Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-10-03

We've added 143 non-merge commits during the last 27 day(s) which contain
a total of 151 files changed, 8321 insertions(+), 1402 deletions(-).

The main changes are:

1) Add kfuncs for PKCS#7 signature verification from BPF programs, from Roberto Sassu.

2) Add support for struct-based arguments for trampoline based BPF programs,
   from Yonghong Song.

3) Fix entry IP for kprobe-multi and trampoline probes under IBT enabled, from Jiri Olsa.

4) Batch of improvements to veristat selftest tool in particular to add CSV output,
   a comparison mode for CSV outputs and filtering, from Andrii Nakryiko.

5) Add preparatory changes needed for the BPF core for upcoming BPF HID support,
   from Benjamin Tissoires.

6) Support for direct writes to nf_conn's mark field from tc and XDP BPF program
   types, from Daniel Xu.

7) Initial batch of documentation improvements for BPF insn set spec, from Dave Thaler.

8) Add a new BPF_MAP_TYPE_USER_RINGBUF map which provides single-user-space-producer /
   single-kernel-consumer semantics for BPF ring buffer, from David Vernet.

9) Follow-up fixes to BPF allocator under RT to always use raw spinlock for the BPF
   hashtab's bucket lock, from Hou Tao.

10) Allow creating an iterator that loops through only the resources of one
    task/thread instead of all, from Kui-Feng Lee.

11) Add support for kptrs in the per-CPU arraymap, from Kumar Kartikeya Dwivedi.

12) Add a new kfunc helper for nf to set src/dst NAT IP/port in a newly allocated CT
    entry which is not yet inserted, from Lorenzo Bianconi.

13) Remove invalid recursion check for struct_ops for TCP congestion control BPF
    programs, from Martin KaFai Lau.

14) Fix W^X issue with BPF trampoline and BPF dispatcher, from Song Liu.

15) Fix percpu_counter leakage in BPF hashtab allocation error path, from Tetsuo Handa.

16) Various cleanups in BPF selftests to use preferred ASSERT_* macros, from Wang Yufen.

17) Add invocation for cgroup/connect{4,6} BPF programs for ICMP pings, from YiFei Zhu.

18) Lift blinding decision under bpf_jit_harden = 1 to bpf_capable(), from Yauheni Kaliuta.

19) Various libbpf fixes and cleanups including a libbpf NULL pointer deref, from Xin Liu.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (143 commits)
  net: netfilter: move bpf_ct_set_nat_info kfunc in nf_nat_bpf.c
  Documentation: bpf: Add implementation notes documentations to table of contents
  bpf, docs: Delete misformatted table.
  selftests/xsk: Fix double free
  bpftool: Fix error message of strerror
  libbpf: Fix overrun in netlink attribute iteration
  selftests/bpf: Fix spelling mistake "unpriviledged" -> "unprivileged"
  samples/bpf: Fix typo in xdp_router_ipv4 sample
  bpftool: Remove unused struct event_ring_info
  bpftool: Remove unused struct btf_attach_point
  bpf, docs: Add TOC and fix formatting.
  bpf, docs: Add Clang note about BPF_ALU
  bpf, docs: Move Clang notes to a separate file
  bpf, docs: Linux byteswap note
  bpf, docs: Move legacy packet instructions to a separate file
  selftests/bpf: Check -EBUSY for the recurred bpf_setsockopt(TCP_CONGESTION)
  bpf: tcp: Stop bpf_setsockopt(TCP_CONGESTION) in init ops to recur itself
  bpf: Refactor bpf_setsockopt(TCP_CONGESTION) handling into another function
  bpf: Move the "cdg" tcp-cc check to the common sol_tcp_sockopt()
  bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline
  ...
====================

Link: https://lore.kernel.org/r/20221003194915.11847-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 55 insertions, 126 deletions

diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
index 8ab4253a1592..c74362854948 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Functions to manage eBPF programs attached to cgroup subsystems
- *
  * Copyright 2022 Google LLC.
  */
 #include "vmlinux.h"
@@ -11,25 +9,14 @@
 
 char _license[] SEC("license") = "GPL";
 
-/*
- * Start times are stored per-task, not per-cgroup, as multiple tasks in one
- * cgroup can perform reclaim concurrently.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
-	__uint(map_flags, BPF_F_NO_PREALLOC);
-	__type(key, int);
-	__type(value, __u64);
-} vmscan_start_time SEC(".maps");
-
-struct vmscan_percpu {
+struct percpu_attach_counter {
 	/* Previous percpu state, to figure out if we have new updates */
 	__u64 prev;
 	/* Current percpu state */
 	__u64 state;
 };
 
-struct vmscan {
+struct attach_counter {
 	/* State propagated through children, pending aggregation */
 	__u64 pending;
 	/* Total state, including all cpus and all children */
@@ -38,147 +25,94 @@ struct vmscan {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
-	__uint(max_entries, 100);
+	__uint(max_entries, 1024);
 	__type(key, __u64);
-	__type(value, struct vmscan_percpu);
-} pcpu_cgroup_vmscan_elapsed SEC(".maps");
+	__type(value, struct percpu_attach_counter);
+} percpu_attach_counters SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
-	__uint(max_entries, 100);
+	__uint(max_entries, 1024);
 	__type(key, __u64);
-	__type(value, struct vmscan);
-} cgroup_vmscan_elapsed SEC(".maps");
+	__type(value, struct attach_counter);
+} attach_counters SEC(".maps");
 
 extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym;
 extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym;
 
-static struct cgroup *task_memcg(struct task_struct *task)
-{
-	int cgrp_id;
-
-#if __has_builtin(__builtin_preserve_enum_value)
-	cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id, memory_cgrp_id);
-#else
-	cgrp_id = memory_cgrp_id;
-#endif
-	return task->cgroups->subsys[cgrp_id]->cgroup;
-}
-
 static uint64_t cgroup_id(struct cgroup *cgrp)
 {
 	return cgrp->kn->id;
 }
 
-static int create_vmscan_percpu_elem(__u64 cg_id, __u64 state)
+static int create_percpu_attach_counter(__u64 cg_id, __u64 state)
 {
-	struct vmscan_percpu pcpu_init = {.state = state, .prev = 0};
+	struct percpu_attach_counter pcpu_init = {.state = state, .prev = 0};
 
-	return bpf_map_update_elem(&pcpu_cgroup_vmscan_elapsed, &cg_id,
+	return bpf_map_update_elem(&percpu_attach_counters, &cg_id,
 				   &pcpu_init, BPF_NOEXIST);
 }
 
-static int create_vmscan_elem(__u64 cg_id, __u64 state, __u64 pending)
+static int create_attach_counter(__u64 cg_id, __u64 state, __u64 pending)
 {
-	struct vmscan init = {.state = state, .pending = pending};
+	struct attach_counter init = {.state = state, .pending = pending};
 
-	return bpf_map_update_elem(&cgroup_vmscan_elapsed, &cg_id,
+	return bpf_map_update_elem(&attach_counters, &cg_id,
 				   &init, BPF_NOEXIST);
 }
 
-SEC("tp_btf/mm_vmscan_memcg_reclaim_begin")
-int BPF_PROG(vmscan_start, int order, gfp_t gfp_flags)
+SEC("fentry/cgroup_attach_task")
+int BPF_PROG(counter, struct cgroup *dst_cgrp, struct task_struct *leader,
+	     bool threadgroup)
 {
-	struct task_struct *task = bpf_get_current_task_btf();
-	__u64 *start_time_ptr;
-
-	start_time_ptr = bpf_task_storage_get(&vmscan_start_time, task, 0,
-					      BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (start_time_ptr)
-		*start_time_ptr = bpf_ktime_get_ns();
-	return 0;
-}
-
-SEC("tp_btf/mm_vmscan_memcg_reclaim_end")
-int BPF_PROG(vmscan_end, unsigned long nr_reclaimed)
-{
-	struct vmscan_percpu *pcpu_stat;
-	struct task_struct *current = bpf_get_current_task_btf();
-	struct cgroup *cgrp;
-	__u64 *start_time_ptr;
-	__u64 current_elapsed, cg_id;
-	__u64 end_time = bpf_ktime_get_ns();
-
-	/*
-	 * cgrp is the first parent cgroup of current that has memcg enabled in
-	 * its subtree_control, or NULL if memcg is disabled in the entire tree.
-	 * In a cgroup hierarchy like this:
-	 *                               a
-	 *                              / \
-	 *                             b   c
-	 *  If "a" has memcg enabled, while "b" doesn't, then processes in "b"
-	 *  will accumulate their stats directly to "a". This makes sure that no
-	 *  stats are lost from processes in leaf cgroups that don't have memcg
-	 *  enabled, but only exposes stats for cgroups that have memcg enabled.
-	 */
-	cgrp = task_memcg(current);
-	if (!cgrp)
+	__u64 cg_id = cgroup_id(dst_cgrp);
+	struct percpu_attach_counter *pcpu_counter = bpf_map_lookup_elem(
+			&percpu_attach_counters,
+			&cg_id);
+
+	if (pcpu_counter)
+		pcpu_counter->state += 1;
+	else if (create_percpu_attach_counter(cg_id, 1))
 		return 0;
 
-	cg_id = cgroup_id(cgrp);
-	start_time_ptr = bpf_task_storage_get(&vmscan_start_time, current, 0,
-					      BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (!start_time_ptr)
-		return 0;
-
-	current_elapsed = end_time - *start_time_ptr;
-	pcpu_stat = bpf_map_lookup_elem(&pcpu_cgroup_vmscan_elapsed,
-					&cg_id);
-	if (pcpu_stat)
-		pcpu_stat->state += current_elapsed;
-	else if (create_vmscan_percpu_elem(cg_id, current_elapsed))
-		return 0;
-
-	cgroup_rstat_updated(cgrp, bpf_get_smp_processor_id());
+	cgroup_rstat_updated(dst_cgrp, bpf_get_smp_processor_id());
 	return 0;
 }
 
 SEC("fentry/bpf_rstat_flush")
-int BPF_PROG(vmscan_flush, struct cgroup *cgrp, struct cgroup *parent, int cpu)
+int BPF_PROG(flusher, struct cgroup *cgrp, struct cgroup *parent, int cpu)
 {
-	struct vmscan_percpu *pcpu_stat;
-	struct vmscan *total_stat, *parent_stat;
+	struct percpu_attach_counter *pcpu_counter;
+	struct attach_counter *total_counter, *parent_counter;
 	__u64 cg_id = cgroup_id(cgrp);
 	__u64 parent_cg_id = parent ? cgroup_id(parent) : 0;
-	__u64 *pcpu_vmscan;
 	__u64 state;
 	__u64 delta = 0;
 
 	/* Add CPU changes on this level since the last flush */
-	pcpu_stat = bpf_map_lookup_percpu_elem(&pcpu_cgroup_vmscan_elapsed,
-					       &cg_id, cpu);
-	if (pcpu_stat) {
-		state = pcpu_stat->state;
-		delta += state - pcpu_stat->prev;
-		pcpu_stat->prev = state;
+	pcpu_counter = bpf_map_lookup_percpu_elem(&percpu_attach_counters,
+						  &cg_id, cpu);
+	if (pcpu_counter) {
+		state = pcpu_counter->state;
+		delta += state - pcpu_counter->prev;
+		pcpu_counter->prev = state;
 	}
 
-	total_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, &cg_id);
-	if (!total_stat) {
-		if (create_vmscan_elem(cg_id, delta, 0))
+	total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id);
+	if (!total_counter) {
+		if (create_attach_counter(cg_id, delta, 0))
 			return 0;
-
 		goto update_parent;
 	}
 
 	/* Collect pending stats from subtree */
-	if (total_stat->pending) {
-		delta += total_stat->pending;
-		total_stat->pending = 0;
+	if (total_counter->pending) {
+		delta += total_counter->pending;
+		total_counter->pending = 0;
 	}
 
 	/* Propagate changes to this cgroup's total */
-	total_stat->state += delta;
+	total_counter->state += delta;
 
 update_parent:
 	/* Skip if there are no changes to propagate, or no parent */
@@ -186,20 +120,20 @@ update_parent:
 		return 0;
 
 	/* Propagate changes to cgroup's parent */
-	parent_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed,
-					  &parent_cg_id);
-	if (parent_stat)
-		parent_stat->pending += delta;
+	parent_counter = bpf_map_lookup_elem(&attach_counters,
+					     &parent_cg_id);
+	if (parent_counter)
+		parent_counter->pending += delta;
 	else
-		create_vmscan_elem(parent_cg_id, 0, delta);
+		create_attach_counter(parent_cg_id, 0, delta);
 	return 0;
 }
 
 SEC("iter.s/cgroup")
-int BPF_PROG(dump_vmscan, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+int BPF_PROG(dumper, struct bpf_iter_meta *meta, struct cgroup *cgrp)
 {
 	struct seq_file *seq = meta->seq;
-	struct vmscan *total_stat;
+	struct attach_counter *total_counter;
 	__u64 cg_id = cgrp ? cgroup_id(cgrp) : 0;
 
 	/* Do nothing for the terminal call */
@@ -209,18 +143,13 @@ int BPF_PROG(dump_vmscan, struct bpf_iter_meta *meta, struct cgroup *cgrp)
 	/* Flush the stats to make sure we get the most updated numbers */
 	cgroup_rstat_flush(cgrp);
 
-	total_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, &cg_id);
-	if (!total_stat) {
-		BPF_SEQ_PRINTF(seq, "cg_id: %llu, total_vmscan_delay: 0\n",
+	total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id);
+	if (!total_counter) {
+		BPF_SEQ_PRINTF(seq, "cg_id: %llu, attach_counter: 0\n",
 			       cg_id);
 	} else {
-		BPF_SEQ_PRINTF(seq, "cg_id: %llu, total_vmscan_delay: %llu\n",
-			       cg_id, total_stat->state);
+		BPF_SEQ_PRINTF(seq, "cg_id: %llu, attach_counter: %llu\n",
+			       cg_id, total_counter->state);
 	}
-
-	/*
-	 * We only dump stats for one cgroup here, so return 1 to stop
-	 * iteration after the first cgroup.
-	 */
-	return 1;
+	return 0;
 }