From f4d05259213ff1e91f767c91dcab455f68308fac Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 27 Aug 2020 18:18:06 -0700 Subject: bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com --- kernel/bpf/arraymap.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 8ff419b632a6..40d1f7f94307 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -625,6 +625,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { static int array_map_btf_id; const struct bpf_map_ops array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, @@ -647,6 +648,7 @@ const struct bpf_map_ops array_map_ops = { static int percpu_array_map_btf_id; const struct bpf_map_ops percpu_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, @@ -1003,6 +1005,11 @@ static void prog_array_map_free(struct bpf_map *map) fd_array_map_free(map); } +/* prog_array->aux->{type,jited} is a runtime binding. + * Doing static check alone in the verifier is not enough. + * Thus, prog_array_map cannot be used as an inner_map + * and map_meta_equal is not implemented. + */ static int prog_array_map_btf_id; const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, @@ -1101,6 +1108,7 @@ static void perf_event_fd_array_release(struct bpf_map *map, static int perf_event_array_map_btf_id; const struct bpf_map_ops perf_event_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = fd_array_map_free, @@ -1137,6 +1145,7 @@ static void cgroup_fd_array_free(struct bpf_map *map) static int cgroup_array_map_btf_id; const struct bpf_map_ops cgroup_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, -- cgit v1.2.3 From 134fede4eecfcbe7900e789f625fa6f9c3a8cd0e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 27 Aug 2020 18:18:13 -0700 Subject: bpf: Relax max_entries check for most of the inner map types Most of the maps do not use max_entries during verification time. Thus, those map_meta_equal() do not need to enforce max_entries when it is inserted as an inner map during runtime. The max_entries check is removed from the default implementation bpf_map_meta_equal(). The prog_array_map and xsk_map are exception. Its map_gen_lookup uses max_entries to generate inline lookup code. Thus, they will implement its own map_meta_equal() to enforce max_entries. Since there are only two cases now, the max_entries check is not refactored and stays in its own .c file. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200828011813.1970516-1-kafai@fb.com --- kernel/bpf/arraymap.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 40d1f7f94307..d851ebbcf302 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -487,6 +487,13 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) vma->vm_pgoff + pgoff); } +static bool array_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1) +{ + return meta0->max_entries == meta1->max_entries && + bpf_map_meta_equal(meta0, meta1); +} + struct bpf_iter_seq_array_map_info { struct bpf_map *map; void *percpu_value_buf; @@ -625,7 +632,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { static int array_map_btf_id; const struct bpf_map_ops array_map_ops = { - .map_meta_equal = bpf_map_meta_equal, + .map_meta_equal = array_map_meta_equal, .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, -- cgit v1.2.3 From 1e6c62a8821557720a9b2ea9617359b264f2f67c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 27 Aug 2020 15:01:11 -0700 Subject: bpf: Introduce sleepable BPF programs Introduce sleepable BPF programs that can request such property for themselves via BPF_F_SLEEPABLE flag at program load time. In such case they will be able to use helpers like bpf_copy_from_user() that might sleep. At present only fentry/fexit/fmod_ret and lsm programs can request to be sleepable and only when they are attached to kernel functions that are known to allow sleeping. The non-sleepable programs are relying on implicit rcu_read_lock() and migrate_disable() to protect life time of programs, maps that they use and per-cpu kernel structures used to pass info between bpf programs and the kernel. The sleepable programs cannot be enclosed into rcu_read_lock(). migrate_disable() maps to preempt_disable() in non-RT kernels, so the progs should not be enclosed in migrate_disable() as well. Therefore rcu_read_lock_trace is used to protect the life time of sleepable progs. There are many networking and tracing program types. In many cases the 'struct bpf_prog *' pointer itself is rcu protected within some other kernel data structure and the kernel code is using rcu_dereference() to load that program pointer and call BPF_PROG_RUN() on it. All these cases are not touched. Instead sleepable bpf programs are allowed with bpf trampoline only. The program pointers are hard-coded into generated assembly of bpf trampoline and synchronize_rcu_tasks_trace() is used to protect the life time of the program. The same trampoline can hold both sleepable and non-sleepable progs. When rcu_read_lock_trace is held it means that some sleepable bpf program is running from bpf trampoline. Those programs can use bpf arrays and preallocated hash/lru maps. These map types are waiting on programs to complete via synchronize_rcu_tasks_trace(); Updates to trampoline now has to do synchronize_rcu_tasks_trace() and synchronize_rcu_tasks() to wait for sleepable progs to finish and for trampoline assembly to finish. This is the first step of introducing sleepable progs. Eventually dynamically allocated hash maps can be allowed and networking program types can become sleepable too. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Reviewed-by: Josef Bacik Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20200827220114.69225-3-alexei.starovoitov@gmail.com --- kernel/bpf/arraymap.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index d851ebbcf302..e046fb7d17cd 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "map_in_map.h" -- cgit v1.2.3