Re: [PATCH v3 16/18] arm/arm64: smccc: Implement SMCCC v1.1 inline primitive
From: Robin Murphy
Date: Thu Feb 01 2018 - 09:18:15 EST
On 01/02/18 13:54, Marc Zyngier wrote:
On 01/02/18 13:34, Robin Murphy wrote:
On 01/02/18 11:46, 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.
Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
---
include/linux/arm-smccc.h | 143 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 143 insertions(+)
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index dd44d8458c04..575aabe85905 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -150,5 +150,148 @@ 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"
Nit: Maybe the argument can go in the template and we just define the
instruction mnemonics here?
+
+#endif
+
+#ifdef CONFIG_ARM
#elif ?
Sure, why not.
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+
+#define SMCCC_SMC_INST __SMC(0)
+#define SMCCC_HVC_INST __HVC(0)
Oh, I see, it was to line up with this :(
I do wonder if we could just embed an asm(".arch armv7-a+virt\n") (if
even necessary) for ARM, then take advantage of the common mnemonics for
all 3 instruction sets instead of needing manual encoding tricks? I
don't think we should ever be pulling this file in for non-v7 builds.
I suppose that strictly that appears to need binutils 2.21 rather than
the offical supported minimum of 2.20, but are people going to be
throwing SMCCC configs at antique toolchains in practice?
It has been an issue in the past, back when we merged KVM. We settled on
a hybrid solution where code outside of KVM would not rely on a newer
toolchain, hence the macros that Dave introduced. Maybe we've moved on
and we can take that bold step?
Either way I think we can happily throw that on the "future cleanup"
pile right now as it's not directly relevant to the purpose of the
patch; I'm sure we don't want to make potential backporting even more
difficult.
+
+#endif
+
+#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 __constraint_write_0 \
+ "+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_1 \
+ "+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_2 \
+ "+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3)
+#define __constraint_write_3 \
+ "+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3)
+#define __constraint_write_4 __constraint_write_3
+#define __constraint_write_5 __constraint_write_4
+#define __constraint_write_6 __constraint_write_5
+#define __constraint_write_7 __constraint_write_6
+
+#define __constraint_read_0
+#define __constraint_read_1
+#define __constraint_read_2
+#define __constraint_read_3
+#define __constraint_read_4 "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 __declare_arg_0(a0, res) \
+ struct arm_smccc_res *___res = res; \
Looks like the declaration of ___res could simply be factored out to the
template...
Tried that. But...
+ 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 ___constraints(count) \
+ : __constraint_write_ ## count \
+ : __constraint_read_ ## count \
+ : "memory"
+#define __constraints(count) ___constraints(count)
+
+/*
+ * We have an output list that is not necessarily used, and GCC feels
+ * entitled to optimise the whole sequence away. "volatile" is what
+ * makes it stick.
+ */
+#define __arm_smccc_1_1(inst, ...) \
+ do { \
+ __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \
+ asm volatile(inst "\n" \
+ __constraints(__count_args(__VA_ARGS__))); \
+ if (___res) \
+ *___res = (typeof(*___res)){r0, r1, r2, r3}; \
...especially since there's no obvious indication of where it comes from
when you're looking here.
... we don't have the variable name at all here (it is the last
parameter, and that doesn't quite work with the idea of variadic macros...).
The alternative would be to add a set of macros that return the result
parameter, based on the number of inputs. Not sure that's an improvement.
Ah, right, the significance of it being the *last* argument hadn't
clicked indeed. A whole barrage of extra macros just to extract res on
its own would be rather clunky, so let's just keep the nice streamlined
(if ever-so-slightly non-obvious) implementation as it is and ignore my
ramblings.
Robin.