From aa3496accc412b3d975e4ee5d06076d73394d8b5 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:55 +0530 Subject: bpf: Refactor kptr_off_tab into btf_record To prepare the BPF verifier to handle special fields in both map values and program allocated types coming from program BTF, we need to refactor the kptr_off_tab handling code into something more generic and reusable across both cases to avoid code duplication. Later patches also require passing this data to helpers at runtime, so that they can work on user defined types, initialize them, destruct them, etc. The main observation is that both map values and such allocated types point to a type in program BTF, hence they can be handled similarly. We can prepare a field metadata table for both cases and store them in struct bpf_map or struct btf depending on the use case. Hence, refactor the code into generic btf_record and btf_field member structs. The btf_record represents the fields of a specific btf_type in user BTF. The cnt indicates the number of special fields we successfully recognized, and field_mask is a bitmask of fields that were found, to enable quick determination of availability of a certain field. Subsequently, refactor the rest of the code to work with these generic types, remove assumptions about kptr and kptr_off_tab, rename variables to more meaningful names, etc. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/arraymap.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 832b2659e96e..417f84342e98 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -310,8 +310,7 @@ static void check_and_free_fields(struct bpf_array *arr, void *val) { if (map_value_has_timer(&arr->map)) bpf_timer_cancel_and_free(val + arr->map.timer_off); - if (map_value_has_kptrs(&arr->map)) - bpf_map_free_kptrs(&arr->map, val); + bpf_obj_free_fields(arr->map.record, val); } /* Called from syscall or from eBPF program */ @@ -409,7 +408,7 @@ static void array_map_free_timers(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - /* We don't reset or free kptr on uref dropping to zero. */ + /* We don't reset or free fields other than timer on uref dropping to zero. */ if (!map_value_has_timer(map)) return; @@ -423,22 +422,22 @@ static void array_map_free(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - if (map_value_has_kptrs(map)) { + if (!IS_ERR_OR_NULL(map->record)) { if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { for (i = 0; i < array->map.max_entries; i++) { void __percpu *pptr = array->pptrs[i & array->index_mask]; int cpu; for_each_possible_cpu(cpu) { - bpf_map_free_kptrs(map, per_cpu_ptr(pptr, cpu)); + bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu)); cond_resched(); } } } else { for (i = 0; i < array->map.max_entries; i++) - bpf_map_free_kptrs(map, array_map_elem_ptr(array, i)); + bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } - bpf_map_free_kptr_off_tab(map); + bpf_map_free_record(map); } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) -- cgit v1.2.3 From db559117828d2448fe81ada051c60bcf39f822e9 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:56 +0530 Subject: bpf: Consolidate spin_lock, timer management into btf_record Now that kptr_off_tab has been refactored into btf_record, and can hold more than one specific field type, accomodate bpf_spin_lock and bpf_timer as well. While they don't require any more metadata than offset, having all special fields in one place allows us to share the same code for allocated user defined types and handle both map values and these allocated objects in a similar fashion. As an optimization, we still keep spin_lock_off and timer_off offsets in the btf_record structure, just to avoid having to find the btf_field struct each time their offset is needed. This is mostly needed to manipulate such objects in a map value at runtime. It's ok to hardcode just one offset as more than one field is disallowed. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/arraymap.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 417f84342e98..672eb17ac421 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -306,13 +306,6 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key return 0; } -static void check_and_free_fields(struct bpf_array *arr, void *val) -{ - if (map_value_has_timer(&arr->map)) - bpf_timer_cancel_and_free(val + arr->map.timer_off); - bpf_obj_free_fields(arr->map.record, val); -} - /* Called from syscall or from eBPF program */ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) @@ -334,13 +327,13 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST; if (unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { val = this_cpu_ptr(array->pptrs[index & array->index_mask]); copy_map_value(map, val, value); - check_and_free_fields(array, val); + bpf_obj_free_fields(array->map.record, val); } else { val = array->value + (u64)array->elem_size * (index & array->index_mask); @@ -348,7 +341,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); - check_and_free_fields(array, val); + bpf_obj_free_fields(array->map.record, val); } return 0; } @@ -385,7 +378,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off); - check_and_free_fields(array, per_cpu_ptr(pptr, cpu)); + bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu)); off += size; } rcu_read_unlock(); @@ -409,11 +402,11 @@ static void array_map_free_timers(struct bpf_map *map) int i; /* We don't reset or free fields other than timer on uref dropping to zero. */ - if (!map_value_has_timer(map)) + if (!btf_record_has_field(map->record, BPF_TIMER)) return; for (i = 0; i < array->map.max_entries; i++) - bpf_timer_cancel_and_free(array_map_elem_ptr(array, i) + map->timer_off); + bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ -- cgit v1.2.3 From d7f5ef653c3dd0c0d649cae6ef2708053bb1fb2b Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:52 +0530 Subject: bpf: Do btf_record_free outside map_free callback Since the commit being fixed, we now miss freeing btf_record for local storage maps which will have a btf_record populated in case they have bpf_spin_lock element. This was missed because I made the choice of offloading the job to free kptr_off_tab (now btf_record) to the map_free callback when adding support for kptrs. Revisiting the reason for this decision, there is the possibility that the btf_record gets used inside map_free callback (e.g. in case of maps embedding kptrs) to iterate over them and free them, hence doing it before the map_free callback would be leaking special field memory, and do invalid memory access. The btf_record keeps module references which is critical to ensure the dtor call made for referenced kptr is safe to do. If doing it after map_free callback, the map area is already freed, so we cannot access bpf_map structure anymore. To fix this and prevent such lapses in future, move bpf_map_free_record out of the map_free callback, and do it after map_free by remembering the btf_record pointer. There is no need to access bpf_map structure in that case, and we can avoid missing this case when support for new map types is added for other special fields. Since a btf_record and its btf_field_offs are used together, for consistency delay freeing of field_offs as well. While not a problem right now, a lot of code assumes that either both record and field_offs are set or none at once. Note that in case of map of maps (outer maps), inner_map_meta->record is only used during verification, not to free fields in map value, hence we simply keep the bpf_map_free_record call as is in bpf_map_meta_free and never touch map->inner_map_meta in bpf_map_free_deferred. Add a comment making note of these details. Fixes: db559117828d ("bpf: Consolidate spin_lock, timer management into btf_record") Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/arraymap.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 672eb17ac421..484706959556 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -430,7 +430,6 @@ static void array_map_free(struct bpf_map *map) for (i = 0; i < array->map.max_entries; i++) bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } - bpf_map_free_record(map); } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) -- cgit v1.2.3