AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-28 11:18:45 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
af53493916
linux_dsm_epyc7002/drivers/infiniband/hw/hfi1/affinity.h

133 lines
4.1 KiB
C
Raw Normal View History

staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
/*
staging/rdma/hfi1: Fix header Fix the header by moving the copyright notice out of the license text and to the top of the header. Also, update the copyright date. Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-15 11:22:17 +07:00
* Copyright(c) 2015, 2016 Intel Corporation.
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
*
* 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
};
IB/hfi1: Change default number of user contexts Change the default number of user contexts to the number of real (non-HT) cpu cores in order to reduce the division of hfi1 hardware contexts in the case of high core counts with hyper-threading enabled. Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Reviewed-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-04-13 01:30:08 +07:00
struct cpu_mask_set {
struct cpumask mask;
struct cpumask used;
uint gen;
};
struct hfi1_affinity {
struct cpu_mask_set def_intr;
struct cpu_mask_set rcv_intr;
struct cpumask real_cpu_mask;
/* spin lock to protect affinity struct */
spinlock_t lock;
};
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
struct hfi1_msix_entry;
IB/hfi1: Change default number of user contexts Change the default number of user contexts to the number of real (non-HT) cpu cores in order to reduce the division of hfi1 hardware contexts in the case of high core counts with hyper-threading enabled. Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Reviewed-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Jubin John <jubin.john@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-04-13 01:30:08 +07:00
/* Initialize non-HT cpu cores mask */
IB/hfi1: Add global structure for affinity assignments When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <jianxin.xiong@intel.com> Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:52:36 +07:00
void init_real_cpu_mask(void);
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
/* Initialize driver affinity data */
IB/hfi1: Add global structure for affinity assignments When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <jianxin.xiong@intel.com> Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:52:36 +07:00
int hfi1_dev_affinity_init(struct hfi1_devdata *);
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
/*
* 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 *, struct hfi1_msix_entry *);
/*
* Remove the IRQ's CPU affinity. This function also updates
* any internal CPU tracking data
*/
void hfi1_put_irq_affinity(struct hfi1_devdata *, struct hfi1_msix_entry *);
/*
* Determine a CPU affinity for a user process, if the process does not
* have an affinity set yet.
*/
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 21:54:57 +07:00
int hfi1_get_proc_affinity(int);
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
/* Release a CPU used by a user process. */
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 21:54:57 +07:00
void hfi1_put_proc_affinity(int);
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
IB/hfi1: Add sysfs entry to override SDMA interrupt affinity Add sysfs entry to allow user to override affinity for SDMA engine interrupts. Reviewed-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-26 03:39:27 +07:00
int hfi1_get_sdma_affinity(struct hfi1_devdata *dd, char *buf);
int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf,
size_t count);
IB/hfi1: Add global structure for affinity assignments When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <jianxin.xiong@intel.com> Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:52:36 +07:00
struct hfi1_affinity_node {
int node;
struct cpu_mask_set def_intr;
struct cpu_mask_set rcv_intr;
IB/hfi1: Reserve and collapse CPU cores for contexts Kernel receive queues oversubscribe CPU cores on multi-HFI systems. To prevent this, the kernel receive queues are separated onto different cores, and the SDMA engine interrupts are constrained to a lesser number of cores. hfi1s_on_numa_node*krcvqs is the number of CPU cores that are reserved for kernel receive queues for all HFIs. Each HFI initializes its kernel receive queues to one of the reserved CPU cores. If there ends up being 0 CPU cores leftover for SDMA engines, use the same CPU cores as receive contexts. In addition, general and control contexts are assigned to their own CPU core, however, both types of contexts tend to have low traffic. To save CPU cores, collapse general and control contexts to one CPU core for all HFI units. This change prevents SDMA engine interrupts from wrapping around general contexts. Reviewed-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:54:48 +07:00
struct cpumask general_intr_mask;
IB/hfi1: Add global structure for affinity assignments When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <jianxin.xiong@intel.com> Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:52:36 +07:00
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 21:54:57 +07:00
int num_core_siblings;
int num_online_nodes;
int num_online_cpus;
IB/hfi1: Add global structure for affinity assignments When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <jianxin.xiong@intel.com> Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:52:36 +07:00
/* protect affinity node list */
spinlock_t lock;
};
IB/hfi1: Reserve and collapse CPU cores for contexts Kernel receive queues oversubscribe CPU cores on multi-HFI systems. To prevent this, the kernel receive queues are separated onto different cores, and the SDMA engine interrupts are constrained to a lesser number of cores. hfi1s_on_numa_node*krcvqs is the number of CPU cores that are reserved for kernel receive queues for all HFIs. Each HFI initializes its kernel receive queues to one of the reserved CPU cores. If there ends up being 0 CPU cores leftover for SDMA engines, use the same CPU cores as receive contexts. In addition, general and control contexts are assigned to their own CPU core, however, both types of contexts tend to have low traffic. To save CPU cores, collapse general and control contexts to one CPU core for all HFI units. This change prevents SDMA engine interrupts from wrapping around general contexts. Reviewed-by: Dean Luick <dean.luick@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:54:48 +07:00
int node_affinity_init(void);
IB/hfi1: Add global structure for affinity assignments When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <jianxin.xiong@intel.com> Reviewed-by: Jubin John <jubin.john@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-07-25 21:52:36 +07:00
void node_affinity_destroy(void);
extern struct hfi1_affinity_node_list node_affinity;
staging/rdma/hfi1: Consolidate CPU/IRQ affinity support This patch unifies the affinity support for CPU and IRQ allocations into a single code base. The goal is to allow the driver to make intelligent placement decision based on an overall view of processes and IRQs across as much of the driver as possible. Pulling all the scattered affinity code into a single code base lays the ground work for accomplishing the above goal. For example, previous implementations made user process placement decision solely based on other user processes. This algorithm is limited as it did not take into account IRQ placement and could result in overloading certain CPUs. A single code base also provides a much easier way to maintain and debug any performance issues related to affinity. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Dean Luick <dean.luick@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-02-04 05:33:40 +07:00
#endif /* _HFI1_AFFINITY_H */
Reference in New Issue Copy Permalink