linux/drivers/infiniband/hw/hfi1/affinity.h

123 lines
3.8 KiB
C
Raw Normal View History

/*
* Copyright(c) 2015 - 2017 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
*
* GPL LICENSE SUMMARY
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* BSD LICENSE
*
* 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.
* - Neither the name of Intel Corporation nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
*/
#ifndef _HFI1_AFFINITY_H
#define _HFI1_AFFINITY_H
#include "hfi.h"
enum irq_type {
IRQ_SDMA,
IRQ_RCVCTXT,
IRQ_GENERAL,
IRQ_OTHER
};
/* Can be used for both memory and cpu */
enum affinity_flags {
AFF_AUTO,
AFF_NUMA_LOCAL,
AFF_DEV_LOCAL,
AFF_IRQ_LOCAL
};
struct cpu_mask_set {
struct cpumask mask;
struct cpumask used;
uint gen;
};
struct hfi1_msix_entry;
/* Initialize non-HT cpu cores mask */
void init_real_cpu_mask(void);
/* Initialize driver affinity data */
int hfi1_dev_affinity_init(struct hfi1_devdata *dd);
/*
* Set IRQ affinity to a CPU. The function will determine the
* CPU and set the affinity to it.
*/
int hfi1_get_irq_affinity(struct hfi1_devdata *dd,
struct hfi1_msix_entry *msix);
/*
* Remove the IRQ's CPU affinity. This function also updates
* any internal CPU tracking data
*/
void hfi1_put_irq_affinity(struct hfi1_devdata *dd,
struct hfi1_msix_entry *msix);
/*
* Determine a CPU affinity for a user process, if the process does not
* have an affinity set yet.
*/
int hfi1_get_proc_affinity(int node);
/* Release a CPU used by a user process. */
void hfi1_put_proc_affinity(int cpu);
struct hfi1_affinity_node {
int node;
struct cpu_mask_set def_intr;
struct cpu_mask_set rcv_intr;
struct cpumask general_intr_mask;
struct list_head list;
};
struct hfi1_affinity_node_list {
struct list_head list;
struct cpumask real_cpu_mask;
struct cpu_mask_set proc;
IB/hfi1: Refine user process affinity algorithm When performing process affinity recommendations for MPI ranks, the current algorithm doesn't take into account multiple HFI units. Also, real cores and HT cores are not distinguished from one another. Therefore, all HT cores are recommended to be assigned first within the local NUMA node before recommending the assignments of cores in other NUMA nodes. It's ideal to assign all real cores across all NUMA nodes first, then all HT 1 cores, then all HT 2 cores, and so on to balance CPU workload. CPU cores in other NUMA nodes could be running interrupt handlers, and this is not taken into account. To balance the CPU workload for user processes, the following recommendation algorithm is used: For each user process that is opening a context on HFI Y: a) If all cores are assigned to user processes, start assignments all over from the first core b) Assign real cores first, then HT cores (First set of HT cores on all physical cores, then second set of HT cores, and, so on) in the following order: 1. Same NUMA node as HFI Y and not running an IRQ handler 2. Same NUMA node as HFI Y and running an IRQ handler 3. Different NUMA node to HFI Y and not running an IRQ handler 4. Different NUMA node to HFI Y and running an IRQ handler c) Mark core as assigned in the global affinity structure. As user processes are done, remove core assignments from global affinity structure. This implementation allows an arbitrary number of HT cores and provides support for multiple HFIs. This is being included in the kernel rather than user space due to the fact that user space has no way of knowing the CPU recommendations for contexts running as part of other jobs. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mitko Haralanov <mitko.haralanov@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 16:54:57 +02:00
int num_core_siblings;
int num_possible_nodes;
IB/hfi1: Refine user process affinity algorithm When performing process affinity recommendations for MPI ranks, the current algorithm doesn't take into account multiple HFI units. Also, real cores and HT cores are not distinguished from one another. Therefore, all HT cores are recommended to be assigned first within the local NUMA node before recommending the assignments of cores in other NUMA nodes. It's ideal to assign all real cores across all NUMA nodes first, then all HT 1 cores, then all HT 2 cores, and so on to balance CPU workload. CPU cores in other NUMA nodes could be running interrupt handlers, and this is not taken into account. To balance the CPU workload for user processes, the following recommendation algorithm is used: For each user process that is opening a context on HFI Y: a) If all cores are assigned to user processes, start assignments all over from the first core b) Assign real cores first, then HT cores (First set of HT cores on all physical cores, then second set of HT cores, and, so on) in the following order: 1. Same NUMA node as HFI Y and not running an IRQ handler 2. Same NUMA node as HFI Y and running an IRQ handler 3. Different NUMA node to HFI Y and not running an IRQ handler 4. Different NUMA node to HFI Y and running an IRQ handler c) Mark core as assigned in the global affinity structure. As user processes are done, remove core assignments from global affinity structure. This implementation allows an arbitrary number of HT cores and provides support for multiple HFIs. This is being included in the kernel rather than user space due to the fact that user space has no way of knowing the CPU recommendations for contexts running as part of other jobs. Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mitko Haralanov <mitko.haralanov@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 16:54:57 +02:00
int num_online_nodes;
int num_online_cpus;
struct mutex lock; /* protects affinity nodes */
};
int node_affinity_init(void);
void node_affinity_destroy(void);
extern struct hfi1_affinity_node_list node_affinity;
#endif /* _HFI1_AFFINITY_H */