firmware: Support position independent execution

Enable OpenSBI to support position independent execution. Because the
position independent code will cause an additional GOT reference when
accessing the global variables, it will reduce performance a bit. Therefore,
the position independent execution is disabled by default. Users can
through specifying "FW_PIC=y" on the make command to enable this feature.

In theory, after enabling position-independent execution, the OpenSBI
can run at arbitrary address with appropriate alignment. Therefore, the
original relocation mechanism will be skipped. In other words, OpenSBI will
directly run at the load address without any code movement.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Anup Patel <anup.patel@wdc.com>

Makefile

@@ -210,8 +210,8 @@ CFLAGS		+=	-mabi=$(PLATFORM_RISCV_ABI) -march=$(PLATFORM_RISCV_ISA)
 CFLAGS		+=	-mcmodel=$(PLATFORM_RISCV_CODE_MODEL)
 CFLAGS		+=	$(GENFLAGS)
 CFLAGS		+=	$(platform-cflags-y)
-CFLAGS		+=	$(firmware-cflags-y)
 CFLAGS		+=	-fno-pie -no-pie
+CFLAGS		+=	$(firmware-cflags-y)
 
 CPPFLAGS	+=	$(GENFLAGS)
 CPPFLAGS	+=	$(platform-cppflags-y)

firmware/fw_base.S

@@ -9,6 +9,7 @@
 
 #include <sbi/riscv_asm.h>
 #include <sbi/riscv_encoding.h>
+#include <sbi/riscv_elf.h>
 #include <sbi/sbi_platform.h>
 #include <sbi/sbi_scratch.h>
 #include <sbi/sbi_trap.h>
@@ -67,6 +68,58 @@ _try_lottery:
 	lla	t1, _start
 	REG_S	t1, 0(t0)
 
+#ifdef FW_PIC
+	/* relocate the global table content */
+	lla	t0, _link_start
+	REG_L	t0, 0(t0)
+	/* t1 shall has the address of _start */
+	sub	t2, t1, t0
+	lla	t3, _runtime_offset
+	REG_S	t2, (t3)
+	lla	t0, __rel_dyn_start
+	lla	t1, __rel_dyn_end
+	beq	t0, t1, _relocate_done
+	j	5f
+2:
+	REG_L	t5, -(REGBYTES*2)(t0)	/* t5 <-- relocation info:type */
+	li	t3, R_RISCV_RELATIVE	/* reloc type R_RISCV_RELATIVE */
+	bne	t5, t3, 3f
+	REG_L	t3, -(REGBYTES*3)(t0)
+	REG_L	t5, -(REGBYTES)(t0)	/* t5 <-- addend */
+	add	t5, t5, t2
+	add	t3, t3, t2
+	REG_S	t5, 0(t3)		/* store runtime address to the GOT entry */
+	j	5f
+
+3:
+	lla	t4, __dyn_sym_start
+
+4:
+	REG_L	t5, -(REGBYTES*2)(t0)	/* t5 <-- relocation info:type */
+	srli	t6, t5, SYM_INDEX	/* t6 <--- sym table index */
+	andi	t5, t5, 0xFF		/* t5 <--- relocation type */
+	li	t3, RELOC_TYPE
+	bne	t5, t3, 5f
+
+	/* address R_RISCV_64 or R_RISCV_32 cases*/
+	REG_L	t3, -(REGBYTES*3)(t0)
+	li	t5, SYM_SIZE
+	mul	t6, t6, t5
+	add	s5, t4, t6
+	REG_L	t6, -(REGBYTES)(t0)	/* t0 <-- addend */
+	REG_L	t5, REGBYTES(s5)
+	add	t5, t5, t6
+	add	t5, t5, t2		/* t5 <-- location to fix up in RAM */
+	add	t3, t3, t2		/* t3 <-- location to fix up in RAM */
+	REG_S	t5, 0(t3)		/* store runtime address to the variable */
+
+5:
+	addi	t0, t0, (REGBYTES*3)
+	ble	t0, t1, 2b
+	j	_relocate_done
+_wait_relocate_copy_done:
+	j	_wait_for_boot_hart
+#else
 	/* Relocate if load address != link address */
 _relocate:
 	lla	t0, _link_start
@@ -137,6 +190,7 @@ _wait_relocate_copy_done:
 	nop
 	bgt     t4, t5, 1b
 	jr	t3
+#endif
 _relocate_done:
 
 	/*
@@ -144,12 +198,14 @@ _relocate_done:
 	 * Use _boot_status copy relative to the load address
 	 */
 	lla	t0, _boot_status
+#ifndef FW_PIC
 	lla	t1, _link_start
 	REG_L	t1, 0(t1)
 	lla	t2, _load_start
 	REG_L	t2, 0(t2)
 	sub	t0, t0, t1
 	add	t0, t0, t2
+#endif
 	li	t1, BOOT_STATUS_RELOCATE_DONE
 	REG_S	t1, 0(t0)
 	fence	rw, rw
@@ -446,6 +502,10 @@ _skip_trap_exit_rv32_hyp:
 	j	_start_hang
 
 	.align 3
+#ifdef FW_PIC
+_runtime_offset:
+	RISCV_PTR	0
+#endif
 _relocate_lottery:
 	RISCV_PTR	0
 _boot_status:
@@ -453,7 +513,7 @@ _boot_status:
 _load_start:
 	RISCV_PTR	_fw_start
 _link_start:
-	RISCV_PTR	_fw_start
+	RISCV_PTR	FW_TEXT_START
 _link_end:
 	RISCV_PTR	_fw_reloc_end
 

firmware/fw_base.ldS

@@ -61,6 +61,19 @@
 		PROVIDE(_data_end = .);
 	}
 
+	.dynsym : {
+		PROVIDE(__dyn_sym_start = .);
+		*(.dynsym)
+		PROVIDE(__dyn_sym_end = .);
+	}
+
+	.rela.dyn : {
+		PROVIDE(__rel_dyn_start = .);
+		*(.rela*)
+		. = ALIGN(8);
+		PROVIDE(__rel_dyn_end = .);
+	}
+
 	. = ALIGN(0x1000); /* Ensure next section is page aligned */
 
 	.bss :

firmware/objects.mk

@@ -13,6 +13,13 @@ firmware-cflags-y +=
 firmware-asflags-y +=
 firmware-ldflags-y +=
 
+ifeq ($(FW_PIC),y)
+firmware-genflags-y +=	-DFW_PIC
+firmware-asflags-y  +=	-fpic
+firmware-cflags-y   +=	-fPIE -pie
+firmware-ldflags-y  +=  -Wl,--no-dynamic-linker
+endif
+
 ifdef FW_TEXT_START
 firmware-genflags-y += -DFW_TEXT_START=$(FW_TEXT_START)
 endif

include/sbi/riscv_elf.h

@@ -0,0 +1,14 @@
+#ifndef __RISCV_ELF_H__
+#define __RISCV_ELF_H__
+
+#include <sbi/riscv_asm.h>
+
+#define R_RISCV_32		1
+#define R_RISCV_64		2
+#define R_RISCV_RELATIVE	3
+
+#define RELOC_TYPE		__REG_SEL(R_RISCV_64, R_RISCV_32)
+#define SYM_INDEX		__REG_SEL(0x20,	0x8)
+#define SYM_SIZE		__REG_SEL(0x18,0x10)
+
+#endif