ARM: 9283/1: permit non-nested kernel mode NEON in softirq context

We currently only permit kernel mode NEON in process context, to avoid
the need to preserve/restore the NEON register file when taking an
exception while running in the kernel.

Like we did on arm64, we can relax this restriction substantially, by
permitting kernel mode NEON from softirq context, while ensuring that
softirq processing is disabled when the NEON is being used in task
context. This guarantees that only NEON context belonging to user space
needs to be preserved and restored, which is already taken care of.

This is especially relevant for network encryption, where incoming
frames are typically handled in softirq context, and deferring software
decryption to a kernel thread or falling back to C code are both
undesirable from a performance PoV.

Tested-by: Martin Willi <[e-mail]>
Reviewed-by: Linus Walleij <[e-mail]>
Signed-off-by: Ard Biesheuvel <[e-mail]>
Signed-off-by: Russell King (Oracle) <[e-mail]>

arch/arm/include/asm/simd.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/hardirq.h>
+
+static __must_check inline bool may_use_simd(void)
+{
+	return IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && !in_hardirq();
+}

arch/arm/vfp/vfpmodule.c

···
 	local_bh_disable();
 
 	/*
-	 * Kernel mode NEON is only allowed outside of interrupt context
-	 * with preemption disabled. This will make sure that the kernel
-	 * mode NEON register contents never need to be preserved.
+	 * Kernel mode NEON is only allowed outside of hardirq context with
+	 * preemption and softirq processing disabled. This will make sure that
+	 * the kernel mode NEON register contents never need to be preserved.
 	 */
-	BUG_ON(in_interrupt());
-	cpu = get_cpu();
+	BUG_ON(in_hardirq());
+	cpu = __smp_processor_id();
 
 	fpexc = fmrx(FPEXC) | FPEXC_EN;
 	fmxr(FPEXC, fpexc);
···
 		vfp_save_state(vfp_current_hw_state[cpu], fpexc);
 #endif
 	vfp_current_hw_state[cpu] = NULL;
-	local_bh_enable();
 }
 EXPORT_SYMBOL(kernel_neon_begin);
 
···
 {
 	/* Disable the NEON/VFP unit. */
 	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
-	put_cpu();
+	local_bh_enable();
 }
 EXPORT_SYMBOL(kernel_neon_end);