summaryrefslogtreecommitdiff
path: root/net/sunrpc
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-10-26 09:55:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-10-26 09:55:25 -0700
commit4390110fef9e5c64e10c6ca19d586932242c9a8a (patch)
treef2f26fe291c8b4e424b97ac57370b33e0c006568 /net/sunrpc
parenta4dd8dce14014665862ce7911b38cb2c69e366dd (diff)
parent42d7ba3d6d56a6cbc773284896108b1e2ebcee81 (diff)
Merge branch 'for-2.6.37' of git://linux-nfs.org/~bfields/linux
* 'for-2.6.37' of git://linux-nfs.org/~bfields/linux: (99 commits) svcrpc: svc_tcp_sendto XPT_DEAD check is redundant svcrpc: no need for XPT_DEAD check in svc_xprt_enqueue svcrpc: assume svc_delete_xprt() called only once svcrpc: never clear XPT_BUSY on dead xprt nfsd4: fix connection allocation in sequence() nfsd4: only require krb5 principal for NFSv4.0 callbacks nfsd4: move minorversion to client nfsd4: delay session removal till free_client nfsd4: separate callback change and callback probe nfsd4: callback program number is per-session nfsd4: track backchannel connections nfsd4: confirm only on succesful create_session nfsd4: make backchannel sequence number per-session nfsd4: use client pointer to backchannel session nfsd4: move callback setup into session init code nfsd4: don't cache seq_misordered replies SUNRPC: Properly initialize sock_xprt.srcaddr in all cases SUNRPC: Use conventional switch statement when reclassifying sockets sunrpc/xprtrdma: clean up workqueue usage sunrpc: Turn list_for_each-s into the ..._entry-s ... Fix up trivial conflicts (two different deprecation notices added in separate branches) in Documentation/feature-removal-schedule.txt
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/Kconfig19
-rw-r--r--net/sunrpc/auth.c2
-rw-r--r--net/sunrpc/auth_generic.c2
-rw-r--r--net/sunrpc/auth_gss/Makefile5
-rw-r--r--net/sunrpc/auth_gss/gss_spkm3_mech.c247
-rw-r--r--net/sunrpc/auth_gss/gss_spkm3_seal.c186
-rw-r--r--net/sunrpc/auth_gss/gss_spkm3_token.c267
-rw-r--r--net/sunrpc/auth_gss/gss_spkm3_unseal.c127
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c51
-rw-r--r--net/sunrpc/cache.c288
-rw-r--r--net/sunrpc/clnt.c1
-rw-r--r--net/sunrpc/netns.h19
-rw-r--r--net/sunrpc/rpcb_clnt.c4
-rw-r--r--net/sunrpc/stats.c43
-rw-r--r--net/sunrpc/sunrpc_syms.c58
-rw-r--r--net/sunrpc/svc.c3
-rw-r--r--net/sunrpc/svc_xprt.c59
-rw-r--r--net/sunrpc/svcauth_unix.c194
-rw-r--r--net/sunrpc/svcsock.c27
-rw-r--r--net/sunrpc/xprt.c39
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma.c11
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_recvfrom.c19
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c82
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c49
-rw-r--r--net/sunrpc/xprtrdma/transport.c25
-rw-r--r--net/sunrpc/xprtsock.c358
26 files changed, 785 insertions, 1400 deletions
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 3376d7657185..8873fd8ddacd 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -36,22 +36,3 @@ config RPCSEC_GSS_KRB5
Kerberos support should be installed.
If unsure, say Y.
-
-config RPCSEC_GSS_SPKM3
- tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)"
- depends on SUNRPC && EXPERIMENTAL
- select SUNRPC_GSS
- select CRYPTO
- select CRYPTO_MD5
- select CRYPTO_DES
- select CRYPTO_CAST5
- select CRYPTO_CBC
- help
- Choose Y here to enable Secure RPC using the SPKM3 public key
- GSS-API mechanism (RFC 2025).
-
- Secure RPC calls with SPKM3 require an auxiliary userspace
- daemon which may be found in the Linux nfs-utils package
- available from http://linux-nfs.org/.
-
- If unsure, say N.
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 68192e562749..afe67849269f 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -658,7 +658,7 @@ out1:
return err;
}
-void __exit rpcauth_remove_module(void)
+void rpcauth_remove_module(void)
{
rpc_destroy_authunix();
rpc_destroy_generic_auth();
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 43162bb3b78f..e010a015d996 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -158,7 +158,7 @@ int __init rpc_init_generic_auth(void)
return rpcauth_init_credcache(&generic_auth);
}
-void __exit rpc_destroy_generic_auth(void)
+void rpc_destroy_generic_auth(void)
{
rpcauth_destroy_credcache(&generic_auth);
}
diff --git a/net/sunrpc/auth_gss/Makefile b/net/sunrpc/auth_gss/Makefile
index 74a231735f67..7350d86a32ee 100644
--- a/net/sunrpc/auth_gss/Makefile
+++ b/net/sunrpc/auth_gss/Makefile
@@ -11,8 +11,3 @@ obj-$(CONFIG_RPCSEC_GSS_KRB5) += rpcsec_gss_krb5.o
rpcsec_gss_krb5-objs := gss_krb5_mech.o gss_krb5_seal.o gss_krb5_unseal.o \
gss_krb5_seqnum.o gss_krb5_wrap.o gss_krb5_crypto.o gss_krb5_keys.o
-
-obj-$(CONFIG_RPCSEC_GSS_SPKM3) += rpcsec_gss_spkm3.o
-
-rpcsec_gss_spkm3-objs := gss_spkm3_mech.o gss_spkm3_seal.o gss_spkm3_unseal.o \
- gss_spkm3_token.o
diff --git a/net/sunrpc/auth_gss/gss_spkm3_mech.c b/net/sunrpc/auth_gss/gss_spkm3_mech.c
deleted file mode 100644
index adade3d313f2..000000000000
--- a/net/sunrpc/auth_gss/gss_spkm3_mech.c
+++ /dev/null
@@ -1,247 +0,0 @@
-/*
- * linux/net/sunrpc/gss_spkm3_mech.c
- *
- * Copyright (c) 2003 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Andy Adamson <andros@umich.edu>
- * J. Bruce Fields <bfields@umich.edu>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the University nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/sunrpc/auth.h>
-#include <linux/in.h>
-#include <linux/sunrpc/svcauth_gss.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/crypto.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY RPCDBG_AUTH
-#endif
-
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, int len)
-{
- const void *q = (const void *)((const char *)p + len);
- if (unlikely(q > end || q < p))
- return ERR_PTR(-EFAULT);
- memcpy(res, p, len);
- return q;
-}
-
-static const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
-{
- const void *q;
- unsigned int len;
- p = simple_get_bytes(p, end, &len, sizeof(len));
- if (IS_ERR(p))
- return p;
- res->len = len;
- if (len == 0) {
- res->data = NULL;
- return p;
- }
- q = (const void *)((const char *)p + len);
- if (unlikely(q > end || q < p))
- return ERR_PTR(-EFAULT);
- res->data = kmemdup(p, len, GFP_NOFS);
- if (unlikely(res->data == NULL))
- return ERR_PTR(-ENOMEM);
- return q;
-}
-
-static int
-gss_import_sec_context_spkm3(const void *p, size_t len,
- struct gss_ctx *ctx_id,
- gfp_t gfp_mask)
-{
- const void *end = (const void *)((const char *)p + len);
- struct spkm3_ctx *ctx;
- int version;
-
- if (!(ctx = kzalloc(sizeof(*ctx), gfp_mask)))
- goto out_err;
-
- p = simple_get_bytes(p, end, &version, sizeof(version));
- if (IS_ERR(p))
- goto out_err_free_ctx;
- if (version != 1) {
- dprintk("RPC: unknown spkm3 token format: "
- "obsolete nfs-utils?\n");
- p = ERR_PTR(-EINVAL);
- goto out_err_free_ctx;
- }
-
- p = simple_get_netobj(p, end, &ctx->ctx_id);
- if (IS_ERR(p))
- goto out_err_free_ctx;
-
- p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime));
- if (IS_ERR(p))
- goto out_err_free_ctx_id;
-
- p = simple_get_netobj(p, end, &ctx->mech_used);
- if (IS_ERR(p))
- goto out_err_free_ctx_id;
-
- p = simple_get_bytes(p, end, &ctx->ret_flags, sizeof(ctx->ret_flags));
- if (IS_ERR(p))
- goto out_err_free_mech;
-
- p = simple_get_netobj(p, end, &ctx->conf_alg);
- if (IS_ERR(p))
- goto out_err_free_mech;
-
- p = simple_get_netobj(p, end, &ctx->derived_conf_key);
- if (IS_ERR(p))
- goto out_err_free_conf_alg;
-
- p = simple_get_netobj(p, end, &ctx->intg_alg);
- if (IS_ERR(p))
- goto out_err_free_conf_key;
-
- p = simple_get_netobj(p, end, &ctx->derived_integ_key);
- if (IS_ERR(p))
- goto out_err_free_intg_alg;
-
- if (p != end) {
- p = ERR_PTR(-EFAULT);
- goto out_err_free_intg_key;
- }
-
- ctx_id->internal_ctx_id = ctx;
-
- dprintk("RPC: Successfully imported new spkm context.\n");
- return 0;
-
-out_err_free_intg_key:
- kfree(ctx->derived_integ_key.data);
-out_err_free_intg_alg:
- kfree(ctx->intg_alg.data);
-out_err_free_conf_key:
- kfree(ctx->derived_conf_key.data);
-out_err_free_conf_alg:
- kfree(ctx->conf_alg.data);
-out_err_free_mech:
- kfree(ctx->mech_used.data);
-out_err_free_ctx_id:
- kfree(ctx->ctx_id.data);
-out_err_free_ctx:
- kfree(ctx);
-out_err:
- return PTR_ERR(p);
-}
-
-static void
-gss_delete_sec_context_spkm3(void *internal_ctx)
-{
- struct spkm3_ctx *sctx = internal_ctx;
-
- kfree(sctx->derived_integ_key.data);
- kfree(sctx->intg_alg.data);
- kfree(sctx->derived_conf_key.data);
- kfree(sctx->conf_alg.data);
- kfree(sctx->mech_used.data);
- kfree(sctx->ctx_id.data);
- kfree(sctx);
-}
-
-static u32
-gss_verify_mic_spkm3(struct gss_ctx *ctx,
- struct xdr_buf *signbuf,
- struct xdr_netobj *checksum)
-{
- u32 maj_stat = 0;
- struct spkm3_ctx *sctx = ctx->internal_ctx_id;
-
- maj_stat = spkm3_read_token(sctx, checksum, signbuf, SPKM_MIC_TOK);
-
- dprintk("RPC: gss_verify_mic_spkm3 returning %d\n", maj_stat);
- return maj_stat;
-}
-
-static u32
-gss_get_mic_spkm3(struct gss_ctx *ctx,
- struct xdr_buf *message_buffer,
- struct xdr_netobj *message_token)
-{
- u32 err = 0;
- struct spkm3_ctx *sctx = ctx->internal_ctx_id;
-
- err = spkm3_make_token(sctx, message_buffer,
- message_token, SPKM_MIC_TOK);
- dprintk("RPC: gss_get_mic_spkm3 returning %d\n", err);
- return err;
-}
-
-static const struct gss_api_ops gss_spkm3_ops = {
- .gss_import_sec_context = gss_import_sec_context_spkm3,
- .gss_get_mic = gss_get_mic_spkm3,
- .gss_verify_mic = gss_verify_mic_spkm3,
- .gss_delete_sec_context = gss_delete_sec_context_spkm3,
-};
-
-static struct pf_desc gss_spkm3_pfs[] = {
- {RPC_AUTH_GSS_SPKM, RPC_GSS_SVC_NONE, "spkm3"},
- {RPC_AUTH_GSS_SPKMI, RPC_GSS_SVC_INTEGRITY, "spkm3i"},
-};
-
-static struct gss_api_mech gss_spkm3_mech = {
- .gm_name = "spkm3",
- .gm_owner = THIS_MODULE,
- .gm_oid = {7, "\053\006\001\005\005\001\003"},
- .gm_ops = &gss_spkm3_ops,
- .gm_pf_num = ARRAY_SIZE(gss_spkm3_pfs),
- .gm_pfs = gss_spkm3_pfs,
-};
-
-static int __init init_spkm3_module(void)
-{
- int status;
-
- status = gss_mech_register(&gss_spkm3_mech);
- if (status)
- printk("Failed to register spkm3 gss mechanism!\n");
- return status;
-}
-
-static void __exit cleanup_spkm3_module(void)
-{
- gss_mech_unregister(&gss_spkm3_mech);
-}
-
-MODULE_LICENSE("GPL");
-module_init(init_spkm3_module);
-module_exit(cleanup_spkm3_module);
diff --git a/net/sunrpc/auth_gss/gss_spkm3_seal.c b/net/sunrpc/auth_gss/gss_spkm3_seal.c
deleted file mode 100644
index 5a3a65a0e2b4..000000000000
--- a/net/sunrpc/auth_gss/gss_spkm3_seal.c
+++ /dev/null
@@ -1,186 +0,0 @@
-/*
- * linux/net/sunrpc/gss_spkm3_seal.c
- *
- * Copyright (c) 2003 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Andy Adamson <andros@umich.edu>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the University nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/jiffies.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/random.h>
-#include <linux/crypto.h>
-#include <linux/pagemap.h>
-#include <linux/scatterlist.h>
-#include <linux/sunrpc/xdr.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY RPCDBG_AUTH
-#endif
-
-const struct xdr_netobj hmac_md5_oid = { 8, "\x2B\x06\x01\x05\x05\x08\x01\x01"};
-const struct xdr_netobj cast5_cbc_oid = {9, "\x2A\x86\x48\x86\xF6\x7D\x07\x42\x0A"};
-
-/*
- * spkm3_make_token()
- *
- * Only SPKM_MIC_TOK with md5 intg-alg is supported
- */
-
-u32
-spkm3_make_token(struct spkm3_ctx *ctx,
- struct xdr_buf * text, struct xdr_netobj * token,
- int toktype)
-{
- s32 checksum_type;
- char tokhdrbuf[25];
- char cksumdata[16];
- struct xdr_netobj md5cksum = {.len = 0, .data = cksumdata};
- struct xdr_netobj mic_hdr = {.len = 0, .data = tokhdrbuf};
- int tokenlen = 0;
- unsigned char *ptr;
- s32 now;
- int ctxelen = 0, ctxzbit = 0;
- int md5elen = 0, md5zbit = 0;
-
- now = jiffies;
-
- if (ctx->ctx_id.len != 16) {
- dprintk("RPC: spkm3_make_token BAD ctx_id.len %d\n",
- ctx->ctx_id.len);
- goto out_err;
- }
-
- if (!g_OID_equal(&ctx->intg_alg, &hmac_md5_oid)) {
- dprintk("RPC: gss_spkm3_seal: unsupported I-ALG "
- "algorithm. only support hmac-md5 I-ALG.\n");
- goto out_err;
- } else
- checksum_type = CKSUMTYPE_HMAC_MD5;
-
- if (!g_OID_equal(&ctx->conf_alg, &cast5_cbc_oid)) {
- dprintk("RPC: gss_spkm3_seal: unsupported C-ALG "
- "algorithm\n");
- goto out_err;
- }
-
- if (toktype == SPKM_MIC_TOK) {
- /* Calculate checksum over the mic-header */
- asn1_bitstring_len(&ctx->ctx_id, &ctxelen, &ctxzbit);
- spkm3_mic_header(&mic_hdr.data, &mic_hdr.len, ctx->ctx_id.data,
- ctxelen, ctxzbit);
- if (make_spkm3_checksum(checksum_type, &ctx->derived_integ_key,
- (char *)mic_hdr.data, mic_hdr.len,
- text, 0, &md5cksum))
- goto out_err;
-
- asn1_bitstring_len(&md5cksum, &md5elen, &md5zbit);
- tokenlen = 10 + ctxelen + 1 + md5elen + 1;
-
- /* Create token header using generic routines */
- token->len = g_token_size(&ctx->mech_used, tokenlen + 2);
-
- ptr = token->data;
- g_make_token_header(&ctx->mech_used, tokenlen + 2, &ptr);
-
- spkm3_make_mic_token(&ptr, tokenlen, &mic_hdr, &md5cksum, md5elen, md5zbit);
- } else if (toktype == SPKM_WRAP_TOK) { /* Not Supported */
- dprintk("RPC: gss_spkm3_seal: SPKM_WRAP_TOK "
- "not supported\n");
- goto out_err;
- }
-
- /* XXX need to implement sequence numbers, and ctx->expired */
-
- return GSS_S_COMPLETE;
-out_err:
- token->data = NULL;
- token->len = 0;
- return GSS_S_FAILURE;
-}
-
-static int
-spkm3_checksummer(struct scatterlist *sg, void *data)
-{
- struct hash_desc *desc = data;
-
- return crypto_hash_update(desc, sg, sg->length);
-}
-
-/* checksum the plaintext data and hdrlen bytes of the token header */
-s32
-make_spkm3_checksum(s32 cksumtype, struct xdr_netobj *key, char *header,
- unsigned int hdrlen, struct xdr_buf *body,
- unsigned int body_offset, struct xdr_netobj *cksum)
-{
- char *cksumname;
- struct hash_desc desc; /* XXX add to ctx? */
- struct scatterlist sg[1];
- int err;
-
- switch (cksumtype) {
- case CKSUMTYPE_HMAC_MD5:
- cksumname = "hmac(md5)";
- break;
- default:
- dprintk("RPC: spkm3_make_checksum:"
- " unsupported checksum %d", cksumtype);
- return GSS_S_FAILURE;
- }
-
- if (key->data == NULL || key->len <= 0) return GSS_S_FAILURE;
-
- desc.tfm = crypto_alloc_hash(cksumname, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(desc.tfm))
- return GSS_S_FAILURE;
- cksum->len = crypto_hash_digestsize(desc.tfm);
- desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-
- err = crypto_hash_setkey(desc.tfm, key->data, key->len);
- if (err)
- goto out;
-
- err = crypto_hash_init(&desc);
- if (err)
- goto out;
-
- sg_init_one(sg, header, hdrlen);
- crypto_hash_update(&desc, sg, sg->length);
-
- xdr_process_buf(body, body_offset, body->len - body_offset,
- spkm3_checksummer, &desc);
- crypto_hash_final(&desc, cksum->data);
-
-out:
- crypto_free_hash(desc.tfm);
-
- return err ? GSS_S_FAILURE : 0;
-}
diff --git a/net/sunrpc/auth_gss/gss_spkm3_token.c b/net/sunrpc/auth_gss/gss_spkm3_token.c
deleted file mode 100644
index a99825d7caa0..000000000000
--- a/net/sunrpc/auth_gss/gss_spkm3_token.c
+++ /dev/null
@@ -1,267 +0,0 @@
-/*
- * linux/net/sunrpc/gss_spkm3_token.c
- *
- * Copyright (c) 2003 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Andy Adamson <andros@umich.edu>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the University nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/jiffies.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/random.h>
-#include <linux/crypto.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY RPCDBG_AUTH
-#endif
-
-/*
- * asn1_bitstring_len()
- *
- * calculate the asn1 bitstring length of the xdr_netobject
- */
-void
-asn1_bitstring_len(struct xdr_netobj *in, int *enclen, int *zerobits)
-{
- int i, zbit = 0,elen = in->len;
- char *ptr;
-
- ptr = &in->data[in->len -1];
-
- /* count trailing 0's */
- for(i = in->len; i > 0; i--) {
- if (*ptr == 0) {
- ptr--;
- elen--;
- } else
- break;
- }
-
- /* count number of 0 bits in final octet */
- ptr = &in->data[elen - 1];
- for(i = 0; i < 8; i++) {
- short mask = 0x01;
-
- if (!((mask << i) & *ptr))
- zbit++;
- else
- break;
- }
- *enclen = elen;
- *zerobits = zbit;
-}
-
-/*
- * decode_asn1_bitstring()
- *
- * decode a bitstring into a buffer of the expected length.
- * enclen = bit string length
- * explen = expected length (define in rfc)
- */
-int
-decode_asn1_bitstring(struct xdr_netobj *out, char *in, int enclen, int explen)
-{
- if (!(out->data = kzalloc(explen,GFP_NOFS)))
- return 0;
- out->len = explen;
- memcpy(out->data, in, enclen);
- return 1;
-}
-
-/*
- * SPKMInnerContextToken choice SPKM_MIC asn1 token layout
- *
- * contextid is always 16 bytes plain data. max asn1 bitstring len = 17.
- *
- * tokenlen = pos[0] to end of token (max pos[45] with MD5 cksum)
- *
- * pos value
- * ----------
- * [0] a4 SPKM-MIC tag
- * [1] ?? innertoken length (max 44)
- *
- *
- * tok_hdr piece of checksum data starts here
- *
- * the maximum mic-header len = 9 + 17 = 26
- * mic-header
- * ----------
- * [2] 30 SEQUENCE tag
- * [3] ?? mic-header length: (max 23) = TokenID + ContextID
- *
- * TokenID - all fields constant and can be hardcoded
- * -------
- * [4] 02 Type 2
- * [5] 02 Length 2
- * [6][7] 01 01 TokenID (SPKM_MIC_TOK)
- *
- * ContextID - encoded length not constant, calculated
- * ---------
- * [8] 03 Type 3
- * [9] ?? encoded length
- * [10] ?? ctxzbit
- * [11] contextid
- *
- * mic_header piece of checksum data ends here.
- *
- * int-cksum - encoded length not constant, calculated
- * ---------
- * [??] 03 Type 3
- * [??] ?? encoded length
- * [??] ?? md5zbit
- * [??] int-cksum (NID_md5 = 16)
- *
- * maximum SPKM-MIC innercontext token length =
- * 10 + encoded contextid_size(17 max) + 2 + encoded
- * cksum_size (17 maxfor NID_md5) = 46
- */
-
-/*
- * spkm3_mic_header()
- *
- * Prepare the SPKM_MIC_TOK mic-header for check-sum calculation
- * elen: 16 byte context id asn1 bitstring encoded length
- */
-void
-spkm3_mic_header(unsigned char **hdrbuf, unsigned int *hdrlen, unsigned char *ctxdata, int elen, int zbit)
-{
- char *hptr = *hdrbuf;
- char *top = *hdrbuf;
-
- *(u8 *)hptr++ = 0x30;
- *(u8 *)hptr++ = elen + 7; /* on the wire header length */
-
- /* tokenid */
- *(u8 *)hptr++ = 0x02;
- *(u8 *)hptr++ = 0x02;
- *(u8 *)hptr++ = 0x01;
- *(u8 *)hptr++ = 0x01;
-
- /* coniextid */
- *(u8 *)hptr++ = 0x03;
- *(u8 *)hptr++ = elen + 1; /* add 1 to include zbit */
- *(u8 *)hptr++ = zbit;
- memcpy(hptr, ctxdata, elen);
- hptr += elen;
- *hdrlen = hptr - top;
-}
-
-/*
- * spkm3_mic_innercontext_token()
- *
- * *tokp points to the beginning of the SPKM_MIC token described
- * in rfc 2025, section 3.2.1:
- *
- * toklen is the inner token length
- */
-void
-spkm3_make_mic_token(unsigned char **tokp, int toklen, struct xdr_netobj *mic_hdr, struct xdr_netobj *md5cksum, int md5elen, int md5zbit)
-{
- unsigned char *ict = *tokp;
-
- *(u8 *)ict++ = 0xa4;
- *(u8 *)ict++ = toklen;
- memcpy(ict, mic_hdr->data, mic_hdr->len);
- ict += mic_hdr->len;
-
- *(u8 *)ict++ = 0x03;
- *(u8 *)ict++ = md5elen + 1; /* add 1 to include zbit */
- *(u8 *)ict++ = md5zbit;
- memcpy(ict, md5cksum->data, md5elen);
-}
-
-u32
-spkm3_verify_mic_token(unsigned char **tokp, int *mic_hdrlen, unsigned char **cksum)
-{
- struct xdr_netobj spkm3_ctx_id = {.len =0, .data = NULL};
- unsigned char *ptr = *tokp;
- int ctxelen;
- u32 ret = GSS_S_DEFECTIVE_TOKEN;
-
- /* spkm3 innercontext token preamble */
- if ((ptr[0] != 0xa4) || (ptr[2] != 0x30)) {
- dprintk("RPC: BAD SPKM ictoken preamble\n");
- goto out;
- }
-
- *mic_hdrlen = ptr[3];
-
- /* token type */
- if ((ptr[4] != 0x02) || (ptr[5] != 0x02)) {
- dprintk("RPC: BAD asn1 SPKM3 token type\n");
- goto out;
- }
-
- /* only support SPKM_MIC_TOK */
- if((ptr[6] != 0x01) || (ptr[7] != 0x01)) {
- dprintk("RPC: ERROR unsupported SPKM3 token\n");
- goto out;
- }
-
- /* contextid */
- if (ptr[8] != 0x03) {
- dprintk("RPC: BAD SPKM3 asn1 context-id type\n");
- goto out;
- }
-
- ctxelen = ptr[9];
- if (ctxelen > 17) { /* length includes asn1 zbit octet */
- dprintk("RPC: BAD SPKM3 contextid len %d\n", ctxelen);
- goto out;
- }
-
- /* ignore ptr[10] */
-
- if(!decode_asn1_bitstring(&spkm3_ctx_id, &ptr[11], ctxelen - 1, 16))
- goto out;
-
- /*
- * in the current implementation: the optional int-alg is not present
- * so the default int-alg (md5) is used the optional snd-seq field is
- * also not present
- */
-
- if (*mic_hdrlen != 6 + ctxelen) {
- dprintk("RPC: BAD SPKM_ MIC_TOK header len %d: we only "
- "support default int-alg (should be absent) "
- "and do not support snd-seq\n", *mic_hdrlen);
- goto out;
- }
- /* checksum */
- *cksum = (&ptr[10] + ctxelen); /* ctxelen includes ptr[10] */
-
- ret = GSS_S_COMPLETE;
-out:
- kfree(spkm3_ctx_id.data);
- return ret;
-}
-
diff --git a/net/sunrpc/auth_gss/gss_spkm3_unseal.c b/net/sunrpc/auth_gss/gss_spkm3_unseal.c
deleted file mode 100644
index cc21ee860bb6..000000000000
--- a/net/sunrpc/auth_gss/gss_spkm3_unseal.c
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * linux/net/sunrpc/gss_spkm3_unseal.c
- *
- * Copyright (c) 2003 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Andy Adamson <andros@umich.edu>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the University nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/jiffies.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/crypto.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY RPCDBG_AUTH
-#endif
-
-/*
- * spkm3_read_token()
- *
- * only SPKM_MIC_TOK with md5 intg-alg is supported
- */
-u32
-spkm3_read_token(struct spkm3_ctx *ctx,
- struct xdr_netobj *read_token, /* checksum */
- struct xdr_buf *message_buffer, /* signbuf */
- int toktype)
-{
- s32 checksum_type;
- s32 code;
- struct xdr_netobj wire_cksum = {.len =0, .data = NULL};
- char cksumdata[16];
- struct xdr_netobj md5cksum = {.len = 0, .data = cksumdata};
- unsigned char *ptr = (unsigned char *)read_token->data;
- unsigned char *cksum;
- int bodysize, md5elen;
- int mic_hdrlen;
- u32 ret = GSS_S_DEFECTIVE_TOKEN;
-
- if (g_verify_token_header((struct xdr_netobj *) &ctx->mech_used,
- &bodysize, &ptr, read_token->len))
- goto out;
-
- /* decode the token */
-
- if (toktype != SPKM_MIC_TOK) {
- dprintk("RPC: BAD SPKM3 token type: %d\n", toktype);
- goto out;
- }
-
- if ((ret = spkm3_verify_mic_token(&ptr, &mic_hdrlen, &cksum)))
- goto out;
-
- if (*cksum++ != 0x03) {
- dprintk("RPC: spkm3_read_token BAD checksum type\n");
- goto out;
- }
- md5elen = *cksum++;
- cksum++; /* move past the zbit */
-
- if (!decode_asn1_bitstring(&wire_cksum, cksum, md5elen - 1, 16))
- goto out;
-
- /* HARD CODED FOR MD5 */
-
- /* compute the checksum of the message.
- * ptr + 2 = start of header piece of checksum
- * mic_hdrlen + 2 = length of header piece of checksum
- */
- ret = GSS_S_DEFECTIVE_TOKEN;
- if (!g_OID_equal(&ctx->intg_alg, &hmac_md5_oid)) {
- dprintk("RPC: gss_spkm3_seal: unsupported I-ALG "
- "algorithm\n");
- goto out;
- }
-
- checksum_type = CKSUMTYPE_HMAC_MD5;
-
- code = make_spkm3_checksum(checksum_type,
- &ctx->derived_integ_key, ptr + 2, mic_hdrlen + 2,
- message_buffer, 0, &md5cksum);
-
- if (code)
- goto out;
-
- ret = GSS_S_BAD_SIG;
- code = memcmp(md5cksum.data, wire_cksum.data, wire_cksum.len);
- if (code) {
- dprintk("RPC: bad MIC checksum\n");
- goto out;
- }
-
-
- /* XXX: need to add expiration and sequencing */
- ret = GSS_S_COMPLETE;
-out:
- kfree(wire_cksum.data);
- return ret;
-}
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index cc385b3a59c2..dec2a6fc7c12 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -964,7 +964,7 @@ svcauth_gss_set_client(struct svc_rqst *rqstp)
if (rqstp->rq_gssclient == NULL)
return SVC_DENIED;
stat = svcauth_unix_set_client(rqstp);
- if (stat == SVC_DROP)
+ if (stat == SVC_DROP || stat == SVC_CLOSE)
return stat;
return SVC_OK;
}
@@ -1018,7 +1018,7 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
return SVC_DENIED;
memset(&rsikey, 0, sizeof(rsikey));
if (dup_netobj(&rsikey.in_handle, &gc->gc_ctx))
- return SVC_DROP;
+ return SVC_CLOSE;
*authp = rpc_autherr_badverf;
if (svc_safe_getnetobj(argv, &tmpobj)) {
kfree(rsikey.in_handle.data);
@@ -1026,38 +1026,35 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
}
if (dup_netobj(&rsikey.in_token, &tmpobj)) {
kfree(rsikey.in_handle.data);
- return SVC_DROP;
+ return SVC_CLOSE;
}
/* Perform upcall, or find upcall result: */
rsip = rsi_lookup(&rsikey);
rsi_free(&rsikey);
if (!rsip)
- return SVC_DROP;
- switch (cache_check(&rsi_cache, &rsip->h, &rqstp->rq_chandle)) {
- case -EAGAIN:
- case -ETIMEDOUT:
- case -ENOENT:
+ return SVC_CLOSE;
+ if (cache_check(&rsi_cache, &rsip->h, &rqstp->rq_chandle) < 0)
/* No upcall result: */
- return SVC_DROP;
- case 0:
- ret = SVC_DROP;
- /* Got an answer to the upcall; use it: */
- if (gss_write_init_verf(rqstp, rsip))
- goto out;
- if (resv->iov_len + 4 > PAGE_SIZE)
- goto out;
- svc_putnl(resv, RPC_SUCCESS);
- if (svc_safe_putnetobj(resv, &rsip->out_handle))
- goto out;
- if (resv->iov_len + 3 * 4 > PAGE_SIZE)
- goto out;
- 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 out;
- }
+ return SVC_CLOSE;
+
+ ret = SVC_CLOSE;
+ /* Got an answer to the upcall; use it: */
+ if (gss_write_init_verf(rqstp, rsip))
+ goto out;
+ if (resv->iov_len + 4 > PAGE_SIZE)
+ goto out;
+ svc_putnl(resv, RPC_SUCCESS);
+ if (svc_safe_putnetobj(resv, &rsip->out_handle))
+ goto out;
+ if (resv->iov_len + 3 * 4 > PAGE_SIZE)
+ goto out;
+ 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 out;
+
ret = SVC_COMPLETE;
out:
cache_put(&rsip->h, &rsi_cache);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 7dce81a926c5..e433e7580e27 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -33,15 +33,16 @@
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
+#include "netns.h"
#define RPCDBG_FACILITY RPCDBG_CACHE
-static int cache_defer_req(struct cache_req *req, struct cache_head *item);
+static void cache_defer_req(struct cache_req *req, struct cache_head *item);
static void cache_revisit_request(struct cache_head *item);
static void cache_init(struct cache_head *h)
{
- time_t now = get_seconds();
+ time_t now = seconds_since_boot();
h->next = NULL;
h->flags = 0;
kref_init(&h->ref);
@@ -51,7 +52,7 @@ static void cache_init(struct cache_head *h)
static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h)
{
- return (h->expiry_time < get_seconds()) ||
+ return (h->expiry_time < seconds_since_boot()) ||
(detail->flush_time > h->last_refresh);
}
@@ -126,7 +127,7 @@ static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
static void cache_fresh_locked(struct cache_head *head, time_t expiry)
{
head->expiry_time = expiry;
- head->last_refresh = get_seconds();
+ head->last_refresh = seconds_since_boot();
set_bit(CACHE_VALID, &head->flags);
}
@@ -237,7 +238,7 @@ int cache_check(struct cache_detail *detail,
/* now see if we want to start an upcall */
refresh_age = (h->expiry_time - h->last_refresh);
- age = get_seconds() - h->last_refresh;
+ age = seconds_since_boot() - h->last_refresh;
if (rqstp == NULL) {
if (rv == -EAGAIN)
@@ -252,7 +253,7 @@ int cache_check(struct cache_detail *detail,
cache_revisit_request(h);
if (rv == -EAGAIN) {
set_bit(CACHE_NEGATIVE, &h->flags);
- cache_fresh_locked(h, get_seconds()+CACHE_NEW_EXPIRY);
+ cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
cache_fresh_unlocked(h, detail);
rv = -ENOENT;
}
@@ -267,7 +268,8 @@ int cache_check(struct cache_detail *detail,
}
if (rv == -EAGAIN) {
- if (cache_defer_req(rqstp, h) < 0) {
+ cache_defer_req(rqstp, h);
+ if (!test_bit(CACHE_PENDING, &h->flags)) {
/* Request is not deferred */
rv = cache_is_valid(detail, h);
if (rv == -EAGAIN)
@@ -387,11 +389,11 @@ static int cache_clean(void)
return -1;
}
current_detail = list_entry(next, struct cache_detail, others);
- if (current_detail->nextcheck > get_seconds())
+ if (current_detail->nextcheck > seconds_since_boot())
current_index = current_detail->hash_size;
else {
current_index = 0;
- current_detail->nextcheck = get_seconds()+30*60;
+ current_detail->nextcheck = seconds_since_boot()+30*60;
}
}
@@ -476,7 +478,7 @@ EXPORT_SYMBOL_GPL(cache_flush);
void cache_purge(struct cache_detail *detail)
{
detail->flush_time = LONG_MAX;
- detail->nextcheck = get_seconds();
+ detail->nextcheck = seconds_since_boot();
cache_flush();
detail->flush_time = 1;
}
@@ -505,81 +507,155 @@ EXPORT_SYMBOL_GPL(cache_purge);
static DEFINE_SPINLOCK(cache_defer_lock);
static LIST_HEAD(cache_defer_list);
-static struct list_head cache_defer_hash[DFR_HASHSIZE];
+static struct hlist_head cache_defer_hash[DFR_HASHSIZE];
static int cache_defer_cnt;
-static int cache_defer_req(struct cache_req *req, struct cache_head *item)
+static void __unhash_deferred_req(struct cache_deferred_req *dreq)
+{
+ hlist_del_init(&dreq->hash);
+ if (!list_empty(&dreq->recent)) {
+ list_del_init(&dreq->recent);
+ cache_defer_cnt--;
+ }
+}
+
+static void __hash_deferred_req(struct cache_deferred_req *dreq, struct cache_head *item)
{
- struct cache_deferred_req *dreq, *discard;
int hash = DFR_HASH(item);
- if (cache_defer_cnt >= DFR_MAX) {
- /* too much in the cache, randomly drop this one,
- * or continue and drop the oldest below
- */
- if (net_random()&1)
- return -ENOMEM;
- }
- dreq = req->defer(req);
- if (dreq == NULL)
- return -ENOMEM;
+ INIT_LIST_HEAD(&dreq->recent);
+ hlist_add_head(&dreq->hash, &cache_defer_hash[hash]);
+}
+
+static void setup_deferral(struct cache_deferred_req *dreq,
+ struct cache_head *item,
+ int count_me)
+{
dreq->item = item;
spin_lock(&cache_defer_lock);
- list_add(&dreq->recent, &cache_defer_list);
-
- if (cache_defer_hash[hash].next == NULL)
- INIT_LIST_HEAD(&cache_defer_hash[hash]);
- list_add(&dreq->hash, &cache_defer_hash[hash]);
+ __hash_deferred_req(dreq, item);
- /* it is in, now maybe clean up */
- discard = NULL;
- if (++cache_defer_cnt > DFR_MAX) {
- discard = list_entry(cache_defer_list.prev,
- struct cache_deferred_req, recent);
- list_del_init(&discard->recent);
- list_del_init(&discard->hash);
- cache_defer_cnt--;
+ if (count_me) {
+ cache_defer_cnt++;
+ list_add(&dreq->recent, &cache_defer_list);
}
+
spin_unlock(&cache_defer_lock);
+}
+
+struct thread_deferred_req {
+ struct cache_deferred_req handle;
+ struct completion completion;
+};
+
+static void cache_restart_thread(struct cache_deferred_req *dreq, int too_many)
+{
+ struct thread_deferred_req *dr =
+ container_of(dreq, struct thread_deferred_req, handle);
+ complete(&dr->completion);
+}
+
+static void cache_wait_req(struct cache_req *req, struct cache_head *item)
+{
+ struct thread_deferred_req sleeper;
+ struct cache_deferred_req *dreq = &sleeper.handle;
+
+ sleeper.completion = COMPLETION_INITIALIZER_ONSTACK(sleeper.completion);
+ dreq->revisit = cache_restart_thread;
+
+ setup_deferral(dreq, item, 0);
+
+ if (!test_bit(CACHE_PENDING, &item->flags) ||
+ wait_for_completion_interruptible_timeout(
+ &sleeper.completion, req->thread_wait) <= 0) {
+ /* The completion wasn't completed, so we need
+ * to clean up
+ */
+ spin_lock(&cache_defer_lock);
+ if (!hlist_unhashed(&sleeper.handle.hash)) {
+ __unhash_deferred_req(&sleeper.handle);
+ spin_unlock(&cache_defer_lock);
+ } else {
+ /* cache_revisit_request already removed
+ * this from the hash table, but hasn't
+ * called ->revisit yet. It will very soon
+ * and we need to wait for it.
+ */
+ spin_unlock(&cache_defer_lock);
+ wait_for_completion(&sleeper.completion);
+ }
+ }
+}
+
+static void cache_limit_defers(void)
+{
+ /* Make sure we haven't exceed the limit of allowed deferred
+ * requests.
+ */
+ struct cache_deferred_req *discard = NULL;
+
+ if (cache_defer_cnt <= DFR_MAX)
+ return;
+
+ spin_lock(&cache_defer_lock);
+
+ /* Consider removing either the first or the last */
+ if (cache_defer_cnt > DFR_MAX) {
+ if (net_random() & 1)
+ discard = list_entry(cache_defer_list.next,
+ struct cache_deferred_req, recent);
+ else
+ discard = list_entry(cache_defer_list.prev,
+ struct cache_deferred_req, recent);
+ __unhash_deferred_req(discard);
+ }
+ spin_unlock(&cache_defer_lock);
if (discard)
- /* there was one too many */
discard->revisit(discard, 1);
+}
- if (!test_bit(CACHE_PENDING, &item->flags)) {
- /* must have just been validated... */
- cache_revisit_request(item);
- return -EAGAIN;
+static void cache_defer_req(struct cache_req *req, struct cache_head *item)
+{
+ struct cache_deferred_req *dreq;
+
+ if (req->thread_wait) {
+ cache_wait_req(req, item);
+ if (!test_bit(CACHE_PENDING, &item->flags))
+ return;
}
- return 0;
+ dreq = req->defer(req);
+ if (dreq == NULL)
+ return;
+ setup_deferral(dreq, item, 1);
+ if (!test_bit(CACHE_PENDING, &item->flags))
+ /* Bit could have been cleared before we managed to
+ * set up the deferral, so need to revisit just in case
+ */
+ cache_revisit_request(item);
+
+ cache_limit_defers();
}
static void cache_revisit_request(struct cache_head *item)
{
struct cache_deferred_req *dreq;
struct list_head pending;
-
- struct list_head *lp;
+ struct hlist_node *lp, *tmp;
int hash = DFR_HASH(item);
INIT_LIST_HEAD(&pending);
spin_lock(&cache_defer_lock);
- lp = cache_defer_hash[hash].next;
- if (lp) {
- while (lp != &cache_defer_hash[hash]) {
- dreq = list_entry(lp, struct cache_deferred_req, hash);
- lp = lp->next;
- if (dreq->item == item) {
- list_del_init(&dreq->hash);
- list_move(&dreq->recent, &pending);
- cache_defer_cnt--;
- }
+ hlist_for_each_entry_safe(dreq, lp, tmp, &cache_defer_hash[hash], hash)
+ if (dreq->item == item) {
+ __unhash_deferred_req(dreq);
+ list_add(&dreq->recent, &pending);
}
- }
+
spin_unlock(&cache_defer_lock);
while (!list_empty(&pending)) {
@@ -600,9 +676,8 @@ void cache_clean_deferred(void *owner)
list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) {
if (dreq->owner == owner) {
- list_del_init(&dreq->hash);
- list_move(&dreq->recent, &pending);
- cache_defer_cnt--;
+ __unhash_deferred_req(dreq);
+ list_add(&dreq->recent, &pending);
}
}
spin_unlock(&cache_defer_lock);
@@ -901,7 +976,7 @@ static int cache_release(struct inode *inode, struct file *filp,
filp->private_data = NULL;
kfree(rp);
- cd->last_close = get_seconds();
+ cd->last_close = seconds_since_boot();
atomic_dec(&cd->readers);
}
module_put(cd->owner);
@@ -1014,6 +1089,23 @@ static void warn_no_listener(struct cache_detail *detail)
}
}
+static bool cache_listeners_exist(struct cache_detail *detail)
+{
+ if (atomic_read(&detail->readers))
+ return true;
+ if (detail->last_close == 0)
+ /* This cache was never opened */
+ return false;
+ if (detail->last_close < seconds_since_boot() - 30)
+ /*
+ * We allow for the possibility that someone might
+ * restart a userspace daemon without restarting the
+ * server; but after 30 seconds, we give up.
+ */
+ return false;
+ return true;
+}
+
/*
* register an upcall request to user-space and queue it up for read() by the
* upcall daemon.
@@ -1032,10 +1124,9 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h,
char *bp;
int len;
- if (atomic_read(&detail->readers) == 0 &&
- detail->last_close < get_seconds() - 30) {
- warn_no_listener(detail);
- return -EINVAL;
+ if (!cache_listeners_exist(detail)) {
+ warn_no_listener(detail);
+ return -EINVAL;
}
buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
@@ -1094,13 +1185,19 @@ int qword_get(char **bpp, char *dest, int bufsize)
if (bp[0] == '\\' && bp[1] == 'x') {
/* HEX STRING */
bp += 2;
- while (isxdigit(bp[0]) && isxdigit(bp[1]) && len < bufsize) {
- int byte = isdigit(*bp) ? *bp-'0' : toupper(*bp)-'A'+10;
- bp++;
- byte <<= 4;
- byte |= isdigit(*bp) ? *bp-'0' : toupper(*bp)-'A'+10;
- *dest++ = byte;
- bp++;
+ while (len < bufsize) {
+ int h, l;
+
+ h = hex_to_bin(bp[0]);
+ if (h < 0)
+ break;
+
+ l = hex_to_bin(bp[1]);
+ if (l < 0)
+ break;
+
+ *dest++ = (h << 4) | l;
+ bp += 2;
len++;
}
} else {
@@ -1218,7 +1315,8 @@ static int c_show(struct seq_file *m, void *p)
ifdebug(CACHE)
seq_printf(m, "# expiry=%ld refcnt=%d flags=%lx\n",
- cp->expiry_time, atomic_read(&cp->ref.refcount), cp->flags);
+ convert_to_wallclock(cp->expiry_time),
+ atomic_read(&cp->ref.refcount), cp->flags);
cache_get(cp);
if (cache_check(cd, cp, NULL))
/* cache_check does a cache_put on failure */
@@ -1284,7 +1382,7 @@ static ssize_t read_flush(struct file *file, char __user *buf,
unsigned long p = *ppos;
size_t len;
- sprintf(tbuf, "%lu\n", cd->flush_time);
+ sprintf(tbuf, "%lu\n", convert_to_wallclock(cd->flush_time));
len = strlen(tbuf);
if (p >= len)
return 0;
@@ -1302,19 +1400,20 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
struct cache_detail *cd)
{
char tbuf[20];
- char *ep;
- long flushtime;
+ char *bp, *ep;
+
if (*ppos || count > sizeof(tbuf)-1)
return -EINVAL;
if (copy_from_user(tbuf, buf, count))
return -EFAULT;
tbuf[count] = 0;
- flushtime = simple_strtoul(tbuf, &ep, 0);
+ simple_strtoul(tbuf, &ep, 0);
if (*ep && *ep != '\n')
return -EINVAL;
- cd->flush_time = flushtime;
- cd->nextcheck = get_seconds();
+ bp = tbuf;
+ cd->flush_time = get_expiry(&bp);
+ cd->nextcheck = seconds_since_boot();
cache_flush();
*ppos += count;
@@ -1438,8 +1537,10 @@ static const struct file_operations cache_flush_operations_procfs = {
.llseek = no_llseek,
};
-static void remove_cache_proc_entries(struct cache_detail *cd)
+static void remove_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
+ struct sunrpc_net *sn;
+
if (cd->u.procfs.proc_ent == NULL)
return;
if (cd->u.procfs.flush_ent)
@@ -1449,15 +1550,18 @@ static void remove_cache_proc_entries(struct cache_detail *cd)
if (cd->u.procfs.content_ent)
remove_proc_entry("content", cd->u.procfs.proc_ent);
cd->u.procfs.proc_ent = NULL;
- remove_proc_entry(cd->name, proc_net_rpc);
+ sn = net_generic(net, sunrpc_net_id);
+ remove_proc_entry(cd->name, sn->proc_net_rpc);
}
#ifdef CONFIG_PROC_FS
-static int create_cache_proc_entries(struct cache_detail *cd)
+static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
struct proc_dir_entry *p;
+ struct sunrpc_net *sn;
- cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc);
+ sn = net_generic(net, sunrpc_net_id);
+ cd->u.procfs.proc_ent = proc_mkdir(cd->name, sn->proc_net_rpc);
if (cd->u.procfs.proc_ent == NULL)
goto out_nomem;
cd->u.procfs.channel_ent = NULL;
@@ -1488,11 +1592,11 @@ static int create_cache_proc_entries(struct cache_detail *cd)
}
return 0;
out_nomem:
- remove_cache_proc_entries(cd);
+ remove_cache_proc_entries(cd, net);
return -ENOMEM;
}
#else /* CONFIG_PROC_FS */
-static int create_cache_proc_entries(struct cache_detail *cd)
+static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
{
return 0;
}
@@ -1503,23 +1607,33 @@ void __init cache_initialize(void)
INIT_DELAYED_WORK_DEFERRABLE(&cache_cleaner, do_cache_clean);
}
-int cache_register(struct cache_detail *cd)
+int cache_register_net(struct cache_detail *cd, struct net *net)
{
int ret;
sunrpc_init_cache_detail(cd);
- ret = create_cache_proc_entries(cd);
+ ret = create_cache_proc_entries(cd, net);
if (ret)
sunrpc_destroy_cache_detail(cd);
return ret;
}
+
+int cache_register(struct cache_detail *cd)
+{
+ return cache_register_net(cd, &init_net);
+}
EXPORT_SYMBOL_GPL(cache_register);
-void cache_unregister(struct cache_detail *cd)
+void cache_unregister_net(struct cache_detail *cd, struct net *net)
{
- remove_cache_proc_entries(cd);
+ remove_cache_proc_entries(cd, net);
sunrpc_destroy_cache_detail(cd);
}
+
+void cache_unregister(struct cache_detail *cd)
+{
+ cache_unregister_net(cd, &init_net);
+}
EXPORT_SYMBOL_GPL(cache_unregister);
static ssize_t cache_read_pipefs(struct file *filp, char __user *buf,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index cbc5b8ccc8be..9dab9573be41 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -284,6 +284,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
struct rpc_xprt *xprt;
struct rpc_clnt *clnt;
struct xprt_create xprtargs = {
+ .net = args->net,
.ident = args->protocol,
.srcaddr = args->saddress,
.dstaddr = args->address,
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
new file mode 100644
index 000000000000..d013bf211cae
--- /dev/null
+++ b/net/sunrpc/netns.h
@@ -0,0 +1,19 @@
+#ifndef __SUNRPC_NETNS_H__
+#define __SUNRPC_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct cache_detail;
+
+struct sunrpc_net {
+ struct proc_dir_entry *proc_net_rpc;
+ struct cache_detail *ip_map_cache;
+};
+
+extern int sunrpc_net_id;
+
+int ip_map_cache_create(struct net *);
+void ip_map_cache_destroy(struct net *);
+
+#endif
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 63ec116b4dd4..fa6d7ca2c851 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -177,6 +177,7 @@ static DEFINE_MUTEX(rpcb_create_local_mutex);
static int rpcb_create_local(void)
{
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = XPRT_TRANSPORT_TCP,
.address = (struct sockaddr *)&rpcb_inaddr_loopback,
.addrsize = sizeof(rpcb_inaddr_loopback),
@@ -229,6 +230,7 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
size_t salen, int proto, u32 version)
{
struct rpc_create_args args = {
+ .net = &init_net,
.protocol = proto,
.address = srvaddr,
.addrsize = salen,
@@ -248,7 +250,7 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
((struct sockaddr_in6 *)srvaddr)->sin6_port = htons(RPCBIND_PORT);
break;
default:
- return NULL;
+ return ERR_PTR(-EAFNOSUPPORT);
}
return rpc_create(&args);
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index ea1046f3f9a3..f71a73107ae9 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -22,11 +22,10 @@
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/metrics.h>
-#include <net/net_namespace.h>
-#define RPCDBG_FACILITY RPCDBG_MISC
+#include "netns.h"
-struct proc_dir_entry *proc_net_rpc = NULL;
+#define RPCDBG_FACILITY RPCDBG_MISC
/*
* Get RPC client stats
@@ -218,10 +217,11 @@ EXPORT_SYMBOL_GPL(rpc_print_iostats);
static inline struct proc_dir_entry *
do_register(const char *name, void *data, const struct file_operations *fops)
{
- rpc_proc_init();
- dprintk("RPC: registering /proc/net/rpc/%s\n", name);
+ struct sunrpc_net *sn;
- return proc_create_data(name, 0, proc_net_rpc, fops, data);
+ dprintk("RPC: registering /proc/net/rpc/%s\n", name);
+ sn = net_generic(&init_net, sunrpc_net_id);
+ return proc_create_data(name, 0, sn->proc_net_rpc, fops, data);
}
struct proc_dir_entry *
@@ -234,7 +234,10 @@ EXPORT_SYMBOL_GPL(rpc_proc_register);
void
rpc_proc_unregister(const char *name)
{
- remove_proc_entry(name, proc_net_rpc);
+ struct sunrpc_net *sn;
+
+ sn = net_generic(&init_net, sunrpc_net_id);
+ remove_proc_entry(name, sn->proc_net_rpc);
}
EXPORT_SYMBOL_GPL(rpc_proc_unregister);
@@ -248,25 +251,29 @@ EXPORT_SYMBOL_GPL(svc_proc_register);
void
svc_proc_unregister(const char *name)
{
- remove_proc_entry(name, proc_net_rpc);
+ struct sunrpc_net *sn;
+
+ sn = net_generic(&init_net, sunrpc_net_id);
+ remove_proc_entry(name, sn->proc_net_rpc);
}
EXPORT_SYMBOL_GPL(svc_proc_unregister);
-void
-rpc_proc_init(void)
+int rpc_proc_init(struct net *net)
{
+ struct sunrpc_net *sn;
+
dprintk("RPC: registering /proc/net/rpc\n");
- if (!proc_net_rpc)
- proc_net_rpc = proc_mkdir("rpc", init_net.proc_net);
+ sn = net_generic(net, sunrpc_net_id);
+ sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net);
+ if (sn->proc_net_rpc == NULL)
+ return -ENOMEM;
+
+ return 0;
}
-void
-rpc_proc_exit(void)
+void rpc_proc_exit(struct net *net)
{
dprintk("RPC: unregistering /proc/net/rpc\n");
- if (proc_net_rpc) {
- proc_net_rpc = NULL;
- remove_proc_entry("rpc", init_net.proc_net);
- }
+ remove_proc_entry("rpc", net->proc_net);
}
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index c0d085013a2b..9d0809160994 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -22,7 +22,44 @@
#include <linux/sunrpc/rpc_pipe_fs.h>
#include <linux/sunrpc/xprtsock.h>
-extern struct cache_detail ip_map_cache, unix_gid_cache;
+#include "netns.h"
+
+int sunrpc_net_id;
+
+static __net_init int sunrpc_init_net(struct net *net)
+{
+ int err;
+
+ err = rpc_proc_init(net);
+ if (err)
+ goto err_proc;
+
+ err = ip_map_cache_create(net);
+ if (err)
+ goto err_ipmap;
+
+ return 0;
+
+err_ipmap:
+ rpc_proc_exit(net);
+err_proc:
+ return err;
+}
+
+static __net_exit void sunrpc_exit_net(struct net *net)
+{
+ ip_map_cache_destroy(net);
+ rpc_proc_exit(net);
+}
+
+static struct pernet_operations sunrpc_net_ops = {
+ .init = sunrpc_init_net,
+ .exit = sunrpc_exit_net,
+ .id = &sunrpc_net_id,
+ .size = sizeof(struct sunrpc_net),
+};
+
+extern struct cache_detail unix_gid_cache;
extern void cleanup_rpcb_clnt(void);
@@ -38,18 +75,22 @@ init_sunrpc(void)
err = rpcauth_init_module();
if (err)
goto out3;
+
+ cache_initialize();
+
+ err = register_pernet_subsys(&sunrpc_net_ops);
+ if (err)
+ goto out4;
#ifdef RPC_DEBUG
rpc_register_sysctl();
#endif
-#ifdef CONFIG_PROC_FS
- rpc_proc_init();
-#endif
- cache_initialize();
- cache_register(&ip_map_cache);
cache_register(&unix_gid_cache);
svc_init_xprt_sock(); /* svc sock transport */
init_socket_xprt(); /* clnt sock transport */
return 0;
+
+out4:
+ rpcauth_remove_module();
out3:
rpc_destroy_mempool();
out2:
@@ -67,14 +108,11 @@ cleanup_sunrpc(void)
svc_cleanup_xprt_sock();
unregister_rpc_pipefs();
rpc_destroy_mempool();
- cache_unregister(&ip_map_cache);
cache_unregister(&unix_gid_cache);
+ unregister_pernet_subsys(&sunrpc_net_ops);
#ifdef RPC_DEBUG
rpc_unregister_sysctl();
#endif
-#ifdef CONFIG_PROC_FS
- rpc_proc_exit();
-#endif
rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
MODULE_LICENSE("GPL");
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d9017d64597e..6359c42c4941 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1055,6 +1055,9 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
goto err_bad;
case SVC_DENIED:
goto err_bad_auth;
+ case SVC_CLOSE:
+ if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+ svc_close_xprt(rqstp->rq_xprt);
case SVC_DROP:
goto dropit;
case SVC_COMPLETE:
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index cbc084939dd8..c82fe739fbdc 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -100,16 +100,14 @@ EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
*/
int svc_print_xprts(char *buf, int maxlen)
{
- struct list_head *le;
+ struct svc_xprt_class *xcl;
char tmpstr[80];
int len = 0;
buf[0] = '\0';
spin_lock(&svc_xprt_class_lock);
- list_for_each(le, &svc_xprt_class_list) {
+ list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
int slen;
- struct svc_xprt_class *xcl =
- list_entry(le, struct svc_xprt_class, xcl_list);
sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
slen = strlen(tmpstr);
@@ -128,9 +126,9 @@ static void svc_xprt_free(struct kref *kref)
struct svc_xprt *xprt =
container_of(kref, struct svc_xprt, xpt_ref);
struct module *owner = xprt->xpt_class->xcl_owner;
- if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags) &&
- xprt->xpt_auth_cache != NULL)
- svcauth_unix_info_release(xprt->xpt_auth_cache);
+ if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags))
+ svcauth_unix_info_release(xprt);
+ put_net(xprt->xpt_net);
xprt->xpt_ops->xpo_free(xprt);
module_put(owner);
}
@@ -156,15 +154,18 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
INIT_LIST_HEAD(&xprt->xpt_list);
INIT_LIST_HEAD(&xprt->xpt_ready);
INIT_LIST_HEAD(&xprt->xpt_deferred);
+ INIT_LIST_HEAD(&xprt->xpt_users);
mutex_init(&xprt->xpt_mutex);
spin_lock_init(&xprt->xpt_lock);
set_bit(XPT_BUSY, &xprt->xpt_flags);
rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending");
+ xprt->xpt_net = get_net(&init_net);
}
EXPORT_SYMBOL_GPL(svc_xprt_init);
static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
struct svc_serv *serv,
+ struct net *net,
const int family,
const unsigned short port,
int flags)
@@ -199,12 +200,12 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
return ERR_PTR(-EAFNOSUPPORT);
}
- return xcl->xcl_ops->xpo_create(serv, sap, len, flags);
+ return xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
}
int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
- const int family, const unsigned short port,
- int flags)
+ struct net *net, const int family,
+ const unsigned short port, int flags)
{
struct svc_xprt_class *xcl;
@@ -220,7 +221,7 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
goto err;
spin_unlock(&svc_xprt_class_lock);
- newxprt = __svc_xpo_create(xcl, serv, family, port, flags);
+ newxprt = __svc_xpo_create(xcl, serv, net, family, port, flags);
if (IS_ERR(newxprt)) {
module_put(xcl->xcl_owner);
return PTR_ERR(newxprt);
@@ -329,12 +330,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
"svc_xprt_enqueue: "
"threads and transports both waiting??\n");
- if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
- /* Don't enqueue dead transports */
- dprintk("svc: transport %p is dead, not enqueued\n", xprt);
- goto out_unlock;
- }
-
pool->sp_stats.packets++;
/* Mark transport as busy. It will remain in this state until
@@ -651,6 +646,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
if (signalled() || kthread_should_stop())
return -EINTR;
+ /* Normally we will wait up to 5 seconds for any required
+ * cache information to be provided.
+ */
+ rqstp->rq_chandle.thread_wait = 5*HZ;
+
spin_lock_bh(&pool->sp_lock);
xprt = svc_xprt_dequeue(pool);
if (xprt) {
@@ -658,6 +658,12 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
svc_xprt_get(xprt);
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+
+ /* As there is a shortage of threads and this request
+ * had to be queued, don't allow the thread to wait so
+ * long for cache updates.
+ */
+ rqstp->rq_chandle.thread_wait = 1*HZ;
} else {
/* No data pending. Go to sleep */
svc_thread_enqueue(pool, rqstp);
@@ -868,6 +874,19 @@ static void svc_age_temp_xprts(unsigned long closure)
mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
}
+static void call_xpt_users(struct svc_xprt *xprt)
+{
+ struct svc_xpt_user *u;
+
+ spin_lock(&xprt->xpt_lock);
+ while (!list_empty(&xprt->xpt_users)) {
+ u = list_first_entry(&xprt->xpt_users, struct svc_xpt_user, list);
+ list_del(&u->list);
+ u->callback(u);
+ }
+ spin_unlock(&xprt->xpt_lock);
+}
+
/*
* Remove a dead transport
*/
@@ -878,7 +897,7 @@ void svc_delete_xprt(struct svc_xprt *xprt)
/* Only do this once */
if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags))
- return;
+ BUG();
dprintk("svc: svc_delete_xprt(%p)\n", xprt);
xprt->xpt_ops->xpo_detach(xprt);
@@ -900,6 +919,7 @@ void svc_delete_xprt(struct svc_xprt *xprt)
while ((dr = svc_deferred_dequeue(xprt)) != NULL)
kfree(dr);
+ call_xpt_users(xprt);
svc_xprt_put(xprt);
}
@@ -910,10 +930,7 @@ void svc_close_xprt(struct svc_xprt *xprt)
/* someone else will have to effect the close */
return;
- svc_xprt_get(xprt);
svc_delete_xprt(xprt);
- clear_bit(XPT_BUSY, &xprt->xpt_flags);
- svc_xprt_put(xprt);
}
EXPORT_SYMBOL_GPL(svc_close_xprt);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 207311610988..560677d187f1 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -18,6 +18,8 @@
#include <linux/sunrpc/clnt.h>
+#include "netns.h"
+
/*
* AUTHUNIX and AUTHNULL credentials are both handled here.
* AUTHNULL is treated just like AUTHUNIX except that the uid/gid
@@ -92,7 +94,6 @@ struct ip_map {
struct unix_domain *m_client;
int m_add_change;
};
-static struct cache_head *ip_table[IP_HASHMAX];
static void ip_map_put(struct kref *kref)
{
@@ -178,8 +179,8 @@ static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h)
return sunrpc_cache_pipe_upcall(cd, h, ip_map_request);
}
-static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr);
-static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry);
+static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct in6_addr *addr);
+static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, struct unix_domain *udom, time_t expiry);
static int ip_map_parse(struct cache_detail *cd,
char *mesg, int mlen)
@@ -219,10 +220,9 @@ static int ip_map_parse(struct cache_detail *cd,
switch (address.sa.sa_family) {
case AF_INET:
/* Form a mapped IPv4 address in sin6 */
- memset(&sin6, 0, sizeof(sin6));
sin6.sin6_family = AF_INET6;
- sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- sin6.sin6_addr.s6_addr32[3] = address.s4.sin_addr.s_addr;
+ ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr,
+ &sin6.sin6_addr);
break;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
case AF_INET6:
@@ -249,9 +249,9 @@ static int ip_map_parse(struct cache_detail *cd,
dom = NULL;
/* IPv6 scope IDs are ignored for now */
- ipmp = ip_map_lookup(class, &sin6.sin6_addr);
+ ipmp = __ip_map_lookup(cd, class, &sin6.sin6_addr);
if (ipmp) {
- err = ip_map_update(ipmp,
+ err = __ip_map_update(cd, ipmp,
container_of(dom, struct unix_domain, h),
expiry);
} else
@@ -294,29 +294,15 @@ static int ip_map_show(struct seq_file *m,
}
-struct cache_detail ip_map_cache = {
- .owner = THIS_MODULE,
- .hash_size = IP_HASHMAX,
- .hash_table = ip_table,
- .name = "auth.unix.ip",
- .cache_put = ip_map_put,
- .cache_upcall = ip_map_upcall,
- .cache_parse = ip_map_parse,
- .cache_show = ip_map_show,
- .match = ip_map_match,
- .init = ip_map_init,
- .update = update,
- .alloc = ip_map_alloc,
-};
-
-static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr)
+static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class,
+ struct in6_addr *addr)
{
struct ip_map ip;
struct cache_head *ch;
strcpy(ip.m_class, class);
ipv6_addr_copy(&ip.m_addr, addr);
- ch = sunrpc_cache_lookup(&ip_map_cache, &ip.h,
+ ch = sunrpc_cache_lookup(cd, &ip.h,
hash_str(class, IP_HASHBITS) ^
hash_ip6(*addr));
@@ -326,7 +312,17 @@ static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr)
return NULL;
}
-static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry)
+static inline struct ip_map *ip_map_lookup(struct net *net, char *class,
+ struct in6_addr *addr)
+{
+ struct sunrpc_net *sn;
+
+ sn = net_generic(net, sunrpc_net_id);
+ return __ip_map_lookup(sn->ip_map_cache, class, addr);
+}
+
+static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm,
+ struct unix_domain *udom, time_t expiry)
{
struct ip_map ip;
struct cache_head *ch;
@@ -344,17 +340,25 @@ static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t ex
ip.m_add_change++;
}
ip.h.expiry_time = expiry;
- ch = sunrpc_cache_update(&ip_map_cache,
- &ip.h, &ipm->h,
+ ch = sunrpc_cache_update(cd, &ip.h, &ipm->h,
hash_str(ipm->m_class, IP_HASHBITS) ^
hash_ip6(ipm->m_addr));
if (!ch)
return -ENOMEM;
- cache_put(ch, &ip_map_cache);
+ cache_put(ch, cd);
return 0;
}
-int auth_unix_add_addr(struct in6_addr *addr, struct auth_domain *dom)
+static inline int ip_map_update(struct net *net, struct ip_map *ipm,
+ struct unix_domain *udom, time_t expiry)
+{
+ struct sunrpc_net *sn;
+
+ sn = net_generic(net, sunrpc_net_id);
+ return __ip_map_update(sn->ip_map_cache, ipm, udom, expiry);
+}
+
+int auth_unix_add_addr(struct net *net, struct in6_addr *addr, struct auth_domain *dom)
{
struct unix_domain *udom;
struct ip_map *ipmp;
@@ -362,10 +366,10 @@ int auth_unix_add_addr(struct in6_addr *addr, struct auth_domain *dom)
if (dom->flavour != &svcauth_unix)
return -EINVAL;
udom = container_of(dom, struct unix_domain, h);
- ipmp = ip_map_lookup("nfsd", addr);
+ ipmp = ip_map_lookup(net, "nfsd", addr);
if (ipmp)
- return ip_map_update(ipmp, udom, NEVER);
+ return ip_map_update(net, ipmp, udom, NEVER);
else
return -ENOMEM;
}
@@ -383,16 +387,18 @@ int auth_unix_forget_old(struct auth_domain *dom)
}
EXPORT_SYMBOL_GPL(auth_unix_forget_old);
-struct auth_domain *auth_unix_lookup(struct in6_addr *addr)
+struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr)
{
struct ip_map *ipm;
struct auth_domain *rv;
+ struct sunrpc_net *sn;
- ipm = ip_map_lookup("nfsd", addr);
+ sn = net_generic(net, sunrpc_net_id);
+ ipm = ip_map_lookup(net, "nfsd", addr);
if (!ipm)
return NULL;
- if (cache_check(&ip_map_cache, &ipm->h, NULL))
+ if (cache_check(sn->ip_map_cache, &ipm->h, NULL))
return NULL;
if ((ipm->m_client->addr_changes - ipm->m_add_change) >0) {
@@ -403,22 +409,29 @@ struct auth_domain *auth_unix_lookup(struct in6_addr *addr)
rv = &ipm->m_client->h;
kref_get(&rv->ref);
}
- cache_put(&ipm->h, &ip_map_cache);
+ cache_put(&ipm->h, sn->ip_map_cache);
return rv;
}
EXPORT_SYMBOL_GPL(auth_unix_lookup);
void svcauth_unix_purge(void)
{
- cache_purge(&ip_map_cache);
+ struct net *net;
+
+ for_each_net(net) {
+ struct sunrpc_net *sn;
+
+ sn = net_generic(net, sunrpc_net_id);
+ cache_purge(sn->ip_map_cache);
+ }
}
EXPORT_SYMBOL_GPL(svcauth_unix_purge);
static inline struct ip_map *
-ip_map_cached_get(struct svc_rqst *rqstp)
+ip_map_cached_get(struct svc_xprt *xprt)
{
struct ip_map *ipm = NULL;
- struct svc_xprt *xprt = rqstp->rq_xprt;
+ struct sunrpc_net *sn;
if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) {
spin_lock(&xprt->xpt_lock);
@@ -430,9 +443,10 @@ ip_map_cached_get(struct svc_rqst *rqstp)
* remembered, e.g. by a second mount from the
* same IP address.
*/
+ sn = net_generic(xprt->xpt_net, sunrpc_net_id);
xprt->xpt_auth_cache = NULL;
spin_unlock(&xprt->xpt_lock);
- cache_put(&ipm->h, &ip_map_cache);
+ cache_put(&ipm->h, sn->ip_map_cache);
return NULL;
}
cache_get(&ipm->h);
@@ -443,10 +457,8 @@ ip_map_cached_get(struct svc_rqst *rqstp)
}
static inline void
-ip_map_cached_put(struct svc_rqst *rqstp, struct ip_map *ipm)
+ip_map_cached_put(struct svc_xprt *xprt, struct ip_map *ipm)
{
- struct svc_xprt *xprt = rqstp->rq_xprt;
-
if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) {
spin_lock(&xprt->xpt_lock);
if (xprt->xpt_auth_cache == NULL) {
@@ -456,15 +468,26 @@ ip_map_cached_put(struct svc_rqst *rqstp, struct ip_map *ipm)
}
spin_unlock(&xprt->xpt_lock);
}
- if (ipm)
- cache_put(&ipm->h, &ip_map_cache);
+ if (ipm) {
+ struct sunrpc_net *sn;
+
+ sn = net_generic(xprt->xpt_net, sunrpc_net_id);
+ cache_put(&ipm->h, sn->ip_map_cache);
+ }
}
void
-svcauth_unix_info_release(void *info)
+svcauth_unix_info_release(struct svc_xprt *xpt)
{
- struct ip_map *ipm = info;
- cache_put(&ipm->h, &ip_map_cache);
+ struct ip_map *ipm;
+
+ ipm = xpt->xpt_auth_cache;
+ if (ipm != NULL) {
+ struct sunrpc_net *sn;
+
+ sn = net_generic(xpt->xpt_net, sunrpc_net_id);
+ cache_put(&ipm->h, sn->ip_map_cache);
+ }
}
/****************************************************************************
@@ -674,6 +697,8 @@ static struct group_info *unix_gid_find(uid_t uid, struct svc_rqst *rqstp)
switch (ret) {
case -ENOENT:
return ERR_PTR(-ENOENT);
+ case -ETIMEDOUT:
+ return ERR_PTR(-ESHUTDOWN);
case 0:
gi = get_group_info(ug->gi);
cache_put(&ug->h, &unix_gid_cache);
@@ -691,6 +716,9 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
struct ip_map *ipm;
struct group_info *gi;
struct svc_cred *cred = &rqstp->rq_cred;
+ struct svc_xprt *xprt = rqstp->rq_xprt;
+ struct net *net = xprt->xpt_net;
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
switch (rqstp->rq_addr.ss_family) {
case AF_INET:
@@ -709,26 +737,27 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
if (rqstp->rq_proc == 0)
return SVC_OK;
- ipm = ip_map_cached_get(rqstp);
+ ipm = ip_map_cached_get(xprt);
if (ipm == NULL)
- ipm = ip_map_lookup(rqstp->rq_server->sv_program->pg_class,
+ ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class,
&sin6->sin6_addr);
if (ipm == NULL)
return SVC_DENIED;
- switch (cache_check(&ip_map_cache, &ipm->h, &rqstp->rq_chandle)) {
+ switch (cache_check(sn->ip_map_cache, &ipm->h, &rqstp->rq_chandle)) {
default:
BUG();
- case -EAGAIN:
case -ETIMEDOUT:
+ return SVC_CLOSE;
+ case -EAGAIN:
return SVC_DROP;
case -ENOENT:
return SVC_DENIED;
case 0:
rqstp->rq_client = &ipm->m_client->h;
kref_get(&rqstp->rq_client->ref);
- ip_map_cached_put(rqstp, ipm);
+ ip_map_cached_put(xprt, ipm);
break;
}
@@ -736,6 +765,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
switch (PTR_ERR(gi)) {
case -EAGAIN:
return SVC_DROP;
+ case -ESHUTDOWN:
+ return SVC_CLOSE;
case -ENOENT:
break;
default:
@@ -776,7 +807,7 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp)
cred->cr_gid = (gid_t) -1;
cred->cr_group_info = groups_alloc(0);
if (cred->cr_group_info == NULL)
- return SVC_DROP; /* kmalloc failure - client must retry */
+ return SVC_CLOSE; /* kmalloc failure - client must retry */
/* Put NULL verifier */
svc_putnl(resv, RPC_AUTH_NULL);
@@ -840,7 +871,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp)
goto badcred;
cred->cr_group_info = groups_alloc(slen);
if (cred->cr_group_info == NULL)
- return SVC_DROP;
+ return SVC_CLOSE;
for (i = 0; i < slen; i++)
GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv);
if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) {
@@ -886,3 +917,56 @@ struct auth_ops svcauth_unix = {
.set_client = svcauth_unix_set_client,
};
+int ip_map_cache_create(struct net *net)
+{
+ int err = -ENOMEM;
+ struct cache_detail *cd;
+ struct cache_head **tbl;
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+
+ cd = kzalloc(sizeof(struct cache_detail), GFP_KERNEL);
+ if (cd == NULL)
+ goto err_cd;
+
+ tbl = kzalloc(IP_HASHMAX * sizeof(struct cache_head *), GFP_KERNEL);
+ if (tbl == NULL)
+ goto err_tbl;
+
+ cd->owner = THIS_MODULE,
+ cd->hash_size = IP_HASHMAX,
+ cd->hash_table = tbl,
+ cd->name = "auth.unix.ip",
+ cd->cache_put = ip_map_put,
+ cd->cache_upcall = ip_map_upcall,
+ cd->cache_parse = ip_map_parse,
+ cd->cache_show = ip_map_show,
+ cd->match = ip_map_match,
+ cd->init = ip_map_init,
+ cd->update = update,
+ cd->alloc = ip_map_alloc,
+
+ err = cache_register_net(cd, net);
+ if (err)
+ goto err_reg;
+
+ sn->ip_map_cache = cd;
+ return 0;
+
+err_reg:
+ kfree(tbl);
+err_tbl:
+ kfree(cd);
+err_cd:
+ return err;
+}
+
+void ip_map_cache_destroy(struct net *net)
+{
+ struct sunrpc_net *sn;
+
+ sn = net_generic(net, sunrpc_net_id);
+ cache_purge(sn->ip_map_cache);
+ cache_unregister_net(sn->ip_map_cache, net);
+ kfree(sn->ip_map_cache->hash_table);
+ kfree(sn->ip_map_cache);
+}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 7e534dd09077..07919e16be3e 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -64,7 +64,8 @@ static void svc_tcp_sock_detach(struct svc_xprt *);
static void svc_sock_free(struct svc_xprt *);
static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
- struct sockaddr *, int, int);
+ struct net *, struct sockaddr *,
+ int, int);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key svc_key[2];
static struct lock_class_key svc_slock_key[2];
@@ -657,10 +658,11 @@ static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
}
static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
+ struct net *net,
struct sockaddr *sa, int salen,
int flags)
{
- return svc_create_socket(serv, IPPROTO_UDP, sa, salen, flags);
+ return svc_create_socket(serv, IPPROTO_UDP, net, sa, salen, flags);
}
static struct svc_xprt_ops svc_udp_ops = {
@@ -1133,9 +1135,6 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
reclen = htonl(0x80000000|((xbufp->len ) - 4));
memcpy(xbufp->head[0].iov_base, &reclen, 4);
- if (test_bit(XPT_DEAD, &rqstp->rq_xprt->xpt_flags))
- return -ENOTCONN;
-
sent = svc_sendto(rqstp, &rqstp->rq_res);
if (sent != xbufp->len) {
printk(KERN_NOTICE
@@ -1178,10 +1177,11 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)
}
static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
+ struct net *net,
struct sockaddr *sa, int salen,
int flags)
{
- return svc_create_socket(serv, IPPROTO_TCP, sa, salen, flags);
+ return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
}
static struct svc_xprt_ops svc_tcp_ops = {
@@ -1258,19 +1258,13 @@ void svc_sock_update_bufs(struct svc_serv *serv)
* The number of server threads has changed. Update
* rcvbuf and sndbuf accordingly on all sockets
*/
- struct list_head *le;
+ struct svc_sock *svsk;
spin_lock_bh(&serv->sv_lock);
- list_for_each(le, &serv->sv_permsocks) {
- struct svc_sock *svsk =
- list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+ list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
- }
- list_for_each(le, &serv->sv_tempsocks) {
- struct svc_sock *svsk =
- list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+ list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
- }
spin_unlock_bh(&serv->sv_lock);
}
EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
@@ -1385,6 +1379,7 @@ EXPORT_SYMBOL_GPL(svc_addsock);
*/
static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
int protocol,
+ struct net *net,
struct sockaddr *sin, int len,
int flags)
{
@@ -1421,7 +1416,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
return ERR_PTR(-EINVAL);
}
- error = sock_create_kern(family, type, protocol, &sock);
+ error = __sock_create(net, family, type, protocol, &sock, 1);
if (error < 0)
return ERR_PTR(error);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 970fb00f388c..4c8f18aff7c3 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -199,8 +199,6 @@ int xprt_reserve_xprt(struct rpc_task *task)
if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) {
if (task == xprt->snd_task)
return 1;
- if (task == NULL)
- return 0;
goto out_sleep;
}
xprt->snd_task = task;
@@ -757,13 +755,11 @@ static void xprt_connect_status(struct rpc_task *task)
*/
struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid)
{
- struct list_head *pos;
+ struct rpc_rqst *entry;
- list_for_each(pos, &xprt->recv) {
- struct rpc_rqst *entry = list_entry(pos, struct rpc_rqst, rq_list);
+ list_for_each_entry(entry, &xprt->recv, rq_list)
if (entry->rq_xid == xid)
return entry;
- }
dprintk("RPC: xprt_lookup_rqst did not find xid %08x\n",
ntohl(xid));
@@ -962,6 +958,37 @@ static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
spin_unlock(&xprt->reserve_lock);
}
+struct rpc_xprt *xprt_alloc(struct net *net, int size, int max_req)
+{
+ struct rpc_xprt *xprt;
+
+ xprt = kzalloc(size, GFP_KERNEL);
+ if (xprt == NULL)
+ goto out;
+
+ xprt->max_reqs = max_req;
+ xprt->slot = kcalloc(max_req, sizeof(struct rpc_rqst), GFP_KERNEL);
+ if (xprt->slot == NULL)
+ goto out_free;
+
+ xprt->xprt_net = get_net(net);
+ return xprt;
+
+out_free:
+ kfree(xprt);
+out:
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(xprt_alloc);
+
+void xprt_free(struct rpc_xprt *xprt)
+{
+ put_net(xprt->xprt_net);
+ kfree(xprt->slot);
+ kfree(xprt);
+}
+EXPORT_SYMBOL_GPL(xprt_free);
+
/**
* xprt_reserve - allocate an RPC request slot
* @task: RPC task requesting a slot allocation
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index d718b8fa9525..09af4fab1a45 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -43,6 +43,7 @@
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/sysctl.h>
+#include <linux/workqueue.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/sched.h>
#include <linux/sunrpc/svc_rdma.h>
@@ -74,6 +75,8 @@ atomic_t rdma_stat_sq_prod;
struct kmem_cache *svc_rdma_map_cachep;
struct kmem_cache *svc_rdma_ctxt_cachep;
+struct workqueue_struct *svc_rdma_wq;
+
/*
* This function implements reading and resetting an atomic_t stat
* variable through read/write to a proc file. Any write to the file
@@ -231,7 +234,7 @@ static ctl_table svcrdma_root_table[] = {
void svc_rdma_cleanup(void)
{
dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
- flush_scheduled_work();
+ destroy_workqueue(svc_rdma_wq);
if (svcrdma_table_header) {
unregister_sysctl_table(svcrdma_table_header);
svcrdma_table_header = NULL;
@@ -249,6 +252,11 @@ int svc_rdma_init(void)
dprintk("\tsq_depth : %d\n",
svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT);
dprintk("\tmax_inline : %d\n", svcrdma_max_req_size);
+
+ svc_rdma_wq = alloc_workqueue("svc_rdma", 0, 0);
+ if (!svc_rdma_wq)
+ return -ENOMEM;
+
if (!svcrdma_table_header)
svcrdma_table_header =
register_sysctl_table(svcrdma_root_table);
@@ -283,6 +291,7 @@ int svc_rdma_init(void)
kmem_cache_destroy(svc_rdma_map_cachep);
err0:
unregister_sysctl_table(svcrdma_table_header);
+ destroy_workqueue(svc_rdma_wq);
return -ENOMEM;
}
MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>");
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 0194de814933..df67211c4baf 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -263,9 +263,9 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
frmr->page_list_len = PAGE_ALIGN(byte_count) >> PAGE_SHIFT;
for (page_no = 0; page_no < frmr->page_list_len; page_no++) {
frmr->page_list->page_list[page_no] =
- ib_dma_map_single(xprt->sc_cm_id->device,
- page_address(rqstp->rq_arg.pages[page_no]),
- PAGE_SIZE, DMA_FROM_DEVICE);
+ ib_dma_map_page(xprt->sc_cm_id->device,
+ rqstp->rq_arg.pages[page_no], 0,
+ PAGE_SIZE, DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[page_no]))
goto fatal_err;
@@ -309,17 +309,21 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
int count)
{
int i;
+ unsigned long off;
ctxt->count = count;
ctxt->direction = DMA_FROM_DEVICE;
for (i = 0; i < count; i++) {
ctxt->sge[i].length = 0; /* in case map fails */
if (!frmr) {
+ BUG_ON(0 == virt_to_page(vec[i].iov_base));
+ off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
ctxt->sge[i].addr =
- ib_dma_map_single(xprt->sc_cm_id->device,
- vec[i].iov_base,
- vec[i].iov_len,
- DMA_FROM_DEVICE);
+ ib_dma_map_page(xprt->sc_cm_id->device,
+ virt_to_page(vec[i].iov_base),
+ off,
+ vec[i].iov_len,
+ DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
ctxt->sge[i].addr))
return -EINVAL;
@@ -491,6 +495,7 @@ next_sge:
printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
err);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+ svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
goto out;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index b15e1ebb2bfa..249a835b703f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -70,8 +70,8 @@
* on extra page for the RPCRMDA header.
*/
static int fast_reg_xdr(struct svcxprt_rdma *xprt,
- struct xdr_buf *xdr,
- struct svc_rdma_req_map *vec)
+ struct xdr_buf *xdr,
+ struct svc_rdma_req_map *vec)
{
int sge_no;
u32 sge_bytes;
@@ -96,21 +96,25 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
vec->count = 2;
sge_no++;
- /* Build the FRMR */
+ /* Map the XDR head */
frmr->kva = frva;
frmr->direction = DMA_TO_DEVICE;
frmr->access_flags = 0;
frmr->map_len = PAGE_SIZE;
frmr->page_list_len = 1;
+ page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
frmr->page_list->page_list[page_no] =
- ib_dma_map_single(xprt->sc_cm_id->device,
- (void *)xdr->head[0].iov_base,
- PAGE_SIZE, DMA_TO_DEVICE);
+ ib_dma_map_page(xprt->sc_cm_id->device,
+ virt_to_page(xdr->head[0].iov_base),
+ page_off,
+ PAGE_SIZE - page_off,
+ DMA_TO_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[page_no]))
goto fatal_err;
atomic_inc(&xprt->sc_dma_used);
+ /* Map the XDR page list */
page_off = xdr->page_base;
page_bytes = xdr->page_len + page_off;
if (!page_bytes)
@@ -128,9 +132,9 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
page_bytes -= sge_bytes;
frmr->page_list->page_list[page_no] =
- ib_dma_map_single(xprt->sc_cm_id->device,
- page_address(page),
- PAGE_SIZE, DMA_TO_DEVICE);
+ ib_dma_map_page(xprt->sc_cm_id->device,
+ page, page_off,
+ sge_bytes, DMA_TO_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[page_no]))
goto fatal_err;
@@ -166,8 +170,10 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
frmr->page_list->page_list[page_no] =
- ib_dma_map_single(xprt->sc_cm_id->device, va, PAGE_SIZE,
- DMA_TO_DEVICE);
+ ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va),
+ page_off,
+ PAGE_SIZE,
+ DMA_TO_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[page_no]))
goto fatal_err;
@@ -245,6 +251,35 @@ static int map_xdr(struct svcxprt_rdma *xprt,
return 0;
}
+static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
+ struct xdr_buf *xdr,
+ u32 xdr_off, size_t len, int dir)
+{
+ struct page *page;
+ dma_addr_t dma_addr;
+ if (xdr_off < xdr->head[0].iov_len) {
+ /* This offset is in the head */
+ xdr_off += (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
+ page = virt_to_page(xdr->head[0].iov_base);
+ } else {
+ xdr_off -= xdr->head[0].iov_len;
+ if (xdr_off < xdr->page_len) {
+ /* This offset is in the page list */
+ page = xdr->pages[xdr_off >> PAGE_SHIFT];
+ xdr_off &= ~PAGE_MASK;
+ } else {
+ /* This offset is in the tail */
+ xdr_off -= xdr->page_len;
+ xdr_off += (unsigned long)
+ xdr->tail[0].iov_base & ~PAGE_MASK;
+ page = virt_to_page(xdr->tail[0].iov_base);
+ }
+ }
+ dma_addr = ib_dma_map_page(xprt->sc_cm_id->device, page, xdr_off,
+ min_t(size_t, PAGE_SIZE, len), dir);
+ return dma_addr;
+}
+
/* Assumptions:
* - We are using FRMR
* - or -
@@ -293,10 +328,9 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
sge[sge_no].length = sge_bytes;
if (!vec->frmr) {
sge[sge_no].addr =
- ib_dma_map_single(xprt->sc_cm_id->device,
- (void *)
- vec->sge[xdr_sge_no].iov_base + sge_off,
- sge_bytes, DMA_TO_DEVICE);
+ dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
+ sge_bytes, DMA_TO_DEVICE);
+ xdr_off += sge_bytes;
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
sge[sge_no].addr))
goto err;
@@ -333,6 +367,8 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
goto err;
return 0;
err:
+ svc_rdma_unmap_dma(ctxt);
+ svc_rdma_put_frmr(xprt, vec->frmr);
svc_rdma_put_context(ctxt, 0);
/* Fatal error, close transport */
return -EIO;
@@ -494,7 +530,8 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
* In all three cases, this function prepares the RPCRDMA header in
* sge[0], the 'type' parameter indicates the type to place in the
* RPCRDMA header, and the 'byte_count' field indicates how much of
- * the XDR to include in this RDMA_SEND.
+ * the XDR to include in this RDMA_SEND. NB: The offset of the payload
+ * to send is zero in the XDR.
*/
static int send_reply(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
@@ -536,23 +573,24 @@ static int send_reply(struct svcxprt_rdma *rdma,
ctxt->sge[0].lkey = rdma->sc_dma_lkey;
ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
ctxt->sge[0].addr =
- ib_dma_map_single(rdma->sc_cm_id->device, page_address(page),
- ctxt->sge[0].length, DMA_TO_DEVICE);
+ ib_dma_map_page(rdma->sc_cm_id->device, page, 0,
+ ctxt->sge[0].length, DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr))
goto err;
atomic_inc(&rdma->sc_dma_used);
ctxt->direction = DMA_TO_DEVICE;
- /* Determine how many of our SGE are to be transmitted */
+ /* Map the payload indicated by 'byte_count' */
for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
+ int xdr_off = 0;
sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
byte_count -= sge_bytes;
if (!vec->frmr) {
ctxt->sge[sge_no].addr =
- ib_dma_map_single(rdma->sc_cm_id->device,
- vec->sge[sge_no].iov_base,
- sge_bytes, DMA_TO_DEVICE);
+ dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
+ sge_bytes, DMA_TO_DEVICE);
+ xdr_off += sge_bytes;
if (ib_dma_mapping_error(rdma->sc_cm_id->device,
ctxt->sge[sge_no].addr))
goto err;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index edea15a54e51..9df1eadc912a 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -45,6 +45,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/workqueue.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <linux/sunrpc/svc_rdma.h>
@@ -52,6 +53,7 @@
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
+ struct net *net,
struct sockaddr *sa, int salen,
int flags);
static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt);
@@ -89,6 +91,9 @@ struct svc_xprt_class svc_rdma_class = {
/* WR context cache. Created in svc_rdma.c */
extern struct kmem_cache *svc_rdma_ctxt_cachep;
+/* Workqueue created in svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
+
struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
{
struct svc_rdma_op_ctxt *ctxt;
@@ -120,7 +125,7 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt)
*/
if (ctxt->sge[i].lkey == xprt->sc_dma_lkey) {
atomic_dec(&xprt->sc_dma_used);
- ib_dma_unmap_single(xprt->sc_cm_id->device,
+ ib_dma_unmap_page(xprt->sc_cm_id->device,
ctxt->sge[i].addr,
ctxt->sge[i].length,
ctxt->direction);
@@ -502,8 +507,8 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
BUG_ON(sge_no >= xprt->sc_max_sge);
page = svc_rdma_get_page();
ctxt->pages[sge_no] = page;
- pa = ib_dma_map_single(xprt->sc_cm_id->device,
- page_address(page), PAGE_SIZE,
+ pa = ib_dma_map_page(xprt->sc_cm_id->device,
+ page, 0, PAGE_SIZE,
DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device, pa))
goto err_put_ctxt;
@@ -511,9 +516,9 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
ctxt->sge[sge_no].addr = pa;
ctxt->sge[sge_no].length = PAGE_SIZE;
ctxt->sge[sge_no].lkey = xprt->sc_dma_lkey;
+ ctxt->count = sge_no + 1;
buflen += PAGE_SIZE;
}
- ctxt->count = sge_no;
recv_wr.next = NULL;
recv_wr.sg_list = &ctxt->sge[0];
recv_wr.num_sge = ctxt->count;
@@ -529,6 +534,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
return ret;
err_put_ctxt:
+ svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 1);
return -ENOMEM;
}
@@ -670,6 +676,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id,
* Create a listening RDMA service endpoint.
*/
static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
+ struct net *net,
struct sockaddr *sa, int salen,
int flags)
{
@@ -798,8 +805,8 @@ static void frmr_unmap_dma(struct svcxprt_rdma *xprt,
if (ib_dma_mapping_error(frmr->mr->device, addr))
continue;
atomic_dec(&xprt->sc_dma_used);
- ib_dma_unmap_single(frmr->mr->device, addr, PAGE_SIZE,
- frmr->direction);
+ ib_dma_unmap_page(frmr->mr->device, addr, PAGE_SIZE,
+ frmr->direction);
}
}
@@ -1184,7 +1191,7 @@ static void svc_rdma_free(struct svc_xprt *xprt)
struct svcxprt_rdma *rdma =
container_of(xprt, struct svcxprt_rdma, sc_xprt);
INIT_WORK(&rdma->sc_work, __svc_rdma_free);
- schedule_work(&rdma->sc_work);
+ queue_work(svc_rdma_wq, &rdma->sc_work);
}
static int svc_rdma_has_wspace(struct svc_xprt *xprt)
@@ -1274,7 +1281,7 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
atomic_read(&xprt->sc_sq_count) <
xprt->sc_sq_depth);
if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
- return 0;
+ return -ENOTCONN;
continue;
}
/* Take a transport ref for each WR posted */
@@ -1306,7 +1313,6 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
enum rpcrdma_errcode err)
{
struct ib_send_wr err_wr;
- struct ib_sge sge;
struct page *p;
struct svc_rdma_op_ctxt *ctxt;
u32 *va;
@@ -1319,26 +1325,27 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
/* XDR encode error */
length = svc_rdma_xdr_encode_error(xprt, rmsgp, err, va);
+ ctxt = svc_rdma_get_context(xprt);
+ ctxt->direction = DMA_FROM_DEVICE;
+ ctxt->count = 1;
+ ctxt->pages[0] = p;
+
/* Prepare SGE for local address */
- sge.addr = ib_dma_map_single(xprt->sc_cm_id->device,
- page_address(p), PAGE_SIZE, DMA_FROM_DEVICE);
- if (ib_dma_mapping_error(xprt->sc_cm_id->device, sge.addr)) {
+ ctxt->sge[0].addr = ib_dma_map_page(xprt->sc_cm_id->device,
+ p, 0, length, DMA_FROM_DEVICE);
+ if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[0].addr)) {
put_page(p);
return;
}
atomic_inc(&xprt->sc_dma_used);
- sge.lkey = xprt->sc_dma_lkey;
- sge.length = length;
-
- ctxt = svc_rdma_get_context(xprt);
- ctxt->count = 1;
- ctxt->pages[0] = p;
+ ctxt->sge[0].lkey = xprt->sc_dma_lkey;
+ ctxt->sge[0].length = length;
/* Prepare SEND WR */
memset(&err_wr, 0, sizeof err_wr);
ctxt->wr_op = IB_WR_SEND;
err_wr.wr_id = (unsigned long)ctxt;
- err_wr.sg_list = &sge;
+ err_wr.sg_list = ctxt->sge;
err_wr.num_sge = 1;
err_wr.opcode = IB_WR_SEND;
err_wr.send_flags = IB_SEND_SIGNALED;
@@ -1348,9 +1355,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
if (ret) {
dprintk("svcrdma: Error %d posting send for protocol error\n",
ret);
- ib_dma_unmap_single(xprt->sc_cm_id->device,
- sge.addr, PAGE_SIZE,
- DMA_FROM_DEVICE);
+ svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 1);
}
}
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index a85e866a77f7..0867070bb5ca 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -237,8 +237,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
dprintk("RPC: %s: called\n", __func__);
- cancel_delayed_work(&r_xprt->rdma_connect);
- flush_scheduled_work();
+ cancel_delayed_work_sync(&r_xprt->rdma_connect);
xprt_clear_connected(xprt);
@@ -251,9 +250,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
xprt_rdma_free_addresses(xprt);
- kfree(xprt->slot);
- xprt->slot = NULL;
- kfree(xprt);
+ xprt_free(xprt);
dprintk("RPC: %s: returning\n", __func__);
@@ -285,23 +282,14 @@ xprt_setup_rdma(struct xprt_create *args)
return ERR_PTR(-EBADF);
}
- xprt = kzalloc(sizeof(struct rpcrdma_xprt), GFP_KERNEL);
+ xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt),
+ xprt_rdma_slot_table_entries);
if (xprt == NULL) {
dprintk("RPC: %s: couldn't allocate rpcrdma_xprt\n",
__func__);
return ERR_PTR(-ENOMEM);
}
- xprt->max_reqs = xprt_rdma_slot_table_entries;
- xprt->slot = kcalloc(xprt->max_reqs,
- sizeof(struct rpc_rqst), GFP_KERNEL);
- if (xprt->slot == NULL) {
- dprintk("RPC: %s: couldn't allocate %d slots\n",
- __func__, xprt->max_reqs);
- kfree(xprt);
- return ERR_PTR(-ENOMEM);
- }
-
/* 60 second timeout, no retries */
xprt->timeout = &xprt_rdma_default_timeout;
xprt->bind_timeout = (60U * HZ);
@@ -410,8 +398,7 @@ out3:
out2:
rpcrdma_ia_close(&new_xprt->rx_ia);
out1:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ERR_PTR(rc);
}
@@ -460,7 +447,7 @@ xprt_rdma_connect(struct rpc_task *task)
} else {
schedule_delayed_work(&r_xprt->rdma_connect, 0);
if (!RPC_IS_ASYNC(task))
- flush_scheduled_work();
+ flush_delayed_work(&r_xprt->rdma_connect);
}
}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index fe9306bf10cc..dfcab5ac65af 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -774,8 +774,7 @@ static void xs_destroy(struct rpc_xprt *xprt)
xs_close(xprt);
xs_free_peer_addresses(xprt);
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
module_put(THIS_MODULE);
}
@@ -1516,7 +1515,7 @@ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
xs_update_peer_port(xprt);
}
-static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock)
+static unsigned short xs_get_srcport(struct sock_xprt *transport)
{
unsigned short port = transport->srcport;
@@ -1525,7 +1524,7 @@ static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket
return port;
}
-static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port)
+static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port)
{
if (transport->srcport != 0)
transport->srcport = 0;
@@ -1535,23 +1534,18 @@ static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket
return xprt_max_resvport;
return --port;
}
-
-static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
+static int xs_bind(struct sock_xprt *transport, struct socket *sock)
{
- struct sockaddr_in myaddr = {
- .sin_family = AF_INET,
- };
- struct sockaddr_in *sa;
+ struct sockaddr_storage myaddr;
int err, nloop = 0;
- unsigned short port = xs_get_srcport(transport, sock);
+ unsigned short port = xs_get_srcport(transport);
unsigned short last;
- sa = (struct sockaddr_in *)&transport->srcaddr;
- myaddr.sin_addr = sa->sin_addr;
+ memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);
do {
- myaddr.sin_port = htons(port);
- err = kernel_bind(sock, (struct sockaddr *) &myaddr,
- sizeof(myaddr));
+ rpc_set_port((struct sockaddr *)&myaddr, port);
+ err = kernel_bind(sock, (struct sockaddr *)&myaddr,
+ transport->xprt.addrlen);
if (port == 0)
break;
if (err == 0) {
@@ -1559,48 +1553,23 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
break;
}
last = port;
- port = xs_next_srcport(transport, sock, port);
+ port = xs_next_srcport(transport, port);
if (port > last)
nloop++;
} while (err == -EADDRINUSE && nloop != 2);
- dprintk("RPC: %s %pI4:%u: %s (%d)\n",
- __func__, &myaddr.sin_addr,
- port, err ? "failed" : "ok", err);
- return err;
-}
-
-static int xs_bind6(struct sock_xprt *transport, struct socket *sock)
-{
- struct sockaddr_in6 myaddr = {
- .sin6_family = AF_INET6,
- };
- struct sockaddr_in6 *sa;
- int err, nloop = 0;
- unsigned short port = xs_get_srcport(transport, sock);
- unsigned short last;
- sa = (struct sockaddr_in6 *)&transport->srcaddr;
- myaddr.sin6_addr = sa->sin6_addr;
- do {
- myaddr.sin6_port = htons(port);
- err = kernel_bind(sock, (struct sockaddr *) &myaddr,
- sizeof(myaddr));
- if (port == 0)
- break;
- if (err == 0) {
- transport->srcport = port;
- break;
- }
- last = port;
- port = xs_next_srcport(transport, sock, port);
- if (port > last)
- nloop++;
- } while (err == -EADDRINUSE && nloop != 2);
- dprintk("RPC: xs_bind6 %pI6:%u: %s (%d)\n",
- &myaddr.sin6_addr, port, err ? "failed" : "ok", err);
+ if (myaddr.ss_family == AF_INET)
+ dprintk("RPC: %s %pI4:%u: %s (%d)\n", __func__,
+ &((struct sockaddr_in *)&myaddr)->sin_addr,
+ port, err ? "failed" : "ok", err);
+ else
+ dprintk("RPC: %s %pI6:%u: %s (%d)\n", __func__,
+ &((struct sockaddr_in6 *)&myaddr)->sin6_addr,
+ port, err ? "failed" : "ok", err);
return err;
}
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key xs_key[2];
static struct lock_class_key xs_slock_key[2];
@@ -1622,6 +1591,18 @@ static inline void xs_reclassify_socket6(struct socket *sock)
sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC",
&xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]);
}
+
+static inline void xs_reclassify_socket(int family, struct socket *sock)
+{
+ switch (family) {
+ case AF_INET:
+ xs_reclassify_socket4(sock);
+ break;
+ case AF_INET6:
+ xs_reclassify_socket6(sock);
+ break;
+ }
+}
#else
static inline void xs_reclassify_socket4(struct socket *sock)
{
@@ -1630,8 +1611,36 @@ static inline void xs_reclassify_socket4(struct socket *sock)
static inline void xs_reclassify_socket6(struct socket *sock)
{
}
+
+static inline void xs_reclassify_socket(int family, struct socket *sock)
+{
+}
#endif
+static struct socket *xs_create_sock(struct rpc_xprt *xprt,
+ struct sock_xprt *transport, int family, int type, int protocol)
+{
+ struct socket *sock;
+ int err;
+
+ err = __sock_create(xprt->xprt_net, family, type, protocol, &sock, 1);
+ if (err < 0) {
+ dprintk("RPC: can't create %d transport socket (%d).\n",
+ protocol, -err);
+ goto out;
+ }
+ xs_reclassify_socket(family, sock);
+
+ if (xs_bind(transport, sock)) {
+ sock_release(sock);
+ goto out;
+ }
+
+ return sock;
+out:
+ return ERR_PTR(err);
+}
+
static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -1661,82 +1670,23 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
xs_udp_do_set_buffer_size(xprt);
}
-/**
- * xs_udp_connect_worker4 - set up a UDP socket
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
-static void xs_udp_connect_worker4(struct work_struct *work)
+static void xs_udp_setup_socket(struct work_struct *work)
{
struct sock_xprt *transport =
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
- int err, status = -EIO;
+ int status = -EIO;
if (xprt->shutdown)
goto out;
/* Start by resetting any existing state */
xs_reset_transport(transport);
-
- err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
+ sock = xs_create_sock(xprt, transport,
+ xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP);
+ if (IS_ERR(sock))
goto out;
- }
- xs_reclassify_socket4(sock);
-
- if (xs_bind4(transport, sock)) {
- sock_release(sock);
- goto out;
- }
-
- dprintk("RPC: worker connecting xprt %p via %s to "
- "%s (port %s)\n", xprt,
- xprt->address_strings[RPC_DISPLAY_PROTO],
- xprt->address_strings[RPC_DISPLAY_ADDR],
- xprt->address_strings[RPC_DISPLAY_PORT]);
-
- xs_udp_finish_connecting(xprt, sock);
- status = 0;
-out:
- xprt_clear_connecting(xprt);
- xprt_wake_pending_tasks(xprt, status);
-}
-
-/**
- * xs_udp_connect_worker6 - set up a UDP socket
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
-static void xs_udp_connect_worker6(struct work_struct *work)
-{
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
- struct socket *sock = transport->sock;
- int err, status = -EIO;
-
- if (xprt->shutdown)
- goto out;
-
- /* Start by resetting any existing state */
- xs_reset_transport(transport);
-
- err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
- goto out;
- }
- xs_reclassify_socket6(sock);
-
- if (xs_bind6(transport, sock) < 0) {
- sock_release(sock);
- goto out;
- }
dprintk("RPC: worker connecting xprt %p via %s to "
"%s (port %s)\n", xprt,
@@ -1755,12 +1705,12 @@ out:
* We need to preserve the port number so the reply cache on the server can
* find our cached RPC replies when we get around to reconnecting.
*/
-static void xs_abort_connection(struct rpc_xprt *xprt, struct sock_xprt *transport)
+static void xs_abort_connection(struct sock_xprt *transport)
{
int result;
struct sockaddr any;
- dprintk("RPC: disconnecting xprt %p to reuse port\n", xprt);
+ dprintk("RPC: disconnecting xprt %p to reuse port\n", transport);
/*
* Disconnect the transport socket by doing a connect operation
@@ -1770,13 +1720,13 @@ static void xs_abort_connection(struct rpc_xprt *xprt, struct sock_xprt *transpo
any.sa_family = AF_UNSPEC;
result = kernel_connect(transport->sock, &any, sizeof(any), 0);
if (!result)
- xs_sock_mark_closed(xprt);
+ xs_sock_mark_closed(&transport->xprt);
else
dprintk("RPC: AF_UNSPEC connect return code %d\n",
result);
}
-static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *transport)
+static void xs_tcp_reuse_connection(struct sock_xprt *transport)
{
unsigned int state = transport->inet->sk_state;
@@ -1799,7 +1749,7 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *tra
"sk_shutdown set to %d\n",
__func__, transport->inet->sk_shutdown);
}
- xs_abort_connection(xprt, transport);
+ xs_abort_connection(transport);
}
static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
@@ -1852,12 +1802,12 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
*
* Invoked by a work queue tasklet.
*/
-static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
- struct sock_xprt *transport,
- struct socket *(*create_sock)(struct rpc_xprt *,
- struct sock_xprt *))
+static void xs_tcp_setup_socket(struct work_struct *work)
{
+ struct sock_xprt *transport =
+ container_of(work, struct sock_xprt, connect_worker.work);
struct socket *sock = transport->sock;
+ struct rpc_xprt *xprt = &transport->xprt;
int status = -EIO;
if (xprt->shutdown)
@@ -1865,7 +1815,8 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
if (!sock) {
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
- sock = create_sock(xprt, transport);
+ sock = xs_create_sock(xprt, transport,
+ xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP);
if (IS_ERR(sock)) {
status = PTR_ERR(sock);
goto out;
@@ -1876,7 +1827,7 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
&xprt->state);
/* "close" the socket, preserving the local port */
- xs_tcp_reuse_connection(xprt, transport);
+ xs_tcp_reuse_connection(transport);
if (abort_and_exit)
goto out_eagain;
@@ -1925,84 +1876,6 @@ out:
xprt_wake_pending_tasks(xprt, status);
}
-static struct socket *xs_create_tcp_sock4(struct rpc_xprt *xprt,
- struct sock_xprt *transport)
-{
- struct socket *sock;
- int err;
-
- /* start from scratch */
- err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create TCP transport socket (%d).\n",
- -err);
- goto out_err;
- }
- xs_reclassify_socket4(sock);
-
- if (xs_bind4(transport, sock) < 0) {
- sock_release(sock);
- goto out_err;
- }
- return sock;
-out_err:
- return ERR_PTR(-EIO);
-}
-
-/**
- * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
-static void xs_tcp_connect_worker4(struct work_struct *work)
-{
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
-
- xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock4);
-}
-
-static struct socket *xs_create_tcp_sock6(struct rpc_xprt *xprt,
- struct sock_xprt *transport)
-{
- struct socket *sock;
- int err;
-
- /* start from scratch */
- err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock);
- if (err < 0) {
- dprintk("RPC: can't create TCP transport socket (%d).\n",
- -err);
- goto out_err;
- }
- xs_reclassify_socket6(sock);
-
- if (xs_bind6(transport, sock) < 0) {
- sock_release(sock);
- goto out_err;
- }
- return sock;
-out_err:
- return ERR_PTR(-EIO);
-}
-
-/**
- * xs_tcp_connect_worker6 - connect a TCP socket to a remote endpoint
- * @work: RPC transport to connect
- *
- * Invoked by a work queue tasklet.
- */
-static void xs_tcp_connect_worker6(struct work_struct *work)
-{
- struct sock_xprt *transport =
- container_of(work, struct sock_xprt, connect_worker.work);
- struct rpc_xprt *xprt = &transport->xprt;
-
- xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock6);
-}
-
/**
* xs_connect - connect a socket to a remote endpoint
* @task: address of RPC task that manages state of connect request
@@ -2262,6 +2135,31 @@ static struct rpc_xprt_ops bc_tcp_ops = {
.print_stats = xs_tcp_print_stats,
};
+static int xs_init_anyaddr(const int family, struct sockaddr *sap)
+{
+ static const struct sockaddr_in sin = {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = htonl(INADDR_ANY),
+ };
+ static const struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ };
+
+ switch (family) {
+ case AF_INET:
+ memcpy(sap, &sin, sizeof(sin));
+ break;
+ case AF_INET6:
+ memcpy(sap, &sin6, sizeof(sin6));
+ break;
+ default:
+ dprintk("RPC: %s: Bad address family\n", __func__);
+ return -EAFNOSUPPORT;
+ }
+ return 0;
+}
+
static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
unsigned int slot_table_size)
{
@@ -2273,27 +2171,25 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
return ERR_PTR(-EBADF);
}
- new = kzalloc(sizeof(*new), GFP_KERNEL);
- if (new == NULL) {
+ xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size);
+ if (xprt == NULL) {
dprintk("RPC: xs_setup_xprt: couldn't allocate "
"rpc_xprt\n");
return ERR_PTR(-ENOMEM);
}
- xprt = &new->xprt;
-
- xprt->max_reqs = slot_table_size;
- xprt->slot = kcalloc(xprt->max_reqs, sizeof(struct rpc_rqst), GFP_KERNEL);
- if (xprt->slot == NULL) {
- kfree(xprt);
- dprintk("RPC: xs_setup_xprt: couldn't allocate slot "
- "table\n");
- return ERR_PTR(-ENOMEM);
- }
+ new = container_of(xprt, struct sock_xprt, xprt);
memcpy(&xprt->addr, args->dstaddr, args->addrlen);
xprt->addrlen = args->addrlen;
if (args->srcaddr)
memcpy(&new->srcaddr, args->srcaddr, args->addrlen);
+ else {
+ int err;
+ err = xs_init_anyaddr(args->dstaddr->sa_family,
+ (struct sockaddr *)&new->srcaddr);
+ if (err != 0)
+ return ERR_PTR(err);
+ }
return xprt;
}
@@ -2341,7 +2237,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_udp_connect_worker4);
+ xs_udp_setup_socket);
xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
break;
case AF_INET6:
@@ -2349,7 +2245,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_udp_connect_worker6);
+ xs_udp_setup_socket);
xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6);
break;
default:
@@ -2371,8 +2267,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
return xprt;
ret = ERR_PTR(-EINVAL);
out_err:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ret;
}
@@ -2416,7 +2311,7 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_tcp_connect_worker4);
+ xs_tcp_setup_socket);
xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP);
break;
case AF_INET6:
@@ -2424,7 +2319,7 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
xprt_set_bound(xprt);
INIT_DELAYED_WORK(&transport->connect_worker,
- xs_tcp_connect_worker6);
+ xs_tcp_setup_socket);
xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6);
break;
default:
@@ -2447,8 +2342,7 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
return xprt;
ret = ERR_PTR(-EINVAL);
out_err:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ret;
}
@@ -2507,15 +2401,10 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
goto out_err;
}
- if (xprt_bound(xprt))
- dprintk("RPC: set up xprt to %s (port %s) via %s\n",
- xprt->address_strings[RPC_DISPLAY_ADDR],
- xprt->address_strings[RPC_DISPLAY_PORT],
- xprt->address_strings[RPC_DISPLAY_PROTO]);
- else
- dprintk("RPC: set up xprt to %s (autobind) via %s\n",
- xprt->address_strings[RPC_DISPLAY_ADDR],
- xprt->address_strings[RPC_DISPLAY_PROTO]);
+ dprintk("RPC: set up xprt to %s (port %s) via %s\n",
+ xprt->address_strings[RPC_DISPLAY_ADDR],
+ xprt->address_strings[RPC_DISPLAY_PORT],
+ xprt->address_strings[RPC_DISPLAY_PROTO]);
/*
* Since we don't want connections for the backchannel, we set
@@ -2528,8 +2417,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
return xprt;
ret = ERR_PTR(-EINVAL);
out_err:
- kfree(xprt->slot);
- kfree(xprt);
+ xprt_free(xprt);
return ret;
}