powerpc/bpf ppc32: Fix BPF_SUB when imm == 0x80000000

Special case handling of the smallest 32-bit negative number for BPF_SUB.

Fixes: 51c66ad ("powerpc/bpf: Implement extended BPF on PPC32")
Signed-off-by: Naveen N. Rao <[email protected]>
Reviewed-by: Christophe Leroy <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/7135360a0cdf70adedbccf9863128b8daef18764.1633464148.git.naveen.n.rao@linux.vnet.ibm.com

Author: rnav

arch/powerpc/net/bpf_jit_comp32.c

@@ -357,7 +357,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				PPC_LI32(_R0, imm);
 				EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, _R0));
 			}
-			if (imm >= 0)
+			if (imm >= 0 || (BPF_OP(code) == BPF_SUB && imm == 0x80000000))
 				EMIT(PPC_RAW_ADDZE(dst_reg_h, dst_reg_h));
 			else
 				EMIT(PPC_RAW_ADDME(dst_reg_h, dst_reg_h));