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.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

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 {

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];

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)

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); }

tools/testing/selftests/bpf/progs/verifier_nocsr.c → 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";

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;