x86: Separate out entry text section

Put x86 entry code into a separate link section: .entry.text.

Separating the entry text section seems to have performance
benefits - caused by more efficient instruction cache usage.

Running hackbench with perf stat --repeat showed that the change
compresses the icache footprint. The icache load miss rate went
down by about 15%:

before patch:
19417627 L1-icache-load-misses ( +- 0.147% )

after patch:
16490788 L1-icache-load-misses ( +- 0.180% )

The motivation of the patch was to fix a particular kprobes
bug that relates to the entry text section, the performance
advantage was discovered accidentally.

Whole perf output follows:

- results for current tip tree:

Performance counter stats for './hackbench/hackbench 10' (500 runs):

19417627 L1-icache-load-misses ( +- 0.147% )
2676914223 instructions # 0.497 IPC ( +- 0.079% )
5389516026 cycles ( +- 0.144% )

0.206267711 seconds time elapsed ( +- 0.138% )

- results for current tip tree with the patch applied:

Performance counter stats for './hackbench/hackbench 10' (500 runs):

16490788 L1-icache-load-misses ( +- 0.180% )
2717734941 instructions # 0.502 IPC ( +- 0.079% )
5414756975 cycles ( +- 0.148% )

0.206747566 seconds time elapsed ( +- 0.137% )

Signed-off-by: Jiri Olsa <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Frederic Weisbecker <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Cc: Nick Piggin <[e-mail]>
Cc: Eric Dumazet <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
LKML-Reference: <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

arch/x86/ia32/ia32entry.S

···
 #define sysretl_audit ia32_ret_from_sys_call
 #endif
 
+	.section .entry.text, "ax"
+
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
 
 	.macro IA32_ARG_FIXUP noebp=0

arch/x86/kernel/entry_32.S

···
 #define sysexit_audit	syscall_exit_work
 #endif
 
+	.section .entry.text, "ax"
+
 /*
  * We use macros for low-level operations which need to be overridden
  * for paravirtualization.  The following will never clobber any registers:
···
  */
 .section .init.rodata,"a"
 ENTRY(interrupt)
-.text
+.section .entry.text, "ax"
 	.p2align 5
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
···
       .endif
       .previous
 	.long 1b
-      .text
+      .section .entry.text, "ax"
 vector=vector+1
     .endif
   .endr

arch/x86/kernel/entry_64.S

···
 #define __AUDIT_ARCH_LE	   0x40000000
 
 	.code64
+	.section .entry.text, "ax"
+
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
···
  */
 	.section .init.rodata,"a"
 ENTRY(interrupt)
-	.text
+	.section .entry.text
 	.p2align 5
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
···
       .endif
       .previous
 	.quad 1b
-      .text
+      .section .entry.text
 vector=vector+1
     .endif
   .endr

arch/x86/kernel/vmlinux.lds.S

···
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		ENTRY_TEXT
 		IRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)

include/asm-generic/sections.h

···
 extern char _end[];
 extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
 

include/asm-generic/vmlinux.lds.h

···
 		*(.kprobes.text)					\
 		VMLINUX_SYMBOL(__kprobes_text_end) = .;
 
+#define ENTRY_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__entry_text_start) = .;			\
+		*(.entry.text)						\
+		VMLINUX_SYMBOL(__entry_text_end) = .;
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define IRQENTRY_TEXT							\
 		ALIGN_FUNCTION();					\