bpf: Zero-fill re-used per-cpu map element

Zero-fill element values for all other cpus than current, just as
when not using prealloc. This is the only way the bpf program can
ensure known initial values for all cpus ('onallcpus' cannot be
set when coming from the bpf program).

The scenario is: bpf program inserts some elements in a per-cpu
map, then deletes some (or userspace does). When later adding
new elements using bpf_map_update_elem(), the bpf program can
only set the value of the new elements for the current cpu.
When prealloc is enabled, previously deleted elements are re-used.
Without the fix, values for other cpus remain whatever they were
when the re-used entry was previously freed.

A selftest is added to validate correct operation in above
scenario as well as in case of LRU per-cpu map element re-use.

Fixes: 6c90598 ("bpf: pre-allocate hash map elements")
Signed-off-by: David Verbeiren <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Acked-by: Matthieu Baerts <[email protected]>
Acked-by: Andrii Nakryiko <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: dverbeir

kernel/bpf/hashtab.c

@@ -703,6 +703,32 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 	}
 }
 
+static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
+			    void *value, bool onallcpus)
+{
+	/* When using prealloc and not setting the initial value on all cpus,
+	 * zero-fill element values for other cpus (just as what happens when
+	 * not using prealloc). Otherwise, bpf program has no way to ensure
+	 * known initial values for cpus other than current one
+	 * (onallcpus=false always when coming from bpf prog).
+	 */
+	if (htab_is_prealloc(htab) && !onallcpus) {
+		u32 size = round_up(htab->map.value_size, 8);
+		int current_cpu = raw_smp_processor_id();
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			if (cpu == current_cpu)
+				bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value,
+						size);
+			else
+				memset(per_cpu_ptr(pptr, cpu), 0, size);
+		}
+	} else {
+		pcpu_copy_value(htab, pptr, value, onallcpus);
+	}
+}
+
 static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 {
 	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
@@ -778,7 +804,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			}
 		}
 
-		pcpu_copy_value(htab, pptr, value, onallcpus);
+		pcpu_init_value(htab, pptr, value, onallcpus);
 
 		if (!prealloc)
 			htab_elem_set_ptr(l_new, key_size, pptr);
@@ -1033,7 +1059,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
 				value, onallcpus);
 	} else {
-		pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+		pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
 				value, onallcpus);
 		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;