Merge branch 'support-bpf_fastcall-patterns-for-calls-to-kfuncs'

Eduard Zingerman says:

====================
support bpf_fastcall patterns for calls to kfuncs

As an extension of [1], allow bpf_fastcall patterns for kfuncs:
- pattern rules are the same as for helpers;
- spill/fill removal is allowed only for kfuncs listed in the
  is_fastcall_kfunc_call (under assumption that such kfuncs would
  always be members of special_kfunc_list).

Allow bpf_fastcall rewrite for bpf_cast_to_kern_ctx() and
bpf_rdonly_cast() in order to conjure selftests for this feature.

After this patch-set verifier would rewrite the program below:

  r2 = 1
  *(u64 *)(r10 - 32) = r2
  call %[bpf_cast_to_kern_ctx]
  r2 = *(u64 *)(r10 - 32)
  r0 = r2;"

As follows:

  r2 = 1   /* spill/fill at r10[-32] is removed */
  r0 = r1  /* replacement for bpf_cast_to_kern_ctx() */
  r0 = r2
  exit

Also, attribute used by LLVM implementation of the feature had been
changed from no_caller_saved_registers to bpf_fastcall (see [2]).
This patch-set replaces references to nocsr by references to
bpf_fastcall to keep LLVM and Kernel parts in sync.

[1] no_caller_saved_registers attribute for helper calls
    https://lore.kernel.org/bpf/20240722233844.1406874-1-eddyz87@gmail.com/
[2] [BPF] introduce __attribute__((bpf_fastcall))
    https://github.com/llvm/llvm-project/pull/105417

Changes v2->v3:
- added a patch fixing arch_mask handling in test_loader,
  otherwise newly added tests for the feature were skipped
  (a fix for regression introduced by a recent commit);
- fixed warning regarding unused 'params' variable;
- applied stylistical fixes suggested by Yonghong;
- added acks from Yonghong;

Changes v1->v2:
- added two patches replacing all mentions of nocsr by bpf_fastcall
  (suggested by Andrii);
- removed KF_NOCSR flag (suggested by Yonghong).

v1: https://lore.kernel.org/bpf/20240812234356.2089263-1-eddyz87@gmail.com/
v2: https://lore.kernel.org/bpf/20240817015140.1039351-1-eddyz87@gmail.com/
====================

Link: https://lore.kernel.org/r/20240822084112.3257995-1-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

7 files changed, 192 insertions, 102 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f0192c173ed8..00dc4dd28cbd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -808,12 +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:
+	/* set to true if helper follows contract for llvm
+	 * attribute bpf_fastcall:
 	 * - void functions do not scratch r0
 	 * - functions taking N arguments scratch only registers r1-rN
 	 */
-	bool allow_nocsr;
+	bool allow_fastcall;
 	enum bpf_return_type ret_type;
 	union {
 		struct {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 5cea15c81b8a..634a302a39e3 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -577,13 +577,13 @@ struct bpf_insn_aux_data {
 	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.
+	 * pattern for a bpf_fastcall call.
 	 */
-	u8 nocsr_pattern:1;
+	u8 fastcall_pattern:1;
 	/* for CALL instructions, a number of spill/fill pairs in the
-	 * no_caller_saved_registers pattern.
+	 * bpf_fastcall pattern.
 	 */
-	u8 nocsr_spills_num:3;
+	u8 fastcall_spills_num:3;
 
 	/* below fields are initialized once */
 	unsigned int orig_idx; /* original instruction index */
@@ -653,10 +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.
+	/* offsets in range [stack_depth .. fastcall_stack_off)
+	 * are used for bpf_fastcall spills and fills.
 	 */
-	s16 nocsr_stack_off;
+	s16 fastcall_stack_off;
 	bool has_tail_call: 1;
 	bool tail_call_reachable: 1;
 	bool has_ld_abs: 1;
@@ -664,8 +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;
+	/* true if bpf_fastcall stack region is used by functions that can't be inlined */
+	bool keep_fastcall_stack: 1;
 
 	u8 arg_cnt;
 	struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS];
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index ccca6fe0367c..4105b4af6e03 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -158,7 +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,
+	.allow_fastcall	= true,
 };
 
 BPF_CALL_0(bpf_get_numa_node_id)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 920d7c5fe944..543b8c9edac7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4579,28 +4579,28 @@ 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)
+/* See comment for mark_fastcall_pattern_for_call() */
+static void check_fastcall_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)
+	if (subprog->fastcall_stack_off <= off || aux[insn_idx].fastcall_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.
+	/* access to the region [max_stack_depth .. fastcall_stack_off)
+	 * from something that is not a part of the fastcall pattern,
+	 * disable fastcall rewrites for current subprogram by setting
+	 * fastcall_stack_off to a value smaller than any possible offset.
 	 */
-	subprog->nocsr_stack_off = S16_MIN;
-	/* reset nocsr aux flags within subprogram,
+	subprog->fastcall_stack_off = S16_MIN;
+	/* reset fastcall 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;
+		aux[i].fastcall_spills_num = 0;
+		aux[i].fastcall_pattern = 0;
 	}
 }
 
@@ -4652,7 +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);
+	check_fastcall_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;
@@ -4787,7 +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);
+	check_fastcall_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;
@@ -4926,7 +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);
+	check_fastcall_stack_contract(env, state, env->insn_idx, off);
 
 	if (is_spilled_reg(&reg_state->stack[spi])) {
 		u8 spill_size = 1;
@@ -5087,7 +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);
+	check_fastcall_stack_contract(env, ptr_state, env->insn_idx, min_off);
 	return 0;
 }
 
@@ -6804,13 +6804,13 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
 	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,
+	/* If accessing instruction is a spill/fill from bpf_fastcall pattern,
 	 * add room for all caller saved registers below MAX_BPF_STACK.
-	 * In case if nocsr rewrite won't happen maximal stack depth
+	 * In case if bpf_fastcall 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)
+	if (aux->fastcall_pattern)
 		max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE;
 
 	if (t == BPF_WRITE || env->allow_uninit_stack)
@@ -16118,14 +16118,14 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 
 /* 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:
+ * bpf_fastcall 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)
+static u32 helper_fastcall_clobber_mask(const struct bpf_func_proto *fn)
 {
-	u8 mask;
+	u32 mask;
 	int i;
 
 	mask = 0;
@@ -16138,8 +16138,8 @@ static u32 helper_nocsr_clobber_mask(const struct bpf_func_proto *fn)
 }
 
 /* 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).
+ * replacement patch is presumed to follow bpf_fastcall contract
+ * (see mark_fastcall_pattern_for_call() below).
  */
 static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
 {
@@ -16153,7 +16153,30 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
 	}
 }
 
-/* GCC and LLVM define a no_caller_saved_registers function attribute.
+/* Same as helper_fastcall_clobber_mask() but for kfuncs, see comment above */
+static u32 kfunc_fastcall_clobber_mask(struct bpf_kfunc_call_arg_meta *meta)
+{
+	u32 vlen, i, mask;
+
+	vlen = btf_type_vlen(meta->func_proto);
+	mask = 0;
+	if (!btf_type_is_void(btf_type_by_id(meta->btf, meta->func_proto->type)))
+		mask |= BIT(BPF_REG_0);
+	for (i = 0; i < vlen; ++i)
+		mask |= BIT(BPF_REG_1 + i);
+	return mask;
+}
+
+/* Same as verifier_inlines_helper_call() but for kfuncs, see comment above */
+static bool is_fastcall_kfunc_call(struct bpf_kfunc_call_arg_meta *meta)
+{
+	if (meta->btf == btf_vmlinux)
+		return meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
+		       meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast];
+	return false;
+}
+
+/* LLVM define a bpf_fastcall 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:
@@ -16163,13 +16186,12 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
  *
  * 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):
+ * kernels that don't understand bpf_fastcall calls:
  *
- * - for nocsr calls clang allocates registers as-if relevant r0-r5
+ * - for bpf_fastcall 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
+ * - as a post-processing step, clang visits each bpf_fastcall call and adds
  *   spill/fill for every live r0-r5;
  *
  * - stack offsets used for the spill/fill are allocated as lowest
@@ -16177,11 +16199,11 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
  *   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;
+ *   (bpf_fastcall function surrounded by spills/fills) and checks if
+ *   spill/fill stack offsets are used exclusively in fastcall patterns;
  *
  * - if so, and if verifier or current JIT inlines the call to the
- *   nocsr function (e.g. a helper call), kernel removes unnecessary
+ *   bpf_fastcall function (e.g. a helper call), kernel removes unnecessary
  *   spill/fill pairs;
  *
  * - when old kernel loads a program, presence of spill/fill pairs
@@ -16200,22 +16222,22 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
  *   r0 += r2;
  *   exit;
  *
- * The purpose of mark_nocsr_pattern_for_call is to:
+ * The purpose of mark_fastcall_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.
+ * - mark spill and fill instructions in env->insn_aux_data[*].fastcall_pattern;
+ * - mark set env->insn_aux_data[*].fastcall_spills_num for call instruction;
+ * - update env->subprog_info[*]->fastcall_stack_off to find an offset
+ *   at which bpf_fastcall spill/fill stack slots start;
+ * - update env->subprog_info[*]->keep_fastcall_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.
+ * The .fastcall_pattern and .fastcall_stack_off are used by
+ * check_fastcall_stack_contract() to check if every stack access to
+ * fastcall spill/fill stack slot originates from spill/fill
+ * instructions, members of fastcall 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
+ * If such condition holds true for a subprogram, fastcall patterns could
+ * be rewritten by remove_fastcall_spills_fills().
+ * Otherwise bpf_fastcall 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:
@@ -16228,9 +16250,9 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
  *   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)
+static void mark_fastcall_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];
@@ -16245,12 +16267,25 @@ static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env,
 		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 &&
+		clobbered_regs_mask = helper_fastcall_clobber_mask(fn);
+		can_be_inlined = fn->allow_fastcall &&
 				 (verifier_inlines_helper_call(env, call->imm) ||
 				  bpf_jit_inlines_helper_call(call->imm));
 	}
 
+	if (bpf_pseudo_kfunc_call(call)) {
+		struct bpf_kfunc_call_arg_meta meta;
+		int err;
+
+		err = fetch_kfunc_meta(env, call, &meta, NULL);
+		if (err < 0)
+			/* error would be reported later */
+			return;
+
+		clobbered_regs_mask = kfunc_fastcall_clobber_mask(&meta);
+		can_be_inlined = is_fastcall_kfunc_call(&meta);
+	}
+
 	if (clobbered_regs_mask == ALL_CALLER_SAVED_REGS)
 		return;
 
@@ -16289,36 +16324,36 @@ static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env,
 		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;
+		env->insn_aux_data[insn_idx - i].fastcall_pattern = 1;
+		env->insn_aux_data[insn_idx + i].fastcall_pattern = 1;
 	}
 	if (i == 1)
 		return;
 
-	/* Conditionally set 'nocsr_spills_num' to allow forward
+	/* Conditionally set 'fastcall_spills_num' to allow forward
 	 * compatibility when more helper functions are marked as
-	 * nocsr at compile time than current kernel supports, e.g:
+	 * bpf_fastcall at compile time than current kernel supports, e.g:
 	 *
 	 *   1: *(u64 *)(r10 - 8) = r1
-	 *   2: call A                  ;; assume A is nocsr for current kernel
+	 *   2: call A                  ;; assume A is bpf_fastcall for current kernel
 	 *   3: r1 = *(u64 *)(r10 - 8)
 	 *   4: *(u64 *)(r10 - 8) = r1
-	 *   5: call B                  ;; assume B is not nocsr for current kernel
+	 *   5: call B                  ;; assume B is not bpf_fastcall 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()
+	 * There is no need to block bpf_fastcall rewrite for such program.
+	 * Set 'fastcall_pattern' for both calls to keep check_fastcall_stack_contract() happy,
+	 * don't set 'fastcall_spills_num' for call B so that remove_fastcall_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;
+		env->insn_aux_data[insn_idx].fastcall_spills_num = i - 1;
 	else
-		subprog->keep_nocsr_stack = 1;
-	subprog->nocsr_stack_off = min(subprog->nocsr_stack_off, off);
+		subprog->keep_fastcall_stack = 1;
+	subprog->fastcall_stack_off = min(subprog->fastcall_stack_off, off);
 }
 
-static int mark_nocsr_patterns(struct bpf_verifier_env *env)
+static int mark_fastcall_patterns(struct bpf_verifier_env *env)
 {
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn;
@@ -16335,12 +16370,12 @@ static int mark_nocsr_patterns(struct bpf_verifier_env *env)
 				continue;
 			lowest_off = min(lowest_off, insn->off);
 		}
-		/* use this offset to find nocsr patterns */
+		/* use this offset to find fastcall 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);
+			mark_fastcall_pattern_for_call(env, subprog, i, lowest_off);
 		}
 	}
 	return 0;
@@ -21244,10 +21279,10 @@ static int optimize_bpf_loop(struct bpf_verifier_env *env)
 	return 0;
 }
 
-/* Remove unnecessary spill/fill pairs, members of nocsr pattern,
+/* Remove unnecessary spill/fill pairs, members of fastcall pattern,
  * adjust subprograms stack depth when possible.
  */
-static int remove_nocsr_spills_fills(struct bpf_verifier_env *env)
+static int remove_fastcall_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;
@@ -21258,8 +21293,8 @@ static int remove_nocsr_spills_fills(struct bpf_verifier_env *env)
 	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;
+		if (aux[i].fastcall_spills_num > 0) {
+			spills_num = aux[i].fastcall_spills_num;
 			/* NOPs would be removed by opt_remove_nops() */
 			for (j = 1; j <= spills_num; ++j) {
 				*(insn - j) = NOP;
@@ -21268,8 +21303,8 @@ static int remove_nocsr_spills_fills(struct bpf_verifier_env *env)
 			modified = true;
 		}
 		if ((subprog + 1)->start == i + 1) {
-			if (modified && !subprog->keep_nocsr_stack)
-				subprog->stack_depth = -subprog->nocsr_stack_off;
+			if (modified && !subprog->keep_fastcall_stack)
+				subprog->stack_depth = -subprog->fastcall_stack_off;
 			subprog++;
 			modified = false;
 		}
@@ -22192,7 +22227,7 @@ 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);
+	ret = mark_fastcall_patterns(env);
 	if (ret < 0)
 		goto skip_full_check;
 
@@ -22209,7 +22244,7 @@ skip_full_check:
 	 * allocate additional slots.
 	 */
 	if (ret == 0)
-		ret = remove_nocsr_spills_fills(env);
+		ret = remove_fastcall_spills_fills(env);
 
 	if (ret == 0)
 		ret = check_max_stack_depth(env);
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index cf3662dbd24f..80a90c627182 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -53,7 +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_bpf_fastcall.skel.h"
 #include "verifier_or_jmp32_k.skel.h"
 #include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
@@ -177,7 +177,7 @@ 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_bpf_fastcall(void)         { RUN(verifier_bpf_fastcall); }
 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_bpf_fastcall.c
index 666c736d196f..9da97d2efcd9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_nocsr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -2,8 +2,11 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 #include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
 
 SEC("raw_tp")
 __arch_x86_64
@@ -39,7 +42,7 @@ __naked void simple(void)
 	: __clobber_all);
 }
 
-/* The logic for detecting and verifying nocsr pattern is the same for
+/* The logic for detecting and verifying bpf_fastcall 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
@@ -52,7 +55,7 @@ __naked void simple(void)
  *
  * 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
+ * jit is correctly processed by bpf_fastcall logic, keep the rest of the
  * tests as x86.
  */
 SEC("raw_tp")
@@ -463,7 +466,7 @@ __naked static void bad_write_in_subprog_aux(void)
 {
 	asm volatile (
 	"r0 = 1;"
-	"*(u64 *)(r1 - 0) = r0;"	/* invalidates nocsr contract for caller: */
+	"*(u64 *)(r1 - 0) = r0;"	/* invalidates bpf_fastcall contract for caller: */
 	"exit;"				/* caller stack at -8 used outside of the pattern */
 	::: __clobber_all);
 }
@@ -480,7 +483,7 @@ __naked void bad_helper_write(void)
 {
 	asm volatile (
 	"r1 = 1;"
-	/* nocsr pattern with stack offset -8 */
+	/* bpf_fastcall pattern with stack offset -8 */
 	"*(u64 *)(r10 - 8) = r1;"
 	"call %[bpf_get_smp_processor_id];"
 	"r1 = *(u64 *)(r10 - 8);"
@@ -488,7 +491,7 @@ __naked void bad_helper_write(void)
 	"r1 += -8;"
 	"r2 = 1;"
 	"r3 = 42;"
-	/* read dst is fp[-8], thus nocsr rewrite not applied */
+	/* read dst is fp[-8], thus bpf_fastcall rewrite not applied */
 	"call %[bpf_probe_read_kernel];"
 	"exit;"
 	:
@@ -598,7 +601,7 @@ __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)
+__naked void helper_call_does_not_prevent_bpf_fastcall(void)
 {
 	asm volatile (
 	"r1 = 1;"
@@ -689,7 +692,7 @@ __naked int bpf_loop_interaction1(void)
 {
 	asm volatile (
 	"r1 = 1;"
-	/* nocsr stack region at -16, but could be removed */
+	/* bpf_fastcall stack region at -16, but could be removed */
 	"*(u64 *)(r10 - 16) = r1;"
 	"call %[bpf_get_smp_processor_id];"
 	"r1 = *(u64 *)(r10 - 16);"
@@ -729,7 +732,7 @@ __naked int bpf_loop_interaction2(void)
 {
 	asm volatile (
 	"r1 = 42;"
-	/* nocsr stack region at -16, cannot be removed */
+	/* bpf_fastcall stack region at -16, cannot be removed */
 	"*(u64 *)(r10 - 16) = r1;"
 	"call %[bpf_get_smp_processor_id];"
 	"r1 = *(u64 *)(r10 - 16);"
@@ -759,8 +762,8 @@ __msg("stack depth 512+0")
 __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
+ * called subprogram uses an additional slot for bpf_fastcall spill/fill,
+ * since bpf_fastcall spill/fill could be removed the program still fits
  * in MAX_BPF_STACK and should be accepted.
  */
 __naked int cumulative_stack_depth(void)
@@ -798,7 +801,7 @@ __xlated("3: r0 = &(void __percpu *)(r0)")
 __xlated("4: r0 = *(u32 *)(r0 +0)")
 __xlated("5: exit")
 __success
-__naked int nocsr_max_stack_ok(void)
+__naked int bpf_fastcall_max_stack_ok(void)
 {
 	asm volatile(
 	"r1 = 42;"
@@ -820,7 +823,7 @@ __arch_x86_64
 __log_level(4)
 __msg("stack depth 520")
 __failure
-__naked int nocsr_max_stack_fail(void)
+__naked int bpf_fastcall_max_stack_fail(void)
 {
 	asm volatile(
 	"r1 = 42;"
@@ -828,7 +831,7 @@ __naked int nocsr_max_stack_fail(void)
 	"*(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 */
+	/* call to prandom blocks bpf_fastcall rewrite */
 	"*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
 	"call %[bpf_get_prandom_u32];"
 	"r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
@@ -842,4 +845,56 @@ __naked int nocsr_max_stack_fail(void)
 	);
 }
 
+SEC("cgroup/getsockname_unix")
+__xlated("0: r2 = 1")
+/* bpf_cast_to_kern_ctx is replaced by a single assignment */
+__xlated("1: r0 = r1")
+__xlated("2: r0 = r2")
+__xlated("3: exit")
+__success
+__naked void kfunc_bpf_cast_to_kern_ctx(void)
+{
+	asm volatile (
+	"r2 = 1;"
+	"*(u64 *)(r10 - 32) = r2;"
+	"call %[bpf_cast_to_kern_ctx];"
+	"r2 = *(u64 *)(r10 - 32);"
+	"r0 = r2;"
+	"exit;"
+	:
+	: __imm(bpf_cast_to_kern_ctx)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__xlated("3: r3 = 1")
+/* bpf_rdonly_cast is replaced by a single assignment */
+__xlated("4: r0 = r1")
+__xlated("5: r0 = r3")
+void kfunc_bpf_rdonly_cast(void)
+{
+	asm volatile (
+	"r2 = %[btf_id];"
+	"r3 = 1;"
+	"*(u64 *)(r10 - 32) = r3;"
+	"call %[bpf_rdonly_cast];"
+	"r3 = *(u64 *)(r10 - 32);"
+	"r0 = r3;"
+	:
+	: __imm(bpf_rdonly_cast),
+	 [btf_id]"r"(bpf_core_type_id_kernel(union bpf_attr))
+	: __clobber_common);
+}
+
+/* BTF FUNC records are not generated for kfuncs referenced
+ * from inline assembly. These records are necessary for
+ * libbpf to link the program. The function below is a hack
+ * to ensure that BTF FUNC records are generated.
+ */
+void kfunc_root(void)
+{
+	bpf_cast_to_kern_ctx(0);
+	bpf_rdonly_cast(0, 0);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index b229dd013355..2ca9b73e5a6b 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -543,7 +543,7 @@ static int parse_test_spec(struct test_loader *tester,
 		}
 	}
 
-	spec->arch_mask = arch_mask;
+	spec->arch_mask = arch_mask ?: -1;
 
 	if (spec->mode_mask == 0)
 		spec->mode_mask = PRIV;