* [PATCH][v3][0/21] Initial submission of InfiniBand patches for review
@ 2004-12-13 18:09 Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][1/21] Add core InfiniBand support (public headers) Roland Dreier
0 siblings, 1 reply; 5+ messages in thread
From: Roland Dreier @ 2004-12-13 18:09 UTC (permalink / raw)
To: linux-kernel; +Cc: openib-general
The following series of patches is the latest version of the OpenIB
InfiniBand drivers. We believe that this version is suitable for
merging when 2.6.11 opens (or into -mm immediately), although of
course we are willing to go through as many more iterations as
required to fix any remaining issues.
We appreciate all of the excellent feedback we received for our
previous posting, and we believe we have addressed all of the problems
that were identified. We did not intentionally ignore any issues --
if we did not address some of your comments, please rest assured that
it was an error on our part.
Based on the discussion on cleaning up kernel headers, we have left
our .h files under drivers/infiniband/include. None of these .h files
are used outside of drivers/infiniband, so it seems that it is better
not to add them to the global include/ namespace.
Thanks,
Roland Dreier
OpenIB Alliance
www.openib.org
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH][v3][1/21] Add core InfiniBand support (public headers)
2004-12-13 18:09 [PATCH][v3][0/21] Initial submission of InfiniBand patches for review Roland Dreier
@ 2004-12-13 18:09 ` Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][2/21] Add core InfiniBand support Roland Dreier
0 siblings, 1 reply; 5+ messages in thread
From: Roland Dreier @ 2004-12-13 18:09 UTC (permalink / raw)
To: linux-kernel; +Cc: openib-general
Add public headers for core InfiniBand support. This can be thought
of as a midlayer that provides an abstraction between low-level
hardware drivers and upper level protocols (such as
IP-over-InfiniBand).
Signed-off-by: Roland Dreier <roland@topspin.com>
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/include/ib_cache.h 2004-12-13 09:44:39.409919591 -0800
@@ -0,0 +1,42 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Communications. All rights reserved.
+ *
+ * $Id: ib_cache.h 1288 2004-11-24 01:12:39Z roland $
+ */
+
+#ifndef _IB_CACHE_H
+#define _IB_CACHE_H
+
+#include <ib_verbs.h>
+
+int ib_cached_gid_get(struct ib_device *device,
+ u8 port,
+ int index,
+ union ib_gid *gid);
+int ib_cached_pkey_get(struct ib_device *device_handle,
+ u8 port,
+ int index,
+ u16 *pkey);
+int ib_cached_pkey_find(struct ib_device *device,
+ u8 port,
+ u16 pkey,
+ u16 *index);
+
+#endif /* _IB_CACHE_H */
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/include/ib_fmr_pool.h 2004-12-13 09:44:39.435915761 -0800
@@ -0,0 +1,81 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ *
+ * $Id: ib_fmr_pool.h 1295 2004-11-25 19:26:33Z roland $
+ */
+
+#if !defined(IB_FMR_POOL_H)
+#define IB_FMR_POOL_H
+
+#include <ib_verbs.h>
+
+struct ib_fmr_pool;
+
+/**
+ * struct ib_fmr_pool_param - Parameters for creating FMR pool
+ * @max_pages_per_fmr:Maximum number of pages per map request.
+ * @access:Access flags for FMRs in pool.
+ * @pool_size:Number of FMRs to allocate for pool.
+ * @dirty_watermark:Flush is triggered when @dirty_watermark dirty
+ * FMRs are present.
+ * @flush_function:Callback called when unmapped FMRs are flushed and
+ * more FMRs are possibly available for mapping
+ * @flush_arg:Context passed to user's flush function.
+ * @cache:If set, FMRs may be reused after unmapping for identical map
+ * requests.
+ */
+struct ib_fmr_pool_param {
+ int max_pages_per_fmr;
+ enum ib_access_flags access;
+ int pool_size;
+ int dirty_watermark;
+ void (*flush_function)(struct ib_fmr_pool *pool,
+ void * arg);
+ void *flush_arg;
+ unsigned cache:1;
+};
+
+struct ib_pool_fmr {
+ struct ib_fmr *fmr;
+ struct ib_fmr_pool *pool;
+ struct list_head list;
+ struct hlist_node cache_node;
+ int ref_count;
+ int remap_count;
+ u64 io_virtual_address;
+ int page_list_len;
+ u64 page_list[0];
+};
+
+struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd *pd,
+ struct ib_fmr_pool_param *params);
+
+int ib_destroy_fmr_pool(struct ib_fmr_pool *pool);
+
+int ib_flush_fmr_pool(struct ib_fmr_pool *pool);
+
+struct ib_pool_fmr *ib_fmr_pool_map_phys(struct ib_fmr_pool *pool_handle,
+ u64 *page_list,
+ int list_len,
+ u64 *io_virtual_address);
+
+int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr);
+
+#endif /* IB_FMR_POOL_H */
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/include/ib_pack.h 2004-12-13 09:44:39.467911048 -0800
@@ -0,0 +1,234 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ *
+ * $Id: ib_pack.h 1288 2004-11-24 01:12:39Z roland $
+ */
+
+#ifndef IB_PACK_H
+#define IB_PACK_H
+
+#include <ib_verbs.h>
+
+enum {
+ IB_LRH_BYTES = 8,
+ IB_GRH_BYTES = 40,
+ IB_BTH_BYTES = 12,
+ IB_DETH_BYTES = 8
+};
+
+struct ib_field {
+ size_t struct_offset_bytes;
+ size_t struct_size_bytes;
+ int offset_words;
+ int offset_bits;
+ int size_bits;
+ char *field_name;
+};
+
+#define RESERVED \
+ .field_name = "reserved"
+
+/*
+ * This macro cleans up the definitions of constants for BTH opcodes.
+ * It is used to define constants such as IB_OPCODE_UD_SEND_ONLY,
+ * which becomes IB_OPCODE_UD + IB_OPCODE_SEND_ONLY, and this gives
+ * the correct value.
+ *
+ * In short, user code should use the constants defined using the
+ * macro rather than worrying about adding together other constants.
+*/
+#define IB_OPCODE(transport, op) \
+ IB_OPCODE_ ## transport ## _ ## op = \
+ IB_OPCODE_ ## transport + IB_OPCODE_ ## op
+
+enum {
+ /* transport types -- just used to define real constants */
+ IB_OPCODE_RC = 0x00,
+ IB_OPCODE_UC = 0x20,
+ IB_OPCODE_RD = 0x40,
+ IB_OPCODE_UD = 0x60,
+
+ /* operations -- just used to define real constants */
+ IB_OPCODE_SEND_FIRST = 0x00,
+ IB_OPCODE_SEND_MIDDLE = 0x01,
+ IB_OPCODE_SEND_LAST = 0x02,
+ IB_OPCODE_SEND_LAST_WITH_IMMEDIATE = 0x03,
+ IB_OPCODE_SEND_ONLY = 0x04,
+ IB_OPCODE_SEND_ONLY_WITH_IMMEDIATE = 0x05,
+ IB_OPCODE_RDMA_WRITE_FIRST = 0x06,
+ IB_OPCODE_RDMA_WRITE_MIDDLE = 0x07,
+ IB_OPCODE_RDMA_WRITE_LAST = 0x08,
+ IB_OPCODE_RDMA_WRITE_LAST_WITH_IMMEDIATE = 0x09,
+ IB_OPCODE_RDMA_WRITE_ONLY = 0x0a,
+ IB_OPCODE_RDMA_WRITE_ONLY_WITH_IMMEDIATE = 0x0b,
+ IB_OPCODE_RDMA_READ_REQUEST = 0x0c,
+ IB_OPCODE_RDMA_READ_RESPONSE_FIRST = 0x0d,
+ IB_OPCODE_RDMA_READ_RESPONSE_MIDDLE = 0x0e,
+ IB_OPCODE_RDMA_READ_RESPONSE_LAST = 0x0f,
+ IB_OPCODE_RDMA_READ_RESPONSE_ONLY = 0x10,
+ IB_OPCODE_ACKNOWLEDGE = 0x11,
+ IB_OPCODE_ATOMIC_ACKNOWLEDGE = 0x12,
+ IB_OPCODE_COMPARE_SWAP = 0x13,
+ IB_OPCODE_FETCH_ADD = 0x14,
+
+ /* real constants follow -- see comment about above IB_OPCODE()
+ macro for more details */
+
+ /* RC */
+ IB_OPCODE(RC, SEND_FIRST),
+ IB_OPCODE(RC, SEND_MIDDLE),
+ IB_OPCODE(RC, SEND_LAST),
+ IB_OPCODE(RC, SEND_LAST_WITH_IMMEDIATE),
+ IB_OPCODE(RC, SEND_ONLY),
+ IB_OPCODE(RC, SEND_ONLY_WITH_IMMEDIATE),
+ IB_OPCODE(RC, RDMA_WRITE_FIRST),
+ IB_OPCODE(RC, RDMA_WRITE_MIDDLE),
+ IB_OPCODE(RC, RDMA_WRITE_LAST),
+ IB_OPCODE(RC, RDMA_WRITE_LAST_WITH_IMMEDIATE),
+ IB_OPCODE(RC, RDMA_WRITE_ONLY),
+ IB_OPCODE(RC, RDMA_WRITE_ONLY_WITH_IMMEDIATE),
+ IB_OPCODE(RC, RDMA_READ_REQUEST),
+ IB_OPCODE(RC, RDMA_READ_RESPONSE_FIRST),
+ IB_OPCODE(RC, RDMA_READ_RESPONSE_MIDDLE),
+ IB_OPCODE(RC, RDMA_READ_RESPONSE_LAST),
+ IB_OPCODE(RC, RDMA_READ_RESPONSE_ONLY),
+ IB_OPCODE(RC, ACKNOWLEDGE),
+ IB_OPCODE(RC, ATOMIC_ACKNOWLEDGE),
+ IB_OPCODE(RC, COMPARE_SWAP),
+ IB_OPCODE(RC, FETCH_ADD),
+
+ /* UC */
+ IB_OPCODE(UC, SEND_FIRST),
+ IB_OPCODE(UC, SEND_MIDDLE),
+ IB_OPCODE(UC, SEND_LAST),
+ IB_OPCODE(UC, SEND_LAST_WITH_IMMEDIATE),
+ IB_OPCODE(UC, SEND_ONLY),
+ IB_OPCODE(UC, SEND_ONLY_WITH_IMMEDIATE),
+ IB_OPCODE(UC, RDMA_WRITE_FIRST),
+ IB_OPCODE(UC, RDMA_WRITE_MIDDLE),
+ IB_OPCODE(UC, RDMA_WRITE_LAST),
+ IB_OPCODE(UC, RDMA_WRITE_LAST_WITH_IMMEDIATE),
+ IB_OPCODE(UC, RDMA_WRITE_ONLY),
+ IB_OPCODE(UC, RDMA_WRITE_ONLY_WITH_IMMEDIATE),
+
+ /* RD */
+ IB_OPCODE(RD, SEND_FIRST),
+ IB_OPCODE(RD, SEND_MIDDLE),
+ IB_OPCODE(RD, SEND_LAST),
+ IB_OPCODE(RD, SEND_LAST_WITH_IMMEDIATE),
+ IB_OPCODE(RD, SEND_ONLY),
+ IB_OPCODE(RD, SEND_ONLY_WITH_IMMEDIATE),
+ IB_OPCODE(RD, RDMA_WRITE_FIRST),
+ IB_OPCODE(RD, RDMA_WRITE_MIDDLE),
+ IB_OPCODE(RD, RDMA_WRITE_LAST),
+ IB_OPCODE(RD, RDMA_WRITE_LAST_WITH_IMMEDIATE),
+ IB_OPCODE(RD, RDMA_WRITE_ONLY),
+ IB_OPCODE(RD, RDMA_WRITE_ONLY_WITH_IMMEDIATE),
+ IB_OPCODE(RD, RDMA_READ_REQUEST),
+ IB_OPCODE(RD, RDMA_READ_RESPONSE_FIRST),
+ IB_OPCODE(RD, RDMA_READ_RESPONSE_MIDDLE),
+ IB_OPCODE(RD, RDMA_READ_RESPONSE_LAST),
+ IB_OPCODE(RD, RDMA_READ_RESPONSE_ONLY),
+ IB_OPCODE(RD, ACKNOWLEDGE),
+ IB_OPCODE(RD, ATOMIC_ACKNOWLEDGE),
+ IB_OPCODE(RD, COMPARE_SWAP),
+ IB_OPCODE(RD, FETCH_ADD),
+
+ /* UD */
+ IB_OPCODE(UD, SEND_ONLY),
+ IB_OPCODE(UD, SEND_ONLY_WITH_IMMEDIATE)
+};
+
+enum {
+ IB_LNH_RAW = 0,
+ IB_LNH_IP = 1,
+ IB_LNH_IBA_LOCAL = 2,
+ IB_LNH_IBA_GLOBAL = 3
+};
+
+struct ib_unpacked_lrh {
+ u8 virtual_lane;
+ u8 link_version;
+ u8 service_level;
+ u8 link_next_header;
+ __be16 destination_lid;
+ __be16 packet_length;
+ __be16 source_lid;
+};
+
+struct ib_unpacked_grh {
+ u8 ip_version;
+ u8 traffic_class;
+ __be32 flow_label;
+ __be16 payload_length;
+ u8 next_header;
+ u8 hop_limit;
+ union ib_gid source_gid;
+ union ib_gid destination_gid;
+};
+
+struct ib_unpacked_bth {
+ u8 opcode;
+ u8 solicited_event;
+ u8 mig_req;
+ u8 pad_count;
+ u8 transport_header_version;
+ __be16 pkey;
+ __be32 destination_qpn;
+ u8 ack_req;
+ __be32 psn;
+};
+
+struct ib_unpacked_deth {
+ __be32 qkey;
+ __be32 source_qpn;
+};
+
+struct ib_ud_header {
+ struct ib_unpacked_lrh lrh;
+ int grh_present;
+ struct ib_unpacked_grh grh;
+ struct ib_unpacked_bth bth;
+ struct ib_unpacked_deth deth;
+ int immediate_present;
+ __be32 immediate_data;
+};
+
+void ib_pack(const struct ib_field *desc,
+ int desc_len,
+ void *structure,
+ void *buf);
+
+void ib_unpack(const struct ib_field *desc,
+ int desc_len,
+ void *buf,
+ void *structure);
+
+void ib_ud_header_init(int payload_bytes,
+ int grh_present,
+ struct ib_ud_header *header);
+
+int ib_ud_header_pack(struct ib_ud_header *header,
+ void *buf);
+
+int ib_ud_header_unpack(void *buf,
+ struct ib_ud_header *header);
+
+#endif /* IB_PACK_H */
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/include/ib_verbs.h 2004-12-13 09:44:39.495906923 -0800
@@ -0,0 +1,1225 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved.
+ * Copyright (c) 2004 Infinicon Corporation. All rights reserved.
+ * Copyright (c) 2004 Intel Corporation. All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation. All rights reserved.
+ *
+ * $Id: ib_verbs.h 1304 2004-11-30 19:01:25Z sean.hefty $
+ */
+
+#if !defined(IB_VERBS_H)
+#define IB_VERBS_H
+
+#include <linux/types.h>
+#include <linux/device.h>
+#include <asm/atomic.h>
+
+union ib_gid {
+ u8 raw[16];
+ struct {
+ u64 subnet_prefix;
+ u64 interface_id;
+ } global;
+};
+
+enum ib_node_type {
+ IB_NODE_CA = 1,
+ IB_NODE_SWITCH,
+ IB_NODE_ROUTER
+};
+
+enum ib_device_cap_flags {
+ IB_DEVICE_RESIZE_MAX_WR = 1,
+ IB_DEVICE_BAD_PKEY_CNTR = (1<<1),
+ IB_DEVICE_BAD_QKEY_CNTR = (1<<2),
+ IB_DEVICE_RAW_MULTI = (1<<3),
+ IB_DEVICE_AUTO_PATH_MIG = (1<<4),
+ IB_DEVICE_CHANGE_PHY_PORT = (1<<5),
+ IB_DEVICE_UD_AV_PORT_ENFORCE = (1<<6),
+ IB_DEVICE_CURR_QP_STATE_MOD = (1<<7),
+ IB_DEVICE_SHUTDOWN_PORT = (1<<8),
+ IB_DEVICE_INIT_TYPE = (1<<9),
+ IB_DEVICE_PORT_ACTIVE_EVENT = (1<<10),
+ IB_DEVICE_SYS_IMAGE_GUID = (1<<11),
+ IB_DEVICE_RC_RNR_NAK_GEN = (1<<12),
+ IB_DEVICE_SRQ_RESIZE = (1<<13),
+ IB_DEVICE_N_NOTIFY_CQ = (1<<14),
+ IB_DEVICE_RQ_SIG_TYPE = (1<<15)
+};
+
+enum ib_atomic_cap {
+ IB_ATOMIC_NONE,
+ IB_ATOMIC_HCA,
+ IB_ATOMIC_GLOB
+};
+
+struct ib_device_attr {
+ u64 fw_ver;
+ u64 node_guid;
+ u64 sys_image_guid;
+ u64 max_mr_size;
+ u64 page_size_cap;
+ u32 vendor_id;
+ u32 vendor_part_id;
+ u32 hw_ver;
+ int max_qp;
+ int max_qp_wr;
+ int device_cap_flags;
+ int max_sge;
+ int max_sge_rd;
+ int max_cq;
+ int max_cqe;
+ int max_mr;
+ int max_pd;
+ int max_qp_rd_atom;
+ int max_ee_rd_atom;
+ int max_res_rd_atom;
+ int max_qp_init_rd_atom;
+ int max_ee_init_rd_atom;
+ enum ib_atomic_cap atomic_cap;
+ int max_ee;
+ int max_rdd;
+ int max_mw;
+ int max_raw_ipv6_qp;
+ int max_raw_ethy_qp;
+ int max_mcast_grp;
+ int max_mcast_qp_attach;
+ int max_total_mcast_qp_attach;
+ int max_ah;
+ int max_fmr;
+ int max_map_per_fmr;
+ int max_srq;
+ int max_srq_wr;
+ int max_srq_sge;
+ u16 max_pkeys;
+ u8 local_ca_ack_delay;
+};
+
+enum ib_mtu {
+ IB_MTU_256 = 1,
+ IB_MTU_512 = 2,
+ IB_MTU_1024 = 3,
+ IB_MTU_2048 = 4,
+ IB_MTU_4096 = 5
+};
+
+static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
+{
+ switch (mtu) {
+ case IB_MTU_256: return 256;
+ case IB_MTU_512: return 512;
+ case IB_MTU_1024: return 1024;
+ case IB_MTU_2048: return 2048;
+ case IB_MTU_4096: return 4096;
+ default: return -1;
+ }
+}
+
+enum ib_static_rate {
+ IB_STATIC_RATE_FULL = 0,
+ IB_STATIC_RATE_12X_TO_4X = 2,
+ IB_STATIC_RATE_4X_TO_1X = 3,
+ IB_STATIC_RATE_12X_TO_1X = 11
+};
+
+enum ib_port_state {
+ IB_PORT_NOP = 0,
+ IB_PORT_DOWN = 1,
+ IB_PORT_INIT = 2,
+ IB_PORT_ARMED = 3,
+ IB_PORT_ACTIVE = 4,
+ IB_PORT_ACTIVE_DEFER = 5
+};
+
+enum ib_port_cap_flags {
+ IB_PORT_SM = (1<<31),
+ IB_PORT_NOTICE_SUP = (1<<30),
+ IB_PORT_TRAP_SUP = (1<<29),
+ IB_PORT_AUTO_MIGR_SUP = (1<<27),
+ IB_PORT_SL_MAP_SUP = (1<<26),
+ IB_PORT_MKEY_NVRAM = (1<<25),
+ IB_PORT_PKEY_NVRAM = (1<<24),
+ IB_PORT_LED_INFO_SUP = (1<<23),
+ IB_PORT_SM_DISABLED = (1<<22),
+ IB_PORT_SYS_IMAGE_GUID_SUP = (1<<21),
+ IB_PORT_PKEY_SW_EXT_PORT_TRAP_SUP = (1<<20),
+ IB_PORT_CM_SUP = (1<<16),
+ IB_PORT_SNMP_TUNNEL_SUP = (1<<15),
+ IB_PORT_REINIT_SUP = (1<<14),
+ IB_PORT_DEVICE_MGMT_SUP = (1<<13),
+ IB_PORT_VENDOR_CLASS_SUP = (1<<12),
+ IB_PORT_DR_NOTICE_SUP = (1<<11),
+ IB_PORT_PORT_NOTICE_SUP = (1<<10),
+ IB_PORT_BOOT_MGMT_SUP = (1<<9)
+};
+
+struct ib_port_attr {
+ enum ib_port_state state;
+ enum ib_mtu max_mtu;
+ enum ib_mtu active_mtu;
+ int gid_tbl_len;
+ u32 port_cap_flags;
+ u32 max_msg_sz;
+ u32 bad_pkey_cntr;
+ u32 qkey_viol_cntr;
+ u16 pkey_tbl_len;
+ u16 lid;
+ u16 sm_lid;
+ u8 lmc;
+ u8 max_vl_num;
+ u8 sm_sl;
+ u8 subnet_timeout;
+ u8 init_type_reply;
+};
+
+enum ib_device_modify_flags {
+ IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1
+};
+
+struct ib_device_modify {
+ u64 sys_image_guid;
+};
+
+enum ib_port_modify_flags {
+ IB_PORT_SHUTDOWN = 1,
+ IB_PORT_INIT_TYPE = (1<<2),
+ IB_PORT_RESET_QKEY_CNTR = (1<<3)
+};
+
+struct ib_port_modify {
+ u32 set_port_cap_mask;
+ u32 clr_port_cap_mask;
+ u8 init_type;
+};
+
+enum ib_event_type {
+ IB_EVENT_CQ_ERR,
+ IB_EVENT_QP_FATAL,
+ IB_EVENT_QP_REQ_ERR,
+ IB_EVENT_QP_ACCESS_ERR,
+ IB_EVENT_COMM_EST,
+ IB_EVENT_SQ_DRAINED,
+ IB_EVENT_PATH_MIG,
+ IB_EVENT_PATH_MIG_ERR,
+ IB_EVENT_DEVICE_FATAL,
+ IB_EVENT_PORT_ACTIVE,
+ IB_EVENT_PORT_ERR,
+ IB_EVENT_LID_CHANGE,
+ IB_EVENT_PKEY_CHANGE,
+ IB_EVENT_SM_CHANGE
+};
+
+struct ib_event {
+ struct ib_device *device;
+ union {
+ struct ib_cq *cq;
+ struct ib_qp *qp;
+ u8 port_num;
+ } element;
+ enum ib_event_type event;
+};
+
+struct ib_event_handler {
+ struct ib_device *device;
+ void (*handler)(struct ib_event_handler *, struct ib_event *);
+ struct list_head list;
+};
+
+#define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \
+ do { \
+ (_ptr)->device = _device; \
+ (_ptr)->handler = _handler; \
+ INIT_LIST_HEAD(&(_ptr)->list); \
+ } while (0)
+
+struct ib_global_route {
+ union ib_gid dgid;
+ u32 flow_label;
+ u8 sgid_index;
+ u8 hop_limit;
+ u8 traffic_class;
+};
+
+enum {
+ IB_MULTICAST_QPN = 0xffffff
+};
+
+enum ib_ah_flags {
+ IB_AH_GRH = 1
+};
+
+struct ib_ah_attr {
+ struct ib_global_route grh;
+ u16 dlid;
+ u8 sl;
+ u8 src_path_bits;
+ u8 static_rate;
+ u8 ah_flags;
+ u8 port_num;
+};
+
+enum ib_wc_status {
+ IB_WC_SUCCESS,
+ IB_WC_LOC_LEN_ERR,
+ IB_WC_LOC_QP_OP_ERR,
+ IB_WC_LOC_EEC_OP_ERR,
+ IB_WC_LOC_PROT_ERR,
+ IB_WC_WR_FLUSH_ERR,
+ IB_WC_MW_BIND_ERR,
+ IB_WC_BAD_RESP_ERR,
+ IB_WC_LOC_ACCESS_ERR,
+ IB_WC_REM_INV_REQ_ERR,
+ IB_WC_REM_ACCESS_ERR,
+ IB_WC_REM_OP_ERR,
+ IB_WC_RETRY_EXC_ERR,
+ IB_WC_RNR_RETRY_EXC_ERR,
+ IB_WC_LOC_RDD_VIOL_ERR,
+ IB_WC_REM_INV_RD_REQ_ERR,
+ IB_WC_REM_ABORT_ERR,
+ IB_WC_INV_EECN_ERR,
+ IB_WC_INV_EEC_STATE_ERR,
+ IB_WC_FATAL_ERR,
+ IB_WC_RESP_TIMEOUT_ERR,
+ IB_WC_GENERAL_ERR
+};
+
+enum ib_wc_opcode {
+ IB_WC_SEND,
+ IB_WC_RDMA_WRITE,
+ IB_WC_RDMA_READ,
+ IB_WC_COMP_SWAP,
+ IB_WC_FETCH_ADD,
+ IB_WC_BIND_MW,
+/*
+ * Set value of IB_WC_RECV so consumers can test if a completion is a
+ * receive by testing (opcode & IB_WC_RECV).
+ */
+ IB_WC_RECV = 1 << 7,
+ IB_WC_RECV_RDMA_WITH_IMM
+};
+
+enum ib_wc_flags {
+ IB_WC_GRH = 1,
+ IB_WC_WITH_IMM = (1<<1)
+};
+
+struct ib_wc {
+ u64 wr_id;
+ enum ib_wc_status status;
+ enum ib_wc_opcode opcode;
+ u32 vendor_err;
+ u32 byte_len;
+ __be32 imm_data;
+ u32 src_qp;
+ int wc_flags;
+ u16 pkey_index;
+ u16 slid;
+ u8 sl;
+ u8 dlid_path_bits;
+ u8 port_num; /* valid only for DR SMPs on switches */
+};
+
+enum ib_cq_notify {
+ IB_CQ_SOLICITED,
+ IB_CQ_NEXT_COMP
+};
+
+struct ib_qp_cap {
+ u32 max_send_wr;
+ u32 max_recv_wr;
+ u32 max_send_sge;
+ u32 max_recv_sge;
+ u32 max_inline_data;
+};
+
+enum ib_sig_type {
+ IB_SIGNAL_ALL_WR,
+ IB_SIGNAL_REQ_WR
+};
+
+enum ib_qp_type {
+ /*
+ * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries
+ * here (and in that order) since the MAD layer uses them as
+ * indices into a 2-entry table.
+ */
+ IB_QPT_SMI,
+ IB_QPT_GSI,
+
+ IB_QPT_RC,
+ IB_QPT_UC,
+ IB_QPT_UD,
+ IB_QPT_RAW_IPV6,
+ IB_QPT_RAW_ETY
+};
+
+struct ib_qp_init_attr {
+ void (*event_handler)(struct ib_event *, void *);
+ void *qp_context;
+ struct ib_cq *send_cq;
+ struct ib_cq *recv_cq;
+ struct ib_srq *srq;
+ struct ib_qp_cap cap;
+ enum ib_sig_type sq_sig_type;
+ enum ib_sig_type rq_sig_type;
+ enum ib_qp_type qp_type;
+ u8 port_num; /* special QP types only */
+};
+
+enum ib_rnr_timeout {
+ IB_RNR_TIMER_655_36 = 0,
+ IB_RNR_TIMER_000_01 = 1,
+ IB_RNR_TIMER_000_02 = 2,
+ IB_RNR_TIMER_000_03 = 3,
+ IB_RNR_TIMER_000_04 = 4,
+ IB_RNR_TIMER_000_06 = 5,
+ IB_RNR_TIMER_000_08 = 6,
+ IB_RNR_TIMER_000_12 = 7,
+ IB_RNR_TIMER_000_16 = 8,
+ IB_RNR_TIMER_000_24 = 9,
+ IB_RNR_TIMER_000_32 = 10,
+ IB_RNR_TIMER_000_48 = 11,
+ IB_RNR_TIMER_000_64 = 12,
+ IB_RNR_TIMER_000_96 = 13,
+ IB_RNR_TIMER_001_28 = 14,
+ IB_RNR_TIMER_001_92 = 15,
+ IB_RNR_TIMER_002_56 = 16,
+ IB_RNR_TIMER_003_84 = 17,
+ IB_RNR_TIMER_005_12 = 18,
+ IB_RNR_TIMER_007_68 = 19,
+ IB_RNR_TIMER_010_24 = 20,
+ IB_RNR_TIMER_015_36 = 21,
+ IB_RNR_TIMER_020_48 = 22,
+ IB_RNR_TIMER_030_72 = 23,
+ IB_RNR_TIMER_040_96 = 24,
+ IB_RNR_TIMER_061_44 = 25,
+ IB_RNR_TIMER_081_92 = 26,
+ IB_RNR_TIMER_122_88 = 27,
+ IB_RNR_TIMER_163_84 = 28,
+ IB_RNR_TIMER_245_76 = 29,
+ IB_RNR_TIMER_327_68 = 30,
+ IB_RNR_TIMER_491_52 = 31
+};
+
+enum ib_qp_attr_mask {
+ IB_QP_STATE = 1,
+ IB_QP_CUR_STATE = (1<<1),
+ IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2),
+ IB_QP_ACCESS_FLAGS = (1<<3),
+ IB_QP_PKEY_INDEX = (1<<4),
+ IB_QP_PORT = (1<<5),
+ IB_QP_QKEY = (1<<6),
+ IB_QP_AV = (1<<7),
+ IB_QP_PATH_MTU = (1<<8),
+ IB_QP_TIMEOUT = (1<<9),
+ IB_QP_RETRY_CNT = (1<<10),
+ IB_QP_RNR_RETRY = (1<<11),
+ IB_QP_RQ_PSN = (1<<12),
+ IB_QP_MAX_QP_RD_ATOMIC = (1<<13),
+ IB_QP_ALT_PATH = (1<<14),
+ IB_QP_MIN_RNR_TIMER = (1<<15),
+ IB_QP_SQ_PSN = (1<<16),
+ IB_QP_MAX_DEST_RD_ATOMIC = (1<<17),
+ IB_QP_PATH_MIG_STATE = (1<<18),
+ IB_QP_CAP = (1<<19),
+ IB_QP_DEST_QPN = (1<<20)
+};
+
+enum ib_qp_state {
+ IB_QPS_RESET,
+ IB_QPS_INIT,
+ IB_QPS_RTR,
+ IB_QPS_RTS,
+ IB_QPS_SQD,
+ IB_QPS_SQE,
+ IB_QPS_ERR
+};
+
+enum ib_mig_state {
+ IB_MIG_MIGRATED,
+ IB_MIG_REARM,
+ IB_MIG_ARMED
+};
+
+struct ib_qp_attr {
+ enum ib_qp_state qp_state;
+ enum ib_qp_state cur_qp_state;
+ enum ib_mtu path_mtu;
+ enum ib_mig_state path_mig_state;
+ u32 qkey;
+ u32 rq_psn;
+ u32 sq_psn;
+ u32 dest_qp_num;
+ int qp_access_flags;
+ struct ib_qp_cap cap;
+ struct ib_ah_attr ah_attr;
+ struct ib_ah_attr alt_ah_attr;
+ u16 pkey_index;
+ u16 alt_pkey_index;
+ u8 en_sqd_async_notify;
+ u8 sq_draining;
+ u8 max_rd_atomic;
+ u8 max_dest_rd_atomic;
+ u8 min_rnr_timer;
+ u8 port_num;
+ u8 timeout;
+ u8 retry_cnt;
+ u8 rnr_retry;
+ u8 alt_port_num;
+ u8 alt_timeout;
+};
+
+enum ib_wr_opcode {
+ IB_WR_RDMA_WRITE,
+ IB_WR_RDMA_WRITE_WITH_IMM,
+ IB_WR_SEND,
+ IB_WR_SEND_WITH_IMM,
+ IB_WR_RDMA_READ,
+ IB_WR_ATOMIC_CMP_AND_SWP,
+ IB_WR_ATOMIC_FETCH_AND_ADD
+};
+
+enum ib_send_flags {
+ IB_SEND_FENCE = 1,
+ IB_SEND_SIGNALED = (1<<1),
+ IB_SEND_SOLICITED = (1<<2),
+ IB_SEND_INLINE = (1<<3)
+};
+
+enum ib_recv_flags {
+ IB_RECV_SIGNALED = 1
+};
+
+struct ib_sge {
+ u64 addr;
+ u32 length;
+ u32 lkey;
+};
+
+struct ib_send_wr {
+ struct ib_send_wr *next;
+ u64 wr_id;
+ struct ib_sge *sg_list;
+ int num_sge;
+ enum ib_wr_opcode opcode;
+ int send_flags;
+ u32 imm_data;
+ union {
+ struct {
+ u64 remote_addr;
+ u32 rkey;
+ } rdma;
+ struct {
+ u64 remote_addr;
+ u64 compare_add;
+ u64 swap;
+ u32 rkey;
+ } atomic;
+ struct {
+ struct ib_ah *ah;
+ struct ib_mad_hdr *mad_hdr;
+ u32 remote_qpn;
+ u32 remote_qkey;
+ int timeout_ms; /* valid for MADs only */
+ u16 pkey_index; /* valid for GSI only */
+ u8 port_num; /* valid for DR SMPs on switch only */
+ } ud;
+ } wr;
+};
+
+struct ib_recv_wr {
+ struct ib_recv_wr *next;
+ u64 wr_id;
+ struct ib_sge *sg_list;
+ int num_sge;
+ int recv_flags;
+};
+
+enum ib_access_flags {
+ IB_ACCESS_LOCAL_WRITE = 1,
+ IB_ACCESS_REMOTE_WRITE = (1<<1),
+ IB_ACCESS_REMOTE_READ = (1<<2),
+ IB_ACCESS_REMOTE_ATOMIC = (1<<3),
+ IB_ACCESS_MW_BIND = (1<<4)
+};
+
+struct ib_phys_buf {
+ u64 addr;
+ u64 size;
+};
+
+struct ib_mr_attr {
+ struct ib_pd *pd;
+ u64 device_virt_addr;
+ u64 size;
+ int mr_access_flags;
+ u32 lkey;
+ u32 rkey;
+};
+
+enum ib_mr_rereg_flags {
+ IB_MR_REREG_TRANS = 1,
+ IB_MR_REREG_PD = (1<<1),
+ IB_MR_REREG_ACCESS = (1<<2)
+};
+
+struct ib_mw_bind {
+ struct ib_mr *mr;
+ u64 wr_id;
+ u64 addr;
+ u32 length;
+ int send_flags;
+ int mw_access_flags;
+};
+
+struct ib_fmr_attr {
+ int max_pages;
+ int max_maps;
+ u8 page_size;
+};
+
+struct ib_pd {
+ struct ib_device *device;
+ atomic_t usecnt; /* count all resources */
+};
+
+struct ib_ah {
+ struct ib_device *device;
+ struct ib_pd *pd;
+};
+
+typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
+
+struct ib_cq {
+ struct ib_device *device;
+ ib_comp_handler comp_handler;
+ void (*event_handler)(struct ib_event *, void *);
+ void * cq_context;
+ int cqe;
+ atomic_t usecnt; /* count number of work queues */
+};
+
+struct ib_srq {
+ struct ib_device *device;
+ struct ib_pd *pd;
+ void *srq_context;
+ atomic_t usecnt;
+};
+
+struct ib_qp {
+ struct ib_device *device;
+ struct ib_pd *pd;
+ struct ib_cq *send_cq;
+ struct ib_cq *recv_cq;
+ struct ib_srq *srq;
+ void (*event_handler)(struct ib_event *, void *);
+ void *qp_context;
+ u32 qp_num;
+};
+
+struct ib_mr {
+ struct ib_device *device;
+ struct ib_pd *pd;
+ u32 lkey;
+ u32 rkey;
+ atomic_t usecnt; /* count number of MWs */
+};
+
+struct ib_mw {
+ struct ib_device *device;
+ struct ib_pd *pd;
+ u32 rkey;
+};
+
+struct ib_fmr {
+ struct ib_device *device;
+ struct ib_pd *pd;
+ struct list_head list;
+ u32 lkey;
+ u32 rkey;
+};
+
+struct ib_mad;
+
+enum ib_process_mad_flags {
+ IB_MAD_IGNORE_MKEY = 1
+};
+
+enum ib_mad_result {
+ IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */
+ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */
+ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */
+ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */
+};
+
+#define IB_DEVICE_NAME_MAX 64
+
+struct ib_cache {
+ rwlock_t lock;
+ struct ib_event_handler event_handler;
+ struct ib_pkey_cache **pkey_cache;
+ struct ib_gid_cache **gid_cache;
+};
+
+struct ib_device {
+ struct device *dma_device;
+
+ char name[IB_DEVICE_NAME_MAX];
+
+ struct list_head event_handler_list;
+ spinlock_t event_handler_lock;
+
+ struct list_head core_list;
+ struct list_head client_data_list;
+ spinlock_t client_data_lock;
+
+ struct ib_cache cache;
+
+ u32 flags;
+
+ int (*query_device)(struct ib_device *device,
+ struct ib_device_attr *device_attr);
+ int (*query_port)(struct ib_device *device,
+ u8 port_num,
+ struct ib_port_attr *port_attr);
+ int (*query_gid)(struct ib_device *device,
+ u8 port_num, int index,
+ union ib_gid *gid);
+ int (*query_pkey)(struct ib_device *device,
+ u8 port_num, u16 index, u16 *pkey);
+ int (*modify_device)(struct ib_device *device,
+ int device_modify_mask,
+ struct ib_device_modify *device_modify);
+ int (*modify_port)(struct ib_device *device,
+ u8 port_num, int port_modify_mask,
+ struct ib_port_modify *port_modify);
+ struct ib_pd * (*alloc_pd)(struct ib_device *device);
+ int (*dealloc_pd)(struct ib_pd *pd);
+ struct ib_ah * (*create_ah)(struct ib_pd *pd,
+ struct ib_ah_attr *ah_attr);
+ int (*modify_ah)(struct ib_ah *ah,
+ struct ib_ah_attr *ah_attr);
+ int (*query_ah)(struct ib_ah *ah,
+ struct ib_ah_attr *ah_attr);
+ int (*destroy_ah)(struct ib_ah *ah);
+ struct ib_qp * (*create_qp)(struct ib_pd *pd,
+ struct ib_qp_init_attr *qp_init_attr);
+ int (*modify_qp)(struct ib_qp *qp,
+ struct ib_qp_attr *qp_attr,
+ int qp_attr_mask);
+ int (*query_qp)(struct ib_qp *qp,
+ struct ib_qp_attr *qp_attr,
+ int qp_attr_mask,
+ struct ib_qp_init_attr *qp_init_attr);
+ int (*destroy_qp)(struct ib_qp *qp);
+ int (*post_send)(struct ib_qp *qp,
+ struct ib_send_wr *send_wr,
+ struct ib_send_wr **bad_send_wr);
+ int (*post_recv)(struct ib_qp *qp,
+ struct ib_recv_wr *recv_wr,
+ struct ib_recv_wr **bad_recv_wr);
+ struct ib_cq * (*create_cq)(struct ib_device *device,
+ int cqe);
+ int (*destroy_cq)(struct ib_cq *cq);
+ int (*resize_cq)(struct ib_cq *cq, int *cqe);
+ int (*poll_cq)(struct ib_cq *cq, int num_entries,
+ struct ib_wc *wc);
+ int (*peek_cq)(struct ib_cq *cq, int wc_cnt);
+ int (*req_notify_cq)(struct ib_cq *cq,
+ enum ib_cq_notify cq_notify);
+ int (*req_ncomp_notif)(struct ib_cq *cq,
+ int wc_cnt);
+ struct ib_mr * (*get_dma_mr)(struct ib_pd *pd,
+ int mr_access_flags);
+ struct ib_mr * (*reg_phys_mr)(struct ib_pd *pd,
+ struct ib_phys_buf *phys_buf_array,
+ int num_phys_buf,
+ int mr_access_flags,
+ u64 *iova_start);
+ int (*query_mr)(struct ib_mr *mr,
+ struct ib_mr_attr *mr_attr);
+ int (*dereg_mr)(struct ib_mr *mr);
+ int (*rereg_phys_mr)(struct ib_mr *mr,
+ int mr_rereg_mask,
+ struct ib_pd *pd,
+ struct ib_phys_buf *phys_buf_array,
+ int num_phys_buf,
+ int mr_access_flags,
+ u64 *iova_start);
+ struct ib_mw * (*alloc_mw)(struct ib_pd *pd);
+ int (*bind_mw)(struct ib_qp *qp,
+ struct ib_mw *mw,
+ struct ib_mw_bind *mw_bind);
+ int (*dealloc_mw)(struct ib_mw *mw);
+ struct ib_fmr * (*alloc_fmr)(struct ib_pd *pd,
+ int mr_access_flags,
+ struct ib_fmr_attr *fmr_attr);
+ int (*map_phys_fmr)(struct ib_fmr *fmr,
+ u64 *page_list, int list_len,
+ u64 iova);
+ int (*unmap_fmr)(struct list_head *fmr_list);
+ int (*dealloc_fmr)(struct ib_fmr *fmr);
+ int (*attach_mcast)(struct ib_qp *qp,
+ union ib_gid *gid,
+ u16 lid);
+ int (*detach_mcast)(struct ib_qp *qp,
+ union ib_gid *gid,
+ u16 lid);
+ int (*process_mad)(struct ib_device *device,
+ int process_mad_flags,
+ u8 port_num,
+ u16 source_lid,
+ struct ib_mad *in_mad,
+ struct ib_mad *out_mad);
+
+ struct class_device class_dev;
+ struct kobject ports_parent;
+ struct list_head port_list;
+
+ enum {
+ IB_DEV_UNINITIALIZED,
+ IB_DEV_REGISTERED,
+ IB_DEV_UNREGISTERED
+ } reg_state;
+
+ u8 node_type;
+ u8 phys_port_cnt;
+};
+
+struct ib_client {
+ char *name;
+ void (*add) (struct ib_device *);
+ void (*remove)(struct ib_device *);
+
+ struct list_head list;
+};
+
+struct ib_device *ib_alloc_device(size_t size);
+void ib_dealloc_device(struct ib_device *device);
+
+int ib_register_device (struct ib_device *device);
+void ib_unregister_device(struct ib_device *device);
+
+int ib_register_client (struct ib_client *client);
+void ib_unregister_client(struct ib_client *client);
+
+void *ib_get_client_data(struct ib_device *device, struct ib_client *client);
+void ib_set_client_data(struct ib_device *device, struct ib_client *client,
+ void *data);
+
+int ib_register_event_handler (struct ib_event_handler *event_handler);
+int ib_unregister_event_handler(struct ib_event_handler *event_handler);
+void ib_dispatch_event(struct ib_event *event);
+
+int ib_query_device(struct ib_device *device,
+ struct ib_device_attr *device_attr);
+
+int ib_query_port(struct ib_device *device,
+ u8 port_num, struct ib_port_attr *port_attr);
+
+int ib_query_gid(struct ib_device *device,
+ u8 port_num, int index, union ib_gid *gid);
+
+int ib_query_pkey(struct ib_device *device,
+ u8 port_num, u16 index, u16 *pkey);
+
+int ib_modify_device(struct ib_device *device,
+ int device_modify_mask,
+ struct ib_device_modify *device_modify);
+
+int ib_modify_port(struct ib_device *device,
+ u8 port_num, int port_modify_mask,
+ struct ib_port_modify *port_modify);
+
+/**
+ * ib_alloc_pd - Allocates an unused protection domain.
+ * @device: The device on which to allocate the protection domain.
+ *
+ * A protection domain object provides an association between QPs, shared
+ * receive queues, address handles, memory regions, and memory windows.
+ */
+struct ib_pd *ib_alloc_pd(struct ib_device *device);
+
+/**
+ * ib_dealloc_pd - Deallocates a protection domain.
+ * @pd: The protection domain to deallocate.
+ */
+int ib_dealloc_pd(struct ib_pd *pd);
+
+/**
+ * ib_create_ah - Creates an address handle for the given address vector.
+ * @pd: The protection domain associated with the address handle.
+ * @ah_attr: The attributes of the address vector.
+ *
+ * The address handle is used to reference a local or global destination
+ * in all UD QP post sends.
+ */
+struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+
+/**
+ * ib_modify_ah - Modifies the address vector associated with an address
+ * handle.
+ * @ah: The address handle to modify.
+ * @ah_attr: The new address vector attributes to associate with the
+ * address handle.
+ */
+int ib_modify_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr);
+
+/**
+ * ib_query_ah - Queries the address vector associated with an address
+ * handle.
+ * @ah: The address handle to query.
+ * @ah_attr: The address vector attributes associated with the address
+ * handle.
+ */
+int ib_query_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr);
+
+/**
+ * ib_destroy_ah - Destroys an address handle.
+ * @ah: The address handle to destroy.
+ */
+int ib_destroy_ah(struct ib_ah *ah);
+
+/**
+ * ib_create_qp - Creates a QP associated with the specified protection
+ * domain.
+ * @pd: The protection domain associated with the QP.
+ * @qp_init_attr: A list of initial attributes required to create the QP.
+ */
+struct ib_qp *ib_create_qp(struct ib_pd *pd,
+ struct ib_qp_init_attr *qp_init_attr);
+
+/**
+ * ib_modify_qp - Modifies the attributes for the specified QP and then
+ * transitions the QP to the given state.
+ * @qp: The QP to modify.
+ * @qp_attr: On input, specifies the QP attributes to modify. On output,
+ * the current values of selected QP attributes are returned.
+ * @qp_attr_mask: A bit-mask used to specify which attributes of the QP
+ * are being modified.
+ */
+int ib_modify_qp(struct ib_qp *qp,
+ struct ib_qp_attr *qp_attr,
+ int qp_attr_mask);
+
+/**
+ * ib_query_qp - Returns the attribute list and current values for the
+ * specified QP.
+ * @qp: The QP to query.
+ * @qp_attr: The attributes of the specified QP.
+ * @qp_attr_mask: A bit-mask used to select specific attributes to query.
+ * @qp_init_attr: Additional attributes of the selected QP.
+ *
+ * The qp_attr_mask may be used to limit the query to gathering only the
+ * selected attributes.
+ */
+int ib_query_qp(struct ib_qp *qp,
+ struct ib_qp_attr *qp_attr,
+ int qp_attr_mask,
+ struct ib_qp_init_attr *qp_init_attr);
+
+/**
+ * ib_destroy_qp - Destroys the specified QP.
+ * @qp: The QP to destroy.
+ */
+int ib_destroy_qp(struct ib_qp *qp);
+
+/**
+ * ib_post_send - Posts a list of work requests to the send queue of
+ * the specified QP.
+ * @qp: The QP to post the work request on.
+ * @send_wr: A list of work requests to post on the send queue.
+ * @bad_send_wr: On an immediate failure, this parameter will reference
+ * the work request that failed to be posted on the QP.
+ */
+static inline int ib_post_send(struct ib_qp *qp,
+ struct ib_send_wr *send_wr,
+ struct ib_send_wr **bad_send_wr)
+{
+ return qp->device->post_send(qp, send_wr, bad_send_wr);
+}
+
+/**
+ * ib_post_recv - Posts a list of work requests to the receive queue of
+ * the specified QP.
+ * @qp: The QP to post the work request on.
+ * @recv_wr: A list of work requests to post on the receive queue.
+ * @bad_recv_wr: On an immediate failure, this parameter will reference
+ * the work request that failed to be posted on the QP.
+ */
+static inline int ib_post_recv(struct ib_qp *qp,
+ struct ib_recv_wr *recv_wr,
+ struct ib_recv_wr **bad_recv_wr)
+{
+ return qp->device->post_recv(qp, recv_wr, bad_recv_wr);
+}
+
+/**
+ * ib_create_cq - Creates a CQ on the specified device.
+ * @device: The device on which to create the CQ.
+ * @comp_handler: A user-specified callback that is invoked when a
+ * completion event occurs on the CQ.
+ * @event_handler: A user-specified callback that is invoked when an
+ * asynchronous event not associated with a completion occurs on the CQ.
+ * @cq_context: Context associated with the CQ returned to the user via
+ * the associated completion and event handlers.
+ * @cqe: The minimum size of the CQ.
+ *
+ * Users can examine the cq structure to determine the actual CQ size.
+ */
+struct ib_cq *ib_create_cq(struct ib_device *device,
+ ib_comp_handler comp_handler,
+ void (*event_handler)(struct ib_event *, void *),
+ void *cq_context, int cqe);
+
+/**
+ * ib_resize_cq - Modifies the capacity of the CQ.
+ * @cq: The CQ to resize.
+ * @cqe: The minimum size of the CQ.
+ *
+ * Users can examine the cq structure to determine the actual CQ size.
+ */
+int ib_resize_cq(struct ib_cq *cq, int cqe);
+
+/**
+ * ib_destroy_cq - Destroys the specified CQ.
+ * @cq: The CQ to destroy.
+ */
+int ib_destroy_cq(struct ib_cq *cq);
+
+/**
+ * ib_poll_cq - poll a CQ for completion(s)
+ * @cq:the CQ being polled
+ * @num_entries:maximum number of completions to return
+ * @wc:array of at least @num_entries &struct ib_wc where completions
+ * will be returned
+ *
+ * Poll a CQ for (possibly multiple) completions. If the return value
+ * is < 0, an error occurred. If the return value is >= 0, it is the
+ * number of completions returned. If the return value is
+ * non-negative and < num_entries, then the CQ was emptied.
+ */
+static inline int ib_poll_cq(struct ib_cq *cq, int num_entries,
+ struct ib_wc *wc)
+{
+ return cq->device->poll_cq(cq, num_entries, wc);
+}
+
+/**
+ * ib_peek_cq - Returns the number of unreaped completions currently
+ * on the specified CQ.
+ * @cq: The CQ to peek.
+ * @wc_cnt: A minimum number of unreaped completions to check for.
+ *
+ * If the number of unreaped completions is greater than or equal to wc_cnt,
+ * this function returns wc_cnt, otherwise, it returns the actual number of
+ * unreaped completions.
+ */
+int ib_peek_cq(struct ib_cq *cq, int wc_cnt);
+
+/**
+ * ib_req_notify_cq - Request completion notification on a CQ.
+ * @cq: The CQ to generate an event for.
+ * @cq_notify: If set to %IB_CQ_SOLICITED, completion notification will
+ * occur on the next solicited event. If set to %IB_CQ_NEXT_COMP,
+ * notification will occur on the next completion.
+ */
+static inline int ib_req_notify_cq(struct ib_cq *cq,
+ enum ib_cq_notify cq_notify)
+{
+ return cq->device->req_notify_cq(cq, cq_notify);
+}
+
+/**
+ * ib_req_ncomp_notif - Request completion notification when there are
+ * at least the specified number of unreaped completions on the CQ.
+ * @cq: The CQ to generate an event for.
+ * @wc_cnt: The number of unreaped completions that should be on the
+ * CQ before an event is generated.
+ */
+static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt)
+{
+ return cq->device->req_ncomp_notif ?
+ cq->device->req_ncomp_notif(cq, wc_cnt) :
+ -ENOSYS;
+}
+
+/**
+ * ib_get_dma_mr - Returns a memory region for system memory that is
+ * usable for DMA.
+ * @pd: The protection domain associated with the memory region.
+ * @mr_access_flags: Specifies the memory access rights.
+ */
+struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags);
+
+/**
+ * ib_reg_phys_mr - Prepares a virtually addressed memory region for use
+ * by an HCA.
+ * @pd: The protection domain associated assigned to the registered region.
+ * @phys_buf_array: Specifies a list of physical buffers to use in the
+ * memory region.
+ * @num_phys_buf: Specifies the size of the phys_buf_array.
+ * @mr_access_flags: Specifies the memory access rights.
+ * @iova_start: The offset of the region's starting I/O virtual address.
+ */
+struct ib_mr *ib_reg_phys_mr(struct ib_pd *pd,
+ struct ib_phys_buf *phys_buf_array,
+ int num_phys_buf,
+ int mr_access_flags,
+ u64 *iova_start);
+
+/**
+ * ib_rereg_phys_mr - Modifies the attributes of an existing memory region.
+ * Conceptually, this call performs the functions deregister memory region
+ * followed by register physical memory region. Where possible,
+ * resources are reused instead of deallocated and reallocated.
+ * @mr: The memory region to modify.
+ * @mr_rereg_mask: A bit-mask used to indicate which of the following
+ * properties of the memory region are being modified.
+ * @pd: If %IB_MR_REREG_PD is set in mr_rereg_mask, this field specifies
+ * the new protection domain to associated with the memory region,
+ * otherwise, this parameter is ignored.
+ * @phys_buf_array: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
+ * field specifies a list of physical buffers to use in the new
+ * translation, otherwise, this parameter is ignored.
+ * @num_phys_buf: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
+ * field specifies the size of the phys_buf_array, otherwise, this
+ * parameter is ignored.
+ * @mr_access_flags: If %IB_MR_REREG_ACCESS is set in mr_rereg_mask, this
+ * field specifies the new memory access rights, otherwise, this
+ * parameter is ignored.
+ * @iova_start: The offset of the region's starting I/O virtual address.
+ */
+int ib_rereg_phys_mr(struct ib_mr *mr,
+ int mr_rereg_mask,
+ struct ib_pd *pd,
+ struct ib_phys_buf *phys_buf_array,
+ int num_phys_buf,
+ int mr_access_flags,
+ u64 *iova_start);
+
+/**
+ * ib_query_mr - Retrieves information about a specific memory region.
+ * @mr: The memory region to retrieve information about.
+ * @mr_attr: The attributes of the specified memory region.
+ */
+int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
+
+/**
+ * ib_dereg_mr - Deregisters a memory region and removes it from the
+ * HCA translation table.
+ * @mr: The memory region to deregister.
+ */
+int ib_dereg_mr(struct ib_mr *mr);
+
+/**
+ * ib_alloc_mw - Allocates a memory window.
+ * @pd: The protection domain associated with the memory window.
+ */
+struct ib_mw *ib_alloc_mw(struct ib_pd *pd);
+
+/**
+ * ib_bind_mw - Posts a work request to the send queue of the specified
+ * QP, which binds the memory window to the given address range and
+ * remote access attributes.
+ * @qp: QP to post the bind work request on.
+ * @mw: The memory window to bind.
+ * @mw_bind: Specifies information about the memory window, including
+ * its address range, remote access rights, and associated memory region.
+ */
+static inline int ib_bind_mw(struct ib_qp *qp,
+ struct ib_mw *mw,
+ struct ib_mw_bind *mw_bind)
+{
+ /* XXX reference counting in corresponding MR? */
+ return mw->device->bind_mw ?
+ mw->device->bind_mw(qp, mw, mw_bind) :
+ -ENOSYS;
+}
+
+/**
+ * ib_dealloc_mw - Deallocates a memory window.
+ * @mw: The memory window to deallocate.
+ */
+int ib_dealloc_mw(struct ib_mw *mw);
+
+/**
+ * ib_alloc_fmr - Allocates a unmapped fast memory region.
+ * @pd: The protection domain associated with the unmapped region.
+ * @mr_access_flags: Specifies the memory access rights.
+ * @fmr_attr: Attributes of the unmapped region.
+ *
+ * A fast memory region must be mapped before it can be used as part of
+ * a work request.
+ */
+struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd,
+ int mr_access_flags,
+ struct ib_fmr_attr *fmr_attr);
+
+/**
+ * ib_map_phys_fmr - Maps a list of physical pages to a fast memory region.
+ * @fmr: The fast memory region to associate with the pages.
+ * @page_list: An array of physical pages to map to the fast memory region.
+ * @list_len: The number of pages in page_list.
+ * @iova: The I/O virtual address to use with the mapped region.
+ */
+static inline int ib_map_phys_fmr(struct ib_fmr *fmr,
+ u64 *page_list, int list_len,
+ u64 iova)
+{
+ return fmr->device->map_phys_fmr(fmr, page_list, list_len, iova);
+}
+
+/**
+ * ib_unmap_fmr - Removes the mapping from a list of fast memory regions.
+ * @fmr_list: A linked list of fast memory regions to unmap.
+ */
+int ib_unmap_fmr(struct list_head *fmr_list);
+
+/**
+ * ib_dealloc_fmr - Deallocates a fast memory region.
+ * @fmr: The fast memory region to deallocate.
+ */
+int ib_dealloc_fmr(struct ib_fmr *fmr);
+
+/**
+ * ib_attach_mcast - Attaches the specified QP to a multicast group.
+ * @qp: QP to attach to the multicast group. The QP must be type
+ * IB_QPT_UD.
+ * @gid: Multicast group GID.
+ * @lid: Multicast group LID in host byte order.
+ *
+ * In order to send and receive multicast packets, subnet
+ * administration must have created the multicast group and configured
+ * the fabric appropriately. The port associated with the specified
+ * QP must also be a member of the multicast group.
+ */
+int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);
+
+/**
+ * ib_detach_mcast - Detaches the specified QP from a multicast group.
+ * @qp: QP to detach from the multicast group.
+ * @gid: Multicast group GID.
+ * @lid: Multicast group LID in host byte order.
+ */
+int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);
+
+#endif /* IB_VERBS_H */
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH][v3][2/21] Add core InfiniBand support
2004-12-13 18:09 ` [PATCH][v3][1/21] Add core InfiniBand support (public headers) Roland Dreier
@ 2004-12-13 18:09 ` Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][3/21] Hook up drivers/infiniband Roland Dreier
0 siblings, 1 reply; 5+ messages in thread
From: Roland Dreier @ 2004-12-13 18:09 UTC (permalink / raw)
To: linux-kernel; +Cc: openib-general
Add implementation of core InfiniBand support. This can be thought of
as a midlayer that provides an abstraction between low-level hardware
drivers and upper level protocols (such as IP-over-InfiniBand).
Signed-off-by: Roland Dreier <roland@topspin.com>
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/Kconfig 2004-12-13 09:44:40.230798660 -0800
@@ -0,0 +1,11 @@
+menu "InfiniBand support"
+
+config INFINIBAND
+ tristate "InfiniBand support"
+ default n
+ ---help---
+ Core support for InfiniBand (IB). Make sure to also select
+ any protocols you wish to use as well as drivers for your
+ InfiniBand hardware.
+
+endmenu
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/Makefile 2004-12-13 09:44:40.278791590 -0800
@@ -0,0 +1 @@
+obj-$(CONFIG_INFINIBAND) += core/
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/Makefile 2004-12-13 09:44:40.305787613 -0800
@@ -0,0 +1,13 @@
+EXTRA_CFLAGS += -Idrivers/infiniband/include
+
+obj-$(CONFIG_INFINIBAND) += \
+ ib_core.o
+
+ib_core-objs := \
+ packer.o \
+ ud_header.o \
+ verbs.o \
+ sysfs.o \
+ device.o \
+ fmr_pool.o \
+ cache.o
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/cache.c 2004-12-13 09:44:40.502758596 -0800
@@ -0,0 +1,317 @@
+/*
+ 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 at
+ <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ license, available in the LICENSE.TXT file accompanying this
+ software. These details are also available at
+ <http://openib.org/license.html>.
+
+ 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.
+
+ Copyright (c) 2004 Topspin Communications. All rights reserved.
+
+ $Id: cache.c 1293 2004-11-25 16:04:07Z roland $
+*/
+
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "core_priv.h"
+
+struct ib_pkey_cache {
+ int table_len;
+ u16 table[0];
+};
+
+struct ib_gid_cache {
+ int table_len;
+ union ib_gid table[0];
+};
+
+struct ib_update_work {
+ struct work_struct work;
+ struct ib_device *device;
+ u8 port_num;
+};
+
+static inline int start_port(struct ib_device *device)
+{
+ return device->node_type == IB_NODE_SWITCH ? 0 : 1;
+}
+
+static inline int end_port(struct ib_device *device)
+{
+ return device->node_type == IB_NODE_SWITCH ? 0 : device->phys_port_cnt;
+}
+
+int ib_cached_gid_get(struct ib_device *device,
+ u8 port,
+ int index,
+ union ib_gid *gid)
+{
+ struct ib_gid_cache *cache;
+ unsigned long flags;
+ int ret = 0;
+
+ if (port < start_port(device) || port > end_port(device))
+ return -EINVAL;
+
+ read_lock_irqsave(&device->cache.lock, flags);
+
+ cache = device->cache.gid_cache[port - start_port(device)];
+
+ if (index < 0 || index >= cache->table_len)
+ ret = -EINVAL;
+ else
+ *gid = cache->table[index];
+
+ read_unlock_irqrestore(&device->cache.lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_cached_gid_get);
+
+int ib_cached_pkey_get(struct ib_device *device,
+ u8 port,
+ int index,
+ u16 *pkey)
+{
+ struct ib_pkey_cache *cache;
+ unsigned long flags;
+ int ret = 0;
+
+ if (port < start_port(device) || port > end_port(device))
+ return -EINVAL;
+
+ read_lock_irqsave(&device->cache.lock, flags);
+
+ cache = device->cache.pkey_cache[port - start_port(device)];
+
+ if (index < 0 || index >= cache->table_len)
+ ret = -EINVAL;
+ else
+ *pkey = cache->table[index];
+
+ read_unlock_irqrestore(&device->cache.lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_cached_pkey_get);
+
+int ib_cached_pkey_find(struct ib_device *device,
+ u8 port,
+ u16 pkey,
+ u16 *index)
+{
+ struct ib_pkey_cache *cache;
+ unsigned long flags;
+ int i;
+ int ret = -ENOENT;
+
+ if (port < start_port(device) || port > end_port(device))
+ return -EINVAL;
+
+ read_lock_irqsave(&device->cache.lock, flags);
+
+ cache = device->cache.pkey_cache[port - start_port(device)];
+
+ *index = -1;
+
+ for (i = 0; i < cache->table_len; ++i)
+ if ((cache->table[i] & 0x7fff) == (pkey & 0x7fff)) {
+ *index = i;
+ ret = 0;
+ break;
+ }
+
+ read_unlock_irqrestore(&device->cache.lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_cached_pkey_find);
+
+static void ib_cache_update(struct ib_device *device,
+ u8 port)
+{
+ struct ib_port_attr *tprops = NULL;
+ struct ib_pkey_cache *pkey_cache = NULL, *old_pkey_cache;
+ struct ib_gid_cache *gid_cache = NULL, *old_gid_cache;
+ int i;
+ int ret;
+
+ tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
+ if (!tprops)
+ return;
+
+ ret = ib_query_port(device, port, tprops);
+ if (ret) {
+ printk(KERN_WARNING "ib_query_port failed (%d) for %s\n",
+ ret, device->name);
+ goto err;
+ }
+
+ pkey_cache = kmalloc(sizeof *pkey_cache + tprops->pkey_tbl_len *
+ sizeof *pkey_cache->table, GFP_KERNEL);
+ if (!pkey_cache)
+ goto err;
+
+ pkey_cache->table_len = tprops->pkey_tbl_len;
+
+ gid_cache = kmalloc(sizeof *gid_cache + tprops->gid_tbl_len *
+ sizeof *gid_cache->table, GFP_KERNEL);
+ if (!gid_cache)
+ goto err;
+
+ gid_cache->table_len = tprops->gid_tbl_len;
+
+ for (i = 0; i < pkey_cache->table_len; ++i) {
+ ret = ib_query_pkey(device, port, i, pkey_cache->table + i);
+ if (ret) {
+ printk(KERN_WARNING "ib_query_pkey failed (%d) for %s (index %d)\n",
+ ret, device->name, i);
+ goto err;
+ }
+ }
+
+ for (i = 0; i < gid_cache->table_len; ++i) {
+ ret = ib_query_gid(device, port, i, gid_cache->table + i);
+ if (ret) {
+ printk(KERN_WARNING "ib_query_gid failed (%d) for %s (index %d)\n",
+ ret, device->name, i);
+ goto err;
+ }
+ }
+
+ write_lock_irq(&device->cache.lock);
+
+ old_pkey_cache = device->cache.pkey_cache[port - start_port(device)];
+ old_gid_cache = device->cache.gid_cache [port - start_port(device)];
+
+ device->cache.pkey_cache[port - start_port(device)] = pkey_cache;
+ device->cache.gid_cache [port - start_port(device)] = gid_cache;
+
+ write_unlock_irq(&device->cache.lock);
+
+ kfree(old_pkey_cache);
+ kfree(old_gid_cache);
+ kfree(tprops);
+ return;
+
+err:
+ kfree(pkey_cache);
+ kfree(gid_cache);
+ kfree(tprops);
+}
+
+static void ib_cache_task(void *work_ptr)
+{
+ struct ib_update_work *work = work_ptr;
+
+ ib_cache_update(work->device, work->port_num);
+ kfree(work);
+}
+
+static void ib_cache_event(struct ib_event_handler *handler,
+ struct ib_event *event)
+{
+ struct ib_update_work *work;
+
+ if (event->event == IB_EVENT_PORT_ERR ||
+ event->event == IB_EVENT_PORT_ACTIVE ||
+ event->event == IB_EVENT_LID_CHANGE ||
+ event->event == IB_EVENT_PKEY_CHANGE ||
+ event->event == IB_EVENT_SM_CHANGE) {
+ work = kmalloc(sizeof *work, GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(&work->work, ib_cache_task, work);
+ work->device = event->device;
+ work->port_num = event->element.port_num;
+ schedule_work(&work->work);
+ }
+ }
+}
+
+void ib_cache_setup_one(struct ib_device *device)
+{
+ int p;
+
+ rwlock_init(&device->cache.lock);
+
+ device->cache.pkey_cache =
+ kmalloc(sizeof *device->cache.pkey_cache *
+ (end_port(device) - start_port(device) + 1), GFP_KERNEL);
+ device->cache.gid_cache =
+ kmalloc(sizeof *device->cache.pkey_cache *
+ (end_port(device) - start_port(device) + 1), GFP_KERNEL);
+
+ if (!device->cache.pkey_cache || !device->cache.gid_cache) {
+ printk(KERN_WARNING "Couldn't allocate cache "
+ "for %s\n", device->name);
+ goto err;
+ }
+
+ for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+ device->cache.pkey_cache[p] = NULL;
+ device->cache.gid_cache [p] = NULL;
+ ib_cache_update(device, p + start_port(device));
+ }
+
+ INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
+ device, ib_cache_event);
+ if (ib_register_event_handler(&device->cache.event_handler))
+ goto err_cache;
+
+ return;
+
+err_cache:
+ for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+ kfree(device->cache.pkey_cache[p]);
+ kfree(device->cache.gid_cache[p]);
+ }
+
+err:
+ kfree(device->cache.pkey_cache);
+ kfree(device->cache.gid_cache);
+}
+
+void ib_cache_cleanup_one(struct ib_device *device)
+{
+ int p;
+
+ ib_unregister_event_handler(&device->cache.event_handler);
+ flush_scheduled_work();
+
+ for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+ kfree(device->cache.pkey_cache[p]);
+ kfree(device->cache.gid_cache[p]);
+ }
+
+ kfree(device->cache.pkey_cache);
+ kfree(device->cache.gid_cache);
+}
+
+struct ib_client cache_client = {
+ .name = "cache",
+ .add = ib_cache_setup_one,
+ .remove = ib_cache_cleanup_one
+};
+
+int __init ib_cache_setup(void)
+{
+ return ib_register_client(&cache_client);
+}
+
+void __exit ib_cache_cleanup(void)
+{
+ ib_unregister_client(&cache_client);
+}
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/core_priv.h 2004-12-13 09:44:40.527754913 -0800
@@ -0,0 +1,41 @@
+/*
+ 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 at
+ <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ license, available in the LICENSE.TXT file accompanying this
+ software. These details are also available at
+ <http://openib.org/license.html>.
+
+ 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.
+
+ Copyright (c) 2004 Topspin Communications. All rights reserved.
+
+ $Id: core_priv.h 1288 2004-11-24 01:12:39Z roland $
+*/
+
+#ifndef _CORE_PRIV_H
+#define _CORE_PRIV_H
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#include <ib_verbs.h>
+
+int ib_device_register_sysfs(struct ib_device *device);
+void ib_device_unregister_sysfs(struct ib_device *device);
+
+int ib_sysfs_setup(void);
+void ib_sysfs_cleanup(void);
+
+int ib_cache_setup(void);
+void ib_cache_cleanup(void);
+
+#endif /* _CORE_PRIV_H */
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/device.c 2004-12-13 09:44:40.448766550 -0800
@@ -0,0 +1,603 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Communications. All rights reserved.
+ *
+ * $Id: device.c 1304 2004-11-30 19:01:25Z sean.hefty $
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+
+#include <asm/semaphore.h>
+
+#include "core_priv.h"
+
+MODULE_AUTHOR("Roland Dreier");
+MODULE_DESCRIPTION("core kernel InfiniBand API");
+MODULE_LICENSE("Dual BSD/GPL");
+
+struct ib_client_data {
+ struct list_head list;
+ struct ib_client *client;
+ void * data;
+};
+
+static LIST_HEAD(device_list);
+static LIST_HEAD(client_list);
+
+/*
+ * device_sem protects access to both device_list and client_list.
+ * There's no real point to using multiple locks or something fancier
+ * like an rwsem: we always access both lists, and we're always
+ * modifying one list or the other list. In any case this is not a
+ * hot path so there's no point in trying to optimize.
+ */
+static DECLARE_MUTEX(device_sem);
+
+static int ib_device_check_mandatory(struct ib_device *device)
+{
+#define IB_MANDATORY_FUNC(x) { offsetof(struct ib_device, x), #x }
+ static const struct {
+ size_t offset;
+ char *name;
+ } mandatory_table[] = {
+ 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),
+ IB_MANDATORY_FUNC(destroy_ah),
+ IB_MANDATORY_FUNC(create_qp),
+ IB_MANDATORY_FUNC(modify_qp),
+ IB_MANDATORY_FUNC(destroy_qp),
+ IB_MANDATORY_FUNC(post_send),
+ IB_MANDATORY_FUNC(post_recv),
+ IB_MANDATORY_FUNC(create_cq),
+ IB_MANDATORY_FUNC(destroy_cq),
+ IB_MANDATORY_FUNC(poll_cq),
+ IB_MANDATORY_FUNC(req_notify_cq),
+ IB_MANDATORY_FUNC(get_dma_mr),
+ IB_MANDATORY_FUNC(dereg_mr)
+ };
+ int i;
+
+ for (i = 0; i < sizeof mandatory_table / sizeof mandatory_table[0]; ++i) {
+ if (!*(void **) ((void *) device + mandatory_table[i].offset)) {
+ printk(KERN_WARNING "Device %s is missing mandatory function %s\n",
+ device->name, mandatory_table[i].name);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static struct ib_device *__ib_device_get_by_name(const char *name)
+{
+ struct ib_device *device;
+
+ list_for_each_entry(device, &device_list, core_list)
+ if (!strncmp(name, device->name, IB_DEVICE_NAME_MAX))
+ return device;
+
+ return NULL;
+}
+
+
+static int alloc_name(char *name)
+{
+ long *inuse;
+ char buf[IB_DEVICE_NAME_MAX];
+ struct ib_device *device;
+ int i;
+
+ inuse = (long *) get_zeroed_page(GFP_KERNEL);
+ if (!inuse)
+ return -ENOMEM;
+
+ list_for_each_entry(device, &device_list, core_list) {
+ if (!sscanf(device->name, name, &i))
+ continue;
+ if (i < 0 || i >= PAGE_SIZE * 8)
+ continue;
+ snprintf(buf, sizeof buf, name, i);
+ if (!strncmp(buf, device->name, IB_DEVICE_NAME_MAX))
+ set_bit(i, inuse);
+ }
+
+ i = find_first_zero_bit(inuse, PAGE_SIZE * 8);
+ free_page((unsigned long) inuse);
+ snprintf(buf, sizeof buf, name, i);
+
+ if (__ib_device_get_by_name(buf))
+ return -ENFILE;
+
+ strlcpy(name, buf, IB_DEVICE_NAME_MAX);
+ return 0;
+}
+
+/**
+ * ib_alloc_device - allocate an IB device struct
+ * @size:size of structure to allocate
+ *
+ * Low-level drivers should use ib_alloc_device() to allocate &struct
+ * ib_device. @size is the size of the structure to be allocated,
+ * including any private data used by the low-level driver.
+ * ib_dealloc_device() must be used to free structures allocated with
+ * ib_alloc_device().
+ */
+struct ib_device *ib_alloc_device(size_t size)
+{
+ void *dev;
+
+ BUG_ON(size < sizeof (struct ib_device));
+
+ dev = kmalloc(size, GFP_KERNEL);
+ if (!dev)
+ return NULL;
+
+ memset(dev, 0, size);
+
+ return dev;
+}
+EXPORT_SYMBOL(ib_alloc_device);
+
+/**
+ * ib_dealloc_device - free an IB device struct
+ * @device:structure to free
+ *
+ * Free a structure allocated with ib_alloc_device().
+ */
+void ib_dealloc_device(struct ib_device *device)
+{
+ if (device->reg_state == IB_DEV_UNINITIALIZED) {
+ kfree(device);
+ return;
+ }
+
+ BUG_ON(device->reg_state != IB_DEV_UNREGISTERED);
+
+ ib_device_unregister_sysfs(device);
+}
+EXPORT_SYMBOL(ib_dealloc_device);
+
+static int add_client_context(struct ib_device *device, struct ib_client *client)
+{
+ struct ib_client_data *context;
+ unsigned long flags;
+
+ context = kmalloc(sizeof *context, GFP_KERNEL);
+ if (!context) {
+ printk(KERN_WARNING "Couldn't allocate client context for %s/%s\n",
+ device->name, client->name);
+ return -ENOMEM;
+ }
+
+ context->client = client;
+ context->data = NULL;
+
+ spin_lock_irqsave(&device->client_data_lock, flags);
+ list_add(&context->list, &device->client_data_list);
+ spin_unlock_irqrestore(&device->client_data_lock, flags);
+
+ return 0;
+}
+
+/**
+ * ib_register_device - Register an IB device with IB core
+ * @device:Device to register
+ *
+ * Low-level drivers use ib_register_device() to register their
+ * devices with the IB core. All registered clients will receive a
+ * callback for each device that is added. @device must be allocated
+ * with ib_alloc_device().
+ */
+int ib_register_device(struct ib_device *device)
+{
+ int ret;
+
+ down(&device_sem);
+
+ if (strchr(device->name, '%')) {
+ ret = alloc_name(device->name);
+ if (ret)
+ goto out;
+ }
+
+ if (ib_device_check_mandatory(device)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ INIT_LIST_HEAD(&device->event_handler_list);
+ INIT_LIST_HEAD(&device->client_data_list);
+ spin_lock_init(&device->event_handler_lock);
+ spin_lock_init(&device->client_data_lock);
+
+ ret = ib_device_register_sysfs(device);
+ if (ret) {
+ printk(KERN_WARNING "Couldn't register device %s with driver model\n",
+ device->name);
+ goto out;
+ }
+
+ list_add_tail(&device->core_list, &device_list);
+
+ device->reg_state = IB_DEV_REGISTERED;
+
+ {
+ struct ib_client *client;
+
+ list_for_each_entry(client, &client_list, list)
+ if (client->add && !add_client_context(device, client))
+ client->add(device);
+ }
+
+ out:
+ up(&device_sem);
+ return ret;
+}
+EXPORT_SYMBOL(ib_register_device);
+
+/**
+ * ib_unregister_device - Unregister an IB device
+ * @device:Device to unregister
+ *
+ * Unregister an IB device. All clients will receive a remove callback.
+ */
+void ib_unregister_device(struct ib_device *device)
+{
+ struct ib_client *client;
+ struct ib_client_data *context, *tmp;
+ unsigned long flags;
+
+ down(&device_sem);
+
+ list_for_each_entry_reverse(client, &client_list, list)
+ if (client->remove)
+ client->remove(device);
+
+ list_del(&device->core_list);
+
+ up(&device_sem);
+
+ spin_lock_irqsave(&device->client_data_lock, flags);
+ list_for_each_entry_safe(context, tmp, &device->client_data_list, list)
+ kfree(context);
+ spin_unlock_irqrestore(&device->client_data_lock, flags);
+
+ device->reg_state = IB_DEV_UNREGISTERED;
+}
+EXPORT_SYMBOL(ib_unregister_device);
+
+/**
+ * ib_register_client - Register an IB client
+ * @client:Client to register
+ *
+ * Upper level users of the IB drivers can use ib_register_client() to
+ * register callbacks for IB device addition and removal. When an IB
+ * device is added, each registered client's add method will be called
+ * (in the order the clients were registered), and when a device is
+ * removed, each client's remove method will be called (in the reverse
+ * order that clients were registered). In addition, when
+ * ib_register_client() is called, the client will receive an add
+ * callback for all devices already registered.
+ */
+int ib_register_client(struct ib_client *client)
+{
+ struct ib_device *device;
+
+ down(&device_sem);
+
+ list_add_tail(&client->list, &client_list);
+ list_for_each_entry(device, &device_list, core_list)
+ if (client->add && !add_client_context(device, client))
+ client->add(device);
+
+ up(&device_sem);
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_register_client);
+
+/**
+ * ib_unregister_client - Unregister an IB client
+ * @client:Client to unregister
+ *
+ * Upper level users use ib_unregister_client() to remove their client
+ * registration. When ib_unregister_client() is called, the client
+ * will receive a remove callback for each IB device still registered.
+ */
+void ib_unregister_client(struct ib_client *client)
+{
+ struct ib_client_data *context, *tmp;
+ struct ib_device *device;
+ unsigned long flags;
+
+ down(&device_sem);
+
+ list_for_each_entry(device, &device_list, core_list) {
+ if (client->remove)
+ client->remove(device);
+
+ spin_lock_irqsave(&device->client_data_lock, flags);
+ list_for_each_entry_safe(context, tmp, &device->client_data_list, list)
+ if (context->client == client) {
+ list_del(&context->list);
+ kfree(context);
+ }
+ spin_unlock_irqrestore(&device->client_data_lock, flags);
+ }
+ list_del(&client->list);
+
+ up(&device_sem);
+}
+EXPORT_SYMBOL(ib_unregister_client);
+
+/**
+ * ib_get_client_data - Get IB client context
+ * @device:Device to get context for
+ * @client:Client to get context for
+ *
+ * ib_get_client_data() returns client context set with
+ * ib_set_client_data().
+ */
+void *ib_get_client_data(struct ib_device *device, struct ib_client *client)
+{
+ struct ib_client_data *context;
+ void *ret = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&device->client_data_lock, flags);
+ list_for_each_entry(context, &device->client_data_list, list)
+ if (context->client == client) {
+ ret = context->data;
+ break;
+ }
+ spin_unlock_irqrestore(&device->client_data_lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_get_client_data);
+
+/**
+ * ib_set_client_data - Get IB client context
+ * @device:Device to set context for
+ * @client:Client to set context for
+ * @data:Context to set
+ *
+ * ib_set_client_data() sets client context that can be retrieved with
+ * ib_get_client_data().
+ */
+void ib_set_client_data(struct ib_device *device, struct ib_client *client,
+ void *data)
+{
+ struct ib_client_data *context;
+ unsigned long flags;
+
+ spin_lock_irqsave(&device->client_data_lock, flags);
+ list_for_each_entry(context, &device->client_data_list, list)
+ if (context->client == client) {
+ context->data = data;
+ goto out;
+ }
+
+ printk(KERN_WARNING "No client context found for %s/%s\n",
+ device->name, client->name);
+
+out:
+ spin_unlock_irqrestore(&device->client_data_lock, flags);
+}
+EXPORT_SYMBOL(ib_set_client_data);
+
+/**
+ * ib_register_event_handler - Register an IB event handler
+ * @event_handler:Handler to register
+ *
+ * ib_register_event_handler() registers an event handler that will be
+ * called back when asynchronous IB events occur (as defined in
+ * chapter 11 of the InfiniBand Architecture Specification). This
+ * callback may occur in interrupt context.
+ */
+int ib_register_event_handler (struct ib_event_handler *event_handler)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
+ list_add_tail(&event_handler->list,
+ &event_handler->device->event_handler_list);
+ spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_register_event_handler);
+
+/**
+ * ib_unregister_event_handler - Unregister an event handler
+ * @event_handler:Handler to unregister
+ *
+ * Unregister an event handler registered with
+ * ib_register_event_handler().
+ */
+int ib_unregister_event_handler(struct ib_event_handler *event_handler)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
+ list_del(&event_handler->list);
+ spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_unregister_event_handler);
+
+/**
+ * ib_dispatch_event - Dispatch an asynchronous event
+ * @event:Event to dispatch
+ *
+ * Low-level drivers must call ib_dispatch_event() to dispatch the
+ * event to all registered event handlers when an asynchronous event
+ * occurs.
+ */
+void ib_dispatch_event(struct ib_event *event)
+{
+ unsigned long flags;
+ struct ib_event_handler *handler;
+
+ spin_lock_irqsave(&event->device->event_handler_lock, flags);
+
+ list_for_each_entry(handler, &event->device->event_handler_list, list)
+ handler->handler(handler, event);
+
+ spin_unlock_irqrestore(&event->device->event_handler_lock, flags);
+}
+EXPORT_SYMBOL(ib_dispatch_event);
+
+/**
+ * ib_query_device - Query IB device attributes
+ * @device:Device to query
+ * @device_attr:Device attributes
+ *
+ * ib_query_device() returns the attributes of a device through the
+ * @device_attr pointer.
+ */
+int ib_query_device(struct ib_device *device,
+ struct ib_device_attr *device_attr)
+{
+ return device->query_device(device, device_attr);
+}
+EXPORT_SYMBOL(ib_query_device);
+
+/**
+ * ib_query_port - Query IB port attributes
+ * @device:Device to query
+ * @port_num:Port number to query
+ * @port_attr:Port attributes
+ *
+ * ib_query_port() returns the attributes of a port through the
+ * @port_attr pointer.
+ */
+int ib_query_port(struct ib_device *device,
+ u8 port_num,
+ struct ib_port_attr *port_attr)
+{
+ return device->query_port(device, port_num, port_attr);
+}
+EXPORT_SYMBOL(ib_query_port);
+
+/**
+ * ib_query_gid - Get GID table entry
+ * @device:Device to query
+ * @port_num:Port number to query
+ * @index:GID table index to query
+ * @gid:Returned GID
+ *
+ * ib_query_gid() fetches the specified GID table entry.
+ */
+int ib_query_gid(struct ib_device *device,
+ u8 port_num, int index, union ib_gid *gid)
+{
+ return device->query_gid(device, port_num, index, gid);
+}
+EXPORT_SYMBOL(ib_query_gid);
+
+/**
+ * ib_query_pkey - Get P_Key table entry
+ * @device:Device to query
+ * @port_num:Port number to query
+ * @index:P_Key table index to query
+ * @pkey:Returned P_Key
+ *
+ * ib_query_pkey() fetches the specified P_Key table entry.
+ */
+int ib_query_pkey(struct ib_device *device,
+ u8 port_num, u16 index, u16 *pkey)
+{
+ return device->query_pkey(device, port_num, index, pkey);
+}
+EXPORT_SYMBOL(ib_query_pkey);
+
+/**
+ * ib_modify_device - Change IB device attributes
+ * @device:Device to modify
+ * @device_modify_mask:Mask of attributes to change
+ * @device_modify:New attribute values
+ *
+ * ib_modify_device() changes a device's attributes as specified by
+ * the @device_modify_mask and @device_modify structure.
+ */
+int ib_modify_device(struct ib_device *device,
+ int device_modify_mask,
+ struct ib_device_modify *device_modify)
+{
+ return device->modify_device(device, device_modify_mask,
+ device_modify);
+}
+EXPORT_SYMBOL(ib_modify_device);
+
+/**
+ * ib_modify_port - Modifies the attributes for the specified port.
+ * @device: The device to modify.
+ * @port_num: The number of the port to modify.
+ * @port_modify_mask: Mask used to specify which attributes of the port
+ * to change.
+ * @port_modify: New attribute values for the port.
+ *
+ * ib_modify_port() changes a port's attributes as specified by the
+ * @port_modify_mask and @port_modify structure.
+ */
+int ib_modify_port(struct ib_device *device,
+ u8 port_num, int port_modify_mask,
+ struct ib_port_modify *port_modify)
+{
+ return device->modify_port(device, port_num, port_modify_mask,
+ port_modify);
+}
+EXPORT_SYMBOL(ib_modify_port);
+
+static int __init ib_core_init(void)
+{
+ int ret;
+
+ ret = ib_sysfs_setup();
+ if (ret)
+ printk(KERN_WARNING "Couldn't create InfiniBand device class\n");
+
+ ret = ib_cache_setup();
+ if (ret) {
+ printk(KERN_WARNING "Couldn't set up InfiniBand P_Key/GID cache\n");
+ ib_sysfs_cleanup();
+ }
+
+ return ret;
+}
+
+static void __exit ib_core_cleanup(void)
+{
+ ib_cache_cleanup();
+ ib_sysfs_cleanup();
+}
+
+module_init(ib_core_init);
+module_exit(ib_core_cleanup);
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/fmr_pool.c 2004-12-13 09:44:40.476762425 -0800
@@ -0,0 +1,496 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Communications. All rights reserved.
+ *
+ * $Id: fmr_pool.c 1294 2004-11-25 19:17:57Z roland $
+ */
+
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/jhash.h>
+#include <linux/kthread.h>
+
+#include <ib_fmr_pool.h>
+
+#include "core_priv.h"
+
+enum {
+ IB_FMR_MAX_REMAPS = 32,
+
+ IB_FMR_HASH_BITS = 8,
+ IB_FMR_HASH_SIZE = 1 << IB_FMR_HASH_BITS,
+ IB_FMR_HASH_MASK = IB_FMR_HASH_SIZE - 1
+};
+
+/*
+ * If an FMR is not in use, then the list member will point to either
+ * its pool's free_list (if the FMR can be mapped again; that is,
+ * remap_count < IB_FMR_MAX_REMAPS) or its pool's dirty_list (if the
+ * FMR needs to be unmapped before being remapped). In either of
+ * these cases it is a bug if the ref_count is not 0. In other words,
+ * if ref_count is > 0, then the list member must not be linked into
+ * either free_list or dirty_list.
+ *
+ * The cache_node member is used to link the FMR into a cache bucket
+ * (if caching is enabled). This is independent of the reference
+ * count of the FMR. When a valid FMR is released, its ref_count is
+ * decremented, and if ref_count reaches 0, the FMR is placed in
+ * either free_list or dirty_list as appropriate. However, it is not
+ * removed from the cache and may be "revived" if a call to
+ * ib_fmr_register_physical() occurs before the FMR is remapped. In
+ * this case we just increment the ref_count and remove the FMR from
+ * free_list/dirty_list.
+ *
+ * Before we remap an FMR from free_list, we remove it from the cache
+ * (to prevent another user from obtaining a stale FMR). When an FMR
+ * is released, we add it to the tail of the free list, so that our
+ * cache eviction policy is "least recently used."
+ *
+ * All manipulation of ref_count, list and cache_node is protected by
+ * pool_lock to maintain consistency.
+ */
+
+struct ib_fmr_pool {
+ spinlock_t pool_lock;
+
+ int pool_size;
+ int max_pages;
+ int dirty_watermark;
+ int dirty_len;
+ struct list_head free_list;
+ struct list_head dirty_list;
+ struct hlist_head *cache_bucket;
+
+ void (*flush_function)(struct ib_fmr_pool *pool,
+ void * arg);
+ void *flush_arg;
+
+ struct task_struct *thread;
+
+ atomic_t req_ser;
+ atomic_t flush_ser;
+
+ wait_queue_head_t force_wait;
+};
+
+static inline u32 ib_fmr_hash(u64 first_page)
+{
+ return jhash_2words((u32) first_page,
+ (u32) (first_page >> 32),
+ 0);
+}
+
+/* Caller must hold pool_lock */
+static inline struct ib_pool_fmr *ib_fmr_cache_lookup(struct ib_fmr_pool *pool,
+ u64 *page_list,
+ int page_list_len,
+ u64 io_virtual_address)
+{
+ struct hlist_head *bucket;
+ struct ib_pool_fmr *fmr;
+ struct hlist_node *pos;
+
+ if (!pool->cache_bucket)
+ return NULL;
+
+ bucket = pool->cache_bucket + ib_fmr_hash(*page_list);
+
+ hlist_for_each_entry(fmr, pos, bucket, cache_node)
+ if (io_virtual_address == fmr->io_virtual_address &&
+ page_list_len == fmr->page_list_len &&
+ !memcmp(page_list, fmr->page_list,
+ page_list_len * sizeof *page_list))
+ return fmr;
+
+ return NULL;
+}
+
+static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
+{
+ int ret;
+ struct ib_pool_fmr *fmr;
+ LIST_HEAD(unmap_list);
+ LIST_HEAD(fmr_list);
+
+ spin_lock_irq(&pool->pool_lock);
+
+ list_for_each_entry(fmr, &pool->dirty_list, list) {
+ hlist_del_init(&fmr->cache_node);
+ fmr->remap_count = 0;
+ list_add_tail(&fmr->fmr->list, &fmr_list);
+
+#ifdef DEBUG
+ if (fmr->ref_count !=0) {
+ printk(KERN_WARNING "Unmapping FMR 0x%08x with ref count %d",
+ fmr, fmr->ref_count);
+ }
+#endif
+ }
+
+ list_splice(&pool->dirty_list, &unmap_list);
+ INIT_LIST_HEAD(&pool->dirty_list);
+ pool->dirty_len = 0;
+
+ spin_unlock_irq(&pool->pool_lock);
+
+ if (list_empty(&unmap_list)) {
+ return;
+ }
+
+ ret = ib_unmap_fmr(&fmr_list);
+ if (ret)
+ printk(KERN_WARNING "ib_unmap_fmr returned %d", ret);
+
+ spin_lock_irq(&pool->pool_lock);
+ list_splice(&unmap_list, &pool->free_list);
+ spin_unlock_irq(&pool->pool_lock);
+}
+
+static int ib_fmr_cleanup_thread(void *pool_ptr)
+{
+ struct ib_fmr_pool *pool = pool_ptr;
+
+ do {
+ if (pool->dirty_len >= pool->dirty_watermark ||
+ atomic_read(&pool->flush_ser) - atomic_read(&pool->req_ser) < 0) {
+ ib_fmr_batch_release(pool);
+
+ atomic_inc(&pool->flush_ser);
+ wake_up_interruptible(&pool->force_wait);
+
+ if (pool->flush_function)
+ pool->flush_function(pool, pool->flush_arg);
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (pool->dirty_len < pool->dirty_watermark &&
+ atomic_read(&pool->flush_ser) - atomic_read(&pool->req_ser) >= 0 &&
+ !kthread_should_stop())
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ } while (!kthread_should_stop());
+
+ return 0;
+}
+
+/**
+ * ib_create_fmr_pool - Create an FMR pool
+ * @pd:Protection domain for FMRs
+ * @params:FMR pool parameters
+ *
+ * Create a pool of FMRs. Return value is pointer to new pool or
+ * error code if creation failed.
+ */
+struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd *pd,
+ struct ib_fmr_pool_param *params)
+{
+ struct ib_device *device;
+ struct ib_fmr_pool *pool;
+ int i;
+ int ret;
+
+ if (!params)
+ return ERR_PTR(-EINVAL);
+
+ device = pd->device;
+ if (!device->alloc_fmr || !device->dealloc_fmr ||
+ !device->map_phys_fmr || !device->unmap_fmr) {
+ printk(KERN_WARNING "Device %s does not support fast memory regions",
+ device->name);
+ return ERR_PTR(-ENOSYS);
+ }
+
+ pool = kmalloc(sizeof *pool, GFP_KERNEL);
+ if (!pool) {
+ printk(KERN_WARNING "couldn't allocate pool struct");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ pool->cache_bucket = NULL;
+
+ pool->flush_function = params->flush_function;
+ pool->flush_arg = params->flush_arg;
+
+ INIT_LIST_HEAD(&pool->free_list);
+ INIT_LIST_HEAD(&pool->dirty_list);
+
+ if (params->cache) {
+ pool->cache_bucket =
+ kmalloc(IB_FMR_HASH_SIZE * sizeof *pool->cache_bucket,
+ GFP_KERNEL);
+ if (!pool->cache_bucket) {
+ printk(KERN_WARNING "Failed to allocate cache in pool");
+ ret = -ENOMEM;
+ goto out_free_pool;
+ }
+
+ for (i = 0; i < IB_FMR_HASH_SIZE; ++i)
+ INIT_HLIST_HEAD(pool->cache_bucket + i);
+ }
+
+ pool->pool_size = 0;
+ pool->max_pages = params->max_pages_per_fmr;
+ pool->dirty_watermark = params->dirty_watermark;
+ pool->dirty_len = 0;
+ spin_lock_init(&pool->pool_lock);
+ atomic_set(&pool->req_ser, 0);
+ atomic_set(&pool->flush_ser, 0);
+ init_waitqueue_head(&pool->force_wait);
+
+ pool->thread = kthread_create(ib_fmr_cleanup_thread,
+ pool,
+ "ib_fmr(%s)",
+ device->name);
+ if (IS_ERR(pool->thread)) {
+ printk(KERN_WARNING "couldn't start cleanup thread");
+ ret = PTR_ERR(pool->thread);
+ goto out_free_pool;
+ }
+
+ {
+ struct ib_pool_fmr *fmr;
+ struct ib_fmr_attr attr = {
+ .max_pages = params->max_pages_per_fmr,
+ .max_maps = IB_FMR_MAX_REMAPS,
+ .page_size = PAGE_SHIFT
+ };
+
+ for (i = 0; i < params->pool_size; ++i) {
+ fmr = kmalloc(sizeof *fmr + params->max_pages_per_fmr * sizeof (u64),
+ GFP_KERNEL);
+ if (!fmr) {
+ printk(KERN_WARNING "failed to allocate fmr struct "
+ "for FMR %d", i);
+ goto out_fail;
+ }
+
+ fmr->pool = pool;
+ fmr->remap_count = 0;
+ fmr->ref_count = 0;
+ INIT_HLIST_NODE(&fmr->cache_node);
+
+ fmr->fmr = ib_alloc_fmr(pd, params->access, &attr);
+ if (IS_ERR(fmr->fmr)) {
+ printk(KERN_WARNING "fmr_create failed for FMR %d", i);
+ kfree(fmr);
+ goto out_fail;
+ }
+
+ list_add_tail(&fmr->list, &pool->free_list);
+ ++pool->pool_size;
+ }
+ }
+
+ return pool;
+
+ out_free_pool:
+ kfree(pool->cache_bucket);
+ kfree(pool);
+
+ return ERR_PTR(ret);
+
+ out_fail:
+ ib_destroy_fmr_pool(pool);
+
+ return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL(ib_create_fmr_pool);
+
+/**
+ * ib_destroy_fmr_pool - Free FMR pool
+ * @pool:FMR pool to free
+ *
+ * Destroy an FMR pool and free all associated resources.
+ */
+int ib_destroy_fmr_pool(struct ib_fmr_pool *pool)
+{
+ struct ib_pool_fmr *fmr;
+ struct ib_pool_fmr *tmp;
+ int i;
+
+ kthread_stop(pool->thread);
+ ib_fmr_batch_release(pool);
+
+ i = 0;
+ list_for_each_entry_safe(fmr, tmp, &pool->free_list, list) {
+ ib_dealloc_fmr(fmr->fmr);
+ list_del(&fmr->list);
+ kfree(fmr);
+ ++i;
+ }
+
+ if (i < pool->pool_size)
+ printk(KERN_WARNING "pool still has %d regions registered",
+ pool->pool_size - i);
+
+ kfree(pool->cache_bucket);
+ kfree(pool);
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_destroy_fmr_pool);
+
+/**
+ * ib_flush_fmr_pool - Invalidate all unmapped FMRs
+ * @pool:FMR pool to flush
+ *
+ * Ensure that all unmapped FMRs are fully invalidated.
+ */
+int ib_flush_fmr_pool(struct ib_fmr_pool *pool)
+{
+ int serial;
+
+ atomic_inc(&pool->req_ser);
+ /*
+ * It's OK if someone else bumps req_ser again here -- we'll
+ * just wait a little longer.
+ */
+ serial = atomic_read(&pool->req_ser);
+
+ wake_up_process(pool->thread);
+
+ if (wait_event_interruptible(pool->force_wait,
+ atomic_read(&pool->flush_ser) -
+ atomic_read(&pool->req_ser) >= 0))
+ return -EINTR;
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_flush_fmr_pool);
+
+/**
+ * ib_fmr_pool_map_phys -
+ * @pool:FMR pool to allocate FMR from
+ * @page_list:List of pages to map
+ * @list_len:Number of pages in @page_list
+ * @io_virtual_address:I/O virtual address for new FMR
+ *
+ * Map an FMR from an FMR pool.
+ */
+struct ib_pool_fmr *ib_fmr_pool_map_phys(struct ib_fmr_pool *pool_handle,
+ u64 *page_list,
+ int list_len,
+ u64 *io_virtual_address)
+{
+ struct ib_fmr_pool *pool = pool_handle;
+ struct ib_pool_fmr *fmr;
+ unsigned long flags;
+ int result;
+
+ if (list_len < 1 || list_len > pool->max_pages)
+ return ERR_PTR(-EINVAL);
+
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ fmr = ib_fmr_cache_lookup(pool,
+ page_list,
+ list_len,
+ *io_virtual_address);
+ if (fmr) {
+ /* found in cache */
+ ++fmr->ref_count;
+ if (fmr->ref_count == 1) {
+ list_del(&fmr->list);
+ }
+
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return fmr;
+ }
+
+ if (list_empty(&pool->free_list)) {
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+ return ERR_PTR(-EAGAIN);
+ }
+
+ fmr = list_entry(pool->free_list.next, struct ib_pool_fmr, list);
+ list_del(&fmr->list);
+ hlist_del_init(&fmr->cache_node);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ result = ib_map_phys_fmr(fmr->fmr, page_list, list_len,
+ *io_virtual_address);
+
+ if (result) {
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ list_add(&fmr->list, &pool->free_list);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ printk(KERN_WARNING "fmr_map returns %d",
+ result);
+
+ return ERR_PTR(result);
+ }
+
+ ++fmr->remap_count;
+ fmr->ref_count = 1;
+
+ if (pool->cache_bucket) {
+ fmr->io_virtual_address = *io_virtual_address;
+ fmr->page_list_len = list_len;
+ memcpy(fmr->page_list, page_list, list_len * sizeof(*page_list));
+
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ hlist_add_head(&fmr->cache_node,
+ pool->cache_bucket + ib_fmr_hash(fmr->page_list[0]));
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+ }
+
+ return fmr;
+}
+EXPORT_SYMBOL(ib_fmr_pool_map_phys);
+
+/**
+ * ib_fmr_pool_unmap - Unmap FMR
+ * @fmr:FMR to unmap
+ *
+ * Unmap an FMR. The FMR mapping may remain valid until the FMR is
+ * reused (or until ib_flush_fmr_pool() is called).
+ */
+int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr)
+{
+ struct ib_fmr_pool *pool;
+ unsigned long flags;
+
+ pool = fmr->pool;
+
+ spin_lock_irqsave(&pool->pool_lock, flags);
+
+ --fmr->ref_count;
+ if (!fmr->ref_count) {
+ if (fmr->remap_count < IB_FMR_MAX_REMAPS) {
+ list_add_tail(&fmr->list, &pool->free_list);
+ } else {
+ list_add_tail(&fmr->list, &pool->dirty_list);
+ ++pool->dirty_len;
+ wake_up_process(pool->thread);
+ }
+ }
+
+#ifdef DEBUG
+ if (fmr->ref_count < 0)
+ printk(KERN_WARNING "FMR %p has ref count %d < 0",
+ fmr, fmr->ref_count);
+#endif
+
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_fmr_pool_unmap);
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/packer.c 2004-12-13 09:44:40.335783194 -0800
@@ -0,0 +1,190 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ *
+ * $Id: packer.c 1292 2004-11-25 05:24:40Z roland $
+ */
+
+#include <ib_pack.h>
+
+static u64 value_read(int offset, int size, void *structure)
+{
+ switch (size) {
+ case 1: return *(u8 *) (structure + offset);
+ case 2: return be16_to_cpup((__be16 *) (structure + offset));
+ case 4: return be32_to_cpup((__be32 *) (structure + offset));
+ case 8: return be64_to_cpup((__be64 *) (structure + offset));
+ default:
+ printk(KERN_WARNING "Field size %d bits not handled\n", size * 8);
+ return 0;
+ }
+}
+
+/**
+ * ib_pack - Pack a structure into a buffer
+ * @desc:Array of structure field descriptions
+ * @desc_len:Number of entries in @desc
+ * @structure:Structure to pack from
+ * @buf:Buffer to pack into
+ *
+ * ib_pack() packs a list of structure fields into a buffer,
+ * controlled by the array of fields in @desc.
+ */
+void ib_pack(const struct ib_field *desc,
+ int desc_len,
+ void *structure,
+ void *buf)
+{
+ int i;
+
+ for (i = 0; i < desc_len; ++i) {
+ if (desc[i].size_bits <= 32) {
+ int shift;
+ u32 val;
+ __be32 mask;
+ __be32 *addr;
+
+ shift = 32 - desc[i].offset_bits - desc[i].size_bits;
+ if (desc[i].struct_size_bytes)
+ val = value_read(desc[i].struct_offset_bytes,
+ desc[i].struct_size_bytes,
+ structure) << shift;
+ else
+ val = 0;
+
+ mask = cpu_to_be32(((1ull << desc[i].size_bits) - 1) << shift);
+ addr = (__be32 *) buf + desc[i].offset_words;
+ *addr = (*addr & ~mask) | (cpu_to_be32(val) & mask);
+ } else if (desc[i].size_bits <= 64) {
+ int shift;
+ u64 val;
+ __be64 mask;
+ __be64 *addr;
+
+ shift = 64 - desc[i].offset_bits - desc[i].size_bits;
+ if (desc[i].struct_size_bytes)
+ val = value_read(desc[i].struct_offset_bytes,
+ desc[i].struct_size_bytes,
+ structure) << shift;
+ else
+ val = 0;
+
+ mask = cpu_to_be64(((1ull << desc[i].size_bits) - 1) << shift);
+ addr = (__be64 *) ((__be32 *) buf + desc[i].offset_words);
+ *addr = (*addr & ~mask) | (cpu_to_be64(val) & mask);
+ } else {
+ if (desc[i].offset_bits % 8 ||
+ desc[i].size_bits % 8) {
+ printk(KERN_WARNING "Structure field %s of size %d "
+ "bits is not byte-aligned\n",
+ desc[i].field_name, desc[i].size_bits);
+ }
+
+ if (desc[i].struct_size_bytes)
+ memcpy(buf + desc[i].offset_words * 4 +
+ desc[i].offset_bits / 8,
+ structure + desc[i].struct_offset_bytes,
+ desc[i].size_bits / 8);
+ else
+ memset(buf + desc[i].offset_words * 4 +
+ desc[i].offset_bits / 8,
+ 0,
+ desc[i].size_bits / 8);
+ }
+ }
+}
+EXPORT_SYMBOL(ib_pack);
+
+static void value_write(int offset, int size, u64 val, void *structure)
+{
+ switch (size * 8) {
+ case 8: *( u8 *) (structure + offset) = val; break;
+ case 16: *(__be16 *) (structure + offset) = cpu_to_be16(val); break;
+ case 32: *(__be32 *) (structure + offset) = cpu_to_be32(val); break;
+ case 64: *(__be64 *) (structure + offset) = cpu_to_be64(val); break;
+ default:
+ printk(KERN_WARNING "Field size %d bits not handled\n", size * 8);
+ }
+}
+
+/**
+ * ib_unpack - Unpack a buffer into a structure
+ * @desc:Array of structure field descriptions
+ * @desc_len:Number of entries in @desc
+ * @buf:Buffer to unpack from
+ * @structure:Structure to unpack into
+ *
+ * ib_pack() unpacks a list of structure fields from a buffer,
+ * controlled by the array of fields in @desc.
+ */
+void ib_unpack(const struct ib_field *desc,
+ int desc_len,
+ void *buf,
+ void *structure)
+{
+ int i;
+
+ for (i = 0; i < desc_len; ++i) {
+ if (!desc[i].struct_size_bytes)
+ continue;
+
+ if (desc[i].size_bits <= 32) {
+ int shift;
+ u32 val;
+ u32 mask;
+ __be32 *addr;
+
+ shift = 32 - desc[i].offset_bits - desc[i].size_bits;
+ mask = ((1ull << desc[i].size_bits) - 1) << shift;
+ addr = (__be32 *) buf + desc[i].offset_words;
+ val = (be32_to_cpup(addr) & mask) >> shift;
+ value_write(desc[i].struct_offset_bytes,
+ desc[i].struct_size_bytes,
+ val,
+ structure);
+ } else if (desc[i].size_bits <= 64) {
+ int shift;
+ u64 val;
+ u64 mask;
+ __be64 *addr;
+
+ shift = 64 - desc[i].offset_bits - desc[i].size_bits;
+ mask = ((1ull << desc[i].size_bits) - 1) << shift;
+ addr = (__be64 *) buf + desc[i].offset_words;
+ val = (be64_to_cpup(addr) & mask) >> shift;
+ value_write(desc[i].struct_offset_bytes,
+ desc[i].struct_size_bytes,
+ val,
+ structure);
+ } else {
+ if (desc[i].offset_bits % 8 ||
+ desc[i].size_bits % 8) {
+ printk(KERN_WARNING "Structure field %s of size %d "
+ "bits is not byte-aligned\n",
+ desc[i].field_name, desc[i].size_bits);
+ }
+
+ memcpy(structure + desc[i].struct_offset_bytes,
+ buf + desc[i].offset_words * 4 +
+ desc[i].offset_bits / 8,
+ desc[i].size_bits / 8);
+ }
+ }
+}
+EXPORT_SYMBOL(ib_unpack);
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/sysfs.c 2004-12-13 09:44:40.421770527 -0800
@@ -0,0 +1,684 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Communications. All rights reserved.
+ *
+ * $Id: sysfs.c 1257 2004-11-17 23:12:18Z roland $
+ */
+
+#include "core_priv.h"
+
+#include <ib_mad.h>
+
+struct ib_port {
+ struct kobject kobj;
+ struct ib_device *ibdev;
+ struct attribute_group gid_group;
+ struct attribute **gid_attr;
+ struct attribute_group pkey_group;
+ struct attribute **pkey_attr;
+ u8 port_num;
+};
+
+struct port_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct ib_port *, struct port_attribute *, char *buf);
+ ssize_t (*store)(struct ib_port *, struct port_attribute *,
+ const char *buf, size_t count);
+};
+
+#define PORT_ATTR(_name, _mode, _show, _store) \
+struct port_attribute port_attr_##_name = __ATTR(_name, _mode, _show, _store)
+
+#define PORT_ATTR_RO(_name) \
+struct port_attribute port_attr_##_name = __ATTR_RO(_name)
+
+struct port_table_attribute {
+ struct port_attribute attr;
+ int index;
+};
+
+static ssize_t port_attr_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct port_attribute *port_attr =
+ container_of(attr, struct port_attribute, attr);
+ struct ib_port *p = container_of(kobj, struct ib_port, kobj);
+
+ if (!port_attr->show)
+ return 0;
+
+ return port_attr->show(p, port_attr, buf);
+}
+
+static struct sysfs_ops port_sysfs_ops = {
+ .show = port_attr_show
+};
+
+static ssize_t state_show(struct ib_port *p, struct port_attribute *unused,
+ char *buf)
+{
+ struct ib_port_attr attr;
+ ssize_t ret;
+
+ static const char *state_name[] = {
+ [IB_PORT_NOP] = "NOP",
+ [IB_PORT_DOWN] = "DOWN",
+ [IB_PORT_INIT] = "INIT",
+ [IB_PORT_ARMED] = "ARMED",
+ [IB_PORT_ACTIVE] = "ACTIVE",
+ [IB_PORT_ACTIVE_DEFER] = "ACTIVE_DEFER"
+ };
+
+ ret = ib_query_port(p->ibdev, p->port_num, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%d: %s\n", attr.state,
+ attr.state >= 0 && attr.state <= ARRAY_SIZE(state_name) ?
+ state_name[attr.state] : "UNKNOWN");
+}
+
+static ssize_t lid_show(struct ib_port *p, struct port_attribute *unused,
+ char *buf)
+{
+ struct ib_port_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_port(p->ibdev, p->port_num, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "0x%x\n", attr.lid);
+}
+
+static ssize_t lid_mask_count_show(struct ib_port *p,
+ struct port_attribute *unused,
+ char *buf)
+{
+ struct ib_port_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_port(p->ibdev, p->port_num, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%d\n", attr.lmc);
+}
+
+static ssize_t sm_lid_show(struct ib_port *p, struct port_attribute *unused,
+ char *buf)
+{
+ struct ib_port_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_port(p->ibdev, p->port_num, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "0x%x\n", attr.sm_lid);
+}
+
+static ssize_t sm_sl_show(struct ib_port *p, struct port_attribute *unused,
+ char *buf)
+{
+ struct ib_port_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_port(p->ibdev, p->port_num, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%d\n", attr.sm_sl);
+}
+
+static ssize_t cap_mask_show(struct ib_port *p, struct port_attribute *unused,
+ char *buf)
+{
+ struct ib_port_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_port(p->ibdev, p->port_num, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "0x%08x\n", attr.port_cap_flags);
+}
+
+static PORT_ATTR_RO(state);
+static PORT_ATTR_RO(lid);
+static PORT_ATTR_RO(lid_mask_count);
+static PORT_ATTR_RO(sm_lid);
+static PORT_ATTR_RO(sm_sl);
+static PORT_ATTR_RO(cap_mask);
+
+static struct attribute *port_default_attrs[] = {
+ &port_attr_state.attr,
+ &port_attr_lid.attr,
+ &port_attr_lid_mask_count.attr,
+ &port_attr_sm_lid.attr,
+ &port_attr_sm_sl.attr,
+ &port_attr_cap_mask.attr,
+ NULL
+};
+
+static ssize_t show_port_gid(struct ib_port *p, struct port_attribute *attr,
+ char *buf)
+{
+ struct port_table_attribute *tab_attr =
+ container_of(attr, struct port_table_attribute, attr);
+ union ib_gid gid;
+ ssize_t ret;
+
+ ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n",
+ be16_to_cpu(((u16 *) gid.raw)[0]),
+ be16_to_cpu(((u16 *) gid.raw)[1]),
+ be16_to_cpu(((u16 *) gid.raw)[2]),
+ be16_to_cpu(((u16 *) gid.raw)[3]),
+ be16_to_cpu(((u16 *) gid.raw)[4]),
+ be16_to_cpu(((u16 *) gid.raw)[5]),
+ be16_to_cpu(((u16 *) gid.raw)[6]),
+ be16_to_cpu(((u16 *) gid.raw)[7]));
+}
+
+static ssize_t show_port_pkey(struct ib_port *p, struct port_attribute *attr,
+ char *buf)
+{
+ struct port_table_attribute *tab_attr =
+ container_of(attr, struct port_table_attribute, attr);
+ u16 pkey;
+ ssize_t ret;
+
+ ret = ib_query_pkey(p->ibdev, p->port_num, tab_attr->index, &pkey);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "0x%04x\n", pkey);
+}
+
+#define PORT_PMA_ATTR(_name, _counter, _width, _offset) \
+struct port_table_attribute port_pma_attr_##_name = { \
+ .attr = __ATTR(_name, S_IRUGO, show_pma_counter, NULL), \
+ .index = (_offset) | ((_width) << 16) | ((_counter) << 24) \
+}
+
+static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
+ char *buf)
+{
+ struct port_table_attribute *tab_attr =
+ container_of(attr, struct port_table_attribute, attr);
+ int offset = tab_attr->index & 0xffff;
+ int width = (tab_attr->index >> 16) & 0xff;
+ struct ib_mad *in_mad = NULL;
+ struct ib_mad *out_mad = NULL;
+ ssize_t ret;
+
+ if (!p->ibdev->process_mad)
+ return sprintf(buf, "N/A (no PMA)\n");
+
+ in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ out_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ if (!in_mad || !out_mad) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ memset(in_mad, 0, sizeof *in_mad);
+ in_mad->mad_hdr.base_version = 1;
+ in_mad->mad_hdr.mgmt_class = IB_MGMT_CLASS_PERF_MGMT;
+ in_mad->mad_hdr.class_version = 1;
+ in_mad->mad_hdr.method = IB_MGMT_METHOD_GET;
+ in_mad->mad_hdr.attr_id = cpu_to_be16(0x12); /* PortCounters */
+
+ in_mad->data[41] = p->port_num; /* PortSelect field */
+
+ if ((p->ibdev->process_mad(p->ibdev, IB_MAD_IGNORE_MKEY, p->port_num, 0xffff,
+ in_mad, out_mad) &
+ (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) !=
+ (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ switch (width) {
+ case 4:
+ ret = sprintf(buf, "%u\n", (out_mad->data[40 + offset / 8] >>
+ (offset % 4)) & 0xf);
+ break;
+ case 8:
+ ret = sprintf(buf, "%u\n", out_mad->data[40 + offset / 8]);
+ break;
+ case 16:
+ ret = sprintf(buf, "%u\n",
+ be16_to_cpup((u16 *)(out_mad->data + 40 + offset / 8)));
+ break;
+ case 32:
+ ret = sprintf(buf, "%u\n",
+ be32_to_cpup((u32 *)(out_mad->data + 40 + offset / 8)));
+ break;
+ default:
+ ret = 0;
+ }
+
+out:
+ kfree(in_mad);
+ kfree(out_mad);
+
+ return ret;
+}
+
+static PORT_PMA_ATTR(symbol_error , 0, 16, 32);
+static PORT_PMA_ATTR(link_error_recovery , 1, 8, 48);
+static PORT_PMA_ATTR(link_downed , 2, 8, 56);
+static PORT_PMA_ATTR(port_rcv_errors , 3, 16, 64);
+static PORT_PMA_ATTR(port_rcv_remote_physical_errors, 4, 16, 80);
+static PORT_PMA_ATTR(port_rcv_switch_relay_errors , 5, 16, 96);
+static PORT_PMA_ATTR(port_xmit_discards , 6, 16, 112);
+static PORT_PMA_ATTR(port_xmit_constraint_errors , 7, 8, 128);
+static PORT_PMA_ATTR(port_rcv_constraint_errors , 8, 8, 136);
+static PORT_PMA_ATTR(local_link_integrity_errors , 9, 4, 152);
+static PORT_PMA_ATTR(excessive_buffer_overrun_errors, 10, 4, 156);
+static PORT_PMA_ATTR(VL15_dropped , 11, 16, 176);
+static PORT_PMA_ATTR(port_xmit_data , 12, 32, 192);
+static PORT_PMA_ATTR(port_rcv_data , 13, 32, 224);
+static PORT_PMA_ATTR(port_xmit_packets , 14, 32, 256);
+static PORT_PMA_ATTR(port_rcv_packets , 15, 32, 288);
+
+static struct attribute *pma_attrs[] = {
+ &port_pma_attr_symbol_error.attr.attr,
+ &port_pma_attr_link_error_recovery.attr.attr,
+ &port_pma_attr_link_downed.attr.attr,
+ &port_pma_attr_port_rcv_errors.attr.attr,
+ &port_pma_attr_port_rcv_remote_physical_errors.attr.attr,
+ &port_pma_attr_port_rcv_switch_relay_errors.attr.attr,
+ &port_pma_attr_port_xmit_discards.attr.attr,
+ &port_pma_attr_port_xmit_constraint_errors.attr.attr,
+ &port_pma_attr_port_rcv_constraint_errors.attr.attr,
+ &port_pma_attr_local_link_integrity_errors.attr.attr,
+ &port_pma_attr_excessive_buffer_overrun_errors.attr.attr,
+ &port_pma_attr_VL15_dropped.attr.attr,
+ &port_pma_attr_port_xmit_data.attr.attr,
+ &port_pma_attr_port_rcv_data.attr.attr,
+ &port_pma_attr_port_xmit_packets.attr.attr,
+ &port_pma_attr_port_rcv_packets.attr.attr,
+ NULL
+};
+
+static struct attribute_group pma_group = {
+ .name = "counters",
+ .attrs = pma_attrs
+};
+
+static void ib_port_release(struct kobject *kobj)
+{
+ struct ib_port *p = container_of(kobj, struct ib_port, kobj);
+ struct attribute *a;
+ int i;
+
+ for (i = 0; (a = p->gid_attr[i]); ++i) {
+ kfree(a->name);
+ kfree(a);
+ }
+
+ for (i = 0; (a = p->pkey_attr[i]); ++i) {
+ kfree(a->name);
+ kfree(a);
+ }
+
+ kfree(p->gid_attr);
+ kfree(p);
+}
+
+static struct kobj_type port_type = {
+ .release = ib_port_release,
+ .sysfs_ops = &port_sysfs_ops,
+ .default_attrs = port_default_attrs
+};
+
+static void ib_device_release(struct class_device *cdev)
+{
+ struct ib_device *dev = container_of(cdev, struct ib_device, class_dev);
+
+ kfree(dev);
+}
+
+static int ib_device_hotplug(struct class_device *cdev, char **envp,
+ int num_envp, char *buf, int size)
+{
+ struct ib_device *dev = container_of(cdev, struct ib_device, class_dev);
+ int i = 0, len = 0;
+
+ if (add_hotplug_env_var(envp, num_envp, &i, buf, size, &len,
+ "NAME=%s", dev->name))
+ return -ENOMEM;
+
+ /*
+ * It might be nice to pass the node GUID to hotplug, but
+ * right now the only way to get it is to query the device
+ * provider, and this can crash during device removal because
+ * we are will be running after driver removal has started.
+ * We could add a node_guid field to struct ib_device, or we
+ * could just let the hotplug script read the node GUID from
+ * sysfs when devices are added.
+ */
+
+ envp[i] = NULL;
+ return 0;
+}
+
+static int alloc_group(struct attribute ***attr,
+ ssize_t (*show)(struct ib_port *,
+ struct port_attribute *, char *buf),
+ int len)
+{
+ struct port_table_attribute ***tab_attr =
+ (struct port_table_attribute ***) attr;
+ int i;
+ int ret;
+
+ *tab_attr = kmalloc((1 + len) * sizeof *tab_attr, GFP_KERNEL);
+ if (!*tab_attr)
+ return -ENOMEM;
+
+ memset(*tab_attr, 0, (1 + len) * sizeof *tab_attr);
+
+ for (i = 0; i < len; ++i) {
+ (*tab_attr)[i] = kmalloc(sizeof *(*tab_attr)[i], GFP_KERNEL);
+ if (!(*tab_attr)[i]) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ memset((*tab_attr)[i], 0, sizeof *(*tab_attr)[i]);
+ (*tab_attr)[i]->attr.attr.name = kmalloc(8, GFP_KERNEL);
+ if (!(*tab_attr)[i]->attr.attr.name) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ if (snprintf((*tab_attr)[i]->attr.attr.name, 8, "%d", i) >= 8) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ (*tab_attr)[i]->attr.attr.mode = S_IRUGO;
+ (*tab_attr)[i]->attr.attr.owner = THIS_MODULE;
+ (*tab_attr)[i]->attr.show = show;
+ (*tab_attr)[i]->index = i;
+ }
+
+ return 0;
+
+err:
+ for (i = 0; i < len; ++i) {
+ if ((*tab_attr)[i])
+ kfree((*tab_attr)[i]->attr.attr.name);
+ kfree((*tab_attr)[i]);
+ }
+
+ kfree(*tab_attr);
+
+ return ret;
+}
+
+static int add_port(struct ib_device *device, int port_num)
+{
+ struct ib_port *p;
+ struct ib_port_attr attr;
+ int i;
+ int ret;
+
+ ret = ib_query_port(device, port_num, &attr);
+ if (ret)
+ return ret;
+
+ p = kmalloc(sizeof *p, GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+ memset(p, 0, sizeof *p);
+
+ p->ibdev = device;
+ p->port_num = port_num;
+ p->kobj.ktype = &port_type;
+
+ p->kobj.parent = kobject_get(&device->ports_parent);
+ if (!p->kobj.parent) {
+ ret = -EBUSY;
+ goto err;
+ }
+
+ ret = kobject_set_name(&p->kobj, "%d", port_num);
+ if (ret)
+ goto err_put;
+
+ ret = kobject_register(&p->kobj);
+ if (ret)
+ goto err_put;
+
+ ret = sysfs_create_group(&p->kobj, &pma_group);
+ if (ret)
+ goto err_put;
+
+ ret = alloc_group(&p->gid_attr, show_port_gid, attr.gid_tbl_len);
+ if (ret)
+ goto err_remove_pma;
+
+ p->gid_group.name = "gids";
+ p->gid_group.attrs = p->gid_attr;
+
+ ret = sysfs_create_group(&p->kobj, &p->gid_group);
+ if (ret)
+ goto err_free_gid;
+
+ ret = alloc_group(&p->pkey_attr, show_port_pkey, attr.pkey_tbl_len);
+ if (ret)
+ goto err_remove_gid;
+
+ p->pkey_group.name = "pkeys";
+ p->pkey_group.attrs = p->pkey_attr;
+
+ ret = sysfs_create_group(&p->kobj, &p->pkey_group);
+ if (ret)
+ goto err_free_pkey;
+
+ list_add_tail(&p->kobj.entry, &device->port_list);
+
+ return 0;
+
+err_free_pkey:
+ for (i = 0; i < attr.pkey_tbl_len; ++i) {
+ kfree(p->pkey_attr[i]->name);
+ kfree(p->pkey_attr[i]);
+ }
+
+ kfree(p->pkey_attr);
+
+err_remove_gid:
+ sysfs_remove_group(&p->kobj, &p->gid_group);
+
+err_free_gid:
+ for (i = 0; i < attr.gid_tbl_len; ++i) {
+ kfree(p->gid_attr[i]->name);
+ kfree(p->gid_attr[i]);
+ }
+
+ kfree(p->gid_attr);
+
+err_remove_pma:
+ sysfs_remove_group(&p->kobj, &pma_group);
+
+err_put:
+ kobject_put(&device->ports_parent);
+
+err:
+ kfree(p);
+ return ret;
+}
+
+static ssize_t show_sys_image_guid(struct class_device *cdev, char *buf)
+{
+ struct ib_device *dev = container_of(cdev, struct ib_device, class_dev);
+ struct ib_device_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_device(dev, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%04x:%04x:%04x:%04x\n",
+ be16_to_cpu(((u16 *) &attr.sys_image_guid)[0]),
+ be16_to_cpu(((u16 *) &attr.sys_image_guid)[1]),
+ be16_to_cpu(((u16 *) &attr.sys_image_guid)[2]),
+ be16_to_cpu(((u16 *) &attr.sys_image_guid)[3]));
+}
+
+static ssize_t show_node_guid(struct class_device *cdev, char *buf)
+{
+ struct ib_device *dev = container_of(cdev, struct ib_device, class_dev);
+ struct ib_device_attr attr;
+ ssize_t ret;
+
+ ret = ib_query_device(dev, &attr);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%04x:%04x:%04x:%04x\n",
+ be16_to_cpu(((u16 *) &attr.node_guid)[0]),
+ be16_to_cpu(((u16 *) &attr.node_guid)[1]),
+ be16_to_cpu(((u16 *) &attr.node_guid)[2]),
+ be16_to_cpu(((u16 *) &attr.node_guid)[3]));
+}
+
+static CLASS_DEVICE_ATTR(sys_image_guid, S_IRUGO, show_sys_image_guid, NULL);
+static CLASS_DEVICE_ATTR(node_guid, S_IRUGO, show_node_guid, NULL);
+
+static struct class_device_attribute *ib_class_attributes[] = {
+ &class_device_attr_sys_image_guid,
+ &class_device_attr_node_guid
+};
+
+static struct class ib_class = {
+ .name = "infiniband",
+ .release = ib_device_release,
+ .hotplug = ib_device_hotplug,
+};
+
+int ib_device_register_sysfs(struct ib_device *device)
+{
+ struct class_device *class_dev = &device->class_dev;
+ int ret;
+ int i;
+
+ class_dev->class = &ib_class;
+ class_dev->class_data = device;
+ strlcpy(class_dev->class_id, device->name, BUS_ID_SIZE);
+
+ INIT_LIST_HEAD(&device->port_list);
+
+ ret = class_device_register(class_dev);
+ if (ret)
+ goto err;
+
+ for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i) {
+ ret = class_device_create_file(class_dev, ib_class_attributes[i]);
+ if (ret)
+ goto err_unregister;
+ }
+
+ device->ports_parent.parent = kobject_get(&class_dev->kobj);
+ if (!device->ports_parent.parent) {
+ ret = -EBUSY;
+ goto err_unregister;
+ }
+ ret = kobject_set_name(&device->ports_parent, "ports");
+ if (ret)
+ goto err_put;
+ ret = kobject_register(&device->ports_parent);
+ if (ret)
+ goto err_put;
+
+ if (device->node_type == IB_NODE_SWITCH) {
+ ret = add_port(device, 0);
+ if (ret)
+ goto err_put;
+ } else {
+ int i;
+
+ for (i = 1; i <= device->phys_port_cnt; ++i) {
+ ret = add_port(device, i);
+ if (ret)
+ goto err_put;
+ }
+ }
+
+ return 0;
+
+err_put:
+ {
+ struct kobject *p, *t;
+ struct ib_port *port;
+
+ list_for_each_entry_safe(p, t, &device->port_list, entry) {
+ list_del(&p->entry);
+ port = container_of(p, struct ib_port, kobj);
+ sysfs_remove_group(p, &pma_group);
+ sysfs_remove_group(p, &port->pkey_group);
+ sysfs_remove_group(p, &port->gid_group);
+ kobject_unregister(p);
+ }
+ }
+
+ kobject_put(&class_dev->kobj);
+
+err_unregister:
+ class_device_unregister(class_dev);
+
+err:
+ return ret;
+}
+
+void ib_device_unregister_sysfs(struct ib_device *device)
+{
+ struct kobject *p, *t;
+ struct ib_port *port;
+
+ list_for_each_entry_safe(p, t, &device->port_list, entry) {
+ list_del(&p->entry);
+ port = container_of(p, struct ib_port, kobj);
+ sysfs_remove_group(p, &pma_group);
+ sysfs_remove_group(p, &port->pkey_group);
+ sysfs_remove_group(p, &port->gid_group);
+ kobject_unregister(p);
+ }
+
+ kobject_unregister(&device->ports_parent);
+ class_device_unregister(&device->class_dev);
+}
+
+int ib_sysfs_setup(void)
+{
+ return class_register(&ib_class);
+}
+
+void ib_sysfs_cleanup(void)
+{
+ class_unregister(&ib_class);
+}
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/ud_header.c 2004-12-13 09:44:40.360779512 -0800
@@ -0,0 +1,354 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ *
+ * $Id: ud_header.c 1292 2004-11-25 05:24:40Z roland $
+ */
+
+#include <linux/errno.h>
+
+#include <ib_pack.h>
+
+#define STRUCT_FIELD(header, field) \
+ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \
+ .struct_size_bytes = sizeof ((struct ib_unpacked_ ## header *) 0)->field, \
+ .field_name = #header ":" #field
+
+static const struct ib_field lrh_table[] = {
+ { STRUCT_FIELD(lrh, virtual_lane),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 4 },
+ { STRUCT_FIELD(lrh, link_version),
+ .offset_words = 0,
+ .offset_bits = 4,
+ .size_bits = 4 },
+ { STRUCT_FIELD(lrh, service_level),
+ .offset_words = 0,
+ .offset_bits = 8,
+ .size_bits = 4 },
+ { RESERVED,
+ .offset_words = 0,
+ .offset_bits = 12,
+ .size_bits = 2 },
+ { STRUCT_FIELD(lrh, link_next_header),
+ .offset_words = 0,
+ .offset_bits = 14,
+ .size_bits = 2 },
+ { STRUCT_FIELD(lrh, destination_lid),
+ .offset_words = 0,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { RESERVED,
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 5 },
+ { STRUCT_FIELD(lrh, packet_length),
+ .offset_words = 1,
+ .offset_bits = 5,
+ .size_bits = 11 },
+ { STRUCT_FIELD(lrh, source_lid),
+ .offset_words = 1,
+ .offset_bits = 16,
+ .size_bits = 16 }
+};
+
+static const struct ib_field grh_table[] = {
+ { STRUCT_FIELD(grh, ip_version),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 4 },
+ { STRUCT_FIELD(grh, traffic_class),
+ .offset_words = 0,
+ .offset_bits = 4,
+ .size_bits = 8 },
+ { STRUCT_FIELD(grh, flow_label),
+ .offset_words = 0,
+ .offset_bits = 12,
+ .size_bits = 20 },
+ { STRUCT_FIELD(grh, payload_length),
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 16 },
+ { STRUCT_FIELD(grh, next_header),
+ .offset_words = 1,
+ .offset_bits = 16,
+ .size_bits = 8 },
+ { STRUCT_FIELD(grh, hop_limit),
+ .offset_words = 1,
+ .offset_bits = 24,
+ .size_bits = 8 },
+ { STRUCT_FIELD(grh, source_gid),
+ .offset_words = 2,
+ .offset_bits = 0,
+ .size_bits = 128 },
+ { STRUCT_FIELD(grh, destination_gid),
+ .offset_words = 6,
+ .offset_bits = 0,
+ .size_bits = 128 }
+};
+
+static const struct ib_field bth_table[] = {
+ { STRUCT_FIELD(bth, opcode),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 8 },
+ { STRUCT_FIELD(bth, solicited_event),
+ .offset_words = 0,
+ .offset_bits = 8,
+ .size_bits = 1 },
+ { STRUCT_FIELD(bth, mig_req),
+ .offset_words = 0,
+ .offset_bits = 9,
+ .size_bits = 1 },
+ { STRUCT_FIELD(bth, pad_count),
+ .offset_words = 0,
+ .offset_bits = 10,
+ .size_bits = 2 },
+ { STRUCT_FIELD(bth, transport_header_version),
+ .offset_words = 0,
+ .offset_bits = 12,
+ .size_bits = 4 },
+ { STRUCT_FIELD(bth, pkey),
+ .offset_words = 0,
+ .offset_bits = 16,
+ .size_bits = 16 },
+ { RESERVED,
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 8 },
+ { STRUCT_FIELD(bth, destination_qpn),
+ .offset_words = 1,
+ .offset_bits = 8,
+ .size_bits = 24 },
+ { STRUCT_FIELD(bth, ack_req),
+ .offset_words = 2,
+ .offset_bits = 0,
+ .size_bits = 1 },
+ { RESERVED,
+ .offset_words = 2,
+ .offset_bits = 1,
+ .size_bits = 7 },
+ { STRUCT_FIELD(bth, psn),
+ .offset_words = 2,
+ .offset_bits = 8,
+ .size_bits = 24 }
+};
+
+static const struct ib_field deth_table[] = {
+ { STRUCT_FIELD(deth, qkey),
+ .offset_words = 0,
+ .offset_bits = 0,
+ .size_bits = 32 },
+ { RESERVED,
+ .offset_words = 1,
+ .offset_bits = 0,
+ .size_bits = 8 },
+ { STRUCT_FIELD(deth, source_qpn),
+ .offset_words = 1,
+ .offset_bits = 8,
+ .size_bits = 24 }
+};
+
+/**
+ * ib_ud_header_init - Initialize UD header structure
+ * @payload_bytes:Length of packet payload
+ * @grh_present:GRH flag (if non-zero, GRH will be included)
+ * @header:Structure to initialize
+ *
+ * ib_ud_header_init() initializes the lrh.link_version, lrh.link_next_header,
+ * lrh.packet_length, grh.ip_version, grh.payload_length,
+ * grh.next_header, bth.opcode, bth.pad_count and
+ * bth.transport_header_version fields of a &struct ib_ud_header given
+ * the payload length and whether a GRH will be included.
+ */
+void ib_ud_header_init(int payload_bytes,
+ int grh_present,
+ struct ib_ud_header *header)
+{
+ int header_len;
+
+ memset(header, 0, sizeof *header);
+
+ header_len =
+ IB_LRH_BYTES +
+ IB_BTH_BYTES +
+ IB_DETH_BYTES;
+ if (grh_present) {
+ header_len += IB_GRH_BYTES;
+ }
+
+ header->lrh.link_version = 0;
+ header->lrh.link_next_header =
+ grh_present ? IB_LNH_IBA_GLOBAL : IB_LNH_IBA_LOCAL;
+ header->lrh.packet_length = (IB_LRH_BYTES +
+ IB_BTH_BYTES +
+ IB_DETH_BYTES +
+ payload_bytes +
+ 4 + /* ICRC */
+ 3) / 4; /* round up */
+
+ header->grh_present = grh_present;
+ if (grh_present) {
+ header->lrh.packet_length += IB_GRH_BYTES / 4;
+
+ header->grh.ip_version = 6;
+ header->grh.payload_length =
+ cpu_to_be16((IB_BTH_BYTES +
+ IB_DETH_BYTES +
+ payload_bytes +
+ 4 + /* ICRC */
+ 3) & ~3); /* round up */
+ header->grh.next_header = 0x1b;
+ }
+
+ cpu_to_be16s(&header->lrh.packet_length);
+
+ if (header->immediate_present)
+ header->bth.opcode = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE;
+ else
+ header->bth.opcode = IB_OPCODE_UD_SEND_ONLY;
+ header->bth.pad_count = (4 - payload_bytes) & 3;
+ header->bth.transport_header_version = 0;
+}
+EXPORT_SYMBOL(ib_ud_header_init);
+
+/**
+ * ib_ud_header_pack - Pack UD header struct into wire format
+ * @header:UD header struct
+ * @buf:Buffer to pack into
+ *
+ * ib_ud_header_pack() packs the UD header structure @header into wire
+ * format in the buffer @buf.
+ */
+int ib_ud_header_pack(struct ib_ud_header *header,
+ void *buf)
+{
+ int len = 0;
+
+ ib_pack(lrh_table, ARRAY_SIZE(lrh_table),
+ &header->lrh, buf);
+ len += IB_LRH_BYTES;
+
+ if (header->grh_present) {
+ ib_pack(grh_table, ARRAY_SIZE(grh_table),
+ &header->grh, buf + len);
+ len += IB_GRH_BYTES;
+ }
+
+ ib_pack(bth_table, ARRAY_SIZE(bth_table),
+ &header->bth, buf + len);
+ len += IB_BTH_BYTES;
+
+ ib_pack(deth_table, ARRAY_SIZE(deth_table),
+ &header->deth, buf + len);
+ len += IB_DETH_BYTES;
+
+ if (header->immediate_present) {
+ memcpy(buf + len, &header->immediate_data, sizeof header->immediate_data);
+ len += sizeof header->immediate_data;
+ }
+
+ return len;
+}
+EXPORT_SYMBOL(ib_ud_header_pack);
+
+/**
+ * ib_ud_header_unpack - Unpack UD header struct from wire format
+ * @header:UD header struct
+ * @buf:Buffer to pack into
+ *
+ * ib_ud_header_pack() unpacks the UD header structure @header from wire
+ * format in the buffer @buf.
+ */
+int ib_ud_header_unpack(void *buf,
+ struct ib_ud_header *header)
+{
+ ib_unpack(lrh_table, ARRAY_SIZE(lrh_table),
+ buf, &header->lrh);
+ buf += IB_LRH_BYTES;
+
+ if (header->lrh.link_version != 0) {
+ printk(KERN_WARNING "Invalid LRH.link_version %d\n",
+ header->lrh.link_version);
+ return -EINVAL;
+ }
+
+ switch (header->lrh.link_next_header) {
+ case IB_LNH_IBA_LOCAL:
+ header->grh_present = 0;
+ break;
+
+ case IB_LNH_IBA_GLOBAL:
+ header->grh_present = 1;
+ ib_unpack(grh_table, ARRAY_SIZE(grh_table),
+ buf, &header->grh);
+ buf += IB_GRH_BYTES;
+
+ if (header->grh.ip_version != 6) {
+ printk(KERN_WARNING "Invalid GRH.ip_version %d\n",
+ header->grh.ip_version);
+ return -EINVAL;
+ }
+ if (header->grh.next_header != 0x1b) {
+ printk(KERN_WARNING "Invalid GRH.next_header 0x%02x\n",
+ header->grh.next_header);
+ return -EINVAL;
+ }
+ break;
+
+ default:
+ printk(KERN_WARNING "Invalid LRH.link_next_header %d\n",
+ header->lrh.link_next_header);
+ return -EINVAL;
+ }
+
+ ib_unpack(bth_table, ARRAY_SIZE(bth_table),
+ buf, &header->bth);
+ buf += IB_BTH_BYTES;
+
+ switch (header->bth.opcode) {
+ case IB_OPCODE_UD_SEND_ONLY:
+ header->immediate_present = 0;
+ break;
+ case IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE:
+ header->immediate_present = 1;
+ break;
+ default:
+ printk(KERN_WARNING "Invalid BTH.opcode 0x%02x\n",
+ header->bth.opcode);
+ return -EINVAL;
+ }
+
+ if (header->bth.transport_header_version != 0) {
+ printk(KERN_WARNING "Invalid BTH.transport_header_version %d\n",
+ header->bth.transport_header_version);
+ return -EINVAL;
+ }
+
+ ib_unpack(deth_table, ARRAY_SIZE(deth_table),
+ buf, &header->deth);
+ buf += IB_DETH_BYTES;
+
+ if (header->immediate_present)
+ memcpy(&header->immediate_data, buf, sizeof header->immediate_data);
+
+ return 0;
+}
+EXPORT_SYMBOL(ib_ud_header_unpack);
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/core/verbs.c 2004-12-13 09:44:40.392774798 -0800
@@ -0,0 +1,420 @@
+/*
+ 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 at
+ <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ license, available in the LICENSE.TXT file accompanying this
+ software. These details are also available at
+ <http://openib.org/license.html>.
+
+ 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.
+
+ Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved.
+ Copyright (c) 2004 Infinicon Corporation. All rights reserved.
+ Copyright (c) 2004 Intel Corporation. All rights reserved.
+ Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ Copyright (c) 2004 Voltaire Corporation. All rights reserved.
+*/
+
+#include <linux/errno.h>
+#include <linux/err.h>
+
+#include <ib_verbs.h>
+
+/* Protection domains */
+
+struct ib_pd *ib_alloc_pd(struct ib_device *device)
+{
+ struct ib_pd *pd;
+
+ pd = device->alloc_pd(device);
+
+ if (!IS_ERR(pd)) {
+ pd->device = device;
+ atomic_set(&pd->usecnt, 0);
+ }
+
+ return pd;
+}
+EXPORT_SYMBOL(ib_alloc_pd);
+
+int ib_dealloc_pd(struct ib_pd *pd)
+{
+ if (atomic_read(&pd->usecnt))
+ return -EBUSY;
+
+ return pd->device->dealloc_pd(pd);
+}
+EXPORT_SYMBOL(ib_dealloc_pd);
+
+/* Address handles */
+
+struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+{
+ struct ib_ah *ah;
+
+ ah = pd->device->create_ah(pd, ah_attr);
+
+ if (!IS_ERR(ah)) {
+ ah->device = pd->device;
+ ah->pd = pd;
+ atomic_inc(&pd->usecnt);
+ }
+
+ return ah;
+}
+EXPORT_SYMBOL(ib_create_ah);
+
+int ib_modify_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr)
+{
+ return ah->device->modify_ah ?
+ ah->device->modify_ah(ah, ah_attr) :
+ -ENOSYS;
+}
+EXPORT_SYMBOL(ib_modify_ah);
+
+int ib_query_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr)
+{
+ return ah->device->query_ah ?
+ ah->device->query_ah(ah, ah_attr) :
+ -ENOSYS;
+}
+EXPORT_SYMBOL(ib_query_ah);
+
+int ib_destroy_ah(struct ib_ah *ah)
+{
+ struct ib_pd *pd;
+ int ret;
+
+ pd = ah->pd;
+ ret = ah->device->destroy_ah(ah);
+ if (!ret)
+ atomic_dec(&pd->usecnt);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_destroy_ah);
+
+/* Queue pairs */
+
+struct ib_qp *ib_create_qp(struct ib_pd *pd,
+ struct ib_qp_init_attr *qp_init_attr)
+{
+ struct ib_qp *qp;
+
+ qp = pd->device->create_qp(pd, qp_init_attr);
+
+ if (!IS_ERR(qp)) {
+ qp->device = pd->device;
+ qp->pd = pd;
+ qp->send_cq = qp_init_attr->send_cq;
+ qp->recv_cq = qp_init_attr->recv_cq;
+ qp->srq = qp_init_attr->srq;
+ qp->event_handler = qp_init_attr->event_handler;
+ qp->qp_context = qp_init_attr->qp_context;
+ atomic_inc(&pd->usecnt);
+ atomic_inc(&qp_init_attr->send_cq->usecnt);
+ atomic_inc(&qp_init_attr->recv_cq->usecnt);
+ if (qp_init_attr->srq)
+ atomic_inc(&qp_init_attr->srq->usecnt);
+ }
+
+ return qp;
+}
+EXPORT_SYMBOL(ib_create_qp);
+
+int ib_modify_qp(struct ib_qp *qp,
+ struct ib_qp_attr *qp_attr,
+ int qp_attr_mask)
+{
+ return qp->device->modify_qp(qp, qp_attr, qp_attr_mask);
+}
+EXPORT_SYMBOL(ib_modify_qp);
+
+int ib_query_qp(struct ib_qp *qp,
+ struct ib_qp_attr *qp_attr,
+ int qp_attr_mask,
+ struct ib_qp_init_attr *qp_init_attr)
+{
+ return qp->device->query_qp ?
+ qp->device->query_qp(qp, qp_attr, qp_attr_mask, qp_init_attr) :
+ -ENOSYS;
+}
+EXPORT_SYMBOL(ib_query_qp);
+
+int ib_destroy_qp(struct ib_qp *qp)
+{
+ struct ib_pd *pd;
+ struct ib_cq *scq, *rcq;
+ struct ib_srq *srq;
+ int ret;
+
+ pd = qp->pd;
+ scq = qp->send_cq;
+ rcq = qp->recv_cq;
+ srq = qp->srq;
+
+ ret = qp->device->destroy_qp(qp);
+ if (!ret) {
+ atomic_dec(&pd->usecnt);
+ atomic_dec(&scq->usecnt);
+ atomic_dec(&rcq->usecnt);
+ if (srq)
+ atomic_dec(&srq->usecnt);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_destroy_qp);
+
+/* Completion queues */
+
+struct ib_cq *ib_create_cq(struct ib_device *device,
+ ib_comp_handler comp_handler,
+ void (*event_handler)(struct ib_event *, void *),
+ void *cq_context, int cqe)
+{
+ struct ib_cq *cq;
+
+ cq = device->create_cq(device, cqe);
+
+ if (!IS_ERR(cq)) {
+ cq->device = device;
+ cq->comp_handler = comp_handler;
+ cq->event_handler = event_handler;
+ cq->cq_context = cq_context;
+ atomic_set(&cq->usecnt, 0);
+ }
+
+ return cq;
+}
+EXPORT_SYMBOL(ib_create_cq);
+
+int ib_destroy_cq(struct ib_cq *cq)
+{
+ if (atomic_read(&cq->usecnt))
+ return -EBUSY;
+
+ return cq->device->destroy_cq(cq);
+}
+EXPORT_SYMBOL(ib_destroy_cq);
+
+int ib_resize_cq(struct ib_cq *cq,
+ int cqe)
+{
+ int ret;
+
+ if (!cq->device->resize_cq)
+ return -ENOSYS;
+
+ ret = cq->device->resize_cq(cq, &cqe);
+ if (!ret)
+ cq->cqe = cqe;
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_resize_cq);
+
+/* Memory regions */
+
+struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags)
+{
+ struct ib_mr *mr;
+
+ mr = pd->device->get_dma_mr(pd, mr_access_flags);
+
+ if (!IS_ERR(mr)) {
+ mr->device = pd->device;
+ mr->pd = pd;
+ atomic_inc(&pd->usecnt);
+ atomic_set(&mr->usecnt, 0);
+ }
+
+ return mr;
+}
+EXPORT_SYMBOL(ib_get_dma_mr);
+
+struct ib_mr *ib_reg_phys_mr(struct ib_pd *pd,
+ struct ib_phys_buf *phys_buf_array,
+ int num_phys_buf,
+ int mr_access_flags,
+ u64 *iova_start)
+{
+ struct ib_mr *mr;
+
+ mr = pd->device->reg_phys_mr(pd, phys_buf_array, num_phys_buf,
+ mr_access_flags, iova_start);
+
+ if (!IS_ERR(mr)) {
+ mr->device = pd->device;
+ mr->pd = pd;
+ atomic_inc(&pd->usecnt);
+ atomic_set(&mr->usecnt, 0);
+ }
+
+ return mr;
+}
+EXPORT_SYMBOL(ib_reg_phys_mr);
+
+int ib_rereg_phys_mr(struct ib_mr *mr,
+ int mr_rereg_mask,
+ struct ib_pd *pd,
+ struct ib_phys_buf *phys_buf_array,
+ int num_phys_buf,
+ int mr_access_flags,
+ u64 *iova_start)
+{
+ struct ib_pd *old_pd;
+ int ret;
+
+ if (!mr->device->rereg_phys_mr)
+ return -ENOSYS;
+
+ if (atomic_read(&mr->usecnt))
+ return -EBUSY;
+
+ old_pd = mr->pd;
+
+ ret = mr->device->rereg_phys_mr(mr, mr_rereg_mask, pd,
+ phys_buf_array, num_phys_buf,
+ mr_access_flags, iova_start);
+
+ if (!ret && (mr_rereg_mask & IB_MR_REREG_PD)) {
+ atomic_dec(&old_pd->usecnt);
+ atomic_inc(&pd->usecnt);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_rereg_phys_mr);
+
+int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr)
+{
+ return mr->device->query_mr ?
+ mr->device->query_mr(mr, mr_attr) : -ENOSYS;
+}
+EXPORT_SYMBOL(ib_query_mr);
+
+int ib_dereg_mr(struct ib_mr *mr)
+{
+ struct ib_pd *pd;
+ int ret;
+
+ if (atomic_read(&mr->usecnt))
+ return -EBUSY;
+
+ pd = mr->pd;
+ ret = mr->device->dereg_mr(mr);
+ if (!ret)
+ atomic_dec(&pd->usecnt);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_dereg_mr);
+
+/* Memory windows */
+
+struct ib_mw *ib_alloc_mw(struct ib_pd *pd)
+{
+ struct ib_mw *mw;
+
+ if (!pd->device->alloc_mw)
+ return ERR_PTR(-ENOSYS);
+
+ mw = pd->device->alloc_mw(pd);
+ if (!IS_ERR(mw)) {
+ mw->device = pd->device;
+ mw->pd = pd;
+ atomic_inc(&pd->usecnt);
+ }
+
+ return mw;
+}
+EXPORT_SYMBOL(ib_alloc_mw);
+
+int ib_dealloc_mw(struct ib_mw *mw)
+{
+ struct ib_pd *pd;
+ int ret;
+
+ pd = mw->pd;
+ ret = mw->device->dealloc_mw(mw);
+ if (!ret)
+ atomic_dec(&pd->usecnt);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_dealloc_mw);
+
+/* "Fast" memory regions */
+
+struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd,
+ int mr_access_flags,
+ struct ib_fmr_attr *fmr_attr)
+{
+ struct ib_fmr *fmr;
+
+ if (!pd->device->alloc_fmr)
+ return ERR_PTR(-ENOSYS);
+
+ fmr = pd->device->alloc_fmr(pd, mr_access_flags, fmr_attr);
+ if (!IS_ERR(fmr)) {
+ fmr->device = pd->device;
+ fmr->pd = pd;
+ atomic_inc(&pd->usecnt);
+ }
+
+ return fmr;
+}
+EXPORT_SYMBOL(ib_alloc_fmr);
+
+int ib_unmap_fmr(struct list_head *fmr_list)
+{
+ struct ib_fmr *fmr;
+
+ if (list_empty(fmr_list))
+ return 0;
+
+ fmr = list_entry(fmr_list->next, struct ib_fmr, list);
+ return fmr->device->unmap_fmr(fmr_list);
+}
+EXPORT_SYMBOL(ib_unmap_fmr);
+
+int ib_dealloc_fmr(struct ib_fmr *fmr)
+{
+ struct ib_pd *pd;
+ int ret;
+
+ pd = fmr->pd;
+ ret = fmr->device->dealloc_fmr(fmr);
+ if (!ret)
+ atomic_dec(&pd->usecnt);
+
+ return ret;
+}
+EXPORT_SYMBOL(ib_dealloc_fmr);
+
+/* Multicast groups */
+
+int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
+{
+ return qp->device->attach_mcast ?
+ qp->device->attach_mcast(qp, gid, lid) :
+ -ENOSYS;
+}
+EXPORT_SYMBOL(ib_attach_mcast);
+
+int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
+{
+ return qp->device->detach_mcast ?
+ qp->device->detach_mcast(qp, gid, lid) :
+ -ENOSYS;
+}
+EXPORT_SYMBOL(ib_detach_mcast);
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH][v3][3/21] Hook up drivers/infiniband
2004-12-13 18:09 ` [PATCH][v3][2/21] Add core InfiniBand support Roland Dreier
@ 2004-12-13 18:09 ` Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][4/21] Add InfiniBand MAD (management datagram) support (public headers) Roland Dreier
0 siblings, 1 reply; 5+ messages in thread
From: Roland Dreier @ 2004-12-13 18:09 UTC (permalink / raw)
To: linux-kernel; +Cc: openib-general
Add the appropriate lines to drivers/Kconfig and drivers/Makefile so
that the kernel configuration and build systems know about drivers/infiniband.
Signed-off-by: Roland Dreier <roland@topspin.com>
--- linux-bk.orig/drivers/Kconfig 2004-12-11 15:16:34.000000000 -0800
+++ linux-bk/drivers/Kconfig 2004-12-13 09:44:41.933547814 -0800
@@ -54,4 +54,6 @@
source "drivers/usb/Kconfig"
+source "drivers/infiniband/Kconfig"
+
endmenu
--- linux-bk.orig/drivers/Makefile 2004-12-11 15:16:49.000000000 -0800
+++ linux-bk/drivers/Makefile 2004-12-13 09:44:41.953544868 -0800
@@ -59,4 +59,5 @@
obj-$(CONFIG_EISA) += eisa/
obj-$(CONFIG_CPU_FREQ) += cpufreq/
obj-$(CONFIG_MMC) += mmc/
+obj-$(CONFIG_INFINIBAND) += infiniband/
obj-y += firmware/
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH][v3][4/21] Add InfiniBand MAD (management datagram) support (public headers)
2004-12-13 18:09 ` [PATCH][v3][3/21] Hook up drivers/infiniband Roland Dreier
@ 2004-12-13 18:09 ` Roland Dreier
0 siblings, 0 replies; 5+ messages in thread
From: Roland Dreier @ 2004-12-13 18:09 UTC (permalink / raw)
To: linux-kernel; +Cc: openib-general
Add public headers for handling InfiniBand MADs (management
datagrams), including sending and receiving MADs as well as passing
MADs on to local agents.
Signed-off-by: Roland Dreier <roland@topspin.com>
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/include/ib_mad.h 2004-12-13 09:44:42.628445443 -0800
@@ -0,0 +1,393 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved.
+ * Copyright (c) 2004 Infinicon Corporation. All rights reserved.
+ * Copyright (c) 2004 Intel Corporation. All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation. All rights reserved.
+ *
+ * $Id$
+ */
+
+#if !defined( IB_MAD_H )
+#define IB_MAD_H
+
+#include <ib_verbs.h>
+
+/* Management base version */
+#define IB_MGMT_BASE_VERSION 1
+
+/* Management classes */
+#define IB_MGMT_CLASS_SUBN_LID_ROUTED 0x01
+#define IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE 0x81
+#define IB_MGMT_CLASS_SUBN_ADM 0x03
+#define IB_MGMT_CLASS_PERF_MGMT 0x04
+#define IB_MGMT_CLASS_BM 0x05
+#define IB_MGMT_CLASS_DEVICE_MGMT 0x06
+#define IB_MGMT_CLASS_CM 0x07
+#define IB_MGMT_CLASS_SNMP 0x08
+#define IB_MGMT_CLASS_VENDOR_RANGE2_START 0x30
+#define IB_MGMT_CLASS_VENDOR_RANGE2_END 0x4F
+
+/* Management methods */
+#define IB_MGMT_METHOD_GET 0x01
+#define IB_MGMT_METHOD_SET 0x02
+#define IB_MGMT_METHOD_GET_RESP 0x81
+#define IB_MGMT_METHOD_SEND 0x03
+#define IB_MGMT_METHOD_TRAP 0x05
+#define IB_MGMT_METHOD_REPORT 0x06
+#define IB_MGMT_METHOD_REPORT_RESP 0x86
+#define IB_MGMT_METHOD_TRAP_REPRESS 0x07
+
+#define IB_MGMT_METHOD_RESP 0x80
+
+#define IB_MGMT_MAX_METHODS 128
+
+#define IB_QP0 0
+#define IB_QP1 cpu_to_be32(1)
+#define IB_QP1_QKEY 0x80010000
+
+struct ib_grh {
+ u32 version_tclass_flow;
+ u16 paylen;
+ u8 next_hdr;
+ u8 hop_limit;
+ union ib_gid sgid;
+ union ib_gid dgid;
+} __attribute__ ((packed));
+
+struct ib_mad_hdr {
+ u8 base_version;
+ u8 mgmt_class;
+ u8 class_version;
+ u8 method;
+ u16 status;
+ u16 class_specific;
+ u64 tid;
+ u16 attr_id;
+ u16 resv;
+ u32 attr_mod;
+} __attribute__ ((packed));
+
+struct ib_rmpp_hdr {
+ u8 rmpp_version;
+ u8 rmpp_type;
+ u8 rmpp_rtime_flags;
+ u8 rmpp_status;
+ u32 seg_num;
+ u32 paylen_newwin;
+} __attribute__ ((packed));
+
+struct ib_mad {
+ struct ib_mad_hdr mad_hdr;
+ u8 data[232];
+} __attribute__ ((packed));
+
+struct ib_rmpp_mad {
+ struct ib_mad_hdr mad_hdr;
+ struct ib_rmpp_hdr rmpp_hdr;
+ u8 data[220];
+} __attribute__ ((packed));
+
+struct ib_vendor_mad {
+ struct ib_mad_hdr mad_hdr;
+ struct ib_rmpp_hdr rmpp_hdr;
+ u8 reserved;
+ u8 oui[3];
+ u8 data[216];
+} __attribute__ ((packed));
+
+struct ib_mad_agent;
+struct ib_mad_send_wc;
+struct ib_mad_recv_wc;
+
+/**
+ * ib_mad_send_handler - callback handler for a sent MAD.
+ * @mad_agent: MAD agent that sent the MAD.
+ * @mad_send_wc: Send work completion information on the sent MAD.
+ */
+typedef void (*ib_mad_send_handler)(struct ib_mad_agent *mad_agent,
+ struct ib_mad_send_wc *mad_send_wc);
+
+/**
+ * ib_mad_snoop_handler - Callback handler for snooping sent MADs.
+ * @mad_agent: MAD agent that snooped the MAD.
+ * @send_wr: Work request information on the sent MAD.
+ * @mad_send_wc: Work completion information on the sent MAD. Valid
+ * only for snooping that occurs on a send completion.
+ *
+ * Clients snooping MADs should not modify data referenced by the @send_wr
+ * or @mad_send_wc.
+ */
+typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
+ struct ib_send_wr *send_wr,
+ struct ib_mad_send_wc *mad_send_wc);
+
+/**
+ * ib_mad_recv_handler - callback handler for a received MAD.
+ * @mad_agent: MAD agent requesting the received MAD.
+ * @mad_recv_wc: Received work completion information on the received MAD.
+ *
+ * MADs received in response to a send request operation will be handed to
+ * the user after the send operation completes. All data buffers given
+ * to registered agents through this routine are owned by the receiving
+ * client, except for snooping agents. Clients snooping MADs should not
+ * modify the data referenced by @mad_recv_wc.
+ */
+typedef void (*ib_mad_recv_handler)(struct ib_mad_agent *mad_agent,
+ struct ib_mad_recv_wc *mad_recv_wc);
+
+/**
+ * ib_mad_agent - Used to track MAD registration with the access layer.
+ * @device: Reference to device registration is on.
+ * @qp: Reference to QP used for sending and receiving MADs.
+ * @recv_handler: Callback handler for a received MAD.
+ * @send_handler: Callback handler for a sent MAD.
+ * @snoop_handler: Callback handler for snooped sent MADs.
+ * @context: User-specified context associated with this registration.
+ * @hi_tid: Access layer assigned transaction ID for this client.
+ * Unsolicited MADs sent by this client will have the upper 32-bits
+ * of their TID set to this value.
+ * @port_num: Port number on which QP is registered
+ */
+struct ib_mad_agent {
+ struct ib_device *device;
+ struct ib_qp *qp;
+ ib_mad_recv_handler recv_handler;
+ ib_mad_send_handler send_handler;
+ ib_mad_snoop_handler snoop_handler;
+ void *context;
+ u32 hi_tid;
+ u8 port_num;
+};
+
+/**
+ * ib_mad_send_wc - MAD send completion information.
+ * @wr_id: Work request identifier associated with the send MAD request.
+ * @status: Completion status.
+ * @vendor_err: Optional vendor error information returned with a failed
+ * request.
+ */
+struct ib_mad_send_wc {
+ u64 wr_id;
+ enum ib_wc_status status;
+ u32 vendor_err;
+};
+
+/**
+ * ib_mad_recv_buf - received MAD buffer information.
+ * @list: Reference to next data buffer for a received RMPP MAD.
+ * @grh: References a data buffer containing the global route header.
+ * The data refereced by this buffer is only valid if the GRH is
+ * valid.
+ * @mad: References the start of the received MAD.
+ */
+struct ib_mad_recv_buf {
+ struct list_head list;
+ struct ib_grh *grh;
+ struct ib_mad *mad;
+};
+
+/**
+ * ib_mad_recv_wc - received MAD information.
+ * @wc: Completion information for the received data.
+ * @recv_buf: Specifies the location of the received data buffer(s).
+ * @mad_len: The length of the received MAD, without duplicated headers.
+ *
+ * For received response, the wr_id field of the wc is set to the wr_id
+ * for the corresponding send request.
+ */
+struct ib_mad_recv_wc {
+ struct ib_wc *wc;
+ struct ib_mad_recv_buf recv_buf;
+ int mad_len;
+};
+
+/**
+ * ib_mad_reg_req - MAD registration request
+ * @mgmt_class: Indicates which management class of MADs should be receive
+ * by the caller. This field is only required if the user wishes to
+ * receive unsolicited MADs, otherwise it should be 0.
+ * @mgmt_class_version: Indicates which version of MADs for the given
+ * management class to receive.
+ * @oui: Indicates IEEE OUI when mgmt_class is a vendor class
+ * in the range from 0x30 to 0x4f. Otherwise not used.
+ * @method_mask: The caller will receive unsolicited MADs for any method
+ * where @method_mask = 1.
+ */
+struct ib_mad_reg_req {
+ u8 mgmt_class;
+ u8 mgmt_class_version;
+ u8 oui[3];
+ DECLARE_BITMAP(method_mask, IB_MGMT_MAX_METHODS);
+};
+
+/**
+ * ib_register_mad_agent - Register to send/receive MADs.
+ * @device: The device to register with.
+ * @port_num: The port on the specified device to use.
+ * @qp_type: Specifies which QP to access. Must be either
+ * IB_QPT_SMI or IB_QPT_GSI.
+ * @mad_reg_req: Specifies which unsolicited MADs should be received
+ * by the caller. This parameter may be NULL if the caller only
+ * wishes to receive solicited responses.
+ * @rmpp_version: If set, indicates that the client will send
+ * and receive MADs that contain the RMPP header for the given version.
+ * If set to 0, indicates that RMPP is not used by this client.
+ * @send_handler: The completion callback routine invoked after a send
+ * request has completed.
+ * @recv_handler: The completion callback routine invoked for a received
+ * MAD.
+ * @context: User specified context associated with the registration.
+ */
+struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
+ u8 port_num,
+ enum ib_qp_type qp_type,
+ struct ib_mad_reg_req *mad_reg_req,
+ u8 rmpp_version,
+ ib_mad_send_handler send_handler,
+ ib_mad_recv_handler recv_handler,
+ void *context);
+
+enum ib_mad_snoop_flags {
+ /*IB_MAD_SNOOP_POSTED_SENDS = 1,*/
+ /*IB_MAD_SNOOP_RMPP_SENDS = (1<<1),*/
+ IB_MAD_SNOOP_SEND_COMPLETIONS = (1<<2),
+ /*IB_MAD_SNOOP_RMPP_SEND_COMPLETIONS = (1<<3),*/
+ IB_MAD_SNOOP_RECVS = (1<<4)
+ /*IB_MAD_SNOOP_RMPP_RECVS = (1<<5),*/
+ /*IB_MAD_SNOOP_REDIRECTED_QPS = (1<<6)*/
+};
+
+/**
+ * ib_register_mad_snoop - Register to snoop sent and received MADs.
+ * @device: The device to register with.
+ * @port_num: The port on the specified device to use.
+ * @qp_type: Specifies which QP traffic to snoop. Must be either
+ * IB_QPT_SMI or IB_QPT_GSI.
+ * @mad_snoop_flags: Specifies information where snooping occurs.
+ * @send_handler: The callback routine invoked for a snooped send.
+ * @recv_handler: The callback routine invoked for a snooped receive.
+ * @context: User specified context associated with the registration.
+ */
+struct ib_mad_agent *ib_register_mad_snoop(struct ib_device *device,
+ u8 port_num,
+ enum ib_qp_type qp_type,
+ int mad_snoop_flags,
+ ib_mad_snoop_handler snoop_handler,
+ ib_mad_recv_handler recv_handler,
+ void *context);
+
+/**
+ * ib_unregister_mad_agent - Unregisters a client from using MAD services.
+ * @mad_agent: Corresponding MAD registration request to deregister.
+ *
+ * After invoking this routine, MAD services are no longer usable by the
+ * client on the associated QP.
+ */
+int ib_unregister_mad_agent(struct ib_mad_agent *mad_agent);
+
+/**
+ * ib_post_send_mad - Posts MAD(s) to the send queue of the QP associated
+ * with the registered client.
+ * @mad_agent: Specifies the associated registration to post the send to.
+ * @send_wr: Specifies the information needed to send the MAD(s).
+ * @bad_send_wr: Specifies the MAD on which an error was encountered.
+ *
+ * Sent MADs are not guaranteed to complete in the order that they were posted.
+ */
+int ib_post_send_mad(struct ib_mad_agent *mad_agent,
+ struct ib_send_wr *send_wr,
+ struct ib_send_wr **bad_send_wr);
+
+/**
+ * ib_coalesce_recv_mad - Coalesces received MAD data into a single buffer.
+ * @mad_recv_wc: Work completion information for a received MAD.
+ * @buf: User-provided data buffer to receive the coalesced buffers. The
+ * referenced buffer should be at least the size of the mad_len specified
+ * by @mad_recv_wc.
+ *
+ * This call copies a chain of received RMPP MADs into a single data buffer,
+ * removing duplicated headers.
+ */
+void ib_coalesce_recv_mad(struct ib_mad_recv_wc *mad_recv_wc,
+ void *buf);
+
+/**
+ * ib_free_recv_mad - Returns data buffers used to receive a MAD to the
+ * access layer.
+ * @mad_recv_wc: Work completion information for a received MAD.
+ *
+ * Clients receiving MADs through their ib_mad_recv_handler must call this
+ * routine to return the work completion buffers to the access layer.
+ */
+void ib_free_recv_mad(struct ib_mad_recv_wc *mad_recv_wc);
+
+/**
+ * ib_cancel_mad - Cancels an outstanding send MAD operation.
+ * @mad_agent: Specifies the registration associated with sent MAD.
+ * @wr_id: Indicates the work request identifier of the MAD to cancel.
+ *
+ * MADs will be returned to the user through the corresponding
+ * ib_mad_send_handler.
+ */
+void ib_cancel_mad(struct ib_mad_agent *mad_agent,
+ u64 wr_id);
+
+/**
+ * ib_redirect_mad_qp - Registers a QP for MAD services.
+ * @qp: Reference to a QP that requires MAD services.
+ * @rmpp_version: If set, indicates that the client will send
+ * and receive MADs that contain the RMPP header for the given version.
+ * If set to 0, indicates that RMPP is not used by this client.
+ * @send_handler: The completion callback routine invoked after a send
+ * request has completed.
+ * @recv_handler: The completion callback routine invoked for a received
+ * MAD.
+ * @context: User specified context associated with the registration.
+ *
+ * Use of this call allows clients to use MAD services, such as RMPP,
+ * on user-owned QPs. After calling this routine, users may send
+ * MADs on the specified QP by calling ib_mad_post_send.
+ */
+struct ib_mad_agent *ib_redirect_mad_qp(struct ib_qp *qp,
+ u8 rmpp_version,
+ ib_mad_send_handler send_handler,
+ ib_mad_recv_handler recv_handler,
+ void *context);
+
+/**
+ * ib_process_mad_wc - Processes a work completion associated with a
+ * MAD sent or received on a redirected QP.
+ * @mad_agent: Specifies the registered MAD service using the redirected QP.
+ * @wc: References a work completion associated with a sent or received
+ * MAD segment.
+ *
+ * This routine is used to complete or continue processing on a MAD request.
+ * If the work completion is associated with a send operation, calling
+ * this routine is required to continue an RMPP transfer or to wait for a
+ * corresponding response, if it is a request. If the work completion is
+ * associated with a receive operation, calling this routine is required to
+ * process an inbound or outbound RMPP transfer, or to match a response MAD
+ * with its corresponding request.
+ */
+int ib_process_mad_wc(struct ib_mad_agent *mad_agent,
+ struct ib_wc *wc);
+
+#endif /* IB_MAD_H */
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-bk/drivers/infiniband/include/ib_smi.h 2004-12-13 09:44:42.653441760 -0800
@@ -0,0 +1,67 @@
+/*
+ * 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 at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://openib.org/license.html>.
+ *
+ * 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.
+ *
+ * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved.
+ * Copyright (c) 2004 Infinicon Corporation. All rights reserved.
+ * Copyright (c) 2004 Intel Corporation. All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation. All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation. All rights reserved.
+ *
+ * $Id$
+ */
+
+#if !defined( IB_SMI_H )
+#define IB_SMI_H
+
+#include <ib_mad.h>
+
+#define IB_LID_PERMISSIVE 0xFFFF
+
+#define IB_SMP_DATA_SIZE 64
+#define IB_SMP_MAX_PATH_HOPS 64
+
+struct ib_smp {
+ u8 base_version;
+ u8 mgmt_class;
+ u8 class_version;
+ u8 method;
+ u16 status;
+ u8 hop_ptr;
+ u8 hop_cnt;
+ u64 tid;
+ u16 attr_id;
+ u16 resv;
+ u32 attr_mod;
+ u64 mkey;
+ u16 dr_slid;
+ u16 dr_dlid;
+ u8 reserved[28];
+ u8 data[IB_SMP_DATA_SIZE];
+ u8 initial_path[IB_SMP_MAX_PATH_HOPS];
+ u8 return_path[IB_SMP_MAX_PATH_HOPS];
+} __attribute__ ((packed));
+
+#define IB_SMP_DIRECTION cpu_to_be16(0x8000)
+
+static inline u8
+ib_get_smp_direction(struct ib_smp *smp)
+{
+ return ((smp->status & IB_SMP_DIRECTION) == IB_SMP_DIRECTION);
+}
+
+#endif /* IB_SMI_H */
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2004-12-13 18:23 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2004-12-13 18:09 [PATCH][v3][0/21] Initial submission of InfiniBand patches for review Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][1/21] Add core InfiniBand support (public headers) Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][2/21] Add core InfiniBand support Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][3/21] Hook up drivers/infiniband Roland Dreier
2004-12-13 18:09 ` [PATCH][v3][4/21] Add InfiniBand MAD (management datagram) support (public headers) Roland Dreier
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).