1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
|
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 1 Feb 2024 15:39:56 +0100
Subject: [PATCH 15/15] net: Move per-CPU flush-lists to bpf_net_context on
PREEMPT_RT.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.10/older/patches-6.10.2-rt14.tar.xz
The per-CPU flush lists, which are accessed from within the NAPI callback
(xdp_do_flush() for instance), are per-CPU. There are subject to the
same problem as struct bpf_redirect_info.
Add the per-CPU lists cpu_map_flush_list, dev_map_flush_list and
xskmap_map_flush_list to struct bpf_net_context. Add wrappers for the
access. The lists initialized on first usage (similar to
bpf_net_ctx_get_ri()).
Cc: "Björn Töpel" <bjorn@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Jesper Dangaard Brouer <hawk@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: bpf@vger.kernel.org
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/filter.h | 42 ++++++++++++++++++++++++++++++++++++++++++
kernel/bpf/cpumap.c | 19 +++----------------
kernel/bpf/devmap.c | 11 +++--------
net/xdp/xsk.c | 12 ++++--------
4 files changed, 52 insertions(+), 32 deletions(-)
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -736,6 +736,9 @@ struct bpf_nh_params {
/* flags for bpf_redirect_info kern_flags */
#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */
#define BPF_RI_F_RI_INIT BIT(1)
+#define BPF_RI_F_CPU_MAP_INIT BIT(2)
+#define BPF_RI_F_DEV_MAP_INIT BIT(3)
+#define BPF_RI_F_XSK_MAP_INIT BIT(4)
struct bpf_redirect_info {
u64 tgt_index;
@@ -750,6 +753,9 @@ struct bpf_redirect_info {
struct bpf_net_context {
struct bpf_redirect_info ri;
+ struct list_head cpu_map_flush_list;
+ struct list_head dev_map_flush_list;
+ struct list_head xskmap_map_flush_list;
};
static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx)
@@ -787,6 +793,42 @@ static inline struct bpf_redirect_info *
return &bpf_net_ctx->ri;
}
+static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void)
+{
+ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+ if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) {
+ INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list);
+ bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT;
+ }
+
+ return &bpf_net_ctx->cpu_map_flush_list;
+}
+
+static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void)
+{
+ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+ if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) {
+ INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list);
+ bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT;
+ }
+
+ return &bpf_net_ctx->dev_map_flush_list;
+}
+
+static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void)
+{
+ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+ if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) {
+ INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list);
+ bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT;
+ }
+
+ return &bpf_net_ctx->xskmap_map_flush_list;
+}
+
/* Compute the linear packet data range [data, data_end) which
* will be accessed by various program types (cls_bpf, act_bpf,
* lwt, ...). Subsystems allowing direct data access must (!)
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -79,8 +79,6 @@ struct bpf_cpu_map {
struct bpf_cpu_map_entry __rcu **cpu_map;
};
-static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);
-
static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
{
u32 value_size = attr->value_size;
@@ -709,7 +707,7 @@ static void bq_flush_to_queue(struct xdp
*/
static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
{
- struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
+ struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list();
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
@@ -761,7 +759,7 @@ int cpu_map_generic_redirect(struct bpf_
void __cpu_map_flush(void)
{
- struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
+ struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list();
struct xdp_bulk_queue *bq, *tmp;
list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
@@ -775,20 +773,9 @@ void __cpu_map_flush(void)
#ifdef CONFIG_DEBUG_NET
bool cpu_map_check_flush(void)
{
- if (list_empty(this_cpu_ptr(&cpu_map_flush_list)))
+ if (list_empty(bpf_net_ctx_get_cpu_map_flush_list()))
return false;
__cpu_map_flush();
return true;
}
#endif
-
-static int __init cpu_map_init(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu)
- INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu));
- return 0;
-}
-
-subsys_initcall(cpu_map_init);
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -83,7 +83,6 @@ struct bpf_dtab {
u32 n_buckets;
};
-static DEFINE_PER_CPU(struct list_head, dev_flush_list);
static DEFINE_SPINLOCK(dev_map_lock);
static LIST_HEAD(dev_map_list);
@@ -415,7 +414,7 @@ static void bq_xmit_all(struct xdp_dev_b
*/
void __dev_flush(void)
{
- struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+ struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list();
struct xdp_dev_bulk_queue *bq, *tmp;
list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
@@ -429,7 +428,7 @@ void __dev_flush(void)
#ifdef CONFIG_DEBUG_NET
bool dev_check_flush(void)
{
- if (list_empty(this_cpu_ptr(&dev_flush_list)))
+ if (list_empty(bpf_net_ctx_get_dev_flush_list()))
return false;
__dev_flush();
return true;
@@ -460,7 +459,7 @@ static void *__dev_map_lookup_elem(struc
static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx, struct bpf_prog *xdp_prog)
{
- struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+ struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list();
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
@@ -1160,15 +1159,11 @@ static struct notifier_block dev_map_not
static int __init dev_map_init(void)
{
- int cpu;
-
/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
offsetof(struct _bpf_dtab_netdev, dev));
register_netdevice_notifier(&dev_map_notifier);
- for_each_possible_cpu(cpu)
- INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
return 0;
}
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -35,8 +35,6 @@
#define TX_BATCH_SIZE 32
#define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE)
-static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);
-
void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
{
if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -372,7 +370,7 @@ static int xsk_rcv(struct xdp_sock *xs,
int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
{
- struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list);
+ struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list();
int err;
err = xsk_rcv(xs, xdp);
@@ -387,7 +385,7 @@ int __xsk_map_redirect(struct xdp_sock *
void __xsk_map_flush(void)
{
- struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list);
+ struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list();
struct xdp_sock *xs, *tmp;
list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
@@ -399,7 +397,7 @@ void __xsk_map_flush(void)
#ifdef CONFIG_DEBUG_NET
bool xsk_map_check_flush(void)
{
- if (list_empty(this_cpu_ptr(&xskmap_flush_list)))
+ if (list_empty(bpf_net_ctx_get_xskmap_flush_list()))
return false;
__xsk_map_flush();
return true;
@@ -1772,7 +1770,7 @@ static struct pernet_operations xsk_net_
static int __init xsk_init(void)
{
- int err, cpu;
+ int err;
err = proto_register(&xsk_proto, 0 /* no slab */);
if (err)
@@ -1790,8 +1788,6 @@ static int __init xsk_init(void)
if (err)
goto out_pernet;
- for_each_possible_cpu(cpu)
- INIT_LIST_HEAD(&per_cpu(xskmap_flush_list, cpu));
return 0;
out_pernet:
|
