linux_dsm_epyc7002/drivers/net/mlx4/cq.c

320 lines
8.6 KiB
C
Raw Normal View History

/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. 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 <linux/hardirq.h>
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/mlx4/cmd.h>
#include <linux/mlx4/cq.h>
#include "mlx4.h"
#include "icm.h"
struct mlx4_cq_context {
__be32 flags;
u16 reserved1[3];
__be16 page_offset;
__be32 logsize_usrpage;
__be16 cq_period;
__be16 cq_max_count;
u8 reserved2[3];
u8 comp_eqn;
u8 log_page_size;
u8 reserved3[2];
u8 mtt_base_addr_h;
__be32 mtt_base_addr_l;
__be32 last_notified_index;
__be32 solicit_producer_index;
__be32 consumer_index;
__be32 producer_index;
u32 reserved4[2];
__be64 db_rec_addr;
};
#define MLX4_CQ_STATUS_OK ( 0 << 28)
#define MLX4_CQ_STATUS_OVERFLOW ( 9 << 28)
#define MLX4_CQ_STATUS_WRITE_FAIL (10 << 28)
#define MLX4_CQ_FLAG_CC ( 1 << 18)
#define MLX4_CQ_FLAG_OI ( 1 << 17)
#define MLX4_CQ_STATE_ARMED ( 9 << 8)
#define MLX4_CQ_STATE_ARMED_SOL ( 6 << 8)
#define MLX4_EQ_STATE_FIRED (10 << 8)
void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
{
struct mlx4_cq *cq;
cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
cqn & (dev->caps.num_cqs - 1));
if (!cq) {
mlx4_warn(dev, "Completion event for bogus CQ %08x\n", cqn);
return;
}
++cq->arm_sn;
cq->comp(cq);
}
void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
{
struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
struct mlx4_cq *cq;
spin_lock(&cq_table->lock);
cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1));
if (cq)
atomic_inc(&cq->refcount);
spin_unlock(&cq_table->lock);
if (!cq) {
mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn);
return;
}
cq->event(cq, event_type);
if (atomic_dec_and_test(&cq->refcount))
complete(&cq->free);
}
static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int cq_num)
{
return mlx4_cmd(dev, mailbox->dma, cq_num, 0, MLX4_CMD_SW2HW_CQ,
MLX4_CMD_TIME_CLASS_A);
}
static int mlx4_MODIFY_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int cq_num, u32 opmod)
{
return mlx4_cmd(dev, mailbox->dma, cq_num, opmod, MLX4_CMD_MODIFY_CQ,
MLX4_CMD_TIME_CLASS_A);
}
static int mlx4_HW2SW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int cq_num)
{
return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, cq_num,
mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
MLX4_CMD_TIME_CLASS_A);
}
int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
u16 count, u16 period)
{
struct mlx4_cmd_mailbox *mailbox;
struct mlx4_cq_context *cq_context;
int err;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
cq_context = mailbox->buf;
memset(cq_context, 0, sizeof *cq_context);
cq_context->cq_max_count = cpu_to_be16(count);
cq_context->cq_period = cpu_to_be16(period);
err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 1);
mlx4_free_cmd_mailbox(dev, mailbox);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_cq_modify);
int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
int entries, struct mlx4_mtt *mtt)
{
struct mlx4_cmd_mailbox *mailbox;
struct mlx4_cq_context *cq_context;
u64 mtt_addr;
int err;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
cq_context = mailbox->buf;
memset(cq_context, 0, sizeof *cq_context);
cq_context->logsize_usrpage = cpu_to_be32(ilog2(entries) << 24);
cq_context->log_page_size = mtt->page_shift - 12;
mtt_addr = mlx4_mtt_addr(dev, mtt);
cq_context->mtt_base_addr_h = mtt_addr >> 32;
cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 0);
mlx4_free_cmd_mailbox(dev, mailbox);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_cq_resize);
int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
unsigned vector, int collapsed)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_cq_table *cq_table = &priv->cq_table;
struct mlx4_cmd_mailbox *mailbox;
struct mlx4_cq_context *cq_context;
u64 mtt_addr;
int err;
if (vector > dev->caps.num_comp_vectors + dev->caps.comp_pool)
return -EINVAL;
cq->vector = vector;
cq->cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
if (cq->cqn == -1)
return -ENOMEM;
err = mlx4_table_get(dev, &cq_table->table, cq->cqn);
if (err)
goto err_out;
err = mlx4_table_get(dev, &cq_table->cmpt_table, cq->cqn);
if (err)
goto err_put;
spin_lock_irq(&cq_table->lock);
err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
spin_unlock_irq(&cq_table->lock);
if (err)
goto err_cmpt_put;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox)) {
err = PTR_ERR(mailbox);
goto err_radix;
}
cq_context = mailbox->buf;
memset(cq_context, 0, sizeof *cq_context);
cq_context->flags = cpu_to_be32(!!collapsed << 18);
cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index);
cq_context->comp_eqn = priv->eq_table.eq[vector].eqn;
cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
mtt_addr = mlx4_mtt_addr(dev, mtt);
cq_context->mtt_base_addr_h = mtt_addr >> 32;
cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
cq_context->db_rec_addr = cpu_to_be64(db_rec);
err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn);
mlx4_free_cmd_mailbox(dev, mailbox);
if (err)
goto err_radix;
cq->cons_index = 0;
cq->arm_sn = 1;
cq->uar = uar;
atomic_set(&cq->refcount, 1);
init_completion(&cq->free);
return 0;
err_radix:
spin_lock_irq(&cq_table->lock);
radix_tree_delete(&cq_table->tree, cq->cqn);
spin_unlock_irq(&cq_table->lock);
err_cmpt_put:
mlx4_table_put(dev, &cq_table->cmpt_table, cq->cqn);
err_put:
mlx4_table_put(dev, &cq_table->table, cq->cqn);
err_out:
mlx4_bitmap_free(&cq_table->bitmap, cq->cqn);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_cq_alloc);
void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_cq_table *cq_table = &priv->cq_table;
int err;
err = mlx4_HW2SW_CQ(dev, NULL, cq->cqn);
if (err)
mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);
synchronize_irq(priv->eq_table.eq[cq->vector].irq);
spin_lock_irq(&cq_table->lock);
radix_tree_delete(&cq_table->tree, cq->cqn);
spin_unlock_irq(&cq_table->lock);
if (atomic_dec_and_test(&cq->refcount))
complete(&cq->free);
wait_for_completion(&cq->free);
mlx4_table_put(dev, &cq_table->table, cq->cqn);
mlx4_bitmap_free(&cq_table->bitmap, cq->cqn);
}
EXPORT_SYMBOL_GPL(mlx4_cq_free);
int mlx4_init_cq_table(struct mlx4_dev *dev)
{
struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
int err;
spin_lock_init(&cq_table->lock);
INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
if (err)
return err;
return 0;
}
void mlx4_cleanup_cq_table(struct mlx4_dev *dev)
{
/* Nothing to do to clean up radix_tree */
mlx4_bitmap_cleanup(&mlx4_priv(dev)->cq_table.bitmap);
}