[RFC PATCH 13/29] arm64/sve: Basic support for KERNEL_MODE_NEON

[Dave Martin]

In order to enable CONFIG_KERNEL_MODE_NEON and things that rely on
it to be configured together with Scalable Vector Extension support
in the same kernel, this patch implements basic support for
saving/restoring the SVE state around kernel_neon_begin()...
kernel_neon_end().

This patch is not optimal and will generally save more state than
necessary, more often than necessary.  Further optimisations can be
implemented in future patches.

This patch is not intended to allow general-purpose _SVE_ code to
execute in the kernel safely.  That functionality may also follow
in later patches.

Signed-off-by: Dave Martin <Dave.Martin at arm.com>
---
 arch/arm64/Kconfig         |  1 -
 arch/arm64/kernel/fpsimd.c | 22 ++++++++++++++++++----
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index e8d04dd..7266761 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -880,7 +880,6 @@ endmenu
 config ARM64_SVE
 	bool "ARM Scalable Vector Extension support"
 	default y
-	depends on !KERNEL_MODE_NEON	# until it works with SVE
 	help
 	  The Scalable Vector Extension (SVE) is an extension to the AArch64
 	  execution state which complements and extends the SIMD functionality
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 81cfdb5..cb947dd 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -282,11 +282,26 @@ static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
  */
 void kernel_neon_begin_partial(u32 num_regs)
 {
+	preempt_disable();
+
+	/*
+	 * For now, we have no special storage for SVE registers in
+	 * interrupt context, so always save the userland SVE state
+	 * if there is any, even for interrupts.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_SVE) && (elf_hwcap & HWCAP_SVE) &&
+	    current->mm &&
+	    !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		fpsimd_save_state(&current->thread.fpsimd_state);
+		this_cpu_write(fpsimd_last_state, NULL);
+	}
+
 	if (in_interrupt()) {
 		struct fpsimd_partial_state *s = this_cpu_ptr(
 			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
-
 		BUG_ON(num_regs > 32);
+
+		/* Save partial state for interrupted kernel-mode NEON code: */
 		fpsimd_save_partial_state(s, roundup(num_regs, 2));
 	} else {
 		/*
@@ -295,7 +310,6 @@ void kernel_neon_begin_partial(u32 num_regs)
 		 * that there is no longer userland FPSIMD state in the
 		 * registers.
 		 */
-		preempt_disable();
 		if (current->mm &&
 		    !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
 			fpsimd_save_state(&current->thread.fpsimd_state);
@@ -310,9 +324,9 @@ void kernel_neon_end(void)
 		struct fpsimd_partial_state *s = this_cpu_ptr(
 			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
 		fpsimd_load_partial_state(s);
-	} else {
-		preempt_enable();
 	}
+
+	preempt_enable();
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
-- 
2.1.4