Merge branch 'for-next/fpsimd' into for-next/core

* for-next/fpsimd:
  arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD
  arm64: fpsimd: Preserve/restore kernel mode NEON at context switch
  arm64: fpsimd: Drop unneeded 'busy' flag

1 files changed, 106 insertions, 59 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index bc9384517db3..505f389be3e0 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -85,13 +85,13 @@
  * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and
  * flag the register state as invalid.
  *
- * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may
- * save the task's FPSIMD context back to task_struct from softirq context.
- * To prevent this from racing with the manipulation of the task's FPSIMD state
- * from task context and thereby corrupting the state, it is necessary to
- * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
- * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
- * run but prevent them to use FPSIMD.
+ * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be
+ * called from softirq context, which will save the task's FPSIMD context back
+ * to task_struct. To prevent this from racing with the manipulation of the
+ * task's FPSIMD state from task context and thereby corrupting the state, it
+ * is necessary to protect any manipulation of a task's fpsimd_state or
+ * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend
+ * softirq servicing entirely until put_cpu_fpsimd_context() is called.
  *
  * For a certain task, the sequence may look something like this:
  * - the task gets scheduled in; if both the task's fpsimd_cpu field
@@ -209,27 +209,14 @@ static inline void sme_free(struct task_struct *t) { }
 
 #endif
 
-DEFINE_PER_CPU(bool, fpsimd_context_busy);
-EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
-
 static void fpsimd_bind_task_to_cpu(void);
 
-static void __get_cpu_fpsimd_context(void)
-{
-	bool busy = __this_cpu_xchg(fpsimd_context_busy, true);
-
-	WARN_ON(busy);
-}
-
 /*
  * Claim ownership of the CPU FPSIMD context for use by the calling context.
  *
  * The caller may freely manipulate the FPSIMD context metadata until
  * put_cpu_fpsimd_context() is called.
  *
- * The double-underscore version must only be called if you know the task
- * can't be preempted.
- *
  * On RT kernels local_bh_disable() is not sufficient because it only
  * serializes soft interrupt related sections via a local lock, but stays
  * preemptible. Disabling preemption is the right choice here as bottom
@@ -242,14 +229,6 @@ static void get_cpu_fpsimd_context(void)
 		local_bh_disable();
 	else
 		preempt_disable();
-	__get_cpu_fpsimd_context();
-}
-
-static void __put_cpu_fpsimd_context(void)
-{
-	bool busy = __this_cpu_xchg(fpsimd_context_busy, false);
-
-	WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */
 }
 
 /*
@@ -261,18 +240,12 @@ static void __put_cpu_fpsimd_context(void)
  */
 static void put_cpu_fpsimd_context(void)
 {
-	__put_cpu_fpsimd_context();
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		local_bh_enable();
 	else
 		preempt_enable();
 }
 
-static bool have_cpu_fpsimd_context(void)
-{
-	return !preemptible() && __this_cpu_read(fpsimd_context_busy);
-}
-
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type)
 {
 	return task->thread.vl[type];
@@ -383,7 +356,8 @@ static void task_fpsimd_load(void)
 	bool restore_ffr;
 
 	WARN_ON(!system_supports_fpsimd());
-	WARN_ON(!have_cpu_fpsimd_context());
+	WARN_ON(preemptible());
+	WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
 
 	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
@@ -406,7 +380,7 @@ static void task_fpsimd_load(void)
 		default:
 			/*
 			 * This indicates either a bug in
-			 * fpsimd_save() or memory corruption, we
+			 * fpsimd_save_user_state() or memory corruption, we
 			 * should always record an explicit format
 			 * when we save. We always at least have the
 			 * memory allocated for FPSMID registers so
@@ -457,7 +431,7 @@ static void task_fpsimd_load(void)
  * than via current, if we are saving KVM state then it will have
  * ensured that the type of registers to save is set in last->to_save.
  */
-static void fpsimd_save(void)
+static void fpsimd_save_user_state(void)
 {
 	struct cpu_fp_state const *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -467,7 +441,7 @@ static void fpsimd_save(void)
 	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
-	WARN_ON(!have_cpu_fpsimd_context());
+	WARN_ON(preemptible());
 
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
@@ -888,7 +862,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	if (task == current) {
 		get_cpu_fpsimd_context();
 
-		fpsimd_save();
+		fpsimd_save_user_state();
 	}
 
 	fpsimd_flush_task_state(task);
@@ -1500,6 +1474,34 @@ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs)
 		       current);
 }
 
+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)
 {
 	bool wrong_task, wrong_cpu;
@@ -1507,24 +1509,31 @@ void fpsimd_thread_switch(struct task_struct *next)
 	if (!system_supports_fpsimd())
 		return;
 
-	__get_cpu_fpsimd_context();
+	WARN_ON_ONCE(!irqs_disabled());
 
 	/* Save unsaved fpsimd state, if any: */
-	fpsimd_save();
-
-	/*
-	 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
-	 * state.  For kernel threads, FPSIMD registers are never loaded
-	 * and wrong_task and wrong_cpu will always be true.
-	 */
-	wrong_task = __this_cpu_read(fpsimd_last_state.st) !=
-					&next->thread.uw.fpsimd_state;
-	wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id();
+	if (test_thread_flag(TIF_KERNEL_FPSTATE))
+		fpsimd_save_kernel_state(current);
+	else
+		fpsimd_save_user_state();
 
-	update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
-			       wrong_task || wrong_cpu);
+	if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
+		fpsimd_load_kernel_state(next);
+		set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
+	} else {
+		/*
+		 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
+		 * state.  For kernel threads, FPSIMD registers are never
+		 * loaded with user mode FPSIMD state and so wrong_task and
+		 * wrong_cpu will always be true.
+		 */
+		wrong_task = __this_cpu_read(fpsimd_last_state.st) !=
+			&next->thread.uw.fpsimd_state;
+		wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id();
 
-	__put_cpu_fpsimd_context();
+		update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
+				       wrong_task || wrong_cpu);
+	}
 }
 
 static void fpsimd_flush_thread_vl(enum vec_type type)
@@ -1614,7 +1623,7 @@ void fpsimd_preserve_current_state(void)
 		return;
 
 	get_cpu_fpsimd_context();
-	fpsimd_save();
+	fpsimd_save_user_state();
 	put_cpu_fpsimd_context();
 }
 
@@ -1826,13 +1835,15 @@ static void fpsimd_flush_cpu_state(void)
  */
 void fpsimd_save_and_flush_cpu_state(void)
 {
+	unsigned long flags;
+
 	if (!system_supports_fpsimd())
 		return;
 	WARN_ON(preemptible());
-	__get_cpu_fpsimd_context();
-	fpsimd_save();
+	local_irq_save(flags);
+	fpsimd_save_user_state();
 	fpsimd_flush_cpu_state();
-	__put_cpu_fpsimd_context();
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_KERNEL_MODE_NEON
@@ -1864,10 +1875,37 @@ void kernel_neon_begin(void)
 	get_cpu_fpsimd_context();
 
 	/* Save unsaved fpsimd state, if any: */
-	fpsimd_save();
+	if (test_thread_flag(TIF_KERNEL_FPSTATE)) {
+		BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq());
+		fpsimd_save_kernel_state(current);
+	} else {
+		fpsimd_save_user_state();
+
+		/*
+		 * Set the thread flag so that the kernel mode FPSIMD state
+		 * will be context switched along with the rest of the task
+		 * state.
+		 *
+		 * On non-PREEMPT_RT, softirqs may interrupt task level kernel
+		 * mode FPSIMD, but the task will not be preemptible so setting
+		 * TIF_KERNEL_FPSTATE for those would be both wrong (as it
+		 * would mark the task context FPSIMD state as requiring a
+		 * context switch) and unnecessary.
+		 *
+		 * On PREEMPT_RT, softirqs are serviced from a separate thread,
+		 * which is scheduled as usual, and this guarantees that these
+		 * softirqs are not interrupting use of the FPSIMD in kernel
+		 * mode in task context. So in this case, setting the flag here
+		 * is always appropriate.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq())
+			set_thread_flag(TIF_KERNEL_FPSTATE);
+	}
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
 	fpsimd_flush_cpu_state();
+
+	put_cpu_fpsimd_context();
 }
 EXPORT_SYMBOL_GPL(kernel_neon_begin);
 
@@ -1885,7 +1923,16 @@ void kernel_neon_end(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	put_cpu_fpsimd_context();
+	/*
+	 * If we are returning from a nested use of kernel mode FPSIMD, restore
+	 * the task context kernel mode FPSIMD state. This can only happen when
+	 * running in softirq context on non-PREEMPT_RT.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() &&
+	    test_thread_flag(TIF_KERNEL_FPSTATE))
+		fpsimd_load_kernel_state(current);
+	else
+		clear_thread_flag(TIF_KERNEL_FPSTATE);
 }
 EXPORT_SYMBOL_GPL(kernel_neon_end);