summaryrefslogtreecommitdiff
path: root/net/rds
diff options
context:
space:
mode:
Diffstat (limited to 'net/rds')
-rw-r--r--net/rds/Kconfig9
-rw-r--r--net/rds/Makefile5
-rw-r--r--net/rds/af_rds.c2
-rw-r--r--net/rds/connection.c10
-rw-r--r--net/rds/ib.h4
-rw-r--r--net/rds/ib_rdma.c4
-rw-r--r--net/rds/ib_sysctl.c1
-rw-r--r--net/rds/page.c25
-rw-r--r--net/rds/rdma.c3
-rw-r--r--net/rds/recv.c13
-rw-r--r--net/rds/send.c11
-rw-r--r--net/rds/stats.c3
-rw-r--r--net/rds/sysctl.c1
-rw-r--r--net/rds/tcp.c52
-rw-r--r--net/rds/tcp_listen.c6
-rw-r--r--net/rds/tcp_recv.c4
16 files changed, 91 insertions, 62 deletions
diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 75cd696963b2..f007730aa2bb 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -26,3 +26,12 @@ config RDS_DEBUG
bool "RDS debugging messages"
depends on RDS
default n
+
+config GCOV_PROFILE_RDS
+ bool "Enable GCOV profiling on RDS"
+ depends on GCOV_KERNEL
+ help
+ Enable GCOV profiling on RDS for checking which functions/lines
+ are executed.
+
+ If unsure, say N.
diff --git a/net/rds/Makefile b/net/rds/Makefile
index 8fdc118e2927..3af1ca1d965c 100644
--- a/net/rds/Makefile
+++ b/net/rds/Makefile
@@ -15,3 +15,8 @@ rds_tcp-y := tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \
tcp_send.o tcp_stats.o
ccflags-$(CONFIG_RDS_DEBUG) := -DRDS_DEBUG
+
+# for GCOV coverage profiling
+ifdef CONFIG_GCOV_PROFILE_RDS
+GCOV_PROFILE := y
+endif
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 01c4cdfef45d..8435a20968ef 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval,
rs->rs_rx_traces = trace.rx_traces;
for (i = 0; i < rs->rs_rx_traces; i++) {
- if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) {
+ if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) {
rs->rs_rx_traces = 0;
return -EFAULT;
}
diff --git a/net/rds/connection.c b/net/rds/connection.c
index b4cc699c5fad..d62f486ab29f 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -749,8 +749,7 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
cinfo->laddr = conn->c_laddr.s6_addr32[3];
cinfo->faddr = conn->c_faddr.s6_addr32[3];
cinfo->tos = conn->c_tos;
- strncpy(cinfo->transport, conn->c_trans->t_name,
- sizeof(cinfo->transport));
+ strscpy_pad(cinfo->transport, conn->c_trans->t_name);
cinfo->flags = 0;
rds_conn_info_set(cinfo->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags),
@@ -775,8 +774,7 @@ static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
cinfo6->next_rx_seq = cp->cp_next_rx_seq;
cinfo6->laddr = conn->c_laddr;
cinfo6->faddr = conn->c_faddr;
- strncpy(cinfo6->transport, conn->c_trans->t_name,
- sizeof(cinfo6->transport));
+ strscpy_pad(cinfo6->transport, conn->c_trans->t_name);
cinfo6->flags = 0;
rds_conn_info_set(cinfo6->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags),
@@ -829,9 +827,7 @@ int rds_conn_init(void)
if (ret)
return ret;
- rds_conn_slab = kmem_cache_create("rds_connection",
- sizeof(struct rds_connection),
- 0, 0, NULL);
+ rds_conn_slab = KMEM_CACHE(rds_connection, 0);
if (!rds_conn_slab) {
rds_loop_net_exit();
return -ENOMEM;
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 2ba71102b1f1..8ef3178ed4d6 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -369,9 +369,6 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp);
void rds_ib_conn_free(void *arg);
int rds_ib_conn_path_connect(struct rds_conn_path *cp);
void rds_ib_conn_path_shutdown(struct rds_conn_path *cp);
-void rds_ib_state_change(struct sock *sk);
-int rds_ib_listen_init(void);
-void rds_ib_listen_stop(void);
__printf(2, 3)
void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...);
int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
@@ -402,7 +399,6 @@ void rds_ib_inc_free(struct rds_incoming *inc);
int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc,
struct rds_ib_ack_state *state);
-void rds_ib_recv_tasklet_fn(unsigned long data);
void rds_ib_recv_init_ring(struct rds_ib_connection *ic);
void rds_ib_recv_clear_ring(struct rds_ib_connection *ic);
void rds_ib_recv_init_ack(struct rds_ib_connection *ic);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 8f070ee7e742..d1cfceeff133 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -40,10 +40,6 @@
#include "rds.h"
struct workqueue_struct *rds_ib_mr_wq;
-struct rds_ib_dereg_odp_mr {
- struct work_struct work;
- struct ib_mr *mr;
-};
static void rds_ib_odp_mr_worker(struct work_struct *work);
diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c
index e4e41b3afce7..2af678e71e3c 100644
--- a/net/rds/ib_sysctl.c
+++ b/net/rds/ib_sysctl.c
@@ -103,7 +103,6 @@ static struct ctl_table rds_ib_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- { }
};
void rds_ib_sysctl_exit(void)
diff --git a/net/rds/page.c b/net/rds/page.c
index 7cc57e098ddb..afb151eac271 100644
--- a/net/rds/page.c
+++ b/net/rds/page.c
@@ -40,10 +40,12 @@
struct rds_page_remainder {
struct page *r_page;
unsigned long r_offset;
+ local_lock_t bh_lock;
};
-static
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders) = {
+ .bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
/**
* rds_page_remainder_alloc - build up regions of a message.
@@ -69,7 +71,6 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
gfp_t gfp)
{
struct rds_page_remainder *rem;
- unsigned long flags;
struct page *page;
int ret;
@@ -87,8 +88,9 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
goto out;
}
- rem = &per_cpu(rds_page_remainders, get_cpu());
- local_irq_save(flags);
+ local_bh_disable();
+ local_lock_nested_bh(&rds_page_remainders.bh_lock);
+ rem = this_cpu_ptr(&rds_page_remainders);
while (1) {
/* avoid a tiny region getting stuck by tossing it */
@@ -116,13 +118,14 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
}
/* alloc if there is nothing for us to use */
- local_irq_restore(flags);
- put_cpu();
+ local_unlock_nested_bh(&rds_page_remainders.bh_lock);
+ local_bh_enable();
page = alloc_page(gfp);
- rem = &per_cpu(rds_page_remainders, get_cpu());
- local_irq_save(flags);
+ local_bh_disable();
+ local_lock_nested_bh(&rds_page_remainders.bh_lock);
+ rem = this_cpu_ptr(&rds_page_remainders);
if (!page) {
ret = -ENOMEM;
@@ -140,8 +143,8 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
rem->r_offset = 0;
}
- local_irq_restore(flags);
- put_cpu();
+ local_unlock_nested_bh(&rds_page_remainders.bh_lock);
+ local_bh_enable();
out:
rdsdebug("bytes %lu ret %d %p %u %u\n", bytes, ret,
ret ? NULL : sg_page(scat), ret ? 0 : scat->offset,
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index fba82d36593a..00dbcd4d28e6 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
kfree(sg);
}
ret = PTR_ERR(trans_private);
+ /* Trigger connection so that its ready for the next retry */
+ if (ret == -ENODEV && cp)
+ rds_conn_connect_if_down(cp->cp_conn);
goto out;
}
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c71b923764fd..5627f80013f8 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
struct sock *sk = rds_rs_to_sk(rs);
int ret = 0;
unsigned long flags;
+ struct rds_incoming *to_drop = NULL;
write_lock_irqsave(&rs->rs_recv_lock, flags);
if (!list_empty(&inc->i_item)) {
@@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
-be32_to_cpu(inc->i_hdr.h_len),
inc->i_hdr.h_dport);
list_del_init(&inc->i_item);
- rds_inc_put(inc);
+ to_drop = inc;
}
}
write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+ if (to_drop)
+ rds_inc_put(to_drop);
+
rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop);
return ret;
}
@@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs)
struct sock *sk = rds_rs_to_sk(rs);
struct rds_incoming *inc, *tmp;
unsigned long flags;
+ LIST_HEAD(to_drop);
write_lock_irqsave(&rs->rs_recv_lock, flags);
list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) {
rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong,
-be32_to_cpu(inc->i_hdr.h_len),
inc->i_hdr.h_dport);
+ list_move(&inc->i_item, &to_drop);
+ }
+ write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+
+ list_for_each_entry_safe(inc, tmp, &to_drop, i_item) {
list_del_init(&inc->i_item);
rds_inc_put(inc);
}
- write_unlock_irqrestore(&rs->rs_recv_lock, flags);
}
/*
diff --git a/net/rds/send.c b/net/rds/send.c
index 5e57a1581dc6..09a280110654 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset);
static int acquire_in_xmit(struct rds_conn_path *cp)
{
- return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0;
+ return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0;
}
static void release_in_xmit(struct rds_conn_path *cp)
{
- clear_bit(RDS_IN_XMIT, &cp->cp_flags);
- smp_mb__after_atomic();
+ clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags);
/*
* We don't use wait_on_bit()/wake_up_bit() because our waking is in a
* hot path and finding waiters is very rare. We don't want to walk
@@ -1313,12 +1312,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
/* Parse any control messages the user may have included. */
ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct);
- if (ret) {
- /* Trigger connection so that its ready for the next retry */
- if (ret == -EAGAIN)
- rds_conn_connect_if_down(conn);
+ if (ret)
goto out;
- }
if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) {
printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n",
diff --git a/net/rds/stats.c b/net/rds/stats.c
index 9e87da43c004..cb2e3d2cdf73 100644
--- a/net/rds/stats.c
+++ b/net/rds/stats.c
@@ -89,8 +89,7 @@ void rds_stats_info_copy(struct rds_info_iterator *iter,
for (i = 0; i < nr; i++) {
BUG_ON(strlen(names[i]) >= sizeof(ctr.name));
- strncpy(ctr.name, names[i], sizeof(ctr.name) - 1);
- ctr.name[sizeof(ctr.name) - 1] = '\0';
+ strscpy_pad(ctr.name, names[i]);
ctr.value = values[i];
rds_info_copy(iter, &ctr, sizeof(ctr));
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index e381bbcd9cc1..025f518a4349 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -89,7 +89,6 @@ static struct ctl_table rds_sysctl_rds_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- { }
};
void rds_sysctl_exit(void)
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 2dba7505b414..3cc2f303bf78 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -61,8 +61,10 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0);
static struct kmem_cache *rds_tcp_conn_slab;
-static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
- void *buffer, size_t *lenp, loff_t *fpos);
+static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *fpos);
+static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *fpos);
static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -74,7 +76,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
/* data is per-net pointer */
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = rds_tcp_skbuf_handler,
+ .proc_handler = rds_tcp_sndbuf_handler,
.extra1 = &rds_tcp_min_sndbuf,
},
#define RDS_TCP_RCVBUF 1
@@ -83,10 +85,9 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
/* data is per-net pointer */
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = rds_tcp_skbuf_handler,
+ .proc_handler = rds_tcp_rcvbuf_handler,
.extra1 = &rds_tcp_min_rcvbuf,
},
- { }
};
u32 rds_tcp_write_seq(struct rds_tcp_connection *tc)
@@ -503,12 +504,8 @@ bool rds_tcp_tune(struct socket *sock)
release_sock(sk);
return false;
}
- /* Update ns_tracker to current stack trace and refcounted tracker */
- __netns_tracker_free(net, &sk->ns_tracker, false);
-
- sk->sk_net_refcnt = 1;
- netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL);
- sock_inuse_add(net, 1);
+ sk_net_refcnt_upgrade(sk);
+ put_net(net);
}
rtn = net_generic(net, rds_tcp_netid);
if (rtn->sndbuf_size > 0) {
@@ -683,10 +680,10 @@ static void rds_tcp_sysctl_reset(struct net *net)
spin_unlock_irq(&rds_tcp_conn_lock);
}
-static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
+static int rds_tcp_skbuf_handler(struct rds_tcp_net *rtn,
+ const struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *fpos)
{
- struct net *net = current->nsproxy->net_ns;
int err;
err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos);
@@ -695,11 +692,34 @@ static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
*(int *)(ctl->extra1));
return err;
}
- if (write)
+
+ if (write && rtn->rds_tcp_listen_sock && rtn->rds_tcp_listen_sock->sk) {
+ struct net *net = sock_net(rtn->rds_tcp_listen_sock->sk);
+
rds_tcp_sysctl_reset(net);
+ }
+
return 0;
}
+static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *fpos)
+{
+ struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net,
+ sndbuf_size);
+
+ return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos);
+}
+
+static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *fpos)
+{
+ struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net,
+ rcvbuf_size);
+
+ return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos);
+}
+
static void rds_tcp_exit(void)
{
rds_tcp_set_unloading();
@@ -720,9 +740,7 @@ static int __init rds_tcp_init(void)
{
int ret;
- rds_tcp_conn_slab = kmem_cache_create("rds_tcp_connection",
- sizeof(struct rds_tcp_connection),
- 0, 0, NULL);
+ rds_tcp_conn_slab = KMEM_CACHE(rds_tcp_connection, 0);
if (!rds_tcp_conn_slab) {
ret = -ENOMEM;
goto out;
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 05008ce5c421..d89bd8d0c354 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -105,6 +105,10 @@ int rds_tcp_accept_one(struct socket *sock)
int conn_state;
struct rds_conn_path *cp;
struct in6_addr *my_addr, *peer_addr;
+ struct proto_accept_arg arg = {
+ .flags = O_NONBLOCK,
+ .kern = true,
+ };
#if !IS_ENABLED(CONFIG_IPV6)
struct in6_addr saddr, daddr;
#endif
@@ -119,7 +123,7 @@ int rds_tcp_accept_one(struct socket *sock)
if (ret)
goto out;
- ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true);
+ ret = sock->ops->accept(sock, new_sock, &arg);
if (ret < 0)
goto out;
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index c00f04a1a534..7997a19d1da3 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -337,9 +337,7 @@ out:
int rds_tcp_recv_init(void)
{
- rds_tcp_incoming_slab = kmem_cache_create("rds_tcp_incoming",
- sizeof(struct rds_tcp_incoming),
- 0, 0, NULL);
+ rds_tcp_incoming_slab = KMEM_CACHE(rds_tcp_incoming, 0);
if (!rds_tcp_incoming_slab)
return -ENOMEM;
return 0;
generated by cgit (git 2.34.1) at 2025-08-01 08:12:36 +0000