linux/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h

79 lines
2.8 KiB
C
Raw Normal View History

/*
* 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"
#include "amdgpu_ras.h"
struct amdgpu_hive_info {
struct kobject kobj;
uint64_t hive_id;
struct list_head device_list;
struct list_head node;
atomic_t number_devices;
struct mutex hive_lock;
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_reset_domain *reset_domain;
drm/amdgpu: Adjust removal control flow for smu v13_0_2 Adjust removal control flow for smu v13_0_2: During amdgpu uninstallation, when removing the first device, the kernel needs to first send a mode1reset message to all gpu devices. Otherwise, smu initialization will fail the next time amdgpu is installed. V2: 1. Update commit comments. 2. Remove the global variable amdgpu_device_remove_cnt and add a variable to the structure amdgpu_hive_info. 3. Use hive to detect the first removed device instead of a global variable. V3: 1. Update commit comments. 2. Split a patch into multiple patches. 3. The current patch does: a. Add a work mode of AMDGPU_RESET_FOR_DEVICE_REMOVE into the existing gpu recover path, which make all devices in hive list only have HW reset but no resume (except the base IP). b. Call AMDGPU_RESET_FOR_DEVICE_REMOVE and AMDGPU_NEED_FULL_RESET mode of amdgpu_device_gpu_recover in amdgpu_pci_remove when removing the first device in hive list. c. When removing the first device, the IP blocks keyword function call sequence is as follows: .suspend->mode1reset->.resume(basic ip)->.hw_fini->.early_fini->.sw_fini. ^ | |-<----------<---------<----| The first three sequences are because of a call to amdgpu_device_gpu_recover. The three sequences will be executed in a loop until all devices in the hive list are iterated. The sequences starting from .hw_fini only apply to the first device. Since .suspend has been called before, except the resumed phase1 basic ip blocks, all other ip blocks .hw_fini of current device will do nothing. d. When removing other devices, the calling sequences is the same as legacy: .hw_fini -> .early_fini -> .sw_fini. Since .suspend has been called when removing the first device, except the resumed phase1 basic ip blocks, all of other ip blocks .hw_fini of current device will do nothing. Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2022-09-07 16:07:42 +08:00
uint32_t device_remove_count;
};
struct amdgpu_pcs_ras_field {
const char *err_name;
uint32_t pcs_err_mask;
uint32_t pcs_err_shift;
};
extern struct amdgpu_xgmi_ras xgmi_ras;
struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev);
void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive);
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_get_num_links(struct amdgpu_device *adev,
struct amdgpu_device *peer_adev);
uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev,
uint64_t addr);
static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
struct amdgpu_device *bo_adev)
{
return (amdgpu_use_xgmi_p2p &&
adev != bo_adev &&
adev->gmc.xgmi.hive_id &&
adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id);
}
int amdgpu_xgmi_ras_sw_init(struct amdgpu_device *adev);
#endif