bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack

BPF trampolines will create a bpf_tramp_run_ctx, a bpf_run_ctx, on
stacks and set/reset the current bpf_run_ctx before/after calling a
bpf_prog.
Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220510205923.3206889-3-kuifeng@fb.com

arch/x86/net/bpf_jit_comp.c

@@ -1763,14 +1763,30 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_tramp_link *l, int stack_size,
-			   bool save_ret)
+			   int run_ctx_off, bool save_ret)
 {
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
+	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
 	struct bpf_prog *p = l->link.prog;
 
+	/* mov rdi, 0 */
+	emit_mov_imm64(&prog, BPF_REG_1, 0, 0);
+
+	/* Prepare struct bpf_tramp_run_ctx.
+	 *
+	 * bpf_tramp_run_ctx is already preserved by
+	 * arch_prepare_bpf_trampoline().
+	 *
+	 * mov QWORD PTR [rbp - run_ctx_off + ctx_cookie_off], rdi
+	 */
+	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
+
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
+	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
+	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
+
 	if (emit_call(&prog,
 		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
 		      __bpf_prog_enter, prog))
@@ -1816,6 +1832,8 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: mov rsi, rbx <- start time in nsec */
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+	/* arg3: lea rdx, [rbp - run_ctx_off] */
+	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
 	if (emit_call(&prog,
 		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
 		      __bpf_prog_exit, prog))
@@ -1853,14 +1871,14 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 		      struct bpf_tramp_links *tl, int stack_size,
-		      bool save_ret)
+		      int run_ctx_off, bool save_ret)
 {
 	int i;
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tl->nr_links; i++) {
 		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
-				    save_ret))
+				    run_ctx_off, save_ret))
 			return -EINVAL;
 	}
 	*pprog = prog;
@@ -1869,7 +1887,7 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 
 static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 			      struct bpf_tramp_links *tl, int stack_size,
-			      u8 **branches)
+			      int run_ctx_off, u8 **branches)
 {
 	u8 *prog = *pprog;
 	int i;
@@ -1880,7 +1898,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_imm32(&prog, false, BPF_REG_0, 0);
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 	for (i = 0; i < tl->nr_links; i++) {
-		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, true))
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true))
 			return -EINVAL;
 
 		/* mod_ret prog stored return value into [rbp - 8]. Emit:
@@ -1986,7 +2004,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				void *orig_call)
 {
 	int ret, i, nr_args = m->nr_args;
-	int regs_off, ip_off, args_off, stack_size = nr_args * 8;
+	int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -2016,6 +2034,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	 * RBP - args_off  [ args count      ]  always
 	 *
 	 * RBP - ip_off    [ traced function ]  BPF_TRAMP_F_IP_ARG flag
+	 *
+	 * RBP - run_ctx_off [ bpf_tramp_run_ctx ]
 	 */
 
 	/* room for return value of orig_call or fentry prog */
@@ -2034,6 +2054,9 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 
 	ip_off = stack_size;
 
+	stack_size += (sizeof(struct bpf_tramp_run_ctx) + 7) & ~0x7;
+	run_ctx_off = stack_size;
+
 	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
@@ -2081,7 +2104,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fentry->nr_links)
-		if (invoke_bpf(m, &prog, fentry, regs_off,
+		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
 			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
 			return -EINVAL;
 
@@ -2092,7 +2115,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			return -ENOMEM;
 
 		if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off,
-				       branches)) {
+				       run_ctx_off, branches)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2129,7 +2152,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fexit->nr_links)
-		if (invoke_bpf(m, &prog, fexit, regs_off, false)) {
+		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}

include/linux/bpf.h

@@ -730,6 +730,8 @@ struct bpf_tramp_links {
 	int nr_links;
 };
 
+struct bpf_tramp_run_ctx;
+
 /* Different use cases for BPF trampoline:
  * 1. replace nop at the function entry (kprobe equivalent)
  *    flags = BPF_TRAMP_F_RESTORE_REGS
@@ -756,10 +758,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i
 				struct bpf_tramp_links *tlinks,
 				void *orig_call);
 /* these two functions are called from generated trampoline */
-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);
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+				       struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
 void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
 
@@ -1351,6 +1354,12 @@ struct bpf_trace_run_ctx {
 	u64 bpf_cookie;
 };
 
+struct bpf_tramp_run_ctx {
+	struct bpf_run_ctx run_ctx;
+	u64 bpf_cookie;
+	struct bpf_run_ctx *saved_run_ctx;
+};
+
 static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
 {
 	struct bpf_run_ctx *old_ctx = NULL;

kernel/bpf/syscall.c

@@ -5020,6 +5020,7 @@ static bool syscall_prog_is_valid_access(int off, int size,
 BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 {
 	struct bpf_prog * __maybe_unused prog;
+	struct bpf_tramp_run_ctx __maybe_unused run_ctx;
 
 	switch (cmd) {
 	case BPF_MAP_CREATE:
@@ -5047,13 +5048,15 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 			return -EINVAL;
 		}
 
-		if (!__bpf_prog_enter_sleepable(prog)) {
+		run_ctx.bpf_cookie = 0;
+		run_ctx.saved_run_ctx = NULL;
+		if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) {
 			/* recursion detected */
 			bpf_prog_put(prog);
 			return -EBUSY;
 		}
 		attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in);
-		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */);
+		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx);
 		bpf_prog_put(prog);
 		return 0;
 #endif

kernel/bpf/trampoline.c

@@ -568,11 +568,14 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
  * [2..MAX_U64] - execute bpf prog and record execution time.
  *     This is start time.
  */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
 	__acquires(RCU)
 {
 	rcu_read_lock();
 	migrate_disable();
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
 	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
 		inc_misses_counter(prog);
 		return 0;
@@ -602,29 +605,38 @@ static void notrace update_prog_stats(struct bpf_prog *prog,
 	}
 }
 
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx)
 	__releases(RCU)
 {
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
 	update_prog_stats(prog, start);
 	__this_cpu_dec(*(prog->active));
 	migrate_enable();
 	rcu_read_unlock();
 }
 
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog)
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
 {
 	rcu_read_lock_trace();
 	migrate_disable();
 	might_fault();
+
 	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
 		inc_misses_counter(prog);
 		return 0;
 	}
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
 	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+				       struct bpf_tramp_run_ctx *run_ctx)
 {
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
 	update_prog_stats(prog, start);
 	__this_cpu_dec(*(prog->active));
 	migrate_enable();