Merge branch 'bpf-riscv-add-timed-may_goto-support'

Feng Jiang says:

====================
bpf, riscv: add timed may_goto support

This series adds RISC-V JIT support for the timed may_goto loop bound.

Patch 1 implements arch_bpf_timed_may_goto() and enables
bpf_jit_supports_timed_may_goto() so the verifier uses the timed
expansion path.

Patch 2 adds a test that checks R0-R5 are preserved across
arch_bpf_timed_may_goto() calls.

Patch 3 enables the verifier_may_goto_1, stream_cond_break, and
may_goto_interaction fastcall tests on riscv64.

Tested on riscv64 QEMU (rva23s64): may_goto programs load and JIT
correctly, and the 250ms timeout path works as expected.

Signed-off-by: Feng Jiang <jiangfeng@kylinos.cn>
Tested-by: Pu Lehui <pulehui@huawei.com>
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Björn Töpel <bjorn@kernel.org>
---
Changes in v5:
- Use REG_S/REG_L/SZREG in arch_bpf_timed_may_goto assembly. (Pu Lehui)
- Add __arch_s390x to the timed_may_goto_preserves_regs test. (Pu Lehui)
- Switch the preserves-regs test to SEC("syscall") to fix
  bpf_prog_test_run() EINVAL.
- Link to v4: https://lore.kernel.org/r/20260722-riscv-bpf-timed-may-goto-v4-0-e117e6337bc7@kylinos.cn

Changes in v4:
- Add 'bpf-next' prefix to match the BPF kernel tree workflow.
- Add a test checking that R0-R5 are preserved across
  arch_bpf_timed_may_goto() calls. Use bpf_get_prandom_u32() to
  prevent the verifier from removing the checks via DCE.
- Rename may_goto_interaction_arm64() to may_goto_interaction().
- Wrap the arch_bpf_timed_may_goto address check to a single line.
- Link to v3: https://lore.kernel.org/r/20260715-riscv-bpf-timed-may-goto-v3-0-cf2a9c3d843f@kylinos.cn

Changes in v3:
- Set up the frame pointer in arch_bpf_timed_may_goto() so the function
  does not break stack unwinding under CONFIG_FRAME_POINTER.

Changes in v2:
- Fix BPF_REG_0 being clobbered after arch_bpf_timed_may_goto() calls.
- Enable the may_goto_interaction fastcall test on riscv64.

---
====================

Link: https://patch.msgid.link/20260723-riscv-bpf-timed-may-goto-v5-0-86acb54e5642@kylinos.cn
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>

arch/riscv/net/Makefile

@@ -3,7 +3,7 @@
 obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o
 
 ifeq ($(CONFIG_ARCH_RV64I),y)
-	obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o
+	obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o bpf_timed_may_goto.o
 else
 	obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
 endif

arch/riscv/net/bpf_jit_comp64.c

@@ -1841,7 +1841,12 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		if (aux->tail_call_reachable && insn->src_reg == BPF_PSEUDO_CALL)
 			emit_sd(RV_REG_SP, ctx->tcc_offset, RV_REG_TCC, ctx);
 
-		if (insn->src_reg != BPF_PSEUDO_CALL)
+		/*
+		 * arch_bpf_timed_may_goto() is emitted by the verifier and
+		 * returns its result in BPF_REG_AX instead of BPF_REG_0, so
+		 * skip the normal "move return register into R0".
+		 */
+		if (insn->src_reg != BPF_PSEUDO_CALL && addr != (u64)arch_bpf_timed_may_goto)
 			emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_A0, ctx);
 		break;
 	}
@@ -2161,3 +2166,8 @@ bool bpf_jit_supports_subprog_tailcalls(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_timed_may_goto(void)
+{
+	return true;
+}

arch/riscv/net/bpf_timed_may_goto.S

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Feng Jiang <jiangfeng@kylinos.cn> */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+/*
+ * Trampoline for the BPF timed may_goto loop bound. Custom calling convention:
+ *	- input:  stack offset in BPF_REG_AX (t0)
+ *	- output: updated count in BPF_REG_AX (t0)
+ *
+ * Calls bpf_check_timed_may_goto(ptr) with the standard RISC-V ABI, where
+ * ptr = BPF_REG_FP (s5) + BPF_REG_AX (t0). BPF R0-R5 (a5, a0-a4) are saved
+ * across the call; BPF_REG_FP (s5) is callee-saved and needs no saving.
+ */
+
+SYM_FUNC_START(arch_bpf_timed_may_goto)
+	addi	sp, sp, -(8*SZREG)
+	REG_S	ra, 7*SZREG(sp)
+	REG_S	s0, 6*SZREG(sp)
+	addi	s0, sp, 8*SZREG
+
+	/* Save BPF registers R0-R5 (a5, a0-a4) */
+	REG_S	a5, 5*SZREG(sp)
+	REG_S	a0, 4*SZREG(sp)
+	REG_S	a1, 3*SZREG(sp)
+	REG_S	a2, 2*SZREG(sp)
+	REG_S	a3, 1*SZREG(sp)
+	REG_S	a4, 0*SZREG(sp)
+
+	add	a0, t0, s5
+	call	bpf_check_timed_may_goto
+	mv	t0, a0
+
+	/* Restore BPF registers R0-R5 */
+	REG_L	a4, 0*SZREG(sp)
+	REG_L	a3, 1*SZREG(sp)
+	REG_L	a2, 2*SZREG(sp)
+	REG_L	a1, 3*SZREG(sp)
+	REG_L	a0, 4*SZREG(sp)
+	REG_L	a5, 5*SZREG(sp)
+
+	REG_L	s0, 6*SZREG(sp)
+	REG_L	ra, 7*SZREG(sp)
+	addi	sp, sp, 8*SZREG
+	ret
+SYM_FUNC_END(arch_bpf_timed_may_goto)

tools/testing/selftests/bpf/progs/stream.c

@@ -64,6 +64,7 @@ SEC("syscall")
 __arch_x86_64
 __arch_arm64
 __arch_s390x
+__arch_riscv64
 __success __retval(0)
 __stderr("ERROR: Timeout detected for may_goto instruction")
 __stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")

tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c

@@ -660,6 +660,7 @@ __naked void may_goto_interaction_x86_64(void)
 
 SEC("raw_tp")
 __arch_arm64
+__arch_riscv64
 __log_level(4) __msg("stack depth 24")
 /* may_goto counter at -24 */
 __xlated("0: *(u64 *)(r10 -24) =")
@@ -679,7 +680,7 @@ __xlated("10: *(u64 *)(r10 -24) = r12")
 __xlated("11: *(u64 *)(r10 -8) = r1")
 __xlated("12: exit")
 __success
-__naked void may_goto_interaction_arm64(void)
+__naked void may_goto_interaction(void)
 {
 	asm volatile (
 	"r1 = 1;"

tools/testing/selftests/bpf/progs/verifier_may_goto_1.c

@@ -11,6 +11,7 @@ __description("may_goto 0")
 __arch_x86_64
 __arch_s390x
 __arch_arm64
+__arch_riscv64
 __xlated("0: r0 = 1")
 __xlated("1: exit")
 __success
@@ -31,6 +32,7 @@ __description("batch 2 of may_goto 0")
 __arch_x86_64
 __arch_s390x
 __arch_arm64
+__arch_riscv64
 __xlated("0: r0 = 1")
 __xlated("1: exit")
 __success
@@ -53,6 +55,7 @@ __description("may_goto batch with offsets 2/1/0")
 __arch_x86_64
 __arch_s390x
 __arch_arm64
+__arch_riscv64
 __xlated("0: r0 = 1")
 __xlated("1: exit")
 __success
@@ -79,6 +82,7 @@ __description("may_goto batch with offsets 2/0")
 __arch_x86_64
 __arch_s390x
 __arch_arm64
+__arch_riscv64
 __xlated("0: *(u64 *)(r10 -16) = 65535")
 __xlated("1: *(u64 *)(r10 -8) = 0")
 __xlated("2: r12 = *(u64 *)(r10 -16)")
@@ -106,4 +110,62 @@ __naked void may_goto_batch_2(void)
 	: __clobber_all);
 }
 
+/*
+ * Use bpf_get_prandom_u32() to prevent DCE from removing the checks.
+ * retval: 0=all ok, 1-6=R0-R5 clobbered.
+ */
+SEC("syscall")
+__description("timed may_goto preserves R0-R5")
+__arch_x86_64
+__arch_s390x
+__arch_arm64
+__arch_riscv64
+__success
+__retval(0)
+__naked void timed_may_goto_preserves_regs(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r6 = r0;"
+	"r0 = 0x1111;"
+	"r0 += r6;"
+	"r1 = 0x2222;"
+	"r1 += r6;"
+	"r2 = 0x3333;"
+	"r2 += r6;"
+	"r3 = 0x4444;"
+	"r3 += r6;"
+	"r4 = 0x5555;"
+	"r4 += r6;"
+	"r5 = 0x6666;"
+	"r5 += r6;"
+	".8byte %[may_goto];"
+	".8byte %[loop];"
+	"r0 -= r6;"
+	"r1 -= r6;"
+	"r2 -= r6;"
+	"r3 -= r6;"
+	"r4 -= r6;"
+	"r5 -= r6;"
+	"if r0 != 0x1111 goto 1f;"
+	"if r1 != 0x2222 goto 2f;"
+	"if r2 != 0x3333 goto 3f;"
+	"if r3 != 0x4444 goto 4f;"
+	"if r4 != 0x5555 goto 5f;"
+	"if r5 != 0x6666 goto 6f;"
+	"r0 = 0;"
+	"exit;"
+	"1: r0 = 1; exit;"
+	"2: r0 = 2; exit;"
+	"3: r0 = 3; exit;"
+	"4: r0 = 4; exit;"
+	"5: r0 = 5; exit;"
+	"6: r0 = 6; exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 1, 0)),
+	  __imm_insn(loop, BPF_RAW_INSN(BPF_JMP | BPF_JA, 0, 0, -2, 0))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";