arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD

Now that kernel mode FPSIMD state is context switched along with other
task state, we can enable the existing logic that keeps track of which
task's FPSIMD state the CPU is holding in its registers. If it is the
context of the task that we are switching to, we can elide the reload of
the FPSIMD state from memory.

Note that we also need to check whether the FPSIMD state on this CPU is
the most recent: if a task gets migrated away and back again, the state
in memory may be more recent than the state in the CPU. So add another
CPU id field to task_struct to keep track of this. (We could reuse the
existing CPU id field used for user mode context, but that might result
in user state to be discarded unnecessarily, given that two distinct
CPUs could be holding the most recent user mode state and the most
recent kernel mode state)

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20231208113218.3001940-9-ardb@google.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: ardbiesheuvel

arch/arm64/include/asm/processor.h

@@ -169,6 +169,7 @@ struct thread_struct {
 	struct debug_info	debug;		/* debugging */
 
 	struct user_fpsimd_state	kernel_fpsimd_state;
+	unsigned int			kernel_fpsimd_cpu;
 #ifdef CONFIG_ARM64_PTR_AUTH
 	struct ptrauth_keys_user	keys_user;
 #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL

arch/arm64/kernel/fpsimd.c

@@ -1476,12 +1476,30 @@ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs)
 
 static void fpsimd_load_kernel_state(struct task_struct *task)
 {
+	struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
+
+	/*
+	 * Elide the load if this CPU holds the most recent kernel mode
+	 * FPSIMD context of the current task.
+	 */
+	if (last->st == &task->thread.kernel_fpsimd_state &&
+	    task->thread.kernel_fpsimd_cpu == smp_processor_id())
+		return;
+
 	fpsimd_load_state(&task->thread.kernel_fpsimd_state);
 }
 
 static void fpsimd_save_kernel_state(struct task_struct *task)
 {
+	struct cpu_fp_state cpu_fp_state = {
+		.st		= &task->thread.kernel_fpsimd_state,
+		.to_save	= FP_STATE_FPSIMD,
+	};
+
 	fpsimd_save_state(&task->thread.kernel_fpsimd_state);
+	fpsimd_bind_state_to_cpu(&cpu_fp_state);
+
+	task->thread.kernel_fpsimd_cpu = smp_processor_id();
 }
 
 void fpsimd_thread_switch(struct task_struct *next)