tjh.dev
Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
drm/xe/pf: Track adverse events notifications from GuC
When thresholds used to monitor VFs activities are configured,
then GuC may send GUC2PF_ADVERSE_EVENT messages informing the
PF driver about exceeded thresholds. Start handling such messages.
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240514190015.2172-8-michal.wajdeczko@intel.com
+206
+1
drivers/gpu/drm/xe/Makefile
+1
drivers/gpu/drm/xe/Makefile
+147
drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c
+147
drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c
···
1
+
// SPDX-License-Identifier: MIT
2
+
/*
3
+
* Copyright © 2023-2024 Intel Corporation
4
+
*/
5
+
6
+
#include "abi/guc_actions_sriov_abi.h"
7
+
#include "abi/guc_messages_abi.h"
8
+
9
+
#include "xe_gt_sriov_pf_config.h"
10
+
#include "xe_gt_sriov_pf_helpers.h"
11
+
#include "xe_gt_sriov_pf_monitor.h"
12
+
#include "xe_gt_sriov_printk.h"
13
+
#include "xe_guc_klv_helpers.h"
14
+
#include "xe_guc_klv_thresholds_set.h"
15
+
16
+
/**
17
+
* xe_gt_sriov_pf_monitor_flr - Cleanup VF data after VF FLR.
18
+
* @gt: the &xe_gt
19
+
* @vfid: the VF identifier
20
+
*
21
+
* On FLR this function will reset all event data related to the VF.
22
+
* This function is for PF only.
23
+
*/
24
+
void xe_gt_sriov_pf_monitor_flr(struct xe_gt *gt, u32 vfid)
25
+
{
26
+
int e;
27
+
28
+
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
29
+
xe_gt_sriov_pf_assert_vfid(gt, vfid);
30
+
31
+
for (e = 0; e < XE_GUC_KLV_NUM_THRESHOLDS; e++)
32
+
gt->sriov.pf.vfs[vfid].monitor.guc.events[e] = 0;
33
+
}
34
+
35
+
static void pf_update_event_counter(struct xe_gt *gt, u32 vfid,
36
+
enum xe_guc_klv_threshold_index e)
37
+
{
38
+
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
39
+
xe_gt_assert(gt, e < XE_GUC_KLV_NUM_THRESHOLDS);
40
+
41
+
gt->sriov.pf.vfs[vfid].monitor.guc.events[e]++;
42
+
}
43
+
44
+
static int pf_handle_vf_threshold_event(struct xe_gt *gt, u32 vfid, u32 threshold)
45
+
{
46
+
char origin[8];
47
+
int e;
48
+
49
+
e = xe_guc_klv_threshold_key_to_index(threshold);
50
+
xe_sriov_function_name(vfid, origin, sizeof(origin));
51
+
52
+
/* was there a new KEY added that we missed? */
53
+
if (unlikely(e < 0)) {
54
+
xe_gt_sriov_notice(gt, "unknown threshold key %#x reported for %s\n",
55
+
threshold, origin);
56
+
return -ENOTCONN;
57
+
}
58
+
59
+
xe_gt_sriov_dbg(gt, "%s exceeded threshold %u %s\n",
60
+
origin, xe_gt_sriov_pf_config_get_threshold(gt, vfid, e),
61
+
xe_guc_klv_key_to_string(threshold));
62
+
63
+
pf_update_event_counter(gt, vfid, e);
64
+
65
+
return 0;
66
+
}
67
+
68
+
/**
69
+
* xe_gt_sriov_pf_monitor_process_guc2pf - Handle adverse event notification from the GuC.
70
+
* @gt: the &xe_gt
71
+
* @msg: G2H event message
72
+
* @len: length of the message
73
+
*
74
+
* This function is intended for PF only.
75
+
*
76
+
* Return: 0 on success or a negative error code on failure.
77
+
*/
78
+
int xe_gt_sriov_pf_monitor_process_guc2pf(struct xe_gt *gt, const u32 *msg, u32 len)
79
+
{
80
+
struct xe_device *xe = gt_to_xe(gt);
81
+
u32 vfid;
82
+
u32 threshold;
83
+
84
+
xe_gt_assert(gt, len >= GUC_HXG_MSG_MIN_LEN);
85
+
xe_gt_assert(gt, FIELD_GET(GUC_HXG_MSG_0_ORIGIN, msg[0]) == GUC_HXG_ORIGIN_GUC);
86
+
xe_gt_assert(gt, FIELD_GET(GUC_HXG_MSG_0_TYPE, msg[0]) == GUC_HXG_TYPE_EVENT);
87
+
xe_gt_assert(gt, FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, msg[0]) ==
88
+
GUC_ACTION_GUC2PF_ADVERSE_EVENT);
89
+
90
+
if (unlikely(!IS_SRIOV_PF(xe)))
91
+
return -EPROTO;
92
+
93
+
if (unlikely(FIELD_GET(GUC2PF_ADVERSE_EVENT_EVENT_MSG_0_MBZ, msg[0])))
94
+
return -EPFNOSUPPORT;
95
+
96
+
if (unlikely(len < GUC2PF_ADVERSE_EVENT_EVENT_MSG_LEN))
97
+
return -EPROTO;
98
+
99
+
vfid = FIELD_GET(GUC2PF_ADVERSE_EVENT_EVENT_MSG_1_VFID, msg[1]);
100
+
threshold = FIELD_GET(GUC2PF_ADVERSE_EVENT_EVENT_MSG_2_THRESHOLD, msg[2]);
101
+
102
+
if (unlikely(vfid > xe_gt_sriov_pf_get_totalvfs(gt)))
103
+
return -EINVAL;
104
+
105
+
return pf_handle_vf_threshold_event(gt, vfid, threshold);
106
+
}
107
+
108
+
/**
109
+
* xe_gt_sriov_pf_monitor_print_events - Print adverse events counters.
110
+
* @gt: the &xe_gt to print events from
111
+
* @p: the &drm_printer
112
+
*
113
+
* Print adverse events counters for all VFs.
114
+
* VFs with no events are not printed.
115
+
*
116
+
* This function can only be called on PF.
117
+
*/
118
+
void xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p)
119
+
{
120
+
unsigned int n, total_vfs = xe_gt_sriov_pf_get_totalvfs(gt);
121
+
const struct xe_gt_sriov_monitor *data;
122
+
int e;
123
+
124
+
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
125
+
126
+
for (n = 1; n <= total_vfs; n++) {
127
+
data = >->sriov.pf.vfs[n].monitor;
128
+
129
+
for (e = 0; e < XE_GUC_KLV_NUM_THRESHOLDS; e++)
130
+
if (data->guc.events[e])
131
+
break;
132
+
133
+
/* skip empty unless in debug mode */
134
+
if (e >= XE_GUC_KLV_NUM_THRESHOLDS &&
135
+
!IS_ENABLED(CONFIG_DRM_XE_DEBUG_SRIOV))
136
+
continue;
137
+
138
+
#define __format(...) "%s:%u "
139
+
#define __value(TAG, NAME, ...) , #NAME, data->guc.events[MAKE_XE_GUC_KLV_THRESHOLD_INDEX(TAG)]
140
+
141
+
drm_printf(p, "VF%u:\t" MAKE_XE_GUC_KLV_THRESHOLDS_SET(__format) "\n",
142
+
n MAKE_XE_GUC_KLV_THRESHOLDS_SET(__value));
143
+
144
+
#undef __format
145
+
#undef __value
146
+
}
147
+
}
+27
drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h
+27
drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h
···
1
+
/* SPDX-License-Identifier: MIT */
2
+
/*
3
+
* Copyright © 2023-2024 Intel Corporation
4
+
*/
5
+
6
+
#ifndef _XE_GT_SRIOV_PF_MONITOR_H_
7
+
#define _XE_GT_SRIOV_PF_MONITOR_H_
8
+
9
+
#include <linux/errno.h>
10
+
#include <linux/types.h>
11
+
12
+
struct drm_printer;
13
+
struct xe_gt;
14
+
15
+
void xe_gt_sriov_pf_monitor_flr(struct xe_gt *gt, u32 vfid);
16
+
void xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p);
17
+
18
+
#ifdef CONFIG_PCI_IOV
19
+
int xe_gt_sriov_pf_monitor_process_guc2pf(struct xe_gt *gt, const u32 *msg, u32 len);
20
+
#else
21
+
static inline int xe_gt_sriov_pf_monitor_process_guc2pf(struct xe_gt *gt, const u32 *msg, u32 len)
22
+
{
23
+
return -EPROTO;
24
+
}
25
+
#endif
26
+
27
+
#endif
+22
drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor_types.h
+22
drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor_types.h
···
1
+
/* SPDX-License-Identifier: MIT */
2
+
/*
3
+
* Copyright © 2023-2024 Intel Corporation
4
+
*/
5
+
6
+
#ifndef _XE_GT_SRIOV_PF_MONITOR_TYPES_H_
7
+
#define _XE_GT_SRIOV_PF_MONITOR_TYPES_H_
8
+
9
+
#include "xe_guc_klv_thresholds_set_types.h"
10
+
11
+
/**
12
+
* struct xe_gt_sriov_monitor - GT level per-VF monitoring data.
13
+
*/
14
+
struct xe_gt_sriov_monitor {
15
+
/** @guc: monitoring data related to the GuC. */
16
+
struct {
17
+
/** @guc.events: number of adverse events reported by the GuC. */
18
+
unsigned int events[XE_GUC_KLV_NUM_THRESHOLDS];
19
+
} guc;
20
+
};
21
+
22
+
#endif
+5
drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h
+5
drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h
···
9
9
#include <linux/types.h>
10
10
11
11
#include "xe_gt_sriov_pf_config_types.h"
12
+
#include "xe_gt_sriov_pf_monitor_types.h"
12
13
#include "xe_gt_sriov_pf_policy_types.h"
13
14
#include "xe_gt_sriov_pf_service_types.h"
14
15
···
19
18
struct xe_gt_sriov_metadata {
20
19
/** @config: per-VF provisioning data. */
21
20
struct xe_gt_sriov_config config;
21
+
22
+
/** @monitor: per-VF monitoring data. */
23
+
struct xe_gt_sriov_monitor monitor;
24
+
22
25
/** @version: negotiated VF/PF ABI version */
23
26
struct xe_gt_sriov_pf_service_version version;
24
27
};
+4
drivers/gpu/drm/xe/xe_guc_ct.c
+4
drivers/gpu/drm/xe/xe_guc_ct.c
···
22
22
#include "xe_gt_pagefault.h"
23
23
#include "xe_gt_printk.h"
24
24
#include "xe_gt_sriov_pf_control.h"
25
+
#include "xe_gt_sriov_pf_monitor.h"
25
26
#include "xe_gt_tlb_invalidation.h"
26
27
#include "xe_guc.h"
27
28
#include "xe_guc_relay.h"
···
1071
1070
break;
1072
1071
case GUC_ACTION_GUC2PF_VF_STATE_NOTIFY:
1073
1072
ret = xe_gt_sriov_pf_control_process_guc2pf(gt, hxg, hxg_len);
1073
+
break;
1074
+
case GUC_ACTION_GUC2PF_ADVERSE_EVENT:
1075
+
ret = xe_gt_sriov_pf_monitor_process_guc2pf(gt, hxg, hxg_len);
1074
1076
break;
1075
1077
default:
1076
1078
xe_gt_err(gt, "unexpected G2H action 0x%04x\n", action);