summaryrefslogtreecommitdiff
path: root/drivers/staging/lustre
diff options
context:
space:
mode:
authorLiang Zhen <liang.zhen@intel.com>2016-03-07 18:10:16 -0500
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2016-03-07 16:17:45 -0800
commit0fbbced21a94e038e4edb9069fa7a6d98c7ec64a (patch)
treef12a794157f586b0ed21528f3bebf1e4d1aa4895 /drivers/staging/lustre
parenta921e9bd4e22a792279e46f97a85891a3d5f1b7d (diff)
staging: lustre: LNet drop rule implementation
This is implementation of LNet Drop Rule, which can randomly drop LNet messages at specified rate. LNet Drop Rule can only be applied to receive side of message. User can add drop_rule either on end point of cluster (client/server) or on LNet routers. Here are lctl command to control LNet Drop Rules: - net_drop_add -s SRC_NID -d DEST_NID --rate VALUE drop 1/@VALUE of messages from @SRC_NID to @DEST_NID - net_drop_del -s SRC_NID -d DEST_NID remove all drop rules from @SRC_NID to @DEST_NID - net_drop_list list all drop rules on current node Examples: - lctl net_drop_add -s *@o2ib0 -d 192.168.1.102@tcp 1000 add new drop rule, it will drop 1/1000 messages from network o2ib0 to 192.168.1.102@tcp - lctl net_drop_add -s 10.8.6.123@o2ib1 -d * 500 add new drop rule, it will drop 1/500 messages from 10.8.6.123@o2ib1 to all nodes Signed-off-by: Liang Zhen <liang.zhen@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5435 Reviewed-on: http://review.whamcloud.com/11314 Reviewed-by: Bobi Jam <bobijam@gmail.com> Reviewed-by: Amir Shehata <amir.shehata@intel.com> Reviewed-by: Johann Lombardi <johann.lombardi@intel.com> Reviewed-by: Oleg Drokin <oleg.drokin@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/staging/lustre')
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h1
-rw-r--r--drivers/staging/lustre/include/linux/lnet/lib-lnet.h10
-rw-r--r--drivers/staging/lustre/include/linux/lnet/lib-types.h2
-rw-r--r--drivers/staging/lustre/include/linux/lnet/lnetctl.h83
-rw-r--r--drivers/staging/lustre/lnet/lnet/Makefile2
-rw-r--r--drivers/staging/lustre/lnet/lnet/api-ni.c6
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-move.c8
-rw-r--r--drivers/staging/lustre/lnet/lnet/net_fault.c434
8 files changed, 545 insertions, 1 deletions
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
index f78863143005..5ca99bd6f4e9 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
@@ -121,6 +121,7 @@ struct libcfs_ioctl_handler {
#define IOC_LIBCFS_PING _IOWR('e', 61, long)
/* #define IOC_LIBCFS_DEBUG_PEER _IOWR('e', 62, long) */
#define IOC_LIBCFS_LNETST _IOWR('e', 63, long)
+#define IOC_LIBCFS_LNET_FAULT _IOWR('e', 64, long)
/* lnd ioctls */
#define IOC_LIBCFS_REGISTER_MYNID _IOWR('e', 70, long)
#define IOC_LIBCFS_CLOSE_CONNECTION _IOWR('e', 71, long)
diff --git a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
index 84642dc76ba8..7b3f858c8b15 100644
--- a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
+++ b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
@@ -578,6 +578,16 @@ char *lnet_msgtyp2str(int type);
void lnet_print_hdr(lnet_hdr_t *hdr);
int lnet_fail_nid(lnet_nid_t nid, unsigned int threshold);
+/** \addtogroup lnet_fault_simulation @{ */
+
+int lnet_fault_ctl(int cmd, struct libcfs_ioctl_data *data);
+int lnet_fault_init(void);
+void lnet_fault_fini(void);
+
+bool lnet_drop_rule_match(lnet_hdr_t *hdr);
+
+/** @} lnet_fault_simulation */
+
void lnet_counters_get(lnet_counters_t *counters);
void lnet_counters_reset(void);
diff --git a/drivers/staging/lustre/include/linux/lnet/lib-types.h b/drivers/staging/lustre/include/linux/lnet/lib-types.h
index d2513db41114..cb09a8abddfa 100644
--- a/drivers/staging/lustre/include/linux/lnet/lib-types.h
+++ b/drivers/staging/lustre/include/linux/lnet/lib-types.h
@@ -40,6 +40,7 @@
#include <linux/types.h>
#include "types.h"
+#include "lnetctl.h"
/* Max payload size */
#define LNET_MAX_PAYLOAD CONFIG_LNET_MAX_PAYLOAD
@@ -572,6 +573,7 @@ typedef struct {
struct lnet_peer_table **ln_peer_tables;
/* failure simulation */
struct list_head ln_test_peers;
+ struct list_head ln_drop_rules;
struct list_head ln_nis; /* LND instances */
/* NIs bond on specific CPT(s) */
diff --git a/drivers/staging/lustre/include/linux/lnet/lnetctl.h b/drivers/staging/lustre/include/linux/lnet/lnetctl.h
index 4b64f625af01..ec33bf865624 100644
--- a/drivers/staging/lustre/include/linux/lnet/lnetctl.h
+++ b/drivers/staging/lustre/include/linux/lnet/lnetctl.h
@@ -17,6 +17,89 @@
#include "types.h"
+/** \addtogroup lnet_fault_simulation
+ * @{
+ */
+
+enum {
+ LNET_CTL_DROP_ADD,
+ LNET_CTL_DROP_DEL,
+ LNET_CTL_DROP_RESET,
+ LNET_CTL_DROP_LIST,
+};
+
+#define LNET_ACK_BIT BIT(0)
+#define LNET_PUT_BIT BIT(1)
+#define LNET_GET_BIT BIT(2)
+#define LNET_REPLY_BIT BIT(3)
+
+/** ioctl parameter for LNet fault simulation */
+struct lnet_fault_attr {
+ /**
+ * source NID of drop rule
+ * LNET_NID_ANY is wildcard for all sources
+ * 255.255.255.255@net is wildcard for all addresses from @net
+ */
+ lnet_nid_t fa_src;
+ /** destination NID of drop rule, see \a dr_src for details */
+ lnet_nid_t fa_dst;
+ /**
+ * Portal mask to drop, -1 means all portals, for example:
+ * fa_ptl_mask = (1 << _LDLM_CB_REQUEST_PORTAL ) |
+ * (1 << LDLM_CANCEL_REQUEST_PORTAL)
+ *
+ * If it is non-zero then only PUT and GET will be filtered, otherwise
+ * there is no portal filter, all matched messages will be checked.
+ */
+ __u64 fa_ptl_mask;
+ /**
+ * message types to drop, for example:
+ * dra_type = LNET_DROP_ACK_BIT | LNET_DROP_PUT_BIT
+ *
+ * If it is non-zero then only specified message types are filtered,
+ * otherwise all message types will be checked.
+ */
+ __u32 fa_msg_mask;
+ union {
+ /** message drop simulation */
+ struct {
+ /** drop rate of this rule */
+ __u32 da_rate;
+ /**
+ * time interval of message drop, it is exclusive
+ * with da_rate
+ */
+ __u32 da_interval;
+ } drop;
+ /** TODO: add more */
+ __u64 space[8];
+ } u;
+};
+
+/** fault simluation stats */
+struct lnet_fault_stat {
+ /** total # matched messages */
+ __u64 fs_count;
+ /** # dropped LNET_MSG_PUT by this rule */
+ __u64 fs_put;
+ /** # dropped LNET_MSG_ACK by this rule */
+ __u64 fs_ack;
+ /** # dropped LNET_MSG_GET by this rule */
+ __u64 fs_get;
+ /** # dropped LNET_MSG_REPLY by this rule */
+ __u64 fs_reply;
+ union {
+ struct {
+ /** total # dropped messages */
+ __u64 ds_dropped;
+ } drop;
+ /** TODO: add more */
+ __u64 space[8];
+ } u;
+};
+
+/** @} lnet_fault_simulation */
+
#define LNET_DEV_ID 0
#define LNET_DEV_PATH "/dev/lnet"
#define LNET_DEV_MAJOR 10
diff --git a/drivers/staging/lustre/lnet/lnet/Makefile b/drivers/staging/lustre/lnet/lnet/Makefile
index e276fe2bf8f3..4c81fa19429a 100644
--- a/drivers/staging/lustre/lnet/lnet/Makefile
+++ b/drivers/staging/lustre/lnet/lnet/Makefile
@@ -1,6 +1,6 @@
obj-$(CONFIG_LNET) += lnet.o
-lnet-y := api-ni.o config.o nidstrings.o \
+lnet-y := api-ni.o config.o nidstrings.o net_fault.o \
lib-me.o lib-msg.o lib-eq.o lib-md.o lib-ptl.o \
lib-socket.o lib-move.o module.o lo.o \
router.o router_proc.o acceptor.o peer.o
diff --git a/drivers/staging/lustre/lnet/lnet/api-ni.c b/drivers/staging/lustre/lnet/lnet/api-ni.c
index 99cdf9e54294..4d77ca368373 100644
--- a/drivers/staging/lustre/lnet/lnet/api-ni.c
+++ b/drivers/staging/lustre/lnet/lnet/api-ni.c
@@ -550,6 +550,7 @@ lnet_prepare(lnet_pid_t requested_pid)
INIT_LIST_HEAD(&the_lnet.ln_nis_cpt);
INIT_LIST_HEAD(&the_lnet.ln_nis_zombie);
INIT_LIST_HEAD(&the_lnet.ln_routers);
+ INIT_LIST_HEAD(&the_lnet.ln_drop_rules);
rc = lnet_create_remote_nets_table();
if (rc)
@@ -1564,6 +1565,7 @@ LNetNIInit(lnet_pid_t requested_pid)
if (rc)
goto err_stop_ping;
+ lnet_fault_init();
lnet_router_debugfs_init();
mutex_unlock(&the_lnet.ln_api_mutex);
@@ -1616,6 +1618,7 @@ LNetNIFini(void)
} else {
LASSERT(!the_lnet.ln_niinit_self);
+ lnet_fault_fini();
lnet_router_debugfs_fini();
lnet_router_checker_stop();
lnet_ping_target_fini();
@@ -2030,6 +2033,9 @@ LNetCtl(unsigned int cmd, void *arg)
lnet_net_unlock(LNET_LOCK_EX);
return 0;
+ case IOC_LIBCFS_LNET_FAULT:
+ return lnet_fault_ctl(data->ioc_flags, data);
+
case IOC_LIBCFS_PING:
id.nid = data->ioc_nid;
id.pid = data->ioc_u32[0];
diff --git a/drivers/staging/lustre/lnet/lnet/lib-move.c b/drivers/staging/lustre/lnet/lnet/lib-move.c
index 2d187e49ddce..29f79b1deb8c 100644
--- a/drivers/staging/lustre/lnet/lnet/lib-move.c
+++ b/drivers/staging/lustre/lnet/lnet/lib-move.c
@@ -1931,6 +1931,14 @@ lnet_parse(lnet_ni_t *ni, lnet_hdr_t *hdr, lnet_nid_t from_nid,
goto drop;
}
+ if (!list_empty(&the_lnet.ln_drop_rules) &&
+ lnet_drop_rule_match(hdr)) {
+ 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));
+ goto drop;
+ }
+
msg = lnet_msg_alloc();
if (!msg) {
CERROR("%s, src %s: Dropping %s (out of memory)\n",
diff --git a/drivers/staging/lustre/lnet/lnet/net_fault.c b/drivers/staging/lustre/lnet/lnet/net_fault.c
new file mode 100644
index 000000000000..a7005620fa2f
--- /dev/null
+++ b/drivers/staging/lustre/lnet/lnet/net_fault.c
@@ -0,0 +1,434 @@
+/*
+ * GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see
+ * http://www.gnu.org/licenses/gpl-2.0.html
+ *
+ * GPL HEADER END
+ */
+/*
+ * Copyright (c) 2014, Intel Corporation.
+ */
+/*
+ * This file is part of Lustre, http://www.lustre.org/
+ * Lustre is a trademark of Seagate, Inc.
+ *
+ * lnet/lnet/net_fault.c
+ *
+ * Lustre network fault simulation
+ *
+ * Author: liang.zhen@intel.com
+ */
+
+#define DEBUG_SUBSYSTEM S_LNET
+
+#include "../../include/linux/lnet/lib-lnet.h"
+#include "../../include/linux/lnet/lnetctl.h"
+
+#define LNET_MSG_MASK (LNET_PUT_BIT | LNET_ACK_BIT | \
+ LNET_GET_BIT | LNET_REPLY_BIT)
+
+struct lnet_drop_rule {
+ /** link chain on the_lnet.ln_drop_rules */
+ struct list_head dr_link;
+ /** attributes of this rule */
+ struct lnet_fault_attr dr_attr;
+ /** lock to protect \a dr_drop_at and \a dr_stat */
+ spinlock_t dr_lock;
+ /**
+ * the message sequence to drop, which means message is dropped when
+ * dr_stat.drs_count == dr_drop_at
+ */
+ unsigned long dr_drop_at;
+ /**
+ * seconds to drop the next message, it's exclusive with dr_drop_at
+ */
+ unsigned long dr_drop_time;
+ /** baseline to caculate dr_drop_time */
+ unsigned long dr_time_base;
+ /** statistic of dropped messages */
+ struct lnet_fault_stat dr_stat;
+};
+
+static bool
+lnet_fault_nid_match(lnet_nid_t nid, lnet_nid_t msg_nid)
+{
+ if (nid == msg_nid || nid == LNET_NID_ANY)
+ return true;
+
+ if (LNET_NIDNET(nid) != LNET_NIDNET(msg_nid))
+ return false;
+
+ /* 255.255.255.255@net is wildcard for all addresses in a network */
+ return LNET_NIDADDR(nid) == LNET_NIDADDR(LNET_NID_ANY);
+}
+
+static bool
+lnet_fault_attr_match(struct lnet_fault_attr *attr, lnet_nid_t src,
+ lnet_nid_t dst, unsigned int type, unsigned int portal)
+{
+ if (!lnet_fault_nid_match(attr->fa_src, src) ||
+ !lnet_fault_nid_match(attr->fa_dst, dst))
+ return false;
+
+ if (!(attr->fa_msg_mask & (1 << type)))
+ return false;
+
+ /**
+ * NB: ACK and REPLY have no portal, but they should have been
+ * rejected by message mask
+ */
+ if (attr->fa_ptl_mask && /* has portal filter */
+ !(attr->fa_ptl_mask & (1ULL << portal)))
+ return false;
+
+ return true;
+}
+
+static int
+lnet_fault_attr_validate(struct lnet_fault_attr *attr)
+{
+ if (!attr->fa_msg_mask)
+ attr->fa_msg_mask = LNET_MSG_MASK; /* all message types */
+
+ if (!attr->fa_ptl_mask) /* no portal filter */
+ return 0;
+
+ /* NB: only PUT and GET can be filtered if portal filter has been set */
+ attr->fa_msg_mask &= LNET_GET_BIT | LNET_PUT_BIT;
+ if (!attr->fa_msg_mask) {
+ CDEBUG(D_NET, "can't find valid message type bits %x\n",
+ attr->fa_msg_mask);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static void
+lnet_fault_stat_inc(struct lnet_fault_stat *stat, unsigned int type)
+{
+ /* NB: fs_counter is NOT updated by this function */
+ switch (type) {
+ case LNET_MSG_PUT:
+ stat->fs_put++;
+ return;
+ case LNET_MSG_ACK:
+ stat->fs_ack++;
+ return;
+ case LNET_MSG_GET:
+ stat->fs_get++;
+ return;
+ case LNET_MSG_REPLY:
+ stat->fs_reply++;
+ return;
+ }
+}
+
+/**
+ * Add a new drop rule to LNet
+ * There is no check for duplicated drop rule, all rules will be checked for
+ * incoming message.
+ */
+static int
+lnet_drop_rule_add(struct lnet_fault_attr *attr)
+{
+ struct lnet_drop_rule *rule;
+
+ if (!attr->u.drop.da_rate == !attr->u.drop.da_interval) {
+ CDEBUG(D_NET, "invalid rate %d or interval %d\n",
+ attr->u.drop.da_rate, attr->u.drop.da_interval);
+ return -EINVAL;
+ }
+
+ if (lnet_fault_attr_validate(attr))
+ return -EINVAL;
+
+ CFS_ALLOC_PTR(rule);
+ if (!rule)
+ return -ENOMEM;
+
+ spin_lock_init(&rule->dr_lock);
+
+ rule->dr_attr = *attr;
+ if (attr->u.drop.da_interval) {
+ rule->dr_time_base = cfs_time_shift(attr->u.drop.da_interval);
+ rule->dr_drop_time = cfs_time_shift(cfs_rand() %
+ attr->u.drop.da_interval);
+ } else {
+ rule->dr_drop_at = cfs_rand() % attr->u.drop.da_rate;
+ }
+
+ lnet_net_lock(LNET_LOCK_EX);
+ list_add(&rule->dr_link, &the_lnet.ln_drop_rules);
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ CDEBUG(D_NET, "Added drop rule: src %s, dst %s, rate %d, interval %d\n",
+ libcfs_nid2str(attr->fa_src), libcfs_nid2str(attr->fa_src),
+ attr->u.drop.da_rate, attr->u.drop.da_interval);
+ return 0;
+}
+
+/**
+ * Remove matched drop rules from lnet, all rules that can match \a src and
+ * \a dst will be removed.
+ * If \a src is zero, then all rules have \a dst as destination will be remove
+ * If \a dst is zero, then all rules have \a src as source will be removed
+ * If both of them are zero, all rules will be removed
+ */
+static int
+lnet_drop_rule_del(lnet_nid_t src, lnet_nid_t dst)
+{
+ struct lnet_drop_rule *rule;
+ struct lnet_drop_rule *tmp;
+ struct list_head zombies;
+ int n = 0;
+
+ INIT_LIST_HEAD(&zombies);
+
+ lnet_net_lock(LNET_LOCK_EX);
+ list_for_each_entry_safe(rule, tmp, &the_lnet.ln_drop_rules, dr_link) {
+ if (rule->dr_attr.fa_src != src && src)
+ continue;
+
+ if (rule->dr_attr.fa_dst != dst && dst)
+ continue;
+
+ list_move(&rule->dr_link, &zombies);
+ }
+ lnet_net_unlock(LNET_LOCK_EX);
+
+ list_for_each_entry_safe(rule, tmp, &zombies, dr_link) {
+ CDEBUG(D_NET, "Remove drop rule: src %s->dst: %s (1/%d, %d)\n",
+ libcfs_nid2str(rule->dr_attr.fa_src),
+ libcfs_nid2str(rule->dr_attr.fa_dst),
+ rule->dr_attr.u.drop.da_rate,
+ rule->dr_attr.u.drop.da_interval);
+
+ list_del(&rule->dr_link);
+ CFS_FREE_PTR(rule);
+ n++;
+ }
+
+ return n;
+}
+
+/**
+ * List drop rule at position of \a pos
+ */
+static int
+lnet_drop_rule_list(int pos, struct lnet_fault_attr *attr,
+ struct lnet_fault_stat *stat)
+{
+ struct lnet_drop_rule *rule;
+ int cpt;
+ int i = 0;
+ int rc = -ENOENT;
+
+ cpt = lnet_net_lock_current();
+ list_for_each_entry(rule, &the_lnet.ln_drop_rules, dr_link) {
+ if (i++ < pos)
+ continue;
+
+ spin_lock(&rule->dr_lock);
+ *attr = rule->dr_attr;
+ *stat = rule->dr_stat;
+ spin_unlock(&rule->dr_lock);
+ rc = 0;
+ break;
+ }
+
+ lnet_net_unlock(cpt);
+ return rc;
+}
+
+/**
+ * reset counters for all drop rules
+ */
+static void
+lnet_drop_rule_reset(void)
+{
+ struct lnet_drop_rule *rule;
+ int cpt;
+
+ cpt = lnet_net_lock_current();
+
+ list_for_each_entry(rule, &the_lnet.ln_drop_rules, dr_link) {
+ struct lnet_fault_attr *attr = &rule->dr_attr;
+
+ spin_lock(&rule->dr_lock);
+
+ memset(&rule->dr_stat, 0, sizeof(rule->dr_stat));
+ if (attr->u.drop.da_rate) {
+ rule->dr_drop_at = cfs_rand() % attr->u.drop.da_rate;
+ } else {
+ rule->dr_drop_time = cfs_time_shift(cfs_rand() %
+ attr->u.drop.da_interval);
+ rule->dr_time_base = cfs_time_shift(attr->u.drop.da_interval);
+ }
+ spin_unlock(&rule->dr_lock);
+ }
+
+ lnet_net_unlock(cpt);
+}
+
+/**
+ * check source/destination NID, portal, message type and drop rate,
+ * decide whether should drop this message or not
+ */
+static bool
+drop_rule_match(struct lnet_drop_rule *rule, lnet_nid_t src,
+ lnet_nid_t dst, unsigned int type, unsigned int portal)
+{
+ struct lnet_fault_attr *attr = &rule->dr_attr;
+ bool drop;
+
+ if (!lnet_fault_attr_match(attr, src, dst, type, portal))
+ return false;
+
+ /* match this rule, check drop rate now */
+ spin_lock(&rule->dr_lock);
+ if (rule->dr_drop_time) { /* time based drop */
+ unsigned long now = cfs_time_current();
+
+ rule->dr_stat.fs_count++;
+ drop = cfs_time_aftereq(now, rule->dr_drop_time);
+ if (drop) {
+ if (cfs_time_after(now, rule->dr_time_base))
+ rule->dr_time_base = now;
+
+ rule->dr_drop_time = rule->dr_time_base +
+ cfs_time_seconds(cfs_rand() %
+ attr->u.drop.da_interval);
+ rule->dr_time_base += cfs_time_seconds(attr->u.drop.da_interval);
+
+ CDEBUG(D_NET, "Drop Rule %s->%s: next drop : %lu\n",
+ libcfs_nid2str(attr->fa_src),
+ libcfs_nid2str(attr->fa_dst),
+ rule->dr_drop_time);
+ }
+
+ } else { /* rate based drop */
+ drop = rule->dr_stat.fs_count++ == rule->dr_drop_at;
+
+ if (!do_div(rule->dr_stat.fs_count, attr->u.drop.da_rate)) {
+ rule->dr_drop_at = rule->dr_stat.fs_count +
+ cfs_rand() % attr->u.drop.da_rate;
+ CDEBUG(D_NET, "Drop Rule %s->%s: next drop: %lu\n",
+ libcfs_nid2str(attr->fa_src),
+ libcfs_nid2str(attr->fa_dst), rule->dr_drop_at);
+ }
+ }
+
+ if (drop) { /* drop this message, update counters */
+ lnet_fault_stat_inc(&rule->dr_stat, type);
+ rule->dr_stat.u.drop.ds_dropped++;
+ }
+
+ spin_unlock(&rule->dr_lock);
+ return drop;
+}
+
+/**
+ * Check if message from \a src to \a dst can match any existed drop rule
+ */
+bool
+lnet_drop_rule_match(lnet_hdr_t *hdr)
+{
+ struct lnet_drop_rule *rule;
+ lnet_nid_t src = le64_to_cpu(hdr->src_nid);
+ lnet_nid_t dst = le64_to_cpu(hdr->dest_nid);
+ unsigned int typ = le32_to_cpu(hdr->type);
+ unsigned int ptl = -1;
+ bool drop = false;
+ int cpt;
+
+ /**
+ * NB: if Portal is specified, then only PUT and GET will be
+ * filtered by drop rule
+ */
+ if (typ == LNET_MSG_PUT)
+ ptl = le32_to_cpu(hdr->msg.put.ptl_index);
+ else if (typ == LNET_MSG_GET)
+ ptl = le32_to_cpu(hdr->msg.get.ptl_index);
+
+ cpt = lnet_net_lock_current();
+ list_for_each_entry(rule, &the_lnet.ln_drop_rules, dr_link) {
+ drop = drop_rule_match(rule, src, dst, typ, ptl);
+ if (drop)
+ break;
+ }
+
+ lnet_net_unlock(cpt);
+ return drop;
+}
+
+int
+lnet_fault_ctl(int opc, struct libcfs_ioctl_data *data)
+{
+ struct lnet_fault_attr *attr;
+ struct lnet_fault_stat *stat;
+
+ attr = (struct lnet_fault_attr *)data->ioc_inlbuf1;
+
+ switch (opc) {
+ default:
+ return -EINVAL;
+
+ case LNET_CTL_DROP_ADD:
+ if (!attr)
+ return -EINVAL;
+
+ return lnet_drop_rule_add(attr);
+
+ case LNET_CTL_DROP_DEL:
+ if (!attr)
+ return -EINVAL;
+
+ data->ioc_count = lnet_drop_rule_del(attr->fa_src,
+ attr->fa_dst);
+ return 0;
+
+ case LNET_CTL_DROP_RESET:
+ lnet_drop_rule_reset();
+ return 0;
+
+ case LNET_CTL_DROP_LIST:
+ stat = (struct lnet_fault_stat *)data->ioc_inlbuf2;
+ if (!attr || !stat)
+ return -EINVAL;
+
+ return lnet_drop_rule_list(data->ioc_count, attr, stat);
+ }
+}
+
+int
+lnet_fault_init(void)
+{
+ CLASSERT(LNET_PUT_BIT == 1 << LNET_MSG_PUT);
+ CLASSERT(LNET_ACK_BIT == 1 << LNET_MSG_ACK);
+ CLASSERT(LNET_GET_BIT == 1 << LNET_MSG_GET);
+ CLASSERT(LNET_REPLY_BIT == 1 << LNET_MSG_REPLY);
+
+ return 0;
+}
+
+void
+lnet_fault_fini(void)
+{
+ lnet_drop_rule_del(0, 0);
+
+ LASSERT(list_empty(&the_lnet.ln_drop_rules));
+}