Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH v2 15/16] arm/arm64: smccc: Implement SMCCC v1.1 inline
 primitive
To:     Marc Zyngier <marc.zyngier@arm.com>, linux-kernel@vger.kernel.org,
        linux-arm-kernel@lists.infradead.org, kvmarm@lists.cs.columbia.edu
Cc:     Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Peter Maydell <peter.maydell@linaro.org>,
        Christoffer Dall <christoffer.dall@linaro.org>,
        Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>,
        Mark Rutland <mark.rutland@arm.com>,
        Ard Biesheuvel <ard.biesheuvel@linaro.org>,
        Jon Masters <jcm@redhat.com>
References: <20180129174559.1866-1-marc.zyngier@arm.com>
 <20180129174559.1866-16-marc.zyngier@arm.com>
From:   Robin Murphy <robin.murphy@arm.com>
Message-ID: <04d16ecd-044c-fe56-f9be-78d0cb591e71@arm.com>
Date:   Mon, 29 Jan 2018 19:07:00 +0000
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.5.0
MIME-Version: 1.0
In-Reply-To: <20180129174559.1866-16-marc.zyngier@arm.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-GB
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 29/01/18 17:45, Marc Zyngier 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.

This is disgusting... I love it :D

> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
> ---
>   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)),

Rather than embedding a guaranteed spill to memory, I wonder if there's 
money in just always declaring r0-r3 as in-out operands, and propagating 
them by value afterwards, i.e.:

	asm(...);
	if (___res)
		*___res = (struct arm_smccc_res){ r0, r1, r2, r3 };

In theory, for sufficiently simple callers that might allow res to stay 
in registers for its entire lifetime and give nicer codegen. It *might* 
also simplify some of this macro machinery too, although at this point 
in the evening I can't really tell...

Robin.

> +
> +#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)
> +#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*/
>