Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-27 05:11:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
85ad181ea7
linux/drivers/net/mlx4/profile.c
Tejun Heo 5a0e3ad6af 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>
2010-03-30 22:02:32 +09:00

241 lines
7.6 KiB
C
Raw Blame History

/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Mellanox Technologies. All rights reserved.
* Copyright (c) 2006, 2007 Cisco Systems, 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/slab.h>
#include "mlx4.h"
#include "fw.h"
enum {
MLX4_RES_QP,
MLX4_RES_RDMARC,
MLX4_RES_ALTC,
MLX4_RES_AUXC,
MLX4_RES_SRQ,
MLX4_RES_CQ,
MLX4_RES_EQ,
MLX4_RES_DMPT,
MLX4_RES_CMPT,
MLX4_RES_MTT,
MLX4_RES_MCG,
MLX4_RES_NUM
};
static const char *res_name[] = {
[MLX4_RES_QP] = "QP",
[MLX4_RES_RDMARC] = "RDMARC",
[MLX4_RES_ALTC] = "ALTC",
[MLX4_RES_AUXC] = "AUXC",
[MLX4_RES_SRQ] = "SRQ",
[MLX4_RES_CQ] = "CQ",
[MLX4_RES_EQ] = "EQ",
[MLX4_RES_DMPT] = "DMPT",
[MLX4_RES_CMPT] = "CMPT",
[MLX4_RES_MTT] = "MTT",
[MLX4_RES_MCG] = "MCG",
};
u64 mlx4_make_profile(struct mlx4_dev *dev,
struct mlx4_profile *request,
struct mlx4_dev_cap *dev_cap,
struct mlx4_init_hca_param *init_hca)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_resource {
u64 size;
u64 start;
int type;
int num;
int log_num;
};
u64 total_size = 0;
struct mlx4_resource *profile;
struct mlx4_resource tmp;
int i, j;
profile = kzalloc(MLX4_RES_NUM * sizeof *profile, GFP_KERNEL);
if (!profile)
return -ENOMEM;
profile[MLX4_RES_QP].size = dev_cap->qpc_entry_sz;
profile[MLX4_RES_RDMARC].size = dev_cap->rdmarc_entry_sz;
profile[MLX4_RES_ALTC].size = dev_cap->altc_entry_sz;
profile[MLX4_RES_AUXC].size = dev_cap->aux_entry_sz;
profile[MLX4_RES_SRQ].size = dev_cap->srq_entry_sz;
profile[MLX4_RES_CQ].size = dev_cap->cqc_entry_sz;
profile[MLX4_RES_EQ].size = dev_cap->eqc_entry_sz;
profile[MLX4_RES_DMPT].size = dev_cap->dmpt_entry_sz;
profile[MLX4_RES_CMPT].size = dev_cap->cmpt_entry_sz;
profile[MLX4_RES_MTT].size = dev->caps.mtts_per_seg * dev_cap->mtt_entry_sz;
profile[MLX4_RES_MCG].size = MLX4_MGM_ENTRY_SIZE;
profile[MLX4_RES_QP].num = request->num_qp;
profile[MLX4_RES_RDMARC].num = request->num_qp * request->rdmarc_per_qp;
profile[MLX4_RES_ALTC].num = request->num_qp;
profile[MLX4_RES_AUXC].num = request->num_qp;
profile[MLX4_RES_SRQ].num = request->num_srq;
profile[MLX4_RES_CQ].num = request->num_cq;
profile[MLX4_RES_EQ].num = min_t(unsigned, dev_cap->max_eqs,
dev_cap->reserved_eqs +
num_possible_cpus() + 1);
profile[MLX4_RES_DMPT].num = request->num_mpt;
profile[MLX4_RES_CMPT].num = MLX4_NUM_CMPTS;
profile[MLX4_RES_MTT].num = request->num_mtt;
profile[MLX4_RES_MCG].num = request->num_mcg;
for (i = 0; i < MLX4_RES_NUM; ++i) {
profile[i].type = i;
profile[i].num = roundup_pow_of_two(profile[i].num);
profile[i].log_num = ilog2(profile[i].num);
profile[i].size *= profile[i].num;
profile[i].size = max(profile[i].size, (u64) PAGE_SIZE);
}
/*
* Sort the resources in decreasing order of size. Since they
* all have sizes that are powers of 2, we'll be able to keep
* resources aligned to their size and pack them without gaps
* using the sorted order.
*/
for (i = MLX4_RES_NUM; i > 0; --i)
for (j = 1; j < i; ++j) {
if (profile[j].size > profile[j - 1].size) {
tmp = profile[j];
profile[j] = profile[j - 1];
profile[j - 1] = tmp;
}
}
for (i = 0; i < MLX4_RES_NUM; ++i) {
if (profile[i].size) {
profile[i].start = total_size;
total_size += profile[i].size;
}
if (total_size > dev_cap->max_icm_sz) {
mlx4_err(dev, "Profile requires 0x%llx bytes; "
"won't fit in 0x%llx bytes of context memory.\n",
(unsigned long long) total_size,
(unsigned long long) dev_cap->max_icm_sz);
kfree(profile);
return -ENOMEM;
}
if (profile[i].size)
mlx4_dbg(dev, " profile[%2d] (%6s): 2^%02d entries @ 0x%10llx, "
"size 0x%10llx\n",
i, res_name[profile[i].type], profile[i].log_num,
(unsigned long long) profile[i].start,
(unsigned long long) profile[i].size);
}
mlx4_dbg(dev, "HCA context memory: reserving %d KB\n",
(int) (total_size >> 10));
for (i = 0; i < MLX4_RES_NUM; ++i) {
switch (profile[i].type) {
case MLX4_RES_QP:
dev->caps.num_qps = profile[i].num;
init_hca->qpc_base = profile[i].start;
init_hca->log_num_qps = profile[i].log_num;
break;
case MLX4_RES_RDMARC:
for (priv->qp_table.rdmarc_shift = 0;
request->num_qp << priv->qp_table.rdmarc_shift < profile[i].num;
++priv->qp_table.rdmarc_shift)
; /* nothing */
dev->caps.max_qp_dest_rdma = 1 << priv->qp_table.rdmarc_shift;
priv->qp_table.rdmarc_base = (u32) profile[i].start;
init_hca->rdmarc_base = profile[i].start;
init_hca->log_rd_per_qp = priv->qp_table.rdmarc_shift;
break;
case MLX4_RES_ALTC:
init_hca->altc_base = profile[i].start;
break;
case MLX4_RES_AUXC:
init_hca->auxc_base = profile[i].start;
break;
case MLX4_RES_SRQ:
dev->caps.num_srqs = profile[i].num;
init_hca->srqc_base = profile[i].start;
init_hca->log_num_srqs = profile[i].log_num;
break;
case MLX4_RES_CQ:
dev->caps.num_cqs = profile[i].num;
init_hca->cqc_base = profile[i].start;
init_hca->log_num_cqs = profile[i].log_num;
break;
case MLX4_RES_EQ:
dev->caps.num_eqs = profile[i].num;
init_hca->eqc_base = profile[i].start;
init_hca->log_num_eqs = profile[i].log_num;
break;
case MLX4_RES_DMPT:
dev->caps.num_mpts = profile[i].num;
priv->mr_table.mpt_base = profile[i].start;
init_hca->dmpt_base = profile[i].start;
init_hca->log_mpt_sz = profile[i].log_num;
break;
case MLX4_RES_CMPT:
init_hca->cmpt_base = profile[i].start;
break;
case MLX4_RES_MTT:
dev->caps.num_mtt_segs = profile[i].num;
priv->mr_table.mtt_base = profile[i].start;
init_hca->mtt_base = profile[i].start;
break;
case MLX4_RES_MCG:
dev->caps.num_mgms = profile[i].num >> 1;
dev->caps.num_amgms = profile[i].num >> 1;
init_hca->mc_base = profile[i].start;
init_hca->log_mc_entry_sz = ilog2(MLX4_MGM_ENTRY_SIZE);
init_hca->log_mc_table_sz = profile[i].log_num;
init_hca->log_mc_hash_sz = profile[i].log_num - 1;
break;
default:
break;
}
}
/*
* PDs don't take any HCA memory, but we assign them as part
* of the HCA profile anyway.
*/
dev->caps.num_pds = MLX4_NUM_PDS;
kfree(profile);
return total_size;
}
Reference in New Issue View Git Blame Copy Permalink