MIPS: Stop building position independent code

U-Boot has up until now built with -fpic for the MIPS architecture,
producing position independent code which uses indirection through a
global offset table, making relocation fairly straightforward as it
simply involves patching up GOT entries.

Using -fpic does however have some downsides. The biggest of these is
that generated code is bloated in various ways. For example, function
calls are indirected through the GOT & the t9 register:

  8f998064   lw     t9,-32668(gp)
  0320f809   jalr   t9

Without -fpic the call is simply:

  0f803f01   jal    be00fc04 <puts>

This is more compact & faster (due to the lack of the load & the
dependency the jump has on its result). It is also easier to read &
debug because the disassembly shows what function is being called,
rather than just an offset from gp which would then have to be looked up
in the ELF to discover the target function.

Another disadvantage of -fpic is that each function begins with a
sequence to calculate the value of the gp register, for example:

  3c1c0004   lui    gp,0x4
  279c3384   addiu  gp,gp,13188
  0399e021   addu   gp,gp,t9

Without using -fpic this sequence no longer appears at the start of each
function, reducing code size considerably.

This patch switches U-Boot from building with -fpic to building with
-fno-pic, in order to gain the benefits described above. The cost of
this is an extra step during the build process to extract relocation
data from the ELF & write it into a new .rel section in a compact
format, plus the added complexity of dealing with multiple types of
relocation rather than the single type that applied to the GOT. The
benefit is smaller, cleaner, more debuggable code. The relocate_code()
function is reimplemented in C to handle the new relocation scheme,
which also makes it easier to read & debug.

Taking maltael_defconfig as an example the size of u-boot.bin built
using the Codescape MIPS 2016.05-06 toolchain (gcc 4.9.2, binutils
2.24.90) shrinks from 254KiB to 224KiB.

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Daniel Schwierzeck <daniel.schwierzeck@gmail.com>
Cc: u-boot@lists.denx.de
Reviewed-by: Daniel Schwierzeck <daniel.schwierzeck@gmail.com>
Tested-by: Daniel Schwierzeck <daniel.schwierzeck@gmail.com>
diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink
new file mode 100644
index 0000000..7da3acd
--- /dev/null
+++ b/arch/mips/Makefile.postlink
@@ -0,0 +1,23 @@
+#
+# Copyright (c) 2017 Imagination Technologies Ltd.
+#
+# SPDX-License-Identifier:	GPL-2.0+
+#
+
+PHONY := __archpost
+__archpost:
+
+-include include/config/auto.conf
+include scripts/Kbuild.include
+
+CMD_RELOCS = tools/mips-relocs
+quiet_cmd_relocs = RELOCS  $@
+      cmd_relocs = $(CMD_RELOCS) $@
+
+u-boot: FORCE
+	@true
+	$(call if_changed,relocs)
+
+.PHONY: FORCE
+
+FORCE:
diff --git a/arch/mips/config.mk b/arch/mips/config.mk
index 2c72c15..cefdbe6 100644
--- a/arch/mips/config.mk
+++ b/arch/mips/config.mk
@@ -56,25 +56,14 @@
 # LDFLAGS_vmlinux		+= -G 0 -static -n -nostdlib
 # MODFLAGS			+= -mlong-calls
 #
-# On the other hand, we want PIC in the U-Boot code to relocate it from ROM
-# to RAM. $28 is always used as gp.
-#
-ifdef CONFIG_SPL_BUILD
-PF_ABICALLS			:= -mno-abicalls
-PF_PIC				:= -fno-pic
-PF_PIE				:=
-else
-PF_ABICALLS			:= -mabicalls
-PF_PIC				:= -fpic
-PF_PIE				:= -pie
-PF_OBJCOPY			:= -j .got -j .rel.dyn -j .padding
-PF_OBJCOPY			+= -j .dtb.init.rodata
+ifndef CONFIG_SPL_BUILD
+OBJCOPYFLAGS			+= -j .got -j .rel -j .padding -j .dtb.init.rodata
+LDFLAGS_FINAL			+= --emit-relocs
 endif
 
-PLATFORM_CPPFLAGS		+= -G 0 $(PF_ABICALLS) $(PF_PIC)
+PLATFORM_CPPFLAGS		+= -G 0 -mno-abicalls -fno-pic
 PLATFORM_CPPFLAGS		+= -msoft-float
 PLATFORM_LDFLAGS		+= -G 0 -static -n -nostdlib
 PLATFORM_RELFLAGS		+= -ffunction-sections -fdata-sections
-LDFLAGS_FINAL			+= --gc-sections $(PF_PIE)
+LDFLAGS_FINAL			+= --gc-sections
 OBJCOPYFLAGS			+= -j .text -j .rodata -j .data -j .u_boot_list
-OBJCOPYFLAGS			+= $(PF_OBJCOPY)
diff --git a/arch/mips/cpu/start.S b/arch/mips/cpu/start.S
index d01ee9f..952c57a 100644
--- a/arch/mips/cpu/start.S
+++ b/arch/mips/cpu/start.S
@@ -221,18 +221,6 @@
 	ehb
 #endif
 
-	/*
-	 * Initialize $gp, force pointer sized alignment of bal instruction to
-	 * forbid the compiler to put nop's between bal and _gp. This is
-	 * required to keep _gp and ra aligned to 8 byte.
-	 */
-	.align	PTRLOG
-	bal	1f
-	 nop
-	PTR	_gp
-1:
-	PTR_L	gp, 0(ra)
-
 #ifdef CONFIG_MIPS_CM
 	PTR_LA	t9, mips_cm_map
 	jalr	t9
@@ -291,121 +279,3 @@
 	 move	ra, zero
 
 	END(_start)
-
-/*
- * void relocate_code (addr_sp, gd, addr_moni)
- *
- * This "function" does not return, instead it continues in RAM
- * after relocating the monitor code.
- *
- * a0 = addr_sp
- * a1 = gd
- * a2 = destination address
- */
-ENTRY(relocate_code)
-	move	sp, a0			# set new stack pointer
-	move	fp, sp
-
-	move	s0, a1			# save gd in s0
-	move	s2, a2			# save destination address in s2
-
-	PTR_LI	t0, CONFIG_SYS_MONITOR_BASE
-	PTR_SUB	s1, s2, t0		# s1 <-- relocation offset
-
-	PTR_LA	t2, __image_copy_end
-	move	t1, a2
-
-	/*
-	 * t0 = source address
-	 * t1 = target address
-	 * t2 = source end address
-	 */
-1:
-	PTR_L	t3, 0(t0)
-	PTR_S	t3, 0(t1)
-	PTR_ADDU t0, PTRSIZE
-	blt	t0, t2, 1b
-	 PTR_ADDU t1, PTRSIZE
-
-	/*
-	 * Now we want to update GOT.
-	 *
-	 * GOT[0] is reserved. GOT[1] is also reserved for the dynamic object
-	 * generated by GNU ld. Skip these reserved entries from relocation.
-	 */
-	PTR_LA	t3, num_got_entries
-	PTR_LA	t8, _GLOBAL_OFFSET_TABLE_
-	PTR_ADD	t8, s1			# t8 now holds relocated _G_O_T_
-	PTR_ADDIU t8, t8, 2 * PTRSIZE	# skipping first two entries
-	PTR_LI	t2, 2
-1:
-	PTR_L	t1, 0(t8)
-	beqz	t1, 2f
-	 PTR_ADD t1, s1
-	PTR_S	t1, 0(t8)
-2:
-	PTR_ADDIU t2, 1
-	blt	t2, t3, 1b
-	 PTR_ADDIU t8, PTRSIZE
-
-	/* Update dynamic relocations */
-	PTR_LA	t1, __rel_dyn_start
-	PTR_LA	t2, __rel_dyn_end
-
-	b	2f			# skip first reserved entry
-	 PTR_ADDIU t1, 2 * PTRSIZE
-
-1:
-	lw	t8, -4(t1)		# t8 <-- relocation info
-
-	PTR_LI	t3, MIPS_RELOC
-	bne	t8, t3, 2f		# skip non-MIPS_RELOC entries
-	 nop
-
-	PTR_L	t3, -(2 * PTRSIZE)(t1)	# t3 <-- location to fix up in FLASH
-
-	PTR_L	t8, 0(t3)		# t8 <-- original pointer
-	PTR_ADD	t8, s1			# t8 <-- adjusted pointer
-
-	PTR_ADD	t3, s1			# t3 <-- location to fix up in RAM
-	PTR_S	t8, 0(t3)
-
-2:
-	blt	t1, t2, 1b
-	 PTR_ADDIU t1, 2 * PTRSIZE	# each rel.dyn entry is 2*PTRSIZE bytes
-
-	/*
-	 * Flush caches to ensure our newly modified instructions are visible
-	 * to the instruction cache. We're still running with the old GOT, so
-	 * apply the reloc offset to the start address.
-	 */
-	PTR_LA	a0, __text_start
-	PTR_LA	a1, __text_end
-	PTR_SUB	a1, a1, a0
-	PTR_LA	t9, flush_cache
-	jalr	t9
-	 PTR_ADD	a0, s1
-
-	PTR_ADD	gp, s1			# adjust gp
-
-	/*
-	 * Clear BSS
-	 *
-	 * GOT is now relocated. Thus __bss_start and __bss_end can be
-	 * accessed directly via $gp.
-	 */
-	PTR_LA	t1, __bss_start		# t1 <-- __bss_start
-	PTR_LA	t2, __bss_end		# t2 <-- __bss_end
-
-1:
-	PTR_S	zero, 0(t1)
-	blt	t1, t2, 1b
-	 PTR_ADDIU t1, PTRSIZE
-
-	move	a0, s0			# a0 <-- gd
-	move	a1, s2
-	PTR_LA	t9, board_init_r
-	jr	t9
-	 move	ra, zero
-
-	END(relocate_code)
diff --git a/arch/mips/cpu/u-boot.lds b/arch/mips/cpu/u-boot.lds
index 0129c99..bd5536f 100644
--- a/arch/mips/cpu/u-boot.lds
+++ b/arch/mips/cpu/u-boot.lds
@@ -34,15 +34,6 @@
 		*(.data*)
 	}
 
-	. = .;
-	_gp = ALIGN(16) + 0x7ff0;
-
-	.got : {
-		*(.got)
-	}
-
-	num_got_entries = SIZEOF(.got) >> PTR_COUNT_SHIFT;
-
 	. = ALIGN(4);
 	.sdata : {
 		*(.sdata*)
@@ -57,33 +48,19 @@
 	__image_copy_end = .;
 	__init_end = .;
 
-	.rel.dyn : {
-		__rel_dyn_start = .;
-		*(.rel.dyn)
-		__rel_dyn_end = .;
-	}
-
-	.padding : {
-		/*
-		 * Workaround for a binutils feature (or bug?).
-		 *
-		 * The GNU ld from binutils puts the dynamic relocation
-		 * entries into the .rel.dyn section. Sometimes it
-		 * allocates more dynamic relocation entries than it needs
-		 * and the unused slots are set to R_MIPS_NONE entries.
-		 *
-		 * However the size of the .rel.dyn section in the ELF
-		 * section header does not cover the unused entries, so
-		 * objcopy removes those during stripping.
-		 *
-		 * Create a small section here to avoid that.
-		 */
-		LONG(0xFFFFFFFF)
+	/*
+	 * .rel must come last so that the mips-relocs tool can shrink
+	 * the section size & the PT_LOAD program header filesz.
+	 */
+	.rel : {
+		__rel_start = .;
+		BYTE(0x0)
+		. += (32 * 1024) - 1;
 	}
 
 	_end = .;
 
-	.bss __rel_dyn_start (OVERLAY) : {
+	.bss __rel_start (OVERLAY) : {
 		__bss_start = .;
 		*(.sbss.*)
 		*(.bss.*)
diff --git a/arch/mips/include/asm/relocs.h b/arch/mips/include/asm/relocs.h
new file mode 100644
index 0000000..92e9d04
--- /dev/null
+++ b/arch/mips/include/asm/relocs.h
@@ -0,0 +1,24 @@
+/*
+ * MIPS Relocations
+ *
+ * Copyright (c) 2017 Imagination Technologies Ltd.
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#ifndef __ASM_MIPS_RELOCS_H__
+#define __ASM_MIPS_RELOCS_H__
+
+#define R_MIPS_NONE		0
+#define R_MIPS_32		2
+#define R_MIPS_26		4
+#define R_MIPS_HI16		5
+#define R_MIPS_LO16		6
+#define R_MIPS_PC16		10
+#define R_MIPS_64		18
+#define R_MIPS_HIGHER		28
+#define R_MIPS_HIGHEST		29
+#define R_MIPS_PC21_S2		60
+#define R_MIPS_PC26_S2		61
+
+#endif /* __ASM_MIPS_RELOCS_H__ */
diff --git a/arch/mips/include/asm/sections.h b/arch/mips/include/asm/sections.h
index fc4640a..b9d2179 100644
--- a/arch/mips/include/asm/sections.h
+++ b/arch/mips/include/asm/sections.h
@@ -8,4 +8,11 @@
 
 #include <asm-generic/sections.h>
 
+/**
+ * __rel_start: Relocation data generated by the mips-relocs tool
+ *
+ * See arch/mips/lib/reloc.c for details on the format & use of this data.
+ */
+extern uint8_t __rel_start[];
+
 #endif
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 659c6ad..ef557c6 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -8,6 +8,7 @@
 obj-y	+= cache.o
 obj-y	+= cache_init.o
 obj-y	+= genex.o
+obj-y	+= reloc.o
 obj-y	+= stack.o
 obj-y	+= traps.o
 
diff --git a/arch/mips/lib/reloc.c b/arch/mips/lib/reloc.c
new file mode 100644
index 0000000..d0c52c9
--- /dev/null
+++ b/arch/mips/lib/reloc.c
@@ -0,0 +1,164 @@
+/*
+ * MIPS Relocation
+ *
+ * Copyright (c) 2017 Imagination Technologies Ltd.
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ *
+ * Relocation data, found in the .rel section, is generated by the mips-relocs
+ * tool & contains a record of all locations in the U-Boot binary that need to
+ * be fixed up during relocation.
+ *
+ * The data is a sequence of unsigned integers, which are of somewhat arbitrary
+ * size. This is achieved by encoding integers as a sequence of bytes, each of
+ * which contains 7 bits of data with the most significant bit indicating
+ * whether any further bytes need to be read. The least significant bits of the
+ * integer are found in the first byte - ie. it somewhat resembles little
+ * endian.
+ *
+ * Each pair of two integers represents a relocation that must be applied. The
+ * first integer represents the type of relocation as a standard ELF relocation
+ * type (ie. R_MIPS_*). The second integer represents the offset at which to
+ * apply the relocation, relative to the previous relocation or for the first
+ * relocation the start of the relocated .text section.
+ *
+ * The end of the relocation data is indicated when type R_MIPS_NONE (0) is
+ * read, at which point no further integers should be read. That is, the
+ * terminating R_MIPS_NONE reloc includes no offset.
+ */
+
+#include <common.h>
+#include <asm/relocs.h>
+#include <asm/sections.h>
+
+/**
+ * read_uint() - Read an unsigned integer from the buffer
+ * @buf: pointer to a pointer to the reloc buffer
+ *
+ * Read one whole unsigned integer from the relocation data pointed to by @buf,
+ * advancing @buf past the bytes encoding the integer.
+ *
+ * Returns: the integer read from @buf
+ */
+static unsigned long read_uint(uint8_t **buf)
+{
+	unsigned long val = 0;
+	unsigned int shift = 0;
+	uint8_t new;
+
+	do {
+		new = *(*buf)++;
+		val |= (new & 0x7f) << shift;
+		shift += 7;
+	} while (new & 0x80);
+
+	return val;
+}
+
+/**
+ * apply_reloc() - Apply a single relocation
+ * @type: the type of reloc (R_MIPS_*)
+ * @addr: the address that the reloc should be applied to
+ * @off: the relocation offset, ie. number of bytes we're moving U-Boot by
+ *
+ * Apply a single relocation of type @type at @addr. This function is
+ * intentionally simple, and does the bare minimum needed to fixup the
+ * relocated U-Boot - in particular, it does not check for overflows.
+ */
+static void apply_reloc(unsigned int type, void *addr, long off)
+{
+	uint32_t u32;
+
+	switch (type) {
+	case R_MIPS_26:
+		u32 = *(uint32_t *)addr;
+		u32 = (u32 & GENMASK(31, 26)) |
+		      ((u32 + (off >> 2)) & GENMASK(25, 0));
+		*(uint32_t *)addr = u32;
+		break;
+
+	case R_MIPS_32:
+		*(uint32_t *)addr += off;
+		break;
+
+	case R_MIPS_64:
+		*(uint64_t *)addr += off;
+		break;
+
+	case R_MIPS_HI16:
+		*(uint32_t *)addr += off >> 16;
+		break;
+
+	default:
+		panic("Unhandled reloc type %u\n", type);
+	}
+}
+
+/**
+ * relocate_code() - Relocate U-Boot, generally from flash to DDR
+ * @start_addr_sp: new stack pointer
+ * @new_gd: pointer to relocated global data
+ * @relocaddr: the address to relocate to
+ *
+ * Relocate U-Boot from its current location (generally in flash) to a new one
+ * (generally in DDR). This function will copy the U-Boot binary & apply
+ * relocations as necessary, then jump to board_init_r in the new build of
+ * U-Boot. As such, this function does not return.
+ */
+void relocate_code(ulong start_addr_sp, gd_t *new_gd, ulong relocaddr)
+{
+	unsigned long addr, length, bss_len;
+	uint8_t *buf, *bss_start;
+	unsigned int type;
+	long off;
+
+	/*
+	 * Ensure that we're relocating by an offset which is a multiple of
+	 * 64KiB, ie. doesn't change the least significant 16 bits of any
+	 * addresses. This allows us to discard R_MIPS_LO16 relocs, saving
+	 * space in the U-Boot binary & complexity in handling them.
+	 */
+	off = relocaddr - (unsigned long)__text_start;
+	if (off & 0xffff)
+		panic("Mis-aligned relocation\n");
+
+	/* Copy U-Boot to RAM */
+	length = __image_copy_end - __text_start;
+	memcpy((void *)relocaddr, __text_start, length);
+
+	/* Now apply relocations to the copy in RAM */
+	buf = __rel_start;
+	addr = relocaddr;
+	while (true) {
+		type = read_uint(&buf);
+		if (type == R_MIPS_NONE)
+			break;
+
+		addr += read_uint(&buf) << 2;
+		apply_reloc(type, (void *)addr, off);
+	}
+
+	/* Ensure the icache is coherent */
+	flush_cache(relocaddr, length);
+
+	/* Clear the .bss section */
+	bss_start = (uint8_t *)((unsigned long)__bss_start + off);
+	bss_len = (unsigned long)&__bss_end - (unsigned long)__bss_start;
+	memset(bss_start, 0, bss_len);
+
+	/* Jump to the relocated U-Boot */
+	asm volatile(
+		       "move	$29, %0\n"
+		"	move	$4, %1\n"
+		"	move	$5, %2\n"
+		"	move	$31, $0\n"
+		"	jr	%3"
+		: /* no outputs */
+		: "r"(start_addr_sp),
+		  "r"(new_gd),
+		  "r"(relocaddr),
+		  "r"((unsigned long)board_init_r + off));
+
+	/* Since we jumped to the new U-Boot above, we won't get here */
+	unreachable();
+}