1 files changed, 78 insertions, 71 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..feabc0193852 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
-	bool bypass_spec_v1 = bpf_bypass_spec_v1();
+	bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL);
 	u64 array_size, mask64;
 	struct bpf_array *array;
 
@@ -246,6 +246,38 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
 }
 
+/* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */
+static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_insn *insn = insn_buf;
+
+	if (!bpf_jit_supports_percpu_insn())
+		return -EOPNOTSUPP;
+
+	if (map->map_flags & BPF_F_INNER_MAP)
+		return -EOPNOTSUPP;
+
+	BUILD_BUG_ON(offsetof(struct bpf_array, map) != 0);
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct bpf_array, pptrs));
+
+	*insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0);
+	if (!map->bypass_spec_v1) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 6);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_0, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 5);
+	}
+
+	*insn++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
+	*insn++ = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
+	*insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(BPF_REG_0, 0);
+	return insn - insn_buf;
+}
+
 static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
@@ -396,17 +428,22 @@ static void *array_map_vmalloc_addr(struct bpf_array *array)
 	return (void *)round_down((unsigned long)array, PAGE_SIZE);
 }
 
-static void array_map_free_timers(struct bpf_map *map)
+static void array_map_free_timers_wq(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
-	/* We don't reset or free fields other than timer on uref dropping to zero. */
-	if (!btf_record_has_field(map->record, BPF_TIMER))
-		return;
-
-	for (i = 0; i < array->map.max_entries; i++)
-		bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i));
+	/* We don't reset or free fields other than timer and workqueue
+	 * on uref dropping to zero.
+	 */
+	if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) {
+		for (i = 0; i < array->map.max_entries; i++) {
+			if (btf_record_has_field(map->record, BPF_TIMER))
+				bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i));
+			if (btf_record_has_field(map->record, BPF_WORKQUEUE))
+				bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i));
+		}
+	}
 }
 
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
@@ -750,7 +787,7 @@ const struct bpf_map_ops array_map_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
-	.map_release_uref = array_map_free_timers,
+	.map_release_uref = array_map_free_timers_wq,
 	.map_lookup_elem = array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
@@ -776,6 +813,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = percpu_array_map_lookup_elem,
+	.map_gen_lookup = percpu_array_map_gen_lookup,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem,
@@ -867,11 +905,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 	}
 
 	if (old_ptr)
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, true);
 	return 0;
 }
 
-static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *old_ptr;
@@ -890,13 +928,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 
 	if (old_ptr) {
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return __fd_array_map_delete_elem(map, key, true);
+}
+
 static void *prog_fd_array_get_ptr(struct bpf_map *map,
 				   struct file *map_file, int fd)
 {
@@ -913,8 +956,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map,
 	return prog;
 }
 
-static void prog_fd_array_put_ptr(void *ptr)
+static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_prog is freed after one RCU or tasks trace grace period */
 	bpf_prog_put(ptr);
 }
 
@@ -924,13 +968,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-static void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		fd_array_map_delete_elem(map, &i);
+		__fd_array_map_delete_elem(map, &i, need_defer);
 }
 
 static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -1012,11 +1056,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
 	mutex_unlock(&aux->poke_mutex);
 }
 
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+				      struct bpf_prog *new, struct bpf_prog *old)
+{
+	WARN_ON_ONCE(1);
+}
+
 static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
-	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -1025,7 +1074,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 
 	list_for_each_entry(elem, &aux->poke_progs, list) {
 		struct bpf_jit_poke_descriptor *poke;
-		int i, ret;
+		int i;
 
 		for (i = 0; i < elem->aux->size_poke_tab; i++) {
 			poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1093,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    activated, so tail call updates can arrive from here
 			 *    while JIT is still finishing its final fixup for
 			 *    non-activated poke entries.
-			 * 3) On program teardown, the program's kallsym entry gets
-			 *    removed out of RCU callback, but we can only untrack
-			 *    from sleepable context, therefore bpf_arch_text_poke()
-			 *    might not see that this is in BPF text section and
-			 *    bails out with -EINVAL. As these are unreachable since
-			 *    RCU grace period already passed, we simply skip them.
-			 * 4) Also programs reaching refcount of zero while patching
+			 * 3) Also programs reaching refcount of zero while patching
 			 *    is in progress is okay since we're protected under
 			 *    poke_mutex and untrack the programs before the JIT
-			 *    buffer is freed. When we're still in the middle of
-			 *    patching and suddenly kallsyms entry of the program
-			 *    gets evicted, we just skip the rest which is fine due
-			 *    to point 3).
-			 * 5) Any other error happening below from bpf_arch_text_poke()
-			 *    is a unexpected bug.
+			 *    buffer is freed.
 			 */
 			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
@@ -1068,39 +1106,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			old_bypass_addr = old ? NULL : poke->bypass_addr;
-			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
-			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
-			if (new) {
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, new_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				if (!old) {
-					ret = bpf_arch_text_poke(poke->tailcall_bypass,
-								 BPF_MOD_JUMP,
-								 poke->bypass_addr,
-								 NULL);
-					BUG_ON(ret < 0 && ret != -EINVAL);
-				}
-			} else {
-				ret = bpf_arch_text_poke(poke->tailcall_bypass,
-							 BPF_MOD_JUMP,
-							 old_bypass_addr,
-							 poke->bypass_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				/* let other CPUs finish the execution of program
-				 * so that it will not possible to expose them
-				 * to invalid nop, stack unwind, nop state
-				 */
-				if (!ret)
-					synchronize_rcu();
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, NULL);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-			}
+			bpf_arch_poke_desc_update(poke, new, old);
 		}
 	}
 }
@@ -1109,7 +1115,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_array_aux,
 					   work)->map;
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, true);
 	bpf_map_put(map);
 }
 
@@ -1189,7 +1195,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
 {
 	struct bpf_event_entry *ee;
 
-	ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
+	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
 	if (ee) {
 		ee->event = perf_file->private_data;
 		ee->perf_file = perf_file;
@@ -1239,8 +1245,9 @@ err_out:
 	return ee;
 }
 
-static void perf_event_fd_array_put_ptr(void *ptr)
+static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_perf_event is freed after one RCU grace period */
 	bpf_event_entry_free_rcu(ptr);
 }
 
@@ -1258,7 +1265,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	for (i = 0; i < array->map.max_entries; i++) {
 		ee = READ_ONCE(array->ptrs[i]);
 		if (ee && ee->map_file == map_file)
-			fd_array_map_delete_elem(map, &i);
+			__fd_array_map_delete_elem(map, &i, true);
 	}
 	rcu_read_unlock();
 }
@@ -1266,7 +1273,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 static void perf_event_fd_array_map_free(struct bpf_map *map)
 {
 	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
-		bpf_fd_array_map_clear(map);
+		bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1294,7 +1301,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 	return cgroup_get_from_fd(fd);
 }
 
-static void cgroup_fd_array_put_ptr(void *ptr)
+static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	/* cgroup_put free cgrp after a rcu grace period */
 	cgroup_put(ptr);
@@ -1302,7 +1309,7 @@ static void cgroup_fd_array_put_ptr(void *ptr)
 
 static void cgroup_fd_array_free(struct bpf_map *map)
 {
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1347,7 +1354,7 @@ static void array_of_map_free(struct bpf_map *map)
 	 * is protected by fdget/fdput.
 	 */
 	bpf_map_meta_free(map->inner_map_meta);
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }