From 05a68ce5fa51a83c360381630f823545c5757aa2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 9 Mar 2021 10:50:28 -0800 Subject: bpf: Don't do bpf_cgroup_storage_set() for kuprobe/tp programs For kuprobe and tracepoint bpf programs, kernel calls trace_call_bpf() which calls BPF_PROG_RUN_ARRAY_CHECK() to run the program array. Currently, BPF_PROG_RUN_ARRAY_CHECK() also calls bpf_cgroup_storage_set() to set percpu cgroup local storage with NULL value. This is due to Commit 394e40a29788 ("bpf: extend bpf_prog_array to store pointers to the cgroup storage") which modified __BPF_PROG_RUN_ARRAY() to call bpf_cgroup_storage_set() and this macro is also used by BPF_PROG_RUN_ARRAY_CHECK(). kuprobe and tracepoint programs are not allowed to call bpf_get_local_storage() helper hence does not access percpu cgroup local storage. Let us change BPF_PROG_RUN_ARRAY_CHECK() not to modify percpu cgroup local storage. The issue is observed when I tried to debug [1] where percpu data is overwritten due to preempt_disable -> migration_disable change. This patch does not completely fix the above issue, which will be addressed separately, e.g., multiple cgroup prog runs may preempt each other. But it does fix any potential issue caused by tracing program overwriting percpu cgroup storage: - in a busy system, a tracing program is to run between bpf_cgroup_storage_set() and the cgroup prog run. - a kprobe program is triggered by a helper in cgroup prog before bpf_get_local_storage() is called. [1] https://lore.kernel.org/bpf/CAKH8qBuXCfUz=w8L+Fj74OaUpbosO29niYwTki7e3Ag044_aww@mail.gmail.com/T Fixes: 394e40a29788 ("bpf: extend bpf_prog_array to store pointers to the cgroup storage") Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Roman Gushchin Link: https://lore.kernel.org/bpf/20210309185028.3763817-1-yhs@fb.com --- include/linux/bpf.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cccaef1088ea..d7e0f479a5b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1093,7 +1093,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, _ret; \ }) -#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ +#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \ ({ \ struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ @@ -1106,7 +1106,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, goto _out; \ _item = &_array->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ + if (set_cg_storage) \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ _ret &= func(_prog, ctx); \ _item++; \ } \ @@ -1153,10 +1154,10 @@ _out: \ }) #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, false) + __BPF_PROG_RUN_ARRAY(array, ctx, func, false, true) #define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, true) + __BPF_PROG_RUN_ARRAY(array, ctx, func, true, false) #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -- cgit v1.2.3 From e21aa341785c679dd409c8cb71f864c00fe6c463 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 16 Mar 2021 14:00:07 -0700 Subject: bpf: Fix fexit trampoline. The fexit/fmod_ret programs can be attached to kernel functions that can sleep. The synchronize_rcu_tasks() will not wait for such tasks to complete. In such case the trampoline image will be freed and when the task wakes up the return IP will point to freed memory causing the crash. Solve this by adding percpu_ref_get/put for the duration of trampoline and separate trampoline vs its image life times. The "half page" optimization has to be removed, since first_half->second_half->first_half transition cannot be guaranteed to complete in deterministic time. Every trampoline update becomes a new image. The image with fmod_ret or fexit progs will be freed via percpu_ref_kill and call_rcu_tasks. Together they will wait for the original function and trampoline asm to complete. The trampoline is patched from nop to jmp to skip fexit progs. They are freed independently from the trampoline. The image with fentry progs only will be freed via call_rcu_tasks_trace+call_rcu_tasks which will wait for both sleepable and non-sleepable progs to complete. Fixes: fec56f5890d9 ("bpf: Introduce BPF trampoline") Reported-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Paul E. McKenney # for RCU Link: https://lore.kernel.org/bpf/20210316210007.38949-1-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d7e0f479a5b0..3625f019767d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -21,6 +21,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -556,7 +557,8 @@ struct bpf_tramp_progs { * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ -int arch_prepare_bpf_trampoline(void *image, void *image_end, +struct bpf_tramp_image; +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call); @@ -565,6 +567,8 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); +void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); +void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); struct bpf_ksym { unsigned long start; @@ -583,6 +587,18 @@ enum bpf_tramp_prog_type { BPF_TRAMP_REPLACE, /* more than MAX */ }; +struct bpf_tramp_image { + void *image; + struct bpf_ksym ksym; + struct percpu_ref pcref; + void *ip_after_call; + void *ip_epilogue; + union { + struct rcu_head rcu; + struct work_struct work; + }; +}; + struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; @@ -605,9 +621,8 @@ struct bpf_trampoline { /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ - void *image; + struct bpf_tramp_image *cur_image; u64 selector; - struct bpf_ksym ksym; }; struct bpf_attach_target_info { @@ -691,6 +706,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); +int bpf_jit_charge_modmem(u32 pages); +void bpf_jit_uncharge_modmem(u32 pages); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -787,7 +804,6 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; - enum bpf_tramp_prog_type trampoline_prog_type; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; -- cgit v1.2.3