Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index a367fc8..c61a23b 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -52,7 +52,6 @@ struct xdp_bulk_queue {
struct bpf_cpu_map_entry {
u32 cpu; /* kthread CPU and map index */
int map_id; /* Back reference to map */
- u32 qsize; /* Queue size placeholder for map lookup */
/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
struct xdp_bulk_queue __percpu *bulkq;
@@ -62,34 +61,40 @@ struct bpf_cpu_map_entry {
/* Queue with potential multi-producers, and single-consumer kthread */
struct ptr_ring *queue;
struct task_struct *kthread;
- struct work_struct kthread_stop_wq;
+
+ struct bpf_cpumap_val value;
+ struct bpf_prog *prog;
atomic_t refcnt; /* Control when this struct can be free'ed */
struct rcu_head rcu;
+
+ struct work_struct kthread_stop_wq;
};
struct bpf_cpu_map {
struct bpf_map map;
/* Below members specific for map type */
struct bpf_cpu_map_entry **cpu_map;
- struct list_head __percpu *flush_list;
};
-static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx);
+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;
struct bpf_cpu_map *cmap;
int err = -ENOMEM;
- int ret, cpu;
u64 cost;
+ int ret;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return ERR_PTR(-EPERM);
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
- attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+ (value_size != offsetofend(struct bpf_cpumap_val, qsize) &&
+ value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) ||
+ attr->map_flags & ~BPF_F_NUMA_NODE)
return ERR_PTR(-EINVAL);
cmap = kzalloc(sizeof(*cmap), GFP_USER);
@@ -106,7 +111,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
/* make sure page count doesn't overflow */
cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
- cost += sizeof(struct list_head) * num_possible_cpus();
/* Notice returns -EPERM on if map size is larger than memlock limit */
ret = bpf_map_charge_init(&cmap->map.memory, cost);
@@ -115,23 +119,14 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
goto free_cmap;
}
- cmap->flush_list = alloc_percpu(struct list_head);
- if (!cmap->flush_list)
- goto free_charge;
-
- for_each_possible_cpu(cpu)
- INIT_LIST_HEAD(per_cpu_ptr(cmap->flush_list, cpu));
-
/* Alloc array for possible remote "destination" CPUs */
cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
sizeof(struct bpf_cpu_map_entry *),
cmap->map.numa_node);
if (!cmap->cpu_map)
- goto free_percpu;
+ goto free_charge;
return &cmap->map;
-free_percpu:
- free_percpu(cmap->flush_list);
free_charge:
bpf_map_charge_finish(&cmap->map.memory);
free_cmap:
@@ -160,8 +155,7 @@ static void cpu_map_kthread_stop(struct work_struct *work)
kthread_stop(rcpu->kthread);
}
-static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
- struct xdp_frame *xdpf,
+static struct sk_buff *cpu_map_build_skb(struct xdp_frame *xdpf,
struct sk_buff *skb)
{
unsigned int hard_start_headroom;
@@ -171,25 +165,10 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
/* Part of headroom was reserved to xdpf */
hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom;
- /* build_skb need to place skb_shared_info after SKB end, and
- * also want to know the memory "truesize". Thus, need to
- * know the memory frame size backing xdp_buff.
- *
- * XDP was designed to have PAGE_SIZE frames, but this
- * assumption is not longer true with ixgbe and i40e. It
- * would be preferred to set frame_size to 2048 or 4096
- * depending on the driver.
- * frame_size = 2048;
- * frame_len = frame_size - sizeof(*xdp_frame);
- *
- * Instead, with info avail, skb_shared_info in placed after
- * packet len. This, unfortunately fakes the truesize.
- * Another disadvantage of this approach, the skb_shared_info
- * is not at a fixed memory location, with mixed length
- * packets, which is bad for cache-line hotness.
+ /* Memory size backing xdp_frame data already have reserved
+ * room for build_skb to place skb_shared_info in tailroom.
*/
- frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ frame_size = xdpf->frame_sz;
pkt_data_start = xdpf->data - hard_start_headroom;
skb = build_skb_around(skb, pkt_data_start, frame_size);
@@ -236,6 +215,8 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
{
if (atomic_dec_and_test(&rcpu->refcnt)) {
+ if (rcpu->prog)
+ bpf_prog_put(rcpu->prog);
/* The queue should be empty at this point */
__cpu_map_ring_cleanup(rcpu->queue);
ptr_ring_cleanup(rcpu->queue, NULL);
@@ -244,6 +225,75 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
}
}
+static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
+ void **frames, int n,
+ struct xdp_cpumap_stats *stats)
+{
+ struct xdp_rxq_info rxq;
+ struct xdp_buff xdp;
+ int i, nframes = 0;
+
+ if (!rcpu->prog)
+ return n;
+
+ rcu_read_lock_bh();
+
+ xdp_set_return_frame_no_direct();
+ xdp.rxq = &rxq;
+
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ u32 act;
+ int err;
+
+ rxq.dev = xdpf->dev_rx;
+ rxq.mem = xdpf->mem;
+ /* TODO: report queue_index to xdp_rxq_info */
+
+ xdp_convert_frame_to_buff(xdpf, &xdp);
+
+ act = bpf_prog_run_xdp(rcpu->prog, &xdp);
+ switch (act) {
+ case XDP_PASS:
+ err = xdp_update_frame_from_buff(&xdp, xdpf);
+ if (err < 0) {
+ xdp_return_frame(xdpf);
+ stats->drop++;
+ } else {
+ frames[nframes++] = xdpf;
+ stats->pass++;
+ }
+ break;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(xdpf->dev_rx, &xdp,
+ rcpu->prog);
+ if (unlikely(err)) {
+ xdp_return_frame(xdpf);
+ stats->drop++;
+ } else {
+ stats->redirect++;
+ }
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ fallthrough;
+ case XDP_DROP:
+ xdp_return_frame(xdpf);
+ stats->drop++;
+ break;
+ }
+ }
+
+ if (stats->redirect)
+ xdp_do_flush_map();
+
+ xdp_clear_return_frame_no_direct();
+
+ rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
+
+ return nframes;
+}
+
#define CPUMAP_BATCH 8
static int cpu_map_kthread_run(void *data)
@@ -258,11 +308,12 @@ static int cpu_map_kthread_run(void *data)
* kthread_stop signal until queue is empty.
*/
while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+ struct xdp_cpumap_stats stats = {}; /* zero stats */
+ gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
unsigned int drops = 0, sched = 0;
void *frames[CPUMAP_BATCH];
void *skbs[CPUMAP_BATCH];
- gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
- int i, n, m;
+ int i, n, m, nframes;
/* Release CPU reschedule checks */
if (__ptr_ring_empty(rcpu->queue)) {
@@ -283,8 +334,8 @@ static int cpu_map_kthread_run(void *data)
* kthread CPU pinned. Lockless access to ptr_ring
* consume side valid as no-resize allowed of queue.
*/
- n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH);
-
+ n = __ptr_ring_consume_batched(rcpu->queue, frames,
+ CPUMAP_BATCH);
for (i = 0; i < n; i++) {
void *f = frames[i];
struct page *page = virt_to_page(f);
@@ -296,20 +347,24 @@ static int cpu_map_kthread_run(void *data)
prefetchw(page);
}
- m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs);
- if (unlikely(m == 0)) {
- for (i = 0; i < n; i++)
- skbs[i] = NULL; /* effect: xdp_return_frame */
- drops = n;
+ /* Support running another XDP prog on this CPU */
+ nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats);
+ if (nframes) {
+ m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
+ if (unlikely(m == 0)) {
+ for (i = 0; i < nframes; i++)
+ skbs[i] = NULL; /* effect: xdp_return_frame */
+ drops += nframes;
+ }
}
local_bh_disable();
- for (i = 0; i < n; i++) {
+ for (i = 0; i < nframes; i++) {
struct xdp_frame *xdpf = frames[i];
struct sk_buff *skb = skbs[i];
int ret;
- skb = cpu_map_build_skb(rcpu, xdpf, skb);
+ skb = cpu_map_build_skb(xdpf, skb);
if (!skb) {
xdp_return_frame(xdpf);
continue;
@@ -321,7 +376,7 @@ static int cpu_map_kthread_run(void *data)
drops++;
}
/* Feedback loop via tracepoint */
- trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
+ trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats);
local_bh_enable(); /* resched point, may call do_softirq() */
}
@@ -331,13 +386,38 @@ static int cpu_map_kthread_run(void *data)
return 0;
}
-static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
- int map_id)
+bool cpu_map_prog_allowed(struct bpf_map *map)
{
+ return map->map_type == BPF_MAP_TYPE_CPUMAP &&
+ map->value_size != offsetofend(struct bpf_cpumap_val, qsize);
+}
+
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+{
+ struct bpf_prog *prog;
+
+ prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
+ rcpu->value.bpf_prog.id = prog->aux->id;
+ rcpu->prog = prog;
+
+ return 0;
+}
+
+static struct bpf_cpu_map_entry *
+__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
+{
+ int numa, err, i, fd = value->bpf_prog.fd;
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
struct bpf_cpu_map_entry *rcpu;
struct xdp_bulk_queue *bq;
- int numa, err, i;
/* Have map->numa_node, but choose node of redirect target CPU */
numa = cpu_to_node(cpu);
@@ -362,19 +442,22 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
if (!rcpu->queue)
goto free_bulkq;
- err = ptr_ring_init(rcpu->queue, qsize, gfp);
+ err = ptr_ring_init(rcpu->queue, value->qsize, gfp);
if (err)
goto free_queue;
rcpu->cpu = cpu;
rcpu->map_id = map_id;
- rcpu->qsize = qsize;
+ rcpu->value.qsize = value->qsize;
+
+ if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+ goto free_ptr_ring;
/* Setup kthread */
rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
"cpumap/%d/map:%d", cpu, map_id);
if (IS_ERR(rcpu->kthread))
- goto free_ptr_ring;
+ goto free_prog;
get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
@@ -385,6 +468,9 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
return rcpu;
+free_prog:
+ if (rcpu->prog)
+ bpf_prog_put(rcpu->prog);
free_ptr_ring:
ptr_ring_cleanup(rcpu->queue, NULL);
free_queue:
@@ -399,22 +485,14 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
static void __cpu_map_entry_free(struct rcu_head *rcu)
{
struct bpf_cpu_map_entry *rcpu;
- int cpu;
/* This cpu_map_entry have been disconnected from map and one
- * RCU graze-period have elapsed. Thus, XDP cannot queue any
+ * RCU grace-period have elapsed. Thus, XDP cannot queue any
* new packets and cannot change/set flush_needed that can
* find this entry.
*/
rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
- /* Flush remaining packets in percpu bulkq */
- for_each_online_cpu(cpu) {
- struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
-
- /* No concurrent bq_enqueue can run at this point */
- bq_flush_to_queue(bq, false);
- }
free_percpu(rcpu->bulkq);
/* Cannot kthread_stop() here, last put free rcpu resources */
put_cpu_map_entry(rcpu);
@@ -436,7 +514,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
* percpu bulkq to queue. Due to caller map_delete_elem() disable
* preemption, cannot call kthread_stop() to make sure queue is empty.
* Instead a work_queue is started for stopping kthread,
- * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * cpu_map_kthread_stop, which waits for an RCU grace period before
* stopping kthread, emptying the queue.
*/
static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
@@ -469,12 +547,12 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ struct bpf_cpumap_val cpumap_value = {};
struct bpf_cpu_map_entry *rcpu;
-
/* Array index key correspond to CPU number */
u32 key_cpu = *(u32 *)key;
- /* Value is the queue size */
- u32 qsize = *(u32 *)value;
+
+ memcpy(&cpumap_value, value, map->value_size);
if (unlikely(map_flags > BPF_EXIST))
return -EINVAL;
@@ -482,18 +560,18 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
return -E2BIG;
if (unlikely(map_flags == BPF_NOEXIST))
return -EEXIST;
- if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+ if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */
return -EOVERFLOW;
/* Make sure CPU is a valid possible cpu */
if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
return -ENODEV;
- if (qsize == 0) {
+ if (cpumap_value.qsize == 0) {
rcpu = NULL; /* Same as deleting */
} else {
/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
- rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+ rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id);
if (!rcpu)
return -ENOMEM;
rcpu->cmap = cmap;
@@ -507,7 +585,6 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
static void cpu_map_free(struct bpf_map *map)
{
struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
- int cpu;
u32 i;
/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
@@ -522,18 +599,6 @@ static void cpu_map_free(struct bpf_map *map)
bpf_clear_redirect_map(map);
synchronize_rcu();
- /* To ensure all pending flush operations have completed wait for flush
- * list be empty on _all_ cpus. Because the above synchronize_rcu()
- * ensures the map is disconnected from the program we can assume no new
- * items will be added to the list.
- */
- for_each_online_cpu(cpu) {
- struct list_head *flush_list = per_cpu_ptr(cmap->flush_list, cpu);
-
- while (!list_empty(flush_list))
- cond_resched();
- }
-
/* For cpu_map the remote CPUs can still be using the entries
* (struct bpf_cpu_map_entry).
*/
@@ -544,10 +609,9 @@ static void cpu_map_free(struct bpf_map *map)
if (!rcpu)
continue;
- /* bq flush and cleanup happens after RCU graze-period */
+ /* bq flush and cleanup happens after RCU grace-period */
__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
}
- free_percpu(cmap->flush_list);
bpf_map_area_free(cmap->cpu_map);
kfree(cmap);
}
@@ -569,7 +633,7 @@ static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
struct bpf_cpu_map_entry *rcpu =
__cpu_map_lookup_elem(map, *(u32 *)key);
- return rcpu ? &rcpu->qsize : NULL;
+ return rcpu ? &rcpu->value : NULL;
}
static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -589,7 +653,9 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
return 0;
}
+static int cpu_map_btf_id;
const struct bpf_map_ops cpu_map_ops = {
+ .map_meta_equal = bpf_map_meta_equal,
.map_alloc = cpu_map_alloc,
.map_free = cpu_map_free,
.map_delete_elem = cpu_map_delete_elem,
@@ -597,9 +663,11 @@ const struct bpf_map_ops cpu_map_ops = {
.map_lookup_elem = cpu_map_lookup_elem,
.map_get_next_key = cpu_map_get_next_key,
.map_check_btf = map_check_no_btf,
+ .map_btf_name = "bpf_cpu_map",
+ .map_btf_id = &cpu_map_btf_id,
};
-static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx)
+static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
{
struct bpf_cpu_map_entry *rcpu = bq->obj;
unsigned int processed = 0, drops = 0;
@@ -608,7 +676,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx)
int i;
if (unlikely(!bq->count))
- return 0;
+ return;
q = rcpu->queue;
spin_lock(&q->producer_lock);
@@ -620,10 +688,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx)
err = __ptr_ring_produce(q, xdpf);
if (err) {
drops++;
- if (likely(in_napi_ctx))
- xdp_return_frame_rx_napi(xdpf);
- else
- xdp_return_frame(xdpf);
+ xdp_return_frame_rx_napi(xdpf);
}
processed++;
}
@@ -634,19 +699,18 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx)
/* Feedback loop via tracepoints */
trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
- return 0;
}
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
-static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
+static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
{
- struct list_head *flush_list = this_cpu_ptr(rcpu->cmap->flush_list);
+ struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
- bq_flush_to_queue(bq, true);
+ bq_flush_to_queue(bq);
/* Notice, xdp_buff/page MUST be queued here, long enough for
* driver to code invoking us to finished, due to driver
@@ -661,8 +725,6 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
if (!bq->flush_node.prev)
list_add(&bq->flush_node, flush_list);
-
- return 0;
}
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
@@ -670,7 +732,7 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
{
struct xdp_frame *xdpf;
- xdpf = convert_to_xdp_frame(xdp);
+ xdpf = xdp_convert_buff_to_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
@@ -681,16 +743,26 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
return 0;
}
-void __cpu_map_flush(struct bpf_map *map)
+void __cpu_map_flush(void)
{
- struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
- struct list_head *flush_list = this_cpu_ptr(cmap->flush_list);
+ struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
struct xdp_bulk_queue *bq, *tmp;
list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
- bq_flush_to_queue(bq, true);
+ bq_flush_to_queue(bq);
/* If already running, costs spin_lock_irqsave + smb_mb */
wake_up_process(bq->obj->kthread);
}
}
+
+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);