arm64: smccc: Support SMCCC v1.3 SVE register saving hint

SMCCC v1.2 requires that all SVE state be preserved over SMC calls which
introduces substantial overhead in the common case where there is no SVE
state in the registers. To avoid this SMCCC v1.3 introduces a flag which
allows the caller to say that there is no state that needs to be preserved
in the registers. Make use of this flag, setting it if the SMCCC version
indicates support for it and the TIF_ flags indicate that there is no live
SVE state in the registers, this avoids placing any constraints on when
SMCCC calls can be done or triggering extra saving and reloading of SVE
register state in the kernel.

This would be straightforward enough except for the rather entertaining
inline assembly we use to do SMCCC v1.1 calls to allow us to take advantage
of the limited number of registers it clobbers. Deal with this by having a
function which we call immediately before issuing the SMCCC call to make
our checks and set the flag. Using alternatives the overhead if SVE is
supported but not detected at runtime can be reduced to a single NOP.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210603184118.15090-1-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>

Author: broonie

arch/arm64/kernel/smccc-call.S

@@ -7,8 +7,34 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include <asm/thread_info.h>
+
+/*
+ * If we have SMCCC v1.3 and (as is likely) no SVE state in
+ * the registers then set the SMCCC hint bit to say there's no
+ * need to preserve it.  Do this by directly adjusting the SMCCC
+ * function value which is already stored in x0 ready to be called.
+ */
+SYM_FUNC_START(__arm_smccc_sve_check)
+
+	ldr_l	x16, smccc_has_sve_hint
+	cbz	x16, 2f
+
+	get_current_task x16
+	ldr	x16, [x16, #TSK_TI_FLAGS]
+	tbnz	x16, #TIF_FOREIGN_FPSTATE, 1f	// Any live FP state?
+	tbnz	x16, #TIF_SVE, 2f		// Does that state include SVE?
+
+1:	orr	x0, x0, ARM_SMCCC_1_3_SVE_HINT
+
+2:	ret
+SYM_FUNC_END(__arm_smccc_sve_check)
+EXPORT_SYMBOL(__arm_smccc_sve_check)
 
 	.macro SMCCC instr
+alternative_if ARM64_SVE
+	bl	__arm_smccc_sve_check
+alternative_else_nop_endif
 	\instr	#0
 	ldr	x4, [sp]
 	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]

drivers/firmware/smccc/smccc.c

@@ -15,13 +15,17 @@ static u32 smccc_version = ARM_SMCCC_VERSION_1_0;
 static enum arm_smccc_conduit smccc_conduit = SMCCC_CONDUIT_NONE;
 
 bool __ro_after_init smccc_trng_available = false;
+u64 __ro_after_init smccc_has_sve_hint = false;
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit)
 {
 	smccc_version = version;
 	smccc_conduit = conduit;
 
 	smccc_trng_available = smccc_probe_trng();
+	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
+	    smccc_version >= ARM_SMCCC_VERSION_1_3)
+		smccc_has_sve_hint = true;
 }
 
 enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)

include/linux/arm-smccc.h

@@ -63,6 +63,9 @@
 #define ARM_SMCCC_VERSION_1_0		0x10000
 #define ARM_SMCCC_VERSION_1_1		0x10001
 #define ARM_SMCCC_VERSION_1_2		0x10002
+#define ARM_SMCCC_VERSION_1_3		0x10003
+
+#define ARM_SMCCC_1_3_SVE_HINT		0x10000
 
 #define ARM_SMCCC_VERSION_FUNC_ID					\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
@@ -216,6 +219,8 @@ u32 arm_smccc_get_version(void);
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit);
 
+extern u64 smccc_has_sve_hint;
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
@@ -295,6 +300,15 @@ struct arm_smccc_quirk {
 	} state;
 };
 
+/**
+ * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls
+ *
+ * Sets the SMCCC hint bit to indicate if there is live state in the SVE
+ * registers, this modifies x0 in place and should never be called from C
+ * code.
+ */
+asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0);
+
 /**
  * __arm_smccc_smc() - make SMC calls
  * @a0-a7: arguments passed in registers 0 to 7
@@ -352,6 +366,20 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 
 #endif
 
+/* nVHE hypervisor doesn't have a current thread so needs separate checks */
+#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__)
+
+#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n",  "bl __arm_smccc_sve_check \n", \
+				    ARM64_SVE)
+#define smccc_sve_clobbers "x16", "x30", "cc",
+
+#else
+
+#define SMCCC_SVE_CHECK
+#define smccc_sve_clobbers
+
+#endif
+
 #define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
 
 #define __count_args(...)						\
@@ -419,7 +447,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 
 #define ___constraints(count)						\
 	: __constraint_read_ ## count					\
-	: "memory"
+	: smccc_sve_clobbers "memory"
 #define __constraints(count)	___constraints(count)
 
 /*
@@ -434,7 +462,8 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 		register unsigned long r2 asm("r2");			\
 		register unsigned long r3 asm("r3"); 			\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm volatile(inst "\n" :				\
+		asm volatile(SMCCC_SVE_CHECK				\
+			     inst "\n" :				\
 			     "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3)	\
 			     __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\