drm/amdgpu: validate bad page threshold in ras(v3)

Bad page threshold value should be valid in the range between
-1 and max records length of eeprom. It could determine when
saved bad pages exceed threshold value, and proceed corresponding
actions.

v2: When using the default typical value, it should be min
value between typical value and eeprom max records length.

v3: drop the case of setting bad_page_cnt_threshold to be
    0xFFFFFFFF, as it confuses user.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -69,6 +69,9 @@ const char *ras_block_string[] = {
 /* inject address is 52 bits */
 #define	RAS_UMC_INJECT_ADDR_LIMIT	(0x1ULL << 52)
 
+/* typical ECC bad page rate(1 bad page per 100MB VRAM) */
+#define RAS_BAD_PAGE_RATE		(100 * 1024 * 1024ULL)
+
 enum amdgpu_ras_retire_page_reservation {
 	AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 	AMDGPU_RAS_RETIRE_PAGE_PENDING,
@@ -1699,6 +1702,47 @@ out:
 	return ret;
 }
 
+static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
+					uint32_t max_length)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	int tmp_threshold = amdgpu_bad_page_threshold;
+	u64 val;
+
+	/*
+	 * Justification of value bad_page_cnt_threshold in ras structure
+	 *
+	 * Generally, -1 <= amdgpu_bad_page_threshold <= max record length
+	 * in eeprom, and introduce two scenarios accordingly.
+	 *
+	 * Bad page retirement enablement:
+	 *    - If amdgpu_bad_page_threshold = -1,
+	 *      bad_page_cnt_threshold = typical value by formula.
+	 *
+	 *    - When the value from user is 0 < amdgpu_bad_page_threshold <
+	 *      max record length in eeprom, use it directly.
+	 *
+	 * Bad page retirement disablement:
+	 *    - If amdgpu_bad_page_threshold = 0, bad page retirement
+	 *      functionality is disabled, and bad_page_cnt_threshold will
+	 *      take no effect.
+	 */
+
+	if (tmp_threshold < -1)
+		tmp_threshold = -1;
+	else if (tmp_threshold > max_length)
+		tmp_threshold = max_length;
+
+	if (tmp_threshold == -1) {
+		val = adev->gmc.mc_vram_size;
+		do_div(val, RAS_BAD_PAGE_RATE);
+		con->bad_page_cnt_threshold = min(lower_32_bits(val),
+						max_length);
+	} else {
+		con->bad_page_cnt_threshold = tmp_threshold;
+	}
+}
+
 /* called in gpu recovery/init */
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
 {
@@ -1776,6 +1820,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data **data;
+	uint32_t max_eeprom_records_len = 0;
 	int ret;
 
 	if (con)
@@ -1794,6 +1839,9 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	atomic_set(&con->in_recovery, 0);
 	con->adev = adev;
 
+	max_eeprom_records_len = amdgpu_ras_eeprom_get_record_max_length();
+	amdgpu_ras_validate_threshold(adev, max_eeprom_records_len);
+
 	ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
 	if (ret)
 		goto free;

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h

@@ -336,6 +336,9 @@ struct amdgpu_ras {
 	struct amdgpu_ras_eeprom_control eeprom_control;
 
 	bool error_query_ready;
+
+	/* bad page count threshold */
+	uint32_t bad_page_cnt_threshold;
 };
 
 struct ras_fs_data {

drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c

@@ -499,6 +499,11 @@ free_buff:
 	return ret == num ? 0 : -EIO;
 }
 
+inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void)
+{
+	return EEPROM_MAX_RECORD_NUM;
+}
+
 /* Used for testing if bugs encountered */
 #if 0
 void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control)

drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h

@@ -84,6 +84,8 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    bool write,
 					    int num);
 
+inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void);
+
 void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control);
 
 #endif // _AMDGPU_RAS_EEPROM_H