diff --git a/Documentation/infiniband/sysfs.txt b/Documentation/infiniband/sysfs.txt index 3ecf0c3a133f..45bcafe6ff8a 100644 --- a/Documentation/infiniband/sysfs.txt +++ b/Documentation/infiniband/sysfs.txt @@ -56,6 +56,18 @@ SYSFS FILES ports/1/pkeys/10 contains the value at index 10 in port 1's P_Key table. + There is an optional "hw_counters" subdirectory that may be under either + the parent device or the port subdirectories or both. If present, + there are a list of counters provided by the hardware. They may match + some of the counters in the counters directory, but they often include + many other counters. In addition to the various counters, there will + be a file named "lifespan" that configures how frequently the core + should update the counters when they are being accessed (counters are + not updated if they are not being accessed). The lifespan is in milli- + seconds and defaults to 10 unless set to something else by the driver. + Users may echo a value between 0 - 10000 to the lifespan file to set + the length of time between updates in milliseconds. + MTHCA The Mellanox HCA driver also creates the files: diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 14606afbfaa8..5e573bb18660 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -56,8 +56,10 @@ struct ib_port { struct gid_attr_group *gid_attr_group; struct attribute_group gid_group; struct attribute_group pkey_group; - u8 port_num; struct attribute_group *pma_table; + struct attribute_group *hw_stats_ag; + struct rdma_hw_stats *hw_stats; + u8 port_num; }; struct port_attribute { @@ -80,6 +82,18 @@ struct port_table_attribute { __be16 attr_id; }; +struct hw_stats_attribute { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, + struct attribute *attr, char *buf); + ssize_t (*store)(struct kobject *kobj, + struct attribute *attr, + const char *buf, + size_t count); + int index; + u8 port_num; +}; + static ssize_t port_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -733,6 +747,212 @@ static struct attribute_group *get_counter_table(struct ib_device *dev, return &pma_group; } +static int update_hw_stats(struct ib_device *dev, struct rdma_hw_stats *stats, + u8 port_num, int index) +{ + int ret; + + if (time_is_after_eq_jiffies(stats->timestamp + stats->lifespan)) + return 0; + ret = dev->get_hw_stats(dev, stats, port_num, index); + if (ret < 0) + return ret; + if (ret == stats->num_counters) + stats->timestamp = jiffies; + + return 0; +} + +static ssize_t print_hw_stat(struct rdma_hw_stats *stats, int index, char *buf) +{ + return sprintf(buf, "%llu\n", stats->value[index]); +} + +static ssize_t show_hw_stats(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct ib_device *dev; + struct ib_port *port; + struct hw_stats_attribute *hsa; + struct rdma_hw_stats *stats; + int ret; + + hsa = container_of(attr, struct hw_stats_attribute, attr); + if (!hsa->port_num) { + dev = container_of((struct device *)kobj, + struct ib_device, dev); + stats = dev->hw_stats; + } else { + port = container_of(kobj, struct ib_port, kobj); + dev = port->ibdev; + stats = port->hw_stats; + } + ret = update_hw_stats(dev, stats, hsa->port_num, hsa->index); + if (ret) + return ret; + return print_hw_stat(stats, hsa->index, buf); +} + +static ssize_t show_stats_lifespan(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct hw_stats_attribute *hsa; + int msecs; + + hsa = container_of(attr, struct hw_stats_attribute, attr); + if (!hsa->port_num) { + struct ib_device *dev = container_of((struct device *)kobj, + struct ib_device, dev); + msecs = jiffies_to_msecs(dev->hw_stats->lifespan); + } else { + struct ib_port *p = container_of(kobj, struct ib_port, kobj); + msecs = jiffies_to_msecs(p->hw_stats->lifespan); + } + return sprintf(buf, "%d\n", msecs); +} + +static ssize_t set_stats_lifespan(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) +{ + struct hw_stats_attribute *hsa; + int msecs; + int jiffies; + int ret; + + ret = kstrtoint(buf, 10, &msecs); + if (ret) + return ret; + if (msecs < 0 || msecs > 10000) + return -EINVAL; + jiffies = msecs_to_jiffies(msecs); + hsa = container_of(attr, struct hw_stats_attribute, attr); + if (!hsa->port_num) { + struct ib_device *dev = container_of((struct device *)kobj, + struct ib_device, dev); + dev->hw_stats->lifespan = jiffies; + } else { + struct ib_port *p = container_of(kobj, struct ib_port, kobj); + p->hw_stats->lifespan = jiffies; + } + return count; +} + +static void free_hsag(struct kobject *kobj, struct attribute_group *attr_group) +{ + struct attribute **attr; + + sysfs_remove_group(kobj, attr_group); + + for (attr = attr_group->attrs; *attr; attr++) + kfree(*attr); + kfree(attr_group); +} + +static struct attribute *alloc_hsa(int index, u8 port_num, const char *name) +{ + struct hw_stats_attribute *hsa; + + hsa = kmalloc(sizeof(*hsa), GFP_KERNEL); + if (!hsa) + return NULL; + + hsa->attr.name = (char *)name; + hsa->attr.mode = S_IRUGO; + hsa->show = show_hw_stats; + hsa->store = NULL; + hsa->index = index; + hsa->port_num = port_num; + + return &hsa->attr; +} + +static struct attribute *alloc_hsa_lifespan(char *name, u8 port_num) +{ + struct hw_stats_attribute *hsa; + + hsa = kmalloc(sizeof(*hsa), GFP_KERNEL); + if (!hsa) + return NULL; + + hsa->attr.name = name; + hsa->attr.mode = S_IWUSR | S_IRUGO; + hsa->show = show_stats_lifespan; + hsa->store = set_stats_lifespan; + hsa->index = 0; + hsa->port_num = port_num; + + return &hsa->attr; +} + +static void setup_hw_stats(struct ib_device *device, struct ib_port *port, + u8 port_num) +{ + struct attribute_group *hsag = NULL; + struct rdma_hw_stats *stats; + int i = 0, ret; + + stats = device->alloc_hw_stats(device, port_num); + + if (!stats) + return; + + if (!stats->names || stats->num_counters <= 0) + goto err; + + hsag = kzalloc(sizeof(*hsag) + + // 1 extra for the lifespan config entry + sizeof(void *) * (stats->num_counters + 1), + GFP_KERNEL); + if (!hsag) + return; + + ret = device->get_hw_stats(device, stats, port_num, + stats->num_counters); + if (ret != stats->num_counters) + goto err; + + stats->timestamp = jiffies; + + hsag->name = "hw_counters"; + hsag->attrs = (void *)hsag + sizeof(*hsag); + + for (i = 0; i < stats->num_counters; i++) { + hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]); + if (!hsag->attrs[i]) + goto err; + } + + /* treat an error here as non-fatal */ + hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num); + + if (port) { + struct kobject *kobj = &port->kobj; + ret = sysfs_create_group(kobj, hsag); + if (ret) + goto err; + port->hw_stats_ag = hsag; + port->hw_stats = stats; + } else { + struct kobject *kobj = &device->dev.kobj; + ret = sysfs_create_group(kobj, hsag); + if (ret) + goto err; + device->hw_stats_ag = hsag; + device->hw_stats = stats; + } + + return; + +err: + kfree(stats); + for (; i >= 0; i--) + kfree(hsag->attrs[i]); + kfree(hsag); + return; +} + static int add_port(struct ib_device *device, int port_num, int (*port_callback)(struct ib_device *, u8, struct kobject *)) @@ -835,6 +1055,14 @@ static int add_port(struct ib_device *device, int port_num, goto err_remove_pkey; } + /* + * If port == 0, it means we have only one port and the parent + * device, not this port device, should be the holder of the + * hw_counters + */ + if (device->alloc_hw_stats && port_num) + setup_hw_stats(device, p, port_num); + list_add_tail(&p->kobj.entry, &device->port_list); kobject_uevent(&p->kobj, KOBJ_ADD); @@ -972,120 +1200,6 @@ static struct device_attribute *ib_class_attributes[] = { &dev_attr_node_desc }; -/* Show a given an attribute in the statistics group */ -static ssize_t show_protocol_stat(const struct device *device, - struct device_attribute *attr, char *buf, - unsigned offset) -{ - struct ib_device *dev = container_of(device, struct ib_device, dev); - union rdma_protocol_stats stats; - ssize_t ret; - - ret = dev->get_protocol_stats(dev, &stats); - if (ret) - return ret; - - return sprintf(buf, "%llu\n", - (unsigned long long) ((u64 *) &stats)[offset]); -} - -/* generate a read-only iwarp statistics attribute */ -#define IW_STATS_ENTRY(name) \ -static ssize_t show_##name(struct device *device, \ - struct device_attribute *attr, char *buf) \ -{ \ - return show_protocol_stat(device, attr, buf, \ - offsetof(struct iw_protocol_stats, name) / \ - sizeof (u64)); \ -} \ -static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) - -IW_STATS_ENTRY(ipInReceives); -IW_STATS_ENTRY(ipInHdrErrors); -IW_STATS_ENTRY(ipInTooBigErrors); -IW_STATS_ENTRY(ipInNoRoutes); -IW_STATS_ENTRY(ipInAddrErrors); -IW_STATS_ENTRY(ipInUnknownProtos); -IW_STATS_ENTRY(ipInTruncatedPkts); -IW_STATS_ENTRY(ipInDiscards); -IW_STATS_ENTRY(ipInDelivers); -IW_STATS_ENTRY(ipOutForwDatagrams); -IW_STATS_ENTRY(ipOutRequests); -IW_STATS_ENTRY(ipOutDiscards); -IW_STATS_ENTRY(ipOutNoRoutes); -IW_STATS_ENTRY(ipReasmTimeout); -IW_STATS_ENTRY(ipReasmReqds); -IW_STATS_ENTRY(ipReasmOKs); -IW_STATS_ENTRY(ipReasmFails); -IW_STATS_ENTRY(ipFragOKs); -IW_STATS_ENTRY(ipFragFails); -IW_STATS_ENTRY(ipFragCreates); -IW_STATS_ENTRY(ipInMcastPkts); -IW_STATS_ENTRY(ipOutMcastPkts); -IW_STATS_ENTRY(ipInBcastPkts); -IW_STATS_ENTRY(ipOutBcastPkts); -IW_STATS_ENTRY(tcpRtoAlgorithm); -IW_STATS_ENTRY(tcpRtoMin); -IW_STATS_ENTRY(tcpRtoMax); -IW_STATS_ENTRY(tcpMaxConn); -IW_STATS_ENTRY(tcpActiveOpens); -IW_STATS_ENTRY(tcpPassiveOpens); -IW_STATS_ENTRY(tcpAttemptFails); -IW_STATS_ENTRY(tcpEstabResets); -IW_STATS_ENTRY(tcpCurrEstab); -IW_STATS_ENTRY(tcpInSegs); -IW_STATS_ENTRY(tcpOutSegs); -IW_STATS_ENTRY(tcpRetransSegs); -IW_STATS_ENTRY(tcpInErrs); -IW_STATS_ENTRY(tcpOutRsts); - -static struct attribute *iw_proto_stats_attrs[] = { - &dev_attr_ipInReceives.attr, - &dev_attr_ipInHdrErrors.attr, - &dev_attr_ipInTooBigErrors.attr, - &dev_attr_ipInNoRoutes.attr, - &dev_attr_ipInAddrErrors.attr, - &dev_attr_ipInUnknownProtos.attr, - &dev_attr_ipInTruncatedPkts.attr, - &dev_attr_ipInDiscards.attr, - &dev_attr_ipInDelivers.attr, - &dev_attr_ipOutForwDatagrams.attr, - &dev_attr_ipOutRequests.attr, - &dev_attr_ipOutDiscards.attr, - &dev_attr_ipOutNoRoutes.attr, - &dev_attr_ipReasmTimeout.attr, - &dev_attr_ipReasmReqds.attr, - &dev_attr_ipReasmOKs.attr, - &dev_attr_ipReasmFails.attr, - &dev_attr_ipFragOKs.attr, - &dev_attr_ipFragFails.attr, - &dev_attr_ipFragCreates.attr, - &dev_attr_ipInMcastPkts.attr, - &dev_attr_ipOutMcastPkts.attr, - &dev_attr_ipInBcastPkts.attr, - &dev_attr_ipOutBcastPkts.attr, - &dev_attr_tcpRtoAlgorithm.attr, - &dev_attr_tcpRtoMin.attr, - &dev_attr_tcpRtoMax.attr, - &dev_attr_tcpMaxConn.attr, - &dev_attr_tcpActiveOpens.attr, - &dev_attr_tcpPassiveOpens.attr, - &dev_attr_tcpAttemptFails.attr, - &dev_attr_tcpEstabResets.attr, - &dev_attr_tcpCurrEstab.attr, - &dev_attr_tcpInSegs.attr, - &dev_attr_tcpOutSegs.attr, - &dev_attr_tcpRetransSegs.attr, - &dev_attr_tcpInErrs.attr, - &dev_attr_tcpOutRsts.attr, - NULL -}; - -static struct attribute_group iw_stats_group = { - .name = "proto_stats", - .attrs = iw_proto_stats_attrs, -}; - static void free_port_list_attributes(struct ib_device *device) { struct kobject *p, *t; @@ -1093,6 +1207,10 @@ static void free_port_list_attributes(struct ib_device *device) list_for_each_entry_safe(p, t, &device->port_list, entry) { struct ib_port *port = container_of(p, struct ib_port, kobj); list_del(&p->entry); + if (port->hw_stats) { + kfree(port->hw_stats); + free_hsag(&port->kobj, port->hw_stats_ag); + } sysfs_remove_group(p, port->pma_table); sysfs_remove_group(p, &port->pkey_group); sysfs_remove_group(p, &port->gid_group); @@ -1149,11 +1267,8 @@ int ib_device_register_sysfs(struct ib_device *device, } } - if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats) { - ret = sysfs_create_group(&class_dev->kobj, &iw_stats_group); - if (ret) - goto err_put; - } + if (device->alloc_hw_stats) + setup_hw_stats(device, NULL, 0); return 0; @@ -1169,15 +1284,18 @@ int ib_device_register_sysfs(struct ib_device *device, void ib_device_unregister_sysfs(struct ib_device *device) { - /* Hold kobject until ib_dealloc_device() */ - struct kobject *kobj_dev = kobject_get(&device->dev.kobj); int i; - if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats) - sysfs_remove_group(kobj_dev, &iw_stats_group); + /* Hold kobject until ib_dealloc_device() */ + kobject_get(&device->dev.kobj); free_port_list_attributes(device); + if (device->hw_stats) { + kfree(device->hw_stats); + free_hsag(&device->dev.kobj, device->hw_stats_ag); + } + for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i) device_remove_file(&device->dev, ib_class_attributes[i]); diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 47cb927a0dd6..bb1a839d4d6d 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1218,59 +1218,119 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr, iwch_dev->rdev.rnic_info.pdev->device); } -static int iwch_get_mib(struct ib_device *ibdev, - union rdma_protocol_stats *stats) +enum counters { + IPINRECEIVES, + IPINHDRERRORS, + IPINADDRERRORS, + IPINUNKNOWNPROTOS, + IPINDISCARDS, + IPINDELIVERS, + IPOUTREQUESTS, + IPOUTDISCARDS, + IPOUTNOROUTES, + IPREASMTIMEOUT, + IPREASMREQDS, + IPREASMOKS, + IPREASMFAILS, + TCPACTIVEOPENS, + TCPPASSIVEOPENS, + TCPATTEMPTFAILS, + TCPESTABRESETS, + TCPCURRESTAB, + TCPINSEGS, + TCPOUTSEGS, + TCPRETRANSSEGS, + TCPINERRS, + TCPOUTRSTS, + TCPRTOMIN, + TCPRTOMAX, + NR_COUNTERS +}; + +static const char * const names[] = { + [IPINRECEIVES] = "ipInReceives", + [IPINHDRERRORS] = "ipInHdrErrors", + [IPINADDRERRORS] = "ipInAddrErrors", + [IPINUNKNOWNPROTOS] = "ipInUnknownProtos", + [IPINDISCARDS] = "ipInDiscards", + [IPINDELIVERS] = "ipInDelivers", + [IPOUTREQUESTS] = "ipOutRequests", + [IPOUTDISCARDS] = "ipOutDiscards", + [IPOUTNOROUTES] = "ipOutNoRoutes", + [IPREASMTIMEOUT] = "ipReasmTimeout", + [IPREASMREQDS] = "ipReasmReqds", + [IPREASMOKS] = "ipReasmOKs", + [IPREASMFAILS] = "ipReasmFails", + [TCPACTIVEOPENS] = "tcpActiveOpens", + [TCPPASSIVEOPENS] = "tcpPassiveOpens", + [TCPATTEMPTFAILS] = "tcpAttemptFails", + [TCPESTABRESETS] = "tcpEstabResets", + [TCPCURRESTAB] = "tcpCurrEstab", + [TCPINSEGS] = "tcpInSegs", + [TCPOUTSEGS] = "tcpOutSegs", + [TCPRETRANSSEGS] = "tcpRetransSegs", + [TCPINERRS] = "tcpInErrs", + [TCPOUTRSTS] = "tcpOutRsts", + [TCPRTOMIN] = "tcpRtoMin", + [TCPRTOMAX] = "tcpRtoMax", +}; + +static struct rdma_hw_stats *iwch_alloc_stats(struct ib_device *ibdev, + u8 port_num) +{ + BUILD_BUG_ON(ARRAY_SIZE(names) != NR_COUNTERS); + + /* Our driver only supports device level stats */ + if (port_num != 0) + return NULL; + + return rdma_alloc_hw_stats_struct(names, NR_COUNTERS, + RDMA_HW_STATS_DEFAULT_LIFESPAN); +} + +static int iwch_get_mib(struct ib_device *ibdev, struct rdma_hw_stats *stats, + u8 port, int index) { struct iwch_dev *dev; struct tp_mib_stats m; int ret; + if (port != 0 || !stats) + return -ENOSYS; + PDBG("%s ibdev %p\n", __func__, ibdev); dev = to_iwch_dev(ibdev); ret = dev->rdev.t3cdev_p->ctl(dev->rdev.t3cdev_p, RDMA_GET_MIB, &m); if (ret) return -ENOSYS; - memset(stats, 0, sizeof *stats); - stats->iw.ipInReceives = ((u64) m.ipInReceive_hi << 32) + - m.ipInReceive_lo; - stats->iw.ipInHdrErrors = ((u64) m.ipInHdrErrors_hi << 32) + - m.ipInHdrErrors_lo; - stats->iw.ipInAddrErrors = ((u64) m.ipInAddrErrors_hi << 32) + - m.ipInAddrErrors_lo; - stats->iw.ipInUnknownProtos = ((u64) m.ipInUnknownProtos_hi << 32) + - m.ipInUnknownProtos_lo; - stats->iw.ipInDiscards = ((u64) m.ipInDiscards_hi << 32) + - m.ipInDiscards_lo; - stats->iw.ipInDelivers = ((u64) m.ipInDelivers_hi << 32) + - m.ipInDelivers_lo; - stats->iw.ipOutRequests = ((u64) m.ipOutRequests_hi << 32) + - m.ipOutRequests_lo; - stats->iw.ipOutDiscards = ((u64) m.ipOutDiscards_hi << 32) + - m.ipOutDiscards_lo; - stats->iw.ipOutNoRoutes = ((u64) m.ipOutNoRoutes_hi << 32) + - m.ipOutNoRoutes_lo; - stats->iw.ipReasmTimeout = (u64) m.ipReasmTimeout; - stats->iw.ipReasmReqds = (u64) m.ipReasmReqds; - stats->iw.ipReasmOKs = (u64) m.ipReasmOKs; - stats->iw.ipReasmFails = (u64) m.ipReasmFails; - stats->iw.tcpActiveOpens = (u64) m.tcpActiveOpens; - stats->iw.tcpPassiveOpens = (u64) m.tcpPassiveOpens; - stats->iw.tcpAttemptFails = (u64) m.tcpAttemptFails; - stats->iw.tcpEstabResets = (u64) m.tcpEstabResets; - stats->iw.tcpOutRsts = (u64) m.tcpOutRsts; - stats->iw.tcpCurrEstab = (u64) m.tcpCurrEstab; - stats->iw.tcpInSegs = ((u64) m.tcpInSegs_hi << 32) + - m.tcpInSegs_lo; - stats->iw.tcpOutSegs = ((u64) m.tcpOutSegs_hi << 32) + - m.tcpOutSegs_lo; - stats->iw.tcpRetransSegs = ((u64) m.tcpRetransSeg_hi << 32) + - m.tcpRetransSeg_lo; - stats->iw.tcpInErrs = ((u64) m.tcpInErrs_hi << 32) + - m.tcpInErrs_lo; - stats->iw.tcpRtoMin = (u64) m.tcpRtoMin; - stats->iw.tcpRtoMax = (u64) m.tcpRtoMax; - return 0; + stats->value[IPINRECEIVES] = ((u64)m.ipInReceive_hi << 32) + m.ipInReceive_lo; + stats->value[IPINHDRERRORS] = ((u64)m.ipInHdrErrors_hi << 32) + m.ipInHdrErrors_lo; + stats->value[IPINADDRERRORS] = ((u64)m.ipInAddrErrors_hi << 32) + m.ipInAddrErrors_lo; + stats->value[IPINUNKNOWNPROTOS] = ((u64)m.ipInUnknownProtos_hi << 32) + m.ipInUnknownProtos_lo; + stats->value[IPINDISCARDS] = ((u64)m.ipInDiscards_hi << 32) + m.ipInDiscards_lo; + stats->value[IPINDELIVERS] = ((u64)m.ipInDelivers_hi << 32) + m.ipInDelivers_lo; + stats->value[IPOUTREQUESTS] = ((u64)m.ipOutRequests_hi << 32) + m.ipOutRequests_lo; + stats->value[IPOUTDISCARDS] = ((u64)m.ipOutDiscards_hi << 32) + m.ipOutDiscards_lo; + stats->value[IPOUTNOROUTES] = ((u64)m.ipOutNoRoutes_hi << 32) + m.ipOutNoRoutes_lo; + stats->value[IPREASMTIMEOUT] = m.ipReasmTimeout; + stats->value[IPREASMREQDS] = m.ipReasmReqds; + stats->value[IPREASMOKS] = m.ipReasmOKs; + stats->value[IPREASMFAILS] = m.ipReasmFails; + stats->value[TCPACTIVEOPENS] = m.tcpActiveOpens; + stats->value[TCPPASSIVEOPENS] = m.tcpPassiveOpens; + stats->value[TCPATTEMPTFAILS] = m.tcpAttemptFails; + stats->value[TCPESTABRESETS] = m.tcpEstabResets; + stats->value[TCPCURRESTAB] = m.tcpOutRsts; + stats->value[TCPINSEGS] = m.tcpCurrEstab; + stats->value[TCPOUTSEGS] = ((u64)m.tcpInSegs_hi << 32) + m.tcpInSegs_lo; + stats->value[TCPRETRANSSEGS] = ((u64)m.tcpOutSegs_hi << 32) + m.tcpOutSegs_lo; + stats->value[TCPINERRS] = ((u64)m.tcpRetransSeg_hi << 32) + m.tcpRetransSeg_lo, + stats->value[TCPOUTRSTS] = ((u64)m.tcpInErrs_hi << 32) + m.tcpInErrs_lo; + stats->value[TCPRTOMIN] = m.tcpRtoMin; + stats->value[TCPRTOMAX] = m.tcpRtoMax; + + return stats->num_counters; } static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL); @@ -1373,7 +1433,8 @@ int iwch_register_device(struct iwch_dev *dev) dev->ibdev.req_notify_cq = iwch_arm_cq; dev->ibdev.post_send = iwch_post_send; dev->ibdev.post_recv = iwch_post_receive; - dev->ibdev.get_protocol_stats = iwch_get_mib; + dev->ibdev.alloc_hw_stats = iwch_alloc_stats; + dev->ibdev.get_hw_stats = iwch_get_mib; dev->ibdev.uverbs_abi_ver = IWCH_UVERBS_ABI_VERSION; dev->ibdev.get_port_immutable = iwch_port_immutable; diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 7574f394fdac..dd8a86b726d2 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -446,20 +446,59 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr, c4iw_dev->rdev.lldi.pdev->device); } +enum counters { + IP4INSEGS, + IP4OUTSEGS, + IP4RETRANSSEGS, + IP4OUTRSTS, + IP6INSEGS, + IP6OUTSEGS, + IP6RETRANSSEGS, + IP6OUTRSTS, + NR_COUNTERS +}; + +static const char * const names[] = { + [IP4INSEGS] = "ip4InSegs", + [IP4OUTSEGS] = "ip4OutSegs", + [IP4RETRANSSEGS] = "ip4RetransSegs", + [IP4OUTRSTS] = "ip4OutRsts", + [IP6INSEGS] = "ip6InSegs", + [IP6OUTSEGS] = "ip6OutSegs", + [IP6RETRANSSEGS] = "ip6RetransSegs", + [IP6OUTRSTS] = "ip6OutRsts" +}; + +static struct rdma_hw_stats *c4iw_alloc_stats(struct ib_device *ibdev, + u8 port_num) +{ + BUILD_BUG_ON(ARRAY_SIZE(names) != NR_COUNTERS); + + if (port_num != 0) + return NULL; + + return rdma_alloc_hw_stats_struct(names, NR_COUNTERS, + RDMA_HW_STATS_DEFAULT_LIFESPAN); +} + static int c4iw_get_mib(struct ib_device *ibdev, - union rdma_protocol_stats *stats) + struct rdma_hw_stats *stats, + u8 port, int index) { struct tp_tcp_stats v4, v6; struct c4iw_dev *c4iw_dev = to_c4iw_dev(ibdev); cxgb4_get_tcp_stats(c4iw_dev->rdev.lldi.pdev, &v4, &v6); - memset(stats, 0, sizeof *stats); - stats->iw.tcpInSegs = v4.tcp_in_segs + v6.tcp_in_segs; - stats->iw.tcpOutSegs = v4.tcp_out_segs + v6.tcp_out_segs; - stats->iw.tcpRetransSegs = v4.tcp_retrans_segs + v6.tcp_retrans_segs; - stats->iw.tcpOutRsts = v4.tcp_out_rsts + v6.tcp_out_rsts; + stats->value[IP4INSEGS] = v4.tcp_in_segs; + stats->value[IP4OUTSEGS] = v4.tcp_out_segs; + stats->value[IP4RETRANSSEGS] = v4.tcp_retrans_segs; + stats->value[IP4OUTRSTS] = v4.tcp_out_rsts; + stats->value[IP6INSEGS] = v6.tcp_in_segs; + stats->value[IP6OUTSEGS] = v6.tcp_out_segs; + stats->value[IP6RETRANSSEGS] = v6.tcp_retrans_segs; + stats->value[IP6OUTRSTS] = v6.tcp_out_rsts; - return 0; + return stats->num_counters; } static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL); @@ -562,7 +601,8 @@ int c4iw_register_device(struct c4iw_dev *dev) dev->ibdev.req_notify_cq = c4iw_arm_cq; dev->ibdev.post_send = c4iw_post_send; dev->ibdev.post_recv = c4iw_post_receive; - dev->ibdev.get_protocol_stats = c4iw_get_mib; + dev->ibdev.alloc_hw_stats = c4iw_alloc_stats; + dev->ibdev.get_hw_stats = c4iw_get_mib; dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION; dev->ibdev.get_port_immutable = c4iw_port_immutable; dev->ibdev.drain_sq = c4iw_drain_sq; diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 4a740f7a0519..02a735b64208 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -2361,58 +2361,130 @@ static int i40iw_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } +static const char * const i40iw_hw_stat_names[] = { + // 32bit names + [I40IW_HW_STAT_INDEX_IP4RXDISCARD] = "ip4InDiscards", + [I40IW_HW_STAT_INDEX_IP4RXTRUNC] = "ip4InTruncatedPkts", + [I40IW_HW_STAT_INDEX_IP4TXNOROUTE] = "ip4OutNoRoutes", + [I40IW_HW_STAT_INDEX_IP6RXDISCARD] = "ip6InDiscards", + [I40IW_HW_STAT_INDEX_IP6RXTRUNC] = "ip6InTruncatedPkts", + [I40IW_HW_STAT_INDEX_IP6TXNOROUTE] = "ip6OutNoRoutes", + [I40IW_HW_STAT_INDEX_TCPRTXSEG] = "tcpRetransSegs", + [I40IW_HW_STAT_INDEX_TCPRXOPTERR] = "tcpInOptErrors", + [I40IW_HW_STAT_INDEX_TCPRXPROTOERR] = "tcpInProtoErrors", + // 64bit names + [I40IW_HW_STAT_INDEX_IP4RXOCTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4InOctets", + [I40IW_HW_STAT_INDEX_IP4RXPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4InPkts", + [I40IW_HW_STAT_INDEX_IP4RXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4InReasmRqd", + [I40IW_HW_STAT_INDEX_IP4RXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4InMcastPkts", + [I40IW_HW_STAT_INDEX_IP4TXOCTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4OutOctets", + [I40IW_HW_STAT_INDEX_IP4TXPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4OutPkts", + [I40IW_HW_STAT_INDEX_IP4TXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4OutSegRqd", + [I40IW_HW_STAT_INDEX_IP4TXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip4OutMcastPkts", + [I40IW_HW_STAT_INDEX_IP6RXOCTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6InOctets", + [I40IW_HW_STAT_INDEX_IP6RXPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6InPkts", + [I40IW_HW_STAT_INDEX_IP6RXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6InReasmRqd", + [I40IW_HW_STAT_INDEX_IP6RXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6InMcastPkts", + [I40IW_HW_STAT_INDEX_IP6TXOCTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6OutOctets", + [I40IW_HW_STAT_INDEX_IP6TXPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6OutPkts", + [I40IW_HW_STAT_INDEX_IP6TXFRAGS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6OutSegRqd", + [I40IW_HW_STAT_INDEX_IP6TXMCPKTS + I40IW_HW_STAT_INDEX_MAX_32] = + "ip6OutMcastPkts", + [I40IW_HW_STAT_INDEX_TCPRXSEGS + I40IW_HW_STAT_INDEX_MAX_32] = + "tcpInSegs", + [I40IW_HW_STAT_INDEX_TCPTXSEG + I40IW_HW_STAT_INDEX_MAX_32] = + "tcpOutSegs", + [I40IW_HW_STAT_INDEX_RDMARXRDS + I40IW_HW_STAT_INDEX_MAX_32] = + "iwInRdmaReads", + [I40IW_HW_STAT_INDEX_RDMARXSNDS + I40IW_HW_STAT_INDEX_MAX_32] = + "iwInRdmaSends", + [I40IW_HW_STAT_INDEX_RDMARXWRS + I40IW_HW_STAT_INDEX_MAX_32] = + "iwInRdmaWrites", + [I40IW_HW_STAT_INDEX_RDMATXRDS + I40IW_HW_STAT_INDEX_MAX_32] = + "iwOutRdmaReads", + [I40IW_HW_STAT_INDEX_RDMATXSNDS + I40IW_HW_STAT_INDEX_MAX_32] = + "iwOutRdmaSends", + [I40IW_HW_STAT_INDEX_RDMATXWRS + I40IW_HW_STAT_INDEX_MAX_32] = + "iwOutRdmaWrites", + [I40IW_HW_STAT_INDEX_RDMAVBND + I40IW_HW_STAT_INDEX_MAX_32] = + "iwRdmaBnd", + [I40IW_HW_STAT_INDEX_RDMAVINV + I40IW_HW_STAT_INDEX_MAX_32] = + "iwRdmaInv" +}; + /** - * i40iw_get_protocol_stats - Populates the rdma_stats structure - * @ibdev: ib dev struct - * @stats: iw protocol stats struct + * i40iw_alloc_hw_stats - Allocate a hw stats structure + * @ibdev: device pointer from stack + * @port_num: port number */ -static int i40iw_get_protocol_stats(struct ib_device *ibdev, - union rdma_protocol_stats *stats) +static struct rdma_hw_stats *i40iw_alloc_hw_stats(struct ib_device *ibdev, + u8 port_num) +{ + struct i40iw_device *iwdev = to_iwdev(ibdev); + struct i40iw_sc_dev *dev = &iwdev->sc_dev; + int num_counters = I40IW_HW_STAT_INDEX_MAX_32 + + I40IW_HW_STAT_INDEX_MAX_64; + unsigned long lifespan = RDMA_HW_STATS_DEFAULT_LIFESPAN; + + BUILD_BUG_ON(ARRAY_SIZE(i40iw_hw_stat_names) != + (I40IW_HW_STAT_INDEX_MAX_32 + + I40IW_HW_STAT_INDEX_MAX_64)); + + /* + * PFs get the default update lifespan, but VFs only update once + * per second + */ + if (!dev->is_pf) + lifespan = 1000; + return rdma_alloc_hw_stats_struct(i40iw_hw_stat_names, num_counters, + lifespan); +} + +/** + * i40iw_get_hw_stats - Populates the rdma_hw_stats structure + * @ibdev: device pointer from stack + * @stats: stats pointer from stack + * @port_num: port number + * @index: which hw counter the stack is requesting we update + */ +static int i40iw_get_hw_stats(struct ib_device *ibdev, + struct rdma_hw_stats *stats, + u8 port_num, int index) { struct i40iw_device *iwdev = to_iwdev(ibdev); struct i40iw_sc_dev *dev = &iwdev->sc_dev; struct i40iw_dev_pestat *devstat = &dev->dev_pestat; struct i40iw_dev_hw_stats *hw_stats = &devstat->hw_stats; - struct timespec curr_time; - static struct timespec last_rd_time = {0, 0}; unsigned long flags; - curr_time = current_kernel_time(); - memset(stats, 0, sizeof(*stats)); - if (dev->is_pf) { spin_lock_irqsave(&devstat->stats_lock, flags); devstat->ops.iw_hw_stat_read_all(devstat, &devstat->hw_stats); spin_unlock_irqrestore(&devstat->stats_lock, flags); } else { - if (((u64)curr_time.tv_sec - (u64)last_rd_time.tv_sec) > 1) - if (i40iw_vchnl_vf_get_pe_stats(dev, &devstat->hw_stats)) - return -ENOSYS; + if (i40iw_vchnl_vf_get_pe_stats(dev, &devstat->hw_stats)) + return -ENOSYS; } - stats->iw.ipInReceives = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4RXPKTS] + - hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6RXPKTS]; - stats->iw.ipInTruncatedPkts = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP4RXTRUNC] + - hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP6RXTRUNC]; - stats->iw.ipInDiscards = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP4RXDISCARD] + - hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP6RXDISCARD]; - stats->iw.ipOutNoRoutes = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP4TXNOROUTE] + - hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_IP6TXNOROUTE]; - stats->iw.ipReasmReqds = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4RXFRAGS] + - hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6RXFRAGS]; - stats->iw.ipFragCreates = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4TXFRAGS] + - hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6TXFRAGS]; - stats->iw.ipInMcastPkts = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4RXMCPKTS] + - hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6RXMCPKTS]; - stats->iw.ipOutMcastPkts = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP4TXMCPKTS] + - hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_IP6TXMCPKTS]; - stats->iw.tcpOutSegs = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_TCPTXSEG]; - stats->iw.tcpInSegs = hw_stats->stat_value_64[I40IW_HW_STAT_INDEX_TCPRXSEGS]; - stats->iw.tcpRetransSegs = hw_stats->stat_value_32[I40IW_HW_STAT_INDEX_TCPRTXSEG]; + memcpy(&stats->value[0], &hw_stats, sizeof(*hw_stats)); - last_rd_time = curr_time; - return 0; + return stats->num_counters; } /** @@ -2551,7 +2623,8 @@ static struct i40iw_ib_device *i40iw_init_rdma_device(struct i40iw_device *iwdev iwibdev->ibdev.get_dma_mr = i40iw_get_dma_mr; iwibdev->ibdev.reg_user_mr = i40iw_reg_user_mr; iwibdev->ibdev.dereg_mr = i40iw_dereg_mr; - iwibdev->ibdev.get_protocol_stats = i40iw_get_protocol_stats; + iwibdev->ibdev.alloc_hw_stats = i40iw_alloc_hw_stats; + iwibdev->ibdev.get_hw_stats = i40iw_get_hw_stats; iwibdev->ibdev.query_device = i40iw_query_device; iwibdev->ibdev.create_ah = i40iw_create_ah; iwibdev->ibdev.destroy_ah = i40iw_destroy_ah; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index fc0320c004a3..432bed510369 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -403,56 +403,55 @@ enum ib_port_speed { IB_SPEED_EDR = 32 }; -struct ib_protocol_stats { - /* TBD... */ +/** + * struct rdma_hw_stats + * @timestamp - Used by the core code to track when the last update was + * @lifespan - Used by the core code to determine how old the counters + * should be before being updated again. Stored in jiffies, defaults + * to 10 milliseconds, drivers can override the default be specifying + * their own value during their allocation routine. + * @name - Array of pointers to static names used for the counters in + * directory. + * @num_counters - How many hardware counters there are. If name is + * shorter than this number, a kernel oops will result. Driver authors + * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) + * in their code to prevent this. + * @value - Array of u64 counters that are accessed by the sysfs code and + * filled in by the drivers get_stats routine + */ +struct rdma_hw_stats { + unsigned long timestamp; + unsigned long lifespan; + const char * const *names; + int num_counters; + u64 value[]; }; -struct iw_protocol_stats { - u64 ipInReceives; - u64 ipInHdrErrors; - u64 ipInTooBigErrors; - u64 ipInNoRoutes; - u64 ipInAddrErrors; - u64 ipInUnknownProtos; - u64 ipInTruncatedPkts; - u64 ipInDiscards; - u64 ipInDelivers; - u64 ipOutForwDatagrams; - u64 ipOutRequests; - u64 ipOutDiscards; - u64 ipOutNoRoutes; - u64 ipReasmTimeout; - u64 ipReasmReqds; - u64 ipReasmOKs; - u64 ipReasmFails; - u64 ipFragOKs; - u64 ipFragFails; - u64 ipFragCreates; - u64 ipInMcastPkts; - u64 ipOutMcastPkts; - u64 ipInBcastPkts; - u64 ipOutBcastPkts; +#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 +/** + * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct + * for drivers. + * @names - Array of static const char * + * @num_counters - How many elements in array + * @lifespan - How many milliseconds between updates + */ +static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct( + const char * const *names, int num_counters, + unsigned long lifespan) +{ + struct rdma_hw_stats *stats; - u64 tcpRtoAlgorithm; - u64 tcpRtoMin; - u64 tcpRtoMax; - u64 tcpMaxConn; - u64 tcpActiveOpens; - u64 tcpPassiveOpens; - u64 tcpAttemptFails; - u64 tcpEstabResets; - u64 tcpCurrEstab; - u64 tcpInSegs; - u64 tcpOutSegs; - u64 tcpRetransSegs; - u64 tcpInErrs; - u64 tcpOutRsts; -}; + stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64), + GFP_KERNEL); + if (!stats) + return NULL; + stats->names = names; + stats->num_counters = num_counters; + stats->lifespan = msecs_to_jiffies(lifespan); + + return stats; +} -union rdma_protocol_stats { - struct ib_protocol_stats ib; - struct iw_protocol_stats iw; -}; /* Define bits for the various functionality this port needs to be supported by * the core. @@ -1707,8 +1706,29 @@ struct ib_device { struct iw_cm_verbs *iwcm; - int (*get_protocol_stats)(struct ib_device *device, - union rdma_protocol_stats *stats); + /** + * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the + * driver initialized data. The struct is kfree()'ed by the sysfs + * core when the device is removed. A lifespan of -1 in the return + * struct tells the core to set a default lifespan. + */ + struct rdma_hw_stats *(*alloc_hw_stats)(struct ib_device *device, + u8 port_num); + /** + * get_hw_stats - Fill in the counter value(s) in the stats struct. + * @index - The index in the value array we wish to have updated, or + * num_counters if we want all stats updated + * Return codes - + * < 0 - Error, no counters updated + * index - Updated the single counter pointed to by index + * num_counters - Updated all counters (will reset the timestamp + * and prevent further calls for lifespan milliseconds) + * Drivers are allowed to update all counters in leiu of just the + * one given in index at their option + */ + int (*get_hw_stats)(struct ib_device *device, + struct rdma_hw_stats *stats, + u8 port, int index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); @@ -1926,6 +1946,8 @@ struct ib_device { u8 node_type; u8 phys_port_cnt; struct ib_device_attr attrs; + struct attribute_group *hw_stats_ag; + struct rdma_hw_stats *hw_stats; /** * The following mandatory functions are used only at device