[U-Boot] [PATCHv2] mpc83xx: Add -fpic relocation support

[Joakim Tjernlund]

This add relocation of .got entries produced
by -fpic. -fpic produces 2-3% smaller code and
is faster. Unfortunately gcc promotes -fpic to
-fPIC when -mrelocatable is used so one need a very
small patch to gcc too(sent upstream).

-fpic puts its GOT entries in .got section(s) and
linker defines the symbol _GLOBAL_OFFSET_TABLE_ to point
to the middle of this table. The entry at _GLOBAL_OFFSET_TABLE_-4
contains a blrl insn which is used to find the table's
real address by branching to _GLOBAL_OFFSET_TABLE_-4.

Here are some size examples for my board:
size with -fPIC
 text    data	    bss	    dec	    hex	filename
 224687  14400	  24228	 263315	  40493	u-boot

size with -mbss-plt -fPIC
 text	   data	    bss	    dec	    hex	filename
 222687  14400	  24228	 261315	  3fcc3	u-boot

size with -mbss-plt -fpic
 text   data	    bss	    dec	    hex	filename
 225179   6580	  24228	 255987	  3e7f3	u-boot

size with -mbss-plt -fpic -msingle-pic-base
 text	  data	    bss	    dec	    hex	filename
 222091   6580	  24228	 252899	  3dbe3	u-boot

Note: -msingle-pic-base is not supported upstarem yet.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund at transmode.se>
---
 v2: Better commit msg
     Fix linker script for two NAND boards.
     Only compile the new -fpic code if compiled
     with -fpic to reduce size.

 arch/powerpc/cpu/mpc83xx/start.S                |   31 +++++++++++++++++++++-
 arch/powerpc/cpu/mpc83xx/u-boot.lds             |    1 +
 nand_spl/board/freescale/mpc8313erdb/u-boot.lds |    2 +
 nand_spl/board/freescale/mpc8315erdb/u-boot.lds |    2 +
 4 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/cpu/mpc83xx/start.S b/arch/powerpc/cpu/mpc83xx/start.S
index c7d85a8..8b540bc 100644
--- a/arch/powerpc/cpu/mpc83xx/start.S
+++ b/arch/powerpc/cpu/mpc83xx/start.S
@@ -69,6 +69,10 @@
  */
 	START_GOT
 	GOT_ENTRY(_GOT2_TABLE_)
+#if defined(__pic__) && __pic__ == 1
+	GOT_ENTRY(_GOT_TABLE_)
+	GOT_ENTRY(_GLOBAL_OFFSET_TABLE_)
+#endif
 	GOT_ENTRY(__bss_start)
 	GOT_ENTRY(_end)
 
@@ -296,7 +300,11 @@ in_flash:
 	/*------------------------------------------------------*/
 
 	GET_GOT			/* initialize GOT access	*/
-
+#if defined(__pic__) && __pic__ == 1
+	/* Needed for upcoming -msingle-pic-base */
+	bl	_GLOBAL_OFFSET_TABLE_ at local-4
+	mflr	r30
+#endif
 	/* r3: IMMR */
 	lis	r3, CONFIG_SYS_IMMR at h
 	/* run low-level CPU init code (in Flash)*/
@@ -950,7 +958,26 @@ in_ram:
 	add	r0,r0,r11
 	stw	r0,0(r3)
 2:	bdnz	1b
-
+#if defined(__pic__) && __pic__ == 1
+	/*
+	 * Relocation of *.got(-fpic)
+	 */
+	lwz	r4,GOT(_GLOBAL_OFFSET_TABLE_)
+	addi	r4,r4,-4 /* don't write over blrl in GOT */
+	lwz	r3,GOT(_GOT_TABLE_)
+	subf.	r4,r3,r4 /* r4 - r3 */
+	ble	3f
+	srwi	r4,r4,2 /* r4/4 */
+	mtctr	r4
+	addi	r3,r3,-4
+1:	lwzu	r0,4(r3)
+	cmpwi	r0,0
+	beq-	2f
+	add	r0,r0,r11
+	stw	r0,0(r3)
+2:	bdnz	1b
+3:
+#endif
 #ifndef CONFIG_NAND_SPL
 	/*
 	 * Now adjust the fixups and the pointers to the fixups
diff --git a/arch/powerpc/cpu/mpc83xx/u-boot.lds b/arch/powerpc/cpu/mpc83xx/u-boot.lds
index 0b74a13..a498a37 100644
--- a/arch/powerpc/cpu/mpc83xx/u-boot.lds
+++ b/arch/powerpc/cpu/mpc83xx/u-boot.lds
@@ -67,6 +67,7 @@ SECTIONS
   PROVIDE (erotext = .);
   .reloc   :
   {
+    _GOT_TABLE_ = .;
     *(.got)
     _GOT2_TABLE_ = .;
     *(.got2)
diff --git a/nand_spl/board/freescale/mpc8313erdb/u-boot.lds b/nand_spl/board/freescale/mpc8313erdb/u-boot.lds
index ad82589..1a3e44f 100644
--- a/nand_spl/board/freescale/mpc8313erdb/u-boot.lds
+++ b/nand_spl/board/freescale/mpc8313erdb/u-boot.lds
@@ -38,6 +38,8 @@ SECTIONS
 	.data : {
 		*(.data*)
 		*(.sdata*)
+		_GOT_TABLE_ = .;
+		*(.got)
 		_GOT2_TABLE_ = .;
 		*(.got2)
 		__got2_entries = (. - _GOT2_TABLE_) >> 2;
diff --git a/nand_spl/board/freescale/mpc8315erdb/u-boot.lds b/nand_spl/board/freescale/mpc8315erdb/u-boot.lds
index ad82589..1a3e44f 100644
--- a/nand_spl/board/freescale/mpc8315erdb/u-boot.lds
+++ b/nand_spl/board/freescale/mpc8315erdb/u-boot.lds
@@ -38,6 +38,8 @@ SECTIONS
 	.data : {
 		*(.data*)
 		*(.sdata*)
+		_GOT_TABLE_ = .;
+		*(.got)
 		_GOT2_TABLE_ = .;
 		*(.got2)
 		__got2_entries = (. - _GOT2_TABLE_) >> 2;
-- 
1.7.2.2