core, x86: Add user return notifiers

Add a general per-cpu notifier that is called whenever the kernel is
about to return to userspace.  The notifier uses a thread_info flag
and existing checks, so there is no impact on user return or context
switch fast paths.

This will be used initially to speed up KVM task switching by lazily
updating MSRs.
Signed-off-by: NAvi Kivity <avi@redhat.com>
LKML-Reference: <1253342422-13811-1-git-send-email-avi@redhat.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

arch/Kconfig

@@ -83,6 +83,13 @@ config KRETPROBES
 	def_bool y
 	depends on KPROBES && HAVE_KRETPROBES
 
+config USER_RETURN_NOTIFIER
+	bool
+	depends on HAVE_USER_RETURN_NOTIFIER
+	help
+	  Provide a kernel-internal notification when a cpu is about to
+	  switch to user mode.
+
 config HAVE_IOREMAP_PROT
 	bool
 
@@ -126,4 +133,7 @@ config HAVE_DMA_API_DEBUG
 config HAVE_DEFAULT_NO_SPIN_MUTEXES
 	bool
 
+config HAVE_USER_RETURN_NOTIFIER
+	bool
+
 source "kernel/gcov/Kconfig"

arch/x86/Kconfig

@@ -50,6 +50,7 @@ config X86
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
 	select HAVE_ARCH_KMEMCHECK
+	select HAVE_USER_RETURN_NOTIFIER
 
 config OUTPUT_FORMAT
 	string

arch/x86/include/asm/thread_info.h

@@ -83,6 +83,7 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
+#define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* 32bit process */
 #define TIF_FORK		18	/* ret_from_fork */
@@ -107,6 +108,7 @@ struct thread_info {
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
+#define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
@@ -142,13 +144,14 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
+	(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |	\
+	 _TIF_USER_RETURN_NOTIFY)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
 	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
 
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
 
 #define PREEMPT_ACTIVE		0x10000000

arch/x86/kernel/process.c

@@ -9,6 +9,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <linux/random.h>
+#include <linux/user-return-notifier.h>
 #include <trace/events/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
@@ -224,6 +225,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 */
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
+	propagate_user_return_notify(prev_p, next_p);
 }
 
 int sys_fork(struct pt_regs *regs)

arch/x86/kernel/signal.c

@@ -19,6 +19,7 @@
 #include <linux/stddef.h>
 #include <linux/personality.h>
 #include <linux/uaccess.h>
+#include <linux/user-return-notifier.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -872,6 +873,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		if (current->replacement_session_keyring)
 			key_replace_session_keyring();
 	}
+	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
+		fire_user_return_notifiers();
 
 #ifdef CONFIG_X86_32
 	clear_thread_flag(TIF_IRET);

include/linux/user-return-notifier.h

+#ifndef _LINUX_USER_RETURN_NOTIFIER_H
+#define _LINUX_USER_RETURN_NOTIFIER_H
+
+#ifdef CONFIG_USER_RETURN_NOTIFIER
+
+#include <linux/list.h>
+#include <linux/sched.h>
+
+struct user_return_notifier {
+	void (*on_user_return)(struct user_return_notifier *urn);
+	struct hlist_node link;
+};
+
+
+void user_return_notifier_register(struct user_return_notifier *urn);
+void user_return_notifier_unregister(struct user_return_notifier *urn);
+
+static inline void propagate_user_return_notify(struct task_struct *prev,
+						struct task_struct *next)
+{
+	if (test_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY)) {
+		clear_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY);
+		set_tsk_thread_flag(next, TIF_USER_RETURN_NOTIFY);
+	}
+}
+
+void fire_user_return_notifiers(void);
+
+#else
+
+struct user_return_notifier {};
+
+static inline void propagate_user_return_notify(struct task_struct *prev,
+						struct task_struct *next)
+{
+}
+
+static inline void fire_user_return_notifiers(void) {}
+
+#endif
+
+#endif

kernel/user-return-notifier.c

+
+#include <linux/user-return-notifier.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
+
+#define URN_LIST_HEAD per_cpu(return_notifier_list, raw_smp_processor_id())
+
+/*
+ * Request a notification when the current cpu returns to userspace.  Must be
+ * called in atomic context.  The notifier will also be called in atomic
+ * context.
+ */
+void user_return_notifier_register(struct user_return_notifier *urn)
+{
+	set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+	hlist_add_head(&urn->link, &URN_LIST_HEAD);
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_register);
+
+/*
+ * Removes a registered user return notifier.  Must be called from atomic
+ * context, and from the same cpu registration occured in.
+ */
+void user_return_notifier_unregister(struct user_return_notifier *urn)
+{
+	hlist_del(&urn->link);
+	if (hlist_empty(&URN_LIST_HEAD))
+		clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
+
+/* Calls registered user return notifiers */
+void fire_user_return_notifiers(void)
+{
+	struct user_return_notifier *urn;
+	struct hlist_node *tmp1, *tmp2;
+	struct hlist_head *head;
+
+	head = &get_cpu_var(return_notifier_list);
+	hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link)
+		urn->on_user_return(urn);
+	put_cpu_var();
+}