mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-18 16:46:45 +07:00
0f5e5a3ab7
Automatic const char[] variables cause unnecessary code
generation. For example, the this_mod variable leads to
3f04: 48 b8 5f 5f 74 68 69 73 5f 6d movabs $0x6d5f736968745f5f,%rax # __this_m
3f0e: 4c 8d 44 24 02 lea 0x2(%rsp),%r8
3f13: 48 8d 7c 24 10 lea 0x10(%rsp),%rdi
3f18: 48 89 44 24 02 mov %rax,0x2(%rsp)
3f1d: 4c 89 e9 mov %r13,%rcx
3f20: b8 65 00 00 00 mov $0x65,%eax # e
3f25: 48 c7 c2 00 00 00 00 mov $0x0,%rdx
3f28: R_X86_64_32S .rodata.str1.1+0x18d
3f2c: be 48 00 00 00 mov $0x48,%esi
3f31: c7 44 24 0a 6f 64 75 6c movl $0x6c75646f,0xa(%rsp) # odul
3f39: 66 89 44 24 0e mov %ax,0xe(%rsp)
i.e., the string gets built on the stack at runtime. Similar code can be
found for the other instances I'm replacing here. Putting the string
in .rodata reduces the combined .text+.rodata size and saves time and
stack space at runtime.
The simplest fix, and what I've done for the this_mod case, is to just
make the variable static.
However, for the "<faulted>" case where the same string is used twice,
that prevents the linker from merging those two literals, so instead use
a macro - that also keeps the two instances automatically in
sync (instead of only the compile-time strlen expression).
Finally, for the two runs of spaces, it turns out that the "build
these strings on the stack" is not the worst part of what gcc does -
it turns print_func_help_header_irq() into "if (tgid) { /*
print_event_info + five seq_printf calls */ } else { /* print
event_info + another five seq_printf */}". Taking inspiration from a
suggestion from Al Viro, use %.*s to make snprintf either stop after
the first two spaces or print the whole string. As a bonus, the
seq_printfs now fit on single lines (at least, they are not longer
than the existing ones in the function just above), making it easier
to see that the ascii art lines up.
x86-64 defconfig + CONFIG_FUNCTION_TRACER:
$ scripts/stackdelta /tmp/stackusage.{0,1}
./kernel/trace/ftrace.c ftrace_mod_callback 152 136 -16
./kernel/trace/trace.c trace_default_header 56 32 -24
./kernel/trace/trace.c tracing_mark_raw_write 96 72 -24
./kernel/trace/trace.c tracing_mark_write 104 80 -24
bloat-o-meter
add/remove: 1/0 grow/shrink: 0/4 up/down: 14/-375 (-361)
Function old new delta
this_mod - 14 +14
ftrace_mod_callback 577 542 -35
tracing_mark_raw_write 444 374 -70
tracing_mark_write 616 540 -76
trace_default_header 600 406 -194
Link: http://lkml.kernel.org/r/20190320081757.6037-1-linux@rasmusvillemoes.dk
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
||
|---|---|---|
| .. | ||
| bpf | ||
| cgroup | ||
| configs | ||
| debug | ||
| dma | ||
| events | ||
| gcov | ||
| irq | ||
| livepatch | ||
| locking | ||
| power | ||
| printk | ||
| rcu | ||
| sched | ||
| time | ||
| trace | ||
| .gitignore | ||
| acct.c | ||
| async.c | ||
| audit_fsnotify.c | ||
| audit_tree.c | ||
| audit_watch.c | ||
| audit.c | ||
| audit.h | ||
| auditfilter.c | ||
| auditsc.c | ||
| backtracetest.c | ||
| bounds.c | ||
| capability.c | ||
| compat.c | ||
| configs.c | ||
| context_tracking.c | ||
| cpu_pm.c | ||
| cpu.c | ||
| crash_core.c | ||
| crash_dump.c | ||
| cred.c | ||
| delayacct.c | ||
| dma.c | ||
| elfcore.c | ||
| exec_domain.c | ||
| exit.c | ||
| extable.c | ||
| fail_function.c | ||
| fork.c | ||
| freezer.c | ||
| futex.c | ||
| groups.c | ||
| hung_task.c | ||
| iomem.c | ||
| irq_work.c | ||
| jump_label.c | ||
| kallsyms.c | ||
| kcmp.c | ||
| Kconfig.freezer | ||
| Kconfig.hz | ||
| Kconfig.locks | ||
| Kconfig.preempt | ||
| kcov.c | ||
| kexec_core.c | ||
| kexec_file.c | ||
| kexec_internal.h | ||
| kexec.c | ||
| kmod.c | ||
| kprobes.c | ||
| ksysfs.c | ||
| kthread.c | ||
| latencytop.c | ||
| Makefile | ||
| memremap.c | ||
| module_signing.c | ||
| module-internal.h | ||
| module.c | ||
| notifier.c | ||
| nsproxy.c | ||
| padata.c | ||
| panic.c | ||
| params.c | ||
| pid_namespace.c | ||
| pid.c | ||
| profile.c | ||
| ptrace.c | ||
| range.c | ||
| reboot.c | ||
| relay.c | ||
| resource.c | ||
| rseq.c | ||
| seccomp.c | ||
| signal.c | ||
| smp.c | ||
| smpboot.c | ||
| smpboot.h | ||
| softirq.c | ||
| stackleak.c | ||
| stacktrace.c | ||
| stop_machine.c | ||
| sys_ni.c | ||
| sys.c | ||
| sysctl_binary.c | ||
| sysctl.c | ||
| task_work.c | ||
| taskstats.c | ||
| test_kprobes.c | ||
| torture.c | ||
| tracepoint.c | ||
| tsacct.c | ||
| ucount.c | ||
| uid16.c | ||
| uid16.h | ||
| umh.c | ||
| up.c | ||
| user_namespace.c | ||
| user-return-notifier.c | ||
| user.c | ||
| utsname_sysctl.c | ||
| utsname.c | ||
| watchdog_hld.c | ||
| watchdog.c | ||
| workqueue_internal.h | ||
| workqueue.c | ||