[lustre-devel] [PATCH 03/24] lnet: introduce struct lnet_nid
James Simmons
jsimmons at infradead.org
Tue Sep 21 19:19:40 PDT 2021
From: Mr NeilBrown <neilb at suse.de>
LNet nids are currently limited to 4-bytes for addresses.
This excludes the use of IPv6.
In order to support IPv6, introduce 'struct lnet_nid' which can hold
up to 128bit address and is extensible, and deprecate 'lnet_nid_t'.
lnet_nid_it will eventually be removed. Where lnet_nid_t is often
passed around by value, 'struct lnet_nid' will normally be passed
around by reference as it is over twice as large.
The net_type field, which currently has value up to 16, is now limited
to 0-254 with 255 being used as a wildcard. The most significant byte
is now a size field which gives the size of the whole nid minus 8. So
zero is correct for current nids with 4-byte addresses.
Where we still need to use 4-byte-address nids, we will use names
containing "nid4". So "nid4" is a lnet_nid_t when "nid" is a struct
lnet_nid. lnet_nid_to_nid4 converts a 'struct lnet_nid' to an
lnet_nid_t.
While lnet_nid_t is stored and often transmitted in host-endian format
(and possibly byte-swapped on receipt), 'struct lnet_nid' is always
stored in network-byte-order (i.e. big-endian). This is more common
approach for network addresses.
In this first instance, 'struct lnet_nid' is used for ni_nid in
'struct lnet_ni', and related support functions.
In particular libcfs_nidstr() is introduced which parallels
libcfs_nid2str(), but takes 'struct lnet_nid'.
In cases were we need to have similar functions for old and new style
nid, the new function is introduced with a slightly different name,
such as libcfs_nid2str above, or LNET_NID_NET (like LNET_NIDNET).
It will be confusing having both, but the plan is to remove the old
names as soon as practical.
WC-bug-id: https://jira.whamcloud.com/browse/LU-10391
Lustre-commit: 82a17076f880770a ("LU-10391 lnet: introduce struct lnet_nid")
Signed-off-by: Mr NeilBrown <neilb at suse.de>
Reviewed-on: https://review.whamcloud.com/42100
Reviewed-by: James Simmons <jsimmons at infradead.org>
Reviewed-by: Serguei Smirnov <ssmirnov at whamcloud.com>
Reviewed-by: Chris Horn <chris.horn at hpe.com>
Reviewed-by: Oleg Drokin <green at whamcloud.com>
Signed-off-by: James Simmons <jsimmons at infradead.org>
---
include/linux/lnet/lib-lnet.h | 4 +-
include/linux/lnet/lib-types.h | 2 +-
include/uapi/linux/lnet/lnet-idl.h | 28 ++++++++++-
include/uapi/linux/lnet/lnet-types.h | 66 ++++++++++++++++++++++++-
include/uapi/linux/lnet/nidstr.h | 10 +++-
net/lnet/klnds/o2iblnd/o2iblnd.c | 13 +++--
net/lnet/klnds/o2iblnd/o2iblnd_cb.c | 17 ++++---
net/lnet/klnds/socklnd/socklnd.c | 10 ++--
net/lnet/klnds/socklnd/socklnd_cb.c | 10 ++--
net/lnet/lnet/acceptor.c | 3 +-
net/lnet/lnet/api-ni.c | 60 +++++++++++++---------
net/lnet/lnet/config.c | 5 +-
net/lnet/lnet/lib-move.c | 96 +++++++++++++++++++++---------------
net/lnet/lnet/lib-msg.c | 11 +++--
net/lnet/lnet/lib-socket.c | 32 +++++++++---
net/lnet/lnet/lo.c | 3 +-
net/lnet/lnet/net_fault.c | 2 +-
net/lnet/lnet/nidstrings.c | 40 +++++++++++++++
net/lnet/lnet/router.c | 8 +--
net/lnet/lnet/router_proc.c | 2 +-
net/lnet/lnet/udsp.c | 13 ++---
21 files changed, 312 insertions(+), 123 deletions(-)
diff --git a/include/linux/lnet/lib-lnet.h b/include/linux/lnet/lib-lnet.h
index 37489ae..acc069d 100644
--- a/include/linux/lnet/lib-lnet.h
+++ b/include/linux/lnet/lib-lnet.h
@@ -110,7 +110,7 @@
if (ni->ni_status && ni->ni_status->ns_status != status) {
CDEBUG(D_NET, "ni %s status changed from %#x to %#x\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
ni->ni_status->ns_status, status);
ni->ni_status->ns_status = status;
update = true;
@@ -123,7 +123,7 @@
lnet_ni_get_status_locked(struct lnet_ni *ni)
__must_hold(&ni->ni_lock)
{
- if (ni->ni_nid == LNET_NID_LO_0)
+ if (nid_is_lo0(&ni->ni_nid))
return LNET_NI_STATUS_UP;
else if (atomic_read(&ni->ni_fatal_error_on))
return LNET_NI_STATUS_DOWN;
diff --git a/include/linux/lnet/lib-types.h b/include/linux/lnet/lib-types.h
index 85b0d54..80cf4f3 100644
--- a/include/linux/lnet/lib-types.h
+++ b/include/linux/lnet/lib-types.h
@@ -463,7 +463,7 @@ struct lnet_ni {
u32 *ni_cpts;
/* interface's NID */
- lnet_nid_t ni_nid;
+ struct lnet_nid ni_nid;
/* instance-specific data */
void *ni_data;
diff --git a/include/uapi/linux/lnet/lnet-idl.h b/include/uapi/linux/lnet/lnet-idl.h
index 1e27f3b..3fc0df1 100644
--- a/include/uapi/linux/lnet/lnet-idl.h
+++ b/include/uapi/linux/lnet/lnet-idl.h
@@ -40,18 +40,42 @@
* These are sent in sender's byte order (i.e. receiver flips).
*/
-/**
- * Address of an end-point in an LNet network.
+/** Address of an end-point in an LNet network.
*
* A node can have multiple end-points and hence multiple addresses.
* An LNet network can be a simple network (e.g. tcp0) or a network of
* LNet networks connected by LNet routers. Therefore an end-point address
* has two parts: network ID, and address within a network.
+ * The most-significant-byte in this format is always 0. A larger value
+ * would imply a larger nid with a larger address.
*
* \see LNET_NIDNET, LNET_NIDADDR, and LNET_MKNID.
*/
typedef __u64 lnet_nid_t;
+/*
+ * Address of LNet end-point in extended form
+ *
+ * To support addresses larger than 32bits we have
+ * an extended nid which supports up to 128 bits
+ * of address and is extensible.
+ * If nid_size is 0, then the nid can be stored in an lnet_nid_t,
+ * and the first 8 bytes of the 'struct lnet_nid' are identical to
+ * the lnet_nid_t in big-endian format.
+ * If nid_type == 0xff, then all other fields should be ignored
+ * and this is an ANY wildcard address. In particular, the nid_size
+ * can be 0xff without making the address too big to fit.
+ */
+struct lnet_nid {
+ __u8 nid_size; /* total bytes - 8 */
+ __u8 nid_type;
+ __be16 nid_num;
+ __be32 nid_addr[4];
+} __attribute__((packed));
+
+#define NID_BYTES(nid) ((nid)->nid_size + 8)
+#define NID_ADDR_BYTES(nid) ((nid)->nid_size + 4)
+
/**
* ID of a process in a node. Shortened as PID to distinguish from
* lnet_process_id, the global process ID.
diff --git a/include/uapi/linux/lnet/lnet-types.h b/include/uapi/linux/lnet/lnet-types.h
index 0c426ac..ba8a079 100644
--- a/include/uapi/linux/lnet/lnet-types.h
+++ b/include/uapi/linux/lnet/lnet-types.h
@@ -37,6 +37,9 @@
#include <linux/types.h>
#include <linux/lnet/lnet-idl.h>
+#include <linux/string.h>
+#include <asm/byteorder.h>
+
/** \addtogroup lnet
* @{
*/
@@ -57,6 +60,15 @@
/** wildcard PID that matches any lnet_pid_t */
#define LNET_PID_ANY ((lnet_pid_t)(-1))
+static inline int LNET_NID_IS_ANY(const struct lnet_nid *nid)
+{
+ /* A NULL pointer can be used to mean "ANY" */
+ return !nid || nid->nid_type == 0xFF;
+}
+
+#define LNET_ANY_NID ((struct lnet_nid) \
+ {0xFF, 0xFF, ~0, {~0, ~0, ~0, ~0} })
+
#define LNET_PID_RESERVED 0xf0000000 /* reserved bits in PID */
#define LNET_PID_USERFLAG 0x80000000 /* set in userspace peers */
#define LNET_PID_LUSTRE 12345
@@ -86,7 +98,7 @@ static inline __u32 LNET_NETNUM(__u32 net)
static inline __u32 LNET_NETTYP(__u32 net)
{
- return (net >> 16) & 0xffff;
+ return (net >> 16) & 0xff;
}
static inline __u32 LNET_MKNET(__u32 type, __u32 num)
@@ -99,6 +111,58 @@ static inline __u32 LNET_MKNET(__u32 type, __u32 num)
#define LNET_NET_ANY LNET_NIDNET(LNET_NID_ANY)
+static inline int nid_is_nid4(const struct lnet_nid *nid)
+{
+ return NID_ADDR_BYTES(nid) == 4;
+}
+
+/* LOLND may not be defined yet, so we cannot use an inline */
+#define nid_is_lo0(__nid) \
+ ((__nid)->nid_type == LOLND && \
+ nid_is_nid4(__nid) && \
+ (__nid)->nid_num == 0 && \
+ (__nid)->nid_addr[0] == 0)
+
+static inline __u32 LNET_NID_NET(const struct lnet_nid *nid)
+{
+ return LNET_MKNET(nid->nid_type, __be16_to_cpu(nid->nid_num));
+}
+
+static inline void lnet_nid4_to_nid(lnet_nid_t nid4, struct lnet_nid *nid)
+{
+ if (nid4 == LNET_NID_ANY) {
+ /* equal to setting to LNET_ANY_NID */
+ memset(nid, 0xff, sizeof(*nid));
+ return;
+ }
+
+ nid->nid_size = 0;
+ nid->nid_type = LNET_NETTYP(LNET_NIDNET(nid4));
+ nid->nid_num = __cpu_to_be16(LNET_NETNUM(LNET_NIDNET(nid4)));
+ nid->nid_addr[0] = __cpu_to_be32(LNET_NIDADDR(nid4));
+ nid->nid_addr[1] = nid->nid_addr[2] = nid->nid_addr[3] = 0;
+}
+
+static inline lnet_nid_t lnet_nid_to_nid4(const struct lnet_nid *nid)
+{
+ if (LNET_NID_IS_ANY(nid))
+ return LNET_NID_ANY;
+
+ return LNET_MKNID(LNET_NID_NET(nid), __be32_to_cpu(nid->nid_addr[0]));
+}
+
+static inline int nid_same(const struct lnet_nid *n1,
+ const struct lnet_nid *n2)
+{
+ return n1->nid_size == n2->nid_size &&
+ n1->nid_type == n2->nid_type &&
+ n1->nid_num == n2->nid_num &&
+ n1->nid_addr[0] == n2->nid_addr[0] &&
+ n1->nid_addr[1] == n2->nid_addr[1] &&
+ n1->nid_addr[2] == n2->nid_addr[2] &&
+ n1->nid_addr[3] == n2->nid_addr[3];
+}
+
struct lnet_counters_health {
__u32 lch_rst_alloc;
__u32 lch_resend_count;
diff --git a/include/uapi/linux/lnet/nidstr.h b/include/uapi/linux/lnet/nidstr.h
index caf28e2..d5b9d69 100644
--- a/include/uapi/linux/lnet/nidstr.h
+++ b/include/uapi/linux/lnet/nidstr.h
@@ -62,7 +62,7 @@ enum {
struct list_head;
#define LNET_NIDSTR_COUNT 1024 /* # of nidstrings */
-#define LNET_NIDSTR_SIZE 32 /* size of each one (see below for usage) */
+#define LNET_NIDSTR_SIZE 64 /* size of each one (see below for usage) */
/* support decl needed by both kernel and user space */
char *libcfs_next_nidstring(void);
@@ -90,6 +90,14 @@ static inline char *libcfs_nid2str(lnet_nid_t nid)
LNET_NIDSTR_SIZE);
}
+char *libcfs_nidstr_r(const struct lnet_nid *nid,
+ char *buf, __kernel_size_t buf_size);
+static inline char *libcfs_nidstr(const struct lnet_nid *nid)
+{
+ return libcfs_nidstr_r(nid, libcfs_next_nidstring(),
+ LNET_NIDSTR_SIZE);
+}
+
__u32 libcfs_str2net(const char *str);
lnet_nid_t libcfs_str2nid(const char *str);
int libcfs_str2anynid(lnet_nid_t *nid, const char *str);
diff --git a/net/lnet/klnds/o2iblnd/o2iblnd.c b/net/lnet/klnds/o2iblnd/o2iblnd.c
index a4949d8..fd807c2 100644
--- a/net/lnet/klnds/o2iblnd/o2iblnd.c
+++ b/net/lnet/klnds/o2iblnd/o2iblnd.c
@@ -178,8 +178,7 @@ void kiblnd_pack_msg(struct lnet_ni *ni, struct kib_msg *msg, int version,
{
struct kib_net *net = ni->ni_data;
- /*
- * CAVEAT EMPTOR! all message fields not set here should have been
+ /* CAVEAT EMPTOR! all message fields not set here should have been
* initialised previously.
*/
msg->ibm_magic = IBLND_MSG_MAGIC;
@@ -188,7 +187,7 @@ void kiblnd_pack_msg(struct lnet_ni *ni, struct kib_msg *msg, int version,
msg->ibm_credits = credits;
/* ibm_nob */
msg->ibm_cksum = 0;
- msg->ibm_srcnid = ni->ni_nid;
+ msg->ibm_srcnid = lnet_nid_to_nid4(&ni->ni_nid);
msg->ibm_srcstamp = net->ibn_incarnation;
msg->ibm_dstnid = dstnid;
msg->ibm_dststamp = dststamp;
@@ -397,7 +396,7 @@ struct kib_peer_ni *kiblnd_find_peer_locked(struct lnet_ni *ni, lnet_nid_t nid)
* created.
*/
if (peer_ni->ibp_nid != nid ||
- peer_ni->ibp_ni->ni_nid != ni->ni_nid)
+ !nid_same(&peer_ni->ibp_ni->ni_nid, &ni->ni_nid))
continue;
CDEBUG(D_NET, "got peer_ni [%p] -> %s (%d) version: %x\n",
@@ -2201,7 +2200,7 @@ static int kiblnd_port_get_attr(struct kib_hca_dev *hdev)
list_for_each_entry(net, &hdev->ibh_dev->ibd_nets, ibn_list) {
if (val)
CDEBUG(D_NETERROR, "Fatal device error for NI %s\n",
- libcfs_nid2str(net->ibn_ni->ni_nid));
+ libcfs_nidstr(&net->ibn_ni->ni_nid));
atomic_set(&net->ibn_ni->ni_fatal_error_on, val);
}
}
@@ -2591,7 +2590,7 @@ static void kiblnd_shutdown(struct lnet_ni *ni)
wait_var_event_warning(&net->ibn_npeers,
atomic_read(&net->ibn_npeers) == 0,
"%s: waiting for %d peers to disconnect\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
atomic_read(&net->ibn_npeers));
kiblnd_net_fini_pools(net);
@@ -2906,7 +2905,7 @@ static int kiblnd_startup(struct lnet_ni *ni)
}
net->ibn_dev = ibdev;
- ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid), ibdev->ibd_ifip);
+ ni->ni_nid.nid_addr[0] = cpu_to_be32(ibdev->ibd_ifip);
ni->ni_dev_cpt = ifaces[i].li_cpt;
diff --git a/net/lnet/klnds/o2iblnd/o2iblnd_cb.c b/net/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 8ccd2ab..380374e 100644
--- a/net/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/net/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -507,7 +507,7 @@ static int kiblnd_init_rdma(struct kib_conn *conn, struct kib_tx *tx, int type,
}
if (msg->ibm_srcnid != conn->ibc_peer->ibp_nid ||
- msg->ibm_dstnid != ni->ni_nid ||
+ msg->ibm_dstnid != lnet_nid_to_nid4(&ni->ni_nid) ||
msg->ibm_srcstamp != conn->ibc_incarnation ||
msg->ibm_dststamp != net->ibn_incarnation) {
CERROR("Stale rx from %s\n",
@@ -2369,11 +2369,12 @@ static int kiblnd_map_tx(struct lnet_ni *ni, struct kib_tx *tx,
}
if (!ni || /* no matching net */
- ni->ni_nid != reqmsg->ibm_dstnid || /* right NET, wrong NID! */
+ lnet_nid_to_nid4(&ni->ni_nid) !=
+ reqmsg->ibm_dstnid || /* right NET, wrong NID! */
net->ibn_dev != ibdev) { /* wrong device */
CERROR("Can't accept conn from %s on %s (%s:%d:%pI4h): bad dst nid %s\n",
libcfs_nid2str(nid),
- !ni ? "NA" : libcfs_nid2str(ni->ni_nid),
+ ni ? libcfs_nidstr(&ni->ni_nid) : "NA",
ibdev->ibd_ifname, ibdev->ibd_nnets,
&ibdev->ibd_ifip,
libcfs_nid2str(reqmsg->ibm_dstnid));
@@ -2490,8 +2491,8 @@ static int kiblnd_map_tx(struct lnet_ni *ni, struct kib_tx *tx,
* the lower NID connection win so we can move forward.
*/
if (peer2->ibp_connecting &&
- nid < ni->ni_nid && peer2->ibp_races <
- MAX_CONN_RACES_BEFORE_ABORT) {
+ nid < lnet_nid_to_nid4(&ni->ni_nid) &&
+ peer2->ibp_races < MAX_CONN_RACES_BEFORE_ABORT) {
peer2->ibp_races++;
write_unlock_irqrestore(g_lock, flags);
@@ -2924,7 +2925,7 @@ static int kiblnd_map_tx(struct lnet_ni *ni, struct kib_tx *tx,
}
read_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
- if (msg->ibm_dstnid == ni->ni_nid &&
+ if (msg->ibm_dstnid == lnet_nid_to_nid4(&ni->ni_nid) &&
msg->ibm_dststamp == net->ibn_incarnation)
rc = 0;
else
@@ -3568,13 +3569,13 @@ static int kiblnd_map_tx(struct lnet_ni *ni, struct kib_tx *tx,
case IB_EVENT_PORT_ERR:
case IB_EVENT_DEVICE_FATAL:
CERROR("Fatal device error for NI %s\n",
- libcfs_nid2str(conn->ibc_peer->ibp_ni->ni_nid));
+ libcfs_nidstr(&conn->ibc_peer->ibp_ni->ni_nid));
atomic_set(&conn->ibc_peer->ibp_ni->ni_fatal_error_on, 1);
return;
case IB_EVENT_PORT_ACTIVE:
CERROR("Port reactivated for NI %s\n",
- libcfs_nid2str(conn->ibc_peer->ibp_ni->ni_nid));
+ libcfs_nidstr(&conn->ibc_peer->ibp_ni->ni_nid));
atomic_set(&conn->ibc_peer->ibp_ni->ni_fatal_error_on, 0);
return;
diff --git a/net/lnet/klnds/socklnd/socklnd.c b/net/lnet/klnds/socklnd/socklnd.c
index 96cb0e0..21569fb 100644
--- a/net/lnet/klnds/socklnd/socklnd.c
+++ b/net/lnet/klnds/socklnd/socklnd.c
@@ -949,7 +949,7 @@ struct ksock_peer_ni *
* Am I already connecting to this guy? Resolve in
* favour of higher NID...
*/
- if (peerid.nid < ni->ni_nid &&
+ if (peerid.nid < lnet_nid_to_nid4(&ni->ni_nid) &&
ksocknal_connecting(peer_ni->ksnp_conn_cb,
((struct sockaddr *)&conn->ksnc_peeraddr))) {
rc = EALREADY;
@@ -1820,12 +1820,13 @@ static int ksocknal_push(struct lnet_ni *ni, struct lnet_process_id id)
case IOC_LIBCFS_REGISTER_MYNID:
/* Ignore if this is a noop */
- if (data->ioc_nid == ni->ni_nid)
+ if (nid_is_nid4(&ni->ni_nid) &&
+ data->ioc_nid == lnet_nid_to_nid4(&ni->ni_nid))
return 0;
CERROR("obsolete IOC_LIBCFS_REGISTER_MYNID: %s(%s)\n",
libcfs_nid2str(data->ioc_nid),
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
return -EINVAL;
case IOC_LIBCFS_PUSH_CONNECTION:
@@ -2369,8 +2370,7 @@ static int ksocknal_device_event(struct notifier_block *unused,
LASSERT(ksi);
LASSERT(ksi->ksni_addr.ss_family == AF_INET);
- ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid),
- ntohl(((struct sockaddr_in *)&ksi->ksni_addr)->sin_addr.s_addr));
+ ni->ni_nid.nid_addr[0] = ((struct sockaddr_in *)&ksi->ksni_addr)->sin_addr.s_addr;
list_add(&net->ksnn_list, &ksocknal_data.ksnd_nets);
net->ksnn_ni = ni;
ksocknal_data.ksnd_nnets++;
diff --git a/net/lnet/klnds/socklnd/socklnd_cb.c b/net/lnet/klnds/socklnd/socklnd_cb.c
index efec479..e6cd976 100644
--- a/net/lnet/klnds/socklnd/socklnd_cb.c
+++ b/net/lnet/klnds/socklnd/socklnd_cb.c
@@ -1579,7 +1579,7 @@ void ksocknal_write_callback(struct ksock_conn *conn)
/* rely on caller to hold a ref on socket so it wouldn't disappear */
LASSERT(conn->ksnc_proto);
- hello->kshm_src_nid = ni->ni_nid;
+ hello->kshm_src_nid = lnet_nid_to_nid4(&ni->ni_nid);
hello->kshm_dst_nid = peer_nid;
hello->kshm_src_pid = the_lnet.ln_pid;
@@ -1628,7 +1628,7 @@ void ksocknal_write_callback(struct ksock_conn *conn)
LASSERT(!active == !(conn->ksnc_type != SOCKLND_CONN_NONE));
timeout = active ? ksocknal_timeout() :
- lnet_acceptor_timeout();
+ lnet_acceptor_timeout();
rc = lnet_sock_read(sock, &hello->kshm_magic,
sizeof(hello->kshm_magic), timeout);
@@ -1672,7 +1672,9 @@ void ksocknal_write_callback(struct ksock_conn *conn)
conn->ksnc_proto = &ksocknal_protocol_v1x;
#endif
hello->kshm_nips = 0;
- ksocknal_send_hello(ni, conn, ni->ni_nid, hello);
+ ksocknal_send_hello(ni, conn,
+ lnet_nid_to_nid4(&ni->ni_nid),
+ hello);
}
CERROR("Unknown protocol version (%d.x expected) from %pIS\n",
@@ -1709,7 +1711,7 @@ void ksocknal_write_callback(struct ksock_conn *conn)
recv_id.pid = rpc_get_port((struct sockaddr *)
&conn->ksnc_peeraddr) |
LNET_PID_USERFLAG;
- recv_id.nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid),
+ recv_id.nid = LNET_MKNID(LNET_NID_NET(&ni->ni_nid),
ntohl(((struct sockaddr_in *)
&conn->ksnc_peeraddr)->sin_addr.s_addr));
} else {
diff --git a/net/lnet/lnet/acceptor.c b/net/lnet/lnet/acceptor.c
index 3708b89..243c34f 100644
--- a/net/lnet/lnet/acceptor.c
+++ b/net/lnet/lnet/acceptor.c
@@ -284,7 +284,8 @@ struct socket *
ni = lnet_nid2ni_addref(cr.acr_nid);
if (!ni || /* no matching net */
- ni->ni_nid != cr.acr_nid) { /* right NET, wrong NID! */
+ lnet_nid_to_nid4(&ni->ni_nid) != cr.acr_nid) {
+ /* right NET, wrong NID! */
if (ni)
lnet_ni_decref(ni);
LCONSOLE_ERROR_MSG(0x120,
diff --git a/net/lnet/lnet/api-ni.c b/net/lnet/lnet/api-ni.c
index 41d2d26..9471edb 100644
--- a/net/lnet/lnet/api-ni.c
+++ b/net/lnet/lnet/api-ni.c
@@ -667,6 +667,17 @@ static void lnet_assert_wire_constants(void)
BUILD_BUG_ON((int)sizeof(lnet_nid_t) != 8);
BUILD_BUG_ON((int)sizeof(lnet_pid_t) != 4);
+ /* Checks for struct lnet_nid */
+ BUILD_BUG_ON((int)sizeof(struct lnet_nid) != 20);
+ BUILD_BUG_ON((int)offsetof(struct lnet_nid, nid_size) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_nid *)0)->nid_size) != 1);
+ BUILD_BUG_ON((int)offsetof(struct lnet_nid, nid_type) != 1);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_nid *)0)->nid_type) != 1);
+ BUILD_BUG_ON((int)offsetof(struct lnet_nid, nid_num) != 2);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_nid *)0)->nid_num) != 2);
+ BUILD_BUG_ON((int)offsetof(struct lnet_nid, nid_addr) != 4);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_nid *)0)->nid_addr) != 16);
+
/* Checks for struct lnet_process_id_packed */
BUILD_BUG_ON((int)sizeof(struct lnet_process_id_packed) != 12);
BUILD_BUG_ON((int)offsetof(struct lnet_process_id_packed, nid) != 0);
@@ -1518,16 +1529,18 @@ struct lnet_net *
}
struct lnet_ni *
-lnet_nid2ni_locked(lnet_nid_t nid, int cpt)
+lnet_nid2ni_locked(lnet_nid_t nid4, int cpt)
{
struct lnet_net *net;
struct lnet_ni *ni;
+ struct lnet_nid nid;
LASSERT(cpt != LNET_LOCK_EX);
+ lnet_nid4_to_nid(nid4, &nid);
list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
- if (ni->ni_nid == nid)
+ if (nid_same(&ni->ni_nid, &nid))
return ni;
}
}
@@ -1826,7 +1839,9 @@ struct lnet_ping_buffer *
ns = &pbuf->pb_info.pi_ni[i];
- ns->ns_nid = ni->ni_nid;
+ if (!nid_is_nid4(&ni->ni_nid))
+ continue;
+ ns->ns_nid = lnet_nid_to_nid4(&ni->ni_nid);
lnet_ni_lock(ni);
ns->ns_status = lnet_ni_get_status_locked(ni);
@@ -2142,7 +2157,7 @@ static void lnet_push_target_fini(void)
++i;
if ((i & (-i)) == i) {
CDEBUG(D_WARNING, "Waiting for zombie LNI %s\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
}
schedule_timeout_uninterruptible(HZ);
@@ -2167,7 +2182,7 @@ static void lnet_push_target_fini(void)
if (!islo)
CDEBUG(D_LNI, "Removed LNI %s\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
lnet_ni_free(ni);
i = 2;
@@ -2283,7 +2298,6 @@ static void lnet_push_target_fini(void)
struct lnet_tx_queue *tq;
int i;
struct lnet_net *net = ni->ni_net;
- u32 seed;
mutex_lock(&the_lnet.ln_lnd_mutex);
@@ -2339,18 +2353,12 @@ static void lnet_push_target_fini(void)
tq->tq_credits = lnet_ni_tq_credits(ni);
}
- /* Nodes with small feet have little entropy. The NID for this
- * node gives the most entropy in the low bits.
- */
- seed = LNET_NIDADDR(ni->ni_nid);
- add_device_randomness(&seed, sizeof(seed));
-
atomic_set(&ni->ni_tx_credits,
lnet_ni_tq_credits(ni) * ni->ni_ncpts);
atomic_set(&ni->ni_healthv, LNET_MAX_HEALTH_VALUE);
CDEBUG(D_LNI, "Added LNI %s [%d/%d/%d/%d]\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
ni->ni_net->net_tunables.lct_peer_tx_credits,
lnet_ni_tq_credits(ni) * LNET_CPT_NUMBER,
ni->ni_net->net_tunables.lct_peer_rtr_credits,
@@ -2924,7 +2932,7 @@ void lnet_lib_exit(void)
size_t min_size = 0;
int i;
- if (!ni || !cfg_ni || !tun)
+ if (!ni || !cfg_ni || !tun || !nid_is_nid4(&ni->ni_nid))
return;
if (ni->ni_interface) {
@@ -2933,7 +2941,7 @@ void lnet_lib_exit(void)
sizeof(cfg_ni->lic_ni_intf));
}
- cfg_ni->lic_nid = ni->ni_nid;
+ cfg_ni->lic_nid = lnet_nid_to_nid4(&ni->ni_nid);
cfg_ni->lic_status = lnet_ni_get_status_locked(ni);
cfg_ni->lic_dev_cpt = ni->ni_dev_cpt;
@@ -2993,7 +3001,7 @@ void lnet_lib_exit(void)
size_t min_size, tunable_size = 0;
int i;
- if (!ni || !config)
+ if (!ni || !config || !nid_is_nid4(&ni->ni_nid))
return;
net_config = (struct lnet_ioctl_net_config *)config->cfg_bulk;
@@ -3007,7 +3015,7 @@ void lnet_lib_exit(void)
ni->ni_interface,
sizeof(net_config->ni_interface));
- config->cfg_nid = ni->ni_nid;
+ config->cfg_nid = lnet_nid_to_nid4(&ni->ni_nid);
config->cfg_config_u.cfg_net.net_peer_timeout =
ni->ni_net->net_tunables.lct_peer_timeout;
config->cfg_config_u.cfg_net.net_max_tx_credits =
@@ -3287,7 +3295,7 @@ static int lnet_add_net_common(struct lnet_net *net,
rc = lnet_udsp_apply_policies_on_ni(ni);
if (rc)
CERROR("Failed to apply UDSPs on ni %s\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
}
lnet_net_unlock(LNET_LOCK_EX);
@@ -3637,12 +3645,13 @@ u32 lnet_get_dlc_seq_locked(void)
lnet_net_lock(LNET_LOCK_EX);
list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
- if (ni->ni_nid == nid || all) {
+ if (all || (nid_is_nid4(&ni->ni_nid) &&
+ lnet_nid_to_nid4(&ni->ni_nid) == nid)) {
atomic_set(&ni->ni_healthv, value);
if (list_empty(&ni->ni_recovery) &&
value < LNET_MAX_HEALTH_VALUE) {
CERROR("manually adding local NI %s to recovery\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
list_add_tail(&ni->ni_recovery,
&the_lnet.ln_mt_localNIRecovq);
lnet_ni_addref_locked(ni, 0);
@@ -3666,7 +3675,7 @@ u32 lnet_get_dlc_seq_locked(void)
lnet_net_lock(LNET_LOCK_EX);
list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
- if (ni->ni_nid != nid && !all)
+ if (lnet_nid_to_nid4(&ni->ni_nid) != nid && !all)
continue;
if (LNET_NETTYP(net->net_id) == SOCKLND)
ni->ni_lnd_tunables.lnd_tun_u.lnd_sock.lnd_conns_per_peer = value;
@@ -3729,7 +3738,9 @@ u32 lnet_get_dlc_seq_locked(void)
lnet_net_lock(LNET_LOCK_EX);
list_for_each_entry(ni, &the_lnet.ln_mt_localNIRecovq, ni_recovery) {
- list->rlst_nid_array[i] = ni->ni_nid;
+ if (!nid_is_nid4(&ni->ni_nid))
+ continue;
+ list->rlst_nid_array[i] = lnet_nid_to_nid4(&ni->ni_nid);
i++;
if (i >= LNET_MAX_SHOW_NUM_NID)
break;
@@ -4381,10 +4392,13 @@ void LNetDebugPeer(struct lnet_process_id id)
list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
+ if (!nid_is_nid4(&ni->ni_nid))
+ /* FIXME this needs to be handled */
+ continue;
if (index-- != 0)
continue;
- id->nid = ni->ni_nid;
+ id->nid = lnet_nid_to_nid4(&ni->ni_nid);
id->pid = the_lnet.ln_pid;
rc = 0;
break;
diff --git a/net/lnet/lnet/config.c b/net/lnet/lnet/config.c
index 0117611..0c833fe 100644
--- a/net/lnet/lnet/config.c
+++ b/net/lnet/lnet/config.c
@@ -375,7 +375,7 @@ struct lnet_net *
if (ni->ni_interface) {
LCONSOLE_ERROR_MSG(0x115, "%s: interface %s already set for net %s: rc = %d\n",
iface, ni->ni_interface,
- libcfs_net2str(LNET_NIDNET(ni->ni_nid)),
+ libcfs_net2str(LNET_NID_NET(&ni->ni_nid)),
-EINVAL);
return -EINVAL;
}
@@ -435,7 +435,8 @@ struct lnet_net *
ni->ni_net = net;
/* LND will fill in the address part of the NID */
- ni->ni_nid = LNET_MKNID(net->net_id, 0);
+ ni->ni_nid.nid_type = LNET_NETTYP(net->net_id);
+ ni->ni_nid.nid_num = cpu_to_be16(LNET_NETNUM(net->net_id));
/* Store net namespace in which current ni is being created */
if (current->nsproxy && current->nsproxy->net_ns)
diff --git a/net/lnet/lnet/lib-move.c b/net/lnet/lnet/lib-move.c
index 035bda3..c70ec37 100644
--- a/net/lnet/lnet/lib-move.c
+++ b/net/lnet/lnet/lib-move.c
@@ -537,7 +537,7 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
int rc;
LASSERT(!in_interrupt());
- LASSERT(ni->ni_nid == LNET_NID_LO_0 ||
+ LASSERT(nid_is_lo0(&ni->ni_nid) ||
(msg->msg_txcredit && msg->msg_peertxcredit));
rc = ni->ni_net->net_lnd->lnd_send(ni, priv, msg);
@@ -648,7 +648,8 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
/* can't get here if we're sending to the loopback interface */
if (the_lnet.ln_loni)
- LASSERT(lp->lpni_nid != the_lnet.ln_loni->ni_nid);
+ LASSERT(lp->lpni_nid !=
+ lnet_nid_to_nid4(&the_lnet.ln_loni->ni_nid));
/* NB 'lp' is always the next hop */
if (!(msg->msg_target.pid & LNET_PID_USERFLAG) &&
@@ -1133,10 +1134,11 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
* preferred, then let's use it
*/
if (best_ni) {
+ /* FIXME need to handle large-addr nid */
lpni_is_preferred = lnet_peer_is_pref_nid_locked(lpni,
- best_ni->ni_nid);
+ lnet_nid_to_nid4(&best_ni->ni_nid));
CDEBUG(D_NET, "%s lpni_is_preferred = %d\n",
- libcfs_nid2str(best_ni->ni_nid),
+ libcfs_nidstr(&best_ni->ni_nid),
lpni_is_preferred);
} else {
lpni_is_preferred = false;
@@ -1514,9 +1516,9 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
if (best_ni)
CDEBUG(D_NET,
"compare ni %s [c:%d, d:%d, s:%d, p:%u, g:%u] with best_ni %s [c:%d, d:%d, s:%d, p:%u, g:%u]\n",
- libcfs_nid2str(ni->ni_nid), ni_credits, distance,
+ libcfs_nidstr(&ni->ni_nid), ni_credits, distance,
ni->ni_seq, ni_sel_prio, ni_dev_prio,
- (best_ni) ? libcfs_nid2str(best_ni->ni_nid)
+ (best_ni) ? libcfs_nidstr(&best_ni->ni_nid)
: "not selected", best_credits, shortest_distance,
(best_ni) ? best_ni->ni_seq : 0,
best_sel_prio, best_dev_prio);
@@ -1561,7 +1563,7 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
}
CDEBUG(D_NET, "selected best_ni %s\n",
- (best_ni) ? libcfs_nid2str(best_ni->ni_nid) : "no selection");
+ (best_ni) ? libcfs_nidstr(&best_ni->ni_nid) : "no selection");
return best_ni;
}
@@ -1620,11 +1622,12 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
/* No send credit hassles with LOLND */
lnet_ni_addref_locked(the_lnet.ln_loni, cpt);
- msg->msg_hdr.dest_nid = cpu_to_le64(the_lnet.ln_loni->ni_nid);
+ msg->msg_hdr.dest_nid =
+ cpu_to_le64(lnet_nid_to_nid4(&the_lnet.ln_loni->ni_nid));
if (!msg->msg_routing)
msg->msg_hdr.src_nid =
- cpu_to_le64(the_lnet.ln_loni->ni_nid);
- msg->msg_target.nid = the_lnet.ln_loni->ni_nid;
+ cpu_to_le64(lnet_nid_to_nid4(&the_lnet.ln_loni->ni_nid));
+ msg->msg_target.nid = lnet_nid_to_nid4(&the_lnet.ln_loni->ni_nid);
lnet_msg_commit(msg, cpt);
msg->msg_txni = the_lnet.ln_loni;
@@ -1655,7 +1658,7 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
CDEBUG(D_NET,
"%s NI seq info: [%d:%d:%d:%u] %s LPNI seq info [%d:%d:%d:%u]\n",
- libcfs_nid2str(best_ni->ni_nid),
+ libcfs_nidstr(&best_ni->ni_nid),
best_ni->ni_seq, best_ni->ni_net->net_seq,
atomic_read(&best_ni->ni_tx_credits),
best_ni->ni_sel_priority,
@@ -1719,7 +1722,8 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
* originator and set it here.
*/
if (!msg->msg_routing)
- msg->msg_hdr.src_nid = cpu_to_le64(msg->msg_txni->ni_nid);
+ msg->msg_hdr.src_nid =
+ cpu_to_le64(lnet_nid_to_nid4(&msg->msg_txni->ni_nid));
if (routing) {
msg->msg_target_is_router = 1;
@@ -1757,7 +1761,7 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
if (!rc)
CDEBUG(D_NET, "TRACE: %s(%s:%s) -> %s(%s:%s) %s : %s try# %d\n",
libcfs_nid2str(msg->msg_hdr.src_nid),
- libcfs_nid2str(msg->msg_txni->ni_nid),
+ libcfs_nidstr(&msg->msg_txni->ni_nid),
libcfs_nid2str(sd->sd_src_nid),
libcfs_nid2str(msg->msg_hdr.dest_nid),
libcfs_nid2str(sd->sd_dst_nid),
@@ -1775,9 +1779,10 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
if (!lnet_peer_is_multi_rail(lpni->lpni_peer_net->lpn_peer) &&
!lnet_msg_is_response(msg) && lpni->lpni_pref_nnids == 0) {
CDEBUG(D_NET, "Setting preferred local NID %s on NMR peer %s\n",
- libcfs_nid2str(lni->ni_nid),
+ libcfs_nidstr(&lni->ni_nid),
libcfs_nid2str(lpni->lpni_nid));
- lnet_peer_ni_set_non_mr_pref_nid(lpni, lni->ni_nid);
+ lnet_peer_ni_set_non_mr_pref_nid(lpni,
+ lnet_nid_to_nid4(&lni->ni_nid));
}
}
@@ -1828,7 +1833,8 @@ void lnet_usr_translate_stats(struct lnet_ioctl_element_msg_stats *msg_stats,
}
if (sd->sd_best_lpni &&
- sd->sd_best_lpni->lpni_nid == the_lnet.ln_loni->ni_nid)
+ sd->sd_best_lpni->lpni_nid ==
+ lnet_nid_to_nid4(&the_lnet.ln_loni->ni_nid))
return lnet_handle_lo_send(sd);
else if (sd->sd_best_lpni)
return lnet_handle_send(sd);
@@ -1951,7 +1957,7 @@ struct lnet_ni *
struct lnet_peer_ni *gwni = NULL;
bool route_found = false;
lnet_nid_t src_nid = (sd->sd_src_nid != LNET_NID_ANY) ? sd->sd_src_nid :
- sd->sd_best_ni ? sd->sd_best_ni->ni_nid :
+ sd->sd_best_ni ? lnet_nid_to_nid4(&sd->sd_best_ni->ni_nid) :
LNET_NID_ANY;
int best_lpn_healthv = 0;
u32 best_lpn_sel_prio = LNET_MAX_SELECTION_PRIORITY;
@@ -2454,7 +2460,8 @@ struct lnet_ni *
* network
*/
if (sd->sd_best_lpni &&
- sd->sd_best_lpni->lpni_nid == the_lnet.ln_loni->ni_nid) {
+ sd->sd_best_lpni->lpni_nid ==
+ lnet_nid_to_nid4(&the_lnet.ln_loni->ni_nid)) {
/* in case we initially started with a routed
* destination, let's reset to local
*/
@@ -3195,7 +3202,7 @@ struct lnet_mt_event_info {
lnet_net_unlock(0);
CDEBUG(D_NET, "attempting to recover local ni: %s\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
lnet_ni_lock(ni);
if (!(ni->ni_recovery_state & LNET_NI_RECOVERY_PENDING)) {
@@ -3205,7 +3212,7 @@ struct lnet_mt_event_info {
ev_info = kzalloc(sizeof(*ev_info), GFP_NOFS);
if (!ev_info) {
CERROR("out of memory. Can't recover %s\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
lnet_ni_lock(ni);
ni->ni_recovery_state &=
~LNET_NI_RECOVERY_PENDING;
@@ -3218,7 +3225,8 @@ struct lnet_mt_event_info {
* We'll unlink the mdh in this case below.
*/
LNetInvalidateMDHandle(&ni->ni_ping_mdh);
- nid = ni->ni_nid;
+ /* FIXME need to handle large-addr nid */
+ nid = lnet_nid_to_nid4(&ni->ni_nid);
/* remove the NI from the local queue and drop the
* reference count to it while we're recovering
@@ -3986,11 +3994,12 @@ void lnet_monitor_thr_stop(void)
lnet_ni_recv(ni, msg->msg_private, NULL, 0, 0, 0, 0);
msg->msg_receiving = 0;
- rc = lnet_send(ni->ni_nid, msg, msg->msg_from);
+ /* FIXME need to handle large-addr nid */
+ rc = lnet_send(lnet_nid_to_nid4(&ni->ni_nid), msg, msg->msg_from);
if (rc < 0) {
/* didn't get as far as lnet_ni_send() */
CERROR("%s: Unable to send REPLY for GET from %s: %d\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
libcfs_id2str(info.mi_id), rc);
lnet_finalize(msg, rc);
@@ -4020,7 +4029,7 @@ void lnet_monitor_thr_stop(void)
md = lnet_wire_handle2md(&hdr->msg.reply.dst_wmd);
if (!md || !md->md_threshold || md->md_me) {
CNETERR("%s: Dropping REPLY from %s for %s MD %#llx.%#llx\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(src),
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(src),
!md ? "invalid" : "inactive",
hdr->msg.reply.dst_wmd.wh_interface_cookie,
hdr->msg.reply.dst_wmd.wh_object_cookie);
@@ -4040,7 +4049,7 @@ void lnet_monitor_thr_stop(void)
if (mlength < rlength &&
!(md->md_options & LNET_MD_TRUNCATE)) {
CNETERR("%s: Dropping REPLY from %s length %d for MD %#llx would overflow (%d)\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(src),
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(src),
rlength, hdr->msg.reply.dst_wmd.wh_object_cookie,
mlength);
lnet_res_unlock(cpt);
@@ -4048,7 +4057,7 @@ void lnet_monitor_thr_stop(void)
}
CDEBUG(D_NET, "%s: Reply from %s of length %d/%d into md %#llx\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(src),
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(src),
mlength, rlength, hdr->msg.reply.dst_wmd.wh_object_cookie);
lnet_msg_attach_md(msg, md, 0, mlength);
@@ -4088,7 +4097,7 @@ void lnet_monitor_thr_stop(void)
/* Don't moan; this is expected */
CDEBUG(D_NET,
"%s: Dropping ACK from %s to %s MD %#llx.%#llx\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(src),
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(src),
!md ? "invalid" : "inactive",
hdr->msg.ack.dst_wmd.wh_interface_cookie,
hdr->msg.ack.dst_wmd.wh_object_cookie);
@@ -4101,7 +4110,7 @@ void lnet_monitor_thr_stop(void)
}
CDEBUG(D_NET, "%s: ACK from %s into md %#llx\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(src),
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(src),
hdr->msg.ack.dst_wmd.wh_object_cookie);
lnet_msg_attach_md(msg, md, 0, 0);
@@ -4213,12 +4222,13 @@ void lnet_monitor_thr_stop(void)
dest_pid = le32_to_cpu(hdr->dest_pid);
payload_length = le32_to_cpu(hdr->payload_length);
- for_me = (ni->ni_nid == dest_nid);
+ /* FIXME handle large-addr nids */
+ for_me = (lnet_nid_to_nid4(&ni->ni_nid) == dest_nid);
cpt = lnet_cpt_of_nid(from_nid, ni);
CDEBUG(D_NET, "TRACE: %s(%s) <- %s : %s\n",
libcfs_nid2str(dest_nid),
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
libcfs_nid2str(src_nid),
lnet_msgtyp2str(type));
@@ -4274,7 +4284,7 @@ void lnet_monitor_thr_stop(void)
* or malicious so we chop them off at the knees :)
*/
if (!for_me) {
- if (LNET_NIDNET(dest_nid) == LNET_NIDNET(ni->ni_nid)) {
+ if (LNET_NIDNET(dest_nid) == LNET_NID_NET(&ni->ni_nid)) {
/* should have gone direct */
CERROR("%s, src %s: Bad dest nid %s (should have been sent direct)\n",
libcfs_nid2str(from_nid),
@@ -4324,8 +4334,9 @@ void lnet_monitor_thr_stop(void)
goto drop;
}
+ /* FIXME need to support large-addr nid */
if (!list_empty(&the_lnet.ln_drop_rules) &&
- lnet_drop_rule_match(hdr, ni->ni_nid, NULL)) {
+ lnet_drop_rule_match(hdr, lnet_nid_to_nid4(&ni->ni_nid), NULL)) {
CDEBUG(D_NET, "%s, src %s, dst %s: Dropping %s to simulate silent message loss\n",
libcfs_nid2str(from_nid), libcfs_nid2str(src_nid),
libcfs_nid2str(dest_nid), lnet_msgtyp2str(type));
@@ -4368,7 +4379,9 @@ void lnet_monitor_thr_stop(void)
}
lnet_net_lock(cpt);
- lpni = lnet_nid2peerni_locked(from_nid, ni->ni_nid, cpt);
+ /* FIXME support large-addr nid */
+ lpni = lnet_nid2peerni_locked(from_nid, lnet_nid_to_nid4(&ni->ni_nid),
+ cpt);
if (IS_ERR(lpni)) {
lnet_net_unlock(cpt);
CERROR("%s, src %s: Dropping %s (error %ld looking up sender)\n",
@@ -4790,7 +4803,7 @@ struct lnet_msg *
msg = kmem_cache_zalloc(lnet_msg_cachep, GFP_NOFS);
if (!msg) {
CERROR("%s: Dropping REPLY from %s: can't allocate msg\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(peer_id));
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(peer_id));
goto drop;
}
@@ -4801,7 +4814,7 @@ struct lnet_msg *
if (!getmd->md_threshold) {
CERROR("%s: Dropping REPLY from %s for inactive MD %p\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(peer_id),
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(peer_id),
getmd);
lnet_res_unlock(cpt);
goto drop;
@@ -4810,7 +4823,7 @@ struct lnet_msg *
LASSERT(!getmd->md_offset);
CDEBUG(D_NET, "%s: Reply from %s md %p\n",
- libcfs_nid2str(ni->ni_nid), libcfs_id2str(peer_id), getmd);
+ libcfs_nidstr(&ni->ni_nid), libcfs_id2str(peer_id), getmd);
/* setup information for lnet_build_msg_event */
msg->msg_initiator = getmsg->msg_txpeer->lpni_peer_net->lpn_peer->lp_primary_nid;
@@ -5032,7 +5045,8 @@ struct lnet_msg *
cpt = lnet_net_lock_current();
while ((ni = lnet_get_next_ni_locked(NULL, ni))) {
- if (ni->ni_nid == dstnid) {
+ /* FIXME support large-addr nid */
+ if (lnet_nid_to_nid4(&ni->ni_nid) == dstnid) {
if (srcnidp)
*srcnidp = dstnid;
if (orderp) {
@@ -5046,7 +5060,7 @@ struct lnet_msg *
return local_nid_dist_zero ? 0 : 1;
}
- if (!matched_dstnet && LNET_NIDNET(ni->ni_nid) == dstnet) {
+ if (!matched_dstnet && LNET_NID_NET(&ni->ni_nid) == dstnet) {
matched_dstnet = true;
/* We matched the destination net, but we may have
* additional local NIs to inspect.
@@ -5055,7 +5069,8 @@ struct lnet_msg *
* they may be overwritten if we match local NI above.
*/
if (srcnidp)
- *srcnidp = ni->ni_nid;
+ /* FIXME support large-addr nids */
+ *srcnidp = lnet_nid_to_nid4(&ni->ni_nid);
if (orderp) {
/* Check if ni was originally created in
@@ -5110,7 +5125,8 @@ struct lnet_msg *
net = lnet_get_net_locked(shortest->lr_lnet);
LASSERT(net);
ni = lnet_get_next_ni_locked(net, NULL);
- *srcnidp = ni->ni_nid;
+ /* FIXME support large-addr nids */
+ *srcnidp = lnet_nid_to_nid4(&ni->ni_nid);
}
if (orderp)
*orderp = order;
diff --git a/net/lnet/lnet/lib-msg.c b/net/lnet/lnet/lib-msg.c
index e471848..b1f684f 100644
--- a/net/lnet/lnet/lib-msg.c
+++ b/net/lnet/lnet/lib-msg.c
@@ -473,7 +473,7 @@
CDEBUG(D_NET,
"%s added to recovery queue. ping count: %u next ping: %lld health :%d\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
ni->ni_ping_count,
ni->ni_next_ping,
atomic_read(&ni->ni_healthv));
@@ -796,10 +796,11 @@
/* if we're sending to the LOLND then the msg_txpeer will not be
* set. So no need to sanity check it.
*/
- if (msg->msg_tx_committed && msg->msg_txni->ni_nid != LNET_NID_LO_0)
+ if (msg->msg_tx_committed &&
+ !nid_is_lo0(&msg->msg_txni->ni_nid))
LASSERT(msg->msg_txpeer);
else if (msg->msg_tx_committed &&
- msg->msg_txni->ni_nid == LNET_NID_LO_0)
+ nid_is_lo0(&msg->msg_txni->ni_nid))
lo = true;
if (hstatus != LNET_MSG_STATUS_OK &&
@@ -827,7 +828,7 @@
LASSERT(ni);
CDEBUG(D_NET, "health check: %s->%s: %s: %s\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
(lo) ? "self" : libcfs_nid2str(lpni->lpni_nid),
lnet_msgtyp2str(msg->msg_type),
lnet_health_error2str(hstatus));
@@ -1114,7 +1115,7 @@
CDEBUG(D_NET,
"src %s(%s)->dst %s: %s simulate health error: %s\n",
libcfs_nid2str(msg->msg_hdr.src_nid),
- libcfs_nid2str(msg->msg_txni->ni_nid),
+ libcfs_nidstr(&msg->msg_txni->ni_nid),
libcfs_nid2str(msg->msg_hdr.dest_nid),
lnet_msgtyp2str(msg->msg_type),
lnet_health_error2str(*hstatus));
diff --git a/net/lnet/lnet/lib-socket.c b/net/lnet/lnet/lib-socket.c
index 317d3cf..7deb48a 100644
--- a/net/lnet/lnet/lib-socket.c
+++ b/net/lnet/lnet/lib-socket.c
@@ -235,9 +235,33 @@ int choose_ipv4_src(u32 *ret, int interface, u32 dst_ipaddr, struct net *ns)
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6: {
struct sockaddr_in6 *sin6 = (void *)&locaddr;
+ int val = 0;
sin6->sin6_family = AF_INET6;
sin6->sin6_addr = in6addr_any;
+
+ /* Make sure we get both IPv4 and IPv6 connections.
+ * This is the default, but it can be overridden so we
+ * force it back.
+ */
+ /* From v5.7-rc6-2614-g5a892ff2facb when
+ * kernel_setsockopt() was removed until
+ * sockptr_t (above) there is no clean way to
+ * pass kernel address to setsockopt. We could
+ * use get_fs()/set_fs(), but in this particular
+ * situation there is an easier way. It depends
+ * on the fact that at least for these few
+ * kernels a NULL address to ipv6_setsockopt()
+ * is treated like the address of a zero.
+ */
+ if (ipv6_only_sock(sock->sk) && !val) {
+ void *optval = NULL;
+
+ sock->ops->setsockopt(sock,
+ IPPROTO_IPV6, IPV6_V6ONLY,
+ optval, sizeof(val));
+ }
+
if (interface >= 0 && remaddr) {
struct sockaddr_in6 *rem = (void *)remaddr;
@@ -352,7 +376,6 @@ struct socket *
lnet_sock_listen(int local_port, int backlog, struct net *ns)
{
struct socket *sock;
- int val = 0;
int rc;
sock = lnet_sock_create(-1, NULL, local_port, ns);
@@ -364,13 +387,6 @@ struct socket *
return ERR_PTR(rc);
}
- /* Make sure we get both IPv4 and IPv6 connections.
- * This is the default, but it can be overridden so
- * we force it back.
- */
- kernel_setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY,
- (char *)&val, sizeof(val));
-
rc = kernel_listen(sock, backlog);
if (!rc)
return sock;
diff --git a/net/lnet/lnet/lo.c b/net/lnet/lnet/lo.c
index 4ddf1cd..3d3dcf8 100644
--- a/net/lnet/lnet/lo.c
+++ b/net/lnet/lnet/lo.c
@@ -40,7 +40,8 @@
LASSERT(!lntmsg->msg_routing);
LASSERT(!lntmsg->msg_target_is_router);
- return lnet_parse(ni, &lntmsg->msg_hdr, ni->ni_nid, lntmsg, 0);
+ return lnet_parse(ni, &lntmsg->msg_hdr,
+ lnet_nid_to_nid4(&ni->ni_nid), lntmsg, 0);
}
static int
diff --git a/net/lnet/lnet/net_fault.c b/net/lnet/lnet/net_fault.c
index 0d19da4..4c50eec 100644
--- a/net/lnet/lnet/net_fault.c
+++ b/net/lnet/lnet/net_fault.c
@@ -684,7 +684,7 @@ struct delay_daemon_data {
list_del_init(&msg->msg_list);
ni = msg->msg_txni;
CDEBUG(D_NET, "TRACE: msg %p %s -> %s : %s\n", msg,
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
libcfs_nid2str(msg->msg_txpeer->lpni_nid),
lnet_msgtyp2str(msg->msg_type));
lnet_ni_send(ni, msg);
diff --git a/net/lnet/lnet/nidstrings.c b/net/lnet/lnet/nidstrings.c
index 209da0f..6da43d5 100644
--- a/net/lnet/lnet/nidstrings.c
+++ b/net/lnet/lnet/nidstrings.c
@@ -906,6 +906,46 @@ int cfs_print_nidlist(char *buffer, int count, struct list_head *nidlist)
}
EXPORT_SYMBOL(libcfs_nid2str_r);
+char *
+libcfs_nidstr_r(const struct lnet_nid *nid, char *buf, size_t buf_size)
+{
+ u32 nnum = be16_to_cpu(nid->nid_num);
+ u32 lnd = nid->nid_type;
+ struct netstrfns *nf;
+
+ if (LNET_NID_IS_ANY(nid)) {
+ strncpy(buf, "<?>", buf_size);
+ buf[buf_size - 1] = '\0';
+ return buf;
+ }
+
+ nf = libcfs_lnd2netstrfns(lnd);
+ if (nf && nid_is_nid4(nid)) {
+ size_t addr_len;
+
+ nf->nf_addr2str(ntohl(nid->nid_addr[0]), buf, buf_size);
+ addr_len = strlen(buf);
+ if (nnum == 0)
+ snprintf(buf + addr_len, buf_size - addr_len, "@%s",
+ nf->nf_name);
+ else
+ snprintf(buf + addr_len, buf_size - addr_len, "@%s%u",
+ nf->nf_name, nnum);
+ } else {
+ int l = 0;
+ int words = DIV_ROUND_UP(NID_ADDR_BYTES(nid), 4);
+ int i;
+
+ for (i = 0; i < words && i < 4; i++)
+ l = snprintf(buf + l, buf_size - l, "%s%x",
+ i ? ":" : "", ntohl(nid->nid_addr[i]));
+ snprintf(buf + l, buf_size - l, "@<%u:%u>", lnd, nnum);
+ }
+
+ return buf;
+}
+EXPORT_SYMBOL(libcfs_nidstr_r);
+
static struct netstrfns *
libcfs_str2net_internal(const char *str, u32 *net)
{
diff --git a/net/lnet/lnet/router.c b/net/lnet/lnet/router.c
index 9003d47..6335425 100644
--- a/net/lnet/lnet/router.c
+++ b/net/lnet/lnet/router.c
@@ -1691,21 +1691,21 @@ bool lnet_router_checker_active(void)
LASSERT(!in_interrupt());
CDEBUG(D_NET, "%s notifying %s: %s\n",
- !ni ? "userspace" : libcfs_nid2str(ni->ni_nid),
+ !ni ? "userspace" : libcfs_nidstr(&ni->ni_nid),
libcfs_nid2str(nid), alive ? "up" : "down");
if (ni &&
- LNET_NIDNET(ni->ni_nid) != LNET_NIDNET(nid)) {
+ LNET_NID_NET(&ni->ni_nid) != LNET_NIDNET(nid)) {
CWARN("Ignoring notification of %s %s by %s (different net)\n",
libcfs_nid2str(nid), alive ? "birth" : "death",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
return -EINVAL;
}
/* can't do predictions... */
if (when > now) {
CWARN("Ignoring prediction from %s of %s %s %lld seconds in the future\n",
- !ni ? "userspace" : libcfs_nid2str(ni->ni_nid),
+ ni ? libcfs_nidstr(&ni->ni_nid) : "userspace",
libcfs_nid2str(nid), alive ? "up" : "down", when - now);
return -EINVAL;
}
diff --git a/net/lnet/lnet/router_proc.c b/net/lnet/lnet/router_proc.c
index 43f70b6..6649f06 100644
--- a/net/lnet/lnet/router_proc.c
+++ b/net/lnet/lnet/router_proc.c
@@ -702,7 +702,7 @@ static int proc_lnet_nis(struct ctl_table *table, int write,
s += scnprintf(s, tmpstr + tmpsiz - s,
"%-24s %6s %5lld %4d %4d %4d %5d %5d %5d\n",
- libcfs_nid2str(ni->ni_nid), stat,
+ libcfs_nidstr(&ni->ni_nid), stat,
last_alive, *ni->ni_refs[i],
ni->ni_net->net_tunables.lct_peer_tx_credits,
ni->ni_net->net_tunables.lct_peer_rtr_credits,
diff --git a/net/lnet/lnet/udsp.c b/net/lnet/lnet/udsp.c
index 516db98..4495062 100644
--- a/net/lnet/lnet/udsp.c
+++ b/net/lnet/lnet/udsp.c
@@ -213,7 +213,7 @@ enum udsp_apply {
struct lnet_ud_nid_descr *ni_match = udi->udi_match;
u32 priority = (udi->udi_revert) ? -1 : udi->udi_priority;
- rc = cfs_match_nid_net(ni->ni_nid,
+ rc = cfs_match_nid_net(lnet_nid_to_nid4(&ni->ni_nid),
ni_match->ud_net_id.udn_net_type,
&ni_match->ud_net_id.udn_net_num_range,
&ni_match->ud_addr_range);
@@ -221,7 +221,7 @@ enum udsp_apply {
return 0;
CDEBUG(D_NET, "apply udsp on ni %s\n",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&ni->ni_nid));
/* Detected match. Set NIDs priority */
lnet_ni_set_sel_priority_locked(ni, priority);
@@ -481,7 +481,7 @@ enum udsp_apply {
ni_action->ud_net_id.udn_net_type)
continue;
list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
- rc = cfs_match_nid_net(ni->ni_nid,
+ rc = cfs_match_nid_net(lnet_nid_to_nid4(&ni->ni_nid),
ni_action->ud_net_id.udn_net_type,
&ni_action->ud_net_id.udn_net_num_range,
&ni_action->ud_addr_range);
@@ -500,15 +500,16 @@ enum udsp_apply {
}
}
CDEBUG(D_NET, "add nid %s as preferred for peer %s\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
libcfs_nid2str(lpni->lpni_nid));
/* match. Add to pref NIDs */
- rc = lnet_peer_add_pref_nid(lpni, ni->ni_nid);
+ rc = lnet_peer_add_pref_nid(lpni,
+ lnet_nid_to_nid4(&ni->ni_nid));
lnet_net_lock(LNET_LOCK_EX);
/* success if EEXIST return */
if (rc && rc != -EEXIST) {
CERROR("Failed to add %s to %s pref nid list\n",
- libcfs_nid2str(ni->ni_nid),
+ libcfs_nidstr(&ni->ni_nid),
libcfs_nid2str(lpni->lpni_nid));
return rc;
}
--
1.8.3.1
More information about the lustre-devel
mailing list