df9c8d1aa2
when GPU hang, driver has multi-paths to enter amdgpu_device_gpu_recover, the atomic adev->in_gpu_reset and hive->in_reset are used to avoid re-entering GPU recovery. During GPU reset and resume, it is unsafe that other threads access GPU, which maybe cause GPU reset failed. Therefore the new rw_semaphore adev->reset_sem is introduced, which protect GPU from being accessed by external threads during recovery. v2: 1. add rwlock for some ioctls, debugfs and file-close function. 2. change to use dqm->is_resetting and dqm_lock for protection in kfd driver. 3. remove try_lock and change adev->in_gpu_reset as atomic, to avoid re-enter GPU recovery for the same GPU hang. v3: 1. change back to use adev->reset_sem to protect kfd callback functions, because dqm_lock couldn't protect all codes, for example: free_mqd must be called outside of dqm_lock; [ 1230.176199] Hardware name: Supermicro SYS-7049GP-TRT/X11DPG-QT, BIOS 3.1 05/23/2019 [ 1230.177221] Call Trace: [ 1230.178249] dump_stack+0x98/0xd5 [ 1230.179443] amdgpu_virt_kiq_reg_write_reg_wait+0x181/0x190 [amdgpu] [ 1230.180673] gmc_v9_0_flush_gpu_tlb+0xcc/0x310 [amdgpu] [ 1230.181882] amdgpu_gart_unbind+0xa9/0xe0 [amdgpu] [ 1230.183098] amdgpu_ttm_backend_unbind+0x46/0x180 [amdgpu] [ 1230.184239] ? ttm_bo_put+0x171/0x5f0 [ttm] [ 1230.185394] ttm_tt_unbind+0x21/0x40 [ttm] [ 1230.186558] ttm_tt_destroy.part.12+0x12/0x60 [ttm] [ 1230.187707] ttm_tt_destroy+0x13/0x20 [ttm] [ 1230.188832] ttm_bo_cleanup_memtype_use+0x36/0x80 [ttm] [ 1230.189979] ttm_bo_put+0x1be/0x5f0 [ttm] [ 1230.191230] amdgpu_bo_unref+0x1e/0x30 [amdgpu] [ 1230.192522] amdgpu_amdkfd_free_gtt_mem+0xaf/0x140 [amdgpu] [ 1230.193833] free_mqd+0x25/0x40 [amdgpu] [ 1230.195143] destroy_queue_cpsch+0x1a7/0x270 [amdgpu] [ 1230.196475] pqm_destroy_queue+0x105/0x260 [amdgpu] [ 1230.197819] kfd_ioctl_destroy_queue+0x37/0x70 [amdgpu] [ 1230.199154] kfd_ioctl+0x277/0x500 [amdgpu] [ 1230.200458] ? kfd_ioctl_get_clock_counters+0x60/0x60 [amdgpu] [ 1230.201656] ? tomoyo_file_ioctl+0x19/0x20 [ 1230.202831] ksys_ioctl+0x98/0xb0 [ 1230.204004] __x64_sys_ioctl+0x1a/0x20 [ 1230.205174] do_syscall_64+0x5f/0x250 [ 1230.206339] entry_SYSCALL_64_after_hwframe+0x49/0xbe 2. remove try_lock and introduce atomic hive->in_reset, to avoid re-enter GPU recovery. v4: 1. remove an unnecessary whitespace change in kfd_chardev.c 2. remove comment codes in amdgpu_device.c 3. add more detailed comment in commit message 4. define a wrap function amdgpu_in_reset v5: 1. Fix some style issues. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Suggested-by: Christian König <christian.koenig@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com> Suggested-by: Luben Tukov <luben.tuikov@amd.com> Signed-off-by: Dennis Li <Dennis.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
77 lines
2.8 KiB
C
77 lines
2.8 KiB
C
/*
|
|
* Copyright 2016 Advanced Micro Devices, Inc.
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
* to deal in the Software without restriction, including without limitation
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice shall be included in
|
|
* all copies or substantial portions of the Software.
|
|
*
|
|
* 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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.
|
|
*/
|
|
#ifndef __AMDGPU_XGMI_H__
|
|
#define __AMDGPU_XGMI_H__
|
|
|
|
#include <drm/task_barrier.h>
|
|
#include "amdgpu_psp.h"
|
|
|
|
|
|
struct amdgpu_hive_info {
|
|
uint64_t hive_id;
|
|
struct list_head device_list;
|
|
int number_devices;
|
|
struct mutex hive_lock;
|
|
atomic_t in_reset;
|
|
struct kobject *kobj;
|
|
struct device_attribute dev_attr;
|
|
struct amdgpu_device *adev;
|
|
int hi_req_count;
|
|
struct amdgpu_device *hi_req_gpu;
|
|
struct task_barrier tb;
|
|
enum {
|
|
AMDGPU_XGMI_PSTATE_MIN,
|
|
AMDGPU_XGMI_PSTATE_MAX_VEGA20,
|
|
AMDGPU_XGMI_PSTATE_UNKNOWN
|
|
} pstate;
|
|
};
|
|
|
|
struct amdgpu_pcs_ras_field {
|
|
const char *err_name;
|
|
uint32_t pcs_err_mask;
|
|
uint32_t pcs_err_shift;
|
|
};
|
|
|
|
struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock);
|
|
int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev);
|
|
int amdgpu_xgmi_add_device(struct amdgpu_device *adev);
|
|
int amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
|
|
int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);
|
|
int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
|
|
struct amdgpu_device *peer_adev);
|
|
int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev);
|
|
void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev);
|
|
uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev,
|
|
uint64_t addr);
|
|
int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
|
|
void *ras_error_status);
|
|
void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev);
|
|
|
|
static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
|
|
struct amdgpu_device *bo_adev)
|
|
{
|
|
return (adev != bo_adev &&
|
|
adev->gmc.xgmi.hive_id &&
|
|
adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id);
|
|
}
|
|
|
|
#endif
|