Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-03-06

We've added 85 non-merge commits during the last 13 day(s) which contain
a total of 131 files changed, 7102 insertions(+), 1792 deletions(-).

The main changes are:

1) Add skb and XDP typed dynptrs which allow BPF programs for more
   ergonomic and less brittle iteration through data and variable-sized
   accesses, from Joanne Koong.

2) Bigger batch of BPF verifier improvements to prepare for upcoming BPF
   open-coded iterators allowing for less restrictive looping capabilities,
   from Andrii Nakryiko.

3) Rework RCU enforcement in the verifier, add kptr_rcu and enforce BPF
   programs to NULL-check before passing such pointers into kfunc,
   from Alexei Starovoitov.

4) Add support for kptrs in percpu hashmaps, percpu LRU hashmaps and in
   local storage maps, from Kumar Kartikeya Dwivedi.

5) Add BPF verifier support for ST instructions in convert_ctx_access()
   which will help new -mcpu=v4 clang flag to start emitting them,
   from Eduard Zingerman.

6) Make uprobe attachment Android APK aware by supporting attachment
   to functions inside ELF objects contained in APKs via function names,
   from Daniel Müller.

7) Add a new flag BPF_F_TIMER_ABS flag for bpf_timer_start() helper
   to start the timer with absolute expiration value instead of relative
   one, from Tero Kristo.

8) Add a new kfunc bpf_cgroup_from_id() to look up cgroups via id,
   from Tejun Heo.

9) Extend libbpf to support users manually attaching kprobes/uprobes
   in the legacy/perf/link mode, from Menglong Dong.

10) Implement workarounds in the mips BPF JIT for DADDI/R4000,
   from Jiaxun Yang.

11) Enable mixing bpf2bpf and tailcalls for the loongarch BPF JIT,
    from Hengqi Chen.

12) Extend BPF instruction set doc with describing the encoding of BPF
    instructions in terms of how bytes are stored under big/little endian,
    from Jose E. Marchesi.

13) Follow-up to enable kfunc support for riscv BPF JIT, from Pu Lehui.

14) Fix bpf_xdp_query() backwards compatibility on old kernels,
    from Yonghong Song.

15) Fix BPF selftest cross compilation with CLANG_CROSS_FLAGS,
    from Florent Revest.

16) Improve bpf_cpumask_ma to only allocate one bpf_mem_cache,
    from Hou Tao.

17) Fix BPF verifier's check_subprogs to not unnecessarily mark
    a subprogram with has_tail_call, from Ilya Leoshkevich.

18) Fix arm syscall regs spec in libbpf's bpf_tracing.h, from Puranjay Mohan.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (85 commits)
  selftests/bpf: Add test for legacy/perf kprobe/uprobe attach mode
  selftests/bpf: Split test_attach_probe into multi subtests
  libbpf: Add support to set kprobe/uprobe attach mode
  tools/resolve_btfids: Add /libsubcmd to .gitignore
  bpf: add support for fixed-size memory pointer returns for kfuncs
  bpf: generalize dynptr_get_spi to be usable for iters
  bpf: mark PTR_TO_MEM as non-null register type
  bpf: move kfunc_call_arg_meta higher in the file
  bpf: ensure that r0 is marked scratched after any function call
  bpf: fix visit_insn()'s detection of BPF_FUNC_timer_set_callback helper
  bpf: clean up visit_insn()'s instruction processing
  selftests/bpf: adjust log_fixup's buffer size for proper truncation
  bpf: honor env->test_state_freq flag in is_state_visited()
  selftests/bpf: enhance align selftest's expected log matching
  bpf: improve regsafe() checks for PTR_TO_{MEM,BUF,TP_BUFFER}
  bpf: improve stack slot state printing
  selftests/bpf: Disassembler tests for verifier.c:convert_ctx_access()
  selftests/bpf: test if pointer type is tracked for BPF_ST_MEM
  bpf: allow ctx writes using BPF_ST_MEM instruction
  bpf: Use separate RCU callbacks for freeing selem
  ...
====================

Link: https://lore.kernel.org/r/20230307004346.27578-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 77 insertions, 8 deletions

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 35f4138a54dc..3d320393a12c 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -51,11 +51,21 @@ owner_storage(struct bpf_local_storage_map *smap, void *owner)
 	return map->ops->map_owner_storage_ptr(owner);
 }
 
+static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem)
+{
+	return !hlist_unhashed_lockless(&selem->snode);
+}
+
 static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
 {
 	return !hlist_unhashed(&selem->snode);
 }
 
+static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem)
+{
+	return !hlist_unhashed_lockless(&selem->map_node);
+}
+
 static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
 {
 	return !hlist_unhashed(&selem->map_node);
@@ -75,6 +85,7 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
 	if (selem) {
 		if (value)
 			copy_map_value(&smap->map, SDATA(selem)->data, value);
+		/* No need to call check_and_init_map_value as memory is zero init */
 		return selem;
 	}
 
@@ -98,7 +109,28 @@ void bpf_local_storage_free_rcu(struct rcu_head *rcu)
 		kfree_rcu(local_storage, rcu);
 }
 
-static void bpf_selem_free_rcu(struct rcu_head *rcu)
+static void bpf_selem_free_fields_rcu(struct rcu_head *rcu)
+{
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map *smap;
+
+	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+	/* protected by the rcu_barrier*() */
+	smap = rcu_dereference_protected(SDATA(selem)->smap, true);
+	bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
+	kfree(selem);
+}
+
+static void bpf_selem_free_fields_trace_rcu(struct rcu_head *rcu)
+{
+	/* Free directly if Tasks Trace RCU GP also implies RCU GP */
+	if (rcu_trace_implies_rcu_gp())
+		bpf_selem_free_fields_rcu(rcu);
+	else
+		call_rcu(rcu, bpf_selem_free_fields_rcu);
+}
+
+static void bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 {
 	struct bpf_local_storage_elem *selem;
 
@@ -119,6 +151,7 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor
 {
 	struct bpf_local_storage_map *smap;
 	bool free_local_storage;
+	struct btf_record *rec;
 	void *owner;
 
 	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
@@ -159,10 +192,26 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor
 	    SDATA(selem))
 		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
 
-	if (use_trace_rcu)
-		call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
-	else
-		kfree_rcu(selem, rcu);
+	/* A different RCU callback is chosen whenever we need to free
+	 * additional fields in selem data before freeing selem.
+	 * bpf_local_storage_map_free only executes rcu_barrier to wait for RCU
+	 * callbacks when it has special fields, hence we can only conditionally
+	 * dereference smap, as by this time the map might have already been
+	 * freed without waiting for our call_rcu callback if it did not have
+	 * any special fields.
+	 */
+	rec = smap->map.record;
+	if (use_trace_rcu) {
+		if (!IS_ERR_OR_NULL(rec))
+			call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_fields_trace_rcu);
+		else
+			call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu);
+	} else {
+		if (!IS_ERR_OR_NULL(rec))
+			call_rcu(&selem->rcu, bpf_selem_free_fields_rcu);
+		else
+			kfree_rcu(selem, rcu);
+	}
 
 	return free_local_storage;
 }
@@ -174,7 +223,7 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem,
 	bool free_local_storage = false;
 	unsigned long flags;
 
-	if (unlikely(!selem_linked_to_storage(selem)))
+	if (unlikely(!selem_linked_to_storage_lockless(selem)))
 		/* selem has already been unlinked from sk */
 		return;
 
@@ -208,7 +257,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 	struct bpf_local_storage_map_bucket *b;
 	unsigned long flags;
 
-	if (unlikely(!selem_linked_to_map(selem)))
+	if (unlikely(!selem_linked_to_map_lockless(selem)))
 		/* selem has already be unlinked from smap */
 		return;
 
@@ -420,7 +469,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		err = check_flags(old_sdata, map_flags);
 		if (err)
 			return ERR_PTR(err);
-		if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
+		if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) {
 			copy_map_value_locked(&smap->map, old_sdata->data,
 					      value, false);
 			return old_sdata;
@@ -713,6 +762,26 @@ void bpf_local_storage_map_free(struct bpf_map *map,
 	 */
 	synchronize_rcu();
 
+	/* Only delay freeing of smap, buckets are not needed anymore */
 	kvfree(smap->buckets);
+
+	/* When local storage has special fields, callbacks for
+	 * bpf_selem_free_fields_rcu and bpf_selem_free_fields_trace_rcu will
+	 * keep using the map BTF record, we need to execute an RCU barrier to
+	 * wait for them as the record will be freed right after our map_free
+	 * callback.
+	 */
+	if (!IS_ERR_OR_NULL(smap->map.record)) {
+		rcu_barrier_tasks_trace();
+		/* We cannot skip rcu_barrier() when rcu_trace_implies_rcu_gp()
+		 * is true, because while call_rcu invocation is skipped in that
+		 * case in bpf_selem_free_fields_trace_rcu (and all local
+		 * storage maps pass use_trace_rcu = true), there can be
+		 * call_rcu callbacks based on use_trace_rcu = false in the
+		 * while ((selem = ...)) loop above or when owner's free path
+		 * calls bpf_local_storage_unlink_nolock.
+		 */
+		rcu_barrier();
+	}
 	bpf_map_area_free(smap);
 }