From a76ab5731e32d50ff5b1ae97e9dc4b23f41c23f5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Nov 2024 08:39:07 -0800 Subject: bpf: Find eligible subprogs for private stack support Private stack will be allocated with percpu allocator in jit time. To avoid complexity at runtime, only one copy of private stack is available per cpu per prog. So runtime recursion check is necessary to avoid stack corruption. Current private stack only supports kprobe/perf_event/tp/raw_tp which has recursion check in the kernel, and prog types that use bpf trampoline recursion check. For trampoline related prog types, currently only tracing progs have recursion checking. To avoid complexity, all async_cb subprogs use normal kernel stack including those subprogs used by both main prog subtree and async_cb subtree. Any prog having tail call also uses kernel stack. To avoid jit penalty with private stack support, a subprog stack size threshold is set such that only if the stack size is no less than the threshold, private stack is supported. The current threshold is 64 bytes. This avoids jit penality if the stack usage is small. A useless 'continue' is also removed from a loop in func check_max_stack_depth(). Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20241112163907.2223839-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 7 +++++++ include/linux/filter.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3a74033d49c4..d62bb2ca1828 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -633,6 +633,12 @@ struct bpf_subprog_arg_info { }; }; +enum priv_stack_mode { + PRIV_STACK_UNKNOWN, + NO_PRIV_STACK, + PRIV_STACK_ADAPTIVE, +}; + struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ @@ -653,6 +659,7 @@ struct bpf_subprog_info { /* true if bpf_fastcall stack region is used by functions that can't be inlined */ bool keep_fastcall_stack: 1; + enum priv_stack_mode priv_stack_mode; u8 arg_cnt; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 7d7578a8eac1..3a21947f2fd4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1119,6 +1119,7 @@ bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); +bool bpf_jit_supports_private_stack(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); -- cgit v1.2.3-70-g09d2 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 + kernel/bpf/verifier.c | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') 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; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fb23793ac53d..176d19ad9d07 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6334,6 +6334,14 @@ static int check_max_stack_depth(struct bpf_verifier_env *env) return ret; } } + + for (int i = 0; i < env->subprog_cnt; i++) { + if (si[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) { + env->prog->aux->jits_use_priv_stack = true; + break; + } + } + return 0; } @@ -20274,6 +20282,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; + if (env->subprog_info[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) + func[i]->aux->jits_use_priv_stack = true; + func[i]->jit_requested = 1; func[i]->blinding_requested = prog->blinding_requested; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; -- cgit v1.2.3-70-g09d2 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 --- arch/x86/net/bpf_jit_comp.c | 136 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/bpf.h | 1 + 2 files changed, 137 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 3ff638c37999..8f896c32172c 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -325,6 +325,22 @@ struct jit_context { /* Number of bytes that will be skipped on tailcall */ #define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE) +static void push_r9(u8 **pprog) +{ + u8 *prog = *pprog; + + EMIT2(0x41, 0x51); /* push r9 */ + *pprog = prog; +} + +static void pop_r9(u8 **pprog) +{ + u8 *prog = *pprog; + + EMIT2(0x41, 0x59); /* pop r9 */ + *pprog = prog; +} + static void push_r12(u8 **pprog) { u8 *prog = *pprog; @@ -1404,6 +1420,24 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) *pprog = prog; } +static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr) +{ + u8 *prog = *pprog; + + /* movabs r9, priv_frame_ptr */ + emit_mov_imm64(&prog, X86_REG_R9, (__force long) priv_frame_ptr >> 32, + (u32) (__force long) priv_frame_ptr); + +#ifdef CONFIG_SMP + /* add , gs:[] */ + EMIT2(0x65, 0x4c); + EMIT3(0x03, 0x0c, 0x25); + EMIT((u32)(unsigned long)&this_cpu_off, 4); +#endif + + *pprog = prog; +} + #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) #define __LOAD_TCC_PTR(off) \ @@ -1412,6 +1446,10 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) #define LOAD_TAIL_CALL_CNT_PTR(stack) \ __LOAD_TCC_PTR(BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack)) +/* Memory size/value to protect private stack overflow/underflow */ +#define PRIV_STACK_GUARD_SZ 8 +#define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -1421,7 +1459,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image int insn_cnt = bpf_prog->len; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; + void __percpu *priv_frame_ptr = NULL; u64 arena_vm_start, user_vm_start; + void __percpu *priv_stack_ptr; int i, excnt = 0; int ilen, proglen = 0; u8 *prog = temp; @@ -1429,6 +1469,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image int err; stack_depth = bpf_prog->aux->stack_depth; + priv_stack_ptr = bpf_prog->aux->priv_stack_ptr; + if (priv_stack_ptr) { + priv_frame_ptr = priv_stack_ptr + PRIV_STACK_GUARD_SZ + round_up(stack_depth, 8); + stack_depth = 0; + } arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena); user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena); @@ -1457,6 +1502,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image emit_mov_imm64(&prog, X86_REG_R12, arena_vm_start >> 32, (u32) arena_vm_start); + if (priv_frame_ptr) + emit_priv_frame_ptr(&prog, priv_frame_ptr); + ilen = prog - temp; if (rw_image) memcpy(rw_image + proglen, temp, ilen); @@ -1476,6 +1524,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image u8 *func; int nops; + if (priv_frame_ptr) { + if (src_reg == BPF_REG_FP) + src_reg = X86_REG_R9; + + if (dst_reg == BPF_REG_FP) + dst_reg = X86_REG_R9; + } + switch (insn->code) { /* ALU */ case BPF_ALU | BPF_ADD | BPF_X: @@ -2136,9 +2192,15 @@ populate_extable: } if (!imm32) return -EINVAL; + if (priv_frame_ptr) { + push_r9(&prog); + ip += 2; + } ip += x86_call_depth_emit_accounting(&prog, func, ip); if (emit_call(&prog, func, ip)) return -EINVAL; + if (priv_frame_ptr) + pop_r9(&prog); break; } @@ -3306,6 +3368,42 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf); } +static const char *bpf_get_prog_name(struct bpf_prog *prog) +{ + if (prog->aux->ksym.prog) + return prog->aux->ksym.name; + return prog->aux->name; +} + +static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size) +{ + int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3; + u64 *stack_ptr; + + for_each_possible_cpu(cpu) { + stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu); + stack_ptr[0] = PRIV_STACK_GUARD_VAL; + stack_ptr[underflow_idx] = PRIV_STACK_GUARD_VAL; + } +} + +static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size, + struct bpf_prog *prog) +{ + int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3; + u64 *stack_ptr; + + for_each_possible_cpu(cpu) { + stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu); + if (stack_ptr[0] != PRIV_STACK_GUARD_VAL || + stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL) { + pr_err("BPF private stack overflow/underflow detected for prog %sx\n", + bpf_get_prog_name(prog)); + break; + } + } +} + struct x64_jit_data { struct bpf_binary_header *rw_header; struct bpf_binary_header *header; @@ -3323,7 +3421,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) struct bpf_binary_header *rw_header = NULL; struct bpf_binary_header *header = NULL; struct bpf_prog *tmp, *orig_prog = prog; + void __percpu *priv_stack_ptr = NULL; struct x64_jit_data *jit_data; + int priv_stack_alloc_sz; int proglen, oldproglen = 0; struct jit_context ctx = {}; bool tmp_blinded = false; @@ -3359,6 +3459,23 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) } prog->aux->jit_data = jit_data; } + priv_stack_ptr = prog->aux->priv_stack_ptr; + if (!priv_stack_ptr && prog->aux->jits_use_priv_stack) { + /* Allocate actual private stack size with verifier-calculated + * stack size plus two memory guards to protect overflow and + * underflow. + */ + priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) + + 2 * PRIV_STACK_GUARD_SZ; + priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_sz, 8, GFP_KERNEL); + if (!priv_stack_ptr) { + prog = orig_prog; + goto out_priv_stack; + } + + priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_sz); + prog->aux->priv_stack_ptr = priv_stack_ptr; + } addrs = jit_data->addrs; if (addrs) { ctx = jit_data->ctx; @@ -3494,6 +3611,11 @@ out_image: bpf_prog_fill_jited_linfo(prog, addrs + 1); out_addrs: kvfree(addrs); + if (!image && priv_stack_ptr) { + free_percpu(priv_stack_ptr); + prog->aux->priv_stack_ptr = NULL; + } +out_priv_stack: kfree(jit_data); prog->aux->jit_data = NULL; } @@ -3532,6 +3654,8 @@ void bpf_jit_free(struct bpf_prog *prog) if (prog->jited) { struct x64_jit_data *jit_data = prog->aux->jit_data; struct bpf_binary_header *hdr; + void __percpu *priv_stack_ptr; + int priv_stack_alloc_sz; /* * If we fail the final pass of JIT (from jit_subprogs), @@ -3547,6 +3671,13 @@ void bpf_jit_free(struct bpf_prog *prog) prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset(); hdr = bpf_jit_binary_pack_hdr(prog); bpf_jit_binary_pack_free(hdr, NULL); + priv_stack_ptr = prog->aux->priv_stack_ptr; + if (priv_stack_ptr) { + priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) + + 2 * PRIV_STACK_GUARD_SZ; + priv_stack_check_guard(priv_stack_ptr, priv_stack_alloc_sz, prog); + free_percpu(prog->aux->priv_stack_ptr); + } WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog)); } @@ -3562,6 +3693,11 @@ bool bpf_jit_supports_exceptions(void) return IS_ENABLED(CONFIG_UNWINDER_ORC); } +bool bpf_jit_supports_private_stack(void) +{ + return true; +} + void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) { #if defined(CONFIG_UNWINDER_ORC) 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 v1.2.3-70-g09d2 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 ++ include/linux/bpf_verifier.h | 1 + kernel/bpf/trampoline.c | 4 ++++ kernel/bpf/verifier.c | 7 ++++++- 4 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') 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 */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d62bb2ca1828..6b7c91629176 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -879,6 +879,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) case BPF_PROG_TYPE_TRACING: return prog->expected_attach_type != BPF_TRACE_ITER; case BPF_PROG_TYPE_STRUCT_OPS: + return prog->aux->jits_use_priv_stack; case BPF_PROG_TYPE_LSM: return false; default: diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 9f36c049f4c2..a8d188b31da5 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -899,6 +899,8 @@ static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); + if (prog->aux->recursion_detected) + prog->aux->recursion_detected(prog); return 0; } return bpf_prog_start_time(); @@ -975,6 +977,8 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); + if (prog->aux->recursion_detected) + prog->aux->recursion_detected(prog); return 0; } return bpf_prog_start_time(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 176d19ad9d07..f4c39bb50511 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6110,7 +6110,7 @@ static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog) case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: - if (bpf_prog_check_recur(prog)) + if (prog->aux->priv_stack_requested || bpf_prog_check_recur(prog)) return PRIV_STACK_ADAPTIVE; fallthrough; default: @@ -22053,6 +22053,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } } + if (prog->aux->priv_stack_requested && !bpf_jit_supports_private_stack()) { + verbose(env, "Private stack not supported by jit\n"); + return -EACCES; + } + /* btf_ctx_access() used this to provide argument type info */ prog->aux->ctx_arg_info = st_ops_desc->arg_info[member_idx].info; -- cgit v1.2.3-70-g09d2