arm64: mte: introduce a per-CPU tag checking mode preference

Add a per-CPU sysfs node, mte_tcf_preferred, that allows the preferred
tag checking mode to be configured. The current possible values are
async and sync.

Link: https://linux-review.googlesource.com/id/I7493dcd533a2785a1437b16c3f6b50919f840854Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20210727205300.2554659-5-pcc@google.comAcked-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/kernel/mte.c

@@ -4,6 +4,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/prctl.h>
@@ -26,6 +27,8 @@ u64 gcr_kernel_excl __ro_after_init;
 
 static bool report_fault_once = true;
 
+static DEFINE_PER_CPU_READ_MOSTLY(u64, mte_tcf_preferred);
+
 #ifdef CONFIG_KASAN_HW_TAGS
 /* Whether the MTE asynchronous mode is enabled. */
 DEFINE_STATIC_KEY_FALSE(mte_async_mode);
@@ -195,11 +198,18 @@ void mte_check_tfsr_el1(void)
 
 static void mte_update_sctlr_user(struct task_struct *task)
 {
+	/*
+	 * This must be called with preemption disabled and can only be called
+	 * on the current or next task since the CPU must match where the thread
+	 * is going to run. The caller is responsible for calling
+	 * update_sctlr_el1() later in the same preemption disabled block.
+	 */
 	unsigned long sctlr = task->thread.sctlr_user;
-	unsigned long pref = MTE_CTRL_TCF_ASYNC;
 	unsigned long mte_ctrl = task->thread.mte_ctrl;
-	unsigned long resolved_mte_tcf = (mte_ctrl & pref) ? pref : mte_ctrl;
+	unsigned long pref, resolved_mte_tcf;
 
+	pref = __this_cpu_read(mte_tcf_preferred);
+	resolved_mte_tcf = (mte_ctrl & pref) ? pref : mte_ctrl;
 	sctlr &= ~SCTLR_EL1_TCF0_MASK;
 	if (resolved_mte_tcf & MTE_CTRL_TCF_ASYNC)
 		sctlr |= SCTLR_EL1_TCF0_ASYNC;
@@ -438,3 +448,54 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request,
 
 	return ret;
 }
+
+static ssize_t mte_tcf_preferred_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	switch (per_cpu(mte_tcf_preferred, dev->id)) {
+	case MTE_CTRL_TCF_ASYNC:
+		return sysfs_emit(buf, "async\n");
+	case MTE_CTRL_TCF_SYNC:
+		return sysfs_emit(buf, "sync\n");
+	default:
+		return sysfs_emit(buf, "???\n");
+	}
+}
+
+static ssize_t mte_tcf_preferred_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t count)
+{
+	u64 tcf;
+
+	if (sysfs_streq(buf, "async"))
+		tcf = MTE_CTRL_TCF_ASYNC;
+	else if (sysfs_streq(buf, "sync"))
+		tcf = MTE_CTRL_TCF_SYNC;
+	else
+		return -EINVAL;
+
+	device_lock(dev);
+	per_cpu(mte_tcf_preferred, dev->id) = tcf;
+	device_unlock(dev);
+
+	return count;
+}
+static DEVICE_ATTR_RW(mte_tcf_preferred);
+
+static int register_mte_tcf_preferred_sysctl(void)
+{
+	unsigned int cpu;
+
+	if (!system_supports_mte())
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		per_cpu(mte_tcf_preferred, cpu) = MTE_CTRL_TCF_ASYNC;
+		device_create_file(get_cpu_device(cpu),
+				   &dev_attr_mte_tcf_preferred);
+	}
+
+	return 0;
+}
+subsys_initcall(register_mte_tcf_preferred_sysctl);