From e00931c02568dc6ac76f94b1ab471de05e6fdfe8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Nov 2024 08:39:12 -0800 Subject: bpf: Enable private stack for eligible subprogs If private stack is used by any subprog, set that subprog prog->aux->jits_use_priv_stack to be true so later jit can allocate private stack for that subprog properly. Also set env->prog->aux->jits_use_priv_stack to be true if any subprog uses private stack. This is a use case for a single main prog (no subprogs) to use private stack, and also a use case for later struct-ops progs where env->prog->aux->jits_use_priv_stack will enable recursion check if any subprog uses private stack. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20241112163912.2224007-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7da41ae2eac8..129b29e85cec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1523,6 +1523,7 @@ struct bpf_prog_aux { bool exception_cb; bool exception_boundary; bool is_extended; /* true if extended by freplace program */ + bool jits_use_priv_stack; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; -- cgit From 7d1cd70d4b16ff0216a5f6c2ae7d0fa9fa978c07 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Nov 2024 08:39:22 -0800 Subject: bpf, x86: Support private stack in jit Private stack is allocated in function bpf_int_jit_compile() with alignment 8. Private stack allocation size includes the stack size determined by verifier and additional space to protect stack overflow and underflow. See below an illustration: ---> memory address increasing [8 bytes to protect overflow] [normal stack] [8 bytes to protect underflow] If overflow/underflow is detected, kernel messages will be emited in dmesg like BPF private stack overflow/underflow detected for prog Fx BPF Private stack overflow/underflow detected for prog bpf_prog_a41699c234a1567a_subprog1x Those messages are generated when I made some changes to jitted code to intentially cause overflow for some progs. For the jited prog, The x86 register 9 (X86_REG_R9) is used to replace bpf frame register (BPF_REG_10). The private stack is used per subprog per cpu. The X86_REG_R9 is saved and restored around every func call (not including tailcall) to maintain correctness of X86_REG_R9. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20241112163922.2224385-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 129b29e85cec..d32cc373dfd1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1507,6 +1507,7 @@ struct bpf_prog_aux { u32 max_rdwr_access; struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; + void __percpu *priv_stack_ptr; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; -- cgit From 5bd36da1e37e7a78e8b38efd287de6e1394b7d6e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Nov 2024 08:39:33 -0800 Subject: bpf: Support private stack for struct_ops progs For struct_ops progs, whether a particular prog uses private stack depends on prog->aux->priv_stack_requested setting before actual insn-level verification for that prog. One particular implementation is to piggyback on struct_ops->check_member(). The next patch has an example for this. The struct_ops->check_member() sets prog->aux->priv_stack_requested to be true which enables private stack usage. The struct_ops prog follows the same rule as kprobe/tracing progs after function bpf_enable_priv_stack(). For example, even a struct_ops prog requests private stack, it could still use normal kernel stack if the stack size is small (< 64 bytes). Similar to tracing progs, nested same cpu same prog run will be skipped. A field (recursion_detected()) is added to bpf_prog_aux structure. If bpf_prog->aux->recursion_detected is implemented by the struct_ops subsystem and nested same cpu/prog happens, the function will be triggered to report an error, collect related info, etc. Acked-by: Tejun Heo Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20241112163933.2224962-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d32cc373dfd1..10945c8858ce 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1525,9 +1525,11 @@ struct bpf_prog_aux { bool exception_boundary; bool is_extended; /* true if extended by freplace program */ bool jits_use_priv_stack; + bool priv_stack_requested; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; + void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */ /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ -- cgit