linux_dsm_epyc7002/drivers/net/ethernet/mellanox/mlx4/qp.c

510 lines
14 KiB
C
Raw Normal View History

/*
* Copyright (c) 2004 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
* Copyright (c) 2004 Voltaire, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/mlx4/cmd.h>
#include <linux/mlx4/qp.h>
#include "mlx4.h"
#include "icm.h"
void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
{
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
struct mlx4_qp *qp;
spin_lock(&qp_table->lock);
qp = __mlx4_qp_lookup(dev, qpn);
if (qp)
atomic_inc(&qp->refcount);
spin_unlock(&qp_table->lock);
if (!qp) {
mlx4_dbg(dev, "Async event for none existent QP %08x\n", qpn);
return;
}
qp->event(qp, event_type);
if (atomic_dec_and_test(&qp->refcount))
complete(&qp->free);
}
static int is_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp)
{
return qp->qpn >= dev->caps.sqp_start &&
qp->qpn <= dev->caps.sqp_start + 1;
}
static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
struct mlx4_qp_context *context,
enum mlx4_qp_optpar optpar,
int sqd_event, struct mlx4_qp *qp, int native)
{
static const u16 op[MLX4_QP_NUM_STATE][MLX4_QP_NUM_STATE] = {
[MLX4_QP_STATE_RST] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
[MLX4_QP_STATE_INIT] = MLX4_CMD_RST2INIT_QP,
},
[MLX4_QP_STATE_INIT] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
[MLX4_QP_STATE_INIT] = MLX4_CMD_INIT2INIT_QP,
[MLX4_QP_STATE_RTR] = MLX4_CMD_INIT2RTR_QP,
},
[MLX4_QP_STATE_RTR] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
[MLX4_QP_STATE_RTS] = MLX4_CMD_RTR2RTS_QP,
},
[MLX4_QP_STATE_RTS] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
[MLX4_QP_STATE_RTS] = MLX4_CMD_RTS2RTS_QP,
[MLX4_QP_STATE_SQD] = MLX4_CMD_RTS2SQD_QP,
},
[MLX4_QP_STATE_SQD] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
[MLX4_QP_STATE_RTS] = MLX4_CMD_SQD2RTS_QP,
[MLX4_QP_STATE_SQD] = MLX4_CMD_SQD2SQD_QP,
},
[MLX4_QP_STATE_SQER] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
[MLX4_QP_STATE_RTS] = MLX4_CMD_SQERR2RTS_QP,
},
[MLX4_QP_STATE_ERR] = {
[MLX4_QP_STATE_RST] = MLX4_CMD_2RST_QP,
[MLX4_QP_STATE_ERR] = MLX4_CMD_2ERR_QP,
}
};
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_cmd_mailbox *mailbox;
int ret = 0;
u8 port;
if (cur_state >= MLX4_QP_NUM_STATE || new_state >= MLX4_QP_NUM_STATE ||
!op[cur_state][new_state])
return -EINVAL;
if (op[cur_state][new_state] == MLX4_CMD_2RST_QP) {
ret = mlx4_cmd(dev, 0, qp->qpn, 2,
MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A, native);
if (mlx4_is_master(dev) && cur_state != MLX4_QP_STATE_ERR &&
cur_state != MLX4_QP_STATE_RST &&
is_qp0(dev, qp)) {
port = (qp->qpn & 1) + 1;
priv->mfunc.master.qp0_state[port].qp0_active = 0;
}
return ret;
}
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
if (cur_state == MLX4_QP_STATE_RST && new_state == MLX4_QP_STATE_INIT) {
u64 mtt_addr = mlx4_mtt_addr(dev, mtt);
context->mtt_base_addr_h = mtt_addr >> 32;
context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
}
*(__be32 *) mailbox->buf = cpu_to_be32(optpar);
memcpy(mailbox->buf + 8, context, sizeof *context);
((struct mlx4_qp_context *) (mailbox->buf + 8))->local_qpn =
cpu_to_be32(qp->qpn);
ret = mlx4_cmd(dev, mailbox->dma,
qp->qpn | (!!sqd_event << 31),
new_state == MLX4_QP_STATE_RST ? 2 : 0,
op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C, native);
mlx4_free_cmd_mailbox(dev, mailbox);
return ret;
}
int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
struct mlx4_qp_context *context,
enum mlx4_qp_optpar optpar,
int sqd_event, struct mlx4_qp *qp)
{
return __mlx4_qp_modify(dev, mtt, cur_state, new_state, context,
optpar, sqd_event, qp, 0);
}
EXPORT_SYMBOL_GPL(mlx4_qp_modify);
int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
int *base)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
if (*base == -1)
return -ENOMEM;
return 0;
}
int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
{
u64 in_param;
u64 out_param;
int err;
if (mlx4_is_mfunc(dev)) {
set_param_l(&in_param, cnt);
set_param_h(&in_param, align);
err = mlx4_cmd_imm(dev, in_param, &out_param,
RES_QP, RES_OP_RESERVE,
MLX4_CMD_ALLOC_RES,
MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
if (err)
return err;
*base = get_param_l(&out_param);
return 0;
}
return __mlx4_qp_reserve_range(dev, cnt, align, base);
}
EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
if (mlx4_is_qp_reserved(dev, (u32) base_qpn))
return;
mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt);
}
void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
{
u64 in_param;
int err;
if (mlx4_is_mfunc(dev)) {
set_param_l(&in_param, base_qpn);
set_param_h(&in_param, cnt);
err = mlx4_cmd(dev, in_param, RES_QP, RES_OP_RESERVE,
MLX4_CMD_FREE_RES,
MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
if (err) {
mlx4_warn(dev, "Failed to release qp range"
" base:%d cnt:%d\n", base_qpn, cnt);
}
} else
__mlx4_qp_release_range(dev, base_qpn, cnt);
}
EXPORT_SYMBOL_GPL(mlx4_qp_release_range);
int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
int err;
err = mlx4_table_get(dev, &qp_table->qp_table, qpn);
if (err)
goto err_out;
err = mlx4_table_get(dev, &qp_table->auxc_table, qpn);
if (err)
goto err_put_qp;
err = mlx4_table_get(dev, &qp_table->altc_table, qpn);
if (err)
goto err_put_auxc;
err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn);
if (err)
goto err_put_altc;
err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn);
if (err)
goto err_put_rdmarc;
return 0;
err_put_rdmarc:
mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
err_put_altc:
mlx4_table_put(dev, &qp_table->altc_table, qpn);
err_put_auxc:
mlx4_table_put(dev, &qp_table->auxc_table, qpn);
err_put_qp:
mlx4_table_put(dev, &qp_table->qp_table, qpn);
err_out:
return err;
}
static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
{
u64 param;
if (mlx4_is_mfunc(dev)) {
set_param_l(&param, qpn);
return mlx4_cmd_imm(dev, param, &param, RES_QP, RES_OP_MAP_ICM,
MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_WRAPPED);
}
return __mlx4_qp_alloc_icm(dev, qpn);
}
void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
mlx4_table_put(dev, &qp_table->cmpt_table, qpn);
mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
mlx4_table_put(dev, &qp_table->altc_table, qpn);
mlx4_table_put(dev, &qp_table->auxc_table, qpn);
mlx4_table_put(dev, &qp_table->qp_table, qpn);
}
static void mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
{
u64 in_param;
if (mlx4_is_mfunc(dev)) {
set_param_l(&in_param, qpn);
if (mlx4_cmd(dev, in_param, RES_QP, RES_OP_MAP_ICM,
MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_WRAPPED))
mlx4_warn(dev, "Failed to free icm of qp:%d\n", qpn);
} else
__mlx4_qp_free_icm(dev, qpn);
}
int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
int err;
if (!qpn)
return -EINVAL;
qp->qpn = qpn;
err = mlx4_qp_alloc_icm(dev, qpn);
if (err)
return err;
spin_lock_irq(&qp_table->lock);
err = radix_tree_insert(&dev->qp_table_tree, qp->qpn &
(dev->caps.num_qps - 1), qp);
spin_unlock_irq(&qp_table->lock);
if (err)
goto err_icm;
atomic_set(&qp->refcount, 1);
init_completion(&qp->free);
return 0;
err_icm:
mlx4_qp_free_icm(dev, qpn);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_qp_alloc);
void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp)
{
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
unsigned long flags;
spin_lock_irqsave(&qp_table->lock, flags);
radix_tree_delete(&dev->qp_table_tree, qp->qpn & (dev->caps.num_qps - 1));
spin_unlock_irqrestore(&qp_table->lock, flags);
}
EXPORT_SYMBOL_GPL(mlx4_qp_remove);
void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
{
if (atomic_dec_and_test(&qp->refcount))
complete(&qp->free);
wait_for_completion(&qp->free);
mlx4_qp_free_icm(dev, qp->qpn);
}
EXPORT_SYMBOL_GPL(mlx4_qp_free);
static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
{
return mlx4_cmd(dev, 0, base_qpn, 0, MLX4_CMD_CONF_SPECIAL_QP,
MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_init_qp_table(struct mlx4_dev *dev)
{
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
int err;
int reserved_from_top = 0;
spin_lock_init(&qp_table->lock);
INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
if (mlx4_is_slave(dev))
return 0;
/*
* We reserve 2 extra QPs per port for the special QPs. The
* block of special QPs must be aligned to a multiple of 8, so
* round up.
*
* We also reserve the MSB of the 24-bit QP number to indicate
* that a QP is an XRC QP.
*/
dev->caps.sqp_start =
ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);
{
int sort[MLX4_NUM_QP_REGION];
int i, j, tmp;
int last_base = dev->caps.num_qps;
for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
sort[i] = i;
for (i = MLX4_NUM_QP_REGION; i > 0; --i) {
for (j = 2; j < i; ++j) {
if (dev->caps.reserved_qps_cnt[sort[j]] >
dev->caps.reserved_qps_cnt[sort[j - 1]]) {
tmp = sort[j];
sort[j] = sort[j - 1];
sort[j - 1] = tmp;
}
}
}
for (i = 1; i < MLX4_NUM_QP_REGION; ++i) {
last_base -= dev->caps.reserved_qps_cnt[sort[i]];
dev->caps.reserved_qps_base[sort[i]] = last_base;
reserved_from_top +=
dev->caps.reserved_qps_cnt[sort[i]];
}
}
err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
(1 << 23) - 1, dev->caps.sqp_start + 8,
reserved_from_top);
if (err)
return err;
return mlx4_CONF_SPECIAL_QP(dev, dev->caps.sqp_start);
}
void mlx4_cleanup_qp_table(struct mlx4_dev *dev)
{
if (mlx4_is_slave(dev))
return;
mlx4_CONF_SPECIAL_QP(dev, 0);
mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap);
}
int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
struct mlx4_qp_context *context)
{
struct mlx4_cmd_mailbox *mailbox;
int err;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
err = mlx4_cmd_box(dev, 0, mailbox->dma, qp->qpn, 0,
MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_WRAPPED);
if (!err)
memcpy(context, mailbox->buf + 8, sizeof *context);
mlx4_free_cmd_mailbox(dev, mailbox);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_qp_query);
int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
struct mlx4_qp_context *context,
struct mlx4_qp *qp, enum mlx4_qp_state *qp_state)
{
int err;
int i;
enum mlx4_qp_state states[] = {
MLX4_QP_STATE_RST,
MLX4_QP_STATE_INIT,
MLX4_QP_STATE_RTR,
MLX4_QP_STATE_RTS
};
for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
context->flags &= cpu_to_be32(~(0xf << 28));
context->flags |= cpu_to_be32(states[i + 1] << 28);
err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
context, 0, 0, qp);
if (err) {
mlx4_err(dev, "Failed to bring QP to state: "
"%d with error: %d\n",
states[i + 1], err);
return err;
}
*qp_state = states[i + 1];
}
return 0;
}
EXPORT_SYMBOL_GPL(mlx4_qp_to_ready);