summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-19 20:06:06 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-19 20:06:06 +0300
commit5f4fc6d440d77a2cf74fe4ea56955674ac7e35e7 (patch)
tree87dedefb73acda80d945a84603c687002c0ce1d5 /net
parent249be8511b269495bc95cb8bdfdd5840b2ba73c0 (diff)
parent8d650cdedaabb33e85e9b7c517c0c71fcecc1de9 (diff)
downloadlinux-5f4fc6d440d77a2cf74fe4ea56955674ac7e35e7.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) Fix AF_XDP cq entry leak, from Ilya Maximets. 2) Fix handling of PHY power-down on RTL8411B, from Heiner Kallweit. 3) Add some new PCI IDs to iwlwifi, from Ihab Zhaika. 4) Fix handling of neigh timers wrt. entries added by userspace, from Lorenzo Bianconi. 5) Various cases of missing of_node_put(), from Nishka Dasgupta. 6) The new NET_ACT_CT needs to depend upon NF_NAT, from Yue Haibing. 7) Various RDS layer fixes, from Gerd Rausch. 8) Fix some more fallout from TCQ_F_CAN_BYPASS generalization, from Cong Wang. 9) Fix FIB source validation checks over loopback, also from Cong Wang. 10) Use promisc for unsupported number of filters, from Justin Chen. 11) Missing sibling route unlink on failure in ipv6, from Ido Schimmel. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (90 commits) tcp: fix tcp_set_congestion_control() use from bpf hook ag71xx: fix return value check in ag71xx_probe() ag71xx: fix error return code in ag71xx_probe() usb: qmi_wwan: add D-Link DWM-222 A2 device ID bnxt_en: Fix VNIC accounting when enabling aRFS on 57500 chips. net: dsa: sja1105: Fix missing unlock on error in sk_buff() gve: replace kfree with kvfree selftests/bpf: fix test_xdp_noinline on s390 selftests/bpf: fix "valid read map access into a read-only array 1" on s390 net/mlx5: Replace kfree with kvfree MAINTAINERS: update netsec driver ipv6: Unlink sibling route in case of failure liquidio: Replace vmalloc + memset with vzalloc udp: Fix typo in net/ipv4/udp.c net: bcmgenet: use promisc for unsupported filters ipv6: rt6_check should return NULL if 'from' is NULL tipc: initialize 'validated' field of received packets selftests: add a test case for rp_filter fib: relax source validation check for loopback packets mlxsw: spectrum: Do not process learned records with a dummy FID ...
Diffstat (limited to 'net')
-rw-r--r--net/core/filter.c26
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/skbuff.c2
-rw-r--r--net/dsa/tag_sja1105.c1
-rw-r--r--net/ipv4/fib_frontend.c5
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_cong.c6
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv6/ip6_fib.c18
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/sit.c13
-rw-r--r--net/rds/ib.h1
-rw-r--r--net/rds/ib_cm.c9
-rw-r--r--net/rds/ib_frmr.c84
-rw-r--r--net/rds/ib_mr.h4
-rw-r--r--net/rds/ib_rdma.c60
-rw-r--r--net/sched/Kconfig2
-rw-r--r--net/sched/cls_api.c1
-rw-r--r--net/sched/sch_fq_codel.c2
-rw-r--r--net/sched/sch_sfq.c2
-rw-r--r--net/sched/sch_taprio.c6
-rw-r--r--net/sctp/sm_make_chunk.c12
-rw-r--r--net/tipc/node.c1
-rw-r--r--net/xdp/xdp_umem.c16
-rw-r--r--net/xdp/xsk.c13
25 files changed, 192 insertions, 102 deletions
diff --git a/net/core/filter.c b/net/core/filter.c
index 47f6386fb17a..4e2a79b2fd77 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4335,7 +4335,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
TCP_CA_NAME_MAX-1));
name[TCP_CA_NAME_MAX-1] = 0;
ret = tcp_set_congestion_control(sk, name, false,
- reinit);
+ reinit, true);
} else {
struct tcp_sock *tp = tcp_sk(sk);
@@ -6884,20 +6884,30 @@ static bool sock_addr_is_valid_access(int off, int size,
case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
msg_src_ip6[3]):
- /* Only narrow read access allowed for now. */
if (type == BPF_READ) {
bpf_ctx_record_field_size(info, size_default);
+
+ if (bpf_ctx_wide_access_ok(off, size,
+ struct bpf_sock_addr,
+ user_ip6))
+ return true;
+
+ if (bpf_ctx_wide_access_ok(off, size,
+ struct bpf_sock_addr,
+ msg_src_ip6))
+ return true;
+
if (!bpf_ctx_narrow_access_ok(off, size, size_default))
return false;
} else {
- if (bpf_ctx_wide_store_ok(off, size,
- struct bpf_sock_addr,
- user_ip6))
+ if (bpf_ctx_wide_access_ok(off, size,
+ struct bpf_sock_addr,
+ user_ip6))
return true;
- if (bpf_ctx_wide_store_ok(off, size,
- struct bpf_sock_addr,
- msg_src_ip6))
+ if (bpf_ctx_wide_access_ok(off, size,
+ struct bpf_sock_addr,
+ msg_src_ip6))
return true;
if (size != size_default)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 26da97359d5b..f79e61c570ea 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1124,6 +1124,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
atomic_set(&neigh->probes,
NEIGH_VAR(neigh->parms, UCAST_PROBES));
+ neigh_del_timer(neigh);
neigh->nud_state = NUD_INCOMPLETE;
neigh->updated = now;
next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
@@ -1140,6 +1141,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
}
} else if (neigh->nud_state & NUD_STALE) {
neigh_dbg(2, "neigh %p is delayed\n", neigh);
+ neigh_del_timer(neigh);
neigh->nud_state = NUD_DELAY;
neigh->updated = jiffies;
neigh_add_timer(neigh, jiffies +
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6f1e31f674a3..0338820ee0ec 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -762,7 +762,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
printk("%sdev name=%s feat=0x%pNF\n",
level, dev->name, &dev->features);
if (sk)
- printk("%ssk family=%hu type=%hu proto=%hu\n",
+ printk("%ssk family=%hu type=%u proto=%u\n",
level, sk->sk_family, sk->sk_type, sk->sk_protocol);
if (full_pkt && headroom)
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 1d96c9d4a8e9..26363d72d25b 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -216,6 +216,7 @@ static struct sk_buff
if (!skb) {
dev_err_ratelimited(dp->ds->dev,
"Failed to copy stampable skb\n");
+ spin_unlock(&sp->data->meta_lock);
return NULL;
}
sja1105_transfer_meta(skb, meta);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 317339cd7f03..e8bc939b56dd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -388,6 +388,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
fib_combine_itag(itag, &res);
dev_match = fib_info_nh_uses_dev(res.fi, dev);
+ /* This is not common, loopback packets retain skb_dst so normally they
+ * would not even hit this slow path.
+ */
+ dev_match = dev_match || (res.type == RTN_LOCAL &&
+ dev == net->loopback_dev);
if (dev_match) {
ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
return ret;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7846afacdf0b..776905899ac0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2785,7 +2785,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
name[val] = 0;
lock_sock(sk);
- err = tcp_set_congestion_control(sk, name, true, true);
+ err = tcp_set_congestion_control(sk, name, true, true,
+ ns_capable(sock_net(sk)->user_ns,
+ CAP_NET_ADMIN));
release_sock(sk);
return err;
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index e1862b64a90f..c445a81d144e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -333,7 +333,8 @@ out:
* tcp_reinit_congestion_control (if the current congestion control was
* already initialized.
*/
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+ bool reinit, bool cap_net_admin)
{
struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_congestion_ops *ca;
@@ -369,8 +370,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo
} else {
err = -EBUSY;
}
- } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
- ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
+ } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
err = -EPERM;
} else if (!try_module_get(ca->owner)) {
err = -EBUSY;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c21862ba9c02..d88821c794fb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2170,7 +2170,7 @@ start_lookup:
/* Initialize UDP checksum. If exited with zero value (success),
* CHECKSUM_UNNECESSARY means, that no more checks are required.
- * Otherwise, csum completion requires chacksumming packet body,
+ * Otherwise, csum completion requires checksumming packet body,
* including udp header and folding it to skb->csum.
*/
static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 49884f96232b..87f47bc55c5e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1151,8 +1151,24 @@ add:
err = call_fib6_entry_notifiers(info->nl_net,
FIB_EVENT_ENTRY_ADD,
rt, extack);
- if (err)
+ if (err) {
+ struct fib6_info *sibling, *next_sibling;
+
+ /* If the route has siblings, then it first
+ * needs to be unlinked from them.
+ */
+ if (!rt->fib6_nsiblings)
+ return err;
+
+ list_for_each_entry_safe(sibling, next_sibling,
+ &rt->fib6_siblings,
+ fib6_siblings)
+ sibling->fib6_nsiblings--;
+ rt->fib6_nsiblings = 0;
+ list_del_init(&rt->fib6_siblings);
+ rt6_multipath_rebalance(next_sibling);
return err;
+ }
}
rcu_assign_pointer(rt->fib6_next, iter);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8b0c33fb19a2..e49fec767a10 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2563,7 +2563,7 @@ static struct dst_entry *rt6_check(struct rt6_info *rt,
{
u32 rt_cookie = 0;
- if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) ||
+ if (!from || !fib6_get_cookie_safe(from, &rt_cookie) ||
rt_cookie != cookie)
return NULL;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 80610899a323..b2ccbc473127 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -900,12 +900,17 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6,
0, dst, tiph->saddr, 0, 0,
sock_net_uid(tunnel->net, NULL));
- rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
- if (IS_ERR(rt)) {
- dev->stats.tx_carrier_errors++;
- goto tx_error_icmp;
+ rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr);
+ if (!rt) {
+ rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
+ if (IS_ERR(rt)) {
+ dev->stats.tx_carrier_errors++;
+ goto tx_error_icmp;
+ }
+ dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr);
}
+
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
dev->stats.tx_carrier_errors++;
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 66c03c7665b2..303c6ee8bdb7 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -156,6 +156,7 @@ struct rds_ib_connection {
/* To control the number of wrs from fastreg */
atomic_t i_fastreg_wrs;
+ atomic_t i_fastreg_inuse_count;
/* interrupt handling */
struct tasklet_struct i_send_tasklet;
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index c36d89cd14a1..fddaa09f7b0d 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -40,6 +40,7 @@
#include "rds_single_path.h"
#include "rds.h"
#include "ib.h"
+#include "ib_mr.h"
/*
* Set the selected protocol version
@@ -526,7 +527,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
attr.qp_type = IB_QPT_RC;
attr.send_cq = ic->i_send_cq;
attr.recv_cq = ic->i_recv_cq;
- atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
/*
* XXX this can fail if max_*_wr is too large? Are we supposed
@@ -993,6 +993,11 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
ic->i_cm_id, err);
}
+ /* kick off "flush_worker" for all pools in order to reap
+ * all FRMR registrations that are still marked "FRMR_IS_INUSE"
+ */
+ rds_ib_flush_mrs();
+
/*
* We want to wait for tx and rx completion to finish
* before we tear down the connection, but we have to be
@@ -1005,6 +1010,7 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
wait_event(rds_ib_ring_empty_wait,
rds_ib_ring_empty(&ic->i_recv_ring) &&
(atomic_read(&ic->i_signaled_sends) == 0) &&
+ (atomic_read(&ic->i_fastreg_inuse_count) == 0) &&
(atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR));
tasklet_kill(&ic->i_send_tasklet);
tasklet_kill(&ic->i_recv_tasklet);
@@ -1132,6 +1138,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
spin_lock_init(&ic->i_ack_lock);
#endif
atomic_set(&ic->i_signaled_sends, 0);
+ atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
/*
* rds_ib_conn_shutdown() waits for these to be emptied so they
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 32ae26ed58a0..06ecf9d2d4bf 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -32,6 +32,24 @@
#include "ib_mr.h"
+static inline void
+rds_transition_frwr_state(struct rds_ib_mr *ibmr,
+ enum rds_ib_fr_state old_state,
+ enum rds_ib_fr_state new_state)
+{
+ if (cmpxchg(&ibmr->u.frmr.fr_state,
+ old_state, new_state) == old_state &&
+ old_state == FRMR_IS_INUSE) {
+ /* enforce order of ibmr->u.frmr.fr_state update
+ * before decrementing i_fastreg_inuse_count
+ */
+ smp_mb__before_atomic();
+ atomic_dec(&ibmr->ic->i_fastreg_inuse_count);
+ if (waitqueue_active(&rds_ib_ring_empty_wait))
+ wake_up(&rds_ib_ring_empty_wait);
+ }
+}
+
static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
int npages)
{
@@ -75,6 +93,8 @@ static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
pool->max_items_soft = pool->max_items;
frmr->fr_state = FRMR_IS_FREE;
+ init_waitqueue_head(&frmr->fr_inv_done);
+ init_waitqueue_head(&frmr->fr_reg_done);
return ibmr;
out_no_cigar:
@@ -116,13 +136,19 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
if (unlikely(ret != ibmr->sg_len))
return ret < 0 ? ret : -EINVAL;
+ if (cmpxchg(&frmr->fr_state,
+ FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE)
+ return -EBUSY;
+
+ atomic_inc(&ibmr->ic->i_fastreg_inuse_count);
+
/* Perform a WR for the fast_reg_mr. Each individual page
* in the sg list is added to the fast reg page list and placed
* inside the fast_reg_mr WR. The key used is a rolling 8bit
* counter, which should guarantee uniqueness.
*/
ib_update_fast_reg_key(frmr->mr, ibmr->remap_count++);
- frmr->fr_state = FRMR_IS_INUSE;
+ frmr->fr_reg = true;
memset(&reg_wr, 0, sizeof(reg_wr));
reg_wr.wr.wr_id = (unsigned long)(void *)ibmr;
@@ -138,12 +164,23 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
ret = ib_post_send(ibmr->ic->i_cm_id->qp, &reg_wr.wr, NULL);
if (unlikely(ret)) {
/* Failure here can be because of -ENOMEM as well */
- frmr->fr_state = FRMR_IS_STALE;
+ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
+
atomic_inc(&ibmr->ic->i_fastreg_wrs);
if (printk_ratelimit())
pr_warn("RDS/IB: %s returned error(%d)\n",
__func__, ret);
+ goto out;
}
+
+ /* Wait for the registration to complete in order to prevent an invalid
+ * access error resulting from a race between the memory region already
+ * being accessed while registration is still pending.
+ */
+ wait_event(frmr->fr_reg_done, !frmr->fr_reg);
+
+out:
+
return ret;
}
@@ -255,12 +292,29 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr)
ret = ib_post_send(i_cm_id->qp, s_wr, NULL);
if (unlikely(ret)) {
- frmr->fr_state = FRMR_IS_STALE;
+ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
frmr->fr_inv = false;
+ /* enforce order of frmr->fr_inv update
+ * before incrementing i_fastreg_wrs
+ */
+ smp_mb__before_atomic();
atomic_inc(&ibmr->ic->i_fastreg_wrs);
pr_err("RDS/IB: %s returned error(%d)\n", __func__, ret);
goto out;
}
+
+ /* Wait for the FRMR_IS_FREE (or FRMR_IS_STALE) transition in order to
+ * 1) avoid a silly bouncing between "clean_list" and "drop_list"
+ * triggered by function "rds_ib_reg_frmr" as it is releases frmr
+ * regions whose state is not "FRMR_IS_FREE" right away.
+ * 2) prevents an invalid access error in a race
+ * from a pending "IB_WR_LOCAL_INV" operation
+ * with a teardown ("dma_unmap_sg", "put_page")
+ * and de-registration ("ib_dereg_mr") of the corresponding
+ * memory region.
+ */
+ wait_event(frmr->fr_inv_done, frmr->fr_state != FRMR_IS_INUSE);
+
out:
return ret;
}
@@ -271,7 +325,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
struct rds_ib_frmr *frmr = &ibmr->u.frmr;
if (wc->status != IB_WC_SUCCESS) {
- frmr->fr_state = FRMR_IS_STALE;
+ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
if (rds_conn_up(ic->conn))
rds_ib_conn_error(ic->conn,
"frmr completion <%pI4,%pI4> status %u(%s), vendor_err 0x%x, disconnecting and reconnecting\n",
@@ -283,10 +337,20 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
}
if (frmr->fr_inv) {
- frmr->fr_state = FRMR_IS_FREE;
+ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_FREE);
frmr->fr_inv = false;
+ wake_up(&frmr->fr_inv_done);
}
+ if (frmr->fr_reg) {
+ frmr->fr_reg = false;
+ wake_up(&frmr->fr_reg_done);
+ }
+
+ /* enforce order of frmr->{fr_reg,fr_inv} update
+ * before incrementing i_fastreg_wrs
+ */
+ smp_mb__before_atomic();
atomic_inc(&ic->i_fastreg_wrs);
}
@@ -295,14 +359,18 @@ void rds_ib_unreg_frmr(struct list_head *list, unsigned int *nfreed,
{
struct rds_ib_mr *ibmr, *next;
struct rds_ib_frmr *frmr;
- int ret = 0;
+ int ret = 0, ret2;
unsigned int freed = *nfreed;
/* String all ib_mr's onto one list and hand them to ib_unmap_fmr */
list_for_each_entry(ibmr, list, unmap_list) {
- if (ibmr->sg_dma_len)
- ret |= rds_ib_post_inv(ibmr);
+ if (ibmr->sg_dma_len) {
+ ret2 = rds_ib_post_inv(ibmr);
+ if (ret2 && !ret)
+ ret = ret2;
+ }
}
+
if (ret)
pr_warn("RDS/IB: %s failed (err=%d)\n", __func__, ret);
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 5da12c248431..9045a8c0edff 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -57,6 +57,9 @@ struct rds_ib_frmr {
struct ib_mr *mr;
enum rds_ib_fr_state fr_state;
bool fr_inv;
+ wait_queue_head_t fr_inv_done;
+ bool fr_reg;
+ wait_queue_head_t fr_reg_done;
struct ib_send_wr fr_wr;
unsigned int dma_npages;
unsigned int sg_byte_len;
@@ -97,6 +100,7 @@ struct rds_ib_mr_pool {
struct llist_head free_list; /* unused MRs */
struct llist_head clean_list; /* unused & unmapped MRs */
wait_queue_head_t flush_wait;
+ spinlock_t clean_lock; /* "clean_list" concurrency */
atomic_t free_pinned; /* memory pinned by free MRs */
unsigned long max_items;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 0b347f46b2f4..c8c1e3ae8d84 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -40,9 +40,6 @@
struct workqueue_struct *rds_ib_mr_wq;
-static DEFINE_PER_CPU(unsigned long, clean_list_grace);
-#define CLEAN_LIST_BUSY_BIT 0
-
static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr)
{
struct rds_ib_device *rds_ibdev;
@@ -195,12 +192,11 @@ struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
{
struct rds_ib_mr *ibmr = NULL;
struct llist_node *ret;
- unsigned long *flag;
+ unsigned long flags;
- preempt_disable();
- flag = this_cpu_ptr(&clean_list_grace);
- set_bit(CLEAN_LIST_BUSY_BIT, flag);
+ spin_lock_irqsave(&pool->clean_lock, flags);
ret = llist_del_first(&pool->clean_list);
+ spin_unlock_irqrestore(&pool->clean_lock, flags);
if (ret) {
ibmr = llist_entry(ret, struct rds_ib_mr, llnode);
if (pool->pool_type == RDS_IB_MR_8K_POOL)
@@ -209,23 +205,9 @@ struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
rds_ib_stats_inc(s_ib_rdma_mr_1m_reused);
}
- clear_bit(CLEAN_LIST_BUSY_BIT, flag);
- preempt_enable();
return ibmr;
}
-static inline void wait_clean_list_grace(void)
-{
- int cpu;
- unsigned long *flag;
-
- for_each_online_cpu(cpu) {
- flag = &per_cpu(clean_list_grace, cpu);
- while (test_bit(CLEAN_LIST_BUSY_BIT, flag))
- cpu_relax();
- }
-}
-
void rds_ib_sync_mr(void *trans_private, int direction)
{
struct rds_ib_mr *ibmr = trans_private;
@@ -324,8 +306,7 @@ static unsigned int llist_append_to_list(struct llist_head *llist,
* of clusters. Each cluster has linked llist nodes of
* MR_CLUSTER_SIZE mrs that are ready for reuse.
*/
-static void list_to_llist_nodes(struct rds_ib_mr_pool *pool,
- struct list_head *list,
+static void list_to_llist_nodes(struct list_head *list,
struct llist_node **nodes_head,
struct llist_node **nodes_tail)
{
@@ -402,8 +383,13 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
*/
dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list);
dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list);
- if (free_all)
+ if (free_all) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->clean_lock, flags);
llist_append_to_list(&pool->clean_list, &unmap_list);
+ spin_unlock_irqrestore(&pool->clean_lock, flags);
+ }
free_goal = rds_ib_flush_goal(pool, free_all);
@@ -416,27 +402,20 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
rds_ib_unreg_fmr(&unmap_list, &nfreed, &unpinned, free_goal);
if (!list_empty(&unmap_list)) {
- /* we have to make sure that none of the things we're about
- * to put on the clean list would race with other cpus trying
- * to pull items off. The llist would explode if we managed to
- * remove something from the clean list and then add it back again
- * while another CPU was spinning on that same item in llist_del_first.
- *
- * This is pretty unlikely, but just in case wait for an llist grace period
- * here before adding anything back into the clean list.
- */
- wait_clean_list_grace();
-
- list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
+ unsigned long flags;
+
+ list_to_llist_nodes(&unmap_list, &clean_nodes, &clean_tail);
if (ibmr_ret) {
*ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);
clean_nodes = clean_nodes->next;
}
/* more than one entry in llist nodes */
- if (clean_nodes)
+ if (clean_nodes) {
+ spin_lock_irqsave(&pool->clean_lock, flags);
llist_add_batch(clean_nodes, clean_tail,
&pool->clean_list);
-
+ spin_unlock_irqrestore(&pool->clean_lock, flags);
+ }
}
atomic_sub(unpinned, &pool->free_pinned);
@@ -471,7 +450,7 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_depleted);
else
rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_depleted);
- return ERR_PTR(-EAGAIN);
+ break;
}
/* We do have some empty MRs. Flush them out. */
@@ -485,7 +464,7 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
return ibmr;
}
- return ibmr;
+ return NULL;
}
static void rds_ib_mr_pool_flush_worker(struct work_struct *work)
@@ -610,6 +589,7 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev,
init_llist_head(&pool->free_list);
init_llist_head(&pool->drop_list);
init_llist_head(&pool->clean_list);
+ spin_lock_init(&pool->clean_lock);
mutex_init(&pool->flush_lock);
init_waitqueue_head(&pool->flush_wait);
INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker);
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index dd55b9ac3a66..afd2ba157a13 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -942,7 +942,7 @@ config NET_ACT_TUNNEL_KEY
config NET_ACT_CT
tristate "connection tracking tc action"
- depends on NET_CLS_ACT && NF_CONNTRACK
+ depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT
help
Say Y here to allow sending the packets to conntrack module.
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 278014e26aec..d144233423c5 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2152,6 +2152,7 @@ replay:
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false, rtnl_held);
tfilter_put(tp, fh);
+ q->flags &= ~TCQ_F_CAN_BYPASS;
}
errout:
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index e2faf33d282b..d59fbcc745d1 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -596,8 +596,6 @@ static unsigned long fq_codel_find(struct Qdisc *sch, u32 classid)
static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent,
u32 classid)
{
- /* we cannot bypass queue discipline anymore */
- sch->flags &= ~TCQ_F_CAN_BYPASS;
return 0;
}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 420bd8411677..68404a9d2ce4 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -824,8 +824,6 @@ static unsigned long sfq_find(struct Qdisc *sch, u32 classid)
static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent,
u32 classid)
{
- /* we cannot bypass queue discipline anymore */
- sch->flags &= ~TCQ_F_CAN_BYPASS;
return 0;
}
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 388750ddc57a..c39db507ba3f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -75,7 +75,7 @@ struct taprio_sched {
struct sched_gate_list __rcu *admin_sched;
struct hrtimer advance_timer;
struct list_head taprio_list;
- int txtime_delay;
+ u32 txtime_delay;
};
static ktime_t sched_base_time(const struct sched_gate_list *sched)
@@ -1113,7 +1113,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
goto unlock;
}
- q->txtime_delay = nla_get_s32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
+ q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
}
if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) &&
@@ -1430,7 +1430,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
goto options_error;
if (q->txtime_delay &&
- nla_put_s32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay))
+ nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay))
goto options_error;
if (oper && dump_schedule(skb, oper))
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ed39396b9bba..36bd8a6e82df 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2582,8 +2582,7 @@ do_addr_param:
case SCTP_PARAM_STATE_COOKIE:
asoc->peer.cookie_len =
ntohs(param.p->length) - sizeof(struct sctp_paramhdr);
- if (asoc->peer.cookie)
- kfree(asoc->peer.cookie);
+ kfree(asoc->peer.cookie);
asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp);
if (!asoc->peer.cookie)
retval = 0;
@@ -2648,8 +2647,7 @@ do_addr_param:
goto fall_through;
/* Save peer's random parameter */
- if (asoc->peer.peer_random)
- kfree(asoc->peer.peer_random);
+ kfree(asoc->peer.peer_random);
asoc->peer.peer_random = kmemdup(param.p,
ntohs(param.p->length), gfp);
if (!asoc->peer.peer_random) {
@@ -2663,8 +2661,7 @@ do_addr_param:
goto fall_through;
/* Save peer's HMAC list */
- if (asoc->peer.peer_hmacs)
- kfree(asoc->peer.peer_hmacs);
+ kfree(asoc->peer.peer_hmacs);
asoc->peer.peer_hmacs = kmemdup(param.p,
ntohs(param.p->length), gfp);
if (!asoc->peer.peer_hmacs) {
@@ -2680,8 +2677,7 @@ do_addr_param:
if (!ep->auth_enable)
goto fall_through;
- if (asoc->peer.peer_chunks)
- kfree(asoc->peer.peer_chunks);
+ kfree(asoc->peer.peer_chunks);
asoc->peer.peer_chunks = kmemdup(param.p,
ntohs(param.p->length), gfp);
if (!asoc->peer.peer_chunks)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 324a1f91b394..3a5be1d7e572 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1807,6 +1807,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
__skb_queue_head_init(&xmitq);
/* Ensure message is well-formed before touching the header */
+ TIPC_SKB_CB(skb)->validated = false;
if (unlikely(!tipc_msg_validate(&skb)))
goto discard;
hdr = buf_msg(skb);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 20c91f02d3d8..83de74ca729a 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -87,21 +87,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
struct netdev_bpf bpf;
int err = 0;
+ ASSERT_RTNL();
+
force_zc = flags & XDP_ZEROCOPY;
force_copy = flags & XDP_COPY;
if (force_zc && force_copy)
return -EINVAL;
- rtnl_lock();
- if (xdp_get_umem_from_qid(dev, queue_id)) {
- err = -EBUSY;
- goto out_rtnl_unlock;
- }
+ if (xdp_get_umem_from_qid(dev, queue_id))
+ return -EBUSY;
err = xdp_reg_umem_at_qid(dev, umem, queue_id);
if (err)
- goto out_rtnl_unlock;
+ return err;
umem->dev = dev;
umem->queue_id = queue_id;
@@ -110,7 +109,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
if (force_copy)
/* For copy-mode, we are done. */
- goto out_rtnl_unlock;
+ return 0;
if (!dev->netdev_ops->ndo_bpf ||
!dev->netdev_ops->ndo_xsk_async_xmit) {
@@ -125,7 +124,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
err = dev->netdev_ops->ndo_bpf(dev, &bpf);
if (err)
goto err_unreg_umem;
- rtnl_unlock();
umem->zc = true;
return 0;
@@ -135,8 +133,6 @@ err_unreg_umem:
err = 0; /* fallback to copy mode */
if (err)
xdp_clear_umem_at_qid(dev, queue_id);
-out_rtnl_unlock:
- rtnl_unlock();
return err;
}
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d4d6f10aa936..59b57d708697 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -240,6 +240,9 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
mutex_lock(&xs->mutex);
+ if (xs->queue_id >= xs->dev->real_num_tx_queues)
+ goto out;
+
while (xskq_peek_desc(xs->tx, &desc)) {
char *buffer;
u64 addr;
@@ -250,12 +253,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
goto out;
}
- if (xskq_reserve_addr(xs->umem->cq))
- goto out;
-
- if (xs->queue_id >= xs->dev->real_num_tx_queues)
- goto out;
-
len = desc.len;
skb = sock_alloc_send_skb(sk, len, 1, &err);
if (unlikely(!skb)) {
@@ -267,7 +264,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
addr = desc.addr;
buffer = xdp_umem_get_data(xs->umem, addr);
err = skb_store_bits(skb, 0, buffer, len);
- if (unlikely(err)) {
+ if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) {
kfree_skb(skb);
goto out;
}
@@ -433,6 +430,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY))
return -EINVAL;
+ rtnl_lock();
mutex_lock(&xs->mutex);
if (xs->state != XSK_READY) {
err = -EBUSY;
@@ -518,6 +516,7 @@ out_unlock:
xs->state = XSK_BOUND;
out_release:
mutex_unlock(&xs->mutex);
+ rtnl_unlock();
return err;
}