summaryrefslogtreecommitdiff
path: root/arch/x86/net
diff options
context:
space:
mode:
authorAlexei Starovoitov <ast@kernel.org>2024-04-02 02:38:00 +0300
committerDaniel Borkmann <daniel@iogearbox.net>2024-04-04 17:13:26 +0300
commitaf682b767a41772499f8e54ca7d7e1deb3395f44 (patch)
tree6d1b833f7a32bae58032ff46b09ffea035ef5147 /arch/x86/net
parent1e9e0b85255e6eca6036b59d8a5fbca6501905ac (diff)
downloadlinux-af682b767a41772499f8e54ca7d7e1deb3395f44.tar.xz
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
Diffstat (limited to 'arch/x86/net')
-rw-r--r--arch/x86/net/bpf_jit_comp.c5
1 files changed, 4 insertions, 1 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 964e8154da66..6cf9a5697c09 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -816,9 +816,10 @@ done:
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));