diff mbox

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

Message ID 20170805205222.19868-2-ard.biesheuvel@linaro.org (mailing list archive)
State New, archived
Headers show

Commit Message

Ard Biesheuvel Aug. 5, 2017, 8:52 p.m. UTC
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@linaro.org>
---
 arch/arm/include/asm/assembler.h | 70 ++++++++++++++++++++
 1 file changed, 70 insertions(+)

Comments

Nicolas Pitre Aug. 8, 2017, 3:10 p.m. UTC | #1
On Sat, 5 Aug 2017, Ard Biesheuvel wrote:

> 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.

There is no adrm_l definition in this patch.

Also, might it be better to change mov_l to movl? Tthis looks similar to 
the ARM64 movl pseudo-instruction, and unlike all the other _l variants, 
this is not producing a pc relative result.

Talking about the _l suffix: I wonder if this could be more meaningful, 
like _rel maybe? At least in the adr_l case, this could easily be 
confused with adrl.

Otherwise I like it pretty much.


> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@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
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Ard Biesheuvel Aug. 8, 2017, 3:19 p.m. UTC | #2
On 8 August 2017 at 16:10, Nicolas Pitre <nicolas.pitre@linaro.org> wrote:
> On Sat, 5 Aug 2017, Ard Biesheuvel wrote:
>
>> 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.
>
> There is no adrm_l definition in this patch.
>

Ah yes, I played around with it but it becomes a bit clunky so I removed it:

        adrl         <reg1>, 222f
        ldm          <reg1>, {<reg1>, <reg2>}
   111: add          <reg1>, <reg1>, pc
        add          <reg2>, <reg2>, pc
        .subsection  1
   222: .long        <sym1> - (111b + 8)
        .long        <sym2> - (111b + 12)
        .previous

The adrl pseudo op always assembles to two instructions, so you need 5
instructions while using adr_l twice uses only 4. I am not sure if
eliminating one of the loads would make a huge difference, given that
there are no use cases for adrm_l on hot paths, at least not in this
series.

> Also, might it be better to change mov_l to movl? Tthis looks similar to
> the ARM64 movl pseudo-instruction, and unlike all the other _l variants,
> this is not producing a pc relative result.
>

On arm64, we have mov_q for a 64-bit absolute load, and I thought
mov_l was less confusing than mov_w. In general, I like the underscore
in the middle because on the one hand, it looks like a ordinary
mnemonic but on the other hand, it is obvious that it is not a true
instruction. mov_abs perhaps?

> Talking about the _l suffix: I wonder if this could be more meaningful,
> like _rel maybe? At least in the adr_l case, this could easily be
> confused with adrl.
>

On arm64, we have ldr_l, str_l and adr_l as well, and I usually try to
align between ARM and arm64 if I can.

> Otherwise I like it pretty much.
>

Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Nicolas Pitre Aug. 8, 2017, 3:39 p.m. UTC | #3
On Tue, 8 Aug 2017, Ard Biesheuvel wrote:

> On 8 August 2017 at 16:10, Nicolas Pitre <nicolas.pitre@linaro.org> wrote:
> > On Sat, 5 Aug 2017, Ard Biesheuvel wrote:
> >
> >> 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.
> >
> > There is no adrm_l definition in this patch.
> >
> 
> Ah yes, I played around with it but it becomes a bit clunky so I removed it:
> 
>         adrl         <reg1>, 222f
>         ldm          <reg1>, {<reg1>, <reg2>}
>    111: add          <reg1>, <reg1>, pc
>         add          <reg2>, <reg2>, pc
>         .subsection  1
>    222: .long        <sym1> - (111b + 8)
>         .long        <sym2> - (111b + 12)
>         .previous
> 
> The adrl pseudo op always assembles to two instructions, so you need 5
> instructions while using adr_l twice uses only 4. I am not sure if
> eliminating one of the loads would make a huge difference, given that
> there are no use cases for adrm_l on hot paths, at least not in this
> series.

I'd suggest you keep it to a minimum.  Using adr_l twice is clear and 
obvious.

> > Also, might it be better to change mov_l to movl? Tthis looks similar to
> > the ARM64 movl pseudo-instruction, and unlike all the other _l variants,
> > this is not producing a pc relative result.
> >
> 
> On arm64, we have mov_q for a 64-bit absolute load, and I thought
> mov_l was less confusing than mov_w. In general, I like the underscore
> in the middle because on the one hand, it looks like a ordinary
> mnemonic but on the other hand, it is obvious that it is not a true
> instruction. mov_abs perhaps?
> 
> > Talking about the _l suffix: I wonder if this could be more meaningful,
> > like _rel maybe? At least in the adr_l case, this could easily be
> > confused with adrl.
> >
> 
> On arm64, we have ldr_l, str_l and adr_l as well, and I usually try to
> align between ARM and arm64 if I can.

OK. I'm much less versed into ARM64 assembly so I'll defer to your 
judgment.  It's good if this mnemonic scheme already exists there with 
a similar meaning.


Nicolas
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

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__ */