Commit 19fd08b8 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "Doug and I are at a conference next week so if another PR is sent I
  expect it to only be bug fixes. Parav noted yesterday that there are
  some fringe case behavior changes in his work that he would like to
  fix, and I see that Intel has a number of rc looking patches for HFI1
  they posted yesterday.

  Parav is again the biggest contributor by patch count with his ongoing
  work to enable container support in the RDMA stack, followed by Leon
  doing syzkaller inspired cleanups, though most of the actual fixing
  went to RC.

  There is one uncomfortable series here fixing the user ABI to actually
  work as intended in 32 bit mode. There are lots of notes in the commit
  messages, but the basic summary is we don't think there is an actual
  32 bit kernel user of drivers/infiniband for several good reasons.

  However we are seeing people want to use a 32 bit user space with 64
  bit kernel, which didn't completely work today. So in fixing it we
  required a 32 bit rxe user to upgrade their userspace. rxe users are
  still already quite rare and we think a 32 bit one is non-existing.

   - Fix RDMA uapi headers to actually compile in userspace and be more
     complete

   - Three shared with netdev pull requests from Mellanox:

      * 7 patches, mostly to net with 1 IB related one at the back).
        This series addresses an IRQ performance issue (patch 1),
        cleanups related to the fix for the IRQ performance problem
        (patches 2-6), and then extends the fragmented completion queue
        support that already exists in the net side of the driver to the
        ib side of the driver (patch 7).

      * Mostly IB, with 5 patches to net that are needed to support the
        remaining 10 patches to the IB subsystem. This series extends
        the current 'representor' framework when the mlx5 driver is in
        switchdev mode from being a netdev only construct to being a
        netdev/IB dev construct. The IB dev is limited to raw Eth queue
        pairs only, but by having an IB dev of this type attached to the
        representor for a switchdev port, it enables DPDK to work on the
        switchdev device.

      * All net related, but needed as infrastructure for the rdma
        driver

   - Updates for the hns, i40iw, bnxt_re, cxgb3, cxgb4, hns drivers

   - SRP performance updates

   - IB uverbs write path cleanup patch series from Leon

   - Add RDMA_CM support to ib_srpt. This is disabled by default. Users
     need to set the port for ib_srpt to listen on in configfs in order
     for it to be enabled
     (/sys/kernel/config/target/srpt/discovery_auth/rdma_cm_port)

   - TSO and Scatter FCS support in mlx4

   - Refactor of modify_qp routine to resolve problems seen while
     working on new code that is forthcoming

   - More refactoring and updates of RDMA CM for containers support from
     Parav

   - mlx5 'fine grained packet pacing', 'ipsec offload' and 'device
     memory' user API features

   - Infrastructure updates for the new IOCTL interface, based on
     increased usage

   - ABI compatibility bug fixes to fully support 32 bit userspace on 64
     bit kernel as was originally intended. See the commit messages for
     extensive details

   - Syzkaller bugs and code cleanups motivated by them"

* tag 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (199 commits)
  IB/rxe: Fix for oops in rxe_register_device on ppc64le arch
  IB/mlx5: Device memory mr registration support
  net/mlx5: Mkey creation command adjustments
  IB/mlx5: Device memory support in mlx5_ib
  net/mlx5: Query device memory capabilities
  IB/uverbs: Add device memory registration ioctl support
  IB/uverbs: Add alloc/free dm uverbs ioctl support
  IB/uverbs: Add device memory capabilities reporting
  IB/uverbs: Expose device memory capabilities to user
  RDMA/qedr: Fix wmb usage in qedr
  IB/rxe: Removed GID add/del dummy routines
  RDMA/qedr: Zero stack memory before copying to user space
  IB/mlx5: Add ability to hash by IPSEC_SPI when creating a TIR
  IB/mlx5: Add information for querying IPsec capabilities
  IB/mlx5: Add IPsec support for egress and ingress
  {net,IB}/mlx5: Add ipsec helper
  IB/mlx5: Add modify_flow_action_esp verb
  IB/mlx5: Add implementation for create and destroy action_xfrm
  IB/uverbs: Introduce ESP steering match filter
  IB/uverbs: Add modify ESP flow_action
  ...
parents 28da7be5 efc365e7
......@@ -102,6 +102,8 @@ Koushik <raghavendra.koushik@neterion.com>
Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
Leonid I Ananiev <leonid.i.ananiev@intel.com>
Linas Vepstas <linas@austin.ibm.com>
Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
......
......@@ -7214,6 +7214,7 @@ M: Shiraz Saleem <shiraz.saleem@intel.com>
L: linux-rdma@vger.kernel.org
S: Supported
F: drivers/infiniband/hw/i40iw/
F: include/uapi/rdma/i40iw-abi.h
INTEL SHA MULTIBUFFER DRIVER
M: Megha Dey <megha.dey@linux.intel.com>
......
......@@ -35,14 +35,13 @@ config INFINIBAND_USER_ACCESS
libibverbs, libibcm and a hardware driver library from
rdma-core <https://github.com/linux-rdma/rdma-core>.
config INFINIBAND_EXP_USER_ACCESS
bool "Enable the full uverbs ioctl interface (EXPERIMENTAL)"
config INFINIBAND_EXP_LEGACY_VERBS_NEW_UAPI
bool "Allow experimental legacy verbs in new ioctl uAPI (EXPERIMENTAL)"
depends on INFINIBAND_USER_ACCESS
---help---
IOCTL based ABI support for Infiniband. This allows userspace
to invoke the experimental IOCTL based ABI.
These commands are parsed via per-device parsing tree and
enables per-device features.
IOCTL based uAPI support for Infiniband is enabled by default for
new verbs only. This allows userspace to invoke the IOCTL based uAPI
for current legacy verbs too.
config INFINIBAND_USER_MEM
bool
......
......@@ -34,4 +34,6 @@ ib_ucm-y := ucm.o
ib_uverbs-y := uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
rdma_core.o uverbs_std_types.o uverbs_ioctl.o \
uverbs_ioctl_merge.o
uverbs_ioctl_merge.o uverbs_std_types_cq.o \
uverbs_std_types_flow_action.o uverbs_std_types_dm.o \
uverbs_std_types_mr.o
......@@ -329,7 +329,8 @@ static void queue_req(struct addr_req *req)
mutex_unlock(&lock);
}
static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
static int ib_nl_fetch_ha(const struct dst_entry *dst,
struct rdma_dev_addr *dev_addr,
const void *daddr, u32 seq, u16 family)
{
if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
......@@ -340,7 +341,8 @@ static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
return ib_nl_ip_send_msg(dev_addr, daddr, seq, family);
}
static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
static int dst_fetch_ha(const struct dst_entry *dst,
struct rdma_dev_addr *dev_addr,
const void *daddr)
{
struct neighbour *n;
......@@ -364,7 +366,7 @@ static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
return ret;
}
static bool has_gateway(struct dst_entry *dst, sa_family_t family)
static bool has_gateway(const struct dst_entry *dst, sa_family_t family)
{
struct rtable *rt;
struct rt6_info *rt6;
......@@ -378,7 +380,7 @@ static bool has_gateway(struct dst_entry *dst, sa_family_t family)
return rt6->rt6i_flags & RTF_GATEWAY;
}
static int fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
static int fetch_ha(const struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
const struct sockaddr *dst_in, u32 seq)
{
const struct sockaddr_in *dst_in4 =
......@@ -482,7 +484,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
}
#endif
static int addr_resolve_neigh(struct dst_entry *dst,
static int addr_resolve_neigh(const struct dst_entry *dst,
const struct sockaddr *dst_in,
struct rdma_dev_addr *addr,
u32 seq)
......@@ -736,7 +738,6 @@ int rdma_resolve_ip_route(struct sockaddr *src_addr,
return addr_resolve(src_in, dst_addr, addr, false, 0);
}
EXPORT_SYMBOL(rdma_resolve_ip_route);
void rdma_addr_cancel(struct rdma_dev_addr *addr)
{
......
This diff is collapsed.
......@@ -462,13 +462,31 @@ static int cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
grh, &av->ah_attr);
}
static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
struct cm_id_private *cm_id_priv)
static int add_cm_id_to_port_list(struct cm_id_private *cm_id_priv,
struct cm_av *av,
struct cm_port *port)
{
unsigned long flags;
int ret = 0;
spin_lock_irqsave(&cm.lock, flags);
if (&cm_id_priv->av == av)
list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list);
else if (&cm_id_priv->alt_av == av)
list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list);
else
ret = -EINVAL;
spin_unlock_irqrestore(&cm.lock, flags);
return ret;
}
static struct cm_port *get_cm_port_from_path(struct sa_path_rec *path)
{
struct cm_device *cm_dev;
struct cm_port *port = NULL;
unsigned long flags;
int ret;
u8 p;
struct net_device *ndev = ib_get_ndev_from_path(path);
......@@ -477,7 +495,7 @@ static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
if (!ib_find_cached_gid(cm_dev->ib_device, &path->sgid,
sa_conv_pathrec_to_gid_type(path),
ndev, &p, NULL)) {
port = cm_dev->port[p-1];
port = cm_dev->port[p - 1];
break;
}
}
......@@ -485,9 +503,20 @@ static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
if (ndev)
dev_put(ndev);
return port;
}
static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
struct cm_id_private *cm_id_priv)
{
struct cm_device *cm_dev;
struct cm_port *port;
int ret;
port = get_cm_port_from_path(path);
if (!port)
return -EINVAL;
cm_dev = port->cm_dev;
ret = ib_find_cached_pkey(cm_dev->ib_device, port->port_num,
be16_to_cpu(path->pkey), &av->pkey_index);
......@@ -502,16 +531,7 @@ static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
av->timeout = path->packet_life_time + 1;
spin_lock_irqsave(&cm.lock, flags);
if (&cm_id_priv->av == av)
list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list);
else if (&cm_id_priv->alt_av == av)
list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list);
else
ret = -EINVAL;
spin_unlock_irqrestore(&cm.lock, flags);
ret = add_cm_id_to_port_list(cm_id_priv, av, port);
return ret;
}
......@@ -1523,6 +1543,8 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
cm_req_get_primary_local_ack_timeout(req_msg);
primary_path->packet_life_time -= (primary_path->packet_life_time > 0);
primary_path->service_id = req_msg->service_id;
if (sa_path_is_roce(primary_path))
primary_path->roce.route_resolved = false;
if (cm_req_has_alt_path(req_msg)) {
alt_path->dgid = req_msg->alt_local_gid;
......@@ -1542,6 +1564,9 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
cm_req_get_alt_local_ack_timeout(req_msg);
alt_path->packet_life_time -= (alt_path->packet_life_time > 0);
alt_path->service_id = req_msg->service_id;
if (sa_path_is_roce(alt_path))
alt_path->roce.route_resolved = false;
}
cm_format_path_lid_from_req(req_msg, primary_path, alt_path);
}
......@@ -3150,6 +3175,13 @@ static int cm_lap_handler(struct cm_work *work)
struct ib_mad_send_buf *msg = NULL;
int ret;
/* Currently Alternate path messages are not supported for
* RoCE link layer.
*/
if (rdma_protocol_roce(work->port->cm_dev->ib_device,
work->port->port_num))
return -EINVAL;
/* todo: verify LAP request and send reject APR if invalid. */
lap_msg = (struct cm_lap_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_id(lap_msg->remote_comm_id,
......@@ -3299,6 +3331,13 @@ static int cm_apr_handler(struct cm_work *work)
struct cm_apr_msg *apr_msg;
int ret;
/* Currently Alternate path messages are not supported for
* RoCE link layer.
*/
if (rdma_protocol_roce(work->port->cm_dev->ib_device,
work->port->port_num))
return -EINVAL;
apr_msg = (struct cm_apr_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_id(apr_msg->remote_comm_id,
apr_msg->local_comm_id);
......
This diff is collapsed.
/*
* Copyright (c) 2005 Voltaire Inc. All rights reserved.
* Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved.
* Copyright (c) 1999-2005, Mellanox Technologies, Inc. All rights reserved.
* Copyright (c) 2005-2006 Intel Corporation. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef _CMA_PRIV_H
#define _CMA_PRIV_H
enum rdma_cm_state {
RDMA_CM_IDLE,
RDMA_CM_ADDR_QUERY,
RDMA_CM_ADDR_RESOLVED,
RDMA_CM_ROUTE_QUERY,
RDMA_CM_ROUTE_RESOLVED,
RDMA_CM_CONNECT,
RDMA_CM_DISCONNECT,
RDMA_CM_ADDR_BOUND,
RDMA_CM_LISTEN,
RDMA_CM_DEVICE_REMOVAL,
RDMA_CM_DESTROYING
};
struct rdma_id_private {
struct rdma_cm_id id;
struct rdma_bind_list *bind_list;
struct hlist_node node;
struct list_head list; /* listen_any_list or cma_device.list */
struct list_head listen_list; /* per device listens */
struct cma_device *cma_dev;
struct list_head mc_list;
int internal_id;
enum rdma_cm_state state;
spinlock_t lock;
struct mutex qp_mutex;
struct completion comp;
atomic_t refcount;
struct mutex handler_mutex;
int backlog;
int timeout_ms;
struct ib_sa_query *query;
int query_id;
union {
struct ib_cm_id *ib;
struct iw_cm_id *iw;
} cm_id;
u32 seq_num;
u32 qkey;
u32 qp_num;
u32 options;
u8 srq;
u8 tos;
bool tos_set;
u8 reuseaddr;
u8 afonly;
enum ib_gid_type gid_type;
/*
* Internal to RDMA/core, don't use in the drivers
*/
struct rdma_restrack_entry res;
};
#endif /* _CMA_PRIV_H */
......@@ -333,4 +333,15 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
return qp;
}
struct rdma_dev_addr;
int rdma_resolve_ip_route(struct sockaddr *src_addr,
const struct sockaddr *dst_addr,
struct rdma_dev_addr *addr);
int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
const union ib_gid *dgid,
u8 *dmac, const struct net_device *ndev,
int *hoplimit);
#endif /* _CORE_PRIV_H */
......@@ -103,7 +103,6 @@ static int ib_device_check_mandatory(struct ib_device *device)
IB_MANDATORY_FUNC(query_device),
IB_MANDATORY_FUNC(query_port),
IB_MANDATORY_FUNC(query_pkey),
IB_MANDATORY_FUNC(query_gid),
IB_MANDATORY_FUNC(alloc_pd),
IB_MANDATORY_FUNC(dealloc_pd),
IB_MANDATORY_FUNC(create_ah),
......@@ -853,7 +852,7 @@ int ib_query_port(struct ib_device *device,
if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND)
return 0;
err = ib_query_gid(device, port_num, 0, &gid, NULL);
err = device->query_gid(device, port_num, 0, &gid);
if (err)
return err;
......@@ -871,19 +870,13 @@ EXPORT_SYMBOL(ib_query_port);
* @attr: Returned GID attributes related to this GID index (only in RoCE).
* NULL means ignore.
*
* ib_query_gid() fetches the specified GID table entry.
* ib_query_gid() fetches the specified GID table entry from the cache.
*/
int ib_query_gid(struct ib_device *device,
u8 port_num, int index, union ib_gid *gid,
struct ib_gid_attr *attr)
{
if (rdma_cap_roce_gid_table(device, port_num))
return ib_get_cached_gid(device, port_num, index, gid, attr);
if (attr)
return -EINVAL;
return device->query_gid(device, port_num, index, gid);
return ib_get_cached_gid(device, port_num, index, gid, attr);
}
EXPORT_SYMBOL(ib_query_gid);
......@@ -1049,19 +1042,18 @@ EXPORT_SYMBOL(ib_modify_port);
* a specified GID value occurs. Its searches only for IB link layer.
* @device: The device to query.
* @gid: The GID value to search for.
* @ndev: The ndev related to the GID to search for.
* @port_num: The port number of the device where the GID value was found.
* @index: The index into the GID table where the GID was found. This
* parameter may be NULL.
*/
int ib_find_gid(struct ib_device *device, union ib_gid *gid,
struct net_device *ndev, u8 *port_num, u16 *index)
u8 *port_num, u16 *index)
{
union ib_gid tmp_gid;
int ret, port, i;
for (port = rdma_start_port(device); port <= rdma_end_port(device); ++port) {
if (rdma_cap_roce_gid_table(device, port))
if (!rdma_protocol_ib(device, port))
continue;
for (i = 0; i < device->port_immutable[port].gid_tbl_len; ++i) {
......
......@@ -439,10 +439,9 @@ struct sk_buff *iwpm_create_nlmsg(u32 nl_op, struct nlmsghdr **nlh,
struct sk_buff *skb = NULL;
skb = dev_alloc_skb(IWPM_MSG_SIZE);
if (!skb) {
pr_err("%s Unable to allocate skb\n", __func__);
if (!skb)
goto create_nlmsg_exit;
}
if (!(ibnl_put_msg(skb, nlh, 0, 0, nl_client, nl_op,
NLM_F_REQUEST))) {
pr_warn("%s: Unable to put the nlmsg header\n", __func__);
......
......@@ -724,21 +724,19 @@ int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num,
{
int ret;
u16 gid_index;
u8 p;
if (rdma_protocol_roce(device, port_num)) {
ret = ib_find_cached_gid_by_port(device, &rec->port_gid,
gid_type, port_num,
ndev,
&gid_index);
} else if (rdma_protocol_ib(device, port_num)) {
ret = ib_find_cached_gid(device, &rec->port_gid,
IB_GID_TYPE_IB, NULL, &p,
&gid_index);
} else {
ret = -EINVAL;
}
/* GID table is not based on the netdevice for IB link layer,
* so ignore ndev during search.
*/
if (rdma_protocol_ib(device, port_num))
ndev = NULL;
else if (!rdma_protocol_roce(device, port_num))
return -EINVAL;
ret = ib_find_cached_gid_by_port(device, &rec->port_gid,
gid_type, port_num,
ndev,
&gid_index);
if (ret)
return ret;
......
This diff is collapsed.
......@@ -350,13 +350,6 @@ struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_obj_type *type,
return type->type_class->alloc_begin(type, ucontext);
}
static void uverbs_uobject_add(struct ib_uobject *uobject)
{
mutex_lock(&uobject->context->uobjects_lock);
list_add(&uobject->list, &uobject->context->uobjects);
mutex_unlock(&uobject->context->uobjects_lock);
}
static int __must_check remove_commit_idr_uobject(struct ib_uobject *uobj,
enum rdma_remove_reason why)
{
......@@ -502,7 +495,6 @@ int rdma_explicit_destroy(struct ib_uobject *uobject)
static void alloc_commit_idr_uobject(struct ib_uobject *uobj)
{
uverbs_uobject_add(uobj);
spin_lock(&uobj->context->ufile->idr_lock);
/*
* We already allocated this IDR with a NULL object, so
......@@ -518,7 +510,6 @@ static void alloc_commit_fd_uobject(struct ib_uobject *uobj)
struct ib_uobject_file *uobj_file =
container_of(uobj, struct ib_uobject_file, uobj);
uverbs_uobject_add(&uobj_file->uobj);
fd_install(uobj_file->uobj.id, uobj->object);
/* This shouldn't be used anymore. Use the file object instead */
uobj_file->uobj.id = 0;
......@@ -545,6 +536,10 @@ int rdma_alloc_commit_uobject(struct ib_uobject *uobj)
assert_uverbs_usecnt(uobj, true);
atomic_set(&uobj->usecnt, 0);
mutex_lock(&uobj->context->uobjects_lock);
list_add(&uobj->list, &uobj->context->uobjects);
mutex_unlock(&uobj->context->uobjects_lock);
uobj->type->type_class->alloc_commit(uobj);
up_read(&uobj->context->cleanup_rwsem);
......
......@@ -3,20 +3,66 @@
* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
*/
#include <rdma/rdma_cm.h>
#include <rdma/ib_verbs.h>
#include <rdma/restrack.h>
#include <linux/mutex.h>
#include <linux/sched/task.h>
#include <linux/pid_namespace.h>
#include "cma_priv.h"
void rdma_restrack_init(struct rdma_restrack_root *res)
{
init_rwsem(&res->rwsem);
}
static const char *type2str(enum rdma_restrack_type type)
{
static const char * const names[RDMA_RESTRACK_MAX] = {
[RDMA_RESTRACK_PD] = "PD",
[RDMA_RESTRACK_CQ] = "CQ",
[RDMA_RESTRACK_QP] = "QP",
[RDMA_RESTRACK_CM_ID] = "CM_ID",
[RDMA_RESTRACK_MR] = "MR",
};
return names[type];
};
void rdma_restrack_clean(struct rdma_restrack_root *res)
{
WARN_ON_ONCE(!hash_empty(res->hash));
struct rdma_restrack_entry *e;
char buf[TASK_COMM_LEN];
struct ib_device *dev;
const char *owner;
int bkt;
if (hash_empty(res->hash))
return;
dev = container_of(res, struct ib_device, res);
pr_err("restrack: %s", CUT_HERE);
pr_err("restrack: BUG: RESTRACK detected leak of resources on %s\n",
dev->name);
hash_for_each(res->hash, bkt, e, node) {
if (rdma_is_kernel_res(e)) {
owner = e->kern_name;
} else {
/*
* There is no need to call get_task_struct here,
* because we can be here only if there are more
* get_task_struct() call than put_task_struct().
*/
get_task_comm(buf, e->task);
owner = buf;
}
pr_err("restrack: %s %s object allocated by %s is not freed\n",
rdma_is_kernel_res(e) ? "Kernel" : "User",
type2str(e->type), owner);
}
pr_err("restrack: %s", CUT_HERE);
}
int rdma_restrack_count(struct rdma_restrack_root *res,
......@@ -40,51 +86,48 @@ EXPORT_SYMBOL(rdma_restrack_count);
static void set_kern_name(struct rdma_restrack_entry *res)
{
enum rdma_restrack_type type = res->type;
struct ib_qp *qp;
if (type != RDMA_RESTRACK_QP)
/* PD and CQ types already have this name embedded in */
return;
struct ib_pd *pd;
qp = container_of(res, struct ib_qp, res);
if (!qp->pd) {
WARN_ONCE(true, "XRC QPs are not supported\n");
/* Survive, despite the programmer's error */
res->kern_name = " ";
return;
switch (res->type) {
case RDMA_RESTRACK_QP:
pd = container_of(res, struct ib_qp, res)->pd;
if (!pd) {
WARN_ONCE(true, "XRC QPs are not supported\n");
/* Survive, despite the programmer's error */
res->kern_name = " ";
}
break;
case RDMA_RESTRACK_MR:
pd = container_of(res, struct ib_mr, res)->pd;
break;
default:
/* Other types set kern_name directly */
pd = NULL;
break;
}
res->kern_name = qp->pd->res.kern_name;
if (pd)
res->kern_name = pd->res.kern_name;
}
static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
{
enum rdma_restrack_type type = res->type;
struct ib_device *dev;
struct ib_pd *pd;
struct ib_cq *cq;
struct ib_qp *qp;
switch (type) {
switch (res->type) {
case RDMA_RESTRACK_PD:
pd = container_of(res, struct ib_pd, res);
dev = pd->device;
break;
return container_of(res, struct ib_pd, res)->device;
case RDMA_RESTRACK_CQ:
cq = container_of(res, struct ib_cq, res);
dev = cq->device;
break;
return container_of(res, struct ib_cq, res)->device;
case RDMA_RESTRACK_QP:
qp = container_of(res, struct ib_qp, res);
dev = qp->device;
break;
return container_of(res, struct ib_qp, res)->device;
case RDMA_RESTRACK_CM_ID:
return container_of(res, struct rdma_id_private,
res)->id.device;
case RDMA_RESTRACK_MR:
return container_of(res, struct ib_mr, res)->device;
default:
WARN_ONCE(true, "Wrong resource tracking type %u\n", type);
WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);
return NULL;
}
return dev;
}
static bool res_is_user(struct rdma_restrack_entry *res)
......@@ -96,6 +139,10 @@ static bool res_is_user(struct rdma_restrack_entry *res)
return container_of(res, struct ib_cq, res)->uobject;
case RDMA_RESTRACK_QP:
return container_of(res, struct ib_qp, res)->uobject;
case RDMA_RESTRACK_CM_ID:
return !res->kern_name;
case RDMA_RESTRACK_MR:
return container_of(res, struct ib_mr, res)->pd->uobject;
default:
WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);
return false;
......@@ -109,13 +156,15 @@ void rdma_restrack_add(struct rdma_restrack_entry *res)
if (!dev)