Introduce load_TLS to the "for" loop.

GCC (4.1 at least) unrolls it anyway, but I can't believe this code was ever justifiable. (I've also submitted a patch which cleans up i386, which is even uglier).

diff -r de5618b5e562 include/asm-x86_64/desc.h
@@ -135,16 +135,13 @@ static inline void set_ldt_desc(unsigned
 	(info)->useable		== 0	&& \
 	(info)->lm		== 0)
 
-#if TLS_SIZE != 24
-# error update this code.
-#endif
-
 static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
 {
+	unsigned int i;
 	u64 *gdt = (u64 *)(cpu_gdt(cpu) + GDT_ENTRY_TLS_MIN);
-	gdt[0] = t->tls_array[0];
-	gdt[1] = t->tls_array[1];
-	gdt[2] = t->tls_array[2];
+
+	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+		gdt[i] = t->tls_array[i];
 } 
 
 /*

Are you sure? Normally it doesn't unroll without -funroll-loops which the kernel does normally not set. Especially not with -Os builds.

-Andi

Does it matter either way in this case?

J

It's in the middle of the context switch.

-Andi

Well, the rest of __switch_to isn't "0PTIM1Z3D!!!" like this.

But even so, that's no excuse for crap code. If it had used memcpy, we wouldn't be wasting cycles on this discussion.

Rusty.

Yep, checked again:

$ gcc --version
gcc (GCC) 4.1.2 20060928 (prerelease) (Ubuntu 4.1.1-13ubuntu5)
...
...
  gcc -Wp,-MD,arch/x86_64/kernel/.process.o.d  -nostdinc
-isystem /usr/lib/gcc/i486-linux-gnu/4.1.2/include -D__KERNEL__
-Iinclude  -include include/linux/autoconf.h -Wall -Wundef
-Wstrict-prototypes -Wno-trigraphs -fno-strict-aliasing -fno-common -O2
-mtune=generic -m64 -mno-red-zone -mcmodel=kernel -pipe
-fno-reorder-blocks -Wno-sign-compare -fno-asynchronous-unwind-tables
-funit-at-a-time -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
-maccumulate-outgoing-args   -fno-omit-frame-pointer
-fno-optimize-sibling-calls -g  -fno-stack-protector
-Wdeclaration-after-statement -Wno-pointer-sign     -D"KBUILD_STR(s)=#s"
-D"KBUILD_BASENAME=KBUILD_STR(process)"
-D"KBUILD_MODNAME=KBUILD_STR(process)" -c -o
arch/x86_64/kernel/process.o arch/x86_64/kernel/process.c
...
$ objdump -Dr arch/x86_64/kernel/process.o | less
...
     6be:       48 8b 94 00 00 00 00    mov    0x0(%rax,%rax,1),%rdx
     6c5:       00 
                        6c2: R_X86_64_32S       cpu_gdt_descr+0x2
     6c6:       48 8b 83 98 02 00 00    mov    0x298(%rbx),%rax
     6cd:       48 83 c2 60             add    $0x60,%rdx
     6d1:       48 89 02                mov    %rax,(%rdx)
     6d4:       48 8b 83 a0 02 00 00    mov    0x2a0(%rbx),%rax
     6db:       48 89 42 08             mov    %rax,0x8(%rdx)
     6df:       48 8b 83 a8 02 00 00    mov    0x2a8(%rbx),%rax
     6e6:       48 89 42 10             mov    %rax,0x10(%rdx)

If I turn on CONFIG_OPTIMIZE_FOR_SIZE, it's still unrolled, interestingly.

Cheers,
Rusty.