On Sun, Jul 3, 2022 at 6:59 PM Ammar Faizi wrote: > > From: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx> > > These functions are called at initialization, which are slow-paths. > Mark them as __cold so that the compiler will optimize for code size. > > Here is the result compiling with Ubuntu clang > 15.0.0-++20220601012204+ec2711b35411-1~exp1~20220601012300.510 > > Without this patch: > > $ wc -c src/liburing.so.2.3 > 71288 src/liburing.so.2.3 > > With this patch: > > $ wc -c src/liburing.so.2.3 > 69448 src/liburing.so.2.3 > > Take one slow-path function example, using __cold avoids aggresive > inlining. > > Without this patch: > > 00000000000024f0 <io_uring_queue_init>: > 24f0: pushq %r14 > 24f2: pushq %rbx > 24f3: subq $0x78,%rsp > 24f7: movq %rsi,%r14 > 24fa: xorps %xmm0,%xmm0 > 24fd: movaps %xmm0,(%rsp) > 2501: movaps %xmm0,0x60(%rsp) > 2506: movaps %xmm0,0x50(%rsp) > 250b: movaps %xmm0,0x40(%rsp) > 2510: movaps %xmm0,0x30(%rsp) > 2515: movaps %xmm0,0x20(%rsp) > 251a: movaps %xmm0,0x10(%rsp) > 251f: movq $0x0,0x70(%rsp) > 2528: movl %edx,0x8(%rsp) > 252c: movq %rsp,%rsi > 252f: movl $0x1a9,%eax > 2534: syscall > 2536: movq %rax,%rbx > 2539: testl %ebx,%ebx > 253b: js 256a <io_uring_queue_init+0x7a> > 253d: movq %rsp,%rsi > 2540: movl %ebx,%edi > 2542: movq %r14,%rdx > 2545: callq 2080 <io_uring_queue_mmap@plt> > 254a: testl %eax,%eax > 254c: je 255d <io_uring_queue_init+0x6d> > 254e: movl %eax,%edx > 2550: movl $0x3,%eax > 2555: movl %ebx,%edi > 2557: syscall > 2559: movl %edx,%ebx > 255b: jmp 256a <io_uring_queue_init+0x7a> > 255d: movl 0x14(%rsp),%eax > 2561: movl %eax,0xc8(%r14) > 2568: xorl %ebx,%ebx > 256a: movl %ebx,%eax > 256c: addq $0x78,%rsp > 2570: popq %rbx > 2571: popq %r14 > 2573: retq > > With this patch: > > 000000000000240c <io_uring_queue_init>: > 240c: subq $0x78,%rsp > 2410: xorps %xmm0,%xmm0 > 2413: movq %rsp,%rax > 2416: movaps %xmm0,(%rax) > 2419: movaps %xmm0,0x60(%rax) > 241d: movaps %xmm0,0x50(%rax) > 2421: movaps %xmm0,0x40(%rax) > 2425: movaps %xmm0,0x30(%rax) > 2429: movaps %xmm0,0x20(%rax) > 242d: movaps %xmm0,0x10(%rax) > 2431: movq $0x0,0x70(%rax) > 2439: movl %edx,0x8(%rax) > 243c: movq %rax,%rdx > 243f: callq 2090 <io_uring_queue_init_params@plt> > 2444: addq $0x78,%rsp > 2448: retq > > Signed-off-by: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx> Reviewed-by: Alviro Iskandar Setiawan <alviro.iskandar@xxxxxxxxxxx> tq -- Viro
