linux/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c

/*
 * Copyright 2019 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.
 *
 */

#include <linux/sort.h>
#include "amdgpu.h"
#include "umc_v6_7.h"
#define MAX_UMC_POISON_POLLING_TIME_SYNC …

#define MAX_UMC_HASH_STRING_SIZE …

static int amdgpu_umc_convert_error_address(struct amdgpu_device *adev,
				    struct ras_err_data *err_data, uint64_t err_addr,
				    uint32_t ch_inst, uint32_t umc_inst)
{ … }

int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
			uint64_t err_addr, uint32_t ch_inst, uint32_t umc_inst)
{ … }

void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
			void *ras_error_status)
{ … }

static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
		void *ras_error_status,
		struct amdgpu_iv_entry *entry,
		uint32_t reset)
{ … }

int amdgpu_umc_bad_page_polling_timeout(struct amdgpu_device *adev,
			uint32_t reset, uint32_t timeout_ms)
{ … }

int amdgpu_umc_pasid_poison_handler(struct amdgpu_device *adev,
			enum amdgpu_ras_block block, uint16_t pasid,
			pasid_notify pasid_fn, void *data, uint32_t reset)
{ … }

int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
			enum amdgpu_ras_block block, uint32_t reset)
{ … }

int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
		void *ras_error_status,
		struct amdgpu_iv_entry *entry)
{ … }

int amdgpu_umc_ras_sw_init(struct amdgpu_device *adev)
{ … }

int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
{ … }

int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
		struct amdgpu_irq_src *source,
		struct amdgpu_iv_entry *entry)
{ … }

int amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
		uint64_t err_addr,
		uint64_t retired_page,
		uint32_t channel_index,
		uint32_t umc_inst)
{ … }

int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
			umc_func func, void *data)
{ … }

int amdgpu_umc_update_ecc_status(struct amdgpu_device *adev,
				uint64_t status, uint64_t ipid, uint64_t addr)
{ … }

static int amdgpu_umc_uint64_cmp(const void *a, const void *b)
{ … }

/* Use string hash to avoid logging the same bad pages repeatedly */
int amdgpu_umc_build_pages_hash(struct amdgpu_device *adev,
		uint64_t *pfns, int len, uint64_t *val)
{ … }

int amdgpu_umc_logs_ecc_err(struct amdgpu_device *adev,
		struct radix_tree_root *ecc_tree, struct ras_ecc_err *ecc_err)
{ … }