powerpc/64/bpf: fix tail calls for PCREL addressing

With PCREL addressing, there is no kernel TOC. So, it is not setup in
prologue when PCREL addressing is used. But the number of instructions
to skip on a tail call was not adjusted accordingly. That resulted in
not so obvious failures while using tailcalls. 'tailcalls' selftest
crashed the system with the below call trace:

bpf_test_run+0xe8/0x3cc (unreliable)
bpf_prog_test_run_skb+0x348/0x778
__sys_bpf+0xb04/0x2b00
sys_bpf+0x28/0x38
system_call_exception+0x168/0x340
system_call_vectored_common+0x15c/0x2ec

Also, as bpf programs are always module addresses and a bpf helper in
general is a core kernel text address, using PC relative addressing
often fails with "out of range of pcrel address" error. Switch to
using kernel base for relative addressing to handle this better.

Fixes: 7e3a68be42e1 ("powerpc/64: vmlinux support building with PCREL addresing")
Cc: [e-mail] # v6.4+
Signed-off-by: Hari Bathini <[e-mail]>
Signed-off-by: Michael Ellerman <[e-mail]>
Link: https://msgid.link/[e-mail]

arch/powerpc/net/bpf_jit_comp64.c

···
 	EMIT(PPC_RAW_BLR());
 }
 
-static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func)
+static int
+bpf_jit_emit_func_call_hlp(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
 {
 	unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0;
 	long reladdr;
···
 		return -EINVAL;
 
 	if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
-		reladdr = func_addr - CTX_NIA(ctx);
+		reladdr = func_addr - local_paca->kernelbase;
 
 		if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) {
-			pr_err("eBPF: address of %ps out of range of pcrel address.\n",
-				(void *)func);
+			pr_err("eBPF: address of %ps out of range of 34-bit relative address.\n",
+			       (void *)func);
 			return -ERANGE;
 		}
-		/* pla r12,addr */
-		EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr));
-		EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr));
-		EMIT(PPC_RAW_MTCTR(_R12));
-		EMIT(PPC_RAW_BCTR());
-
+		EMIT(PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)));
+		/* Align for subsequent prefix instruction */
+		if (!IS_ALIGNED((unsigned long)fimage + CTX_NIA(ctx), 8))
+			EMIT(PPC_RAW_NOP());
+		/* paddi r12,r12,addr */
+		EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(0) | IMM_H18(reladdr));
+		EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12) | IMM_L(reladdr));
 	} else {
 		reladdr = func_addr - kernel_toc_addr();
 		if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
···
 
 		EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr)));
 		EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr)));
-		EMIT(PPC_RAW_MTCTR(_R12));
-		EMIT(PPC_RAW_BCTRL());
 	}
+	EMIT(PPC_RAW_MTCTR(_R12));
+	EMIT(PPC_RAW_BCTRL());
 
 	return 0;
 }
···
 	int b2p_index = bpf_to_ppc(BPF_REG_3);
 	int bpf_tailcall_prologue_size = 8;
 
-	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
+	if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL) && IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
 		bpf_tailcall_prologue_size += 4; /* skip past the toc load */
 
 	/*
···
 				return ret;
 
 			if (func_addr_fixed)
-				ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
+				ret = bpf_jit_emit_func_call_hlp(image, fimage, ctx, func_addr);
 			else
 				ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);