[PATCH] splice: add support for sys_tee()

Basically an in-kernel implementation of tee, which uses splice and the
pipe buffers as an intelligent way to pass data around by reference.

Where the user space tee consumes the input and produces a stdout and
file output, this syscall merely duplicates the data inside a pipe to
another pipe. No data is copied, the output just grabs a reference to the
input pipe data.

Signed-off-by: Jens Axboe <axboe@suse.de>
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 4f58b9c..f48bef1 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -314,3 +314,4 @@
 	.long sys_get_robust_list
 	.long sys_splice
 	.long sys_sync_file_range
+	.long sys_tee			/* 315 */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 6e16f6b..e307988 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1609,5 +1609,6 @@
 	data8 sys_set_robust_list
 	data8 sys_get_robust_list
 	data8 sys_sync_file_range		// 1300
+	data8 sys_tee
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 1424eab..a14c964 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -323,3 +323,4 @@
 COMPAT_SYS(ppoll)
 SYSCALL(unshare)
 SYSCALL(splice)
+SYSCALL(tee)
diff --git a/fs/pipe.c b/fs/pipe.c
index e984beb..7fefb10 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -131,12 +131,19 @@
 	return 0;
 }
 
+static void anon_pipe_buf_get(struct pipe_inode_info *info,
+			      struct pipe_buffer *buf)
+{
+	page_cache_get(buf->page);
+}
+
 static struct pipe_buf_operations anon_pipe_buf_ops = {
 	.can_merge = 1,
 	.map = anon_pipe_buf_map,
 	.unmap = anon_pipe_buf_unmap,
 	.release = anon_pipe_buf_release,
 	.steal = anon_pipe_buf_steal,
+	.get = anon_pipe_buf_get,
 };
 
 static ssize_t
diff --git a/fs/splice.c b/fs/splice.c
index 5d3eda6..8d57e89 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -125,12 +125,19 @@
 	kunmap(buf->page);
 }
 
+static void page_cache_pipe_buf_get(struct pipe_inode_info *info,
+				    struct pipe_buffer *buf)
+{
+	page_cache_get(buf->page);
+}
+
 static struct pipe_buf_operations page_cache_pipe_buf_ops = {
 	.can_merge = 0,
 	.map = page_cache_pipe_buf_map,
 	.unmap = page_cache_pipe_buf_unmap,
 	.release = page_cache_pipe_buf_release,
 	.steal = page_cache_pipe_buf_steal,
+	.get = page_cache_pipe_buf_get,
 };
 
 /*
@@ -963,3 +970,182 @@
 
 	return error;
 }
+
+/*
+ * Link contents of ipipe to opipe.
+ */
+static int link_pipe(struct pipe_inode_info *ipipe,
+		     struct pipe_inode_info *opipe,
+		     size_t len, unsigned int flags)
+{
+	struct pipe_buffer *ibuf, *obuf;
+	int ret = 0, do_wakeup = 0, i;
+
+	/*
+	 * Potential ABBA deadlock, work around it by ordering lock
+	 * grabbing by inode address. Otherwise two different processes
+	 * could deadlock (one doing tee from A -> B, the other from B -> A).
+	 */
+	if (ipipe->inode < opipe->inode) {
+		mutex_lock(&ipipe->inode->i_mutex);
+		mutex_lock(&opipe->inode->i_mutex);
+	} else {
+		mutex_lock(&opipe->inode->i_mutex);
+		mutex_lock(&ipipe->inode->i_mutex);
+	}
+
+	for (i = 0;; i++) {
+		if (!opipe->readers) {
+			send_sig(SIGPIPE, current, 0);
+			if (!ret)
+				ret = -EPIPE;
+			break;
+		}
+		if (ipipe->nrbufs - i) {
+			ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
+
+			/*
+			 * If we have room, fill this buffer
+			 */
+			if (opipe->nrbufs < PIPE_BUFFERS) {
+				int nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);
+
+				/*
+				 * Get a reference to this pipe buffer,
+				 * so we can copy the contents over.
+				 */
+				ibuf->ops->get(ipipe, ibuf);
+
+				obuf = opipe->bufs + nbuf;
+				*obuf = *ibuf;
+
+				if (obuf->len > len)
+					obuf->len = len;
+
+				opipe->nrbufs++;
+				do_wakeup = 1;
+				ret += obuf->len;
+				len -= obuf->len;
+
+				if (!len)
+					break;
+				if (opipe->nrbufs < PIPE_BUFFERS)
+					continue;
+			}
+
+			/*
+			 * We have input available, but no output room.
+			 * If we already copied data, return that.
+			 */
+			if (flags & SPLICE_F_NONBLOCK) {
+				if (!ret)
+					ret = -EAGAIN;
+				break;
+			}
+			if (signal_pending(current)) {
+				if (!ret)
+					ret = -ERESTARTSYS;
+				break;
+			}
+			if (do_wakeup) {
+				smp_mb();
+				if (waitqueue_active(&opipe->wait))
+					wake_up_interruptible(&opipe->wait);
+				kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
+				do_wakeup = 0;
+			}
+
+			opipe->waiting_writers++;
+			pipe_wait(opipe);
+			opipe->waiting_writers--;
+			continue;
+		}
+
+		/*
+		 * No input buffers, do the usual checks for available
+		 * writers and blocking and wait if necessary
+		 */
+		if (!ipipe->writers)
+			break;
+		if (!ipipe->waiting_writers) {
+			if (ret)
+				break;
+		}
+		if (flags & SPLICE_F_NONBLOCK) {
+			if (!ret)
+				ret = -EAGAIN;
+			break;
+		}
+		if (signal_pending(current)) {
+			if (!ret)
+				ret = -ERESTARTSYS;
+			break;
+		}
+
+		if (waitqueue_active(&ipipe->wait))
+			wake_up_interruptible_sync(&ipipe->wait);
+		kill_fasync(&ipipe->fasync_writers, SIGIO, POLL_OUT);
+
+		pipe_wait(ipipe);
+	}
+
+	mutex_unlock(&ipipe->inode->i_mutex);
+	mutex_unlock(&opipe->inode->i_mutex);
+
+	if (do_wakeup) {
+		smp_mb();
+		if (waitqueue_active(&opipe->wait))
+			wake_up_interruptible(&opipe->wait);
+		kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
+	}
+
+	return ret;
+}
+
+/*
+ * This is a tee(1) implementation that works on pipes. It doesn't copy
+ * any data, it simply references the 'in' pages on the 'out' pipe.
+ * The 'flags' used are the SPLICE_F_* variants, currently the only
+ * applicable one is SPLICE_F_NONBLOCK.
+ */
+static long do_tee(struct file *in, struct file *out, size_t len,
+		   unsigned int flags)
+{
+	struct pipe_inode_info *ipipe = in->f_dentry->d_inode->i_pipe;
+	struct pipe_inode_info *opipe = out->f_dentry->d_inode->i_pipe;
+
+	/*
+	 * Link ipipe to the two output pipes, consuming as we go along.
+	 */
+	if (ipipe && opipe)
+		return link_pipe(ipipe, opipe, len, flags);
+
+	return -EINVAL;
+}
+
+asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags)
+{
+	struct file *in;
+	int error, fput_in;
+
+	if (unlikely(!len))
+		return 0;
+
+	error = -EBADF;
+	in = fget_light(fdin, &fput_in);
+	if (in) {
+		if (in->f_mode & FMODE_READ) {
+			int fput_out;
+			struct file *out = fget_light(fdout, &fput_out);
+
+			if (out) {
+				if (out->f_mode & FMODE_WRITE)
+					error = do_tee(in, out, len, flags);
+				fput_light(out, fput_out);
+			}
+		}
+ 		fput_light(in, fput_in);
+ 	}
+
+	return error;
+}
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index 6a8dd83..d81d6cf 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -320,8 +320,9 @@
 #define __NR_get_robust_list	312
 #define __NR_splice		313
 #define __NR_sync_file_range	314
+#define __NR_tee		315
 
-#define NR_syscalls 315
+#define NR_syscalls 316
 
 /*
  * user-visible error numbers are in the range -1 - -128: see
diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h
index 1c749ac..a40ebec 100644
--- a/include/asm-ia64/unistd.h
+++ b/include/asm-ia64/unistd.h
@@ -289,12 +289,13 @@
 #define __NR_set_robust_list		1298
 #define __NR_get_robust_list		1299
 #define __NR_sync_file_range		1300
+#define __NR_tee			1301
 
 #ifdef __KERNEL__
 
 #include <linux/config.h>
 
-#define NR_syscalls			277 /* length of syscall table */
+#define NR_syscalls			278 /* length of syscall table */
 
 #define __ARCH_WANT_SYS_RT_SIGACTION
 
diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h
index 536ba08..c612f1a 100644
--- a/include/asm-powerpc/unistd.h
+++ b/include/asm-powerpc/unistd.h
@@ -302,8 +302,9 @@
 #define __NR_ppoll		281
 #define __NR_unshare		282
 #define __NR_splice		283
+#define __NR_tee		284
 
-#define __NR_syscalls		284
+#define __NR_syscalls		285
 
 #ifdef __KERNEL__
 #define __NR__exit __NR_exit
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index f21ff2c..d86494e 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -611,8 +611,10 @@
 __SYSCALL(__NR_get_robust_list, sys_get_robust_list)
 #define __NR_splice		275
 __SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee		276
+__SYSCALL(__NR_tee, sys_tee)
 
-#define __NR_syscall_max __NR_splice
+#define __NR_syscall_max __NR_tee
 
 #ifndef __NO_STUBS
 
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 123a7c2..ef7f33c 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -21,6 +21,7 @@
 	void (*unmap)(struct pipe_inode_info *, struct pipe_buffer *);
 	void (*release)(struct pipe_inode_info *, struct pipe_buffer *);
 	int (*steal)(struct pipe_inode_info *, struct pipe_buffer *);
+	void (*get)(struct pipe_inode_info *, struct pipe_buffer *);
 };
 
 struct pipe_inode_info {
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index f001bad..d3ebc0e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -574,6 +574,8 @@
 			   int fd_out, loff_t __user *off_out,
 			   size_t len, unsigned int flags);
 
+asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags);
+
 asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
 					unsigned int flags);