summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/Makefile2
-rw-r--r--net/ceph/auth_x.c76
-rw-r--r--net/ceph/auth_x.h1
-rw-r--r--net/ceph/buffer.c4
-rw-r--r--net/ceph/ceph_common.c21
-rw-r--r--net/ceph/messenger.c34
-rw-r--r--net/ceph/osd_client.c118
-rw-r--r--net/core/net_namespace.c39
-rw-r--r--net/nonet.c26
-rw-r--r--net/socket.c19
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c2
-rw-r--r--net/sunrpc/cache.c26
-rw-r--r--net/sunrpc/svc.c42
-rw-r--r--net/sunrpc/svc_xprt.c292
-rw-r--r--net/sunrpc/svcsock.c5
-rw-r--r--net/sunrpc/xdr.c9
16 files changed, 423 insertions, 293 deletions
diff --git a/net/Makefile b/net/Makefile
index 95fc694e4dd..38704bdf941 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -5,8 +5,6 @@
# Rewritten to use lists instead of if-statements.
#
-obj-y := nonet.o
-
obj-$(CONFIG_NET) := socket.o core/
tmp-$(CONFIG_COMPAT) := compat.o
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 7e38b729696..15845814a0f 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -8,6 +8,7 @@
#include <linux/ceph/decode.h>
#include <linux/ceph/auth.h>
+#include <linux/ceph/messenger.h>
#include "crypto.h"
#include "auth_x.h"
@@ -293,6 +294,11 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
dout("build_authorizer for %s %p\n",
ceph_entity_type_name(th->service), au);
+ ceph_crypto_key_destroy(&au->session_key);
+ ret = ceph_crypto_key_clone(&au->session_key, &th->session_key);
+ if (ret)
+ return ret;
+
maxlen = sizeof(*msg_a) + sizeof(msg_b) +
ceph_x_encrypt_buflen(ticket_blob_len);
dout(" need len %d\n", maxlen);
@@ -302,8 +308,10 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
}
if (!au->buf) {
au->buf = ceph_buffer_new(maxlen, GFP_NOFS);
- if (!au->buf)
+ if (!au->buf) {
+ ceph_crypto_key_destroy(&au->session_key);
return -ENOMEM;
+ }
}
au->service = th->service;
au->secret_id = th->secret_id;
@@ -329,7 +337,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
get_random_bytes(&au->nonce, sizeof(au->nonce));
msg_b.struct_v = 1;
msg_b.nonce = cpu_to_le64(au->nonce);
- ret = ceph_x_encrypt(&th->session_key, &msg_b, sizeof(msg_b),
+ ret = ceph_x_encrypt(&au->session_key, &msg_b, sizeof(msg_b),
p, end - p);
if (ret < 0)
goto out_buf;
@@ -560,6 +568,8 @@ static int ceph_x_create_authorizer(
auth->authorizer_buf_len = au->buf->vec.iov_len;
auth->authorizer_reply_buf = au->reply_buf;
auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+ auth->sign_message = ac->ops->sign_message;
+ auth->check_message_signature = ac->ops->check_message_signature;
return 0;
}
@@ -588,17 +598,13 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
struct ceph_authorizer *a, size_t len)
{
struct ceph_x_authorizer *au = (void *)a;
- struct ceph_x_ticket_handler *th;
int ret = 0;
struct ceph_x_authorize_reply reply;
void *preply = &reply;
void *p = au->reply_buf;
void *end = p + sizeof(au->reply_buf);
- th = get_ticket_handler(ac, au->service);
- if (IS_ERR(th))
- return PTR_ERR(th);
- ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply));
+ ret = ceph_x_decrypt(&au->session_key, &p, end, &preply, sizeof(reply));
if (ret < 0)
return ret;
if (ret != sizeof(reply))
@@ -618,6 +624,7 @@ static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac,
{
struct ceph_x_authorizer *au = (void *)a;
+ ceph_crypto_key_destroy(&au->session_key);
ceph_buffer_put(au->buf);
kfree(au);
}
@@ -663,6 +670,59 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
memset(&th->validity, 0, sizeof(th->validity));
}
+static int calcu_signature(struct ceph_x_authorizer *au,
+ struct ceph_msg *msg, __le64 *sig)
+{
+ int ret;
+ char tmp_enc[40];
+ __le32 tmp[5] = {
+ 16u, msg->hdr.crc, msg->footer.front_crc,
+ msg->footer.middle_crc, msg->footer.data_crc,
+ };
+ ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
+ tmp_enc, sizeof(tmp_enc));
+ if (ret < 0)
+ return ret;
+ *sig = *(__le64*)(tmp_enc + 4);
+ return 0;
+}
+
+static int ceph_x_sign_message(struct ceph_auth_handshake *auth,
+ struct ceph_msg *msg)
+{
+ int ret;
+ if (!auth->authorizer)
+ return 0;
+ ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+ msg, &msg->footer.sig);
+ if (ret < 0)
+ return ret;
+ msg->footer.flags |= CEPH_MSG_FOOTER_SIGNED;
+ return 0;
+}
+
+static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
+ struct ceph_msg *msg)
+{
+ __le64 sig_check;
+ int ret;
+
+ if (!auth->authorizer)
+ return 0;
+ ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+ msg, &sig_check);
+ if (ret < 0)
+ return ret;
+ if (sig_check == msg->footer.sig)
+ return 0;
+ if (msg->footer.flags & CEPH_MSG_FOOTER_SIGNED)
+ dout("ceph_x_check_message_signature %p has signature %llx "
+ "expect %llx\n", msg, msg->footer.sig, sig_check);
+ else
+ dout("ceph_x_check_message_signature %p sender did not set "
+ "CEPH_MSG_FOOTER_SIGNED\n", msg);
+ return -EBADMSG;
+}
static const struct ceph_auth_client_ops ceph_x_ops = {
.name = "x",
@@ -677,6 +737,8 @@ static const struct ceph_auth_client_ops ceph_x_ops = {
.invalidate_authorizer = ceph_x_invalidate_authorizer,
.reset = ceph_x_reset,
.destroy = ceph_x_destroy,
+ .sign_message = ceph_x_sign_message,
+ .check_message_signature = ceph_x_check_message_signature,
};
diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h
index 65ee72082d9..e8b7c6917d4 100644
--- a/net/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -26,6 +26,7 @@ struct ceph_x_ticket_handler {
struct ceph_x_authorizer {
+ struct ceph_crypto_key session_key;
struct ceph_buffer *buf;
unsigned int service;
u64 nonce;
diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c
index 621b5f65407..add5f921a0f 100644
--- a/net/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -6,7 +6,7 @@
#include <linux/ceph/buffer.h>
#include <linux/ceph/decode.h>
-#include <linux/ceph/libceph.h> /* for ceph_kv{malloc,free} */
+#include <linux/ceph/libceph.h> /* for ceph_kvmalloc */
struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
{
@@ -35,7 +35,7 @@ void ceph_buffer_release(struct kref *kref)
struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref);
dout("buffer_release %p\n", b);
- ceph_kvfree(b->vec.iov_base);
+ kvfree(b->vec.iov_base);
kfree(b);
}
EXPORT_SYMBOL(ceph_buffer_release);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 58fbfe134f9..5d5ab67f516 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -184,14 +184,6 @@ void *ceph_kvmalloc(size_t size, gfp_t flags)
return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL);
}
-void ceph_kvfree(const void *ptr)
-{
- if (is_vmalloc_addr(ptr))
- vfree(ptr);
- else
- kfree(ptr);
-}
-
static int parse_fsid(const char *str, struct ceph_fsid *fsid)
{
@@ -245,6 +237,8 @@ enum {
Opt_noshare,
Opt_crc,
Opt_nocrc,
+ Opt_cephx_require_signatures,
+ Opt_nocephx_require_signatures,
};
static match_table_t opt_tokens = {
@@ -263,6 +257,8 @@ static match_table_t opt_tokens = {
{Opt_noshare, "noshare"},
{Opt_crc, "crc"},
{Opt_nocrc, "nocrc"},
+ {Opt_cephx_require_signatures, "cephx_require_signatures"},
+ {Opt_nocephx_require_signatures, "nocephx_require_signatures"},
{-1, NULL}
};
@@ -461,6 +457,12 @@ ceph_parse_options(char *options, const char *dev_name,
case Opt_nocrc:
opt->flags |= CEPH_OPT_NOCRC;
break;
+ case Opt_cephx_require_signatures:
+ opt->flags &= ~CEPH_OPT_NOMSGAUTH;
+ break;
+ case Opt_nocephx_require_signatures:
+ opt->flags |= CEPH_OPT_NOMSGAUTH;
+ break;
default:
BUG_ON(token);
@@ -504,6 +506,9 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
init_waitqueue_head(&client->auth_wq);
client->auth_err = 0;
+ if (!ceph_test_opt(client, NOMSGAUTH))
+ required_features |= CEPH_FEATURE_MSG_AUTH;
+
client->extra_mon_dispatch = NULL;
client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
supported_features;
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 8d1653caffd..33a2f201e46 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1196,8 +1196,18 @@ static void prepare_write_message_footer(struct ceph_connection *con)
dout("prepare_write_message_footer %p\n", con);
con->out_kvec_is_msg = true;
con->out_kvec[v].iov_base = &m->footer;
- con->out_kvec[v].iov_len = sizeof(m->footer);
- con->out_kvec_bytes += sizeof(m->footer);
+ if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
+ if (con->ops->sign_message)
+ con->ops->sign_message(con, m);
+ else
+ m->footer.sig = 0;
+ con->out_kvec[v].iov_len = sizeof(m->footer);
+ con->out_kvec_bytes += sizeof(m->footer);
+ } else {
+ m->old_footer.flags = m->footer.flags;
+ con->out_kvec[v].iov_len = sizeof(m->old_footer);
+ con->out_kvec_bytes += sizeof(m->old_footer);
+ }
con->out_kvec_left++;
con->out_more = m->more_to_follow;
con->out_msg_done = true;
@@ -2249,6 +2259,7 @@ static int read_partial_message(struct ceph_connection *con)
int ret;
unsigned int front_len, middle_len, data_len;
bool do_datacrc = !con->msgr->nocrc;
+ bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
u64 seq;
u32 crc;
@@ -2361,12 +2372,21 @@ static int read_partial_message(struct ceph_connection *con)
}
/* footer */
- size = sizeof (m->footer);
+ if (need_sign)
+ size = sizeof(m->footer);
+ else
+ size = sizeof(m->old_footer);
+
end += size;
ret = read_partial(con, end, size, &m->footer);
if (ret <= 0)
return ret;
+ if (!need_sign) {
+ m->footer.flags = m->old_footer.flags;
+ m->footer.sig = 0;
+ }
+
dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
m, front_len, m->footer.front_crc, middle_len,
m->footer.middle_crc, data_len, m->footer.data_crc);
@@ -2390,6 +2410,12 @@ static int read_partial_message(struct ceph_connection *con)
return -EBADMSG;
}
+ if (need_sign && con->ops->check_message_signature &&
+ con->ops->check_message_signature(con, m)) {
+ pr_err("read_partial_message %p signature check failed\n", m);
+ return -EBADMSG;
+ }
+
return 1; /* done! */
}
@@ -3288,7 +3314,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
static void ceph_msg_free(struct ceph_msg *m)
{
dout("%s %p\n", __func__, m);
- ceph_kvfree(m->front.iov_base);
+ kvfree(m->front.iov_base);
kmem_cache_free(ceph_msg_cache, m);
}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6f164289bde..53299c7b0ca 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -292,6 +292,10 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
ceph_osd_data_release(&op->cls.request_data);
ceph_osd_data_release(&op->cls.response_data);
break;
+ case CEPH_OSD_OP_SETXATTR:
+ case CEPH_OSD_OP_CMPXATTR:
+ ceph_osd_data_release(&op->xattr.osd_data);
+ break;
default:
break;
}
@@ -476,8 +480,7 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
size_t payload_len = 0;
BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
- opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO &&
- opcode != CEPH_OSD_OP_TRUNCATE);
+ opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE);
op->extent.offset = offset;
op->extent.length = length;
@@ -545,6 +548,39 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
}
EXPORT_SYMBOL(osd_req_op_cls_init);
+int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
+ u16 opcode, const char *name, const void *value,
+ size_t size, u8 cmp_op, u8 cmp_mode)
+{
+ struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+ struct ceph_pagelist *pagelist;
+ size_t payload_len;
+
+ BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
+
+ pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+ if (!pagelist)
+ return -ENOMEM;
+
+ ceph_pagelist_init(pagelist);
+
+ payload_len = strlen(name);
+ op->xattr.name_len = payload_len;
+ ceph_pagelist_append(pagelist, name, payload_len);
+
+ op->xattr.value_len = size;
+ ceph_pagelist_append(pagelist, value, size);
+ payload_len += size;
+
+ op->xattr.cmp_op = cmp_op;
+ op->xattr.cmp_mode = cmp_mode;
+
+ ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist);
+ op->payload_len = payload_len;
+ return 0;
+}
+EXPORT_SYMBOL(osd_req_op_xattr_init);
+
void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode,
u64 cookie, u64 version, int flag)
@@ -626,7 +662,6 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
case CEPH_OSD_OP_READ:
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_ZERO:
- case CEPH_OSD_OP_DELETE:
case CEPH_OSD_OP_TRUNCATE:
if (src->op == CEPH_OSD_OP_WRITE)
request_data_len = src->extent.length;
@@ -676,6 +711,19 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
dst->alloc_hint.expected_write_size =
cpu_to_le64(src->alloc_hint.expected_write_size);
break;
+ case CEPH_OSD_OP_SETXATTR:
+ case CEPH_OSD_OP_CMPXATTR:
+ dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+ dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+ dst->xattr.cmp_op = src->xattr.cmp_op;
+ dst->xattr.cmp_mode = src->xattr.cmp_mode;
+ osd_data = &src->xattr.osd_data;
+ ceph_osdc_msg_data_add(req->r_request, osd_data);
+ request_data_len = osd_data->pagelist->length;
+ break;
+ case CEPH_OSD_OP_CREATE:
+ case CEPH_OSD_OP_DELETE:
+ break;
default:
pr_err("unsupported osd opcode %s\n",
ceph_osd_op_name(src->op));
@@ -705,7 +753,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
struct ceph_file_layout *layout,
struct ceph_vino vino,
- u64 off, u64 *plen, int num_ops,
+ u64 off, u64 *plen,
+ unsigned int which, int num_ops,
int opcode, int flags,
struct ceph_snap_context *snapc,
u32 truncate_seq,
@@ -716,13 +765,11 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
u64 objnum = 0;
u64 objoff = 0;
u64 objlen = 0;
- u32 object_size;
- u64 object_base;
int r;
BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
- opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO &&
- opcode != CEPH_OSD_OP_TRUNCATE);
+ opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
+ opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
GFP_NOFS);
@@ -738,29 +785,24 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
return ERR_PTR(r);
}
- object_size = le32_to_cpu(layout->fl_object_size);
- object_base = off - objoff;
- if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
- if (truncate_size <= object_base) {
- truncate_size = 0;
- } else {
- truncate_size -= object_base;
- if (truncate_size > object_size)
- truncate_size = object_size;
+ if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
+ osd_req_op_init(req, which, opcode);
+ } else {
+ u32 object_size = le32_to_cpu(layout->fl_object_size);
+ u32 object_base = off - objoff;
+ if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
+ if (truncate_size <= object_base) {
+ truncate_size = 0;
+ } else {
+ truncate_size -= object_base;
+ if (truncate_size > object_size)
+ truncate_size = object_size;
+ }
}
+ osd_req_op_extent_init(req, which, opcode, objoff, objlen,
+ truncate_size, truncate_seq);
}
- osd_req_op_extent_init(req, 0, opcode, objoff, objlen,
- truncate_size, truncate_seq);
-
- /*
- * A second op in the ops array means the caller wants to
- * also issue a include a 'startsync' command so that the
- * osd will flush data quickly.
- */
- if (num_ops > 1)
- osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
-
req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
snprintf(req->r_base_oid.name, sizeof(req->r_base_oid.name),
@@ -2626,7 +2668,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
vino.snap, off, *plen);
- req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 1,
+ req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, truncate_seq, truncate_size,
false);
@@ -2669,7 +2711,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
int page_align = off & ~PAGE_MASK;
BUG_ON(vino.snap != CEPH_NOSNAP); /* snapshots aren't writeable */
- req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 1,
+ req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
CEPH_OSD_OP_WRITE,
CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
snapc, truncate_seq, truncate_size,
@@ -2920,6 +2962,20 @@ static int invalidate_authorizer(struct ceph_connection *con)
return ceph_monc_validate_auth(&osdc->client->monc);
}
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+ struct ceph_osd *o = con->private;
+ struct ceph_auth_handshake *auth = &o->o_auth;
+ return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+ struct ceph_osd *o = con->private;
+ struct ceph_auth_handshake *auth = &o->o_auth;
+ return ceph_auth_check_message_signature(auth, msg);
+}
+
static const struct ceph_connection_operations osd_con_ops = {
.get = get_osd_con,
.put = put_osd_con,
@@ -2928,5 +2984,7 @@ static const struct ceph_connection_operations osd_con_ops = {
.verify_authorizer_reply = verify_authorizer_reply,
.invalidate_authorizer = invalidate_authorizer,
.alloc_msg = alloc_msg,
+ .sign_message = sign_message,
+ .check_message_signature = check_message_signature,
.fault = osd_reset,
};
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7f155175bba..ce780c722e4 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -337,17 +337,17 @@ EXPORT_SYMBOL_GPL(__put_net);
struct net *get_net_ns_by_fd(int fd)
{
- struct proc_ns *ei;
struct file *file;
+ struct ns_common *ns;
struct net *net;
file = proc_ns_fget(fd);
if (IS_ERR(file))
return ERR_CAST(file);
- ei = get_proc_ns(file_inode(file));
- if (ei->ns_ops == &netns_operations)
- net = get_net(ei->ns);
+ ns = get_proc_ns(file_inode(file));
+ if (ns->ops == &netns_operations)
+ net = get_net(container_of(ns, struct net, ns));
else
net = ERR_PTR(-EINVAL);
@@ -386,12 +386,15 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
static __net_init int net_ns_net_init(struct net *net)
{
- return proc_alloc_inum(&net->proc_inum);
+#ifdef CONFIG_NET_NS
+ net->ns.ops = &netns_operations;
+#endif
+ return ns_alloc_inum(&net->ns);
}
static __net_exit void net_ns_net_exit(struct net *net)
{
- proc_free_inum(net->proc_inum);
+ ns_free_inum(&net->ns);
}
static struct pernet_operations __net_initdata net_ns_ops = {
@@ -629,7 +632,7 @@ void unregister_pernet_device(struct pernet_operations *ops)
EXPORT_SYMBOL_GPL(unregister_pernet_device);
#ifdef CONFIG_NET_NS
-static void *netns_get(struct task_struct *task)
+static struct ns_common *netns_get(struct task_struct *task)
{
struct net *net = NULL;
struct nsproxy *nsproxy;
@@ -640,17 +643,22 @@ static void *netns_get(struct task_struct *task)
net = get_net(nsproxy->net_ns);
task_unlock(task);
- return net;
+ return net ? &net->ns : NULL;
}
-static void netns_put(void *ns)
+static inline struct net *to_net_ns(struct ns_common *ns)
{
- put_net(ns);
+ return container_of(ns, struct net, ns);
}
-static int netns_install(struct nsproxy *nsproxy, void *ns)
+static void netns_put(struct ns_common *ns)
{
- struct net *net = ns;
+ put_net(to_net_ns(ns));
+}
+
+static int netns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+{
+ struct net *net = to_net_ns(ns);
if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
@@ -661,18 +669,11 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
return 0;
}
-static unsigned int netns_inum(void *ns)
-{
- struct net *net = ns;
- return net->proc_inum;
-}
-
const struct proc_ns_operations netns_operations = {
.name = "net",
.type = CLONE_NEWNET,
.get = netns_get,
.put = netns_put,
.install = netns_install,
- .inum = netns_inum,
};
#endif
diff --git a/net/nonet.c b/net/nonet.c
deleted file mode 100644
index b1a73fda9c1..00000000000
--- a/net/nonet.c
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * net/nonet.c
- *
- * Dummy functions to allow us to configure network support entirely
- * out of the kernel.
- *
- * Distributed under the terms of the GNU GPL version 2.
- * Copyright (c) Matthew Wilcox 2003
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
-{
- return -ENXIO;
-}
-
-const struct file_operations bad_sock_fops = {
- .owner = THIS_MODULE,
- .open = sock_no_open,
- .llseek = noop_llseek,
-};
diff --git a/net/socket.c b/net/socket.c
index 8809afccf7f..70bbde65e4c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -113,7 +113,6 @@ unsigned int sysctl_net_busy_read __read_mostly;
unsigned int sysctl_net_busy_poll __read_mostly;
#endif
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos);
static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
@@ -151,7 +150,6 @@ static const struct file_operations socket_file_ops = {
.compat_ioctl = compat_sock_ioctl,
#endif
.mmap = sock_mmap,
- .open = sock_no_open, /* special open code to disallow open via /proc */
.release = sock_close,
.fasync = sock_fasync,
.sendpage = sock_sendpage,
@@ -559,23 +557,6 @@ static struct socket *sock_alloc(void)
return sock;
}
-/*
- * In theory you can't get an open on this inode, but /proc provides
- * a back door. Remember to keep it shut otherwise you'll let the
- * creepy crawlies in.
- */
-
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
-{
- return -ENXIO;
-}
-
-const struct file_operations bad_sock_fops = {
- .owner = THIS_MODULE,
- .open = sock_no_open,
- .llseek = noop_llseek,
-};
-
/**
* sock_release - close a socket
* @sock: socket to close
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index de856ddf5fe..224a82f24d3 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -886,7 +886,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
u32 priv_len, maj_stat;
int pad, saved_len, remaining_len, offset;
- rqstp->rq_splice_ok = false;
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
priv_len = svc_getnl(&buf->head[0]);
if (rqstp->rq_deferred) {
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 06636214113..33fb105d435 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -20,6 +20,7 @@
#include <linux/list.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/string_helpers.h>
#include <asm/uaccess.h>
#include <linux/poll.h>
#include <linux/seq_file.h>
@@ -1067,30 +1068,15 @@ void qword_add(char **bpp, int *lp, char *str)
{
char *bp = *bpp;
int len = *lp;
- char c;
+ int ret;
if (len < 0) return;
- while ((c=*str++) && len)
- switch(c) {
- case ' ':
- case '\t':
- case '\n':
- case '\\':
- if (len >= 4) {
- *bp++ = '\\';
- *bp++ = '0' + ((c & 0300)>>6);
- *bp++ = '0' + ((c & 0070)>>3);
- *bp++ = '0' + ((c & 0007)>>0);
- }
- len -= 4;
- break;
- default:
- *bp++ = c;
- len--;
- }
- if (c || len <1) len = -1;
+ ret = string_escape_str(str, &bp, len, ESCAPE_OCTAL, "\\ \n\t");
+ if (ret < 0 || ret == len)
+ len = -1;
else {
+ len -= ret;
*bp++ = ' ';
len--;
}
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 2783fd80c22..91eaef1844c 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -191,7 +191,7 @@ svc_pool_map_init_percpu(struct svc_pool_map *m)
return err;
for_each_online_cpu(cpu) {
- BUG_ON(pidx > maxpools);
+ BUG_ON(pidx >= maxpools);
m->to_pool[cpu] = pidx;
m->pool_to[pidx] = cpu;
pidx++;
@@ -476,15 +476,11 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
i, serv->sv_name);
pool->sp_id = i;
- INIT_LIST_HEAD(&pool->sp_threads);
INIT_LIST_HEAD(&pool->sp_sockets);
INIT_LIST_HEAD(&pool->sp_all_threads);
spin_lock_init(&pool->sp_lock);
}
- if (svc_uses_rpcbind(serv) && (!serv->sv_shutdown))
- serv->sv_shutdown = svc_rpcb_cleanup;
-
return serv;
}
@@ -505,13 +501,15 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
unsigned int npools = svc_pool_map_get();
serv = __svc_create(prog, bufsize, npools, shutdown);
+ if (!serv)
+ goto out_err;
- if (serv != NULL) {
- serv->sv_function = func;
- serv->sv_module = mod;
- }
-
+ serv->sv_function = func;
+ serv->sv_module = mod;
return serv;
+out_err:
+ svc_pool_map_put();
+ return NULL;
}
EXPORT_SYMBOL_GPL(svc_create_pooled);
@@ -615,12 +613,14 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
goto out_enomem;
serv->sv_nrthreads++;
+ __set_bit(RQ_BUSY, &rqstp->rq_flags);
+ spin_lock_init(&rqstp->rq_lock);
+ rqstp->rq_server = serv;
+ rqstp->rq_pool = pool;
spin_lock_bh(&pool->sp_lock);
pool->sp_nrthreads++;
- list_add(&rqstp->rq_all, &pool->sp_all_threads);
+ list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
spin_unlock_bh(&pool->sp_lock);
- rqstp->rq_server = serv;
- rqstp->rq_pool = pool;
rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
if (!rqstp->rq_argp)
@@ -685,7 +685,8 @@ found_pool:
* so we don't try to kill it again.
*/
rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
- list_del_init(&rqstp->rq_all);
+ set_bit(RQ_VICTIM, &rqstp->rq_flags);
+ list_del_rcu(&rqstp->rq_all);
task = rqstp->rq_task;
}
spin_unlock_bh(&pool->sp_lock);
@@ -783,10 +784,11 @@ svc_exit_thread(struct svc_rqst *rqstp)
spin_lock_bh(&pool->sp_lock);
pool->sp_nrthreads--;
- list_del(&rqstp->rq_all);
+ if (!test_and_set_bit(RQ_VICTIM, &rqstp->rq_flags))
+ list_del_rcu(&rqstp->rq_all);
spin_unlock_bh(&pool->sp_lock);
- kfree(rqstp);
+ kfree_rcu(rqstp, rq_rcu_head);
/* Release the server */
if (serv)
@@ -1086,10 +1088,10 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
goto err_short_len;
/* Will be turned off only in gss privacy case: */
- rqstp->rq_splice_ok = true;
+ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Will be turned off only when NFSv4 Sessions are used */
- rqstp->rq_usedeferral = true;
- rqstp->rq_dropme = false;
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_DROPME, &rqstp->rq_flags);
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1189,7 +1191,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
/* Encode reply */
- if (rqstp->rq_dropme) {
+ if (test_bit(RQ_DROPME, &rqstp->rq_flags)) {
if (procp->pc_release)
procp->pc_release(rqstp, NULL, rqstp->rq_resp);
goto dropit;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index bbb3b044b87..c69358b3cf7 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -220,9 +220,11 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
*/
static void svc_xprt_received(struct svc_xprt *xprt)
{
- WARN_ON_ONCE(!test_bit(XPT_BUSY, &xprt->xpt_flags));
- if (!test_bit(XPT_BUSY, &xprt->xpt_flags))
+ if (!test_bit(XPT_BUSY, &xprt->xpt_flags)) {
+ WARN_ONCE(1, "xprt=0x%p already busy!", xprt);
return;
+ }
+
/* As soon as we clear busy, the xprt could be closed and
* 'put', so we need a reference to call svc_xprt_do_enqueue with:
*/
@@ -310,25 +312,6 @@ char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
}
EXPORT_SYMBOL_GPL(svc_print_addr);
-/*
- * Queue up an idle server thread. Must have pool->sp_lock held.
- * Note: this is really a stack rather than a queue, so that we only
- * use as many different threads as we need, and the rest don't pollute
- * the cache.
- */
-static void svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
- list_add(&rqstp->rq_list, &pool->sp_threads);
-}
-
-/*
- * Dequeue an nfsd thread. Must have pool->sp_lock held.
- */
-static void svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
- list_del(&rqstp->rq_list);
-}
-
static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
{
if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE)))
@@ -341,11 +324,12 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
{
struct svc_pool *pool;
- struct svc_rqst *rqstp;
+ struct svc_rqst *rqstp = NULL;
int cpu;
+ bool queued = false;
if (!svc_xprt_has_something_to_do(xprt))
- return;
+ goto out;
/* Mark transport as busy. It will remain in this state until
* the provider calls svc_xprt_received. We update XPT_BUSY
@@ -355,43 +339,69 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
/* Don't enqueue transport while already enqueued */
dprintk("svc: transport %p busy, not enqueued\n", xprt);
- return;
+ goto out;
}
cpu = get_cpu();
pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
- spin_lock_bh(&pool->sp_lock);
- pool->sp_stats.packets++;
-
- if (!list_empty(&pool->sp_threads)) {
- rqstp = list_entry(pool->sp_threads.next,
- struct svc_rqst,
- rq_list);
- dprintk("svc: transport %p served by daemon %p\n",
- xprt, rqstp);
- svc_thread_dequeue(pool, rqstp);
- if (rqstp->rq_xprt)
- printk(KERN_ERR
- "svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
- rqstp, rqstp->rq_xprt);
- /* Note the order of the following 3 lines:
- * We want to assign xprt to rqstp->rq_xprt only _after_
- * we've woken up the process, so that we don't race with
- * the lockless check in svc_get_next_xprt().
+ atomic_long_inc(&pool->sp_stats.packets);
+
+redo_search:
+ /* find a thread for this xprt */
+ rcu_read_lock();
+ list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+ /* Do a lockless check first */
+ if (test_bit(RQ_BUSY, &rqstp->rq_flags))
+ continue;
+
+ /*
+ * Once the xprt has been queued, it can only be dequeued by
+ * the task that intends to service it. All we can do at that
+ * point is to try to wake this thread back up so that it can
+ * do so.
*/
- svc_xprt_get(xprt);
+ if (!queued) {
+ spin_lock_bh(&rqstp->rq_lock);
+ if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) {
+ /* already busy, move on... */
+ spin_unlock_bh(&rqstp->rq_lock);
+ continue;
+ }
+
+ /* this one will do */
+ rqstp->rq_xprt = xprt;
+ svc_xprt_get(xprt);
+ spin_unlock_bh(&rqstp->rq_lock);
+ }
+ rcu_read_unlock();
+
+ atomic_long_inc(&pool->sp_stats.threads_woken);
wake_up_process(rqstp->rq_task);
- rqstp->rq_xprt = xprt;
- pool->sp_stats.threads_woken++;
- } else {
+ put_cpu();
+ goto out;
+ }
+ rcu_read_unlock();
+
+ /*
+ * We didn't find an idle thread to use, so we need to queue the xprt.
+ * Do so and then search again. If we find one, we can't hook this one
+ * up to it directly but we can wake the thread up in the hopes that it
+ * will pick it up once it searches for a xprt to service.
+ */
+ if (!queued) {
+ queued = true;
dprintk("svc: transport %p put into queue\n", xprt);
+ spin_lock_bh(&pool->sp_lock);
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
pool->sp_stats.sockets_queued++;
+ spin_unlock_bh(&pool->sp_lock);
+ goto redo_search;
}
-
- spin_unlock_bh(&pool->sp_lock);
+ rqstp = NULL;
put_cpu();
+out:
+ trace_svc_xprt_do_enqueue(xprt, rqstp);
}
/*
@@ -408,22 +418,28 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
/*
- * Dequeue the first transport. Must be called with the pool->sp_lock held.
+ * Dequeue the first transport, if there is one.
*/
static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
{
- struct svc_xprt *xprt;
+ struct svc_xprt *xprt = NULL;
if (list_empty(&pool->sp_sockets))
- return NULL;
-
- xprt = list_entry(pool->sp_sockets.next,
- struct svc_xprt, xpt_ready);
- list_del_init(&xprt->xpt_ready);
+ goto out;
- dprintk("svc: transport %p dequeued, inuse=%d\n",
- xprt, atomic_read(&xprt->xpt_ref.refcount));
+ spin_lock_bh(&pool->sp_lock);
+ if (likely(!list_empty(&pool->sp_sockets))) {
+ xprt = list_first_entry(&pool->sp_sockets,
+ struct svc_xprt, xpt_ready);
+ list_del_init(&xprt->xpt_ready);
+ svc_xprt_get(xprt);
+ dprintk("svc: transport %p dequeued, inuse=%d\n",
+ xprt, atomic_read(&xprt->xpt_ref.refcount));
+ }
+ spin_unlock_bh(&pool->sp_lock);
+out:
+ trace_svc_xprt_dequeue(xprt);
return xprt;
}
@@ -484,34 +500,36 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
}
/*
- * External function to wake up a server waiting for data
- * This really only makes sense for services like lockd
- * which have exactly one thread anyway.
+ * Some svc_serv's will have occasional work to do, even when a xprt is not
+ * waiting to be serviced. This function is there to "kick" a task in one of
+ * those services so that it can wake up and do that work. Note that we only
+ * bother with pool 0 as we don't need to wake up more than one thread for
+ * this purpose.
*/
void svc_wake_up(struct svc_serv *serv)
{
struct svc_rqst *rqstp;
- unsigned int i;
struct svc_pool *pool;
- for (i = 0; i < serv->sv_nrpools; i++) {
- pool = &serv->sv_pools[i];
+ pool = &serv->sv_pools[0];
- spin_lock_bh(&pool->sp_lock);
- if (!list_empty(&pool->sp_threads)) {
- rqstp = list_entry(pool->sp_threads.next,
- struct svc_rqst,
- rq_list);
- dprintk("svc: daemon %p woken up.\n", rqstp);
- /*
- svc_thread_dequeue(pool, rqstp);
- rqstp->rq_xprt = NULL;
- */
- wake_up_process(rqstp->rq_task);
- } else
- pool->sp_task_pending = 1;
- spin_unlock_bh(&pool->sp_lock);
+ rcu_read_lock();
+ list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+ /* skip any that aren't queued */
+ if (test_bit(RQ_BUSY, &rqstp->rq_flags))
+ continue;
+ rcu_read_unlock();
+ dprintk("svc: daemon %p woken up.\n", rqstp);
+ wake_up_process(rqstp->rq_task);
+ trace_svc_wake_up(rqstp->rq_task->pid);
+ return;
}
+ rcu_read_unlock();
+
+ /* No free entries available */
+ set_bit(SP_TASK_PENDING, &pool->sp_flags);
+ smp_wmb();
+ trace_svc_wake_up(0);
}
EXPORT_SYMBOL_GPL(svc_wake_up);
@@ -622,75 +640,86 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
return 0;
}
+static bool
+rqst_should_sleep(struct svc_rqst *rqstp)
+{
+ struct svc_pool *pool = rqstp->rq_pool;
+
+ /* did someone call svc_wake_up? */
+ if (test_and_clear_bit(SP_TASK_PENDING, &pool->sp_flags))
+ return false;
+
+ /* was a socket queued? */
+ if (!list_empty(&pool->sp_sockets))
+ return false;
+
+ /* are we shutting down? */
+ if (signalled() || kthread_should_stop())
+ return false;
+
+ /* are we freezing? */
+ if (freezing(current))
+ return false;
+
+ return true;
+}
+
static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
{
struct svc_xprt *xprt;
struct svc_pool *pool = rqstp->rq_pool;
long time_left = 0;
+ /* rq_xprt should be clear on entry */
+ WARN_ON_ONCE(rqstp->rq_xprt);
+
/* 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) {
rqstp->rq_xprt = xprt;
- svc_xprt_get(xprt);
/* 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;
- pool->sp_task_pending = 0;
- } else {
- if (pool->sp_task_pending) {
- pool->sp_task_pending = 0;
- xprt = ERR_PTR(-EAGAIN);
- goto out;
- }
- /*
- * We have to be able to interrupt this wait
- * to bring down the daemons ...
- */
- set_current_state(TASK_INTERRUPTIBLE);
+ clear_bit(SP_TASK_PENDING, &pool->sp_flags);
+ return xprt;
+ }
- /* No data pending. Go to sleep */
- svc_thread_enqueue(pool, rqstp);
- spin_unlock_bh(&pool->sp_lock);
+ /*
+ * We have to be able to interrupt this wait
+ * to bring down the daemons ...
+ */
+ set_current_state(TASK_INTERRUPTIBLE);
+ clear_bit(RQ_BUSY, &rqstp->rq_flags);
+ smp_mb();
- if (!(signalled() || kthread_should_stop())) {
- time_left = schedule_timeout(timeout);
- __set_current_state(TASK_RUNNING);
+ if (likely(rqst_should_sleep(rqstp)))
+ time_left = schedule_timeout(timeout);
+ else
+ __set_current_state(TASK_RUNNING);
- try_to_freeze();
+ try_to_freeze();
- xprt = rqstp->rq_xprt;
- if (xprt != NULL)
- return xprt;
- } else
- __set_current_state(TASK_RUNNING);
+ spin_lock_bh(&rqstp->rq_lock);
+ set_bit(RQ_BUSY, &rqstp->rq_flags);
+ spin_unlock_bh(&rqstp->rq_lock);
- spin_lock_bh(&pool->sp_lock);
- if (!time_left)
- pool->sp_stats.threads_timedout++;
+ xprt = rqstp->rq_xprt;
+ if (xprt != NULL)
+ return xprt;
- xprt = rqstp->rq_xprt;
- if (!xprt) {
- svc_thread_dequeue(pool, rqstp);
- spin_unlock_bh(&pool->sp_lock);
- dprintk("svc: server %p, no data yet\n", rqstp);
- if (signalled() || kthread_should_stop())
- return ERR_PTR(-EINTR);
- else
- return ERR_PTR(-EAGAIN);
- }
- }
-out:
- spin_unlock_bh(&pool->sp_lock);
- return xprt;
+ if (!time_left)
+ atomic_long_inc(&pool->sp_stats.threads_timedout);
+
+ if (signalled() || kthread_should_stop())
+ return ERR_PTR(-EINTR);
+ return ERR_PTR(-EAGAIN);
}
static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
@@ -719,7 +748,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
dprintk("svc_recv: found XPT_CLOSE\n");
svc_delete_xprt(xprt);
/* Leave XPT_BUSY set on the dead xprt: */
- return 0;
+ goto out;
}
if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
struct svc_xprt *newxpt;
@@ -750,6 +779,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
}
/* clear XPT_BUSY: */
svc_xprt_received(xprt);
+out:
+ trace_svc_handle_xprt(xprt, len);
return len;
}
@@ -797,7 +828,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
clear_bit(XPT_OLD, &xprt->xpt_flags);
- rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp);
+ if (xprt->xpt_ops->xpo_secure_port(rqstp))
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
+ else
+ clear_bit(RQ_SECURE, &rqstp->rq_flags);
rqstp->rq_chandle.defer = svc_defer;
rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]);
@@ -895,7 +929,6 @@ static void svc_age_temp_xprts(unsigned long closure)
continue;
list_del_init(le);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
- set_bit(XPT_DETACHED, &xprt->xpt_flags);
dprintk("queuing xprt %p for closing\n", xprt);
/* a thread will dequeue and close it soon */
@@ -935,8 +968,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
xprt->xpt_ops->xpo_detach(xprt);
spin_lock_bh(&serv->sv_lock);
- if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags))
- list_del_init(&xprt->xpt_list);
+ list_del_init(&xprt->xpt_list);
WARN_ON_ONCE(!list_empty(&xprt->xpt_ready));
if (test_bit(XPT_TEMP, &xprt->xpt_flags))
serv->sv_tmpcnt--;
@@ -1080,7 +1112,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
struct svc_deferred_req *dr;
- if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
+ if (rqstp->rq_arg.page_len || !test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags))
return NULL; /* if more than a page, give up FIXME */
if (rqstp->rq_deferred) {
dr = rqstp->rq_deferred;
@@ -1109,7 +1141,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
}
svc_xprt_get(rqstp->rq_xprt);
dr->xprt = rqstp->rq_xprt;
- rqstp->rq_dropme = true;
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
dr->handle.revisit = svc_revisit;
return &dr->handle;
@@ -1311,10 +1343,10 @@ static int svc_pool_stats_show(struct seq_file *m, void *p)
seq_printf(m, "%u %lu %lu %lu %lu\n",
pool->sp_id,
- pool->sp_stats.packets,
+ (unsigned long)atomic_long_read(&pool->sp_stats.packets),
pool->sp_stats.sockets_queued,
- pool->sp_stats.threads_woken,
- pool->sp_stats.threads_timedout);
+ (unsigned long)atomic_long_read(&pool->sp_stats.threads_woken),
+ (unsigned long)atomic_long_read(&pool->sp_stats.threads_timedout));
return 0;
}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index f9c052d508f..cc331b6cf57 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1145,7 +1145,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
- rqstp->rq_local = !!test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags);
+ if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
+ set_bit(RQ_LOCAL, &rqstp->rq_flags);
+ else
+ clear_bit(RQ_LOCAL, &rqstp->rq_flags);
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
calldir = p[1];
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 290af97bf6f..1cb61242e55 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -617,9 +617,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
fraglen = min_t(int, buf->len - len, tail->iov_len);
tail->iov_len -= fraglen;
buf->len -= fraglen;
- if (tail->iov_len && buf->len == len) {
+ if (tail->iov_len) {
xdr->p = tail->iov_base + tail->iov_len;
- /* xdr->end, xdr->iov should be set already */
+ WARN_ON_ONCE(!xdr->end);
+ WARN_ON_ONCE(!xdr->iov);
return;
}
WARN_ON_ONCE(fraglen);
@@ -631,11 +632,11 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
old = new + fraglen;
xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT);
- if (buf->page_len && buf->len == len) {
+ if (buf->page_len) {
xdr->p = page_address(*xdr->page_ptr);
xdr->end = (void *)xdr->p + PAGE_SIZE;
xdr->p = (void *)xdr->p + (new % PAGE_SIZE);
- /* xdr->iov should already be NULL */
+ WARN_ON_ONCE(xdr->iov);
return;
}
if (fraglen) {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-15 02:19:58 +0000