Re: [PATCH v2 15/16] arm/arm64: smccc: Implement SMCCC v1.1 inline primitive

From: Ard Biesheuvel
Date: Mon Jan 29 2018 - 16:45:42 EST


On 29 January 2018 at 17:45, Marc Zyngier <marc.zyngier@xxxxxxx> wrote:
> One of the major improvement of SMCCC v1.1 is that it only clobbers
> the first 4 registers, both on 32 and 64bit. This means that it
> becomes very easy to provide an inline version of the SMC call
> primitive, and avoid performing a function call to stash the
> registers that would otherwise be clobbered by SMCCC v1.0.
>
> Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
> ---
> include/linux/arm-smccc.h | 157 ++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 157 insertions(+)
>
> diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
> index dd44d8458c04..bc5843728909 100644
> --- a/include/linux/arm-smccc.h
> +++ b/include/linux/arm-smccc.h
> @@ -150,5 +150,162 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
>
> #define arm_smccc_hvc_quirk(...) __arm_smccc_hvc(__VA_ARGS__)
>
> +/* SMCCC v1.1 implementation madness follows */
> +#ifdef CONFIG_ARM64
> +
> +#define SMCCC_SMC_INST "smc #0"
> +#define SMCCC_HVC_INST "hvc #0"
> +
> +#define __arm_smccc_1_1_prologue(inst) \
> + inst "\n" \
> + "cbz %[ptr], 1f\n" \
> + "stp %x[r0], %x[r1], %[ra0]\n" \
> + "stp %x[r2], %x[r3], %[ra2]\n" \
> + "1:\n" \
> + : [ra0] "=Ump" (*(&___res->a0)), \
> + [ra2] "=Ump" (*(&___res->a2)),
> +
> +#define __arm_smccc_1_1_epilogue : "memory"
> +
> +#endif
> +
> +#ifdef CONFIG_ARM
> +#include <asm/opcodes-sec.h>
> +#include <asm/opcodes-virt.h>
> +
> +#define SMCCC_SMC_INST __SMC(0)
> +#define SMCCC_HVC_INST __HVC(0)
> +
> +#define __arm_smccc_1_1_prologue(inst) \
> + inst "\n" \
> + "cmp %[ptr], #0\n" \
> + "stmne %[ptr], {%[r0], %[r1], %[r2], %[r3]}\n" \
> + : "=m" (*___res),
> +
> +#define __arm_smccc_1_1_epilogue : "memory", "cc"
> +
> +#endif
> +
> +#define __constraint_write_0 \
> + [r0] "+r" (r0), [r1] "=r" (r1), [r2] "=r" (r2), [r3] "=r" (r3)
> +#define __constraint_write_1 \
> + [r0] "+r" (r0), [r1] "+r" (r1), [r2] "=r" (r2), [r3] "=r" (r3)
> +#define __constraint_write_2 \
> + [r0] "+r" (r0), [r1] "+r" (r1), [r2] "+r" (r2), [r3] "=r" (r3)
> +#define __constraint_write_3 \
> + [r0] "+r" (r0), [r1] "+r" (r1), [r2] "+r" (r2), [r3] "+r" (r3)

It seems you need +r for all arguments, otherwise the compiler will
notice that the value is never used, and may assign the register to
'res' instead, i.e.,

3e4: 320107e0 mov w0, #0x80000001 // #-2147483647
3e8: 320183e1 mov w1, #0x80008000 // #-2147450880
3ec: 910123a2 add x2, x29, #0x48
3f0: d4000002 hvc #0x0
3f4: b4000062 cbz x2, 400 <enable_psci_bp_hardening+0x88>
3f8: a90487a0 stp x0, x1, [x29, #72]
3fc: a9058fa2 stp x2, x3, [x29, #88]

(for the code generated in the next patch)

> +#define __constraint_write_4 __constraint_write_3
> +#define __constraint_write_5 __constraint_write_3
> +#define __constraint_write_6 __constraint_write_3
> +#define __constraint_write_7 __constraint_write_3
> +
> +#define __constraint_read_0 : [ptr] "r" (___res)
> +#define __constraint_read_1 __constraint_read_0
> +#define __constraint_read_2 __constraint_read_0
> +#define __constraint_read_3 __constraint_read_0
> +#define __constraint_read_4 __constraint_read_3, "r" (r4)
> +#define __constraint_read_5 __constraint_read_4, "r" (r5)
> +#define __constraint_read_6 __constraint_read_5, "r" (r6)
> +#define __constraint_read_7 __constraint_read_6, "r" (r7)
> +
> +#define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
> +
> +#define __count_args(...) \
> + ___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
> +
> +#define __declare_arg_0(a0, res) \
> + struct arm_smccc_res *___res = res; \
> + register u32 r0 asm("r0") = a0; \
> + register unsigned long r1 asm("r1"); \
> + register unsigned long r2 asm("r2"); \
> + register unsigned long r3 asm("r3")
> +
> +#define __declare_arg_1(a0, a1, res) \
> + struct arm_smccc_res *___res = res; \
> + register u32 r0 asm("r0") = a0; \
> + register typeof(a1) r1 asm("r1") = a1; \
> + register unsigned long r2 asm("r2"); \
> + register unsigned long r3 asm("r3")
> +
> +#define __declare_arg_2(a0, a1, a2, res) \
> + struct arm_smccc_res *___res = res; \
> + register u32 r0 asm("r0") = a0; \
> + register typeof(a1) r1 asm("r1") = a1; \
> + register typeof(a2) r2 asm("r2") = a2; \
> + register unsigned long r3 asm("r3")
> +
> +#define __declare_arg_3(a0, a1, a2, a3, res) \
> + struct arm_smccc_res *___res = res; \
> + register u32 r0 asm("r0") = a0; \
> + register typeof(a1) r1 asm("r1") = a1; \
> + register typeof(a2) r2 asm("r2") = a2; \
> + register typeof(a3) r3 asm("r3") = a3
> +
> +#define __declare_arg_4(a0, a1, a2, a3, a4, res) \
> + __declare_arg_3(a0, a1, a2, a3, res); \
> + register typeof(a4) r4 asm("r4") = a4
> +
> +#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \
> + __declare_arg_4(a0, a1, a2, a3, a4, res); \
> + register typeof(a5) r5 asm("r5") = a5
> +
> +#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \
> + __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \
> + register typeof(a6) r6 asm("r6") = a6
> +
> +#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \
> + __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \
> + register typeof(a7) r7 asm("r7") = a7
> +
> +#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
> +#define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__)
> +
> +#define ___constraint_write(count) __constraint_write_ ## count
> +#define __constraint_write(count) ___constraint_write(count)
> +
> +#define ___constraint_read(count) __constraint_read_ ## count
> +#define __constraint_read(count) ___constraint_read(count)
> +
> +#define __arm_smccc_1_1(inst, ...) \
> + do { \
> + __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \
> + asm(__arm_smccc_1_1_prologue(inst) \
> + __constraint_write(__count_args(__VA_ARGS__)) \
> + __constraint_read(__count_args(__VA_ARGS__)) \
> + __arm_smccc_1_1_epilogue); \
> + } while (0)
> +
> +/*
> + * arm_smccc_1_1_smc() - make an SMCCC v1.1 compliant SMC call
> + *
> + * This is a variadic macro taking one to eight source arguments, and
> + * an optional return structure.
> + *
> + * @a0-a7: arguments passed in registers 0 to 7
> + * @res: result values from registers 0 to 3
> + *
> + * This macro is used to make SMC calls following SMC Calling Convention v1.1.
> + * The content of the supplied param are copied to registers 0 to 7 prior
> + * to the SMC instruction. The return values are updated with the content
> + * from register 0 to 3 on return from the SMC instruction if not NULL.
> + */
> +#define arm_smccc_1_1_smc(...) __arm_smccc_1_1(SMCCC_SMC_INST, __VA_ARGS__)
> +
> +/*
> + * arm_smccc_1_1_hvc() - make an SMCCC v1.1 compliant HVC call
> + *
> + * This is a variadic macro taking one to eight source arguments, and
> + * an optional return structure.
> + *
> + * @a0-a7: arguments passed in registers 0 to 7
> + * @res: result values from registers 0 to 3
> + *
> + * This macro is used to make HVC calls following SMC Calling Convention v1.1.
> + * The content of the supplied param are copied to registers 0 to 7 prior
> + * to the HVC instruction. The return values are updated with the content
> + * from register 0 to 3 on return from the HVC instruction if not NULL.
> + */
> +#define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
> +
> #endif /*__ASSEMBLY__*/
> #endif /*__LINUX_ARM_SMCCC_H*/
> --
> 2.14.2
>