bpf: Optimize emit_mov_imm64().

Turned out that bpf prog callback addresses, bpf prog addresses
used in bpf_trampoline, and in other cases the 64-bit address
can be represented as sign extended 32-bit value.

According to https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82339
"Skylake has 0.64c throughput for mov r64, imm64, vs. 0.25 for mov r32, imm32."
So use shorter encoding and faster instruction when possible.

Special care is needed in jit_subprogs(), since bpf_pseudo_func()
instruction cannot change its size during the last step of JIT.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/CAADnVQKFfpY-QZBrOU2CG8v2du8Lgyb7MNVmOZVK_yTyOdNbBA@mail.gmail.com
Link: https://lore.kernel.org/bpf/20240401233800.42737-1-alexei.starovoitov@gmail.com

arch/x86/net/bpf_jit_comp.c

@@ -816,9 +816,10 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 			   const u32 imm32_hi, const u32 imm32_lo)
 {
+	u64 imm64 = ((u64)imm32_hi << 32) | (u32)imm32_lo;
 	u8 *prog = *pprog;
 
-	if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
+	if (is_uimm32(imm64)) {
 		/*
 		 * For emitting plain u32, where sign bit must not be
 		 * propagated LLVM tends to load imm64 over mov32
@@ -826,6 +827,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 		 * 'mov %eax, imm32' instead.
 		 */
 		emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
+	} else if (is_simm32(imm64)) {
+		emit_mov_imm32(&prog, true, dst_reg, imm32_lo);
 	} else {
 		/* movabsq rax, imm64 */
 		EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));

kernel/bpf/verifier.c

@@ -19147,12 +19147,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		env->insn_aux_data[i].call_imm = insn->imm;
 		/* point imm to __bpf_call_base+1 from JITs point of view */
 		insn->imm = 1;
-		if (bpf_pseudo_func(insn))
+		if (bpf_pseudo_func(insn)) {
+#if defined(MODULES_VADDR)
+			u64 addr = MODULES_VADDR;
+#else
+			u64 addr = VMALLOC_START;
+#endif
 			/* jit (e.g. x86_64) may emit fewer instructions
 			 * if it learns a u32 imm is the same as a u64 imm.
-			 * Force a non zero here.
+			 * Set close enough to possible prog address.
 			 */
-			insn[1].imm = 1;
+			insn[0].imm = (u32)addr;
+			insn[1].imm = addr >> 32;
+		}
 	}
 
 	err = bpf_prog_alloc_jited_linfo(prog);