aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/9p/client.c2
-rw-r--r--net/9p/trans_virtio.c2
-rw-r--r--net/bluetooth/6lowpan.c2
-rw-r--r--net/bluetooth/a2mp.c2
-rw-r--r--net/bluetooth/smp.c2
-rw-r--r--net/ceph/messenger.c113
-rw-r--r--net/ceph/msgpool.c27
-rw-r--r--net/ceph/osd_client.c363
-rw-r--r--net/ceph/pagelist.c20
-rw-r--r--net/core/rtnetlink.c10
-rw-r--r--net/ipv4/igmp.c53
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_bpf.c1
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c2
-rw-r--r--net/openvswitch/flow_netlink.c4
-rw-r--r--net/sctp/associola.c10
-rw-r--r--net/sctp/protocol.c2
-rw-r--r--net/sctp/socket.c8
-rw-r--r--net/smc/smc_clc.c4
-rw-r--r--net/socket.c6
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c41
-rw-r--r--net/sunrpc/cache.c153
-rw-r--r--net/sunrpc/svc_xprt.c2
-rw-r--r--net/sunrpc/svcauth.c74
-rw-r--r--net/sunrpc/svcauth_unix.c24
-rw-r--r--net/sunrpc/svcsock.c55
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_backchannel.c23
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c10
-rw-r--r--net/sunrpc/xprtsock.c4
-rw-r--r--net/tipc/topsrv.c2
-rw-r--r--net/tls/tls_device.c4
-rw-r--r--net/tls/tls_sw.c4
-rw-r--r--net/xfrm/Kconfig1
-rw-r--r--net/xfrm/xfrm_hash.c2
36 files changed, 655 insertions, 383 deletions
diff --git a/net/9p/client.c b/net/9p/client.c
index 5f23e18eecc0..2c9a17b9b46b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -2066,7 +2066,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
struct kvec kv = {.iov_base = data, .iov_len = count};
struct iov_iter to;
- iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count);
+ iov_iter_kvec(&to, READ, &kv, 1, count);
p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n",
fid->fid, (unsigned long long) offset, count);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index eb596c2ed546..b1d39cabf125 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -329,7 +329,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
if (!iov_iter_count(data))
return 0;
- if (!(data->type & ITER_KVEC)) {
+ if (!iov_iter_is_kvec(data)) {
int n;
/*
* We allow only p9_max_pages pinned. We wait for the
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 4e2576fc0c59..828e87fe8027 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -467,7 +467,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
iv.iov_len = skb->len;
memset(&msg, 0, sizeof(msg));
- iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len);
+ iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, skb->len);
err = l2cap_chan_send(chan, &msg, skb->len);
if (err > 0) {
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 51c2cf2d8923..58fc6333d412 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -63,7 +63,7 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *dat
memset(&msg, 0, sizeof(msg));
- iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len);
+ iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, total_len);
l2cap_chan_send(chan, &msg, total_len);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index a1c1b7e8a45c..c822e626761b 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -622,7 +622,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
memset(&msg, 0, sizeof(msg));
- iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len);
+ iov_iter_kvec(&msg.msg_iter, WRITE, iv, 2, 1 + len);
l2cap_chan_send(chan, &msg, 1 + len);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 0a187196aeed..57fcc6b4bf6e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -156,7 +156,6 @@ static bool con_flag_test_and_set(struct ceph_connection *con,
/* Slab caches for frequently-allocated structures */
static struct kmem_cache *ceph_msg_cache;
-static struct kmem_cache *ceph_msg_data_cache;
/* static tag bytes (protocol control messages) */
static char tag_msg = CEPH_MSGR_TAG_MSG;
@@ -235,23 +234,11 @@ static int ceph_msgr_slab_init(void)
if (!ceph_msg_cache)
return -ENOMEM;
- BUG_ON(ceph_msg_data_cache);
- ceph_msg_data_cache = KMEM_CACHE(ceph_msg_data, 0);
- if (ceph_msg_data_cache)
- return 0;
-
- kmem_cache_destroy(ceph_msg_cache);
- ceph_msg_cache = NULL;
-
- return -ENOMEM;
+ return 0;
}
static void ceph_msgr_slab_exit(void)
{
- BUG_ON(!ceph_msg_data_cache);
- kmem_cache_destroy(ceph_msg_data_cache);
- ceph_msg_data_cache = NULL;
-
BUG_ON(!ceph_msg_cache);
kmem_cache_destroy(ceph_msg_cache);
ceph_msg_cache = NULL;
@@ -526,7 +513,7 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
if (!buf)
msg.msg_flags |= MSG_TRUNC;
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len);
+ iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
r = sock_recvmsg(sock, &msg, msg.msg_flags);
if (r == -EAGAIN)
r = 0;
@@ -545,7 +532,7 @@ static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
int r;
BUG_ON(page_offset + length > PAGE_SIZE);
- iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length);
+ iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
r = sock_recvmsg(sock, &msg, msg.msg_flags);
if (r == -EAGAIN)
r = 0;
@@ -607,7 +594,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
else
msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */
- iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size);
+ iov_iter_bvec(&msg.msg_iter, WRITE, &bvec, 1, size);
ret = sock_sendmsg(sock, &msg);
if (ret == -EAGAIN)
ret = 0;
@@ -1141,16 +1128,13 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length)
{
struct ceph_msg_data_cursor *cursor = &msg->cursor;
- struct ceph_msg_data *data;
BUG_ON(!length);
BUG_ON(length > msg->data_length);
- BUG_ON(list_empty(&msg->data));
+ BUG_ON(!msg->num_data_items);
- cursor->data_head = &msg->data;
cursor->total_resid = length;
- data = list_first_entry(&msg->data, struct ceph_msg_data, links);
- cursor->data = data;
+ cursor->data = msg->data;
__ceph_msg_data_cursor_init(cursor);
}
@@ -1231,8 +1215,7 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
if (!cursor->resid && cursor->total_resid) {
WARN_ON(!cursor->last_piece);
- BUG_ON(list_is_last(&cursor->data->links, cursor->data_head));
- cursor->data = list_next_entry(cursor->data, links);
+ cursor->data++;
__ceph_msg_data_cursor_init(cursor);
new_piece = true;
}
@@ -1248,9 +1231,6 @@ static size_t sizeof_footer(struct ceph_connection *con)
static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
{
- BUG_ON(!msg);
- BUG_ON(!data_len);
-
/* Initialize data cursor */
ceph_msg_data_cursor_init(msg, (size_t)data_len);
@@ -1590,7 +1570,7 @@ static int write_partial_message_data(struct ceph_connection *con)
dout("%s %p msg %p\n", __func__, con, msg);
- if (list_empty(&msg->data))
+ if (!msg->num_data_items)
return -EINVAL;
/*
@@ -2347,8 +2327,7 @@ static int read_partial_msg_data(struct ceph_connection *con)
u32 crc = 0;
int ret;
- BUG_ON(!msg);
- if (list_empty(&msg->data))
+ if (!msg->num_data_items)
return -EIO;
if (do_datacrc)
@@ -3256,32 +3235,16 @@ bool ceph_con_keepalive_expired(struct ceph_connection *con,
return false;
}
-static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type)
+static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg)
{
- struct ceph_msg_data *data;
-
- if (WARN_ON(!ceph_msg_data_type_valid(type)))
- return NULL;
-
- data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS);
- if (!data)
- return NULL;
-
- data->type = type;
- INIT_LIST_HEAD(&data->links);
-
- return data;
+ BUG_ON(msg->num_data_items >= msg->max_data_items);
+ return &msg->data[msg->num_data_items++];
}
static void ceph_msg_data_destroy(struct ceph_msg_data *data)
{
- if (!data)
- return;
-
- WARN_ON(!list_empty(&data->links));
if (data->type == CEPH_MSG_DATA_PAGELIST)
ceph_pagelist_release(data->pagelist);
- kmem_cache_free(ceph_msg_data_cache, data);
}
void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
@@ -3292,13 +3255,12 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
BUG_ON(!pages);
BUG_ON(!length);
- data = ceph_msg_data_create(CEPH_MSG_DATA_PAGES);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_PAGES;
data->pages = pages;
data->length = length;
data->alignment = alignment & ~PAGE_MASK;
- list_add_tail(&data->links, &msg->data);
msg->data_length += length;
}
EXPORT_SYMBOL(ceph_msg_data_add_pages);
@@ -3311,11 +3273,11 @@ void ceph_msg_data_add_pagelist(struct ceph_msg *msg,
BUG_ON(!pagelist);
BUG_ON(!pagelist->length);
- data = ceph_msg_data_create(CEPH_MSG_DATA_PAGELIST);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_PAGELIST;
+ refcount_inc(&pagelist->refcnt);
data->pagelist = pagelist;
- list_add_tail(&data->links, &msg->data);
msg->data_length += pagelist->length;
}
EXPORT_SYMBOL(ceph_msg_data_add_pagelist);
@@ -3326,12 +3288,11 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
{
struct ceph_msg_data *data;
- data = ceph_msg_data_create(CEPH_MSG_DATA_BIO);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_BIO;
data->bio_pos = *bio_pos;
data->bio_length = length;
- list_add_tail(&data->links, &msg->data);
msg->data_length += length;
}
EXPORT_SYMBOL(ceph_msg_data_add_bio);
@@ -3342,11 +3303,10 @@ void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
{
struct ceph_msg_data *data;
- data = ceph_msg_data_create(CEPH_MSG_DATA_BVECS);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_BVECS;
data->bvec_pos = *bvec_pos;
- list_add_tail(&data->links, &msg->data);
msg->data_length += bvec_pos->iter.bi_size;
}
EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
@@ -3355,8 +3315,8 @@ EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
* construct a new message with given type, size
* the new msg has a ref count of 1.
*/
-struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
- bool can_fail)
+struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
+ gfp_t flags, bool can_fail)
{
struct ceph_msg *m;
@@ -3370,7 +3330,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
INIT_LIST_HEAD(&m->list_head);
kref_init(&m->kref);
- INIT_LIST_HEAD(&m->data);
/* front */
if (front_len) {
@@ -3385,6 +3344,15 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
}
m->front_alloc_len = m->front.iov_len = front_len;
+ if (max_data_items) {
+ m->data = kmalloc_array(max_data_items, sizeof(*m->data),
+ flags);
+ if (!m->data)
+ goto out2;
+
+ m->max_data_items = max_data_items;
+ }
+
dout("ceph_msg_new %p front %d\n", m, front_len);
return m;
@@ -3401,6 +3369,13 @@ out:
}
return NULL;
}
+EXPORT_SYMBOL(ceph_msg_new2);
+
+struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
+ bool can_fail)
+{
+ return ceph_msg_new2(type, front_len, 0, flags, can_fail);
+}
EXPORT_SYMBOL(ceph_msg_new);
/*
@@ -3496,13 +3471,14 @@ static void ceph_msg_free(struct ceph_msg *m)
{
dout("%s %p\n", __func__, m);
kvfree(m->front.iov_base);
+ kfree(m->data);
kmem_cache_free(ceph_msg_cache, m);
}
static void ceph_msg_release(struct kref *kref)
{
struct ceph_msg *m = container_of(kref, struct ceph_msg, kref);
- struct ceph_msg_data *data, *next;
+ int i;
dout("%s %p\n", __func__, m);
WARN_ON(!list_empty(&m->list_head));
@@ -3515,11 +3491,8 @@ static void ceph_msg_release(struct kref *kref)
m->middle = NULL;
}
- list_for_each_entry_safe(data, next, &m->data, links) {
- list_del_init(&data->links);
- ceph_msg_data_destroy(data);
- }
- m->data_length = 0;
+ for (i = 0; i < m->num_data_items; i++)
+ ceph_msg_data_destroy(&m->data[i]);
if (m->pool)
ceph_msgpool_put(m->pool, m);
diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c
index 72571535883f..e3ecb80cd182 100644
--- a/net/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -14,7 +14,8 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
struct ceph_msgpool *pool = arg;
struct ceph_msg *msg;
- msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true);
+ msg = ceph_msg_new2(pool->type, pool->front_len, pool->max_data_items,
+ gfp_mask, true);
if (!msg) {
dout("msgpool_alloc %s failed\n", pool->name);
} else {
@@ -35,11 +36,13 @@ static void msgpool_free(void *element, void *arg)
}
int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
- int front_len, int size, bool blocking, const char *name)
+ int front_len, int max_data_items, int size,
+ const char *name)
{
dout("msgpool %s init\n", name);
pool->type = type;
pool->front_len = front_len;
+ pool->max_data_items = max_data_items;
pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool);
if (!pool->pool)
return -ENOMEM;
@@ -53,18 +56,21 @@ void ceph_msgpool_destroy(struct ceph_msgpool *pool)
mempool_destroy(pool->pool);
}
-struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool,
- int front_len)
+struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len,
+ int max_data_items)
{
struct ceph_msg *msg;
- if (front_len > pool->front_len) {
- dout("msgpool_get %s need front %d, pool size is %d\n",
- pool->name, front_len, pool->front_len);
- WARN_ON(1);
+ if (front_len > pool->front_len ||
+ max_data_items > pool->max_data_items) {
+ pr_warn_ratelimited("%s need %d/%d, pool %s has %d/%d\n",
+ __func__, front_len, max_data_items, pool->name,
+ pool->front_len, pool->max_data_items);
+ WARN_ON_ONCE(1);
/* try to alloc a fresh message */
- return ceph_msg_new(pool->type, front_len, GFP_NOFS, false);
+ return ceph_msg_new2(pool->type, front_len, max_data_items,
+ GFP_NOFS, false);
}
msg = mempool_alloc(pool->pool, GFP_NOFS);
@@ -80,6 +86,9 @@ void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg)
msg->front.iov_len = pool->front_len;
msg->hdr.front_len = cpu_to_le32(pool->front_len);
+ msg->data_length = 0;
+ msg->num_data_items = 0;
+
kref_init(&msg->kref); /* retake single ref */
mempool_free(msg, pool->pool);
}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 60934bd8796c..d23a9f81f3d7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -126,6 +126,9 @@ static void ceph_osd_data_init(struct ceph_osd_data *osd_data)
osd_data->type = CEPH_OSD_DATA_TYPE_NONE;
}
+/*
+ * Consumes @pages if @own_pages is true.
+ */
static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
struct page **pages, u64 length, u32 alignment,
bool pages_from_pool, bool own_pages)
@@ -138,6 +141,9 @@ static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
osd_data->own_pages = own_pages;
}
+/*
+ * Consumes a ref on @pagelist.
+ */
static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
struct ceph_pagelist *pagelist)
{
@@ -362,6 +368,8 @@ static void ceph_osd_data_release(struct ceph_osd_data *osd_data)
num_pages = calc_pages_for((u64)osd_data->alignment,
(u64)osd_data->length);
ceph_release_page_vector(osd_data->pages, num_pages);
+ } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
+ ceph_pagelist_release(osd_data->pagelist);
}
ceph_osd_data_init(osd_data);
}
@@ -402,6 +410,9 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_LIST_WATCHERS:
ceph_osd_data_release(&op->list_watchers.response_data);
break;
+ case CEPH_OSD_OP_COPY_FROM:
+ ceph_osd_data_release(&op->copy_from.osd_data);
+ break;
default:
break;
}
@@ -606,12 +617,15 @@ static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc)
return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
}
-int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp,
+ int num_request_data_items,
+ int num_reply_data_items)
{
struct ceph_osd_client *osdc = req->r_osdc;
struct ceph_msg *msg;
int msg_size;
+ WARN_ON(req->r_request || req->r_reply);
WARN_ON(ceph_oid_empty(&req->r_base_oid));
WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
@@ -633,9 +647,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
msg_size += 4 + 8; /* retry_attempt, features */
if (req->r_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
+ msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size,
+ num_request_data_items);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
+ msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size,
+ num_request_data_items, gfp, true);
if (!msg)
return -ENOMEM;
@@ -648,9 +664,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
if (req->r_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+ msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size,
+ num_reply_data_items);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true);
+ msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size,
+ num_reply_data_items, gfp, true);
if (!msg)
return -ENOMEM;
@@ -658,7 +676,6 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
return 0;
}
-EXPORT_SYMBOL(ceph_osdc_alloc_messages);
static bool osd_req_opcode_valid(u16 opcode)
{
@@ -671,6 +688,65 @@ __CEPH_FORALL_OSD_OPS(GENERATE_CASE)
}
}
+static void get_num_data_items(struct ceph_osd_request *req,
+ int *num_request_data_items,
+ int *num_reply_data_items)
+{
+ struct ceph_osd_req_op *op;
+
+ *num_request_data_items = 0;
+ *num_reply_data_items = 0;
+
+ for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
+ switch (op->op) {
+ /* request */
+ case CEPH_OSD_OP_WRITE:
+ case CEPH_OSD_OP_WRITEFULL:
+ case CEPH_OSD_OP_SETXATTR:
+ case CEPH_OSD_OP_CMPXATTR:
+ case CEPH_OSD_OP_NOTIFY_ACK:
+ case CEPH_OSD_OP_COPY_FROM:
+ *num_request_data_items += 1;
+ break;
+
+ /* reply */
+ case CEPH_OSD_OP_STAT:
+ case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_LIST_WATCHERS:
+ *num_reply_data_items += 1;
+ break;
+
+ /* both */
+ case CEPH_OSD_OP_NOTIFY:
+ *num_request_data_items += 1;
+ *num_reply_data_items += 1;
+ break;
+ case CEPH_OSD_OP_CALL:
+ *num_request_data_items += 2;
+ *num_reply_data_items += 1;
+ break;
+
+ default:
+ WARN_ON(!osd_req_opcode_valid(op->op));
+ break;
+ }
+ }
+}
+
+/*
+ * oid, oloc and OSD op opcode(s) must be filled in before this function
+ * is called.
+ */
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+{
+ int num_request_data_items, num_reply_data_items;
+
+ get_num_data_items(req, &num_request_data_items, &num_reply_data_items);
+ return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items,
+ num_reply_data_items);
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_messages);
+
/*
* This is an osd op init function for opcodes that have no data or
* other information associated with them. It also serves as a
@@ -767,22 +843,19 @@ void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
EXPORT_SYMBOL(osd_req_op_extent_dup_last);
int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
- u16 opcode, const char *class, const char *method)
+ const char *class, const char *method)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- opcode, 0);
+ struct ceph_osd_req_op *op;
struct ceph_pagelist *pagelist;
size_t payload_len = 0;
size_t size;
- BUG_ON(opcode != CEPH_OSD_OP_CALL);
+ op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
- pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
+ pagelist = ceph_pagelist_alloc(GFP_NOFS);
if (!pagelist)
return -ENOMEM;
- ceph_pagelist_init(pagelist);
-
op->cls.class_name = class;
size = strlen(class);
BUG_ON(size > (size_t) U8_MAX);
@@ -815,12 +888,10 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
- pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+ pagelist = ceph_pagelist_alloc(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);
@@ -900,12 +971,6 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
static u32 osd_req_encode_op(struct ceph_osd_op *dst,
const struct ceph_osd_req_op *src)
{
- if (WARN_ON(!osd_req_opcode_valid(src->op))) {
- pr_err("unrecognized osd opcode %d\n", src->op);
-
- return 0;
- }
-
switch (src->op) {
case CEPH_OSD_OP_STAT:
break;
@@ -955,6 +1020,14 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
case CEPH_OSD_OP_CREATE:
case CEPH_OSD_OP_DELETE:
break;
+ case CEPH_OSD_OP_COPY_FROM:
+ dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid);
+ dst->copy_from.src_version =
+ cpu_to_le64(src->copy_from.src_version);
+ dst->copy_from.flags = src->copy_from.flags;
+ dst->copy_from.src_fadvise_flags =
+ cpu_to_le32(src->copy_from.src_fadvise_flags);
+ break;
default:
pr_err("unsupported osd opcode %s\n",
ceph_osd_op_name(src->op));
@@ -1038,7 +1111,15 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
if (flags & CEPH_OSD_FLAG_WRITE)
req->r_data_offset = off;
- r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+ if (num_ops > 1)
+ /*
+ * This is a special case for ceph_writepages_start(), but it
+ * also covers ceph_uninline_data(). If more multi-op request
+ * use cases emerge, we will need a separate helper.
+ */
+ r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0);
+ else
+ r = ceph_osdc_alloc_messages(req, GFP_NOFS);
if (r)
goto fail;
@@ -1845,48 +1926,55 @@ static bool should_plug_request(struct ceph_osd_request *req)
return true;
}
-static void setup_request_data(struct ceph_osd_request *req,
- struct ceph_msg *msg)
+/*
+ * Keep get_num_data_items() in sync with this function.
+ */
+static void setup_request_data(struct ceph_osd_request *req)
{
- u32 data_len = 0;
- int i;
+ struct ceph_msg *request_msg = req->r_request;
+ struct ceph_msg *reply_msg = req->r_reply;
+ struct ceph_osd_req_op *op;
- if (!list_empty(&msg->data))
+ if (req->r_request->num_data_items || req->r_reply->num_data_items)
return;
- WARN_ON(msg->data_length);
- for (i = 0; i < req->r_num_ops; i++) {
- struct ceph_osd_req_op *op = &req->r_ops[i];
-
+ WARN_ON(request_msg->data_length || reply_msg->data_length);
+ for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
switch (op->op) {
/* request */
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_WRITEFULL:
WARN_ON(op->indata_len != op->extent.length);
- ceph_osdc_msg_data_add(msg, &op->extent.osd_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->extent.osd_data);
break;
case CEPH_OSD_OP_SETXATTR:
case CEPH_OSD_OP_CMPXATTR:
WARN_ON(op->indata_len != op->xattr.name_len +
op->xattr.value_len);
- ceph_osdc_msg_data_add(msg, &op->xattr.osd_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->xattr.osd_data);
break;
case CEPH_OSD_OP_NOTIFY_ACK:
- ceph_osdc_msg_data_add(msg,
+ ceph_osdc_msg_data_add(request_msg,
&op->notify_ack.request_data);
break;
+ case CEPH_OSD_OP_COPY_FROM:
+ ceph_osdc_msg_data_add(request_msg,
+ &op->copy_from.osd_data);
+ break;
/* reply */
case CEPH_OSD_OP_STAT:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->raw_data_in);
break;
case CEPH_OSD_OP_READ:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->extent.osd_data);
break;
case CEPH_OSD_OP_LIST_WATCHERS:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->list_watchers.response_data);
break;
@@ -1895,25 +1983,23 @@ static void setup_request_data(struct ceph_osd_request *req,
WARN_ON(op->indata_len != op->cls.class_len +
op->cls.method_len +
op->cls.indata_len);
- ceph_osdc_msg_data_add(msg, &op->cls.request_info);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->cls.request_info);
/* optional, can be NONE */
- ceph_osdc_msg_data_add(msg, &op->cls.request_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->cls.request_data);
/* optional, can be NONE */
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->cls.response_data);
break;
case CEPH_OSD_OP_NOTIFY:
- ceph_osdc_msg_data_add(msg,
+ ceph_osdc_msg_data_add(request_msg,
&op->notify.request_data);
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->notify.response_data);
break;
}
-
- data_len += op->indata_len;
}
-
- WARN_ON(data_len != msg->data_length);
}
static void encode_pgid(void **p, const struct ceph_pg *pgid)
@@ -1961,7 +2047,7 @@ static void encode_request_partial(struct ceph_osd_request *req,
req->r_data_offset || req->r_snapc);
}
- setup_request_data(req, msg);
+ setup_request_data(req);
encode_spgid(&p, &req->r_t.spgid); /* actual spg */
ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */
@@ -3001,11 +3087,21 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)
struct ceph_osd_client *osdc = lreq->osdc;
struct ceph_osd *osd;
+ down_write(&osdc->lock);
+ linger_register(lreq);
+ if (lreq->is_watch) {
+ lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id;
+ lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id;
+ } else {
+ lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id;
+ }
+
calc_target(osdc, &lreq->t, NULL, false);
osd = lookup_create_osd(osdc, lreq->t.osd, true);
link_linger(osd, lreq);
send_linger(lreq);
+ up_write(&osdc->lock);
}
static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
@@ -4318,9 +4414,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc,
lreq->notify_id, notify_id);
} else if (!completion_done(&lreq->notify_finish_wait)) {
struct ceph_msg_data *data =
- list_first_entry_or_null(&msg->data,
- struct ceph_msg_data,
- links);
+ msg->num_data_items ? &msg->data[0] : NULL;
if (data) {
if (lreq->preply_pages) {
@@ -4476,6 +4570,23 @@ alloc_linger_request(struct ceph_osd_linger_request *lreq)
ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+ return req;
+}
+
+static struct ceph_osd_request *
+alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode)
+{
+ struct ceph_osd_request *req;
+
+ req = alloc_linger_request(lreq);
+ if (!req)
+ return NULL;
+
+ /*
+ * Pass 0 for cookie because we don't know it yet, it will be
+ * filled in by linger_submit().
+ */
+ osd_req_op_watch_init(req, 0, 0, watch_opcode);
if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
ceph_osdc_put_request(req);
@@ -4514,27 +4625,19 @@ ceph_osdc_watch(struct ceph_osd_client *osdc,
lreq->t.flags = CEPH_OSD_FLAG_WRITE;
ktime_get_real_ts64(&lreq->mtime);
- lreq->reg_req = alloc_linger_request(lreq);
+ lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH);
if (!lreq->reg_req) {
ret = -ENOMEM;
goto err_put_lreq;
}
- lreq->ping_req = alloc_linger_request(lreq);
+ lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING);
if (!lreq->ping_req) {
ret = -ENOMEM;
goto err_put_lreq;
}
- down_write(&osdc->lock);
- linger_register(lreq); /* before osd_req_op_* */
- osd_req_op_watch_init(lreq->reg_req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_WATCH);
- osd_req_op_watch_init(lreq->ping_req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_PING);
linger_submit(lreq);
- up_write(&osdc->lock);
-
ret = linger_reg_commit_wait(lreq);
if (ret) {
linger_cancel(lreq);
@@ -4599,11 +4702,10 @@ static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
- pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ pl = ceph_pagelist_alloc(GFP_NOIO);
if (!pl)
return -ENOMEM;
- ceph_pagelist_init(pl);
ret = ceph_pagelist_encode_64(pl, notify_id);
ret |= ceph_pagelist_encode_64(pl, cookie);
if (payload) {
@@ -4641,12 +4743,12 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = CEPH_OSD_FLAG_READ;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
+ payload_len);
if (ret)
goto out_put_req;
- ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
- payload_len);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
if (ret)
goto out_put_req;
@@ -4670,11 +4772,10 @@ static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
op->notify.cookie = cookie;
- pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ pl = ceph_pagelist_alloc(GFP_NOIO);
if (!pl)
return -ENOMEM;
- ceph_pagelist_init(pl);
ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
ret |= ceph_pagelist_encode_32(pl, timeout);
ret |= ceph_pagelist_encode_32(pl, payload_len);
@@ -4733,29 +4834,30 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
goto out_put_lreq;
}
+ /*
+ * Pass 0 for cookie because we don't know it yet, it will be
+ * filled in by linger_submit().
+ */
+ ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout,
+ payload, payload_len);
+ if (ret)
+ goto out_put_lreq;
+
/* for notify_id */
pages = ceph_alloc_page_vector(1, GFP_NOIO);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
goto out_put_lreq;
}
-
- down_write(&osdc->lock);
- linger_register(lreq); /* before osd_req_op_* */
- ret = osd_req_op_notify_init(lreq->reg_req, 0, lreq->linger_id, 1,
- timeout, payload, payload_len);
- if (ret) {
- linger_unregister(lreq);
- up_write(&osdc->lock);
- ceph_release_page_vector(pages, 1);
- goto out_put_lreq;
- }
ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
response_data),
pages, PAGE_SIZE, 0, false, true);
- linger_submit(lreq);
- up_write(&osdc->lock);
+ ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO);
+ if (ret)
+ goto out_put_lreq;
+
+ linger_submit(lreq);
ret = linger_reg_commit_wait(lreq);
if (!ret)
ret = linger_notify_finish_wait(lreq);
@@ -4881,10 +4983,6 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = CEPH_OSD_FLAG_READ;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
- if (ret)
- goto out_put_req;
-
pages = ceph_alloc_page_vector(1, GFP_NOIO);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
@@ -4896,6 +4994,10 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
response_data),
pages, PAGE_SIZE, 0, false, true);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
+
ceph_osdc_start_request(osdc, req, false);
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0) {
@@ -4958,11 +5060,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = flags;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
- if (ret)
- goto out_put_req;
-
- ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
+ ret = osd_req_op_cls_init(req, 0, class, method);
if (ret)
goto out_put_req;
@@ -4973,6 +5071,10 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
osd_req_op_cls_response_data_pages(req, 0, &resp_page,
*resp_len, 0, false, false);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
+
ceph_osdc_start_request(osdc, req, false);
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0) {
@@ -5021,11 +5123,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
goto out_map;
err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
- PAGE_SIZE, 10, true, "osd_op");
+ PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op");
if (err < 0)
goto out_mempool;
err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
- PAGE_SIZE, 10, true, "osd_op_reply");
+ PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10,
+ "osd_op_reply");
if (err < 0)
goto out_msgpool;
@@ -5168,6 +5271,80 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
}
EXPORT_SYMBOL(ceph_osdc_writepages);
+static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
+ u64 src_snapid, u64 src_version,
+ struct ceph_object_id *src_oid,
+ struct ceph_object_locator *src_oloc,
+ u32 src_fadvise_flags,
+ u32 dst_fadvise_flags,
+ u8 copy_from_flags)
+{
+ struct ceph_osd_req_op *op;
+ struct page **pages;
+ void *p, *end;
+
+ pages = ceph_alloc_page_vector(1, GFP_KERNEL);
+ if (IS_ERR(pages))
+ return PTR_ERR(pages);
+
+ op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, dst_fadvise_flags);
+ op->copy_from.snapid = src_snapid;
+ op->copy_from.src_version = src_version;
+ op->copy_from.flags = copy_from_flags;
+ op->copy_from.src_fadvise_flags = src_fadvise_flags;
+
+ p = page_address(pages[0]);
+ end = p + PAGE_SIZE;
+ ceph_encode_string(&p, end, src_oid->name, src_oid->name_len);
+ encode_oloc(&p, end, src_oloc);
+ op->indata_len = PAGE_SIZE - (end - p);
+
+ ceph_osd_data_pages_init(&op->copy_from.osd_data, pages,
+ op->indata_len, 0, false, true);
+ return 0;
+}
+
+int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
+ u64 src_snapid, u64 src_version,
+ struct ceph_object_id *src_oid,
+ struct ceph_object_locator *src_oloc,
+ u32 src_fadvise_flags,
+ struct ceph_object_id *dst_oid,
+ struct ceph_object_locator *dst_oloc,
+ u32 dst_fadvise_flags,
+ u8 copy_from_flags)
+{
+ struct ceph_osd_request *req;
+ int ret;
+
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL);
+ if (!req)
+ return -ENOMEM;
+
+ req->r_flags = CEPH_OSD_FLAG_WRITE;
+
+ ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc);
+ ceph_oid_copy(&req->r_t.base_oid, dst_oid);
+
+ ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
+ src_oloc, src_fadvise_flags,
+ dst_fadvise_flags, copy_from_flags);
+ if (ret)
+ goto out;
+
+ ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+ if (ret)
+ goto out;
+
+ ceph_osdc_start_request(osdc, req, false);
+ ret = ceph_osdc_wait_request(osdc, req);
+
+out:
+ ceph_osdc_put_request(req);
+ return ret;
+}
+EXPORT_SYMBOL(ceph_osdc_copy_from);
+
int __init ceph_osdc_setup(void)
{
size_t size = sizeof(struct ceph_osd_request) +
@@ -5295,7 +5472,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
u32 front_len = le32_to_cpu(hdr->front_len);
u32 data_len = le32_to_cpu(hdr->data_len);
- m = ceph_msg_new(type, front_len, GFP_NOIO, false);
+ m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false);
if (!m)
return NULL;
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 2ea0564771d2..65e34f78b05d 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -6,6 +6,26 @@
#include <linux/highmem.h>
#include <linux/ceph/pagelist.h>
+struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags)
+{
+ struct ceph_pagelist *pl;
+
+ pl = kmalloc(sizeof(*pl), gfp_flags);
+ if (!pl)
+ return NULL;
+
+ INIT_LIST_HEAD(&pl->head);
+ pl->mapped_tail = NULL;
+ pl->length = 0;
+ pl->room = 0;
+ INIT_LIST_HEAD(&pl->free_list);
+ pl->num_pages_free = 0;
+ refcount_set(&pl->refcnt, 1);
+
+ return pl;
+}
+EXPORT_SYMBOL(ceph_pagelist_alloc);
+
static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
{
if (pl->mapped_tail) {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f679c7a7d761..e01274bd5e3e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3600,6 +3600,11 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
return -EINVAL;
}
+ if (dev->type != ARPHRD_ETHER) {
+ NL_SET_ERR_MSG(extack, "FDB add only supported for Ethernet devices");
+ return -EINVAL;
+ }
+
addr = nla_data(tb[NDA_LLADDR]);
err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
@@ -3704,6 +3709,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
return -EINVAL;
}
+ if (dev->type != ARPHRD_ETHER) {
+ NL_SET_ERR_MSG(extack, "FDB delete only supported for Ethernet devices");
+ return -EINVAL;
+ }
+
addr = nla_data(tb[NDA_LLADDR]);
err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 4da39446da2d..765b2b32c4a4 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -111,13 +111,10 @@
#ifdef CONFIG_IP_MULTICAST
/* Parameter names and values are taken from igmp-v2-06 draft */
-#define IGMP_V1_ROUTER_PRESENT_TIMEOUT (400*HZ)
-#define IGMP_V2_ROUTER_PRESENT_TIMEOUT (400*HZ)
#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ)
#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ)
+#define IGMP_QUERY_INTERVAL (125*HZ)
#define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ)
-#define IGMP_QUERY_ROBUSTNESS_VARIABLE 2
-
#define IGMP_INITIAL_REPORT_DELAY (1)
@@ -935,13 +932,15 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
max_delay = IGMP_QUERY_RESPONSE_INTERVAL;
in_dev->mr_v1_seen = jiffies +
- IGMP_V1_ROUTER_PRESENT_TIMEOUT;
+ (in_dev->mr_qrv * in_dev->mr_qi) +
+ in_dev->mr_qri;
group = 0;
} else {
/* v2 router present */
max_delay = ih->code*(HZ/IGMP_TIMER_SCALE);
in_dev->mr_v2_seen = jiffies +
- IGMP_V2_ROUTER_PRESENT_TIMEOUT;
+ (in_dev->mr_qrv * in_dev->mr_qi) +
+ in_dev->mr_qri;
}
/* cancel the interface change timer */
in_dev->mr_ifc_count = 0;
@@ -981,8 +980,21 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
if (!max_delay)
max_delay = 1; /* can't mod w/ 0 */
in_dev->mr_maxdelay = max_delay;
- if (ih3->qrv)
- in_dev->mr_qrv = ih3->qrv;
+
+ /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently
+ * received value was zero, use the default or statically
+ * configured value.
+ */
+ in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
+ in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
+
+ /* RFC3376, 8.3. Query Response Interval:
+ * The number of seconds represented by the [Query Response
+ * Interval] must be less than the [Query Interval].
+ */
+ if (in_dev->mr_qri >= in_dev->mr_qi)
+ in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ;
+
if (!group) { /* general query */
if (ih3->nsrcs)
return true; /* no sources allowed */
@@ -1723,18 +1735,30 @@ void ip_mc_down(struct in_device *in_dev)
ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS);
}
-void ip_mc_init_dev(struct in_device *in_dev)
-{
#ifdef CONFIG_IP_MULTICAST
+static void ip_mc_reset(struct in_device *in_dev)
+{
struct net *net = dev_net(in_dev->dev);
+
+ in_dev->mr_qi = IGMP_QUERY_INTERVAL;
+ in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
+ in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
+}
+#else
+static void ip_mc_reset(struct in_device *in_dev)
+{
+}
#endif
+
+void ip_mc_init_dev(struct in_device *in_dev)
+{
ASSERT_RTNL();
#ifdef CONFIG_IP_MULTICAST
timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0);
timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0);
- in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
#endif
+ ip_mc_reset(in_dev);
spin_lock_init(&in_dev->mc_tomb_lock);
}
@@ -1744,15 +1768,10 @@ void ip_mc_init_dev(struct in_device *in_dev)
void ip_mc_up(struct in_device *in_dev)
{
struct ip_mc_list *pmc;
-#ifdef CONFIG_IP_MULTICAST
- struct net *net = dev_net(in_dev->dev);
-#endif
ASSERT_RTNL();
-#ifdef CONFIG_IP_MULTICAST
- in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
-#endif
+ ip_mc_reset(in_dev);
ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
for_each_pmc_rtnl(in_dev, pmc) {
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f5c9ef2586de..411dd7a90046 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -19,7 +19,7 @@
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1834818ed07b..9e6bc4d6daa7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -262,7 +262,7 @@
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/random.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/cache.h>
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index b7918d4caa30..3b45fe530f91 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -145,6 +145,7 @@ msg_bytes_ready:
ret = err;
goto out;
}
+ copied = -EAGAIN;
}
ret = copied;
out:
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ca3ed931f2a9..1976fddb9e00 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -81,7 +81,7 @@
#include <linux/uaccess.h>
#include <asm/ioctls.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/types.h>
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index d4020c5e831d..2526be6b3d90 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1616,7 +1616,7 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
EnterFunction(7);
/* Receive a packet */
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen);
+ iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, buflen);
len = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
if (len < 0)
return len;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index a70097ecf33c..865ecef68196 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -3030,7 +3030,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
* is already present */
if (mac_proto != MAC_PROTO_NONE)
return -EINVAL;
- mac_proto = MAC_PROTO_NONE;
+ mac_proto = MAC_PROTO_ETHERNET;
break;
case OVS_ACTION_ATTR_POP_ETH:
@@ -3038,7 +3038,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
return -EINVAL;
if (vlan_tci & htons(VLAN_TAG_PRESENT))
return -EINVAL;
- mac_proto = MAC_PROTO_ETHERNET;
+ mac_proto = MAC_PROTO_NONE;
break;
case OVS_ACTION_ATTR_PUSH_NSH:
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index a827a1f562bf..6a28b96e779e 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -499,8 +499,9 @@ void sctp_assoc_set_primary(struct sctp_association *asoc,
void sctp_assoc_rm_peer(struct sctp_association *asoc,
struct sctp_transport *peer)
{
- struct list_head *pos;
- struct sctp_transport *transport;
+ struct sctp_transport *transport;
+ struct list_head *pos;
+ struct sctp_chunk *ch;
pr_debug("%s: association:%p addr:%pISpc\n",
__func__, asoc, &peer->ipaddr.sa);
@@ -564,7 +565,6 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
*/
if (!list_empty(&peer->transmitted)) {
struct sctp_transport *active = asoc->peer.active_path;
- struct sctp_chunk *ch;
/* Reset the transport of each chunk on this list */
list_for_each_entry(ch, &peer->transmitted,
@@ -586,6 +586,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
sctp_transport_hold(active);
}
+ list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list)
+ if (ch->transport == peer)
+ ch->transport = NULL;
+
asoc->peer.transport_count--;
sctp_transport_free(peer);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e948db29ab53..9b277bd36d1a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -46,7 +46,7 @@
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/slab.h>
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fc0386e8ff23..739f3e50120d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7083,14 +7083,15 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len,
}
policy = params.sprstat_policy;
- if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)))
+ if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) ||
+ ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK)))
goto out;
asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
if (!asoc)
goto out;
- if (policy & SCTP_PR_SCTP_ALL) {
+ if (policy == SCTP_PR_SCTP_ALL) {
params.sprstat_abandoned_unsent = 0;
params.sprstat_abandoned_sent = 0;
for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
@@ -7142,7 +7143,8 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
}
policy = params.sprstat_policy;
- if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)))
+ if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) ||
+ ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK)))
goto out;
asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 52241d679cc9..89c3a8c7859a 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -286,7 +286,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
*/
krflags = MSG_PEEK | MSG_WAITALL;
smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1,
+ iov_iter_kvec(&msg.msg_iter, READ, &vec, 1,
sizeof(struct smc_clc_msg_hdr));
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (signal_pending(current)) {
@@ -325,7 +325,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
/* receive the complete CLC message */
memset(&msg, 0, sizeof(struct msghdr));
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
+ iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen);
krflags = MSG_WAITALL;
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
diff --git a/net/socket.c b/net/socket.c
index 99c96851469f..593826e11a53 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -635,7 +635,7 @@ EXPORT_SYMBOL(sock_sendmsg);
int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
struct kvec *vec, size_t num, size_t size)
{
- iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+ iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
return sock_sendmsg(sock, msg);
}
EXPORT_SYMBOL(kernel_sendmsg);
@@ -648,7 +648,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
if (!sock->ops->sendmsg_locked)
return sock_no_sendmsg_locked(sk, msg, size);
- iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+ iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg));
}
@@ -823,7 +823,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
mm_segment_t oldfs = get_fs();
int result;
- iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size);
+ iov_iter_kvec(&msg->msg_iter, READ, vec, num, size);
set_fs(KERNEL_DS);
result = sock_recvmsg(sock, msg, flags);
set_fs(oldfs);
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 860f2a1bbb67..1ece4bc3eb8d 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -76,6 +76,7 @@ struct rsi {
struct xdr_netobj in_handle, in_token;
struct xdr_netobj out_handle, out_token;
int major_status, minor_status;
+ struct rcu_head rcu_head;
};
static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old);
@@ -89,13 +90,21 @@ static void rsi_free(struct rsi *rsii)
kfree(rsii->out_token.data);
}
-static void rsi_put(struct kref *ref)
+static void rsi_free_rcu(struct rcu_head *head)
{
- struct rsi *rsii = container_of(ref, struct rsi, h.ref);
+ struct rsi *rsii = container_of(head, struct rsi, rcu_head);
+
rsi_free(rsii);
kfree(rsii);
}
+static void rsi_put(struct kref *ref)
+{
+ struct rsi *rsii = container_of(ref, struct rsi, h.ref);
+
+ call_rcu(&rsii->rcu_head, rsi_free_rcu);
+}
+
static inline int rsi_hash(struct rsi *item)
{
return hash_mem(item->in_handle.data, item->in_handle.len, RSI_HASHBITS)
@@ -282,7 +291,7 @@ static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item)
struct cache_head *ch;
int hash = rsi_hash(item);
- ch = sunrpc_cache_lookup(cd, &item->h, hash);
+ ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash);
if (ch)
return container_of(ch, struct rsi, h);
else
@@ -330,6 +339,7 @@ struct rsc {
struct svc_cred cred;
struct gss_svc_seq_data seqdata;
struct gss_ctx *mechctx;
+ struct rcu_head rcu_head;
};
static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old);
@@ -343,12 +353,22 @@ static void rsc_free(struct rsc *rsci)
free_svc_cred(&rsci->cred);
}
+static void rsc_free_rcu(struct rcu_head *head)
+{
+ struct rsc *rsci = container_of(head, struct rsc, rcu_head);
+
+ kfree(rsci->handle.data);
+ kfree(rsci);
+}
+
static void rsc_put(struct kref *ref)
{
struct rsc *rsci = container_of(ref, struct rsc, h.ref);
- rsc_free(rsci);
- kfree(rsci);
+ if (rsci->mechctx)
+ gss_delete_sec_context(&rsci->mechctx);
+ free_svc_cred(&rsci->cred);
+ call_rcu(&rsci->rcu_head, rsc_free_rcu);
}
static inline int
@@ -542,7 +562,7 @@ static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item)
struct cache_head *ch;
int hash = rsc_hash(item);
- ch = sunrpc_cache_lookup(cd, &item->h, hash);
+ ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash);
if (ch)
return container_of(ch, struct rsc, h);
else
@@ -1764,14 +1784,21 @@ out_err:
}
static void
-svcauth_gss_domain_release(struct auth_domain *dom)
+svcauth_gss_domain_release_rcu(struct rcu_head *head)
{
+ struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head);
struct gss_domain *gd = container_of(dom, struct gss_domain, h);
kfree(dom->name);
kfree(gd);
}
+static void
+svcauth_gss_domain_release(struct auth_domain *dom)
+{
+ call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu);
+}
+
static struct auth_ops svcauthops_gss = {
.name = "rpcsec_gss",
.owner = THIS_MODULE,
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 109fbe591e7b..f96345b1180e 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -54,28 +54,33 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
h->last_refresh = now;
}
-struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
- struct cache_head *key, int hash)
+static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail,
+ struct cache_head *key,
+ int hash)
{
- struct cache_head *new = NULL, *freeme = NULL, *tmp = NULL;
- struct hlist_head *head;
-
- head = &detail->hash_table[hash];
-
- read_lock(&detail->hash_lock);
+ struct hlist_head *head = &detail->hash_table[hash];
+ struct cache_head *tmp;
- hlist_for_each_entry(tmp, head, cache_list) {
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp, head, cache_list) {
if (detail->match(tmp, key)) {
if (cache_is_expired(detail, tmp))
- /* This entry is expired, we will discard it. */
- break;
- cache_get(tmp);
- read_unlock(&detail->hash_lock);
+ continue;
+ tmp = cache_get_rcu(tmp);
+ rcu_read_unlock();
return tmp;
}
}
- read_unlock(&detail->hash_lock);
- /* Didn't find anything, insert an empty entry */
+ rcu_read_unlock();
+ return NULL;
+}
+
+static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
+ struct cache_head *key,
+ int hash)
+{
+ struct cache_head *new, *tmp, *freeme = NULL;
+ struct hlist_head *head = &detail->hash_table[hash];
new = detail->alloc();
if (!new)
@@ -87,35 +92,46 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
cache_init(new, detail);
detail->init(new, key);
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
/* check if entry appeared while we slept */
- hlist_for_each_entry(tmp, head, cache_list) {
+ hlist_for_each_entry_rcu(tmp, head, cache_list) {
if (detail->match(tmp, key)) {
if (cache_is_expired(detail, tmp)) {
- hlist_del_init(&tmp->cache_list);
+ hlist_del_init_rcu(&tmp->cache_list);
detail->entries --;
freeme = tmp;
break;
}
cache_get(tmp);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_put(new, detail);
return tmp;
}
}
- hlist_add_head(&new->cache_list, head);
+ hlist_add_head_rcu(&new->cache_list, head);
detail->entries++;
cache_get(new);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
if (freeme)
cache_put(freeme, detail);
return new;
}
-EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
+struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail,
+ struct cache_head *key, int hash)
+{
+ struct cache_head *ret;
+
+ ret = sunrpc_cache_find_rcu(detail, key, hash);
+ if (ret)
+ return ret;
+ /* Didn't find anything, insert an empty entry */
+ return sunrpc_cache_add_entry(detail, key, hash);
+}
+EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu);
static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
@@ -151,18 +167,18 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
struct cache_head *tmp;
if (!test_bit(CACHE_VALID, &old->flags)) {
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
if (!test_bit(CACHE_VALID, &old->flags)) {
if (test_bit(CACHE_NEGATIVE, &new->flags))
set_bit(CACHE_NEGATIVE, &old->flags);
else
detail->update(old, new);
cache_fresh_locked(old, new->expiry_time, detail);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(old, detail);
return old;
}
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
}
/* We need to insert a new entry */
tmp = detail->alloc();
@@ -173,7 +189,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
cache_init(tmp, detail);
detail->init(tmp, old);
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
if (test_bit(CACHE_NEGATIVE, &new->flags))
set_bit(CACHE_NEGATIVE, &tmp->flags);
else
@@ -183,7 +199,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
cache_get(tmp);
cache_fresh_locked(tmp, new->expiry_time, detail);
cache_fresh_locked(old, 0, detail);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(tmp, detail);
cache_fresh_unlocked(old, detail);
cache_put(old, detail);
@@ -223,7 +239,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
{
int rv;
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
rv = cache_is_valid(h);
if (rv == -EAGAIN) {
set_bit(CACHE_NEGATIVE, &h->flags);
@@ -231,7 +247,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
detail);
rv = -ENOENT;
}
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(h, detail);
return rv;
}
@@ -341,7 +357,7 @@ static struct delayed_work cache_cleaner;
void sunrpc_init_cache_detail(struct cache_detail *cd)
{
- rwlock_init(&cd->hash_lock);
+ spin_lock_init(&cd->hash_lock);
INIT_LIST_HEAD(&cd->queue);
spin_lock(&cache_list_lock);
cd->nextcheck = 0;
@@ -361,11 +377,11 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
{
cache_purge(cd);
spin_lock(&cache_list_lock);
- write_lock(&cd->hash_lock);
+ spin_lock(&cd->hash_lock);
if (current_detail == cd)
current_detail = NULL;
list_del_init(&cd->others);
- write_unlock(&cd->hash_lock);
+ spin_unlock(&cd->hash_lock);
spin_unlock(&cache_list_lock);
if (list_empty(&cache_list)) {
/* module must be being unloaded so its safe to kill the worker */
@@ -422,7 +438,7 @@ static int cache_clean(void)
struct hlist_head *head;
struct hlist_node *tmp;
- write_lock(&current_detail->hash_lock);
+ spin_lock(&current_detail->hash_lock);
/* Ok, now to clean this strand */
@@ -433,13 +449,13 @@ static int cache_clean(void)
if (!cache_is_expired(current_detail, ch))
continue;
- hlist_del_init(&ch->cache_list);
+ hlist_del_init_rcu(&ch->cache_list);
current_detail->entries--;
rv = 1;
break;
}
- write_unlock(&current_detail->hash_lock);
+ spin_unlock(&current_detail->hash_lock);
d = current_detail;
if (!ch)
current_index ++;
@@ -494,9 +510,9 @@ void cache_purge(struct cache_detail *detail)
struct hlist_node *tmp = NULL;
int i = 0;
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
if (!detail->entries) {
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
return;
}
@@ -504,17 +520,17 @@ void cache_purge(struct cache_detail *detail)
for (i = 0; i < detail->hash_size; i++) {
head = &detail->hash_table[i];
hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
- hlist_del_init(&ch->cache_list);
+ hlist_del_init_rcu(&ch->cache_list);
detail->entries--;
set_bit(CACHE_CLEANED, &ch->flags);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(ch, detail);
cache_put(ch, detail);
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
}
}
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
}
EXPORT_SYMBOL_GPL(cache_purge);
@@ -1289,21 +1305,19 @@ EXPORT_SYMBOL_GPL(qword_get);
* get a header, then pass each real item in the cache
*/
-void *cache_seq_start(struct seq_file *m, loff_t *pos)
- __acquires(cd->hash_lock)
+static void *__cache_seq_start(struct seq_file *m, loff_t *pos)
{
loff_t n = *pos;
unsigned int hash, entry;
struct cache_head *ch;
struct cache_detail *cd = m->private;
- read_lock(&cd->hash_lock);
if (!n--)
return SEQ_START_TOKEN;
hash = n >> 32;
entry = n & ((1LL<<32) - 1);
- hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list)
+ hlist_for_each_entry_rcu(ch, &cd->hash_table[hash], cache_list)
if (!entry--)
return ch;
n &= ~((1LL<<32) - 1);
@@ -1315,12 +1329,12 @@ void *cache_seq_start(struct seq_file *m, loff_t *pos)
if (hash >= cd->hash_size)
return NULL;
*pos = n+1;
- return hlist_entry_safe(cd->hash_table[hash].first,
+ return hlist_entry_safe(rcu_dereference_raw(
+ hlist_first_rcu(&cd->hash_table[hash])),
struct cache_head, cache_list);
}
-EXPORT_SYMBOL_GPL(cache_seq_start);
-void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
+static void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
{
struct cache_head *ch = p;
int hash = (*pos >> 32);
@@ -1333,7 +1347,8 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
*pos += 1LL<<32;
} else {
++*pos;
- return hlist_entry_safe(ch->cache_list.next,
+ return hlist_entry_safe(rcu_dereference_raw(
+ hlist_next_rcu(&ch->cache_list)),
struct cache_head, cache_list);
}
*pos &= ~((1LL<<32) - 1);
@@ -1345,18 +1360,32 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
if (hash >= cd->hash_size)
return NULL;
++*pos;
- return hlist_entry_safe(cd->hash_table[hash].first,
+ return hlist_entry_safe(rcu_dereference_raw(
+ hlist_first_rcu(&cd->hash_table[hash])),
struct cache_head, cache_list);
}
EXPORT_SYMBOL_GPL(cache_seq_next);
-void cache_seq_stop(struct seq_file *m, void *p)
- __releases(cd->hash_lock)
+void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos)
+ __acquires(RCU)
{
- struct cache_detail *cd = m->private;
- read_unlock(&cd->hash_lock);
+ rcu_read_lock();
+ return __cache_seq_start(m, pos);
+}
+EXPORT_SYMBOL_GPL(cache_seq_start_rcu);
+
+void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos)
+{
+ return cache_seq_next(file, p, pos);
+}
+EXPORT_SYMBOL_GPL(cache_seq_next_rcu);
+
+void cache_seq_stop_rcu(struct seq_file *m, void *p)
+ __releases(RCU)
+{
+ rcu_read_unlock();
}
-EXPORT_SYMBOL_GPL(cache_seq_stop);
+EXPORT_SYMBOL_GPL(cache_seq_stop_rcu);
static int c_show(struct seq_file *m, void *p)
{
@@ -1384,9 +1413,9 @@ static int c_show(struct seq_file *m, void *p)
}
static const struct seq_operations cache_content_op = {
- .start = cache_seq_start,
- .next = cache_seq_next,
- .stop = cache_seq_stop,
+ .start = cache_seq_start_rcu,
+ .next = cache_seq_next_rcu,
+ .stop = cache_seq_stop_rcu,
.show = c_show,
};
@@ -1844,13 +1873,13 @@ EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs);
void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h)
{
- write_lock(&cd->hash_lock);
+ spin_lock(&cd->hash_lock);
if (!hlist_unhashed(&h->cache_list)){
- hlist_del_init(&h->cache_list);
+ hlist_del_init_rcu(&h->cache_list);
cd->entries--;
- write_unlock(&cd->hash_lock);
+ spin_unlock(&cd->hash_lock);
cache_put(h, cd);
} else
- write_unlock(&cd->hash_lock);
+ spin_unlock(&cd->hash_lock);
}
EXPORT_SYMBOL_GPL(sunrpc_cache_unhash);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 87533fbb96cf..51d36230b6e3 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -987,7 +987,7 @@ static void call_xpt_users(struct svc_xprt *xprt)
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);
+ list_del_init(&u->list);
u->callback(u);
}
spin_unlock(&xprt->xpt_lock);
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index bb8db3cb8032..775b8c94265b 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -27,12 +27,32 @@
extern struct auth_ops svcauth_null;
extern struct auth_ops svcauth_unix;
-static DEFINE_SPINLOCK(authtab_lock);
-static struct auth_ops *authtab[RPC_AUTH_MAXFLAVOR] = {
- [0] = &svcauth_null,
- [1] = &svcauth_unix,
+static struct auth_ops __rcu *authtab[RPC_AUTH_MAXFLAVOR] = {
+ [RPC_AUTH_NULL] = (struct auth_ops __force __rcu *)&svcauth_null,
+ [RPC_AUTH_UNIX] = (struct auth_ops __force __rcu *)&svcauth_unix,
};
+static struct auth_ops *
+svc_get_auth_ops(rpc_authflavor_t flavor)
+{
+ struct auth_ops *aops;
+
+ if (flavor >= RPC_AUTH_MAXFLAVOR)
+ return NULL;
+ rcu_read_lock();
+ aops = rcu_dereference(authtab[flavor]);
+ if (aops != NULL && !try_module_get(aops->owner))
+ aops = NULL;
+ rcu_read_unlock();
+ return aops;
+}
+
+static void
+svc_put_auth_ops(struct auth_ops *aops)
+{
+ module_put(aops->owner);
+}
+
int
svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
{
@@ -45,14 +65,11 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
dprintk("svc: svc_authenticate (%d)\n", flavor);
- spin_lock(&authtab_lock);
- if (flavor >= RPC_AUTH_MAXFLAVOR || !(aops = authtab[flavor]) ||
- !try_module_get(aops->owner)) {
- spin_unlock(&authtab_lock);
+ aops = svc_get_auth_ops(flavor);
+ if (aops == NULL) {
*authp = rpc_autherr_badcred;
return SVC_DENIED;
}
- spin_unlock(&authtab_lock);
rqstp->rq_auth_slack = 0;
init_svc_cred(&rqstp->rq_cred);
@@ -82,7 +99,7 @@ int svc_authorise(struct svc_rqst *rqstp)
if (aops) {
rv = aops->release(rqstp);
- module_put(aops->owner);
+ svc_put_auth_ops(aops);
}
return rv;
}
@@ -90,13 +107,14 @@ int svc_authorise(struct svc_rqst *rqstp)
int
svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops)
{
+ struct auth_ops *old;
int rv = -EINVAL;
- spin_lock(&authtab_lock);
- if (flavor < RPC_AUTH_MAXFLAVOR && authtab[flavor] == NULL) {
- authtab[flavor] = aops;
- rv = 0;
+
+ if (flavor < RPC_AUTH_MAXFLAVOR) {
+ old = cmpxchg((struct auth_ops ** __force)&authtab[flavor], NULL, aops);
+ if (old == NULL || old == aops)
+ rv = 0;
}
- spin_unlock(&authtab_lock);
return rv;
}
EXPORT_SYMBOL_GPL(svc_auth_register);
@@ -104,10 +122,8 @@ EXPORT_SYMBOL_GPL(svc_auth_register);
void
svc_auth_unregister(rpc_authflavor_t flavor)
{
- spin_lock(&authtab_lock);
if (flavor < RPC_AUTH_MAXFLAVOR)
- authtab[flavor] = NULL;
- spin_unlock(&authtab_lock);
+ rcu_assign_pointer(authtab[flavor], NULL);
}
EXPORT_SYMBOL_GPL(svc_auth_unregister);
@@ -127,10 +143,11 @@ static struct hlist_head auth_domain_table[DN_HASHMAX];
static DEFINE_SPINLOCK(auth_domain_lock);
static void auth_domain_release(struct kref *kref)
+ __releases(&auth_domain_lock)
{
struct auth_domain *dom = container_of(kref, struct auth_domain, ref);
- hlist_del(&dom->hash);
+ hlist_del_rcu(&dom->hash);
dom->flavour->domain_release(dom);
spin_unlock(&auth_domain_lock);
}
@@ -159,7 +176,7 @@ auth_domain_lookup(char *name, struct auth_domain *new)
}
}
if (new)
- hlist_add_head(&new->hash, head);
+ hlist_add_head_rcu(&new->hash, head);
spin_unlock(&auth_domain_lock);
return new;
}
@@ -167,6 +184,21 @@ EXPORT_SYMBOL_GPL(auth_domain_lookup);
struct auth_domain *auth_domain_find(char *name)
{
- return auth_domain_lookup(name, NULL);
+ struct auth_domain *hp;
+ struct hlist_head *head;
+
+ head = &auth_domain_table[hash_str(name, DN_HASHBITS)];
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(hp, head, hash) {
+ if (strcmp(hp->name, name)==0) {
+ if (!kref_get_unless_zero(&hp->ref))
+ hp = NULL;
+ rcu_read_unlock();
+ return hp;
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
}
EXPORT_SYMBOL_GPL(auth_domain_find);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index af7f28fb8102..fb9041b92f72 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -37,20 +37,26 @@ struct unix_domain {
extern struct auth_ops svcauth_null;
extern struct auth_ops svcauth_unix;
-static void svcauth_unix_domain_release(struct auth_domain *dom)
+static void svcauth_unix_domain_release_rcu(struct rcu_head *head)
{
+ struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head);
struct unix_domain *ud = container_of(dom, struct unix_domain, h);
kfree(dom->name);
kfree(ud);
}
+static void svcauth_unix_domain_release(struct auth_domain *dom)
+{
+ call_rcu(&dom->rcu_head, svcauth_unix_domain_release_rcu);
+}
+
struct auth_domain *unix_domain_find(char *name)
{
struct auth_domain *rv;
struct unix_domain *new = NULL;
- rv = auth_domain_lookup(name, NULL);
+ rv = auth_domain_find(name);
while(1) {
if (rv) {
if (new && rv != &new->h)
@@ -91,6 +97,7 @@ struct ip_map {
char m_class[8]; /* e.g. "nfsd" */
struct in6_addr m_addr;
struct unix_domain *m_client;
+ struct rcu_head m_rcu;
};
static void ip_map_put(struct kref *kref)
@@ -101,7 +108,7 @@ static void ip_map_put(struct kref *kref)
if (test_bit(CACHE_VALID, &item->flags) &&
!test_bit(CACHE_NEGATIVE, &item->flags))
auth_domain_put(&im->m_client->h);
- kfree(im);
+ kfree_rcu(im, m_rcu);
}
static inline int hash_ip6(const struct in6_addr *ip)
@@ -280,9 +287,9 @@ static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class,
strcpy(ip.m_class, class);
ip.m_addr = *addr;
- ch = sunrpc_cache_lookup(cd, &ip.h,
- hash_str(class, IP_HASHBITS) ^
- hash_ip6(addr));
+ ch = sunrpc_cache_lookup_rcu(cd, &ip.h,
+ hash_str(class, IP_HASHBITS) ^
+ hash_ip6(addr));
if (ch)
return container_of(ch, struct ip_map, h);
@@ -412,6 +419,7 @@ struct unix_gid {
struct cache_head h;
kuid_t uid;
struct group_info *gi;
+ struct rcu_head rcu;
};
static int unix_gid_hash(kuid_t uid)
@@ -426,7 +434,7 @@ static void unix_gid_put(struct kref *kref)
if (test_bit(CACHE_VALID, &item->flags) &&
!test_bit(CACHE_NEGATIVE, &item->flags))
put_group_info(ug->gi);
- kfree(ug);
+ kfree_rcu(ug, rcu);
}
static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew)
@@ -619,7 +627,7 @@ static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid)
struct cache_head *ch;
ug.uid = uid;
- ch = sunrpc_cache_lookup(cd, &ug.h, unix_gid_hash(uid));
+ ch = sunrpc_cache_lookup_rcu(cd, &ug.h, unix_gid_hash(uid));
if (ch)
return container_of(ch, struct unix_gid, h);
else
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index db8bb6b3a2b0..986f3ed7d1a2 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -325,59 +325,34 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
/*
* Generic recvfrom routine.
*/
-static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
- int buflen)
+static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
+ unsigned int nr, size_t buflen, unsigned int base)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
- struct msghdr msg = {
- .msg_flags = MSG_DONTWAIT,
- };
- int len;
+ struct msghdr msg = { NULL };
+ ssize_t len;
rqstp->rq_xprt_hlen = 0;
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen);
- len = sock_recvmsg(svsk->sk_sock, &msg, msg.msg_flags);
+ iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen);
+ if (base != 0) {
+ iov_iter_advance(&msg.msg_iter, base);
+ buflen -= base;
+ }
+ len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
/* If we read a full record, then assume there may be more
* data to read (stream based sockets only!)
*/
if (len == buflen)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- dprintk("svc: socket %p recvfrom(%p, %zu) = %d\n",
+ dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n",
svsk, iov[0].iov_base, iov[0].iov_len, len);
return len;
}
-static int svc_partial_recvfrom(struct svc_rqst *rqstp,
- struct kvec *iov, int nr,
- int buflen, unsigned int base)
-{
- size_t save_iovlen;
- void *save_iovbase;
- unsigned int i;
- int ret;
-
- if (base == 0)
- return svc_recvfrom(rqstp, iov, nr, buflen);
-
- for (i = 0; i < nr; i++) {
- if (iov[i].iov_len > base)
- break;
- base -= iov[i].iov_len;
- }
- save_iovlen = iov[i].iov_len;
- save_iovbase = iov[i].iov_base;
- iov[i].iov_len -= base;
- iov[i].iov_base += base;
- ret = svc_recvfrom(rqstp, &iov[i], nr - i, buflen);
- iov[i].iov_len = save_iovlen;
- iov[i].iov_base = save_iovbase;
- return ret;
-}
-
/*
* Set socket snd and rcv buffer lengths
*/
@@ -962,7 +937,8 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
iov.iov_len = want;
- if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
+ len = svc_recvfrom(rqstp, &iov, 1, want, 0);
+ if (len < 0)
goto error;
svsk->sk_tcplen += len;
@@ -1088,14 +1064,13 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
vec = rqstp->rq_vec;
- pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
- svsk->sk_datalen + want);
+ pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want);
rqstp->rq_respages = &rqstp->rq_pages[pnum];
rqstp->rq_next_page = rqstp->rq_respages + 1;
/* Now receive data */
- len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
+ len = svc_recvfrom(rqstp, vec, pnum, base + want, base);
if (len >= 0) {
svsk->sk_tcplen += len;
svsk->sk_datalen += len;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index d3a1a237cee6..f3c147d70286 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -5,8 +5,6 @@
* Support for backward direction RPCs on RPC/RDMA (server-side).
*/
-#include <linux/module.h>
-
#include <linux/sunrpc/svc_rdma.h>
#include "xprt_rdma.h"
@@ -32,7 +30,6 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
struct kvec *dst, *src = &rcvbuf->head[0];
struct rpc_rqst *req;
- unsigned long cwnd;
u32 credits;
size_t len;
__be32 xid;
@@ -66,6 +63,8 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
if (dst->iov_len < len)
goto out_unlock;
memcpy(dst->iov_base, p, len);
+ xprt_pin_rqst(req);
+ spin_unlock(&xprt->queue_lock);
credits = be32_to_cpup(rdma_resp + 2);
if (credits == 0)
@@ -74,15 +73,13 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
credits = r_xprt->rx_buf.rb_bc_max_requests;
spin_lock_bh(&xprt->transport_lock);
- cwnd = xprt->cwnd;
xprt->cwnd = credits << RPC_CWNDSHIFT;
- if (xprt->cwnd > cwnd)
- xprt_release_rqst_cong(req->rq_task);
spin_unlock_bh(&xprt->transport_lock);
-
+ spin_lock(&xprt->queue_lock);
ret = 0;
xprt_complete_rqst(req->rq_task, rcvbuf->len);
+ xprt_unpin_rqst(req);
rcvbuf->len = 0;
out_unlock:
@@ -251,7 +248,6 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt)
dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
xprt_free(xprt);
- module_put(THIS_MODULE);
}
static const struct rpc_xprt_ops xprt_rdma_bc_procs = {
@@ -323,20 +319,9 @@ xprt_setup_rdma_bc(struct xprt_create *args)
args->bc_xprt->xpt_bc_xprt = xprt;
xprt->bc_xprt = args->bc_xprt;
- if (!try_module_get(THIS_MODULE))
- goto out_fail;
-
/* Final put for backchannel xprt is in __svc_rdma_free */
xprt_get(xprt);
return xprt;
-
-out_fail:
- xprt_rdma_free_addresses(xprt);
- args->bc_xprt->xpt_bc_xprt = NULL;
- args->bc_xprt->xpt_bc_xps = NULL;
- xprt_put(xprt);
- xprt_free(xprt);
- return ERR_PTR(-EINVAL);
}
struct xprt_class xprt_rdma_bc = {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 2848cafd4a17..2f7ec8912f49 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -475,10 +475,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
/* Qualify the transport resource defaults with the
* capabilities of this particular device */
- newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
- /* transport hdr, head iovec, one page list entry, tail iovec */
- if (newxprt->sc_max_send_sges < 4) {
- pr_err("svcrdma: too few Send SGEs available (%d)\n",
+ /* Transport header, head iovec, tail iovec */
+ newxprt->sc_max_send_sges = 3;
+ /* Add one SGE per page list entry */
+ newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE;
+ if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) {
+ pr_err("svcrdma: too few Send SGEs available (%d needed)\n",
newxprt->sc_max_send_sges);
goto errout;
}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1b51e04d3566..ae77c71c1f64 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -361,7 +361,7 @@ static ssize_t
xs_read_kvec(struct socket *sock, struct msghdr *msg, int flags,
struct kvec *kvec, size_t count, size_t seek)
{
- iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, kvec, 1, count);
+ iov_iter_kvec(&msg->msg_iter, READ, kvec, 1, count);
return xs_sock_recvmsg(sock, msg, flags, seek);
}
@@ -370,7 +370,7 @@ xs_read_bvec(struct socket *sock, struct msghdr *msg, int flags,
struct bio_vec *bvec, unsigned long nr, size_t count,
size_t seek)
{
- iov_iter_bvec(&msg->msg_iter, READ | ITER_BVEC, bvec, nr, count);
+ iov_iter_bvec(&msg->msg_iter, READ, bvec, nr, count);
return xs_sock_recvmsg(sock, msg, flags, seek);
}
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 4bdea0057171..efb16f69bd2c 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
iov.iov_base = &s;
iov.iov_len = sizeof(s);
msg.msg_name = NULL;
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len);
+ iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len);
ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
if (ret == -EWOULDBLOCK)
return -EWOULDBLOCK;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 276edbc04f38..d753e362d2d9 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -489,7 +489,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
iov.iov_base = kaddr + offset;
iov.iov_len = size;
- iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
+ iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
rc = tls_push_data(sk, &msg_iter, size,
flags, TLS_RECORD_TYPE_DATA);
kunmap(page);
@@ -538,7 +538,7 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
{
struct iov_iter msg_iter;
- iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
+ iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0);
return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5cd88ba8acd1..7b1af8b59cd2 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -799,7 +799,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send);
bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC;
unsigned char record_type = TLS_RECORD_TYPE_DATA;
- bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+ bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
bool eor = !(msg->msg_flags & MSG_MORE);
size_t try_to_copy, copied = 0;
struct sk_msg *msg_pl, *msg_en;
@@ -1457,7 +1457,7 @@ int tls_sw_recvmsg(struct sock *sk,
bool cmsg = false;
int target, err = 0;
long timeo;
- bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+ bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
int num_async = 0;
flags |= nonblock;
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 4a9ee2d83158..140270a13d54 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -8,7 +8,6 @@ config XFRM
config XFRM_OFFLOAD
bool
- depends on XFRM
config XFRM_ALGO
tristate
diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c
index 2ad33ce1ea17..eca8d84d99bf 100644
--- a/net/xfrm/xfrm_hash.c
+++ b/net/xfrm/xfrm_hash.c
@@ -6,7 +6,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/xfrm.h>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.