s390/bpf: Add s390 JIT support for timed may_goto

The verifier provides an architecture-independent implementation of the
may_goto instruction, which is currently used on s390x, but it has a
downside: there is no way to prevent progs using it from running for a
very long time.

The solution to this problem is an alternative timed implementation,
which requires architecture-specific bits. Its availability is signaled
to the verifier by bpf_jit_supports_timed_may_goto() returning true.

The verifier then emits a call to arch_bpf_timed_may_goto() using a
non-standard calling convention. This function must act as a trampoline
for bpf_check_timed_may_goto().

Implement bpf_jit_supports_timed_may_goto(), account for the special
calling convention in the BPF_CALL implementation, and implement
arch_bpf_timed_may_goto().

Signed-off-by: Ilya Leoshkevich <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

arch/s390/net/Makefile

···
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
 obj-$(CONFIG_HAVE_PNETID) += pnet.o

arch/s390/net/bpf_jit_comp.c

···
 			}
 		}
 
-		/* brasl %r14,func */
-		EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, (void *)func);
-		/* lgr %b0,%r2: load return value into %b0 */
-		EMIT4(0xb9040000, BPF_REG_0, REG_2);
+		if ((void *)func == arch_bpf_timed_may_goto) {
+			/*
+			 * arch_bpf_timed_may_goto() has a special ABI: the
+			 * parameters are in BPF_REG_AX and BPF_REG_10; the
+			 * return value is in BPF_REG_AX; and all GPRs except
+			 * REG_W0, REG_W1, and BPF_REG_AX are callee-saved.
+			 */
+
+			/* brasl %r0,func */
+			EMIT6_PCREL_RILB_PTR(0xc0050000, REG_0, (void *)func);
+		} else {
+			/* brasl %r14,func */
+			EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, (void *)func);
+			/* lgr %b0,%r2: load return value into %b0 */
+			EMIT4(0xb9040000, BPF_REG_0, REG_2);
+		}
 
 		/*
 		 * Copy the potentially updated tail call counter back.
···
 			break;
 		prev_addr = addr;
 	}
+}
+
+bool bpf_jit_supports_timed_may_goto(void)
+{
+	return true;
 }

arch/s390/net/bpf_timed_may_goto.S

···
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
+
+#define R2_OFF 0
+#define R5_OFF (R2_OFF + (5 - 2 + 1) * 8)
+#define R14_OFF (R5_OFF + 8)
+#define RETADDR_OFF (R14_OFF + 8)
+#define R15_OFF (RETADDR_OFF + 8)
+#define BACKCHAIN_OFF (R15_OFF + 8)
+#define FRAME_SIZE (BACKCHAIN_OFF + 8)
+#define FRAME_OFF (STACK_FRAME_OVERHEAD - FRAME_SIZE)
+#if (FRAME_OFF + BACKCHAIN_OFF) != __SF_BACKCHAIN
+#error Stack frame layout calculation is broken
+#endif
+
+	GEN_BR_THUNK %r1
+
+SYM_FUNC_START(arch_bpf_timed_may_goto)
+	/*
+	 * This function has a special ABI: the parameters are in %r12 and
+	 * %r13; the return value is in %r12; all GPRs except %r0, %r1, and
+	 * %r12 are callee-saved; and the return address is in %r0.
+	 */
+	stmg %r2,%r5,FRAME_OFF+R2_OFF(%r15)
+	stg %r14,FRAME_OFF+R14_OFF(%r15)
+	stg %r0,FRAME_OFF+RETADDR_OFF(%r15)
+	stg %r15,FRAME_OFF+R15_OFF(%r15)
+	lgr %r1,%r15
+	lay %r15,-FRAME_SIZE(%r15)
+	stg %r1,__SF_BACKCHAIN(%r15)
+
+	lay %r2,0(%r12,%r13)
+	brasl %r14,bpf_check_timed_may_goto
+	lgr %r12,%r2
+
+	lg %r15,FRAME_SIZE+FRAME_OFF+R15_OFF(%r15)
+	lmg %r2,%r5,FRAME_OFF+R2_OFF(%r15)
+	lg %r14,FRAME_OFF+R14_OFF(%r15)
+	lg %r1,FRAME_OFF+RETADDR_OFF(%r15)
+	BR_EX %r1
+SYM_FUNC_END(arch_bpf_timed_may_goto)