From 45cbc7a5e004cf08528ef83633c62120cca3a5ee Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:35 -0700
Subject: [PATCH 01/10] bpf: add a get_helper_proto() utility function

Extract the part of check_helper_call() as a utility function allowing
to query 'struct bpf_func_proto' for a specific helper function id.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-2-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 kernel/bpf/verifier.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4759c0ba192b..3ed67452f8c6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10369,6 +10369,19 @@ static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno
 				 state->callback_subprogno == subprogno);
 }
 
+static int get_helper_proto(struct bpf_verifier_env *env, int func_id,
+			    const struct bpf_func_proto **ptr)
+{
+	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID)
+		return -ERANGE;
+
+	if (!env->ops->get_func_proto)
+		return -EINVAL;
+
+	*ptr = env->ops->get_func_proto(func_id, env->prog);
+	return *ptr ? 0 : -EINVAL;
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			     int *insn_idx_p)
 {
@@ -10385,18 +10398,16 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	/* find function prototype */
 	func_id = insn->imm;
-	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
-		verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
-			func_id);
+	err = get_helper_proto(env, insn->imm, &fn);
+	if (err == -ERANGE) {
+		verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id);
 		return -EINVAL;
 	}
 
-	if (env->ops->get_func_proto)
-		fn = env->ops->get_func_proto(func_id, env->prog);
-	if (!fn) {
+	if (err) {
 		verbose(env, "program of this type cannot use helper %s#%d\n",
 			func_id_name(func_id), func_id);
-		return -EINVAL;
+		return err;
 	}
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */

From 5b5f51bff1b66cedb62b5ba74a1878341204e057 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:36 -0700
Subject: [PATCH 02/10] bpf: no_caller_saved_registers attribute for helper
 calls

GCC and LLVM define a no_caller_saved_registers function attribute.
This attribute means that function scratches only some of
the caller saved registers defined by ABI.
For BPF the set of such registers could be defined as follows:
- R0 is scratched only if function is non-void;
- R1-R5 are scratched only if corresponding parameter type is defined
  in the function prototype.

This commit introduces flag bpf_func_prot->allow_nocsr.
If this flag is set for some helper function, verifier assumes that
it follows no_caller_saved_registers calling convention.

The contract between kernel and clang allows to simultaneously use
such functions and maintain backwards compatibility with old
kernels that don't understand no_caller_saved_registers calls
(nocsr for short):

- clang generates a simple pattern for nocsr calls, e.g.:

    r1 = 1;
    r2 = 2;
    *(u64 *)(r10 - 8)  = r1;
    *(u64 *)(r10 - 16) = r2;
    call %[to_be_inlined]
    r2 = *(u64 *)(r10 - 16);
    r1 = *(u64 *)(r10 - 8);
    r0 = r1;
    r0 += r2;
    exit;

- kernel removes unnecessary spills and fills, if called function is
  inlined by verifier or current JIT (with assumption that patch
  inserted by verifier or JIT honors nocsr contract, e.g. does not
  scratch r3-r5 for the example above), e.g. the code above would be
  transformed to:

    r1 = 1;
    r2 = 2;
    call %[to_be_inlined]
    r0 = r1;
    r0 += r2;
    exit;

Technically, the transformation is split into the following phases:
- function mark_nocsr_patterns(), called from bpf_check()
  searches and marks potential patterns in instruction auxiliary data;
- upon stack read or write access,
  function check_nocsr_stack_contract() is used to verify if
  stack offsets, presumably reserved for nocsr patterns, are used
  only from those patterns;
- function remove_nocsr_spills_fills(), called from bpf_check(),
  applies the rewrite for valid patterns.

See comment in mark_nocsr_pattern_for_call() for more details.

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-3-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 include/linux/bpf.h          |   6 +
 include/linux/bpf_verifier.h |  14 ++
 kernel/bpf/verifier.c        | 317 ++++++++++++++++++++++++++++++++++-
 3 files changed, 334 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f560ea0c2b36..b9425e410bcb 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -808,6 +808,12 @@ struct bpf_func_proto {
 	bool gpl_only;
 	bool pkt_access;
 	bool might_sleep;
+	/* set to true if helper follows contract for gcc/llvm
+	 * attribute no_caller_saved_registers:
+	 * - void functions do not scratch r0
+	 * - functions taking N arguments scratch only registers r1-rN
+	 */
+	bool allow_nocsr;
 	enum bpf_return_type ret_type;
 	union {
 		struct {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 731a0a4ac13c..5cea15c81b8a 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -576,6 +576,14 @@ struct bpf_insn_aux_data {
 	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
 	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
 	u8 alu_state; /* used in combination with alu_limit */
+	/* true if STX or LDX instruction is a part of a spill/fill
+	 * pattern for a no_caller_saved_registers call.
+	 */
+	u8 nocsr_pattern:1;
+	/* for CALL instructions, a number of spill/fill pairs in the
+	 * no_caller_saved_registers pattern.
+	 */
+	u8 nocsr_spills_num:3;
 
 	/* below fields are initialized once */
 	unsigned int orig_idx; /* original instruction index */
@@ -645,6 +653,10 @@ struct bpf_subprog_info {
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
 	u16 stack_extra;
+	/* offsets in range [stack_depth .. nocsr_stack_off)
+	 * are used for no_caller_saved_registers spills and fills.
+	 */
+	s16 nocsr_stack_off;
 	bool has_tail_call: 1;
 	bool tail_call_reachable: 1;
 	bool has_ld_abs: 1;
@@ -652,6 +664,8 @@ struct bpf_subprog_info {
 	bool is_async_cb: 1;
 	bool is_exception_cb: 1;
 	bool args_cached: 1;
+	/* true if nocsr stack region is used by functions that can't be inlined */
+	bool keep_nocsr_stack: 1;
 
 	u8 arg_cnt;
 	struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS];
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3ed67452f8c6..7587336967cc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4579,6 +4579,31 @@ static int get_reg_width(struct bpf_reg_state *reg)
 	return fls64(reg->umax_value);
 }
 
+/* See comment for mark_nocsr_pattern_for_call() */
+static void check_nocsr_stack_contract(struct bpf_verifier_env *env, struct bpf_func_state *state,
+				       int insn_idx, int off)
+{
+	struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno];
+	struct bpf_insn_aux_data *aux = env->insn_aux_data;
+	int i;
+
+	if (subprog->nocsr_stack_off <= off || aux[insn_idx].nocsr_pattern)
+		return;
+	/* access to the region [max_stack_depth .. nocsr_stack_off)
+	 * from something that is not a part of the nocsr pattern,
+	 * disable nocsr rewrites for current subprogram by setting
+	 * nocsr_stack_off to a value smaller than any possible offset.
+	 */
+	subprog->nocsr_stack_off = S16_MIN;
+	/* reset nocsr aux flags within subprogram,
+	 * happens at most once per subprogram
+	 */
+	for (i = subprog->start; i < (subprog + 1)->start; ++i) {
+		aux[i].nocsr_spills_num = 0;
+		aux[i].nocsr_pattern = 0;
+	}
+}
+
 /* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
  * stack boundary and alignment are checked in check_mem_access()
  */
@@ -4627,6 +4652,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	if (err)
 		return err;
 
+	check_nocsr_stack_contract(env, state, insn_idx, off);
 	mark_stack_slot_scratched(env, spi);
 	if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) {
 		bool reg_value_fits;
@@ -4761,6 +4787,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
 			return err;
 	}
 
+	check_nocsr_stack_contract(env, state, insn_idx, min_off);
 	/* Variable offset writes destroy any spilled pointers in range. */
 	for (i = min_off; i < max_off; i++) {
 		u8 new_type, *stype;
@@ -4899,6 +4926,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	reg = &reg_state->stack[spi].spilled_ptr;
 
 	mark_stack_slot_scratched(env, spi);
+	check_nocsr_stack_contract(env, state, env->insn_idx, off);
 
 	if (is_spilled_reg(&reg_state->stack[spi])) {
 		u8 spill_size = 1;
@@ -5059,6 +5087,7 @@ static int check_stack_read_var_off(struct bpf_verifier_env *env,
 	min_off = reg->smin_value + off;
 	max_off = reg->smax_value + off;
 	mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno);
+	check_nocsr_stack_contract(env, ptr_state, env->insn_idx, min_off);
 	return 0;
 }
 
@@ -6772,10 +6801,20 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
                                           struct bpf_func_state *state,
                                           enum bpf_access_type t)
 {
-	int min_valid_off;
+	struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx];
+	int min_valid_off, max_bpf_stack;
+
+	/* If accessing instruction is a spill/fill from nocsr pattern,
+	 * add room for all caller saved registers below MAX_BPF_STACK.
+	 * In case if nocsr rewrite won't happen maximal stack depth
+	 * would be checked by check_max_stack_depth_subprog().
+	 */
+	max_bpf_stack = MAX_BPF_STACK;
+	if (aux->nocsr_pattern)
+		max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE;
 
 	if (t == BPF_WRITE || env->allow_uninit_stack)
-		min_valid_off = -MAX_BPF_STACK;
+		min_valid_off = -max_bpf_stack;
 	else
 		min_valid_off = -state->allocated_stack;
 
@@ -16061,6 +16100,232 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 	return ret;
 }
 
+/* Bitmask with 1s for all caller saved registers */
+#define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1)
+
+/* Return a bitmask specifying which caller saved registers are
+ * clobbered by a call to a helper *as if* this helper follows
+ * no_caller_saved_registers contract:
+ * - includes R0 if function is non-void;
+ * - includes R1-R5 if corresponding parameter has is described
+ *   in the function prototype.
+ */
+static u32 helper_nocsr_clobber_mask(const struct bpf_func_proto *fn)
+{
+	u8 mask;
+	int i;
+
+	mask = 0;
+	if (fn->ret_type != RET_VOID)
+		mask |= BIT(BPF_REG_0);
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i)
+		if (fn->arg_type[i] != ARG_DONTCARE)
+			mask |= BIT(BPF_REG_1 + i);
+	return mask;
+}
+
+/* True if do_misc_fixups() replaces calls to helper number 'imm',
+ * replacement patch is presumed to follow no_caller_saved_registers contract
+ * (see mark_nocsr_pattern_for_call() below).
+ */
+static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
+{
+	return false;
+}
+
+/* GCC and LLVM define a no_caller_saved_registers function attribute.
+ * This attribute means that function scratches only some of
+ * the caller saved registers defined by ABI.
+ * For BPF the set of such registers could be defined as follows:
+ * - R0 is scratched only if function is non-void;
+ * - R1-R5 are scratched only if corresponding parameter type is defined
+ *   in the function prototype.
+ *
+ * The contract between kernel and clang allows to simultaneously use
+ * such functions and maintain backwards compatibility with old
+ * kernels that don't understand no_caller_saved_registers calls
+ * (nocsr for short):
+ *
+ * - for nocsr calls clang allocates registers as-if relevant r0-r5
+ *   registers are not scratched by the call;
+ *
+ * - as a post-processing step, clang visits each nocsr call and adds
+ *   spill/fill for every live r0-r5;
+ *
+ * - stack offsets used for the spill/fill are allocated as lowest
+ *   stack offsets in whole function and are not used for any other
+ *   purposes;
+ *
+ * - when kernel loads a program, it looks for such patterns
+ *   (nocsr function surrounded by spills/fills) and checks if
+ *   spill/fill stack offsets are used exclusively in nocsr patterns;
+ *
+ * - if so, and if verifier or current JIT inlines the call to the
+ *   nocsr function (e.g. a helper call), kernel removes unnecessary
+ *   spill/fill pairs;
+ *
+ * - when old kernel loads a program, presence of spill/fill pairs
+ *   keeps BPF program valid, albeit slightly less efficient.
+ *
+ * For example:
+ *
+ *   r1 = 1;
+ *   r2 = 2;
+ *   *(u64 *)(r10 - 8)  = r1;            r1 = 1;
+ *   *(u64 *)(r10 - 16) = r2;            r2 = 2;
+ *   call %[to_be_inlined]         -->   call %[to_be_inlined]
+ *   r2 = *(u64 *)(r10 - 16);            r0 = r1;
+ *   r1 = *(u64 *)(r10 - 8);             r0 += r2;
+ *   r0 = r1;                            exit;
+ *   r0 += r2;
+ *   exit;
+ *
+ * The purpose of mark_nocsr_pattern_for_call is to:
+ * - look for such patterns;
+ * - mark spill and fill instructions in env->insn_aux_data[*].nocsr_pattern;
+ * - mark set env->insn_aux_data[*].nocsr_spills_num for call instruction;
+ * - update env->subprog_info[*]->nocsr_stack_off to find an offset
+ *   at which nocsr spill/fill stack slots start;
+ * - update env->subprog_info[*]->keep_nocsr_stack.
+ *
+ * The .nocsr_pattern and .nocsr_stack_off are used by
+ * check_nocsr_stack_contract() to check if every stack access to
+ * nocsr spill/fill stack slot originates from spill/fill
+ * instructions, members of nocsr patterns.
+ *
+ * If such condition holds true for a subprogram, nocsr patterns could
+ * be rewritten by remove_nocsr_spills_fills().
+ * Otherwise nocsr patterns are not changed in the subprogram
+ * (code, presumably, generated by an older clang version).
+ *
+ * For example, it is *not* safe to remove spill/fill below:
+ *
+ *   r1 = 1;
+ *   *(u64 *)(r10 - 8)  = r1;            r1 = 1;
+ *   call %[to_be_inlined]         -->   call %[to_be_inlined]
+ *   r1 = *(u64 *)(r10 - 8);             r0 = *(u64 *)(r10 - 8);  <---- wrong !!!
+ *   r0 = *(u64 *)(r10 - 8);             r0 += r1;
+ *   r0 += r1;                           exit;
+ *   exit;
+ */
+static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env,
+					struct bpf_subprog_info *subprog,
+					int insn_idx, s16 lowest_off)
+{
+	struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx;
+	struct bpf_insn *call = &env->prog->insnsi[insn_idx];
+	const struct bpf_func_proto *fn;
+	u32 clobbered_regs_mask = ALL_CALLER_SAVED_REGS;
+	u32 expected_regs_mask;
+	bool can_be_inlined = false;
+	s16 off;
+	int i;
+
+	if (bpf_helper_call(call)) {
+		if (get_helper_proto(env, call->imm, &fn) < 0)
+			/* error would be reported later */
+			return;
+		clobbered_regs_mask = helper_nocsr_clobber_mask(fn);
+		can_be_inlined = fn->allow_nocsr &&
+				 (verifier_inlines_helper_call(env, call->imm) ||
+				  bpf_jit_inlines_helper_call(call->imm));
+	}
+
+	if (clobbered_regs_mask == ALL_CALLER_SAVED_REGS)
+		return;
+
+	/* e.g. if helper call clobbers r{0,1}, expect r{2,3,4,5} in the pattern */
+	expected_regs_mask = ~clobbered_regs_mask & ALL_CALLER_SAVED_REGS;
+
+	/* match pairs of form:
+	 *
+	 * *(u64 *)(r10 - Y) = rX   (where Y % 8 == 0)
+	 * ...
+	 * call %[to_be_inlined]
+	 * ...
+	 * rX = *(u64 *)(r10 - Y)
+	 */
+	for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) {
+		if (insn_idx - i < 0 || insn_idx + i >= env->prog->len)
+			break;
+		stx = &insns[insn_idx - i];
+		ldx = &insns[insn_idx + i];
+		/* must be a stack spill/fill pair */
+		if (stx->code != (BPF_STX | BPF_MEM | BPF_DW) ||
+		    ldx->code != (BPF_LDX | BPF_MEM | BPF_DW) ||
+		    stx->dst_reg != BPF_REG_10 ||
+		    ldx->src_reg != BPF_REG_10)
+			break;
+		/* must be a spill/fill for the same reg */
+		if (stx->src_reg != ldx->dst_reg)
+			break;
+		/* must be one of the previously unseen registers */
+		if ((BIT(stx->src_reg) & expected_regs_mask) == 0)
+			break;
+		/* must be a spill/fill for the same expected offset,
+		 * no need to check offset alignment, BPF_DW stack access
+		 * is always 8-byte aligned.
+		 */
+		if (stx->off != off || ldx->off != off)
+			break;
+		expected_regs_mask &= ~BIT(stx->src_reg);
+		env->insn_aux_data[insn_idx - i].nocsr_pattern = 1;
+		env->insn_aux_data[insn_idx + i].nocsr_pattern = 1;
+	}
+	if (i == 1)
+		return;
+
+	/* Conditionally set 'nocsr_spills_num' to allow forward
+	 * compatibility when more helper functions are marked as
+	 * nocsr at compile time than current kernel supports, e.g:
+	 *
+	 *   1: *(u64 *)(r10 - 8) = r1
+	 *   2: call A                  ;; assume A is nocsr for current kernel
+	 *   3: r1 = *(u64 *)(r10 - 8)
+	 *   4: *(u64 *)(r10 - 8) = r1
+	 *   5: call B                  ;; assume B is not nocsr for current kernel
+	 *   6: r1 = *(u64 *)(r10 - 8)
+	 *
+	 * There is no need to block nocsr rewrite for such program.
+	 * Set 'nocsr_pattern' for both calls to keep check_nocsr_stack_contract() happy,
+	 * don't set 'nocsr_spills_num' for call B so that remove_nocsr_spills_fills()
+	 * does not remove spill/fill pair {4,6}.
+	 */
+	if (can_be_inlined)
+		env->insn_aux_data[insn_idx].nocsr_spills_num = i - 1;
+	else
+		subprog->keep_nocsr_stack = 1;
+	subprog->nocsr_stack_off = min(subprog->nocsr_stack_off, off);
+}
+
+static int mark_nocsr_patterns(struct bpf_verifier_env *env)
+{
+	struct bpf_subprog_info *subprog = env->subprog_info;
+	struct bpf_insn *insn;
+	s16 lowest_off;
+	int s, i;
+
+	for (s = 0; s < env->subprog_cnt; ++s, ++subprog) {
+		/* find lowest stack spill offset used in this subprog */
+		lowest_off = 0;
+		for (i = subprog->start; i < (subprog + 1)->start; ++i) {
+			insn = env->prog->insnsi + i;
+			if (insn->code != (BPF_STX | BPF_MEM | BPF_DW) ||
+			    insn->dst_reg != BPF_REG_10)
+				continue;
+			lowest_off = min(lowest_off, insn->off);
+		}
+		/* use this offset to find nocsr patterns */
+		for (i = subprog->start; i < (subprog + 1)->start; ++i) {
+			insn = env->prog->insnsi + i;
+			if (insn->code != (BPF_JMP | BPF_CALL))
+				continue;
+			mark_nocsr_pattern_for_call(env, subprog, i, lowest_off);
+		}
+	}
+	return 0;
+}
+
 /* Visits the instruction at index t and returns one of the following:
  *  < 0 - an error occurred
  *  DONE_EXPLORING - the instruction was fully explored
@@ -19209,9 +19474,11 @@ static int opt_remove_dead_code(struct bpf_verifier_env *env)
 	return 0;
 }
 
+static const struct bpf_insn NOP = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+
 static int opt_remove_nops(struct bpf_verifier_env *env)
 {
-	const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+	const struct bpf_insn ja = NOP;
 	struct bpf_insn *insn = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
 	int i, err;
@@ -20957,6 +21224,40 @@ static int optimize_bpf_loop(struct bpf_verifier_env *env)
 	return 0;
 }
 
+/* Remove unnecessary spill/fill pairs, members of nocsr pattern,
+ * adjust subprograms stack depth when possible.
+ */
+static int remove_nocsr_spills_fills(struct bpf_verifier_env *env)
+{
+	struct bpf_subprog_info *subprog = env->subprog_info;
+	struct bpf_insn_aux_data *aux = env->insn_aux_data;
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	u32 spills_num;
+	bool modified = false;
+	int i, j;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (aux[i].nocsr_spills_num > 0) {
+			spills_num = aux[i].nocsr_spills_num;
+			/* NOPs would be removed by opt_remove_nops() */
+			for (j = 1; j <= spills_num; ++j) {
+				*(insn - j) = NOP;
+				*(insn + j) = NOP;
+			}
+			modified = true;
+		}
+		if ((subprog + 1)->start == i + 1) {
+			if (modified && !subprog->keep_nocsr_stack)
+				subprog->stack_depth = -subprog->nocsr_stack_off;
+			subprog++;
+			modified = false;
+		}
+	}
+
+	return 0;
+}
+
 static void free_states(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state_list *sl, *sln;
@@ -21871,6 +22172,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret < 0)
 		goto skip_full_check;
 
+	ret = mark_nocsr_patterns(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = do_check_main(env);
 	ret = ret ?: do_check_subprogs(env);
 
@@ -21880,6 +22185,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 skip_full_check:
 	kvfree(env->explored_states);
 
+	/* might decrease stack depth, keep it before passes that
+	 * allocate additional slots.
+	 */
+	if (ret == 0)
+		ret = remove_nocsr_spills_fills(env);
+
 	if (ret == 0)
 		ret = check_max_stack_depth(env);
 

From 91b7fbf3936f5c27d1673264dc24a713290e2165 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:37 -0700
Subject: [PATCH 03/10] bpf, x86, riscv, arm: no_caller_saved_registers for
 bpf_get_smp_processor_id()

The function bpf_get_smp_processor_id() is processed in a different
way, depending on the arch:
- on x86 verifier replaces call to bpf_get_smp_processor_id() with a
  sequence of instructions that modify only r0;
- on riscv64 jit replaces call to bpf_get_smp_processor_id() with a
  sequence of instructions that modify only r0;
- on arm64 jit replaces call to bpf_get_smp_processor_id() with a
  sequence of instructions that modify only r0 and tmp registers.

These rewrites satisfy attribute no_caller_saved_registers contract.
Allow rewrite of no_caller_saved_registers patterns for
bpf_get_smp_processor_id() in order to use this function as a canary
for no_caller_saved_registers tests.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-4-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 kernel/bpf/helpers.c  |  1 +
 kernel/bpf/verifier.c | 11 +++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b5f0adae8293..d02ae323996b 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -158,6 +158,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
 	.func		= bpf_get_smp_processor_id,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
+	.allow_nocsr	= true,
 };
 
 BPF_CALL_0(bpf_get_numa_node_id)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7587336967cc..df3be12096cf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16130,7 +16130,14 @@ static u32 helper_nocsr_clobber_mask(const struct bpf_func_proto *fn)
  */
 static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
 {
-	return false;
+	switch (imm) {
+#ifdef CONFIG_X86_64
+	case BPF_FUNC_get_smp_processor_id:
+		return env->prog->jit_requested && bpf_jit_supports_percpu_insn();
+#endif
+	default:
+		return false;
+	}
 }
 
 /* GCC and LLVM define a no_caller_saved_registers function attribute.
@@ -20834,7 +20841,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 #if defined(CONFIG_X86_64) && !defined(CONFIG_UML)
 		/* Implement bpf_get_smp_processor_id() inline. */
 		if (insn->imm == BPF_FUNC_get_smp_processor_id &&
-		    prog->jit_requested && bpf_jit_supports_percpu_insn()) {
+		    verifier_inlines_helper_call(env, insn->imm)) {
 			/* BPF_FUNC_get_smp_processor_id inlining is an
 			 * optimization, so if pcpu_hot.cpu_number is ever
 			 * changed in some incompatible and hard to support

From 424ebaa3678b0d7f653dffb08eae90424740e0f4 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:38 -0700
Subject: [PATCH 04/10] selftests/bpf: extract utility function for BPF
 disassembly

struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz);

  Disassembles instruction 'insn' to a text buffer 'buf'.
  Removes insn->code hex prefix added by kernel disassembly routine.
  Returns a pointer to the next instruction
  (increments insn by either 1 or 2).

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-5-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 tools/testing/selftests/bpf/Makefile          |  1 +
 tools/testing/selftests/bpf/disasm_helpers.c  | 51 +++++++++++++
 tools/testing/selftests/bpf/disasm_helpers.h  | 12 +++
 .../selftests/bpf/prog_tests/ctx_rewrite.c    | 74 +++----------------
 tools/testing/selftests/bpf/testing_helpers.c |  1 +
 5 files changed, 75 insertions(+), 64 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/disasm_helpers.c
 create mode 100644 tools/testing/selftests/bpf/disasm_helpers.h

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 3318d5425d75..888ba68e6592 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -661,6 +661,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c		\
 			 test_loader.c		\
 			 xsk.c			\
 			 disasm.c		\
+			 disasm_helpers.c	\
 			 json_writer.c 		\
 			 flow_dissector_load.h	\
 			 ip_check_defrag_frags.h
diff --git a/tools/testing/selftests/bpf/disasm_helpers.c b/tools/testing/selftests/bpf/disasm_helpers.c
new file mode 100644
index 000000000000..96b1f2ffe438
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm_helpers.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include <bpf/bpf.h>
+#include "disasm.h"
+
+struct print_insn_context {
+	char *buf;
+	size_t sz;
+};
+
+static void print_insn_cb(void *private_data, const char *fmt, ...)
+{
+	struct print_insn_context *ctx = private_data;
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(ctx->buf, ctx->sz, fmt, args);
+	va_end(args);
+}
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz)
+{
+	struct print_insn_context ctx = {
+		.buf = buf,
+		.sz = buf_sz,
+	};
+	struct bpf_insn_cbs cbs = {
+		.cb_print	= print_insn_cb,
+		.private_data	= &ctx,
+	};
+	char *tmp, *pfx_end, *sfx_start;
+	bool double_insn;
+	int len;
+
+	print_bpf_insn(&cbs, insn, true);
+	/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
+	 * for each instruction (FF stands for instruction `code` byte).
+	 * Remove the prefix inplace, and also simplify call instructions.
+	 * E.g.: "(85) call foo#10" -> "call foo".
+	 * Also remove newline in the end (the 'max(strlen(buf) - 1, 0)' thing).
+	 */
+	pfx_end = buf + 5;
+	sfx_start = buf + max((int)strlen(buf) - 1, 0);
+	if (strncmp(pfx_end, "call ", 5) == 0 && (tmp = strrchr(buf, '#')))
+		sfx_start = tmp;
+	len = sfx_start - pfx_end;
+	memmove(buf, pfx_end, len);
+	buf[len] = 0;
+	double_insn = insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+	return insn + (double_insn ? 2 : 1);
+}
diff --git a/tools/testing/selftests/bpf/disasm_helpers.h b/tools/testing/selftests/bpf/disasm_helpers.h
new file mode 100644
index 000000000000..7b26cab70099
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm_helpers.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __DISASM_HELPERS_H
+#define __DISASM_HELPERS_H
+
+#include <stdlib.h>
+
+struct bpf_insn;
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz);
+
+#endif /* __DISASM_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
index 08b6391f2f56..dd75ccb03770 100644
--- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -10,7 +10,8 @@
 #include "bpf/btf.h"
 #include "bpf_util.h"
 #include "linux/filter.h"
-#include "disasm.h"
+#include "linux/kernel.h"
+#include "disasm_helpers.h"
 
 #define MAX_PROG_TEXT_SZ (32 * 1024)
 
@@ -628,63 +629,6 @@ static bool match_pattern(struct btf *btf, char *pattern, char *text, char *reg_
 	return false;
 }
 
-static void print_insn(void *private_data, const char *fmt, ...)
-{
-	va_list args;
-
-	va_start(args, fmt);
-	vfprintf((FILE *)private_data, fmt, args);
-	va_end(args);
-}
-
-/* Disassemble instructions to a stream */
-static void print_xlated(FILE *out, struct bpf_insn *insn, __u32 len)
-{
-	const struct bpf_insn_cbs cbs = {
-		.cb_print	= print_insn,
-		.cb_call	= NULL,
-		.cb_imm		= NULL,
-		.private_data	= out,
-	};
-	bool double_insn = false;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		if (double_insn) {
-			double_insn = false;
-			continue;
-		}
-
-		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
-		print_bpf_insn(&cbs, insn + i, true);
-	}
-}
-
-/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
- * for each instruction (FF stands for instruction `code` byte).
- * This function removes the prefix inplace for each line in `str`.
- */
-static void remove_insn_prefix(char *str, int size)
-{
-	const int prefix_size = 5;
-
-	int write_pos = 0, read_pos = prefix_size;
-	int len = strlen(str);
-	char c;
-
-	size = min(size, len);
-
-	while (read_pos < size) {
-		c = str[read_pos++];
-		if (c == 0)
-			break;
-		str[write_pos++] = c;
-		if (c == '\n')
-			read_pos += prefix_size;
-	}
-	str[write_pos] = 0;
-}
-
 struct prog_info {
 	char *prog_kind;
 	enum bpf_prog_type prog_type;
@@ -699,9 +643,10 @@ static void match_program(struct btf *btf,
 			  char *reg_map[][2],
 			  bool skip_first_insn)
 {
-	struct bpf_insn *buf = NULL;
+	struct bpf_insn *buf = NULL, *insn, *insn_end;
 	int err = 0, prog_fd = 0;
 	FILE *prog_out = NULL;
+	char insn_buf[64];
 	char *text = NULL;
 	__u32 cnt = 0;
 
@@ -739,12 +684,13 @@ static void match_program(struct btf *btf,
 		PRINT_FAIL("Can't open memory stream\n");
 		goto out;
 	}
-	if (skip_first_insn)
-		print_xlated(prog_out, buf + 1, cnt - 1);
-	else
-		print_xlated(prog_out, buf, cnt);
+	insn_end = buf + cnt;
+	insn = buf + (skip_first_insn ? 1 : 0);
+	while (insn < insn_end) {
+		insn = disasm_insn(insn, insn_buf, sizeof(insn_buf));
+		fprintf(prog_out, "%s\n", insn_buf);
+	}
 	fclose(prog_out);
-	remove_insn_prefix(text, MAX_PROG_TEXT_SZ);
 
 	ASSERT_TRUE(match_pattern(btf, pattern, text, reg_map),
 		    pinfo->prog_kind);
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index d5379a0e6da8..ac7c66f4fc7b 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "disasm.h"
 #include "test_progs.h"
 #include "testing_helpers.h"
 #include <linux/membarrier.h>

From 203e6aba7692bca18fd97251b1354da0f5e2ba30 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:39 -0700
Subject: [PATCH 05/10] selftests/bpf: print correct offset for pseudo calls in
 disasm_insn()

Adjust disasm_helpers.c:disasm_insn() to account for the following
part of the verifier.c:jit_subprogs:

  for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
        /* ... */
        if (!bpf_pseudo_call(insn))
                continue;
        insn->off = env->insn_aux_data[i].call_imm;
        subprog = find_subprog(env, i + insn->off + 1);
        insn->imm = subprog;
  }

Where verifier moves offset of the subprogram to the insn->off field.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-6-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 tools/testing/selftests/bpf/disasm_helpers.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/testing/selftests/bpf/disasm_helpers.c b/tools/testing/selftests/bpf/disasm_helpers.c
index 96b1f2ffe438..f529f1c8c171 100644
--- a/tools/testing/selftests/bpf/disasm_helpers.c
+++ b/tools/testing/selftests/bpf/disasm_helpers.c
@@ -4,6 +4,7 @@
 #include "disasm.h"
 
 struct print_insn_context {
+	char scratch[16];
 	char *buf;
 	size_t sz;
 };
@@ -18,6 +19,22 @@ static void print_insn_cb(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
+static const char *print_call_cb(void *private_data, const struct bpf_insn *insn)
+{
+	struct print_insn_context *ctx = private_data;
+
+	/* For pseudo calls verifier.c:jit_subprogs() hides original
+	 * imm to insn->off and changes insn->imm to be an index of
+	 * the subprog instead.
+	 */
+	if (insn->src_reg == BPF_PSEUDO_CALL) {
+		snprintf(ctx->scratch, sizeof(ctx->scratch), "%+d", insn->off);
+		return ctx->scratch;
+	}
+
+	return NULL;
+}
+
 struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz)
 {
 	struct print_insn_context ctx = {
@@ -26,6 +43,7 @@ struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz)
 	};
 	struct bpf_insn_cbs cbs = {
 		.cb_print	= print_insn_cb,
+		.cb_call	= print_call_cb,
 		.private_data	= &ctx,
 	};
 	char *tmp, *pfx_end, *sfx_start;

From 4ef5d6af493558124b7a6c13cace58b938fe27d4 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:40 -0700
Subject: [PATCH 06/10] selftests/bpf: no need to track next_match_pos in
 struct test_loader

The call stack for validate_case() function looks as follows:
- test_loader__run_subtests()
  - process_subtest()
    - run_subtest()
      - prepare_case(), which does 'tester->next_match_pos = 0';
      - validate_case(), which increments tester->next_match_pos.

Hence, each subtest is run with next_match_pos freshly set to zero.
Meaning that there is no need to persist this variable in the
struct test_loader, use local variable instead.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-7-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 tools/testing/selftests/bpf/test_loader.c | 19 ++++++++-----------
 tools/testing/selftests/bpf/test_progs.h  |  1 -
 2 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index f14e10b0de96..47508cf66e89 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -434,7 +434,6 @@ static void prepare_case(struct test_loader *tester,
 	bpf_program__set_flags(prog, prog_flags | spec->prog_flags);
 
 	tester->log_buf[0] = '\0';
-	tester->next_match_pos = 0;
 }
 
 static void emit_verifier_log(const char *log_buf, bool force)
@@ -450,25 +449,23 @@ static void validate_case(struct test_loader *tester,
 			  struct bpf_program *prog,
 			  int load_err)
 {
-	int i, j, err;
-	char *match;
 	regmatch_t reg_match[1];
+	const char *log = tester->log_buf;
+	int i, j, err;
 
 	for (i = 0; i < subspec->expect_msg_cnt; i++) {
 		struct expect_msg *msg = &subspec->expect_msgs[i];
+		const char *match = NULL;
 
 		if (msg->substr) {
-			match = strstr(tester->log_buf + tester->next_match_pos, msg->substr);
+			match = strstr(log, msg->substr);
 			if (match)
-				tester->next_match_pos = match - tester->log_buf + strlen(msg->substr);
+				log += strlen(msg->substr);
 		} else {
-			err = regexec(&msg->regex,
-				      tester->log_buf + tester->next_match_pos, 1, reg_match, 0);
+			err = regexec(&msg->regex, log, 1, reg_match, 0);
 			if (err == 0) {
-				match = tester->log_buf + tester->next_match_pos + reg_match[0].rm_so;
-				tester->next_match_pos += reg_match[0].rm_eo;
-			} else {
-				match = NULL;
+				match = log + reg_match[0].rm_so;
+				log += reg_match[0].rm_eo;
 			}
 		}
 
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 51341d50213b..b1e949fb16cf 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -447,7 +447,6 @@ typedef int (*pre_execution_cb)(struct bpf_object *obj);
 struct test_loader {
 	char *log_buf;
 	size_t log_buf_sz;
-	size_t next_match_pos;
 	pre_execution_cb pre_execution_cb;
 
 	struct bpf_object *obj;

From 64f01e935ddb26f48baec71883c27878ac4231dc Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:41 -0700
Subject: [PATCH 07/10] selftests/bpf: extract test_loader->expect_msgs as a
 data structure

Non-functional change: use a separate data structure to represented
expected messages in test_loader.
This would allow to use the same functionality for expected set of
disassembled instructions in the follow-up commit.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-8-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 tools/testing/selftests/bpf/test_loader.c | 81 ++++++++++++-----------
 1 file changed, 41 insertions(+), 40 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 47508cf66e89..3f84903558dd 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -55,11 +55,15 @@ struct expect_msg {
 	regex_t regex;
 };
 
+struct expected_msgs {
+	struct expect_msg *patterns;
+	size_t cnt;
+};
+
 struct test_subspec {
 	char *name;
 	bool expect_failure;
-	struct expect_msg *expect_msgs;
-	size_t expect_msg_cnt;
+	struct expected_msgs expect_msgs;
 	int retval;
 	bool execute;
 };
@@ -96,44 +100,45 @@ void test_loader_fini(struct test_loader *tester)
 	free(tester->log_buf);
 }
 
-static void free_test_spec(struct test_spec *spec)
+static void free_msgs(struct expected_msgs *msgs)
 {
 	int i;
 
+	for (i = 0; i < msgs->cnt; i++)
+		if (msgs->patterns[i].regex_str)
+			regfree(&msgs->patterns[i].regex);
+	free(msgs->patterns);
+	msgs->patterns = NULL;
+	msgs->cnt = 0;
+}
+
+static void free_test_spec(struct test_spec *spec)
+{
 	/* Deallocate expect_msgs arrays. */
-	for (i = 0; i < spec->priv.expect_msg_cnt; i++)
-		if (spec->priv.expect_msgs[i].regex_str)
-			regfree(&spec->priv.expect_msgs[i].regex);
-	for (i = 0; i < spec->unpriv.expect_msg_cnt; i++)
-		if (spec->unpriv.expect_msgs[i].regex_str)
-			regfree(&spec->unpriv.expect_msgs[i].regex);
+	free_msgs(&spec->priv.expect_msgs);
+	free_msgs(&spec->unpriv.expect_msgs);
 
 	free(spec->priv.name);
 	free(spec->unpriv.name);
-	free(spec->priv.expect_msgs);
-	free(spec->unpriv.expect_msgs);
-
 	spec->priv.name = NULL;
 	spec->unpriv.name = NULL;
-	spec->priv.expect_msgs = NULL;
-	spec->unpriv.expect_msgs = NULL;
 }
 
-static int push_msg(const char *substr, const char *regex_str, struct test_subspec *subspec)
+static int push_msg(const char *substr, const char *regex_str, struct expected_msgs *msgs)
 {
 	void *tmp;
 	int regcomp_res;
 	char error_msg[100];
 	struct expect_msg *msg;
 
-	tmp = realloc(subspec->expect_msgs,
-		      (1 + subspec->expect_msg_cnt) * sizeof(struct expect_msg));
+	tmp = realloc(msgs->patterns,
+		      (1 + msgs->cnt) * sizeof(struct expect_msg));
 	if (!tmp) {
 		ASSERT_FAIL("failed to realloc memory for messages\n");
 		return -ENOMEM;
 	}
-	subspec->expect_msgs = tmp;
-	msg = &subspec->expect_msgs[subspec->expect_msg_cnt];
+	msgs->patterns = tmp;
+	msg = &msgs->patterns[msgs->cnt];
 
 	if (substr) {
 		msg->substr = substr;
@@ -150,7 +155,7 @@ static int push_msg(const char *substr, const char *regex_str, struct test_subsp
 		}
 	}
 
-	subspec->expect_msg_cnt += 1;
+	msgs->cnt += 1;
 	return 0;
 }
 
@@ -272,25 +277,25 @@ static int parse_test_spec(struct test_loader *tester,
 			spec->mode_mask |= UNPRIV;
 		} else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX)) {
 			msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX) - 1;
-			err = push_msg(msg, NULL, &spec->priv);
+			err = push_msg(msg, NULL, &spec->priv.expect_msgs);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= PRIV;
 		} else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV)) {
 			msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX_UNPRIV) - 1;
-			err = push_msg(msg, NULL, &spec->unpriv);
+			err = push_msg(msg, NULL, &spec->unpriv.expect_msgs);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= UNPRIV;
 		} else if (str_has_pfx(s, TEST_TAG_EXPECT_REGEX_PFX)) {
 			msg = s + sizeof(TEST_TAG_EXPECT_REGEX_PFX) - 1;
-			err = push_msg(NULL, msg, &spec->priv);
+			err = push_msg(NULL, msg, &spec->priv.expect_msgs);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= PRIV;
 		} else if (str_has_pfx(s, TEST_TAG_EXPECT_REGEX_PFX_UNPRIV)) {
 			msg = s + sizeof(TEST_TAG_EXPECT_REGEX_PFX_UNPRIV) - 1;
-			err = push_msg(NULL, msg, &spec->unpriv);
+			err = push_msg(NULL, msg, &spec->unpriv.expect_msgs);
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= UNPRIV;
@@ -387,11 +392,12 @@ static int parse_test_spec(struct test_loader *tester,
 			spec->unpriv.execute = spec->priv.execute;
 		}
 
-		if (!spec->unpriv.expect_msgs) {
-			for (i = 0; i < spec->priv.expect_msg_cnt; i++) {
-				struct expect_msg *msg = &spec->priv.expect_msgs[i];
+		if (spec->unpriv.expect_msgs.cnt == 0) {
+			for (i = 0; i < spec->priv.expect_msgs.cnt; i++) {
+				struct expect_msg *msg = &spec->priv.expect_msgs.patterns[i];
 
-				err = push_msg(msg->substr, msg->regex_str, &spec->unpriv);
+				err = push_msg(msg->substr, msg->regex_str,
+					       &spec->unpriv.expect_msgs);
 				if (err)
 					goto cleanup;
 			}
@@ -443,18 +449,14 @@ static void emit_verifier_log(const char *log_buf, bool force)
 	fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log_buf);
 }
 
-static void validate_case(struct test_loader *tester,
-			  struct test_subspec *subspec,
-			  struct bpf_object *obj,
-			  struct bpf_program *prog,
-			  int load_err)
+static void validate_msgs(char *log_buf, struct expected_msgs *msgs)
 {
 	regmatch_t reg_match[1];
-	const char *log = tester->log_buf;
+	const char *log = log_buf;
 	int i, j, err;
 
-	for (i = 0; i < subspec->expect_msg_cnt; i++) {
-		struct expect_msg *msg = &subspec->expect_msgs[i];
+	for (i = 0; i < msgs->cnt; i++) {
+		struct expect_msg *msg = &msgs->patterns[i];
 		const char *match = NULL;
 
 		if (msg->substr) {
@@ -471,9 +473,9 @@ static void validate_case(struct test_loader *tester,
 
 		if (!ASSERT_OK_PTR(match, "expect_msg")) {
 			if (env.verbosity == VERBOSE_NONE)
-				emit_verifier_log(tester->log_buf, true /*force*/);
+				emit_verifier_log(log_buf, true /*force*/);
 			for (j = 0; j <= i; j++) {
-				msg = &subspec->expect_msgs[j];
+				msg = &msgs->patterns[j];
 				fprintf(stderr, "%s %s: '%s'\n",
 					j < i ? "MATCHED " : "EXPECTED",
 					msg->substr ? "SUBSTR" : " REGEX",
@@ -692,9 +694,8 @@ void run_subtest(struct test_loader *tester,
 			goto tobj_cleanup;
 		}
 	}
-
 	emit_verifier_log(tester->log_buf, false /*force*/);
-	validate_case(tester, subspec, tobj, tprog, err);
+	validate_msgs(tester->log_buf, &subspec->expect_msgs);
 
 	if (should_do_test_run(spec, subspec)) {
 		/* For some reason test_verifier executes programs

From 9c9f7339131030949a8ef111080427ff1a8085b5 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:42 -0700
Subject: [PATCH 08/10] selftests/bpf: allow checking xlated programs in
 verifier_* tests

Add a macro __xlated("...") for use with test_loader tests.

When such annotations are present for the test case:
- bpf_prog_get_info_by_fd() is used to get BPF program after all
  rewrites are applied by verifier.
- the program is disassembled and patterns specified in __xlated are
  searched for in the disassembly text.

__xlated matching follows the same mechanics as __msg:
each subsequent pattern is matched from the point where
previous pattern ended.

This allows to write tests like below, where the goal is to verify the
behavior of one of the of the transformations applied by verifier:

    SEC("raw_tp")
    __xlated("1: w0 = ")
    __xlated("2: r0 = &(void __percpu *)(r0)")
    __xlated("3: r0 = *(u32 *)(r0 +0)")
    __xlated("4: exit")
    __success __naked void simple(void)
    {
            asm volatile (
            "call %[bpf_get_smp_processor_id];"
            "exit;"
            :
            : __imm(bpf_get_smp_processor_id)
            : __clobber_all);
    }

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-9-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 tools/testing/selftests/bpf/progs/bpf_misc.h |  5 ++
 tools/testing/selftests/bpf/test_loader.c    | 82 +++++++++++++++++++-
 2 files changed, 84 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 81097a3f15eb..a70939c7bc26 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -26,6 +26,9 @@
  *
  * __regex           Same as __msg, but using a regular expression.
  * __regex_unpriv    Same as __msg_unpriv but using a regular expression.
+ * __xlated          Expect a line in a disassembly log after verifier applies rewrites.
+ *                   Multiple __xlated attributes could be specified.
+ * __xlated_unpriv   Same as __xlated but for unprivileged mode.
  *
  * __success         Expect program load success in privileged mode.
  * __success_unpriv  Expect program load success in unprivileged mode.
@@ -63,11 +66,13 @@
  */
 #define __msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_msg=" msg)))
 #define __regex(regex)		__attribute__((btf_decl_tag("comment:test_expect_regex=" regex)))
+#define __xlated(msg)		__attribute__((btf_decl_tag("comment:test_expect_xlated=" msg)))
 #define __failure		__attribute__((btf_decl_tag("comment:test_expect_failure")))
 #define __success		__attribute__((btf_decl_tag("comment:test_expect_success")))
 #define __description(desc)	__attribute__((btf_decl_tag("comment:test_description=" desc)))
 #define __msg_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" msg)))
 #define __regex_unpriv(regex)	__attribute__((btf_decl_tag("comment:test_expect_regex_unpriv=" regex)))
+#define __xlated_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" msg)))
 #define __failure_unpriv	__attribute__((btf_decl_tag("comment:test_expect_failure_unpriv")))
 #define __success_unpriv	__attribute__((btf_decl_tag("comment:test_expect_success_unpriv")))
 #define __log_level(lvl)	__attribute__((btf_decl_tag("comment:test_log_level="#lvl)))
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 3f84903558dd..b44b6a2fc82c 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -7,6 +7,7 @@
 #include <bpf/btf.h>
 
 #include "autoconf_helper.h"
+#include "disasm_helpers.h"
 #include "unpriv_helpers.h"
 #include "cap_helpers.h"
 
@@ -19,10 +20,12 @@
 #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
 #define TEST_TAG_EXPECT_MSG_PFX "comment:test_expect_msg="
 #define TEST_TAG_EXPECT_REGEX_PFX "comment:test_expect_regex="
+#define TEST_TAG_EXPECT_XLATED_PFX "comment:test_expect_xlated="
 #define TEST_TAG_EXPECT_FAILURE_UNPRIV "comment:test_expect_failure_unpriv"
 #define TEST_TAG_EXPECT_SUCCESS_UNPRIV "comment:test_expect_success_unpriv"
 #define TEST_TAG_EXPECT_MSG_PFX_UNPRIV "comment:test_expect_msg_unpriv="
 #define TEST_TAG_EXPECT_REGEX_PFX_UNPRIV "comment:test_expect_regex_unpriv="
+#define TEST_TAG_EXPECT_XLATED_PFX_UNPRIV "comment:test_expect_xlated_unpriv="
 #define TEST_TAG_LOG_LEVEL_PFX "comment:test_log_level="
 #define TEST_TAG_PROG_FLAGS_PFX "comment:test_prog_flags="
 #define TEST_TAG_DESCRIPTION_PFX "comment:test_description="
@@ -64,6 +67,7 @@ struct test_subspec {
 	char *name;
 	bool expect_failure;
 	struct expected_msgs expect_msgs;
+	struct expected_msgs expect_xlated;
 	int retval;
 	bool execute;
 };
@@ -117,6 +121,8 @@ static void free_test_spec(struct test_spec *spec)
 	/* Deallocate expect_msgs arrays. */
 	free_msgs(&spec->priv.expect_msgs);
 	free_msgs(&spec->unpriv.expect_msgs);
+	free_msgs(&spec->priv.expect_xlated);
+	free_msgs(&spec->unpriv.expect_xlated);
 
 	free(spec->priv.name);
 	free(spec->unpriv.name);
@@ -299,6 +305,18 @@ static int parse_test_spec(struct test_loader *tester,
 			if (err)
 				goto cleanup;
 			spec->mode_mask |= UNPRIV;
+		} else if (str_has_pfx(s, TEST_TAG_EXPECT_XLATED_PFX)) {
+			msg = s + sizeof(TEST_TAG_EXPECT_XLATED_PFX) - 1;
+			err = push_msg(msg, NULL, &spec->priv.expect_xlated);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= PRIV;
+		} else if (str_has_pfx(s, TEST_TAG_EXPECT_XLATED_PFX_UNPRIV)) {
+			msg = s + sizeof(TEST_TAG_EXPECT_XLATED_PFX_UNPRIV) - 1;
+			err = push_msg(msg, NULL, &spec->unpriv.expect_xlated);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= UNPRIV;
 		} else if (str_has_pfx(s, TEST_TAG_RETVAL_PFX)) {
 			val = s + sizeof(TEST_TAG_RETVAL_PFX) - 1;
 			err = parse_retval(val, &spec->priv.retval, "__retval");
@@ -402,6 +420,16 @@ static int parse_test_spec(struct test_loader *tester,
 					goto cleanup;
 			}
 		}
+		if (spec->unpriv.expect_xlated.cnt == 0) {
+			for (i = 0; i < spec->priv.expect_xlated.cnt; i++) {
+				struct expect_msg *msg = &spec->priv.expect_xlated.patterns[i];
+
+				err = push_msg(msg->substr, msg->regex_str,
+					       &spec->unpriv.expect_xlated);
+				if (err)
+					goto cleanup;
+			}
+		}
 	}
 
 	spec->valid = true;
@@ -449,7 +477,15 @@ static void emit_verifier_log(const char *log_buf, bool force)
 	fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log_buf);
 }
 
-static void validate_msgs(char *log_buf, struct expected_msgs *msgs)
+static void emit_xlated(const char *xlated, bool force)
+{
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "XLATED:\n=============\n%s=============\n", xlated);
+}
+
+static void validate_msgs(char *log_buf, struct expected_msgs *msgs,
+			  void (*emit_fn)(const char *buf, bool force))
 {
 	regmatch_t reg_match[1];
 	const char *log = log_buf;
@@ -473,7 +509,7 @@ static void validate_msgs(char *log_buf, struct expected_msgs *msgs)
 
 		if (!ASSERT_OK_PTR(match, "expect_msg")) {
 			if (env.verbosity == VERBOSE_NONE)
-				emit_verifier_log(log_buf, true /*force*/);
+				emit_fn(log_buf, true /*force*/);
 			for (j = 0; j <= i; j++) {
 				msg = &msgs->patterns[j];
 				fprintf(stderr, "%s %s: '%s'\n",
@@ -610,6 +646,37 @@ static bool should_do_test_run(struct test_spec *spec, struct test_subspec *subs
 	return true;
 }
 
+/* Get a disassembly of BPF program after verifier applies all rewrites */
+static int get_xlated_program_text(int prog_fd, char *text, size_t text_sz)
+{
+	struct bpf_insn *insn_start = NULL, *insn, *insn_end;
+	__u32 insns_cnt = 0, i;
+	char buf[64];
+	FILE *out = NULL;
+	int err;
+
+	err = get_xlated_program(prog_fd, &insn_start, &insns_cnt);
+	if (!ASSERT_OK(err, "get_xlated_program"))
+		goto out;
+	out = fmemopen(text, text_sz, "w");
+	if (!ASSERT_OK_PTR(out, "open_memstream"))
+		goto out;
+	insn_end = insn_start + insns_cnt;
+	insn = insn_start;
+	while (insn < insn_end) {
+		i = insn - insn_start;
+		insn = disasm_insn(insn, buf, sizeof(buf));
+		fprintf(out, "%d: %s\n", i, buf);
+	}
+	fflush(out);
+
+out:
+	free(insn_start);
+	if (out)
+		fclose(out);
+	return err;
+}
+
 /* this function is forced noinline and has short generic name to look better
  * in test_progs output (in case of a failure)
  */
@@ -695,7 +762,16 @@ void run_subtest(struct test_loader *tester,
 		}
 	}
 	emit_verifier_log(tester->log_buf, false /*force*/);
-	validate_msgs(tester->log_buf, &subspec->expect_msgs);
+	validate_msgs(tester->log_buf, &subspec->expect_msgs, emit_verifier_log);
+
+	if (subspec->expect_xlated.cnt) {
+		err = get_xlated_program_text(bpf_program__fd(tprog),
+					      tester->log_buf, tester->log_buf_sz);
+		if (err)
+			goto tobj_cleanup;
+		emit_xlated(tester->log_buf, false /*force*/);
+		validate_msgs(tester->log_buf, &subspec->expect_xlated, emit_xlated);
+	}
 
 	if (should_do_test_run(spec, subspec)) {
 		/* For some reason test_verifier executes programs

From ee7fe84468b1732fe65c5af3836437d54ac4c419 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:43 -0700
Subject: [PATCH 09/10] selftests/bpf: __arch_* macro to limit test cases to
 specific archs

Add annotations __arch_x86_64, __arch_arm64, __arch_riscv64
to specify on which architecture the test case should be tested.
Several __arch_* annotations could be specified at once.
When test case is not run on current arch it is marked as skipped.

For example, the following would be tested only on arm64 and riscv64:

  SEC("raw_tp")
  __arch_arm64
  __arch_riscv64
  __xlated("1: *(u64 *)(r10 - 16) = r1")
  __xlated("2: call")
  __xlated("3: r1 = *(u64 *)(r10 - 16);")
  __success
  __naked void canary_arm64_riscv64(void)
  {
  	asm volatile (
  	"r1 = 1;"
  	"*(u64 *)(r10 - 16) = r1;"
  	"call %[bpf_get_smp_processor_id];"
  	"r1 = *(u64 *)(r10 - 16);"
  	"exit;"
  	:
  	: __imm(bpf_get_smp_processor_id)
  	: __clobber_all);
  }

On x86 it would be skipped:

  #467/2   verifier_nocsr/canary_arm64_riscv64:SKIP

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-10-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 tools/testing/selftests/bpf/progs/bpf_misc.h |  8 ++++
 tools/testing/selftests/bpf/test_loader.c    | 43 ++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index a70939c7bc26..a225cd87897c 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -63,6 +63,10 @@
  * __auxiliary         Annotated program is not a separate test, but used as auxiliary
  *                     for some other test cases and should always be loaded.
  * __auxiliary_unpriv  Same, but load program in unprivileged mode.
+ *
+ * __arch_*          Specify on which architecture the test case should be tested.
+ *                   Several __arch_* annotations could be specified at once.
+ *                   When test case is not run on current arch it is marked as skipped.
  */
 #define __msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_msg=" msg)))
 #define __regex(regex)		__attribute__((btf_decl_tag("comment:test_expect_regex=" regex)))
@@ -82,6 +86,10 @@
 #define __auxiliary		__attribute__((btf_decl_tag("comment:test_auxiliary")))
 #define __auxiliary_unpriv	__attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
 #define __btf_path(path)	__attribute__((btf_decl_tag("comment:test_btf_path=" path)))
+#define __arch(arch)		__attribute__((btf_decl_tag("comment:test_arch=" arch)))
+#define __arch_x86_64		__arch("X86_64")
+#define __arch_arm64		__arch("ARM64")
+#define __arch_riscv64		__arch("RISCV64")
 
 /* Convenience macro for use with 'asm volatile' blocks */
 #define __naked __attribute__((naked))
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index b44b6a2fc82c..12b0c41e8d64 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -34,6 +34,7 @@
 #define TEST_TAG_AUXILIARY "comment:test_auxiliary"
 #define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv"
 #define TEST_BTF_PATH "comment:test_btf_path="
+#define TEST_TAG_ARCH "comment:test_arch="
 
 /* Warning: duplicated in bpf_misc.h */
 #define POINTER_VALUE	0xcafe4all
@@ -80,6 +81,7 @@ struct test_spec {
 	int log_level;
 	int prog_flags;
 	int mode_mask;
+	int arch_mask;
 	bool auxiliary;
 	bool valid;
 };
@@ -213,6 +215,12 @@ static void update_flags(int *flags, int flag, bool clear)
 		*flags |= flag;
 }
 
+enum arch {
+	ARCH_X86_64	= 0x1,
+	ARCH_ARM64	= 0x2,
+	ARCH_RISCV64	= 0x4,
+};
+
 /* Uses btf_decl_tag attributes to describe the expected test
  * behavior, see bpf_misc.h for detailed description of each attribute
  * and attribute combinations.
@@ -226,6 +234,7 @@ static int parse_test_spec(struct test_loader *tester,
 	bool has_unpriv_result = false;
 	bool has_unpriv_retval = false;
 	int func_id, i, err = 0;
+	u32 arch_mask = 0;
 	struct btf *btf;
 
 	memset(spec, 0, sizeof(*spec));
@@ -364,11 +373,26 @@ static int parse_test_spec(struct test_loader *tester,
 					goto cleanup;
 				update_flags(&spec->prog_flags, flags, clear);
 			}
+		} else if (str_has_pfx(s, TEST_TAG_ARCH)) {
+			val = s + sizeof(TEST_TAG_ARCH) - 1;
+			if (strcmp(val, "X86_64") == 0) {
+				arch_mask |= ARCH_X86_64;
+			} else if (strcmp(val, "ARM64") == 0) {
+				arch_mask |= ARCH_ARM64;
+			} else if (strcmp(val, "RISCV64") == 0) {
+				arch_mask |= ARCH_RISCV64;
+			} else {
+				PRINT_FAIL("bad arch spec: '%s'", val);
+				err = -EINVAL;
+				goto cleanup;
+			}
 		} else if (str_has_pfx(s, TEST_BTF_PATH)) {
 			spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
 		}
 	}
 
+	spec->arch_mask = arch_mask;
+
 	if (spec->mode_mask == 0)
 		spec->mode_mask = PRIV;
 
@@ -677,6 +701,20 @@ static int get_xlated_program_text(int prog_fd, char *text, size_t text_sz)
 	return err;
 }
 
+static bool run_on_current_arch(int arch_mask)
+{
+	if (arch_mask == 0)
+		return true;
+#if defined(__x86_64__)
+	return arch_mask & ARCH_X86_64;
+#elif defined(__aarch64__)
+	return arch_mask & ARCH_ARM64;
+#elif defined(__riscv) && __riscv_xlen == 64
+	return arch_mask & ARCH_RISCV64;
+#endif
+	return false;
+}
+
 /* this function is forced noinline and has short generic name to look better
  * in test_progs output (in case of a failure)
  */
@@ -701,6 +739,11 @@ void run_subtest(struct test_loader *tester,
 	if (!test__start_subtest(subspec->name))
 		return;
 
+	if (!run_on_current_arch(spec->arch_mask)) {
+		test__skip();
+		return;
+	}
+
 	if (unpriv) {
 		if (!can_execute_unpriv(tester, spec)) {
 			test__skip();

From d0ad1f8f8846cffebca55abdd1ed275e276a6754 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 22 Jul 2024 16:38:44 -0700
Subject: [PATCH 10/10] selftests/bpf: test no_caller_saved_registers
 spill/fill removal

Tests for no_caller_saved_registers processing logic
(see verifier.c:match_and_mark_nocsr_pattern()):
- a canary positive test case;
- a canary test case for arm64 and riscv64;
- various tests with broken patterns;
- tests with read/write fixed/varying stack access that violate nocsr
  stack access contract;
- tests with multiple subprograms;
- tests using nocsr in combination with may_goto/bpf_loop,
  as all of these features affect stack depth;
- tests for nocsr stack spills below max stack depth.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-11-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../selftests/bpf/progs/verifier_nocsr.c      | 796 ++++++++++++++++++
 2 files changed, 798 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_nocsr.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index ff1c7da1d06e..67a49d12472c 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -53,6 +53,7 @@
 #include "verifier_movsx.skel.h"
 #include "verifier_netfilter_ctx.skel.h"
 #include "verifier_netfilter_retcode.skel.h"
+#include "verifier_nocsr.skel.h"
 #include "verifier_or_jmp32_k.skel.h"
 #include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
@@ -173,6 +174,7 @@ void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
 void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
 void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
+void test_verifier_nocsr(void)                { RUN(verifier_nocsr); }
 void test_verifier_or_jmp32_k(void)           { RUN(verifier_or_jmp32_k); }
 void test_verifier_precision(void)            { RUN(verifier_precision); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_nocsr.c b/tools/testing/selftests/bpf/progs/verifier_nocsr.c
new file mode 100644
index 000000000000..a7fe277e5167
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_nocsr.c
@@ -0,0 +1,796 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 8")
+__xlated("4: r5 = 5")
+__xlated("5: w0 = ")
+__xlated("6: r0 = &(void __percpu *)(r0)")
+__xlated("7: r0 = *(u32 *)(r0 +0)")
+__xlated("8: exit")
+__success
+__naked void simple(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	"r3 = 3;"
+	"r4 = 4;"
+	"r5 = 5;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"*(u64 *)(r10 - 24) = r2;"
+	"*(u64 *)(r10 - 32) = r3;"
+	"*(u64 *)(r10 - 40) = r4;"
+	"*(u64 *)(r10 - 48) = r5;"
+	"call %[bpf_get_smp_processor_id];"
+	"r5 = *(u64 *)(r10 - 48);"
+	"r4 = *(u64 *)(r10 - 40);"
+	"r3 = *(u64 *)(r10 - 32);"
+	"r2 = *(u64 *)(r10 - 24);"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+/* The logic for detecting and verifying nocsr pattern is the same for
+ * any arch, however x86 differs from arm64 or riscv64 in a way
+ * bpf_get_smp_processor_id is rewritten:
+ * - on x86 it is done by verifier
+ * - on arm64 and riscv64 it is done by jit
+ *
+ * Which leads to different xlated patterns for different archs:
+ * - on x86 the call is expanded as 3 instructions
+ * - on arm64 and riscv64 the call remains as is
+ *   (but spills/fills are still removed)
+ *
+ * It is really desirable to check instruction indexes in the xlated
+ * patterns, so add this canary test to check that function rewrite by
+ * jit is correctly processed by nocsr logic, keep the rest of the
+ * tests as x86.
+ */
+SEC("raw_tp")
+__arch_arm64
+__arch_riscv64
+__xlated("0: r1 = 1")
+__xlated("1: call bpf_get_smp_processor_id")
+__xlated("2: exit")
+__success
+__naked void canary_arm64_riscv64(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: r0 = &(void __percpu *)(r0)")
+__xlated("3: exit")
+__success
+__naked void canary_zero_spills(void)
+{
+	asm volatile (
+	"call %[bpf_get_smp_processor_id];"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 16")
+__xlated("1: *(u64 *)(r10 -16) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r2 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r6")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r6 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern2(void)
+{
+	asm volatile (
+	"r6 = 1;"
+	"*(u64 *)(r10 - 16) = r6;"
+	"call %[bpf_get_smp_processor_id];"
+	"r6 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r0")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern3(void)
+{
+	asm volatile (
+	"r0 = 1;"
+	"*(u64 *)(r10 - 16) = r0;"
+	"call %[bpf_get_smp_processor_id];"
+	"r0 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u64 *)(r2 -16) = r1")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("6: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_base_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = r10;"
+	"*(u64 *)(r2 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r2 = 1")
+__success
+__naked void wrong_insn_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = 1;"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u64 *)(r10 -16) = r1")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("6: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void wrong_off_in_pattern1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u32 *)(r10 -4) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u32 *)(r10 -4)")
+__success
+__naked void wrong_off_in_pattern2(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u32 *)(r10 - 4) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u32 *)(r10 - 4);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u32 *)(r10 -16) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u32 *)(r10 -16)")
+__success
+__naked void wrong_size_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u32 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u32 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u32 *)(r10 -8) = r1")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("6: r1 = *(u32 *)(r10 -8)")
+__success
+__naked void partial_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	"*(u32 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"r1 = *(u32 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("0: r1 = 1")
+__xlated("1: r2 = 2")
+/* not patched, spills for -8, -16 not removed */
+__xlated("2: *(u64 *)(r10 -8) = r1")
+__xlated("3: *(u64 *)(r10 -16) = r2")
+__xlated("5: r0 = &(void __percpu *)(r0)")
+__xlated("7: r2 = *(u64 *)(r10 -16)")
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+/* patched, spills for -24, -32 removed */
+__xlated("10: r0 = &(void __percpu *)(r0)")
+__xlated("12: exit")
+__success
+__naked void min_stack_offset(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	/* this call won't be patched */
+	"*(u64 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"r1 = *(u64 *)(r10 - 8);"
+	/* this call would be patched */
+	"*(u64 *)(r10 - 24) = r1;"
+	"*(u64 *)(r10 - 32) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 32);"
+	"r1 = *(u64 *)(r10 - 24);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_fixed_read(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r1 = *(u64 *)(r1 - 0);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_fixed_write(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"*(u64 *)(r1 - 0) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("10: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void bad_varying_read(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r1 + 0);" /* random scalar value */
+	"r6 &= 0x7;"		 /* r6 range [0..7] */
+	"r6 += 0x2;"		 /* r6 range [2..9] */
+	"r7 = 0;"
+	"r7 -= r6;"		 /* r7 range [-9..-2] */
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r1 = r10;"
+	"r1 += r7;"
+	"r1 = *(u8 *)(r1 - 0);" /* touches slot [-16..-9] where spills are stored */
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("10: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void bad_varying_write(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r1 + 0);" /* random scalar value */
+	"r6 &= 0x7;"		 /* r6 range [0..7] */
+	"r6 += 0x2;"		 /* r6 range [2..9] */
+	"r7 = 0;"
+	"r7 -= r6;"		 /* r7 range [-9..-2] */
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r1 = r10;"
+	"r1 += r7;"
+	"*(u8 *)(r1 - 0) = r7;" /* touches slot [-16..-9] where spills are stored */
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_write_in_subprog(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"call bad_write_in_subprog_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void bad_write_in_subprog_aux(void)
+{
+	asm volatile (
+	"r0 = 1;"
+	"*(u64 *)(r1 - 0) = r0;"	/* invalidates nocsr contract for caller: */
+	"exit;"				/* caller stack at -8 used outside of the pattern */
+	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_helper_write(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	/* nocsr pattern with stack offset -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r2 = 1;"
+	"r3 = 42;"
+	/* read dst is fp[-8], thus nocsr rewrite not applied */
+	"call %[bpf_probe_read_kernel];"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+/* main, not patched */
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__xlated("9: call pc+1")
+__xlated("10: exit")
+/* subprogram, patched */
+__xlated("11: r1 = 1")
+__xlated("13: r0 = &(void __percpu *)(r0)")
+__xlated("15: exit")
+__success
+__naked void invalidate_one_subprog(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r1 = *(u64 *)(r1 - 0);"
+	"call invalidate_one_subprog_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void invalidate_one_subprog_aux(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+/* main */
+__xlated("0: r1 = 1")
+__xlated("2: r0 = &(void __percpu *)(r0)")
+__xlated("4: call pc+1")
+__xlated("5: exit")
+/* subprogram */
+__xlated("6: r1 = 1")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("10: *(u64 *)(r10 -16) = r1")
+__xlated("11: exit")
+__success
+__naked void subprogs_use_independent_offsets(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"call subprogs_use_independent_offsets_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void subprogs_use_independent_offsets_aux(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 24) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 24);"
+	"*(u64 *)(r10 - 16) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 8")
+__xlated("2: r0 = &(void __percpu *)(r0)")
+__success
+__naked void helper_call_does_not_prevent_nocsr(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 16")
+/* may_goto counter at -16 */
+__xlated("0: *(u64 *)(r10 -16) =")
+__xlated("1: r1 = 1")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+/* may_goto expansion starts */
+__xlated("5: r11 = *(u64 *)(r10 -16)")
+__xlated("6: if r11 == 0x0 goto pc+3")
+__xlated("7: r11 -= 1")
+__xlated("8: *(u64 *)(r10 -16) = r11")
+/* may_goto expansion ends */
+__xlated("9: *(u64 *)(r10 -8) = r1")
+__xlated("10: exit")
+__success
+__naked void may_goto_interaction(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	".8byte %[may_goto];"
+	/* just touch some stack at -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+	: __clobber_all);
+}
+
+__used
+__naked static void dummy_loop_callback(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 32+0")
+__xlated("2: r1 = 1")
+__xlated("3: w0 =")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u32 *)(r0 +0)")
+/* bpf_loop params setup */
+__xlated("6: r2 =")
+__xlated("7: r3 = 0")
+__xlated("8: r4 = 0")
+/* ... part of the inlined bpf_loop */
+__xlated("12: *(u64 *)(r10 -32) = r6")
+__xlated("13: *(u64 *)(r10 -24) = r7")
+__xlated("14: *(u64 *)(r10 -16) = r8")
+/* ... */
+__xlated("21: call pc+8") /* dummy_loop_callback */
+/* ... last insns of the bpf_loop_interaction1 */
+__xlated("28: r0 = 0")
+__xlated("29: exit")
+/* dummy_loop_callback */
+__xlated("30: r0 = 0")
+__xlated("31: exit")
+__success
+__naked int bpf_loop_interaction1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	/* nocsr stack region at -16, but could be removed */
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r2 = %[dummy_loop_callback];"
+	"r3 = 0;"
+	"r4 = 0;"
+	"call %[bpf_loop];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_ptr(dummy_loop_callback),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_loop)
+	: __clobber_common
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 40+0")
+/* call bpf_get_smp_processor_id */
+__xlated("2: r1 = 42")
+__xlated("3: w0 =")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u32 *)(r0 +0)")
+/* call bpf_get_prandom_u32 */
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("7: call")
+__xlated("8: r1 = *(u64 *)(r10 -16)")
+/* ... */
+/* ... part of the inlined bpf_loop */
+__xlated("15: *(u64 *)(r10 -40) = r6")
+__xlated("16: *(u64 *)(r10 -32) = r7")
+__xlated("17: *(u64 *)(r10 -24) = r8")
+__success
+__naked int bpf_loop_interaction2(void)
+{
+	asm volatile (
+	"r1 = 42;"
+	/* nocsr stack region at -16, cannot be removed */
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r2 = %[dummy_loop_callback];"
+	"r3 = 0;"
+	"r4 = 0;"
+	"call %[bpf_loop];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_ptr(dummy_loop_callback),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32),
+	  __imm(bpf_loop)
+	: __clobber_common
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 512+0")
+/* just to print xlated version when debugging */
+__xlated("r0 = &(void __percpu *)(r0)")
+__success
+/* cumulative_stack_depth() stack usage is MAX_BPF_STACK,
+ * called subprogram uses an additional slot for nocsr spill/fill,
+ * since nocsr spill/fill could be removed the program still fits
+ * in MAX_BPF_STACK and should be accepted.
+ */
+__naked int cumulative_stack_depth(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"call cumulative_stack_depth_subprog;"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK)
+	: __clobber_all
+	);
+}
+
+__used
+__naked static void cumulative_stack_depth_subprog(void)
+{
+	asm volatile (
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:: __imm(bpf_get_smp_processor_id) : __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 512")
+__xlated("0: r1 = 42")
+__xlated("1: *(u64 *)(r10 -512) = r1")
+__xlated("2: w0 = ")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("4: r0 = *(u32 *)(r0 +0)")
+__xlated("5: exit")
+__success
+__naked int nocsr_max_stack_ok(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK),
+	  __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8),
+	  __imm(bpf_get_smp_processor_id)
+	: __clobber_all
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 520")
+__failure
+__naked int nocsr_max_stack_fail(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
+	/* call to prandom blocks nocsr rewrite */
+	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK),
+	  __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all
+	);
+}
+
+char _license[] SEC("license") = "GPL";