[PATCH 01/15] ARM: assembler: introduce adr_l, ldr_l and str_l macros

[Ard Biesheuvel]

Like arm64, ARM supports position independent code sequences that
produce symbol references with a greater reach than the ordinary
adr/ldr instructions.

Currently, we use open coded instruction sequences involving literals
and arithmetic operations. Instead, we can use movw/movt pairs on v7
CPUs, circumventing the D-cache entirely. For older CPUs, we can emit
the literal into a subsection, allowing it to be emitted out of line
while retaining the ability to perform arithmetic on label offsets.

E.g., on pre-v7 CPUs, we can emit a PC-relative reference as follows:

       ldr          <reg>, 222f
  111: add          <reg>, <reg>, pc
       .subsection  1
  222: .long        <sym> - (111b + 8)
       .previous

This is allowed by the assembler because, unlike ordinary sections,
subsections are combined into a single section into the object file,
and so the label references are not true cross-section references that
are visible as relocations. Note that we could even do something like

       add          <reg>, pc, #(222f - 111f) & ~0xfff
       ldr          <reg>, [<reg>, #(222f - 111f) & 0xfff]
  111: add          <reg>, <reg>, pc
       .subsection  1
  222: .long        <sym> - (111b + 8)
       .previous

if it turns out that the 4 KB range of the ldr instruction is insufficient
to reach the literal in the subsection, although this is currently not a
problem (of the 98 objects built from .S files in a multi_v7_defconfig
build, only 11 have .text sections that are over 1 KB, and the largest one
[entry-armv.o] is 3308 bytes)

Subsections have been available in binutils since 2004 at least, so
they should not cause any issues with older toolchains.

So use the above to implement the macros mov_l, adr_l, adrm_l (using ldm
to load multiple literals at once), ldr_l and str_l, all of which will
use movw/movt pairs on v7 and later CPUs, and use PC-relative literals
otherwise.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel at linaro.org>
---
 arch/arm/include/asm/assembler.h | 70 ++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index ad301f107dd2..cedf59a7f853 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -518,4 +518,74 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+#ifdef CONFIG_THUMB2_KERNEL
+#define	ARM_PC_BIAS		4
+#else
+#define	ARM_PC_BIAS		8
+#endif
+
+	.macro		__adldst_l, op, reg, sym, tmp
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr		\tmp, 111f
+	.subsection	1
+	.align		2
+111:	.long		\sym - (222f + ARM_PC_BIAS)
+	.previous
+	.else
+	movw		\tmp, #:lower16:\sym - (222f + ARM_PC_BIAS)
+	movt		\tmp, #:upper16:\sym - (222f + ARM_PC_BIAS)
+	.endif
+222:;	.ifc		\op, add
+	add		\reg, \tmp, pc
+	.elseif		CONFIG_THUMB2_KERNEL == 1
+	add		\tmp, \tmp, pc
+	\op		\reg, [\tmp]
+	.else
+	\op		\reg, [pc, \tmp]
+	.endif
+	.endm
+
+	/*
+	 * mov_l - move a constant value or [relocated] address into a register
+	 */
+	.macro		mov_l, dst:req, imm:req
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr		\dst, =\imm
+	.else
+	movw		\dst, #:lower16:\imm
+	movt		\dst, #:upper16:\imm
+	.endif
+	.endm
+
+	/*
+	 * adr_l - adr pseudo-op with unlimited range
+	 *
+	 * @dst: destination register
+	 * @sym: name of the symbol
+	 */
+	.macro		adr_l, dst:req, sym:req
+	__adldst_l	add, \dst, \sym, \dst
+	.endm
+
+	/*
+	 * ldr_l - ldr <literal> pseudo-op with unlimited range
+	 *
+	 * @dst: destination register
+	 * @sym: name of the symbol
+	 */
+	.macro		ldr_l, dst:req, sym:req
+	__adldst_l	ldr, \dst, \sym, \dst
+	.endm
+
+	/*
+	 * str_l - str <literal> pseudo-op with unlimited range
+	 *
+	 * @src: source register
+	 * @sym: name of the symbol
+	 * @tmp: mandatory scratch register
+	 */
+	.macro		str_l, src:req, sym:req, tmp:req
+	__adldst_l	str, \src, \sym, \tmp
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
-- 
2.11.0