From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/infiniband/core/nldev.c | 1657 ++++++++++++++++++++++++++++++++++++++++++++++++----------
1 files changed, 1,364 insertions(+), 293 deletions(-)
diff --git a/kernel/drivers/infiniband/core/nldev.c b/kernel/drivers/infiniband/core/nldev.c
index f6fa9b1..f8dfec7 100644
--- a/kernel/drivers/infiniband/core/nldev.c
+++ b/kernel/drivers/infiniband/core/nldev.c
@@ -33,80 +33,119 @@
#include <linux/module.h>
#include <linux/pid.h>
#include <linux/pid_namespace.h>
+#include <linux/mutex.h>
#include <net/netlink.h>
#include <rdma/rdma_cm.h>
#include <rdma/rdma_netlink.h>
#include "core_priv.h"
#include "cma_priv.h"
+#include "restrack.h"
+#include "uverbs.h"
+typedef int (*res_fill_func_t)(struct sk_buff*, bool,
+ struct rdma_restrack_entry*, uint32_t);
+
+/*
+ * Sort array elements by the netlink attribute name
+ */
static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
- [RDMA_NLDEV_ATTR_DEV_INDEX] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING,
- .len = IB_DEVICE_NAME_MAX - 1},
- [RDMA_NLDEV_ATTR_PORT_INDEX] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_FW_VERSION] = { .type = NLA_NUL_STRING,
- .len = IB_FW_VERSION_NAME_MAX - 1},
- [RDMA_NLDEV_ATTR_NODE_GUID] = { .type = NLA_U64 },
- [RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
- [RDMA_NLDEV_ATTR_SUBNET_PREFIX] = { .type = NLA_U64 },
- [RDMA_NLDEV_ATTR_LID] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_SM_LID] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_LMC] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_PORT_STATE] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_RES_SUMMARY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME] = { .type = NLA_NUL_STRING,
- .len = 16 },
- [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_CHARDEV] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_CHARDEV_ABI] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_CHARDEV_NAME] = { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_EMPTY_STRING },
+ [RDMA_NLDEV_ATTR_CHARDEV_TYPE] = { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE },
+ [RDMA_NLDEV_ATTR_DEV_DIM] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_DEV_INDEX] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING,
+ .len = IB_DEVICE_NAME_MAX },
+ [RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_DEV_PROTOCOL] = { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_EMPTY_STRING },
+ [RDMA_NLDEV_ATTR_DRIVER] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_DRIVER_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_DRIVER_PRINT_TYPE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_DRIVER_STRING] = { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_EMPTY_STRING },
+ [RDMA_NLDEV_ATTR_DRIVER_S32] = { .type = NLA_S32 },
+ [RDMA_NLDEV_ATTR_DRIVER_S64] = { .type = NLA_S64 },
+ [RDMA_NLDEV_ATTR_DRIVER_U32] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_DRIVER_U64] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_FW_VERSION] = { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_EMPTY_STRING },
+ [RDMA_NLDEV_ATTR_LID] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_LINK_TYPE] = { .type = NLA_NUL_STRING,
+ .len = IFNAMSIZ },
+ [RDMA_NLDEV_ATTR_LMC] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_NDEV_INDEX] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_NDEV_NAME] = { .type = NLA_NUL_STRING,
+ .len = IFNAMSIZ },
+ [RDMA_NLDEV_ATTR_NODE_GUID] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_PORT_INDEX] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_PORT_STATE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_RES_CM_ID] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_CM_IDN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_CQ] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_CQE] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_CQN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_CTXN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_DST_ADDR] = {
+ .len = sizeof(struct __kernel_sockaddr_storage) },
+ [RDMA_NLDEV_ATTR_RES_IOVA] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_RES_KERN_NAME] = { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_EMPTY_STRING },
+ [RDMA_NLDEV_ATTR_RES_LKEY] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_LQPN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_MR] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_MRLEN] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_RES_MRN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_MR_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_RES_PD] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_PDN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_PD_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_PID] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_POLL_CTX] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_RES_PS] = { .type = NLA_U32 },
[RDMA_NLDEV_ATTR_RES_QP] = { .type = NLA_NESTED },
[RDMA_NLDEV_ATTR_RES_QP_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_LQPN] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_RAW] = { .type = NLA_BINARY },
+ [RDMA_NLDEV_ATTR_RES_RKEY] = { .type = NLA_U32 },
[RDMA_NLDEV_ATTR_RES_RQPN] = { .type = NLA_U32 },
[RDMA_NLDEV_ATTR_RES_RQ_PSN] = { .type = NLA_U32 },
[RDMA_NLDEV_ATTR_RES_SQ_PSN] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_RES_TYPE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_RES_SRC_ADDR] = {
+ .len = sizeof(struct __kernel_sockaddr_storage) },
[RDMA_NLDEV_ATTR_RES_STATE] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_RES_PID] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_RES_KERN_NAME] = { .type = NLA_NUL_STRING,
- .len = TASK_COMM_LEN },
- [RDMA_NLDEV_ATTR_RES_CM_ID] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_PS] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_RES_SRC_ADDR] = {
- .len = sizeof(struct __kernel_sockaddr_storage) },
- [RDMA_NLDEV_ATTR_RES_DST_ADDR] = {
- .len = sizeof(struct __kernel_sockaddr_storage) },
- [RDMA_NLDEV_ATTR_RES_CQ] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_CQE] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_RES_SUMMARY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR]= { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME]= { .type = NLA_NUL_STRING,
+ .len = RDMA_NLDEV_ATTR_EMPTY_STRING },
+ [RDMA_NLDEV_ATTR_RES_TYPE] = { .type = NLA_U8 },
+ [RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]= { .type = NLA_U32 },
[RDMA_NLDEV_ATTR_RES_USECNT] = { .type = NLA_U64 },
- [RDMA_NLDEV_ATTR_RES_POLL_CTX] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_RES_MR] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_MR_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_RKEY] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_RES_LKEY] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_RES_IOVA] = { .type = NLA_U64 },
- [RDMA_NLDEV_ATTR_RES_MRLEN] = { .type = NLA_U64 },
- [RDMA_NLDEV_ATTR_RES_PD] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_PD_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_NDEV_INDEX] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_NDEV_NAME] = { .type = NLA_NUL_STRING,
- .len = IFNAMSIZ },
- [RDMA_NLDEV_ATTR_DRIVER] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_DRIVER_ENTRY] = { .type = NLA_NESTED },
- [RDMA_NLDEV_ATTR_DRIVER_STRING] = { .type = NLA_NUL_STRING,
- .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN },
- [RDMA_NLDEV_ATTR_DRIVER_PRINT_TYPE] = { .type = NLA_U8 },
- [RDMA_NLDEV_ATTR_DRIVER_S32] = { .type = NLA_S32 },
- [RDMA_NLDEV_ATTR_DRIVER_U32] = { .type = NLA_U32 },
- [RDMA_NLDEV_ATTR_DRIVER_S64] = { .type = NLA_S64 },
- [RDMA_NLDEV_ATTR_DRIVER_U64] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_SM_LID] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_SUBNET_PREFIX] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_STAT_MODE] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_STAT_RES] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_STAT_COUNTER] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_STAT_COUNTER_ID] = { .type = NLA_U32 },
+ [RDMA_NLDEV_ATTR_STAT_HWCOUNTERS] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY] = { .type = NLA_NESTED },
+ [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME] = { .type = NLA_NUL_STRING },
+ [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
+ [RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID] = { .type = NLA_U32 },
+ [RDMA_NLDEV_NET_NS_FD] = { .type = NLA_U32 },
+ [RDMA_NLDEV_SYS_ATTR_NETNS_MODE] = { .type = NLA_U8 },
};
static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
@@ -146,6 +185,19 @@
return 0;
}
+int rdma_nl_put_driver_string(struct sk_buff *msg, const char *name,
+ const char *str)
+{
+ if (put_driver_name_print_type(msg, name,
+ RDMA_NLDEV_PRINT_TYPE_UNSPEC))
+ return -EMSGSIZE;
+ if (nla_put_string(msg, RDMA_NLDEV_ATTR_DRIVER_STRING, str))
+ return -EMSGSIZE;
+
+ return 0;
+}
+EXPORT_SYMBOL(rdma_nl_put_driver_string);
+
int rdma_nl_put_driver_u32(struct sk_buff *msg, const char *name, u32 value)
{
return _rdma_nl_put_driver_u32(msg, name, RDMA_NLDEV_PRINT_TYPE_UNSPEC,
@@ -179,7 +231,8 @@
{
if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
return -EMSGSIZE;
- if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+ if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME,
+ dev_name(&device->dev)))
return -EMSGSIZE;
return 0;
@@ -188,6 +241,8 @@
static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
{
char fw[IB_FW_VERSION_NAME_MAX];
+ int ret = 0;
+ u8 port;
if (fill_nldev_handle(msg, device))
return -EMSGSIZE;
@@ -216,7 +271,27 @@
return -EMSGSIZE;
if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type))
return -EMSGSIZE;
- return 0;
+ if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, device->use_cq_dim))
+ return -EMSGSIZE;
+
+ /*
+ * Link type is determined on first port and mlx4 device
+ * which can potentially have two different link type for the same
+ * IB device is considered as better to be avoided in the future,
+ */
+ port = rdma_start_port(device);
+ if (rdma_cap_opa_mad(device, port))
+ ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "opa");
+ else if (rdma_protocol_ib(device, port))
+ ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "ib");
+ else if (rdma_protocol_iwarp(device, port))
+ ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "iw");
+ else if (rdma_protocol_roce(device, port))
+ ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "roce");
+ else if (rdma_protocol_usnic(device, port))
+ ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL,
+ "usnic");
+ return ret;
}
static int fill_port_info(struct sk_buff *msg,
@@ -226,6 +301,7 @@
struct net_device *netdev = NULL;
struct ib_port_attr attr;
int ret;
+ u64 cap_flags = 0;
if (fill_nldev_handle(msg, device))
return -EMSGSIZE;
@@ -238,10 +314,12 @@
return ret;
if (rdma_protocol_ib(device, port)) {
- BUILD_BUG_ON(sizeof(attr.port_cap_flags) > sizeof(u64));
+ BUILD_BUG_ON((sizeof(attr.port_cap_flags) +
+ sizeof(attr.port_cap_flags2)) > sizeof(u64));
+ cap_flags = attr.port_cap_flags |
+ ((u64)attr.port_cap_flags2 << 32);
if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
- (u64)attr.port_cap_flags,
- RDMA_NLDEV_ATTR_PAD))
+ cap_flags, RDMA_NLDEV_ATTR_PAD))
return -EMSGSIZE;
if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX,
attr.subnet_prefix, RDMA_NLDEV_ATTR_PAD))
@@ -258,9 +336,7 @@
if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_PHYS_STATE, attr.phys_state))
return -EMSGSIZE;
- if (device->get_netdev)
- netdev = device->get_netdev(device, port);
-
+ netdev = ib_device_get_netdev(device, port);
if (netdev && net_eq(dev_net(netdev), net)) {
ret = nla_put_u32(msg,
RDMA_NLDEV_ATTR_NDEV_INDEX, netdev->ifindex);
@@ -281,7 +357,8 @@
{
struct nlattr *entry_attr;
- entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY);
+ entry_attr = nla_nest_start_noflag(msg,
+ RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY);
if (!entry_attr)
return -EMSGSIZE;
@@ -307,23 +384,23 @@
[RDMA_RESTRACK_QP] = "qp",
[RDMA_RESTRACK_CM_ID] = "cm_id",
[RDMA_RESTRACK_MR] = "mr",
+ [RDMA_RESTRACK_CTX] = "ctx",
};
- struct rdma_restrack_root *res = &device->res;
struct nlattr *table_attr;
int ret, i, curr;
if (fill_nldev_handle(msg, device))
return -EMSGSIZE;
- table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_SUMMARY);
+ table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_RES_SUMMARY);
if (!table_attr)
return -EMSGSIZE;
for (i = 0; i < RDMA_RESTRACK_MAX; i++) {
if (!names[i])
continue;
- curr = rdma_restrack_count(res, i, task_active_pid_ns(current));
+ curr = rdma_restrack_count(device, i);
ret = fill_res_info_entry(msg, names[i], curr);
if (ret)
goto err;
@@ -340,29 +417,42 @@
static int fill_res_name_pid(struct sk_buff *msg,
struct rdma_restrack_entry *res)
{
+ int err = 0;
+
/*
* For user resources, user is should read /proc/PID/comm to get the
* name of the task file.
*/
if (rdma_is_kernel_res(res)) {
- if (nla_put_string(msg, RDMA_NLDEV_ATTR_RES_KERN_NAME,
- res->kern_name))
- return -EMSGSIZE;
+ err = nla_put_string(msg, RDMA_NLDEV_ATTR_RES_KERN_NAME,
+ res->kern_name);
} else {
- if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PID,
- task_pid_vnr(res->task)))
- return -EMSGSIZE;
+ pid_t pid;
+
+ pid = task_pid_vnr(res->task);
+ /*
+ * Task is dead and in zombie state.
+ * There is no need to print PID anymore.
+ */
+ if (pid)
+ /*
+ * This part is racy, task can be killed and PID will
+ * be zero right here but it is ok, next query won't
+ * return PID. We don't promise real-time reflection
+ * of SW objects.
+ */
+ err = nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PID, pid);
}
- return 0;
+
+ return err ? -EMSGSIZE : 0;
}
-static int fill_res_qp_entry(struct sk_buff *msg, struct netlink_callback *cb,
- struct rdma_restrack_entry *res, uint32_t port)
+static int fill_res_qp_entry_query(struct sk_buff *msg,
+ struct rdma_restrack_entry *res,
+ struct ib_device *dev,
+ struct ib_qp *qp)
{
- struct ib_qp *qp = container_of(res, struct ib_qp, res);
- struct rdma_restrack_root *resroot = &qp->device->res;
struct ib_qp_init_attr qp_init_attr;
- struct nlattr *entry_attr;
struct ib_qp_attr qp_attr;
int ret;
@@ -370,20 +460,6 @@
if (ret)
return ret;
- if (port && port != qp_attr.port_num)
- return 0;
-
- entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP_ENTRY);
- if (!entry_attr)
- goto out;
-
- /* In create_qp() port is not set yet */
- if (qp_attr.port_num &&
- nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, qp_attr.port_num))
- goto err;
-
- if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qp->qp_num))
- goto err;
if (qp->qp_type == IB_QPT_RC || qp->qp_type == IB_QPT_UC) {
if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_RQPN,
qp_attr.dest_qp_num))
@@ -407,37 +483,65 @@
if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_STATE, qp_attr.qp_state))
goto err;
- if (fill_res_name_pid(msg, res))
- goto err;
-
- if (resroot->fill_res_entry(msg, res))
- goto err;
-
- nla_nest_end(msg, entry_attr);
+ if (dev->ops.fill_res_qp_entry)
+ return dev->ops.fill_res_qp_entry(msg, qp);
return 0;
-err:
- nla_nest_cancel(msg, entry_attr);
-out:
- return -EMSGSIZE;
+err: return -EMSGSIZE;
}
-static int fill_res_cm_id_entry(struct sk_buff *msg,
- struct netlink_callback *cb,
+static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin,
+ struct rdma_restrack_entry *res, uint32_t port)
+{
+ struct ib_qp *qp = container_of(res, struct ib_qp, res);
+ struct ib_device *dev = qp->device;
+ int ret;
+
+ if (port && port != qp->port)
+ return -EAGAIN;
+
+ /* In create_qp() port is not set yet */
+ if (qp->port && nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, qp->port))
+ return -EMSGSIZE;
+
+ ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qp->qp_num);
+ if (ret)
+ return -EMSGSIZE;
+
+ if (!rdma_is_kernel_res(res) &&
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, qp->pd->res.id))
+ return -EMSGSIZE;
+
+ ret = fill_res_name_pid(msg, res);
+ if (ret)
+ return -EMSGSIZE;
+
+ return fill_res_qp_entry_query(msg, res, dev, qp);
+}
+
+static int fill_res_qp_raw_entry(struct sk_buff *msg, bool has_cap_net_admin,
+ struct rdma_restrack_entry *res, uint32_t port)
+{
+ struct ib_qp *qp = container_of(res, struct ib_qp, res);
+ struct ib_device *dev = qp->device;
+
+ if (port && port != qp->port)
+ return -EAGAIN;
+ if (!dev->ops.fill_res_qp_entry_raw)
+ return -EINVAL;
+ return dev->ops.fill_res_qp_entry_raw(msg, qp);
+}
+
+static int fill_res_cm_id_entry(struct sk_buff *msg, bool has_cap_net_admin,
struct rdma_restrack_entry *res, uint32_t port)
{
struct rdma_id_private *id_priv =
container_of(res, struct rdma_id_private, res);
- struct rdma_restrack_root *resroot = &id_priv->id.device->res;
+ struct ib_device *dev = id_priv->id.device;
struct rdma_cm_id *cm_id = &id_priv->id;
- struct nlattr *entry_attr;
if (port && port != cm_id->port_num)
- return 0;
-
- entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY);
- if (!entry_attr)
- goto out;
+ return -EAGAIN;
if (cm_id->port_num &&
nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, cm_id->port_num))
@@ -467,107 +571,113 @@
&cm_id->route.addr.dst_addr))
goto err;
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CM_IDN, res->id))
+ goto err;
+
if (fill_res_name_pid(msg, res))
goto err;
- if (resroot->fill_res_entry(msg, res))
- goto err;
-
- nla_nest_end(msg, entry_attr);
+ if (dev->ops.fill_res_cm_id_entry)
+ return dev->ops.fill_res_cm_id_entry(msg, cm_id);
return 0;
-err:
- nla_nest_cancel(msg, entry_attr);
-out:
- return -EMSGSIZE;
+err: return -EMSGSIZE;
}
-static int fill_res_cq_entry(struct sk_buff *msg, struct netlink_callback *cb,
+static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin,
struct rdma_restrack_entry *res, uint32_t port)
{
struct ib_cq *cq = container_of(res, struct ib_cq, res);
- struct rdma_restrack_root *resroot = &cq->device->res;
- struct nlattr *entry_attr;
-
- entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_CQ_ENTRY);
- if (!entry_attr)
- goto out;
+ struct ib_device *dev = cq->device;
if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQE, cq->cqe))
- goto err;
+ return -EMSGSIZE;
if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_USECNT,
atomic_read(&cq->usecnt), RDMA_NLDEV_ATTR_PAD))
- goto err;
+ return -EMSGSIZE;
/* Poll context is only valid for kernel CQs */
if (rdma_is_kernel_res(res) &&
nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_POLL_CTX, cq->poll_ctx))
- goto err;
+ return -EMSGSIZE;
+
+ if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, (cq->dim != NULL)))
+ return -EMSGSIZE;
+
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQN, res->id))
+ return -EMSGSIZE;
+ if (!rdma_is_kernel_res(res) &&
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CTXN,
+ cq->uobject->uevent.uobject.context->res.id))
+ return -EMSGSIZE;
if (fill_res_name_pid(msg, res))
- goto err;
+ return -EMSGSIZE;
- if (resroot->fill_res_entry(msg, res))
- goto err;
-
- nla_nest_end(msg, entry_attr);
- return 0;
-
-err:
- nla_nest_cancel(msg, entry_attr);
-out:
- return -EMSGSIZE;
+ return (dev->ops.fill_res_cq_entry) ?
+ dev->ops.fill_res_cq_entry(msg, cq) : 0;
}
-static int fill_res_mr_entry(struct sk_buff *msg, struct netlink_callback *cb,
+static int fill_res_cq_raw_entry(struct sk_buff *msg, bool has_cap_net_admin,
+ struct rdma_restrack_entry *res, uint32_t port)
+{
+ struct ib_cq *cq = container_of(res, struct ib_cq, res);
+ struct ib_device *dev = cq->device;
+
+ if (!dev->ops.fill_res_cq_entry_raw)
+ return -EINVAL;
+ return dev->ops.fill_res_cq_entry_raw(msg, cq);
+}
+
+static int fill_res_mr_entry(struct sk_buff *msg, bool has_cap_net_admin,
struct rdma_restrack_entry *res, uint32_t port)
{
struct ib_mr *mr = container_of(res, struct ib_mr, res);
- struct rdma_restrack_root *resroot = &mr->pd->device->res;
- struct nlattr *entry_attr;
+ struct ib_device *dev = mr->pd->device;
- entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_MR_ENTRY);
- if (!entry_attr)
- goto out;
-
- if (netlink_capable(cb->skb, CAP_NET_ADMIN)) {
+ if (has_cap_net_admin) {
if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_RKEY, mr->rkey))
- goto err;
+ return -EMSGSIZE;
if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LKEY, mr->lkey))
- goto err;
+ return -EMSGSIZE;
}
if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_MRLEN, mr->length,
RDMA_NLDEV_ATTR_PAD))
- goto err;
+ return -EMSGSIZE;
+
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_MRN, res->id))
+ return -EMSGSIZE;
+
+ if (!rdma_is_kernel_res(res) &&
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, mr->pd->res.id))
+ return -EMSGSIZE;
if (fill_res_name_pid(msg, res))
- goto err;
+ return -EMSGSIZE;
- if (resroot->fill_res_entry(msg, res))
- goto err;
-
- nla_nest_end(msg, entry_attr);
- return 0;
-
-err:
- nla_nest_cancel(msg, entry_attr);
-out:
- return -EMSGSIZE;
+ return (dev->ops.fill_res_mr_entry) ?
+ dev->ops.fill_res_mr_entry(msg, mr) :
+ 0;
}
-static int fill_res_pd_entry(struct sk_buff *msg, struct netlink_callback *cb,
+static int fill_res_mr_raw_entry(struct sk_buff *msg, bool has_cap_net_admin,
+ struct rdma_restrack_entry *res, uint32_t port)
+{
+ struct ib_mr *mr = container_of(res, struct ib_mr, res);
+ struct ib_device *dev = mr->pd->device;
+
+ if (!dev->ops.fill_res_mr_entry_raw)
+ return -EINVAL;
+ return dev->ops.fill_res_mr_entry_raw(msg, mr);
+}
+
+static int fill_res_pd_entry(struct sk_buff *msg, bool has_cap_net_admin,
struct rdma_restrack_entry *res, uint32_t port)
{
struct ib_pd *pd = container_of(res, struct ib_pd, res);
- struct rdma_restrack_root *resroot = &pd->device->res;
- struct nlattr *entry_attr;
- entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_PD_ENTRY);
- if (!entry_attr)
- goto out;
-
- if (netlink_capable(cb->skb, CAP_NET_ADMIN)) {
+ if (has_cap_net_admin) {
if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY,
pd->local_dma_lkey))
goto err;
@@ -580,10 +690,49 @@
atomic_read(&pd->usecnt), RDMA_NLDEV_ATTR_PAD))
goto err;
- if (fill_res_name_pid(msg, res))
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, res->id))
goto err;
- if (resroot->fill_res_entry(msg, res))
+ if (!rdma_is_kernel_res(res) &&
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CTXN,
+ pd->uobject->context->res.id))
+ goto err;
+
+ return fill_res_name_pid(msg, res);
+
+err: return -EMSGSIZE;
+}
+
+static int fill_stat_counter_mode(struct sk_buff *msg,
+ struct rdma_counter *counter)
+{
+ struct rdma_counter_mode *m = &counter->mode;
+
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, m->mode))
+ return -EMSGSIZE;
+
+ if (m->mode == RDMA_COUNTER_MODE_AUTO) {
+ if ((m->mask & RDMA_COUNTER_MASK_QP_TYPE) &&
+ nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, m->param.qp_type))
+ return -EMSGSIZE;
+
+ if ((m->mask & RDMA_COUNTER_MASK_PID) &&
+ fill_res_name_pid(msg, &counter->res))
+ return -EMSGSIZE;
+ }
+
+ return 0;
+}
+
+static int fill_stat_counter_qp_entry(struct sk_buff *msg, u32 qpn)
+{
+ struct nlattr *entry_attr;
+
+ entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP_ENTRY);
+ if (!entry_attr)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn))
goto err;
nla_nest_end(msg, entry_attr);
@@ -591,8 +740,131 @@
err:
nla_nest_cancel(msg, entry_attr);
-out:
return -EMSGSIZE;
+}
+
+static int fill_stat_counter_qps(struct sk_buff *msg,
+ struct rdma_counter *counter)
+{
+ struct rdma_restrack_entry *res;
+ struct rdma_restrack_root *rt;
+ struct nlattr *table_attr;
+ struct ib_qp *qp = NULL;
+ unsigned long id = 0;
+ int ret = 0;
+
+ table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP);
+ if (!table_attr)
+ return -EMSGSIZE;
+
+ rt = &counter->device->res[RDMA_RESTRACK_QP];
+ xa_lock(&rt->xa);
+ xa_for_each(&rt->xa, id, res) {
+ qp = container_of(res, struct ib_qp, res);
+ if (!qp->counter || (qp->counter->id != counter->id))
+ continue;
+
+ ret = fill_stat_counter_qp_entry(msg, qp->qp_num);
+ if (ret)
+ goto err;
+ }
+
+ xa_unlock(&rt->xa);
+ nla_nest_end(msg, table_attr);
+ return 0;
+
+err:
+ xa_unlock(&rt->xa);
+ nla_nest_cancel(msg, table_attr);
+ return ret;
+}
+
+int rdma_nl_stat_hwcounter_entry(struct sk_buff *msg, const char *name,
+ u64 value)
+{
+ struct nlattr *entry_attr;
+
+ entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY);
+ if (!entry_attr)
+ return -EMSGSIZE;
+
+ if (nla_put_string(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME,
+ name))
+ goto err;
+ if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE,
+ value, RDMA_NLDEV_ATTR_PAD))
+ goto err;
+
+ nla_nest_end(msg, entry_attr);
+ return 0;
+
+err:
+ nla_nest_cancel(msg, entry_attr);
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL(rdma_nl_stat_hwcounter_entry);
+
+static int fill_stat_mr_entry(struct sk_buff *msg, bool has_cap_net_admin,
+ struct rdma_restrack_entry *res, uint32_t port)
+{
+ struct ib_mr *mr = container_of(res, struct ib_mr, res);
+ struct ib_device *dev = mr->pd->device;
+
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_MRN, res->id))
+ goto err;
+
+ if (dev->ops.fill_stat_mr_entry)
+ return dev->ops.fill_stat_mr_entry(msg, mr);
+ return 0;
+
+err:
+ return -EMSGSIZE;
+}
+
+static int fill_stat_counter_hwcounters(struct sk_buff *msg,
+ struct rdma_counter *counter)
+{
+ struct rdma_hw_stats *st = counter->stats;
+ struct nlattr *table_attr;
+ int i;
+
+ table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS);
+ if (!table_attr)
+ return -EMSGSIZE;
+
+ for (i = 0; i < st->num_counters; i++)
+ if (rdma_nl_stat_hwcounter_entry(msg, st->names[i], st->value[i]))
+ goto err;
+
+ nla_nest_end(msg, table_attr);
+ return 0;
+
+err:
+ nla_nest_cancel(msg, table_attr);
+ return -EMSGSIZE;
+}
+
+static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin,
+ struct rdma_restrack_entry *res,
+ uint32_t port)
+{
+ struct rdma_counter *counter =
+ container_of(res, struct rdma_counter, res);
+
+ if (port && port != counter->port)
+ return -EAGAIN;
+
+ /* Dump it even query failed */
+ rdma_counter_query_stats(counter);
+
+ if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, counter->port) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, counter->id) ||
+ fill_stat_counter_mode(msg, counter) ||
+ fill_stat_counter_qps(msg, counter) ||
+ fill_stat_counter_hwcounters(msg, counter))
+ return -EMSGSIZE;
+
+ return 0;
}
static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -604,14 +876,14 @@
u32 index;
int err;
- err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
- nldev_policy, extack);
+ err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
return -EINVAL;
index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
- device = ib_device_get_by_index(index);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
if (!device)
return -EINVAL;
@@ -631,13 +903,66 @@
nlmsg_end(msg, nlh);
- put_device(&device->dev);
- return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
err_free:
nlmsg_free(msg);
err:
- put_device(&device->dev);
+ ib_device_put(device);
+ return err;
+}
+
+static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ struct ib_device *device;
+ u32 index;
+ int err;
+
+ err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) {
+ char name[IB_DEVICE_NAME_MAX] = {};
+
+ nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+ IB_DEVICE_NAME_MAX);
+ if (strlen(name) == 0) {
+ err = -EINVAL;
+ goto done;
+ }
+ err = ib_device_rename(device, name);
+ goto done;
+ }
+
+ if (tb[RDMA_NLDEV_NET_NS_FD]) {
+ u32 ns_fd;
+
+ ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
+ err = ib_device_set_netns_put(skb, device, ns_fd);
+ goto put_done;
+ }
+
+ if (tb[RDMA_NLDEV_ATTR_DEV_DIM]) {
+ u8 use_dim;
+
+ use_dim = nla_get_u8(tb[RDMA_NLDEV_ATTR_DEV_DIM]);
+ err = ib_device_set_dim(device, use_dim);
+ goto done;
+ }
+
+done:
+ ib_device_put(device);
+put_done:
return err;
}
@@ -673,7 +998,7 @@
{
/*
* There is no need to take lock, because
- * we are relying on ib_core's lists_rwsem
+ * we are relying on ib_core's locking.
*/
return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
}
@@ -688,15 +1013,15 @@
u32 port;
int err;
- err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
- nldev_policy, extack);
+ err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
if (err ||
!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
!tb[RDMA_NLDEV_ATTR_PORT_INDEX])
return -EINVAL;
index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
- device = ib_device_get_by_index(index);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
if (!device)
return -EINVAL;
@@ -721,14 +1046,14 @@
goto err_free;
nlmsg_end(msg, nlh);
- put_device(&device->dev);
+ ib_device_put(device);
- return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
err_free:
nlmsg_free(msg);
err:
- put_device(&device->dev);
+ ib_device_put(device);
return err;
}
@@ -742,19 +1067,19 @@
u32 idx = 0;
u32 ifindex;
int err;
- u32 p;
+ unsigned int p;
- err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
- nldev_policy, NULL);
+ err = nlmsg_parse_deprecated(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, NULL);
if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
return -EINVAL;
ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
- device = ib_device_get_by_index(ifindex);
+ device = ib_device_get_by_index(sock_net(skb->sk), ifindex);
if (!device)
return -EINVAL;
- for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+ rdma_for_each_port (device, p) {
/*
* The dumpit function returns all information from specific
* index. This specific index is taken from the netlink
@@ -785,7 +1110,7 @@
}
out:
- put_device(&device->dev);
+ ib_device_put(device);
cb->args[0] = idx;
return skb->len;
}
@@ -799,13 +1124,13 @@
u32 index;
int ret;
- ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
- nldev_policy, extack);
+ ret = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
return -EINVAL;
index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
- device = ib_device_get_by_index(index);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
if (!device)
return -EINVAL;
@@ -824,13 +1149,13 @@
goto err_free;
nlmsg_end(msg, nlh);
- put_device(&device->dev);
- return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
err_free:
nlmsg_free(msg);
err:
- put_device(&device->dev);
+ ib_device_put(device);
return ret;
}
@@ -853,7 +1178,6 @@
nlmsg_cancel(skb, nlh);
goto out;
}
-
nlmsg_end(skb, nlh);
idx++;
@@ -870,57 +1194,155 @@
}
struct nldev_fill_res_entry {
- int (*fill_res_func)(struct sk_buff *msg, struct netlink_callback *cb,
- struct rdma_restrack_entry *res, u32 port);
enum rdma_nldev_attr nldev_attr;
- enum rdma_nldev_command nldev_cmd;
+ u8 flags;
+ u32 entry;
+ u32 id;
+};
+
+enum nldev_res_flags {
+ NLDEV_PER_DEV = 1 << 0,
};
static const struct nldev_fill_res_entry fill_entries[RDMA_RESTRACK_MAX] = {
[RDMA_RESTRACK_QP] = {
- .fill_res_func = fill_res_qp_entry,
- .nldev_cmd = RDMA_NLDEV_CMD_RES_QP_GET,
.nldev_attr = RDMA_NLDEV_ATTR_RES_QP,
+ .entry = RDMA_NLDEV_ATTR_RES_QP_ENTRY,
+ .id = RDMA_NLDEV_ATTR_RES_LQPN,
},
[RDMA_RESTRACK_CM_ID] = {
- .fill_res_func = fill_res_cm_id_entry,
- .nldev_cmd = RDMA_NLDEV_CMD_RES_CM_ID_GET,
.nldev_attr = RDMA_NLDEV_ATTR_RES_CM_ID,
+ .entry = RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY,
+ .id = RDMA_NLDEV_ATTR_RES_CM_IDN,
},
[RDMA_RESTRACK_CQ] = {
- .fill_res_func = fill_res_cq_entry,
- .nldev_cmd = RDMA_NLDEV_CMD_RES_CQ_GET,
.nldev_attr = RDMA_NLDEV_ATTR_RES_CQ,
+ .flags = NLDEV_PER_DEV,
+ .entry = RDMA_NLDEV_ATTR_RES_CQ_ENTRY,
+ .id = RDMA_NLDEV_ATTR_RES_CQN,
},
[RDMA_RESTRACK_MR] = {
- .fill_res_func = fill_res_mr_entry,
- .nldev_cmd = RDMA_NLDEV_CMD_RES_MR_GET,
.nldev_attr = RDMA_NLDEV_ATTR_RES_MR,
+ .flags = NLDEV_PER_DEV,
+ .entry = RDMA_NLDEV_ATTR_RES_MR_ENTRY,
+ .id = RDMA_NLDEV_ATTR_RES_MRN,
},
[RDMA_RESTRACK_PD] = {
- .fill_res_func = fill_res_pd_entry,
- .nldev_cmd = RDMA_NLDEV_CMD_RES_PD_GET,
.nldev_attr = RDMA_NLDEV_ATTR_RES_PD,
+ .flags = NLDEV_PER_DEV,
+ .entry = RDMA_NLDEV_ATTR_RES_PD_ENTRY,
+ .id = RDMA_NLDEV_ATTR_RES_PDN,
+ },
+ [RDMA_RESTRACK_COUNTER] = {
+ .nldev_attr = RDMA_NLDEV_ATTR_STAT_COUNTER,
+ .entry = RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY,
+ .id = RDMA_NLDEV_ATTR_STAT_COUNTER_ID,
},
};
-static int res_get_common_dumpit(struct sk_buff *skb,
- struct netlink_callback *cb,
- enum rdma_restrack_type res_type)
+static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack,
+ enum rdma_restrack_type res_type,
+ res_fill_func_t fill_func)
{
const struct nldev_fill_res_entry *fe = &fill_entries[res_type];
struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
struct rdma_restrack_entry *res;
+ struct ib_device *device;
+ u32 index, id, port = 0;
+ bool has_cap_net_admin;
+ struct sk_buff *msg;
+ int ret;
+
+ ret = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !fe->id || !tb[fe->id])
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) {
+ port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+ if (!rdma_is_port_valid(device, port)) {
+ ret = -EINVAL;
+ goto err;
+ }
+ }
+
+ if ((port && fe->flags & NLDEV_PER_DEV) ||
+ (!port && ~fe->flags & NLDEV_PER_DEV)) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ id = nla_get_u32(tb[fe->id]);
+ res = rdma_restrack_get_byid(device, res_type, id);
+ if (IS_ERR(res)) {
+ ret = PTR_ERR(res);
+ goto err;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto err_get;
+ }
+
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NL_GET_OP(nlh->nlmsg_type)),
+ 0, 0);
+
+ if (fill_nldev_handle(msg, device)) {
+ ret = -EMSGSIZE;
+ goto err_free;
+ }
+
+ has_cap_net_admin = netlink_capable(skb, CAP_NET_ADMIN);
+
+ ret = fill_func(msg, has_cap_net_admin, res, port);
+ if (ret)
+ goto err_free;
+
+ rdma_restrack_put(res);
+ nlmsg_end(msg, nlh);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+
+err_free:
+ nlmsg_free(msg);
+err_get:
+ rdma_restrack_put(res);
+err:
+ ib_device_put(device);
+ return ret;
+}
+
+static int res_get_common_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ enum rdma_restrack_type res_type,
+ res_fill_func_t fill_func)
+{
+ const struct nldev_fill_res_entry *fe = &fill_entries[res_type];
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ struct rdma_restrack_entry *res;
+ struct rdma_restrack_root *rt;
int err, ret = 0, idx = 0;
struct nlattr *table_attr;
+ struct nlattr *entry_attr;
struct ib_device *device;
int start = cb->args[0];
+ bool has_cap_net_admin;
struct nlmsghdr *nlh;
+ unsigned long id;
u32 index, port = 0;
bool filled = false;
- err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
- nldev_policy, NULL);
+ err = nlmsg_parse_deprecated(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, NULL);
/*
* Right now, we are expecting the device index to get res information,
* but it is possible to extend this code to return all devices in
@@ -933,7 +1355,7 @@
return -EINVAL;
index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
- device = ib_device_get_by_index(index);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
if (!device)
return -EINVAL;
@@ -949,7 +1371,8 @@
}
nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
- RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, fe->nldev_cmd),
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NL_GET_OP(cb->nlh->nlmsg_type)),
0, NLM_F_MULTI);
if (fill_nldev_handle(skb, device)) {
@@ -957,61 +1380,55 @@
goto err;
}
- table_attr = nla_nest_start(skb, fe->nldev_attr);
+ table_attr = nla_nest_start_noflag(skb, fe->nldev_attr);
if (!table_attr) {
ret = -EMSGSIZE;
goto err;
}
- down_read(&device->res.rwsem);
- hash_for_each_possible(device->res.hash, res, node, res_type) {
- if (idx < start)
+ has_cap_net_admin = netlink_capable(cb->skb, CAP_NET_ADMIN);
+
+ rt = &device->res[res_type];
+ xa_lock(&rt->xa);
+ /*
+ * FIXME: if the skip ahead is something common this loop should
+ * use xas_for_each & xas_pause to optimize, we can have a lot of
+ * objects.
+ */
+ xa_for_each(&rt->xa, id, res) {
+ if (idx < start || !rdma_restrack_get(res))
goto next;
- if ((rdma_is_kernel_res(res) &&
- task_active_pid_ns(current) != &init_pid_ns) ||
- (!rdma_is_kernel_res(res) && task_active_pid_ns(current) !=
- task_active_pid_ns(res->task)))
- /*
- * 1. Kern resources should be visible in init
- * namspace only
- * 2. Present only resources visible in the current
- * namespace
- */
- goto next;
-
- if (!rdma_restrack_get(res))
- /*
- * Resource is under release now, but we are not
- * relesing lock now, so it will be released in
- * our next pass, once we will get ->next pointer.
- */
- goto next;
+ xa_unlock(&rt->xa);
filled = true;
- up_read(&device->res.rwsem);
- ret = fe->fill_res_func(skb, cb, res, port);
- down_read(&device->res.rwsem);
- /*
- * Return resource back, but it won't be released till
- * the &device->res.rwsem will be released for write.
- */
+ entry_attr = nla_nest_start_noflag(skb, fe->entry);
+ if (!entry_attr) {
+ ret = -EMSGSIZE;
+ rdma_restrack_put(res);
+ goto msg_full;
+ }
+
+ ret = fill_func(skb, has_cap_net_admin, res, port);
+
rdma_restrack_put(res);
- if (ret == -EMSGSIZE)
- /*
- * There is a chance to optimize here.
- * It can be done by using list_prepare_entry
- * and list_for_each_entry_continue afterwards.
- */
- break;
- if (ret)
+ if (ret) {
+ nla_nest_cancel(skb, entry_attr);
+ if (ret == -EMSGSIZE)
+ goto msg_full;
+ if (ret == -EAGAIN)
+ goto again;
goto res_err;
+ }
+ nla_nest_end(skb, entry_attr);
+again: xa_lock(&rt->xa);
next: idx++;
}
- up_read(&device->res.rwsem);
+ xa_unlock(&rt->xa);
+msg_full:
nla_nest_end(skb, table_attr);
nlmsg_end(skb, nlh);
cb->args[0] = idx;
@@ -1023,55 +1440,680 @@
if (!filled)
goto err;
- put_device(&device->dev);
+ ib_device_put(device);
return skb->len;
res_err:
nla_nest_cancel(skb, table_attr);
- up_read(&device->res.rwsem);
err:
nlmsg_cancel(skb, nlh);
err_index:
- put_device(&device->dev);
+ ib_device_put(device);
return ret;
}
-static int nldev_res_get_qp_dumpit(struct sk_buff *skb,
- struct netlink_callback *cb)
+#define RES_GET_FUNCS(name, type) \
+ static int nldev_res_get_##name##_dumpit(struct sk_buff *skb, \
+ struct netlink_callback *cb) \
+ { \
+ return res_get_common_dumpit(skb, cb, type, \
+ fill_res_##name##_entry); \
+ } \
+ static int nldev_res_get_##name##_doit(struct sk_buff *skb, \
+ struct nlmsghdr *nlh, \
+ struct netlink_ext_ack *extack) \
+ { \
+ return res_get_common_doit(skb, nlh, extack, type, \
+ fill_res_##name##_entry); \
+ }
+
+RES_GET_FUNCS(qp, RDMA_RESTRACK_QP);
+RES_GET_FUNCS(qp_raw, RDMA_RESTRACK_QP);
+RES_GET_FUNCS(cm_id, RDMA_RESTRACK_CM_ID);
+RES_GET_FUNCS(cq, RDMA_RESTRACK_CQ);
+RES_GET_FUNCS(cq_raw, RDMA_RESTRACK_CQ);
+RES_GET_FUNCS(pd, RDMA_RESTRACK_PD);
+RES_GET_FUNCS(mr, RDMA_RESTRACK_MR);
+RES_GET_FUNCS(mr_raw, RDMA_RESTRACK_MR);
+RES_GET_FUNCS(counter, RDMA_RESTRACK_COUNTER);
+
+static LIST_HEAD(link_ops);
+static DECLARE_RWSEM(link_ops_rwsem);
+
+static const struct rdma_link_ops *link_ops_get(const char *type)
{
- return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_QP);
+ const struct rdma_link_ops *ops;
+
+ list_for_each_entry(ops, &link_ops, list) {
+ if (!strcmp(ops->type, type))
+ goto out;
+ }
+ ops = NULL;
+out:
+ return ops;
}
-static int nldev_res_get_cm_id_dumpit(struct sk_buff *skb,
- struct netlink_callback *cb)
+void rdma_link_register(struct rdma_link_ops *ops)
{
- return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_CM_ID);
+ down_write(&link_ops_rwsem);
+ if (WARN_ON_ONCE(link_ops_get(ops->type)))
+ goto out;
+ list_add(&ops->list, &link_ops);
+out:
+ up_write(&link_ops_rwsem);
+}
+EXPORT_SYMBOL(rdma_link_register);
+
+void rdma_link_unregister(struct rdma_link_ops *ops)
+{
+ down_write(&link_ops_rwsem);
+ list_del(&ops->list);
+ up_write(&link_ops_rwsem);
+}
+EXPORT_SYMBOL(rdma_link_unregister);
+
+static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ char ibdev_name[IB_DEVICE_NAME_MAX];
+ const struct rdma_link_ops *ops;
+ char ndev_name[IFNAMSIZ];
+ struct net_device *ndev;
+ char type[IFNAMSIZ];
+ int err;
+
+ err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+ !tb[RDMA_NLDEV_ATTR_LINK_TYPE] || !tb[RDMA_NLDEV_ATTR_NDEV_NAME])
+ return -EINVAL;
+
+ nla_strlcpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+ sizeof(ibdev_name));
+ if (strchr(ibdev_name, '%') || strlen(ibdev_name) == 0)
+ return -EINVAL;
+
+ nla_strlcpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
+ nla_strlcpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME],
+ sizeof(ndev_name));
+
+ ndev = dev_get_by_name(sock_net(skb->sk), ndev_name);
+ if (!ndev)
+ return -ENODEV;
+
+ down_read(&link_ops_rwsem);
+ ops = link_ops_get(type);
+#ifdef CONFIG_MODULES
+ if (!ops) {
+ up_read(&link_ops_rwsem);
+ request_module("rdma-link-%s", type);
+ down_read(&link_ops_rwsem);
+ ops = link_ops_get(type);
+ }
+#endif
+ err = ops ? ops->newlink(ibdev_name, ndev) : -EINVAL;
+ up_read(&link_ops_rwsem);
+ dev_put(ndev);
+
+ return err;
}
-static int nldev_res_get_cq_dumpit(struct sk_buff *skb,
- struct netlink_callback *cb)
+static int nldev_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
{
- return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_CQ);
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ struct ib_device *device;
+ u32 index;
+ int err;
+
+ err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ if (!(device->attrs.device_cap_flags & IB_DEVICE_ALLOW_USER_UNREG)) {
+ ib_device_put(device);
+ return -EINVAL;
+ }
+
+ ib_unregister_device_and_put(device);
+ return 0;
}
-static int nldev_res_get_mr_dumpit(struct sk_buff *skb,
- struct netlink_callback *cb)
+static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
{
- return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_MR);
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ char client_name[RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE];
+ struct ib_client_nl_info data = {};
+ struct ib_device *ibdev = NULL;
+ struct sk_buff *msg;
+ u32 index;
+ int err;
+
+ err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy,
+ extack);
+ if (err || !tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE])
+ return -EINVAL;
+
+ nla_strlcpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE],
+ sizeof(client_name));
+
+ if (tb[RDMA_NLDEV_ATTR_DEV_INDEX]) {
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ ibdev = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!ibdev)
+ return -EINVAL;
+
+ if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) {
+ data.port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+ if (!rdma_is_port_valid(ibdev, data.port)) {
+ err = -EINVAL;
+ goto out_put;
+ }
+ } else {
+ data.port = -1;
+ }
+ } else if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) {
+ return -EINVAL;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ err = -ENOMEM;
+ goto out_put;
+ }
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_GET_CHARDEV),
+ 0, 0);
+
+ data.nl_msg = msg;
+ err = ib_get_client_nl_info(ibdev, client_name, &data);
+ if (err)
+ goto out_nlmsg;
+
+ err = nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CHARDEV,
+ huge_encode_dev(data.cdev->devt),
+ RDMA_NLDEV_ATTR_PAD);
+ if (err)
+ goto out_data;
+ err = nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CHARDEV_ABI, data.abi,
+ RDMA_NLDEV_ATTR_PAD);
+ if (err)
+ goto out_data;
+ if (nla_put_string(msg, RDMA_NLDEV_ATTR_CHARDEV_NAME,
+ dev_name(data.cdev))) {
+ err = -EMSGSIZE;
+ goto out_data;
+ }
+
+ nlmsg_end(msg, nlh);
+ put_device(data.cdev);
+ if (ibdev)
+ ib_device_put(ibdev);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+
+out_data:
+ put_device(data.cdev);
+out_nlmsg:
+ nlmsg_free(msg);
+out_put:
+ if (ibdev)
+ ib_device_put(ibdev);
+ return err;
}
-static int nldev_res_get_pd_dumpit(struct sk_buff *skb,
- struct netlink_callback *cb)
+static int nldev_sys_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
{
- return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_PD);
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ struct sk_buff *msg;
+ int err;
+
+ err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (err)
+ return err;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_SYS_GET),
+ 0, 0);
+
+ err = nla_put_u8(msg, RDMA_NLDEV_SYS_ATTR_NETNS_MODE,
+ (u8)ib_devices_shared_netns);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+ nlmsg_end(msg, nlh);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+}
+
+static int nldev_set_sys_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ u8 enable;
+ int err;
+
+ err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (err || !tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE])
+ return -EINVAL;
+
+ enable = nla_get_u8(tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]);
+ /* Only 0 and 1 are supported */
+ if (enable > 1)
+ return -EINVAL;
+
+ err = rdma_compatdev_set(enable);
+ return err;
+}
+
+static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ u32 index, port, mode, mask = 0, qpn, cntn = 0;
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ struct ib_device *device;
+ struct sk_buff *msg;
+ int ret;
+
+ ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ /* Currently only counter for QP is supported */
+ if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+ !tb[RDMA_NLDEV_ATTR_PORT_INDEX] || !tb[RDMA_NLDEV_ATTR_STAT_MODE])
+ return -EINVAL;
+
+ if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP)
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+ if (!rdma_is_port_valid(device, port)) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_STAT_SET),
+ 0, 0);
+
+ mode = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_MODE]);
+ if (mode == RDMA_COUNTER_MODE_AUTO) {
+ if (tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK])
+ mask = nla_get_u32(
+ tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]);
+
+ ret = rdma_counter_set_auto_mode(device, port,
+ mask ? true : false, mask);
+ if (ret)
+ goto err_msg;
+ } else {
+ if (!tb[RDMA_NLDEV_ATTR_RES_LQPN])
+ goto err_msg;
+ qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]);
+ if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) {
+ cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
+ ret = rdma_counter_bind_qpn(device, port, qpn, cntn);
+ } else {
+ ret = rdma_counter_bind_qpn_alloc(device, port,
+ qpn, &cntn);
+ }
+ if (ret)
+ goto err_msg;
+
+ if (fill_nldev_handle(msg, device) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) {
+ ret = -EMSGSIZE;
+ goto err_fill;
+ }
+ }
+
+ nlmsg_end(msg, nlh);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+
+err_fill:
+ rdma_counter_unbind_qpn(device, port, qpn, cntn);
+err_msg:
+ nlmsg_free(msg);
+err:
+ ib_device_put(device);
+ return ret;
+}
+
+static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ struct ib_device *device;
+ struct sk_buff *msg;
+ u32 index, port, qpn, cntn;
+ int ret;
+
+ ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX] ||
+ !tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID] ||
+ !tb[RDMA_NLDEV_ATTR_RES_LQPN])
+ return -EINVAL;
+
+ if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP)
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+ if (!rdma_is_port_valid(device, port)) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_STAT_SET),
+ 0, 0);
+
+ cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
+ qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]);
+ if (fill_nldev_handle(msg, device) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) {
+ ret = -EMSGSIZE;
+ goto err_fill;
+ }
+
+ ret = rdma_counter_unbind_qpn(device, port, qpn, cntn);
+ if (ret)
+ goto err_fill;
+
+ nlmsg_end(msg, nlh);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+
+err_fill:
+ nlmsg_free(msg);
+err:
+ ib_device_put(device);
+ return ret;
+}
+
+static int stat_get_doit_default_counter(struct sk_buff *skb,
+ struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack,
+ struct nlattr *tb[])
+{
+ struct rdma_hw_stats *stats;
+ struct nlattr *table_attr;
+ struct ib_device *device;
+ int ret, num_cnts, i;
+ struct sk_buff *msg;
+ u32 index, port;
+ u64 v;
+
+ if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ if (!device->ops.alloc_hw_stats || !device->ops.get_hw_stats) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+ if (!rdma_is_port_valid(device, port)) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_STAT_GET),
+ 0, 0);
+
+ if (fill_nldev_handle(msg, device) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) {
+ ret = -EMSGSIZE;
+ goto err_msg;
+ }
+
+ stats = device->port_data ? device->port_data[port].hw_stats : NULL;
+ if (stats == NULL) {
+ ret = -EINVAL;
+ goto err_msg;
+ }
+ mutex_lock(&stats->lock);
+
+ num_cnts = device->ops.get_hw_stats(device, stats, port, 0);
+ if (num_cnts < 0) {
+ ret = -EINVAL;
+ goto err_stats;
+ }
+
+ table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS);
+ if (!table_attr) {
+ ret = -EMSGSIZE;
+ goto err_stats;
+ }
+ for (i = 0; i < num_cnts; i++) {
+ v = stats->value[i] +
+ rdma_counter_get_hwstat_value(device, port, i);
+ if (rdma_nl_stat_hwcounter_entry(msg, stats->names[i], v)) {
+ ret = -EMSGSIZE;
+ goto err_table;
+ }
+ }
+ nla_nest_end(msg, table_attr);
+
+ mutex_unlock(&stats->lock);
+ nlmsg_end(msg, nlh);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+
+err_table:
+ nla_nest_cancel(msg, table_attr);
+err_stats:
+ mutex_unlock(&stats->lock);
+err_msg:
+ nlmsg_free(msg);
+err:
+ ib_device_put(device);
+ return ret;
+}
+
+static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack, struct nlattr *tb[])
+
+{
+ static enum rdma_nl_counter_mode mode;
+ static enum rdma_nl_counter_mask mask;
+ struct ib_device *device;
+ struct sk_buff *msg;
+ u32 index, port;
+ int ret;
+
+ if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID])
+ return nldev_res_get_counter_doit(skb, nlh, extack);
+
+ if (!tb[RDMA_NLDEV_ATTR_STAT_MODE] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+ return -EINVAL;
+
+ index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ device = ib_device_get_by_index(sock_net(skb->sk), index);
+ if (!device)
+ return -EINVAL;
+
+ port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+ if (!rdma_is_port_valid(device, port)) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+ RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+ RDMA_NLDEV_CMD_STAT_GET),
+ 0, 0);
+
+ ret = rdma_counter_get_mode(device, port, &mode, &mask);
+ if (ret)
+ goto err_msg;
+
+ if (fill_nldev_handle(msg, device) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) ||
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) {
+ ret = -EMSGSIZE;
+ goto err_msg;
+ }
+
+ if ((mode == RDMA_COUNTER_MODE_AUTO) &&
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) {
+ ret = -EMSGSIZE;
+ goto err_msg;
+ }
+
+ nlmsg_end(msg, nlh);
+ ib_device_put(device);
+ return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
+
+err_msg:
+ nlmsg_free(msg);
+err:
+ ib_device_put(device);
+ return ret;
+}
+
+static int nldev_stat_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ int ret;
+
+ ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, extack);
+ if (ret)
+ return -EINVAL;
+
+ if (!tb[RDMA_NLDEV_ATTR_STAT_RES])
+ return stat_get_doit_default_counter(skb, nlh, extack, tb);
+
+ switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) {
+ case RDMA_NLDEV_ATTR_RES_QP:
+ ret = stat_get_doit_qp(skb, nlh, extack, tb);
+ break;
+ case RDMA_NLDEV_ATTR_RES_MR:
+ ret = res_get_common_doit(skb, nlh, extack, RDMA_RESTRACK_MR,
+ fill_stat_mr_entry);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static int nldev_stat_get_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+ int ret;
+
+ ret = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+ nldev_policy, NULL);
+ if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES])
+ return -EINVAL;
+
+ switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) {
+ case RDMA_NLDEV_ATTR_RES_QP:
+ ret = nldev_res_get_counter_dumpit(skb, cb);
+ break;
+ case RDMA_NLDEV_ATTR_RES_MR:
+ ret = res_get_common_dumpit(skb, cb, RDMA_RESTRACK_MR,
+ fill_stat_mr_entry);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
}
static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
[RDMA_NLDEV_CMD_GET] = {
.doit = nldev_get_doit,
.dump = nldev_get_dumpit,
+ },
+ [RDMA_NLDEV_CMD_GET_CHARDEV] = {
+ .doit = nldev_get_chardev,
+ },
+ [RDMA_NLDEV_CMD_SET] = {
+ .doit = nldev_set_doit,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_NEWLINK] = {
+ .doit = nldev_newlink,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_DELLINK] = {
+ .doit = nldev_dellink,
+ .flags = RDMA_NL_ADMIN_PERM,
},
[RDMA_NLDEV_CMD_PORT_GET] = {
.doit = nldev_port_get_doit,
@@ -1082,29 +2124,58 @@
.dump = nldev_res_get_dumpit,
},
[RDMA_NLDEV_CMD_RES_QP_GET] = {
+ .doit = nldev_res_get_qp_doit,
.dump = nldev_res_get_qp_dumpit,
- /*
- * .doit is not implemented yet for two reasons:
- * 1. It is not needed yet.
- * 2. There is a need to provide identifier, while it is easy
- * for the QPs (device index + port index + LQPN), it is not
- * the case for the rest of resources (PD and CQ). Because it
- * is better to provide similar interface for all resources,
- * let's wait till we will have other resources implemented
- * too.
- */
},
[RDMA_NLDEV_CMD_RES_CM_ID_GET] = {
+ .doit = nldev_res_get_cm_id_doit,
.dump = nldev_res_get_cm_id_dumpit,
},
[RDMA_NLDEV_CMD_RES_CQ_GET] = {
+ .doit = nldev_res_get_cq_doit,
.dump = nldev_res_get_cq_dumpit,
},
[RDMA_NLDEV_CMD_RES_MR_GET] = {
+ .doit = nldev_res_get_mr_doit,
.dump = nldev_res_get_mr_dumpit,
},
[RDMA_NLDEV_CMD_RES_PD_GET] = {
+ .doit = nldev_res_get_pd_doit,
.dump = nldev_res_get_pd_dumpit,
+ },
+ [RDMA_NLDEV_CMD_SYS_GET] = {
+ .doit = nldev_sys_get_doit,
+ },
+ [RDMA_NLDEV_CMD_SYS_SET] = {
+ .doit = nldev_set_sys_set_doit,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_STAT_SET] = {
+ .doit = nldev_stat_set_doit,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_STAT_GET] = {
+ .doit = nldev_stat_get_doit,
+ .dump = nldev_stat_get_dumpit,
+ },
+ [RDMA_NLDEV_CMD_STAT_DEL] = {
+ .doit = nldev_stat_del_doit,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_RES_QP_GET_RAW] = {
+ .doit = nldev_res_get_qp_raw_doit,
+ .dump = nldev_res_get_qp_raw_dumpit,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_RES_CQ_GET_RAW] = {
+ .doit = nldev_res_get_cq_raw_doit,
+ .dump = nldev_res_get_cq_raw_dumpit,
+ .flags = RDMA_NL_ADMIN_PERM,
+ },
+ [RDMA_NLDEV_CMD_RES_MR_GET_RAW] = {
+ .doit = nldev_res_get_mr_raw_doit,
+ .dump = nldev_res_get_mr_raw_dumpit,
+ .flags = RDMA_NL_ADMIN_PERM,
},
};
@@ -1113,7 +2184,7 @@
rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table);
}
-void __exit nldev_exit(void)
+void nldev_exit(void)
{
rdma_nl_unregister(RDMA_NL_NLDEV);
}
--
Gitblit v1.6.2