[PATCH v4 2/3] Add preadv and pwritev system calls.

[Gerd Hoffmann <kraxel@redhat.com>]

This patch adds preadv and pwritev system calls.  These syscalls are a
pretty straightforward combination of pread and readv (same for write).
They are quite useful for doing vectored I/O in threaded applications.
Using lseek+readv instead opens race windows you'll have to plug with
locking.

Other systems have such system calls too, for example NetBSD, check
here: http://www.daemon-systems.org/man/preadv.2.html

The application-visible interface provided by glibc should look like
this to be compatible to the existing implementations in the *BSD family:

  ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset);
  ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset);

This prototype has one problem though:  On 32bit archs is the (64bit)
offset argument unaligned, which the syscall ABI of several archs
doesn't allow to do.  At least s390 needs a wrapper in glibc to handle
this.  As we'll need a wrappers in glibc anyway I've decided to push
problem to glibc entriely and use a syscall prototype which works
without arch-specific wrappers inside the kernel:  The offset argument
is explicitly splitted into two 32bit values.

The patch sports the actual system call implementation and the windup in
the x86 system call tables.  Other archs follow as separate patches.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
 arch/x86/ia32/ia32entry.S          |    2 +
 arch/x86/include/asm/unistd_32.h   |    2 +
 arch/x86/include/asm/unistd_64.h   |    4 ++
 arch/x86/kernel/syscall_table_32.S |    2 +
 fs/compat.c                        |   63 ++++++++++++++++++++++++++++++++++++
 fs/read_write.c                    |   50 ++++++++++++++++++++++++++++
 6 files changed, 123 insertions(+), 0 deletions(-)

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 256b00b..9a8501b 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -826,4 +826,6 @@ ia32_sys_call_table:
 	.quad sys_dup3			/* 330 */
 	.quad sys_pipe2
 	.quad sys_inotify_init1
+	.quad compat_sys_preadv
+	.quad compat_sys_pwritev
 ia32_syscall_end:
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index f2bba78..6e72d74 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -338,6 +338,8 @@
 #define __NR_dup3		330
 #define __NR_pipe2		331
 #define __NR_inotify_init1	332
+#define __NR_preadv		333
+#define __NR_pwritev		334
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index d2e415e..f818294 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3)
 __SYSCALL(__NR_pipe2, sys_pipe2)
 #define __NR_inotify_init1			294
 __SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_preadv				295
+__SYSCALL(__NR_preadv, sys_preadv)
+#define __NR_pwritev				296
+__SYSCALL(__NR_pwritev, sys_pwritev)
 
 
 #ifndef __NO_STUBS
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index d44395f..a1a5506 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -332,3 +332,5 @@ ENTRY(sys_call_table)
 	.long sys_dup3			/* 330 */
 	.long sys_pipe2
 	.long sys_inotify_init1
+	.long sys_preadv
+	.long sys_pwritev
diff --git a/fs/compat.c b/fs/compat.c
index aab2234..00e18aa 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1220,6 +1220,69 @@ out:
 	return ret;
 }
 
+asmlinkage ssize_t
+compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
+                  unsigned long vlen, u32 pos_high, u32 pos_low)
+{
+        loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	struct file *file;
+	ssize_t ret = -EBADF;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+
+	if (!(file->f_mode & FMODE_READ))
+		goto out;
+
+	ret = -EINVAL;
+	if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
+		goto out;
+
+	ret = compat_do_readv_writev(READ, file, vec, vlen, &pos);
+
+out:
+	if (ret > 0)
+		add_rchar(current, ret);
+	inc_syscr(current);
+	fput(file);
+	return ret;
+}
+
+asmlinkage ssize_t
+compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
+                   unsigned long vlen, u32 pos_high, u32 pos_low)
+{
+        loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	struct file *file;
+	ssize_t ret = -EBADF;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+	if (!(file->f_mode & FMODE_WRITE))
+		goto out;
+
+	ret = -EINVAL;
+	if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
+		goto out;
+
+	ret = compat_do_readv_writev(WRITE, file, vec, vlen, &pos);
+
+out:
+	if (ret > 0)
+		add_wchar(current, ret);
+	inc_syscw(current);
+	fput(file);
+	return ret;
+}
+
 asmlinkage long
 compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32,
 		    unsigned int nr_segs, unsigned int flags)
diff --git a/fs/read_write.c b/fs/read_write.c
index 969a6d9..27779d0 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -701,6 +701,56 @@ sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
 	return ret;
 }
 
+asmlinkage ssize_t sys_preadv(unsigned long fd, const struct iovec __user *vec,
+                              unsigned long vlen, u32 pos_high, u32 pos_low)
+{
+        loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	struct file *file;
+	ssize_t ret = -EBADF;
+	int fput_needed;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	file = fget_light(fd, &fput_needed);
+	if (file) {
+		ret = -ESPIPE;
+		if (file->f_mode & FMODE_PREAD)
+			ret = vfs_readv(file, vec, vlen, &pos);
+		fput_light(file, fput_needed);
+	}
+
+	if (ret > 0)
+		add_rchar(current, ret);
+	inc_syscr(current);
+	return ret;
+}
+
+asmlinkage ssize_t sys_pwritev(unsigned long fd, const struct iovec __user *vec,
+                               unsigned long vlen, u32 pos_high, u32 pos_low)
+{
+        loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	struct file *file;
+	ssize_t ret = -EBADF;
+	int fput_needed;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	file = fget_light(fd, &fput_needed);
+	if (file) {
+		ret = -ESPIPE;
+		if (file->f_mode & FMODE_PWRITE)
+			ret = vfs_writev(file, vec, vlen, &pos);
+		fput_light(file, fput_needed);
+	}
+
+	if (ret > 0)
+		add_wchar(current, ret);
+	inc_syscw(current);
+	return ret;
+}
+
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 			   size_t count, loff_t max)
 {
-- 
1.5.6.5