (struct sockaddr *) &addr, sizeof(addr));
+ pmap_clnt = pmap_create(clnt->cl_server, &addr, map->pm_prot, 0);
+ status = PTR_ERR(pmap_clnt);
+ if (IS_ERR(pmap_clnt))
goto bailout;
- }
- task->tk_status = 0;
- /*
- * Note: rpc_new_child will release client after a failure.
- */
- if (!(child = rpc_new_child(pmap_clnt, task)))
+ status = -EIO;
+ child = rpc_run_task(pmap_clnt, RPC_TASK_ASYNC, &pmap_getport_ops, map);
+ if (IS_ERR(child))
goto bailout;
+ rpc_release_task(child);
- /* Setup the call info struct */
- rpc_call_setup(child, &msg, 0);
+ rpc_sleep_on(&xprt->binding, task, NULL, NULL);
- /* ... and run the child task */
task->tk_xprt->stat.bind_count++;
- rpc_run_child(task, child, pmap_getport_done);
return;
bailout:
- spin_lock(&pmap_lock);
- map->pm_binding = 0;
- rpc_wake_up(&map->pm_bindwait);
- spin_unlock(&pmap_lock);
- rpc_exit(task, -EIO);
+ pmap_map_free(map);
+ xprt_put(xprt);
+bailout_nofree:
+ task->tk_status = status;
+ pmap_wake_portmap_waiters(xprt, status);
}
#ifdef CONFIG_ROOT_NFS
-int
-rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
+/**
+ * rpc_getport_external - obtain the port for a given RPC service on a given host
+ * @sin: address of remote peer
+ * @prog: RPC program number to bind
+ * @vers: RPC version number to bind
+ * @prot: transport protocol to use to make this request
+ *
+ * This one is called from outside the RPC client in a synchronous task context.
+ */
+int rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
{
- struct rpc_portmap map = {
+ struct portmap_args map = {
.pm_prog = prog,
.pm_vers = vers,
.pm_prot = prot,
@@ -112,7 +174,7 @@ rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
char hostname[32];
int status;
- dprintk("RPC: rpc_getport_external(%u.%u.%u.%u, %d, %d, %d)\n",
+ dprintk("RPC: rpc_getport_external(%u.%u.%u.%u, %u, %u, %d)\n",
NIPQUAD(sin->sin_addr.s_addr), prog, vers, prot);
sprintf(hostname, "%u.%u.%u.%u", NIPQUAD(sin->sin_addr.s_addr));
@@ -132,45 +194,53 @@ rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
}
#endif
-static void
-pmap_getport_done(struct rpc_task *task)
+/*
+ * Portmapper child task invokes this callback via tk_exit.
+ */
+static void pmap_getport_done(struct rpc_task *child, void *data)
{
- struct rpc_clnt *clnt = task->tk_client;
- struct rpc_xprt *xprt = task->tk_xprt;
- struct rpc_portmap *map = clnt->cl_pmap;
-
- dprintk("RPC: %4d pmap_getport_done(status %d, port %d)\n",
- task->tk_pid, task->tk_status, clnt->cl_port);
-
- xprt->ops->set_port(xprt, 0);
- if (task->tk_status < 0) {
- /* Make the calling task exit with an error */
- task->tk_action = rpc_exit_task;
- } else if (clnt->cl_port == 0) {
- /* Program not registered */
- rpc_exit(task, -EACCES);
+ struct portmap_args *map = data;
+ struct rpc_xprt *xprt = map->pm_xprt;
+ int status = child->tk_status;
+
+ if (status < 0) {
+ /* Portmapper not available */
+ xprt->ops->set_port(xprt, 0);
+ } else if (map->pm_port == 0) {
+ /* Requested RPC service wasn't registered */
+ xprt->ops->set_port(xprt, 0);
+ status = -EACCES;
} else {
- xprt->ops->set_port(xprt, clnt->cl_port);
- clnt->cl_port = htons(clnt->cl_port);
+ /* Succeeded */
+ xprt->ops->set_port(xprt, map->pm_port);
+ xprt_set_bound(xprt);
+ status = 0;
}
- spin_lock(&pmap_lock);
- map->pm_binding = 0;
- rpc_wake_up(&map->pm_bindwait);
- spin_unlock(&pmap_lock);
+
+ dprintk("RPC: %4d pmap_getport_done(status %d, port %u)\n",
+ child->tk_pid, status, map->pm_port);
+
+ pmap_wake_portmap_waiters(xprt, status);
+ xprt_put(xprt);
}
-/*
- * Set or unset a port registration with the local portmapper.
+/**
+ * rpc_register - set or unset a port registration with the local portmapper
+ * @prog: RPC program number to bind
+ * @vers: RPC version number to bind
+ * @prot: transport protocol to use to make this request
+ * @port: port value to register
+ * @okay: result code
+ *
* port == 0 means unregister, port != 0 means register.
*/
-int
-rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
+int rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
{
struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
};
- struct rpc_portmap map = {
+ struct portmap_args map = {
.pm_prog = prog,
.pm_vers = vers,
.pm_prot = prot,
@@ -184,7 +254,7 @@ rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
struct rpc_clnt *pmap_clnt;
int error = 0;
- dprintk("RPC: registering (%d, %d, %d, %d) with portmapper.\n",
+ dprintk("RPC: registering (%u, %u, %d, %u) with portmapper.\n",
prog, vers, prot, port);
pmap_clnt = pmap_create("localhost", &sin, IPPROTO_UDP, 1);
@@ -207,38 +277,32 @@ rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
return error;
}
-static struct rpc_clnt *
-pmap_create(char *hostname, struct sockaddr_in *srvaddr, int proto, int privileged)
+static struct rpc_clnt *pmap_create(char *hostname, struct sockaddr_in *srvaddr, int proto, int privileged)
{
- struct rpc_xprt *xprt;
- struct rpc_clnt *clnt;
-
- /* printk("pmap: create xprt\n"); */
- xprt = xprt_create_proto(proto, srvaddr, NULL);
- if (IS_ERR(xprt))
- return (struct rpc_clnt *)xprt;
- xprt->ops->set_port(xprt, RPC_PMAP_PORT);
+ struct rpc_create_args args = {
+ .protocol = proto,
+ .address = (struct sockaddr *)srvaddr,
+ .addrsize = sizeof(*srvaddr),
+ .servername = hostname,
+ .program = &pmap_program,
+ .version = RPC_PMAP_VERSION,
+ .authflavor = RPC_AUTH_UNIX,
+ .flags = (RPC_CLNT_CREATE_ONESHOT |
+ RPC_CLNT_CREATE_NOPING),
+ };
+
+ srvaddr->sin_port = htons(RPC_PMAP_PORT);
if (!privileged)
- xprt->resvport = 0;
-
- /* printk("pmap: create clnt\n"); */
- clnt = rpc_new_client(xprt, hostname,
- &pmap_program, RPC_PMAP_VERSION,
- RPC_AUTH_UNIX);
- if (!IS_ERR(clnt)) {
- clnt->cl_softrtry = 1;
- clnt->cl_oneshot = 1;
- }
- return clnt;
+ args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+ return rpc_create(&args);
}
/*
* XDR encode/decode functions for PMAP
*/
-static int
-xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct rpc_portmap *map)
+static int xdr_encode_mapping(struct rpc_rqst *req, __be32 *p, struct portmap_args *map)
{
- dprintk("RPC: xdr_encode_mapping(%d, %d, %d, %d)\n",
+ dprintk("RPC: xdr_encode_mapping(%u, %u, %u, %u)\n",
map->pm_prog, map->pm_vers, map->pm_prot, map->pm_port);
*p++ = htonl(map->pm_prog);
*p++ = htonl(map->pm_vers);
@@ -249,15 +313,13 @@ xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct rpc_portmap *map)
return 0;
}
-static int
-xdr_decode_port(struct rpc_rqst *req, u32 *p, unsigned short *portp)
+static int xdr_decode_port(struct rpc_rqst *req, __be32 *p, unsigned short *portp)
{
*portp = (unsigned short) ntohl(*p++);
return 0;
}
-static int
-xdr_decode_bool(struct rpc_rqst *req, u32 *p, unsigned int *boolp)
+static int xdr_decode_bool(struct rpc_rqst *req, __be32 *p, unsigned int *boolp)
{
*boolp = (unsigned int) ntohl(*p++);
return 0;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 0b1a1ac8a4b..9a0b41a97f9 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -327,10 +327,8 @@ rpc_show_info(struct seq_file *m, void *v)
seq_printf(m, "RPC server: %s\n", clnt->cl_server);
seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_protname,
clnt->cl_prog, clnt->cl_vers);
- seq_printf(m, "address: %u.%u.%u.%u\n",
- NIPQUAD(clnt->cl_xprt->addr.sin_addr.s_addr));
- seq_printf(m, "protocol: %s\n",
- clnt->cl_xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
+ seq_printf(m, "address: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR));
+ seq_printf(m, "protocol: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PROTO));
return 0;
}
@@ -490,14 +488,13 @@ rpc_get_inode(struct super_block *sb, int mode)
return NULL;
inode->i_mode = mode;
inode->i_uid = inode->i_gid = 0;
- inode->i_blksize = PAGE_CACHE_SIZE;
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
switch(mode & S_IFMT) {
case S_IFDIR:
inode->i_fop = &simple_dir_operations;
inode->i_op = &simple_dir_inode_operations;
- inode->i_nlink++;
+ inc_nlink(inode);
default:
break;
}
@@ -574,7 +571,7 @@ rpc_populate(struct dentry *parent,
if (private)
rpc_inode_setowner(inode, private);
if (S_ISDIR(mode))
- dir->i_nlink++;
+ inc_nlink(dir);
d_add(dentry, inode);
}
mutex_unlock(&dir->i_mutex);
@@ -596,7 +593,7 @@ __rpc_mkdir(struct inode *dir, struct dentry *dentry)
goto out_err;
inode->i_ino = iunique(dir->i_sb, 100);
d_instantiate(dentry, inode);
- dir->i_nlink++;
+ inc_nlink(dir);
inode_dir_notify(dir, DN_CREATE);
return 0;
out_err:
@@ -623,17 +620,13 @@ __rpc_rmdir(struct inode *dir, struct dentry *dentry)
}
static struct dentry *
-rpc_lookup_negative(char *path, struct nameidata *nd)
+rpc_lookup_create(struct dentry *parent, const char *name, int len)
{
+ struct inode *dir = parent->d_inode;
struct dentry *dentry;
- struct inode *dir;
- int error;
- if ((error = rpc_lookup_parent(path, nd)) != 0)
- return ERR_PTR(error);
- dir = nd->dentry->d_inode;
mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
- dentry = lookup_one_len(nd->last.name, nd->dentry, nd->last.len);
+ dentry = lookup_one_len(name, parent, len);
if (IS_ERR(dentry))
goto out_err;
if (dentry->d_inode) {
@@ -644,7 +637,20 @@ rpc_lookup_negative(char *path, struct nameidata *nd)
return dentry;
out_err:
mutex_unlock(&dir->i_mutex);
- rpc_release_path(nd);
+ return dentry;
+}
+
+static struct dentry *
+rpc_lookup_negative(char *path, struct nameidata *nd)
+{
+ struct dentry *dentry;
+ int error;
+
+ if ((error = rpc_lookup_parent(path, nd)) != 0)
+ return ERR_PTR(error);
+ dentry = rpc_lookup_create(nd->dentry, nd->last.name, nd->last.len);
+ if (IS_ERR(dentry))
+ rpc_release_path(nd);
return dentry;
}
@@ -703,18 +709,17 @@ rpc_rmdir(struct dentry *dentry)
}
struct dentry *
-rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags)
+rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags)
{
- struct nameidata nd;
struct dentry *dentry;
struct inode *dir, *inode;
struct rpc_inode *rpci;
- dentry = rpc_lookup_negative(path, &nd);
+ dentry = rpc_lookup_create(parent, name, strlen(name));
if (IS_ERR(dentry))
return dentry;
- dir = nd.dentry->d_inode;
- inode = rpc_get_inode(dir->i_sb, S_IFSOCK | S_IRUSR | S_IWUSR);
+ dir = parent->d_inode;
+ inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR);
if (!inode)
goto err_dput;
inode->i_ino = iunique(dir->i_sb, 100);
@@ -728,13 +733,13 @@ rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags)
dget(dentry);
out:
mutex_unlock(&dir->i_mutex);
- rpc_release_path(&nd);
return dentry;
err_dput:
dput(dentry);
dentry = ERR_PTR(-ENOMEM);
- printk(KERN_WARNING "%s: %s() failed to create pipe %s (errno = %d)\n",
- __FILE__, __FUNCTION__, path, -ENOMEM);
+ printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n",
+ __FILE__, __FUNCTION__, parent->d_name.name, name,
+ -ENOMEM);
goto out;
}
@@ -852,7 +857,6 @@ int register_rpc_pipefs(void)
void unregister_rpc_pipefs(void)
{
- if (kmem_cache_destroy(rpc_inode_cachep))
- printk(KERN_WARNING "RPC: unable to free inode cache\n");
+ kmem_cache_destroy(rpc_inode_cachep);
unregister_filesystem(&rpc_pipe_fs_type);
}
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 5c3eee76850..a1ab4eed41f 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -21,7 +21,6 @@
#include <linux/mutex.h>
#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
#ifdef RPC_DEBUG
#define RPCDBG_FACILITY RPCDBG_SCHED
@@ -45,12 +44,6 @@ static void rpciod_killall(void);
static void rpc_async_schedule(void *);
/*
- * RPC tasks that create another task (e.g. for contacting the portmapper)
- * will wait on this queue for their child's completion
- */
-static RPC_WAITQ(childq, "childq");
-
-/*
* RPC tasks sit here while waiting for conditions to improve.
*/
static RPC_WAITQ(delay_queue, "delayq");
@@ -324,16 +317,6 @@ static void rpc_make_runnable(struct rpc_task *task)
}
/*
- * Place a newly initialized task on the workqueue.
- */
-static inline void
-rpc_schedule_run(struct rpc_task *task)
-{
- rpc_set_active(task);
- rpc_make_runnable(task);
-}
-
-/*
* Prepare for sleeping on a wait queue.
* By always appending tasks to the list we ensure FIFO behavior.
* NB: An RPC task will only receive interrupt-driven events as long
@@ -559,24 +542,20 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
spin_unlock_bh(&queue->lock);
}
+static void __rpc_atrun(struct rpc_task *task)
+{
+ rpc_wake_up_task(task);
+}
+
/*
* Run a task at a later time
*/
-static void __rpc_atrun(struct rpc_task *);
-void
-rpc_delay(struct rpc_task *task, unsigned long delay)
+void rpc_delay(struct rpc_task *task, unsigned long delay)
{
task->tk_timeout = delay;
rpc_sleep_on(&delay_queue, task, NULL, __rpc_atrun);
}
-static void
-__rpc_atrun(struct rpc_task *task)
-{
- task->tk_status = 0;
- rpc_wake_up_task(task);
-}
-
/*
* Helper to call task->tk_ops->rpc_call_prepare
*/
@@ -933,72 +912,6 @@ struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags,
}
EXPORT_SYMBOL(rpc_run_task);
-/**
- * rpc_find_parent - find the parent of a child task.
- * @child: child task
- * @parent: parent task
- *
- * Checks that the parent task is still sleeping on the
- * queue 'childq'. If so returns a pointer to the parent.
- * Upon failure returns NULL.
- *
- * Caller must hold childq.lock
- */
-static inline struct rpc_task *rpc_find_parent(struct rpc_task *child, struct rpc_task *parent)
-{
- struct rpc_task *task;
- struct list_head *le;
-
- task_for_each(task, le, &childq.tasks[0])
- if (task == parent)
- return parent;
-
- return NULL;
-}
-
-static void rpc_child_exit(struct rpc_task *child, void *calldata)
-{
- struct rpc_task *parent;
-
- spin_lock_bh(&childq.lock);
- if ((parent = rpc_find_parent(child, calldata)) != NULL) {
- parent->tk_status = child->tk_status;
- __rpc_wake_up_task(parent);
- }
- spin_unlock_bh(&childq.lock);
-}
-
-static const struct rpc_call_ops rpc_child_ops = {
- .rpc_call_done = rpc_child_exit,
-};
-
-/*
- * Note: rpc_new_task releases the client after a failure.
- */
-struct rpc_task *
-rpc_new_child(struct rpc_clnt *clnt, struct rpc_task *parent)
-{
- struct rpc_task *task;
-
- task = rpc_new_task(clnt, RPC_TASK_ASYNC | RPC_TASK_CHILD, &rpc_child_ops, parent);
- if (!task)
- goto fail;
- return task;
-
-fail:
- parent->tk_status = -ENOMEM;
- return NULL;
-}
-
-void rpc_run_child(struct rpc_task *task, struct rpc_task *child, rpc_action func)
-{
- spin_lock_bh(&childq.lock);
- /* N.B. Is it possible for the child to have already finished? */
- __rpc_sleep_on(&childq, task, func, NULL);
- rpc_schedule_run(child);
- spin_unlock_bh(&childq.lock);
-}
-
/*
* Kill all tasks for the given client.
* XXX: kill their descendants as well?
@@ -1146,10 +1059,10 @@ rpc_destroy_mempool(void)
mempool_destroy(rpc_buffer_mempool);
if (rpc_task_mempool)
mempool_destroy(rpc_task_mempool);
- if (rpc_task_slabp && kmem_cache_destroy(rpc_task_slabp))
- printk(KERN_INFO "rpc_task: not all structures were freed\n");
- if (rpc_buffer_slabp && kmem_cache_destroy(rpc_buffer_slabp))
- printk(KERN_INFO "rpc_buffers: not all structures were freed\n");
+ if (rpc_task_slabp)
+ kmem_cache_destroy(rpc_task_slabp);
+ if (rpc_buffer_slabp)
+ kmem_cache_destroy(rpc_buffer_slabp);
}
int
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index eb330d4f66d..6f17527b9e6 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -168,7 +168,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
return -1;
if ((unsigned short)csum_fold(desc.csum))
return -1;
- if (unlikely(skb->ip_summed == CHECKSUM_HW))
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
netdev_rx_csum_fault(skb->dev);
return 0;
no_checksum:
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index f38f939ce95..192dff5dabc 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -36,8 +36,6 @@ EXPORT_SYMBOL(rpc_wake_up_status);
EXPORT_SYMBOL(rpc_release_task);
/* RPC client functions */
-EXPORT_SYMBOL(rpc_create_client);
-EXPORT_SYMBOL(rpc_new_client);
EXPORT_SYMBOL(rpc_clone_client);
EXPORT_SYMBOL(rpc_bind_new_program);
EXPORT_SYMBOL(rpc_destroy_client);
@@ -57,7 +55,6 @@ EXPORT_SYMBOL(rpc_queue_upcall);
EXPORT_SYMBOL(rpc_mkpipe);
/* Client transport */
-EXPORT_SYMBOL(xprt_create_proto);
EXPORT_SYMBOL(xprt_set_timeout);
/* Client credential cache */
@@ -73,6 +70,8 @@ EXPORT_SYMBOL(put_rpccred);
/* RPC server stuff */
EXPORT_SYMBOL(svc_create);
EXPORT_SYMBOL(svc_create_thread);
+EXPORT_SYMBOL(svc_create_pooled);
+EXPORT_SYMBOL(svc_set_num_threads);
EXPORT_SYMBOL(svc_exit_thread);
EXPORT_SYMBOL(svc_destroy);
EXPORT_SYMBOL(svc_drop);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index b76a227dd3a..a99e67b164c 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -4,6 +4,10 @@
* High-level RPC service routines
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ *
+ * Multiple threads pools and NUMAisation
+ * Copyright (c) 2006 Silicon Graphics, Inc.
+ * by Greg Banks <gnb@melbourne.sgi.com>
*/
#include <linux/linkage.h>
@@ -12,6 +16,8 @@
#include <linux/net.h>
#include <linux/in.h>
#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
@@ -23,14 +29,252 @@
#define RPC_PARANOIA 1
/*
+ * Mode for mapping cpus to pools.
+ */
+enum {
+ SVC_POOL_NONE = -1, /* uninitialised, choose one of the others */
+ SVC_POOL_GLOBAL, /* no mapping, just a single global pool
+ * (legacy & UP mode) */
+ SVC_POOL_PERCPU, /* one pool per cpu */
+ SVC_POOL_PERNODE /* one pool per numa node */
+};
+
+/*
+ * Structure for mapping cpus to pools and vice versa.
+ * Setup once during sunrpc initialisation.
+ */
+static struct svc_pool_map {
+ int mode; /* Note: int not enum to avoid
+ * warnings about "enumeration value
+ * not handled in switch" */
+ unsigned int npools;
+ unsigned int *pool_to; /* maps pool id to cpu or node */
+ unsigned int *to_pool; /* maps cpu or node to pool id */
+} svc_pool_map = {
+ .mode = SVC_POOL_NONE
+};
+
+
+/*
+ * Detect best pool mapping mode heuristically,
+ * according to the machine's topology.
+ */
+static int
+svc_pool_map_choose_mode(void)
+{
+ unsigned int node;
+
+ if (num_online_nodes() > 1) {
+ /*
+ * Actually have multiple NUMA nodes,
+ * so split pools on NUMA node boundaries
+ */
+ return SVC_POOL_PERNODE;
+ }
+
+ node = any_online_node(node_online_map);
+ if (nr_cpus_node(node) > 2) {
+ /*
+ * Non-trivial SMP, or CONFIG_NUMA on
+ * non-NUMA hardware, e.g. with a generic
+ * x86_64 kernel on Xeons. In this case we
+ * want to divide the pools on cpu boundaries.
+ */
+ return SVC_POOL_PERCPU;
+ }
+
+ /* default: one global pool */
+ return SVC_POOL_GLOBAL;
+}
+
+/*
+ * Allocate the to_pool[] and pool_to[] arrays.
+ * Returns 0 on success or an errno.
+ */
+static int
+svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools)
+{
+ m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL);
+ if (!m->to_pool)
+ goto fail;
+ m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL);
+ if (!m->pool_to)
+ goto fail_free;
+
+ return 0;
+
+fail_free:
+ kfree(m->to_pool);
+fail:
+ return -ENOMEM;
+}
+
+/*
+ * Initialise the pool map for SVC_POOL_PERCPU mode.
+ * Returns number of pools or <0 on error.
+ */
+static int
+svc_pool_map_init_percpu(struct svc_pool_map *m)
+{
+ unsigned int maxpools = highest_possible_processor_id()+1;
+ unsigned int pidx = 0;
+ unsigned int cpu;
+ int err;
+
+ err = svc_pool_map_alloc_arrays(m, maxpools);
+ if (err)
+ return err;
+
+ for_each_online_cpu(cpu) {
+ BUG_ON(pidx > maxpools);
+ m->to_pool[cpu] = pidx;
+ m->pool_to[pidx] = cpu;
+ pidx++;
+ }
+ /* cpus brought online later all get mapped to pool0, sorry */
+
+ return pidx;
+};
+
+
+/*
+ * Initialise the pool map for SVC_POOL_PERNODE mode.
+ * Returns number of pools or <0 on error.
+ */
+static int
+svc_pool_map_init_pernode(struct svc_pool_map *m)
+{
+ unsigned int maxpools = highest_possible_node_id()+1;
+ unsigned int pidx = 0;
+ unsigned int node;
+ int err;
+
+ err = svc_pool_map_alloc_arrays(m, maxpools);
+ if (err)
+ return err;
+
+ for_each_node_with_cpus(node) {
+ /* some architectures (e.g. SN2) have cpuless nodes */
+ BUG_ON(pidx > maxpools);
+ m->to_pool[node] = pidx;
+ m->pool_to[pidx] = node;
+ pidx++;
+ }
+ /* nodes brought online later all get mapped to pool0, sorry */
+
+ return pidx;
+}
+
+
+/*
+ * Build the global map of cpus to pools and vice versa.
+ */
+static unsigned int
+svc_pool_map_init(void)
+{
+ struct svc_pool_map *m = &svc_pool_map;
+ int npools = -1;
+
+ if (m->mode != SVC_POOL_NONE)
+ return m->npools;
+
+ m->mode = svc_pool_map_choose_mode();
+
+ switch (m->mode) {
+ case SVC_POOL_PERCPU:
+ npools = svc_pool_map_init_percpu(m);
+ break;
+ case SVC_POOL_PERNODE:
+ npools = svc_pool_map_init_pernode(m);
+ break;
+ }
+
+ if (npools < 0) {
+ /* default, or memory allocation failure */
+ npools = 1;
+ m->mode = SVC_POOL_GLOBAL;
+ }
+ m->npools = npools;
+
+ return m->npools;
+}
+
+/*
+ * Set the current thread's cpus_allowed mask so that it
+ * will only run on cpus in the given pool.
+ *
+ * Returns 1 and fills in oldmask iff a cpumask was applied.
+ */
+static inline int
+svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask)
+{
+ struct svc_pool_map *m = &svc_pool_map;
+ unsigned int node; /* or cpu */
+
+ /*
+ * The caller checks for sv_nrpools > 1, which
+ * implies that we've been initialized and the
+ * map mode is not NONE.
+ */
+ BUG_ON(m->mode == SVC_POOL_NONE);
+
+ switch (m->mode)
+ {
+ default:
+ return 0;
+ case SVC_POOL_PERCPU:
+ node = m->pool_to[pidx];
+ *oldmask = current->cpus_allowed;
+ set_cpus_allowed(current, cpumask_of_cpu(node));
+ return 1;
+ case SVC_POOL_PERNODE:
+ node = m->pool_to[pidx];
+ *oldmask = current->cpus_allowed;
+ set_cpus_allowed(current, node_to_cpumask(node));
+ return 1;
+ }
+}
+
+/*
+ * Use the mapping mode to choose a pool for a given CPU.
+ * Used when enqueueing an incoming RPC. Always returns
+ * a non-NULL pool pointer.
+ */
+struct svc_pool *
+svc_pool_for_cpu(struct svc_serv *serv, int cpu)
+{
+ struct svc_pool_map *m = &svc_pool_map;
+ unsigned int pidx = 0;
+
+ /*
+ * SVC_POOL_NONE happens in a pure client when
+ * lockd is brought up, so silently treat it the
+ * same as SVC_POOL_GLOBAL.
+ */
+
+ switch (m->mode) {
+ case SVC_POOL_PERCPU:
+ pidx = m->to_pool[cpu];
+ break;
+ case SVC_POOL_PERNODE:
+ pidx = m->to_pool[cpu_to_node(cpu)];
+ break;
+ }
+ return &serv->sv_pools[pidx % serv->sv_nrpools];
+}
+
+
+/*
* Create an RPC service
*/
-struct svc_serv *
-svc_create(struct svc_program *prog, unsigned int bufsize)
+static struct svc_serv *
+__svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
+ void (*shutdown)(struct svc_serv *serv))
{
struct svc_serv *serv;
int vers;
unsigned int xdrsize;
+ unsigned int i;
if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL)))
return NULL;
@@ -39,6 +283,7 @@ svc_create(struct svc_program *prog, unsigned int bufsize)
serv->sv_nrthreads = 1;
serv->sv_stats = prog->pg_stats;
serv->sv_bufsz = bufsize? bufsize : 4096;
+ serv->sv_shutdown = shutdown;
xdrsize = 0;
while (prog) {
prog->pg_lovers = prog->pg_nvers-1;
@@ -53,20 +298,68 @@ svc_create(struct svc_program *prog, unsigned int bufsize)
prog = prog->pg_next;
}
serv->sv_xdrsize = xdrsize;
- INIT_LIST_HEAD(&serv->sv_threads);
- INIT_LIST_HEAD(&serv->sv_sockets);
INIT_LIST_HEAD(&serv->sv_tempsocks);
INIT_LIST_HEAD(&serv->sv_permsocks);
+ init_timer(&serv->sv_temptimer);
spin_lock_init(&serv->sv_lock);
+ serv->sv_nrpools = npools;
+ serv->sv_pools =
+ kcalloc(sizeof(struct svc_pool), serv->sv_nrpools,
+ GFP_KERNEL);
+ if (!serv->sv_pools) {
+ kfree(serv);
+ return NULL;
+ }
+
+ for (i = 0; i < serv->sv_nrpools; i++) {
+ struct svc_pool *pool = &serv->sv_pools[i];
+
+ dprintk("initialising pool %u for %s\n",
+ i, serv->sv_name);
+
+ pool->sp_id = i;
+ INIT_LIST_HEAD(&pool->sp_threads);
+ INIT_LIST_HEAD(&pool->sp_sockets);
+ INIT_LIST_HEAD(&pool->sp_all_threads);
+ spin_lock_init(&pool->sp_lock);
+ }
+
+
/* Remove any stale portmap registrations */
svc_register(serv, 0, 0);
return serv;
}
+struct svc_serv *
+svc_create(struct svc_program *prog, unsigned int bufsize,
+ void (*shutdown)(struct svc_serv *serv))
+{
+ return __svc_create(prog, bufsize, /*npools*/1, shutdown);
+}
+
+struct svc_serv *
+svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
+ void (*shutdown)(struct svc_serv *serv),
+ svc_thread_fn func, int sig, struct module *mod)
+{
+ struct svc_serv *serv;
+ unsigned int npools = svc_pool_map_init();
+
+ serv = __svc_create(prog, bufsize, npools, shutdown);
+
+ if (serv != NULL) {
+ serv->sv_function = func;
+ serv->sv_kill_signal = sig;
+ serv->sv_module = mod;
+ }
+
+ return serv;
+}
+
/*
- * Destroy an RPC service
+ * Destroy an RPC service. Should be called with the BKL held
*/
void
svc_destroy(struct svc_serv *serv)
@@ -85,12 +378,17 @@ svc_destroy(struct svc_serv *serv)
} else
printk("svc_destroy: no threads for serv=%p!\n", serv);
+ del_timer_sync(&serv->sv_temptimer);
+
while (!list_empty(&serv->sv_tempsocks)) {
svsk = list_entry(serv->sv_tempsocks.next,
struct svc_sock,
sk_list);
svc_delete_socket(svsk);
}
+ if (serv->sv_shutdown)
+ serv->sv_shutdown(serv);
+
while (!list_empty(&serv->sv_permsocks)) {
svsk = list_entry(serv->sv_permsocks.next,
struct svc_sock,
@@ -102,6 +400,7 @@ svc_destroy(struct svc_serv *serv)
/* Unregister service with the portmapper */
svc_register(serv, 0, 0);
+ kfree(serv->sv_pools);
kfree(serv);
}
@@ -150,13 +449,18 @@ svc_release_buffer(struct svc_rqst *rqstp)
}
/*
- * Create a server thread
+ * Create a thread in the given pool. Caller must hold BKL.
+ * On a NUMA or SMP machine, with a multi-pool serv, the thread
+ * will be restricted to run on the cpus belonging to the pool.
*/
-int
-svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
+static int
+__svc_create_thread(svc_thread_fn func, struct svc_serv *serv,
+ struct svc_pool *pool)
{
struct svc_rqst *rqstp;
int error = -ENOMEM;
+ int have_oldmask = 0;
+ cpumask_t oldmask;
rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
if (!rqstp)
@@ -170,8 +474,21 @@ svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
goto out_thread;
serv->sv_nrthreads++;
+ spin_lock_bh(&pool->sp_lock);
+ pool->sp_nrthreads++;
+ list_add(&rqstp->rq_all, &pool->sp_all_threads);
+ spin_unlock_bh(&pool->sp_lock);
rqstp->rq_server = serv;
+ rqstp->rq_pool = pool;
+
+ if (serv->sv_nrpools > 1)
+ have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask);
+
error = kernel_thread((int (*)(void *)) func, rqstp, 0);
+
+ if (have_oldmask)
+ set_cpus_allowed(current, oldmask);
+
if (error < 0)
goto out_thread;
svc_sock_update_bufs(serv);
@@ -185,17 +502,136 @@ out_thread:
}
/*
- * Destroy an RPC server thread
+ * Create a thread in the default pool. Caller must hold BKL.
+ */
+int
+svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
+{
+ return __svc_create_thread(func, serv, &serv->sv_pools[0]);
+}
+
+/*
+ * Choose a pool in which to create a new thread, for svc_set_num_threads
+ */
+static inline struct svc_pool *
+choose_pool(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
+{
+ if (pool != NULL)
+ return pool;
+
+ return &serv->sv_pools[(*state)++ % serv->sv_nrpools];
+}
+
+/*
+ * Choose a thread to kill, for svc_set_num_threads
+ */
+static inline struct task_struct *
+choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
+{
+ unsigned int i;
+ struct task_struct *task = NULL;
+
+ if (pool != NULL) {
+ spin_lock_bh(&pool->sp_lock);
+ } else {
+ /* choose a pool in round-robin fashion */
+ for (i = 0; i < serv->sv_nrpools; i++) {
+ pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
+ spin_lock_bh(&pool->sp_lock);
+ if (!list_empty(&pool->sp_all_threads))
+ goto found_pool;
+ spin_unlock_bh(&pool->sp_lock);
+ }
+ return NULL;
+ }
+
+found_pool:
+ if (!list_empty(&pool->sp_all_threads)) {
+ struct svc_rqst *rqstp;
+
+ /*
+ * Remove from the pool->sp_all_threads list
+ * so we don't try to kill it again.
+ */
+ rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
+ list_del_init(&rqstp->rq_all);
+ task = rqstp->rq_task;
+ }
+ spin_unlock_bh(&pool->sp_lock);
+
+ return task;
+}
+
+/*
+ * Create or destroy enough new threads to make the number
+ * of threads the given number. If `pool' is non-NULL, applies
+ * only to threads in that pool, otherwise round-robins between
+ * all pools. Must be called with a svc_get() reference and
+ * the BKL held.
+ *
+ * Destroying threads relies on the service threads filling in
+ * rqstp->rq_task, which only the nfs ones do. Assumes the serv
+ * has been created using svc_create_pooled().
+ *
+ * Based on code that used to be in nfsd_svc() but tweaked
+ * to be pool-aware.
+ */
+int
+svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+ struct task_struct *victim;
+ int error = 0;
+ unsigned int state = serv->sv_nrthreads-1;
+
+ if (pool == NULL) {
+ /* The -1 assumes caller has done a svc_get() */
+ nrservs -= (serv->sv_nrthreads-1);
+ } else {
+ spin_lock_bh(&pool->sp_lock);
+ nrservs -= pool->sp_nrthreads;
+ spin_unlock_bh(&pool->sp_lock);
+ }
+
+ /* create new threads */
+ while (nrservs > 0) {
+ nrservs--;
+ __module_get(serv->sv_module);
+ error = __svc_create_thread(serv->sv_function, serv,
+ choose_pool(serv, pool, &state));
+ if (error < 0) {
+ module_put(serv->sv_module);
+ break;
+ }
+ }
+ /* destroy old threads */
+ while (nrservs < 0 &&
+ (victim = choose_victim(serv, pool, &state)) != NULL) {
+ send_sig(serv->sv_kill_signal, victim, 1);
+ nrservs++;
+ }
+
+ return error;
+}
+
+/*
+ * Called from a server thread as it's exiting. Caller must hold BKL.
*/
void
svc_exit_thread(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
+ struct svc_pool *pool = rqstp->rq_pool;
svc_release_buffer(rqstp);
kfree(rqstp->rq_resp);
kfree(rqstp->rq_argp);
kfree(rqstp->rq_auth_data);
+
+ spin_lock_bh(&pool->sp_lock);
+ pool->sp_nrthreads--;
+ list_del(&rqstp->rq_all);
+ spin_unlock_bh(&pool->sp_lock);
+
kfree(rqstp);
/* Release the server */
@@ -248,19 +684,20 @@ svc_register(struct svc_serv *serv, int proto, unsigned short port)
* Process the RPC request.
*/
int
-svc_process(struct svc_serv *serv, struct svc_rqst *rqstp)
+svc_process(struct svc_rqst *rqstp)
{
struct svc_program *progp;
struct svc_version *versp = NULL; /* compiler food */
struct svc_procedure *procp = NULL;
struct kvec * argv = &rqstp->rq_arg.head[0];
struct kvec * resv = &rqstp->rq_res.head[0];
+ struct svc_serv *serv = rqstp->rq_server;
kxdrproc_t xdr;
- u32 *statp;
- u32 dir, prog, vers, proc,
- auth_stat, rpc_stat;
+ __be32 *statp;
+ u32 dir, prog, vers, proc;
+ __be32 auth_stat, rpc_stat;
int auth_res;
- u32 *accept_statp;
+ __be32 *accept_statp;
rpc_stat = rpc_success;
@@ -284,16 +721,16 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp)
rqstp->rq_sendfile_ok = 1;
/* tcp needs a space for the record length... */
if (rqstp->rq_prot == IPPROTO_TCP)
- svc_putu32(resv, 0);
+ svc_putnl(resv, 0);
rqstp->rq_xid = svc_getu32(argv);
svc_putu32(resv, rqstp->rq_xid);
- dir = ntohl(svc_getu32(argv));
- vers = ntohl(svc_getu32(argv));
+ dir = svc_getnl(argv);
+ vers = svc_getnl(argv);
/* First words of reply: */
- svc_putu32(resv, xdr_one); /* REPLY */
+ svc_putnl(resv, 1); /* REPLY */
if (dir != 0) /* direction != CALL */
goto err_bad_dir;
@@ -303,11 +740,11 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp)
/* Save position in case we later decide to reject: */
accept_statp = resv->iov_base + resv->iov_len;
- svc_putu32(resv, xdr_zero); /* ACCEPT */
+ svc_putnl(resv, 0); /* ACCEPT */
- rqstp->rq_prog = prog = ntohl(svc_getu32(argv)); /* program number */
- rqstp->rq_vers = vers = ntohl(svc_getu32(argv)); /* version number */
- rqstp->rq_proc = proc = ntohl(svc_getu32(argv)); /* procedure number */
+ rqstp->rq_prog = prog = svc_getnl(argv); /* program number */
+ rqstp->rq_vers = vers = svc_getnl(argv); /* version number */
+ rqstp->rq_proc = proc = svc_getnl(argv); /* procedure number */
progp = serv->sv_program;
@@ -361,7 +798,7 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp)
/* Build the reply header. */
statp = resv->iov_base +resv->iov_len;
- svc_putu32(resv, rpc_success); /* RPC_SUCCESS */
+ svc_putnl(resv, RPC_SUCCESS);
/* Bump per-procedure stats counter */
procp->pc_count++;
@@ -439,10 +876,10 @@ err_bad_dir:
err_bad_rpc:
serv->sv_stats->rpcbadfmt++;
- svc_putu32(resv, xdr_one); /* REJECT */
- svc_putu32(resv, xdr_zero); /* RPC_MISMATCH */
- svc_putu32(resv, xdr_two); /* Only RPCv2 supported */
- svc_putu32(resv, xdr_two);
+ svc_putnl(resv, 1); /* REJECT */
+ svc_putnl(resv, 0); /* RPC_MISMATCH */
+ svc_putnl(resv, 2); /* Only RPCv2 supported */
+ svc_putnl(resv, 2);
goto sendit;
err_bad_auth:
@@ -450,15 +887,15 @@ err_bad_auth:
serv->sv_stats->rpcbadauth++;
/* Restore write pointer to location of accept status: */
xdr_ressize_check(rqstp, accept_statp);
- svc_putu32(resv, xdr_one); /* REJECT */
- svc_putu32(resv, xdr_one); /* AUTH_ERROR */
- svc_putu32(resv, auth_stat); /* status */
+ svc_putnl(resv, 1); /* REJECT */
+ svc_putnl(resv, 1); /* AUTH_ERROR */
+ svc_putnl(resv, ntohl(auth_stat)); /* status */
goto sendit;
err_bad_prog:
dprintk("svc: unknown program %d\n", prog);
serv->sv_stats->rpcbadfmt++;
- svc_putu32(resv, rpc_prog_unavail);
+ svc_putnl(resv, RPC_PROG_UNAVAIL);
goto sendit;
err_bad_vers:
@@ -466,9 +903,9 @@ err_bad_vers:
printk("svc: unknown version (%d)\n", vers);
#endif
serv->sv_stats->rpcbadfmt++;
- svc_putu32(resv, rpc_prog_mismatch);
- svc_putu32(resv, htonl(progp->pg_lovers));
- svc_putu32(resv, htonl(progp->pg_hivers));
+ svc_putnl(resv, RPC_PROG_MISMATCH);
+ svc_putnl(resv, progp->pg_lovers);
+ svc_putnl(resv, progp->pg_hivers);
goto sendit;
err_bad_proc:
@@ -476,7 +913,7 @@ err_bad_proc:
printk("svc: unknown procedure (%d)\n", proc);
#endif
serv->sv_stats->rpcbadfmt++;
- svc_putu32(resv, rpc_proc_unavail);
+ svc_putnl(resv, RPC_PROC_UNAVAIL);
goto sendit;
err_garbage:
@@ -486,6 +923,6 @@ err_garbage:
rpc_stat = rpc_garbage_args;
err_bad:
serv->sv_stats->rpcbadfmt++;
- svc_putu32(resv, rpc_stat);
+ svc_putnl(resv, ntohl(rpc_stat));
goto sendit;
}
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index 5b28c617680..8f2320aded5 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -35,14 +35,14 @@ static struct auth_ops *authtab[RPC_AUTH_MAXFLAVOR] = {
};
int
-svc_authenticate(struct svc_rqst *rqstp, u32 *authp)
+svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
{
rpc_authflavor_t flavor;
struct auth_ops *aops;
*authp = rpc_auth_ok;
- flavor = ntohl(svc_getu32(&rqstp->rq_arg.head[0]));
+ flavor = svc_getnl(&rqstp->rq_arg.head[0]);
dprintk("svc: svc_authenticate (%d)\n", flavor);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 7e5707e2d6b..40d41a2831d 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -145,7 +145,7 @@ static void ip_map_request(struct cache_detail *cd,
{
char text_addr[20];
struct ip_map *im = container_of(h, struct ip_map, h);
- __u32 addr = im->m_addr.s_addr;
+ __be32 addr = im->m_addr.s_addr;
snprintf(text_addr, 20, "%u.%u.%u.%u",
ntohl(addr) >> 24 & 0xff,
@@ -249,10 +249,10 @@ static int ip_map_show(struct seq_file *m,
seq_printf(m, "%s %d.%d.%d.%d %s\n",
im->m_class,
- htonl(addr.s_addr) >> 24 & 0xff,
- htonl(addr.s_addr) >> 16 & 0xff,
- htonl(addr.s_addr) >> 8 & 0xff,
- htonl(addr.s_addr) >> 0 & 0xff,
+ ntohl(addr.s_addr) >> 24 & 0xff,
+ ntohl(addr.s_addr) >> 16 & 0xff,
+ ntohl(addr.s_addr) >> 8 & 0xff,
+ ntohl(addr.s_addr) >> 0 & 0xff,
dom
);
return 0;
@@ -348,12 +348,9 @@ int auth_unix_forget_old(struct auth_domain *dom)
struct auth_domain *auth_unix_lookup(struct in_addr addr)
{
- struct ip_map key, *ipm;
+ struct ip_map *ipm;
struct auth_domain *rv;
- strcpy(key.m_class, "nfsd");
- key.m_addr = addr;
-
ipm = ip_map_lookup("nfsd", addr);
if (!ipm)
@@ -410,7 +407,7 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
}
static int
-svcauth_null_accept(struct svc_rqst *rqstp, u32 *authp)
+svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp)
{
struct kvec *argv = &rqstp->rq_arg.head[0];
struct kvec *resv = &rqstp->rq_res.head[0];
@@ -427,7 +424,7 @@ svcauth_null_accept(struct svc_rqst *rqstp, u32 *authp)
*authp = rpc_autherr_badcred;
return SVC_DENIED;
}
- if (svc_getu32(argv) != RPC_AUTH_NULL || svc_getu32(argv) != 0) {
+ if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) {
dprintk("svc: bad null verf\n");
*authp = rpc_autherr_badverf;
return SVC_DENIED;
@@ -441,8 +438,8 @@ svcauth_null_accept(struct svc_rqst *rqstp, u32 *authp)
return SVC_DROP; /* kmalloc failure - client must retry */
/* Put NULL verifier */
- svc_putu32(resv, RPC_AUTH_NULL);
- svc_putu32(resv, 0);
+ svc_putnl(resv, RPC_AUTH_NULL);
+ svc_putnl(resv, 0);
return SVC_OK;
}
@@ -472,7 +469,7 @@ struct auth_ops svcauth_null = {
static int
-svcauth_unix_accept(struct svc_rqst *rqstp, u32 *authp)
+svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp)
{
struct kvec *argv = &rqstp->rq_arg.head[0];
struct kvec *resv = &rqstp->rq_res.head[0];
@@ -488,31 +485,31 @@ svcauth_unix_accept(struct svc_rqst *rqstp, u32 *authp)
svc_getu32(argv); /* length */
svc_getu32(argv); /* time stamp */
- slen = XDR_QUADLEN(ntohl(svc_getu32(argv))); /* machname length */
+ slen = XDR_QUADLEN(svc_getnl(argv)); /* machname length */
if (slen > 64 || (len -= (slen + 3)*4) < 0)
goto badcred;
- argv->iov_base = (void*)((u32*)argv->iov_base + slen); /* skip machname */
+ argv->iov_base = (void*)((__be32*)argv->iov_base + slen); /* skip machname */
argv->iov_len -= slen*4;
- cred->cr_uid = ntohl(svc_getu32(argv)); /* uid */
- cred->cr_gid = ntohl(svc_getu32(argv)); /* gid */
- slen = ntohl(svc_getu32(argv)); /* gids length */
+ cred->cr_uid = svc_getnl(argv); /* uid */
+ cred->cr_gid = svc_getnl(argv); /* gid */
+ slen = svc_getnl(argv); /* gids length */
if (slen > 16 || (len -= (slen + 2)*4) < 0)
goto badcred;
cred->cr_group_info = groups_alloc(slen);
if (cred->cr_group_info == NULL)
return SVC_DROP;
for (i = 0; i < slen; i++)
- GROUP_AT(cred->cr_group_info, i) = ntohl(svc_getu32(argv));
+ GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv);
- if (svc_getu32(argv) != RPC_AUTH_NULL || svc_getu32(argv) != 0) {
+ if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) {
*authp = rpc_autherr_badverf;
return SVC_DENIED;
}
/* Put NULL verifier */
- svc_putu32(resv, RPC_AUTH_NULL);
- svc_putu32(resv, 0);
+ svc_putnl(resv, RPC_AUTH_NULL);
+ svc_putnl(resv, 0);
return SVC_OK;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index d9a95732df4..cba85d19522 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -31,6 +31,7 @@
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <linux/file.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip.h>
@@ -45,13 +46,16 @@
/* SMP locking strategy:
*
- * svc_serv->sv_lock protects most stuff for that service.
+ * svc_pool->sp_lock protects most of the fields of that pool.
+ * svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
+ * when both need to be taken (rare), svc_serv->sv_lock is first.
+ * BKL protects svc_serv->sv_nrthread.
+ * svc_sock->sk_defer_lock protects the svc_sock->sk_deferred list
+ * svc_sock->sk_flags.SK_BUSY prevents a svc_sock being enqueued multiply.
*
* Some flags can be set to certain values at any time
* providing that certain rules are followed:
*
- * SK_BUSY can be set to 0 at any time.
- * svc_sock_enqueue must be called afterwards
* SK_CONN, SK_DATA, can be set or cleared at any time.
* after a set, svc_sock_enqueue must be called.
* after a clear, the socket must be read/accepted
@@ -73,23 +77,30 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
+/* apparently the "standard" is that clients close
+ * idle connections after 5 minutes, servers after
+ * 6 minutes
+ * http://www.connectathon.org/talks96/nfstcp.pdf
+ */
+static int svc_conn_age_period = 6*60;
+
/*
- * Queue up an idle server thread. Must have serv->sv_lock held.
+ * Queue up an idle server thread. Must have pool->sp_lock held.
* Note: this is really a stack rather than a queue, so that we only
- * use as many different threads as we need, and the rest don't polute
+ * use as many different threads as we need, and the rest don't pollute
* the cache.
*/
static inline void
-svc_serv_enqueue(struct svc_serv *serv, struct svc_rqst *rqstp)
+svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
{
- list_add(&rqstp->rq_list, &serv->sv_threads);
+ list_add(&rqstp->rq_list, &pool->sp_threads);
}
/*
- * Dequeue an nfsd thread. Must have serv->sv_lock held.
+ * Dequeue an nfsd thread. Must have pool->sp_lock held.
*/
static inline void
-svc_serv_dequeue(struct svc_serv *serv, struct svc_rqst *rqstp)
+svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
{
list_del(&rqstp->rq_list);
}
@@ -140,7 +151,9 @@ static void
svc_sock_enqueue(struct svc_sock *svsk)
{
struct svc_serv *serv = svsk->sk_server;
+ struct svc_pool *pool;
struct svc_rqst *rqstp;
+ int cpu;
if (!(svsk->sk_flags &
( (1<<SK_CONN)|(1<<SK_DATA)|(1<<SK_CLOSE)|(1<<SK_DEFERRED)) ))
@@ -148,10 +161,14 @@ svc_sock_enqueue(struct svc_sock *svsk)
if (test_bit(SK_DEAD, &svsk->sk_flags))
return;
- spin_lock_bh(&serv->sv_lock);
+ cpu = get_cpu();
+ pool = svc_pool_for_cpu(svsk->sk_server, cpu);
+ put_cpu();
+
+ spin_lock_bh(&pool->sp_lock);
- if (!list_empty(&serv->sv_threads) &&
- !list_empty(&serv->sv_sockets))
+ if (!list_empty(&pool->sp_threads) &&
+ !list_empty(&pool->sp_sockets))
printk(KERN_ERR
"svc_sock_enqueue: threads and sockets both waiting??\n");
@@ -161,73 +178,79 @@ svc_sock_enqueue(struct svc_sock *svsk)
goto out_unlock;
}
- if (test_bit(SK_BUSY, &svsk->sk_flags)) {
- /* Don't enqueue socket while daemon is receiving */
+ /* Mark socket as busy. It will remain in this state until the
+ * server has processed all pending data and put the socket back
+ * on the idle list. We update SK_BUSY atomically because
+ * it also guards against trying to enqueue the svc_sock twice.
+ */
+ if (test_and_set_bit(SK_BUSY, &svsk->sk_flags)) {
+ /* Don't enqueue socket while already enqueued */
dprintk("svc: socket %p busy, not enqueued\n", svsk->sk_sk);
goto out_unlock;
}
+ BUG_ON(svsk->sk_pool != NULL);
+ svsk->sk_pool = pool;
set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
- if (((svsk->sk_reserved + serv->sv_bufsz)*2
+ if (((atomic_read(&svsk->sk_reserved) + serv->sv_bufsz)*2
> svc_sock_wspace(svsk))
&& !test_bit(SK_CLOSE, &svsk->sk_flags)
&& !test_bit(SK_CONN, &svsk->sk_flags)) {
/* Don't enqueue while not enough space for reply */
dprintk("svc: socket %p no space, %d*2 > %ld, not enqueued\n",
- svsk->sk_sk, svsk->sk_reserved+serv->sv_bufsz,
+ svsk->sk_sk, atomic_read(&svsk->sk_reserved)+serv->sv_bufsz,
svc_sock_wspace(svsk));
+ svsk->sk_pool = NULL;
+ clear_bit(SK_BUSY, &svsk->sk_flags);
goto out_unlock;
}
clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
- /* Mark socket as busy. It will remain in this state until the
- * server has processed all pending data and put the socket back
- * on the idle list.
- */
- set_bit(SK_BUSY, &svsk->sk_flags);
- if (!list_empty(&serv->sv_threads)) {
- rqstp = list_entry(serv->sv_threads.next,
+ if (!list_empty(&pool->sp_threads)) {
+ rqstp = list_entry(pool->sp_threads.next,
struct svc_rqst,
rq_list);
dprintk("svc: socket %p served by daemon %p\n",
svsk->sk_sk, rqstp);
- svc_serv_dequeue(serv, rqstp);
+ svc_thread_dequeue(pool, rqstp);
if (rqstp->rq_sock)
printk(KERN_ERR
"svc_sock_enqueue: server %p, rq_sock=%p!\n",
rqstp, rqstp->rq_sock);
rqstp->rq_sock = svsk;
- svsk->sk_inuse++;
+ atomic_inc(&svsk->sk_inuse);
rqstp->rq_reserved = serv->sv_bufsz;
- svsk->sk_reserved += rqstp->rq_reserved;
+ atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
+ BUG_ON(svsk->sk_pool != pool);
wake_up(&rqstp->rq_wait);
} else {
dprintk("svc: socket %p put into queue\n", svsk->sk_sk);
- list_add_tail(&svsk->sk_ready, &serv->sv_sockets);
+ list_add_tail(&svsk->sk_ready, &pool->sp_sockets);
+ BUG_ON(svsk->sk_pool != pool);
}
out_unlock:
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&pool->sp_lock);
}
/*
- * Dequeue the first socket. Must be called with the serv->sv_lock held.
+ * Dequeue the first socket. Must be called with the pool->sp_lock held.
*/
static inline struct svc_sock *
-svc_sock_dequeue(struct svc_serv *serv)
+svc_sock_dequeue(struct svc_pool *pool)
{
struct svc_sock *svsk;
- if (list_empty(&serv->sv_sockets))
+ if (list_empty(&pool->sp_sockets))
return NULL;
- svsk = list_entry(serv->sv_sockets.next,
+ svsk = list_entry(pool->sp_sockets.next,
struct svc_sock, sk_ready);
list_del_init(&svsk->sk_ready);
dprintk("svc: socket %p dequeued, inuse=%d\n",
- svsk->sk_sk, svsk->sk_inuse);
+ svsk->sk_sk, atomic_read(&svsk->sk_inuse));
return svsk;
}
@@ -241,6 +264,7 @@ svc_sock_dequeue(struct svc_serv *serv)
static inline void
svc_sock_received(struct svc_sock *svsk)
{
+ svsk->sk_pool = NULL;
clear_bit(SK_BUSY, &svsk->sk_flags);
svc_sock_enqueue(svsk);
}
@@ -262,10 +286,8 @@ void svc_reserve(struct svc_rqst *rqstp, int space)
if (space < rqstp->rq_reserved) {
struct svc_sock *svsk = rqstp->rq_sock;
- spin_lock_bh(&svsk->sk_server->sv_lock);
- svsk->sk_reserved -= (rqstp->rq_reserved - space);
+ atomic_sub((rqstp->rq_reserved - space), &svsk->sk_reserved);
rqstp->rq_reserved = space;
- spin_unlock_bh(&svsk->sk_server->sv_lock);
svc_sock_enqueue(svsk);
}
@@ -277,17 +299,11 @@ void svc_reserve(struct svc_rqst *rqstp, int space)
static inline void
svc_sock_put(struct svc_sock *svsk)
{
- struct svc_serv *serv = svsk->sk_server;
-
- spin_lock_bh(&serv->sv_lock);
- if (!--(svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) {
- spin_unlock_bh(&serv->sv_lock);
+ if (atomic_dec_and_test(&svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) {
dprintk("svc: releasing dead socket\n");
sock_release(svsk->sk_sock);
kfree(svsk);
}
- else
- spin_unlock_bh(&serv->sv_lock);
}
static void
@@ -321,25 +337,33 @@ svc_sock_release(struct svc_rqst *rqstp)
/*
* External function to wake up a server waiting for data
+ * This really only makes sense for services like lockd
+ * which have exactly one thread anyway.
*/
void
svc_wake_up(struct svc_serv *serv)
{
struct svc_rqst *rqstp;
-
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&serv->sv_threads)) {
- rqstp = list_entry(serv->sv_threads.next,
- struct svc_rqst,
- rq_list);
- dprintk("svc: daemon %p woken up.\n", rqstp);
- /*
- svc_serv_dequeue(serv, rqstp);
- rqstp->rq_sock = NULL;
- */
- wake_up(&rqstp->rq_wait);
+ unsigned int i;
+ struct svc_pool *pool;
+
+ for (i = 0; i < serv->sv_nrpools; i++) {
+ pool = &serv->sv_pools[i];
+
+ spin_lock_bh(&pool->sp_lock);
+ if (!list_empty(&pool->sp_threads)) {
+ rqstp = list_entry(pool->sp_threads.next,
+ struct svc_rqst,
+ rq_list);
+ dprintk("svc: daemon %p woken up.\n", rqstp);
+ /*
+ svc_thread_dequeue(pool, rqstp);
+ rqstp->rq_sock = NULL;
+ */
+ wake_up(&rqstp->rq_wait);
+ }
+ spin_unlock_bh(&pool->sp_lock);
}
- spin_unlock_bh(&serv->sv_lock);
}
/*
@@ -388,7 +412,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
/* send head */
if (slen == xdr->head[0].iov_len)
flags = 0;
- len = sock->ops->sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags);
+ len = kernel_sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags);
if (len != xdr->head[0].iov_len)
goto out;
slen -= xdr->head[0].iov_len;
@@ -400,7 +424,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
while (pglen > 0) {
if (slen == size)
flags = 0;
- result = sock->ops->sendpage(sock, *ppage, base, size, flags);
+ result = kernel_sendpage(sock, *ppage, base, size, flags);
if (result > 0)
len += result;
if (result != size)
@@ -413,7 +437,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
}
/* send tail */
if (xdr->tail[0].iov_len) {
- result = sock->ops->sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage],
+ result = kernel_sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage],
((unsigned long)xdr->tail[0].iov_base)& (PAGE_SIZE-1),
xdr->tail[0].iov_len, 0);
@@ -429,18 +453,60 @@ out:
}
/*
+ * Report socket names for nfsdfs
+ */
+static int one_sock_name(char *buf, struct svc_sock *svsk)
+{
+ int len;
+
+ switch(svsk->sk_sk->sk_family) {
+ case AF_INET:
+ len = sprintf(buf, "ipv4 %s %u.%u.%u.%u %d\n",
+ svsk->sk_sk->sk_protocol==IPPROTO_UDP?
+ "udp" : "tcp",
+ NIPQUAD(inet_sk(svsk->sk_sk)->rcv_saddr),
+ inet_sk(svsk->sk_sk)->num);
+ break;
+ default:
+ len = sprintf(buf, "*unknown-%d*\n",
+ svsk->sk_sk->sk_family);
+ }
+ return len;
+}
+
+int
+svc_sock_names(char *buf, struct svc_serv *serv, char *toclose)
+{
+ struct svc_sock *svsk, *closesk = NULL;
+ int len = 0;
+
+ if (!serv)
+ return 0;
+ spin_lock(&serv->sv_lock);
+ list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) {
+ int onelen = one_sock_name(buf+len, svsk);
+ if (toclose && strcmp(toclose, buf+len) == 0)
+ closesk = svsk;
+ else
+ len += onelen;
+ }
+ spin_unlock(&serv->sv_lock);
+ if (closesk)
+ svc_delete_socket(closesk);
+ return len;
+}
+EXPORT_SYMBOL(svc_sock_names);
+
+/*
* Check input queue length
*/
static int
svc_recv_available(struct svc_sock *svsk)
{
- mm_segment_t oldfs;
struct socket *sock = svsk->sk_sock;
int avail, err;
- oldfs = get_fs(); set_fs(KERNEL_DS);
- err = sock->ops->ioctl(sock, TIOCINQ, (unsigned long) &avail);
- set_fs(oldfs);
+ err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);
return (err >= 0)? avail : err;
}
@@ -472,7 +538,7 @@ svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
* at accept time. FIXME
*/
alen = sizeof(rqstp->rq_addr);
- sock->ops->getname(sock, (struct sockaddr *)&rqstp->rq_addr, &alen, 1);
+ kernel_getpeername(sock, (struct sockaddr *)&rqstp->rq_addr, &alen);
dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
rqstp->rq_sock, iov[0].iov_base, iov[0].iov_len, len);
@@ -560,7 +626,10 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
/* udp sockets need large rcvbuf as all pending
* requests are still in that buffer. sndbuf must
* also be large enough that there is enough space
- * for one reply per thread.
+ * for one reply per thread. We count all threads
+ * rather than threads in a particular pool, which
+ * provides an upper bound on the number of threads
+ * which will access the socket.
*/
svc_sock_setbufsize(svsk->sk_sock,
(serv->sv_nrthreads+3) * serv->sv_bufsz,
@@ -758,7 +827,6 @@ svc_tcp_accept(struct svc_sock *svsk)
struct svc_serv *serv = svsk->sk_server;
struct socket *sock = svsk->sk_sock;
struct socket *newsock;
- const struct proto_ops *ops;
struct svc_sock *newsvsk;
int err, slen;
@@ -766,29 +834,23 @@ svc_tcp_accept(struct svc_sock *svsk)
if (!sock)
return;
- err = sock_create_lite(PF_INET, SOCK_STREAM, IPPROTO_TCP, &newsock);
- if (err) {
+ clear_bit(SK_CONN, &svsk->sk_flags);
+ err = kernel_accept(sock, &newsock, O_NONBLOCK);
+ if (err < 0) {
if (err == -ENOMEM)
printk(KERN_WARNING "%s: no more sockets!\n",
serv->sv_name);
- return;
- }
-
- dprintk("svc: tcp_accept %p allocated\n", newsock);
- newsock->ops = ops = sock->ops;
-
- clear_bit(SK_CONN, &svsk->sk_flags);
- if ((err = ops->accept(sock, newsock, O_NONBLOCK)) < 0) {
- if (err != -EAGAIN && net_ratelimit())
+ else if (err != -EAGAIN && net_ratelimit())
printk(KERN_WARNING "%s: accept failed (err %d)!\n",
serv->sv_name, -err);
- goto failed; /* aborted connection or whatever */
+ return;
}
+
set_bit(SK_CONN, &svsk->sk_flags);
svc_sock_enqueue(svsk);
slen = sizeof(sin);
- err = ops->getname(newsock, (struct sockaddr *) &sin, &slen, 1);
+ err = kernel_getpeername(newsock, (struct sockaddr *) &sin, &slen);
if (err < 0) {
if (net_ratelimit())
printk(KERN_WARNING "%s: peername failed (err %d)!\n",
@@ -854,7 +916,7 @@ svc_tcp_accept(struct svc_sock *svsk)
struct svc_sock,
sk_list);
set_bit(SK_CLOSE, &svsk->sk_flags);
- svsk->sk_inuse ++;
+ atomic_inc(&svsk->sk_inuse);
}
spin_unlock_bh(&serv->sv_lock);
@@ -912,6 +974,11 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
/* sndbuf needs to have room for one request
* per thread, otherwise we can stall even when the
* network isn't a bottleneck.
+ *
+ * We count all threads rather than threads in a
+ * particular pool, which provides an upper bound
+ * on the number of threads which will access the socket.
+ *
* rcvbuf just needs to be able to hold a few requests.
* Normally they will be removed from the queue
* as soon a a complete request arrives.
@@ -1040,7 +1107,7 @@ svc_tcp_sendto(struct svc_rqst *rqstp)
{
struct xdr_buf *xbufp = &rqstp->rq_res;
int sent;
- u32 reclen;
+ __be32 reclen;
/* Set up the first element of the reply kvec.
* Any other kvecs that may be in use have been taken
@@ -1127,12 +1194,16 @@ svc_sock_update_bufs(struct svc_serv *serv)
}
/*
- * Receive the next request on any socket.
+ * Receive the next request on any socket. This code is carefully
+ * organised not to touch any cachelines in the shared svc_serv
+ * structure, only cachelines in the local svc_pool.
*/
int
-svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
+svc_recv(struct svc_rqst *rqstp, long timeout)
{
struct svc_sock *svsk =NULL;
+ struct svc_serv *serv = rqstp->rq_server;
+ struct svc_pool *pool = rqstp->rq_pool;
int len;
int pages;
struct xdr_buf *arg;
@@ -1182,32 +1253,15 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
if (signalled())
return -EINTR;
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&serv->sv_tempsocks)) {
- svsk = list_entry(serv->sv_tempsocks.next,
- struct svc_sock, sk_list);
- /* apparently the "standard" is that clients close
- * idle connections after 5 minutes, servers after
- * 6 minutes
- * http://www.connectathon.org/talks96/nfstcp.pdf
- */
- if (get_seconds() - svsk->sk_lastrecv < 6*60
- || test_bit(SK_BUSY, &svsk->sk_flags))
- svsk = NULL;
- }
- if (svsk) {
- set_bit(SK_BUSY, &svsk->sk_flags);
- set_bit(SK_CLOSE, &svsk->sk_flags);
- rqstp->rq_sock = svsk;
- svsk->sk_inuse++;
- } else if ((svsk = svc_sock_dequeue(serv)) != NULL) {
+ spin_lock_bh(&pool->sp_lock);
+ if ((svsk = svc_sock_dequeue(pool)) != NULL) {
rqstp->rq_sock = svsk;
- svsk->sk_inuse++;
+ atomic_inc(&svsk->sk_inuse);
rqstp->rq_reserved = serv->sv_bufsz;
- svsk->sk_reserved += rqstp->rq_reserved;
+ atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
} else {
/* No data pending. Go to sleep */
- svc_serv_enqueue(serv, rqstp);
+ svc_thread_enqueue(pool, rqstp);
/*
* We have to be able to interrupt this wait
@@ -1215,26 +1269,26 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
*/
set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&rqstp->rq_wait, &wait);
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&pool->sp_lock);
schedule_timeout(timeout);
try_to_freeze();
- spin_lock_bh(&serv->sv_lock);
+ spin_lock_bh(&pool->sp_lock);
remove_wait_queue(&rqstp->rq_wait, &wait);
if (!(svsk = rqstp->rq_sock)) {
- svc_serv_dequeue(serv, rqstp);
- spin_unlock_bh(&serv->sv_lock);
+ svc_thread_dequeue(pool, rqstp);
+ spin_unlock_bh(&pool->sp_lock);
dprintk("svc: server %p, no data yet\n", rqstp);
return signalled()? -EINTR : -EAGAIN;
}
}
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&pool->sp_lock);
- dprintk("svc: server %p, socket %p, inuse=%d\n",
- rqstp, svsk, svsk->sk_inuse);
+ dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
+ rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
len = svsk->sk_recvfrom(rqstp);
dprintk("svc: got len=%d\n", len);
@@ -1245,13 +1299,7 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
return -EAGAIN;
}
svsk->sk_lastrecv = get_seconds();
- if (test_bit(SK_TEMP, &svsk->sk_flags)) {
- /* push active sockets to end of list */
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&svsk->sk_list))
- list_move_tail(&svsk->sk_list, &serv->sv_tempsocks);
- spin_unlock_bh(&serv->sv_lock);
- }
+ clear_bit(SK_OLD, &svsk->sk_flags);
rqstp->rq_secure = ntohs(rqstp->rq_addr.sin_port) < 1024;
rqstp->rq_chandle.defer = svc_defer;
@@ -1311,6 +1359,58 @@ svc_send(struct svc_rqst *rqstp)
}
/*
+ * Timer function to close old temporary sockets, using
+ * a mark-and-sweep algorithm.
+ */
+static void
+svc_age_temp_sockets(unsigned long closure)
+{
+ struct svc_serv *serv = (struct svc_serv *)closure;
+ struct svc_sock *svsk;
+ struct list_head *le, *next;
+ LIST_HEAD(to_be_aged);
+
+ dprintk("svc_age_temp_sockets\n");
+
+ if (!spin_trylock_bh(&serv->sv_lock)) {
+ /* busy, try again 1 sec later */
+ dprintk("svc_age_temp_sockets: busy\n");
+ mod_timer(&serv->sv_temptimer, jiffies + HZ);
+ return;
+ }
+
+ list_for_each_safe(le, next, &serv->sv_tempsocks) {
+ svsk = list_entry(le, struct svc_sock, sk_list);
+
+ if (!test_and_set_bit(SK_OLD, &svsk->sk_flags))
+ continue;
+ if (atomic_read(&svsk->sk_inuse) || test_bit(SK_BUSY, &svsk->sk_flags))
+ continue;
+ atomic_inc(&svsk->sk_inuse);
+ list_move(le, &to_be_aged);
+ set_bit(SK_CLOSE, &svsk->sk_flags);
+ set_bit(SK_DETACHED, &svsk->sk_flags);
+ }
+ spin_unlock_bh(&serv->sv_lock);
+
+ while (!list_empty(&to_be_aged)) {
+ le = to_be_aged.next;
+ /* fiddling the sk_list node is safe 'cos we're SK_DETACHED */
+ list_del_init(le);
+ svsk = list_entry(le, struct svc_sock, sk_list);
+
+ dprintk("queuing svsk %p for closing, %lu seconds old\n",
+ svsk, get_seconds() - svsk->sk_lastrecv);
+
+ /* a thread will dequeue and close it soon */
+ svc_sock_enqueue(svsk);
+ svc_sock_put(svsk);
+ }
+
+ mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
+}
+
+/*
* Initialize socket for RPC use and create svc_sock struct
* XXX: May want to setsockopt SO_SNDBUF and SO_RCVBUF.
*/
@@ -1347,7 +1447,9 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock,
svsk->sk_odata = inet->sk_data_ready;
svsk->sk_owspace = inet->sk_write_space;
svsk->sk_server = serv;
+ atomic_set(&svsk->sk_inuse, 0);
svsk->sk_lastrecv = get_seconds();
+ spin_lock_init(&svsk->sk_defer_lock);
INIT_LIST_HEAD(&svsk->sk_deferred);
INIT_LIST_HEAD(&svsk->sk_ready);
mutex_init(&svsk->sk_mutex);
@@ -1363,6 +1465,13 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock,
set_bit(SK_TEMP, &svsk->sk_flags);
list_add(&svsk->sk_list, &serv->sv_tempsocks);
serv->sv_tmpcnt++;
+ if (serv->sv_temptimer.function == NULL) {
+ /* setup timer to age temp sockets */
+ setup_timer(&serv->sv_temptimer, svc_age_temp_sockets,
+ (unsigned long)serv);
+ mod_timer(&serv->sv_temptimer,
+ jiffies + svc_conn_age_period * HZ);
+ }
} else {
clear_bit(SK_TEMP, &svsk->sk_flags);
list_add(&svsk->sk_list, &serv->sv_permsocks);
@@ -1377,6 +1486,38 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock,
return svsk;
}
+int svc_addsock(struct svc_serv *serv,
+ int fd,
+ char *name_return,
+ int *proto)
+{
+ int err = 0;
+ struct socket *so = sockfd_lookup(fd, &err);
+ struct svc_sock *svsk = NULL;
+
+ if (!so)
+ return err;
+ if (so->sk->sk_family != AF_INET)
+ err = -EAFNOSUPPORT;
+ else if (so->sk->sk_protocol != IPPROTO_TCP &&
+ so->sk->sk_protocol != IPPROTO_UDP)
+ err = -EPROTONOSUPPORT;
+ else if (so->state > SS_UNCONNECTED)
+ err = -EISCONN;
+ else {
+ svsk = svc_setup_socket(serv, so, &err, 1);
+ if (svsk)
+ err = 0;
+ }
+ if (err) {
+ sockfd_put(so);
+ return err;
+ }
+ if (proto) *proto = so->sk->sk_protocol;
+ return one_sock_name(name_return, svsk);
+}
+EXPORT_SYMBOL_GPL(svc_addsock);
+
/*
* Create socket for RPC service.
*/
@@ -1403,17 +1544,15 @@ svc_create_socket(struct svc_serv *serv, int protocol, struct sockaddr_in *sin)
if ((error = sock_create_kern(PF_INET, type, protocol, &sock)) < 0)
return error;
- if (sin != NULL) {
- if (type == SOCK_STREAM)
- sock->sk->sk_reuse = 1; /* allow address reuse */
- error = sock->ops->bind(sock, (struct sockaddr *) sin,
- sizeof(*sin));
- if (error < 0)
- goto bummer;
- }
+ if (type == SOCK_STREAM)
+ sock->sk->sk_reuse = 1; /* allow address reuse */
+ error = kernel_bind(sock, (struct sockaddr *) sin,
+ sizeof(*sin));
+ if (error < 0)
+ goto bummer;
if (protocol == IPPROTO_TCP) {
- if ((error = sock->ops->listen(sock, 64)) < 0)
+ if ((error = kernel_listen(sock, 64)) < 0)
goto bummer;
}
@@ -1446,15 +1585,25 @@ svc_delete_socket(struct svc_sock *svsk)
spin_lock_bh(&serv->sv_lock);
- list_del_init(&svsk->sk_list);
- list_del_init(&svsk->sk_ready);
+ if (!test_and_set_bit(SK_DETACHED, &svsk->sk_flags))
+ list_del_init(&svsk->sk_list);
+ /*
+ * We used to delete the svc_sock from whichever list
+ * it's sk_ready node was on, but we don't actually
+ * need to. This is because the only time we're called
+ * while still attached to a queue, the queue itself
+ * is about to be destroyed (in svc_destroy).
+ */
if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags))
if (test_bit(SK_TEMP, &svsk->sk_flags))
serv->sv_tmpcnt--;
- if (!svsk->sk_inuse) {
+ if (!atomic_read(&svsk->sk_inuse)) {
spin_unlock_bh(&serv->sv_lock);
- sock_release(svsk->sk_sock);
+ if (svsk->sk_sock->file)
+ sockfd_put(svsk->sk_sock);
+ else
+ sock_release(svsk->sk_sock);
kfree(svsk);
} else {
spin_unlock_bh(&serv->sv_lock);
@@ -1485,7 +1634,6 @@ svc_makesock(struct svc_serv *serv, int protocol, unsigned short port)
static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
{
struct svc_deferred_req *dr = container_of(dreq, struct svc_deferred_req, handle);
- struct svc_serv *serv = dreq->owner;
struct svc_sock *svsk;
if (too_many) {
@@ -1496,9 +1644,9 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
dprintk("revisit queued\n");
svsk = dr->svsk;
dr->svsk = NULL;
- spin_lock_bh(&serv->sv_lock);
+ spin_lock_bh(&svsk->sk_defer_lock);
list_add(&dr->handle.recent, &svsk->sk_deferred);
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&svsk->sk_defer_lock);
set_bit(SK_DEFERRED, &svsk->sk_flags);
svc_sock_enqueue(svsk);
svc_sock_put(svsk);
@@ -1530,10 +1678,8 @@ svc_defer(struct cache_req *req)
dr->argslen = rqstp->rq_arg.len >> 2;
memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip, dr->argslen<<2);
}
- spin_lock_bh(&rqstp->rq_server->sv_lock);
- rqstp->rq_sock->sk_inuse++;
+ atomic_inc(&rqstp->rq_sock->sk_inuse);
dr->svsk = rqstp->rq_sock;
- spin_unlock_bh(&rqstp->rq_server->sv_lock);
dr->handle.revisit = svc_revisit;
return &dr->handle;
@@ -1560,11 +1706,10 @@ static int svc_deferred_recv(struct svc_rqst *rqstp)
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
{
struct svc_deferred_req *dr = NULL;
- struct svc_serv *serv = svsk->sk_server;
if (!test_bit(SK_DEFERRED, &svsk->sk_flags))
return NULL;
- spin_lock_bh(&serv->sv_lock);
+ spin_lock_bh(&svsk->sk_defer_lock);
clear_bit(SK_DEFERRED, &svsk->sk_flags);
if (!list_empty(&svsk->sk_deferred)) {
dr = list_entry(svsk->sk_deferred.next,
@@ -1573,6 +1718,6 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
list_del_init(&dr->handle.recent);
set_bit(SK_DEFERRED, &svsk->sk_flags);
}
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&svsk->sk_defer_lock);
return dr;
}
diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c
index bcbdf6430d5..8142fdb8a93 100644
--- a/net/sunrpc/timer.c
+++ b/net/sunrpc/timer.c
@@ -19,8 +19,6 @@
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
-#include <linux/sunrpc/timer.h>
#define RPC_RTO_MAX (60*HZ)
#define RPC_RTO_INIT (HZ/5)
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 6ac45103a27..9022eb8b37e 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -18,8 +18,8 @@
/*
* XDR functions for basic NFS types
*/
-u32 *
-xdr_encode_netobj(u32 *p, const struct xdr_netobj *obj)
+__be32 *
+xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
{
unsigned int quadlen = XDR_QUADLEN(obj->len);
@@ -29,8 +29,8 @@ xdr_encode_netobj(u32 *p, const struct xdr_netobj *obj)
return p + XDR_QUADLEN(obj->len);
}
-u32 *
-xdr_decode_netobj(u32 *p, struct xdr_netobj *obj)
+__be32 *
+xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
{
unsigned int len;
@@ -55,7 +55,7 @@ xdr_decode_netobj(u32 *p, struct xdr_netobj *obj)
* Returns the updated current XDR buffer position
*
*/
-u32 *xdr_encode_opaque_fixed(u32 *p, const void *ptr, unsigned int nbytes)
+__be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int nbytes)
{
if (likely(nbytes != 0)) {
unsigned int quadlen = XDR_QUADLEN(nbytes);
@@ -79,21 +79,21 @@ EXPORT_SYMBOL(xdr_encode_opaque_fixed);
*
* Returns the updated current XDR buffer position
*/
-u32 *xdr_encode_opaque(u32 *p, const void *ptr, unsigned int nbytes)
+__be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes)
{
*p++ = htonl(nbytes);
return xdr_encode_opaque_fixed(p, ptr, nbytes);
}
EXPORT_SYMBOL(xdr_encode_opaque);
-u32 *
-xdr_encode_string(u32 *p, const char *string)
+__be32 *
+xdr_encode_string(__be32 *p, const char *string)
{
return xdr_encode_array(p, string, strlen(string));
}
-u32 *
-xdr_decode_string_inplace(u32 *p, char **sp, int *lenp, int maxlen)
+__be32 *
+xdr_decode_string_inplace(__be32 *p, char **sp, int *lenp, int maxlen)
{
unsigned int len;
@@ -432,7 +432,7 @@ xdr_shift_buf(struct xdr_buf *buf, size_t len)
* of the buffer length, and takes care of adjusting the kvec
* length for us.
*/
-void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p)
+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;
@@ -440,8 +440,8 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p)
BUG_ON(scratch_len < 0);
xdr->buf = buf;
xdr->iov = iov;
- xdr->p = (uint32_t *)((char *)iov->iov_base + iov->iov_len);
- xdr->end = (uint32_t *)((char *)iov->iov_base + scratch_len);
+ xdr->p = (__be32 *)((char *)iov->iov_base + iov->iov_len);
+ xdr->end = (__be32 *)((char *)iov->iov_base + scratch_len);
BUG_ON(iov->iov_len > scratch_len);
if (p != xdr->p && p != NULL) {
@@ -465,10 +465,10 @@ EXPORT_SYMBOL(xdr_init_encode);
* bytes of data. If so, update the total xdr_buf length, and
* adjust the length of the current kvec.
*/
-uint32_t * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
+__be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
{
- uint32_t *p = xdr->p;
- uint32_t *q;
+ __be32 *p = xdr->p;
+ __be32 *q;
/* align nbytes on the next 32-bit boundary */
nbytes += 3;
@@ -524,7 +524,7 @@ EXPORT_SYMBOL(xdr_write_pages);
* @buf: pointer to XDR buffer from which to decode data
* @p: current pointer inside XDR buffer
*/
-void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p)
+void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
{
struct kvec *iov = buf->head;
unsigned int len = iov->iov_len;
@@ -534,7 +534,7 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p)
xdr->buf = buf;
xdr->iov = iov;
xdr->p = p;
- xdr->end = (uint32_t *)((char *)iov->iov_base + len);
+ xdr->end = (__be32 *)((char *)iov->iov_base + len);
}
EXPORT_SYMBOL(xdr_init_decode);
@@ -548,10 +548,10 @@ EXPORT_SYMBOL(xdr_init_decode);
* If so return the current pointer, then update the current
* pointer position.
*/
-uint32_t * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
+__be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
{
- uint32_t *p = xdr->p;
- uint32_t *q = p + XDR_QUADLEN(nbytes);
+ __be32 *p = xdr->p;
+ __be32 *q = p + XDR_QUADLEN(nbytes);
if (unlikely(q > xdr->end || q < p))
return NULL;
@@ -599,8 +599,8 @@ void xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
* Position current pointer at beginning of tail, and
* set remaining message length.
*/
- xdr->p = (uint32_t *)((char *)iov->iov_base + padding);
- xdr->end = (uint32_t *)((char *)iov->iov_base + end);
+ xdr->p = (__be32 *)((char *)iov->iov_base + padding);
+ xdr->end = (__be32 *)((char *)iov->iov_base + end);
}
EXPORT_SYMBOL(xdr_read_pages);
@@ -624,8 +624,8 @@ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len)
*/
if (len > PAGE_CACHE_SIZE - xdr->buf->page_base)
len = PAGE_CACHE_SIZE - xdr->buf->page_base;
- xdr->p = (uint32_t *)(kaddr + xdr->buf->page_base);
- xdr->end = (uint32_t *)((char *)xdr->p + len);
+ xdr->p = (__be32 *)(kaddr + xdr->buf->page_base);
+ xdr->end = (__be32 *)((char *)xdr->p + len);
}
EXPORT_SYMBOL(xdr_enter_page);
@@ -743,7 +743,7 @@ out:
int
xdr_decode_word(struct xdr_buf *buf, int base, u32 *obj)
{
- u32 raw;
+ __be32 raw;
int status;
status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj));
@@ -756,7 +756,7 @@ xdr_decode_word(struct xdr_buf *buf, int base, u32 *obj)
int
xdr_encode_word(struct xdr_buf *buf, int base, u32 obj)
{
- u32 raw = htonl(obj);
+ __be32 raw = htonl(obj);
return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj));
}
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index e8c2bc4977f..80857470dc1 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -534,7 +534,7 @@ void xprt_connect(struct rpc_task *task)
dprintk("RPC: %4d xprt_connect xprt %p %s connected\n", task->tk_pid,
xprt, (xprt_connected(xprt) ? "is" : "is not"));
- if (!xprt->addr.sin_port) {
+ if (!xprt_bound(xprt)) {
task->tk_status = -EIO;
return;
}
@@ -585,13 +585,6 @@ static void xprt_connect_status(struct rpc_task *task)
task->tk_pid, -task->tk_status, task->tk_client->cl_server);
xprt_release_write(xprt, task);
task->tk_status = -EIO;
- return;
- }
-
- /* if soft mounted, just cause this RPC to fail */
- if (RPC_IS_SOFT(task)) {
- xprt_release_write(xprt, task);
- task->tk_status = -EIO;
}
}
@@ -601,7 +594,7 @@ static void xprt_connect_status(struct rpc_task *task)
* @xid: RPC XID of incoming reply
*
*/
-struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid)
+struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid)
{
struct list_head *pos;
@@ -808,7 +801,7 @@ void xprt_reserve(struct rpc_task *task)
spin_unlock(&xprt->reserve_lock);
}
-static inline u32 xprt_alloc_xid(struct rpc_xprt *xprt)
+static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
{
return xprt->xid++;
}
@@ -829,6 +822,7 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt)
req->rq_bufsize = 0;
req->rq_xid = xprt_alloc_xid(xprt);
req->rq_release_snd_buf = NULL;
+ xprt_reset_majortimeo(req);
dprintk("RPC: %4d reserved req %p xid %08x\n", task->tk_pid,
req, ntohl(req->rq_xid));
}
@@ -887,16 +881,32 @@ void xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long i
to->to_exponential = 0;
}
-static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc_timeout *to)
+/**
+ * xprt_create_transport - create an RPC transport
+ * @proto: requested transport protocol
+ * @ap: remote peer address
+ * @size: length of address
+ * @to: timeout parameters
+ *
+ */
+struct rpc_xprt *xprt_create_transport(int proto, struct sockaddr *ap, size_t size, struct rpc_timeout *to)
{
int result;
struct rpc_xprt *xprt;
struct rpc_rqst *req;
- if ((xprt = kzalloc(sizeof(struct rpc_xprt), GFP_KERNEL)) == NULL)
+ if ((xprt = kzalloc(sizeof(struct rpc_xprt), GFP_KERNEL)) == NULL) {
+ dprintk("RPC: xprt_create_transport: no memory\n");
return ERR_PTR(-ENOMEM);
-
- xprt->addr = *ap;
+ }
+ if (size <= sizeof(xprt->addr)) {
+ memcpy(&xprt->addr, ap, size);
+ xprt->addrlen = size;
+ } else {
+ kfree(xprt);
+ dprintk("RPC: xprt_create_transport: address too large\n");
+ return ERR_PTR(-EBADF);
+ }
switch (proto) {
case IPPROTO_UDP:
@@ -908,14 +918,15 @@ static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc
default:
printk(KERN_ERR "RPC: unrecognized transport protocol: %d\n",
proto);
- result = -EIO;
- break;
+ return ERR_PTR(-EIO);
}
if (result) {
kfree(xprt);
+ dprintk("RPC: xprt_create_transport: failed, %d\n", result);
return ERR_PTR(result);
}
+ kref_init(&xprt->kref);
spin_lock_init(&xprt->transport_lock);
spin_lock_init(&xprt->reserve_lock);
@@ -928,6 +939,7 @@ static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc
xprt->last_used = jiffies;
xprt->cwnd = RPC_INITCWND;
+ rpc_init_wait_queue(&xprt->binding, "xprt_binding");
rpc_init_wait_queue(&xprt->pending, "xprt_pending");
rpc_init_wait_queue(&xprt->sending, "xprt_sending");
rpc_init_wait_queue(&xprt->resend, "xprt_resend");
@@ -941,41 +953,43 @@ static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc
dprintk("RPC: created transport %p with %u slots\n", xprt,
xprt->max_reqs);
-
- return xprt;
-}
-/**
- * xprt_create_proto - create an RPC client transport
- * @proto: requested transport protocol
- * @sap: remote peer's address
- * @to: timeout parameters for new transport
- *
- */
-struct rpc_xprt *xprt_create_proto(int proto, struct sockaddr_in *sap, struct rpc_timeout *to)
-{
- struct rpc_xprt *xprt;
-
- xprt = xprt_setup(proto, sap, to);
- if (IS_ERR(xprt))
- dprintk("RPC: xprt_create_proto failed\n");
- else
- dprintk("RPC: xprt_create_proto created xprt %p\n", xprt);
return xprt;
}
/**
* xprt_destroy - destroy an RPC transport, killing off all requests.
- * @xprt: transport to destroy
+ * @kref: kref for the transport to destroy
*
*/
-int xprt_destroy(struct rpc_xprt *xprt)
+static void xprt_destroy(struct kref *kref)
{
+ struct rpc_xprt *xprt = container_of(kref, struct rpc_xprt, kref);
+
dprintk("RPC: destroying transport %p\n", xprt);
xprt->shutdown = 1;
del_timer_sync(&xprt->timer);
xprt->ops->destroy(xprt);
kfree(xprt);
+}
- return 0;
+/**
+ * xprt_put - release a reference to an RPC transport.
+ * @xprt: pointer to the transport
+ *
+ */
+void xprt_put(struct rpc_xprt *xprt)
+{
+ kref_put(&xprt->kref, xprt_destroy);
+}
+
+/**
+ * xprt_get - return a reference to an RPC transport.
+ * @xprt: pointer to the transport
+ *
+ */
+struct rpc_xprt *xprt_get(struct rpc_xprt *xprt)
+{
+ kref_get(&xprt->kref);
+ return xprt;
}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 441bd53f5ec..28100e01922 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -125,6 +125,47 @@ static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)
}
#endif
+static void xs_format_peer_addresses(struct rpc_xprt *xprt)
+{
+ struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
+ char *buf;
+
+ buf = kzalloc(20, GFP_KERNEL);
+ if (buf) {
+ snprintf(buf, 20, "%u.%u.%u.%u",
+ NIPQUAD(addr->sin_addr.s_addr));
+ }
+ xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
+
+ buf = kzalloc(8, GFP_KERNEL);
+ if (buf) {
+ snprintf(buf, 8, "%u",
+ ntohs(addr->sin_port));
+ }
+ xprt->address_strings[RPC_DISPLAY_PORT] = buf;
+
+ if (xprt->prot == IPPROTO_UDP)
+ xprt->address_strings[RPC_DISPLAY_PROTO] = "udp";
+ else
+ xprt->address_strings[RPC_DISPLAY_PROTO] = "tcp";
+
+ buf = kzalloc(48, GFP_KERNEL);
+ if (buf) {
+ snprintf(buf, 48, "addr=%u.%u.%u.%u port=%u proto=%s",
+ NIPQUAD(addr->sin_addr.s_addr),
+ ntohs(addr->sin_port),
+ xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
+ }
+ xprt->address_strings[RPC_DISPLAY_ALL] = buf;
+}
+
+static void xs_free_peer_addresses(struct rpc_xprt *xprt)
+{
+ kfree(xprt->address_strings[RPC_DISPLAY_ADDR]);
+ kfree(xprt->address_strings[RPC_DISPLAY_PORT]);
+ kfree(xprt->address_strings[RPC_DISPLAY_ALL]);
+}
+
#define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL)
static inline int xs_send_head(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, unsigned int len)
@@ -174,7 +215,6 @@ static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int a
struct page **ppage = xdr->pages;
unsigned int len, pglen = xdr->page_len;
int err, ret = 0;
- ssize_t (*sendpage)(struct socket *, struct page *, int, size_t, int);
if (unlikely(!sock))
return -ENOTCONN;
@@ -207,7 +247,6 @@ static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int a
base &= ~PAGE_CACHE_MASK;
}
- sendpage = sock->ops->sendpage ? : sock_no_sendpage;
do {
int flags = XS_SENDMSG_FLAGS;
@@ -220,10 +259,7 @@ static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int a
if (pglen != len || xdr->tail[0].iov_len != 0)
flags |= MSG_MORE;
- /* Hmm... We might be dealing with highmem pages */
- if (PageHighMem(*ppage))
- sendpage = sock_no_sendpage;
- err = sendpage(sock, *ppage, base, len, flags);
+ err = kernel_sendpage(sock, *ppage, base, len, flags);
if (ret == 0)
ret = err;
else if (err > 0)
@@ -300,7 +336,7 @@ static int xs_udp_send_request(struct rpc_task *task)
req->rq_xtime = jiffies;
status = xs_sendpages(xprt->sock, (struct sockaddr *) &xprt->addr,
- sizeof(xprt->addr), xdr, req->rq_bytes_sent);
+ xprt->addrlen, xdr, req->rq_bytes_sent);
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
@@ -490,6 +526,7 @@ static void xs_destroy(struct rpc_xprt *xprt)
xprt_disconnect(xprt);
xs_close(xprt);
+ xs_free_peer_addresses(xprt);
kfree(xprt->slot);
}
@@ -511,7 +548,8 @@ static void xs_udp_data_ready(struct sock *sk, int len)
struct rpc_rqst *rovr;
struct sk_buff *skb;
int err, repsize, copied;
- u32 _xid, *xp;
+ u32 _xid;
+ __be32 *xp;
read_lock(&sk->sk_callback_lock);
dprintk("RPC: xs_udp_data_ready...\n");
@@ -965,6 +1003,19 @@ static unsigned short xs_get_random_port(void)
}
/**
+ * xs_print_peer_address - format an IPv4 address for printing
+ * @xprt: generic transport
+ * @format: flags field indicating which parts of the address to render
+ */
+static char *xs_print_peer_address(struct rpc_xprt *xprt, enum rpc_display_format_t format)
+{
+ if (xprt->address_strings[format] != NULL)
+ return xprt->address_strings[format];
+ else
+ return "unprintable";
+}
+
+/**
* xs_set_port - reset the port number in the remote endpoint address
* @xprt: generic transport
* @port: new port number
@@ -972,8 +1023,11 @@ static unsigned short xs_get_random_port(void)
*/
static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
{
+ struct sockaddr_in *sap = (struct sockaddr_in *) &xprt->addr;
+
dprintk("RPC: setting port for xprt %p to %u\n", xprt, port);
- xprt->addr.sin_port = htons(port);
+
+ sap->sin_port = htons(port);
}
static int xs_bindresvport(struct rpc_xprt *xprt, struct socket *sock)
@@ -986,7 +1040,7 @@ static int xs_bindresvport(struct rpc_xprt *xprt, struct socket *sock)
do {
myaddr.sin_port = htons(port);
- err = sock->ops->bind(sock, (struct sockaddr *) &myaddr,
+ err = kernel_bind(sock, (struct sockaddr *) &myaddr,
sizeof(myaddr));
if (err == 0) {
xprt->port = port;
@@ -1016,11 +1070,9 @@ static void xs_udp_connect_worker(void *args)
struct socket *sock = xprt->sock;
int err, status = -EIO;
- if (xprt->shutdown || xprt->addr.sin_port == 0)
+ if (xprt->shutdown || !xprt_bound(xprt))
goto out;
- dprintk("RPC: xs_udp_connect_worker for xprt %p\n", xprt);
-
/* Start by resetting any existing state */
xs_close(xprt);
@@ -1034,6 +1086,9 @@ static void xs_udp_connect_worker(void *args)
goto out;
}
+ dprintk("RPC: worker connecting xprt %p to address: %s\n",
+ xprt, xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
if (!xprt->inet) {
struct sock *sk = sock->sk;
@@ -1081,7 +1136,7 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt)
*/
memset(&any, 0, sizeof(any));
any.sa_family = AF_UNSPEC;
- result = sock->ops->connect(sock, &any, sizeof(any), 0);
+ result = kernel_connect(sock, &any, sizeof(any), 0);
if (result)
dprintk("RPC: AF_UNSPEC connect return code %d\n",
result);
@@ -1099,11 +1154,9 @@ static void xs_tcp_connect_worker(void *args)
struct socket *sock = xprt->sock;
int err, status = -EIO;
- if (xprt->shutdown || xprt->addr.sin_port == 0)
+ if (xprt->shutdown || !xprt_bound(xprt))
goto out;
- dprintk("RPC: xs_tcp_connect_worker for xprt %p\n", xprt);
-
if (!xprt->sock) {
/* start from scratch */
if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
@@ -1119,6 +1172,9 @@ static void xs_tcp_connect_worker(void *args)
/* "close" the socket, preserving the local port */
xs_tcp_reuse_connection(xprt);
+ dprintk("RPC: worker connecting xprt %p to address: %s\n",
+ xprt, xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
if (!xprt->inet) {
struct sock *sk = sock->sk;
@@ -1151,8 +1207,8 @@ static void xs_tcp_connect_worker(void *args)
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
- status = sock->ops->connect(sock, (struct sockaddr *) &xprt->addr,
- sizeof(xprt->addr), O_NONBLOCK);
+ status = kernel_connect(sock, (struct sockaddr *) &xprt->addr,
+ xprt->addrlen, O_NONBLOCK);
dprintk("RPC: %p connect status %d connected %d sock state %d\n",
xprt, -status, xprt_connected(xprt), sock->sk->sk_state);
if (status < 0) {
@@ -1260,8 +1316,10 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
static struct rpc_xprt_ops xs_udp_ops = {
.set_buffer_size = xs_udp_set_buffer_size,
+ .print_addr = xs_print_peer_address,
.reserve_xprt = xprt_reserve_xprt_cong,
.release_xprt = xprt_release_xprt_cong,
+ .rpcbind = rpc_getport,
.set_port = xs_set_port,
.connect = xs_connect,
.buf_alloc = rpc_malloc,
@@ -1276,8 +1334,10 @@ static struct rpc_xprt_ops xs_udp_ops = {
};
static struct rpc_xprt_ops xs_tcp_ops = {
+ .print_addr = xs_print_peer_address,
.reserve_xprt = xprt_reserve_xprt,
.release_xprt = xs_tcp_release_xprt,
+ .rpcbind = rpc_getport,
.set_port = xs_set_port,
.connect = xs_connect,
.buf_alloc = rpc_malloc,
@@ -1298,8 +1358,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
{
size_t slot_table_size;
-
- dprintk("RPC: setting up udp-ipv4 transport...\n");
+ struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
xprt->max_reqs = xprt_udp_slot_table_entries;
slot_table_size = xprt->max_reqs * sizeof(xprt->slot[0]);
@@ -1307,10 +1366,12 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
if (xprt->slot == NULL)
return -ENOMEM;
- xprt->prot = IPPROTO_UDP;
+ if (ntohs(addr->sin_port != 0))
+ xprt_set_bound(xprt);
xprt->port = xs_get_random_port();
+
+ xprt->prot = IPPROTO_UDP;
xprt->tsh_size = 0;
- xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0;
/* XXX: header size can vary due to auth type, IPv6, etc. */
xprt->max_payload = (1U << 16) - (MAX_HEADER << 3);
@@ -1327,6 +1388,10 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
else
xprt_set_timeout(&xprt->timeout, 5, 5 * HZ);
+ xs_format_peer_addresses(xprt);
+ dprintk("RPC: set up transport to address %s\n",
+ xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
return 0;
}
@@ -1339,8 +1404,7 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
{
size_t slot_table_size;
-
- dprintk("RPC: setting up tcp-ipv4 transport...\n");
+ struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
xprt->max_reqs = xprt_tcp_slot_table_entries;
slot_table_size = xprt->max_reqs * sizeof(xprt->slot[0]);
@@ -1348,10 +1412,12 @@ int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
if (xprt->slot == NULL)
return -ENOMEM;
- xprt->prot = IPPROTO_TCP;
+ if (ntohs(addr->sin_port) != 0)
+ xprt_set_bound(xprt);
xprt->port = xs_get_random_port();
+
+ xprt->prot = IPPROTO_TCP;
xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
- xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0;
xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
INIT_WORK(&xprt->connect_worker, xs_tcp_connect_worker, xprt);
@@ -1367,5 +1433,9 @@ int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
else
xprt_set_timeout(&xprt->timeout, 2, 60 * HZ);
+ xs_format_peer_addresses(xprt);
+ dprintk("RPC: set up transport to address %s\n",
+ xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
return 0;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-01-06 23:55:33 +0000