x86/ioperm: Share I/O bitmap if identical

The I/O bitmap is duplicated on fork. That's wasting memory and slows down
fork. There is no point to do so. As long as the bitmap is not modified it
can be shared between threads and processes.

Add a refcount and just share it on fork. If a task modifies the bitmap
then it has to do the duplication if and only if it is shared.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andy Lutomirski <luto@kernel.org>

3 files changed, 50 insertions, 42 deletions

diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index 784a88edb25d..b664baadf736 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -2,15 +2,20 @@
 #ifndef _ASM_X86_IOBITMAP_H
 #define _ASM_X86_IOBITMAP_H
 
+#include <linux/refcount.h>
 #include <asm/processor.h>
 
 struct io_bitmap {
 	u64		sequence;
+	refcount_t	refcnt;
 	/* The maximum number of bytes to copy so all zero bits are covered */
 	unsigned int	max;
 	unsigned long	bitmap[IO_BITMAP_LONGS];
 };
 
+struct task_struct;
+
+void io_bitmap_share(struct task_struct *tsk);
 void io_bitmap_exit(void);
 
 void tss_update_io_bitmap(void);
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index f9fc69aeb033..f82ca1c62e3e 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -16,6 +16,17 @@
 
 static atomic64_t io_bitmap_sequence;
 
+void io_bitmap_share(struct task_struct *tsk)
+ {
+	/*
+	 * Take a refcount on current's bitmap. It can be used by
+	 * both tasks as long as none of them changes the bitmap.
+	 */
+	refcount_inc(&current->thread.io_bitmap->refcnt);
+	tsk->thread.io_bitmap = current->thread.io_bitmap;
+	set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
+}
+
 void io_bitmap_exit(void)
 {
 	struct io_bitmap *iobm = current->thread.io_bitmap;
@@ -25,7 +36,8 @@ void io_bitmap_exit(void)
 	preempt_disable();
 	tss_update_io_bitmap();
 	preempt_enable();
-	kfree(iobm);
+	if (iobm && refcount_dec_and_test(&iobm->refcnt))
+		kfree(iobm);
 }
 
 /*
@@ -58,9 +70,32 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 			return -ENOMEM;
 
 		memset(iobm->bitmap, 0xff, sizeof(iobm->bitmap));
+		refcount_set(&iobm->refcnt, 1);
+	}
+
+	/*
+	 * If the bitmap is not shared, then nothing can take a refcount as
+	 * current can obviously not fork at the same time. If it's shared
+	 * duplicate it and drop the refcount on the original one.
+	 */
+	if (refcount_read(&iobm->refcnt) > 1) {
+		iobm = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL);
+		if (!iobm)
+			return -ENOMEM;
+		refcount_set(&iobm->refcnt, 1);
+		io_bitmap_exit();
 	}
 
 	/*
+	 * Store the bitmap pointer (might be the same if the task already
+	 * head one). Must be done here so freeing the bitmap when all
+	 * permissions are dropped has the pointer set up.
+	 */
+	t->io_bitmap = iobm;
+	/* Mark it active for context switching and exit to user mode */
+	set_thread_flag(TIF_IO_BITMAP);
+
+	/*
 	 * Update the tasks bitmap. The update of the TSS bitmap happens on
 	 * exit to user mode. So this needs no protection.
 	 */
@@ -86,16 +121,11 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 
 	iobm->max = (max_long + 1) * sizeof(unsigned long);
 
-	/* Update the sequence number to force an update in switch_to() */
-	iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
-
 	/*
-	 * Store the bitmap pointer (might be the same if the task already
-	 * head one). Set the TIF flag, just in case this is the first
-	 * invocation.
+	 * Update the sequence number to force a TSS update on return to
+	 * user mode.
 	 */
-	t->io_bitmap = iobm;
-	set_thread_flag(TIF_IO_BITMAP);
+	iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7ba4d54aec17..0b19c137c442 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -122,37 +122,13 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
 		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
 }
 
-static inline int copy_io_bitmap(struct task_struct *tsk)
-{
-	struct io_bitmap *iobm = current->thread.io_bitmap;
-
-	if (likely(!test_tsk_thread_flag(current, TIF_IO_BITMAP)))
-		return 0;
-
-	tsk->thread.io_bitmap = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL);
-
-	if (!tsk->thread.io_bitmap)
-		return -ENOMEM;
-
-	set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
-	return 0;
-}
-
-static inline void free_io_bitmap(struct task_struct *tsk)
-{
-	if (tsk->thread.io_bitmap) {
-		kfree(tsk->thread.io_bitmap);
-		tsk->thread.io_bitmap = NULL;
-	}
-}
-
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		    unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct inactive_task_frame *frame;
 	struct fork_frame *fork_frame;
 	struct pt_regs *childregs;
-	int ret;
+	int ret = 0;
 
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
@@ -199,16 +175,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	task_user_gs(p) = get_user_gs(current_pt_regs());
 #endif
 
-	ret = copy_io_bitmap(p);
-	if (ret)
-		return ret;
-
 	/* Set a new TLS for the child thread? */
-	if (clone_flags & CLONE_SETTLS) {
+	if (clone_flags & CLONE_SETTLS)
 		ret = set_new_tls(p, tls);
-		if (ret)
-			free_io_bitmap(p);
-	}
+
+	if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
+		io_bitmap_share(p);
+
 	return ret;
 }