[PATCH v7 2/5] vfs: Define new syscalls preadv2,pwritev2

From: Milosz Tanski
Date: Mon Mar 16 2015 - 14:29:22 EST

Next message: Laura Abbott: "[PATCH] mm/page_alloc: Call kernel_map_pages in unset_migrateype_isolate"
Previous message: Milosz Tanski: "[PATCH v7 0/5] vfs: Non-blockling buffered fs read (page cache only)"
In reply to: Milosz Tanski: "[PATCH v7 3/5] x86: wire up preadv2 and pwritev2"
Next in thread: Milosz Tanski: "[PATCH] Add preadv2/pwritev2 documentation."
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

New syscalls that take an flag argument. This change does not add any specific
flags.

Signed-off-by: Milosz Tanski <milosz@xxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
---
fs/read_write.c | 172 ++++++++++++++++++++++++++++++--------
include/linux/compat.h | 6 ++
include/linux/syscalls.h | 6 ++
include/uapi/asm-generic/unistd.h | 6 +-
mm/filemap.c | 5 +-
5 files changed, 156 insertions(+), 39 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index b53bb59..e91f46e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -924,6 +924,8 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
return -EBADF;
if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
+ if (flags & ~0)
+ return -EINVAL;

return do_readv_writev(READ, file, vec, vlen, pos, flags);
}
@@ -937,21 +939,23 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
+ if (flags & ~0)
+ return -EINVAL;

return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
}

EXPORT_SYMBOL(vfs_writev);

-SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen)
+static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;

if (f.file) {
loff_t pos = file_pos_read(f.file);
- ret = vfs_readv(f.file, vec, vlen, &pos, 0);
+ ret = vfs_readv(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
@@ -963,15 +967,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
return ret;
}

-SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen)
+static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;

if (f.file) {
loff_t pos = file_pos_read(f.file);
- ret = vfs_writev(f.file, vec, vlen, &pos, 0);
+ ret = vfs_writev(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
@@ -989,10 +993,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
}

-SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, loff_t pos, int flags)
{
- loff_t pos = pos_from_hilo(pos_h, pos_l);
struct fd f;
ssize_t ret = -EBADF;

@@ -1003,7 +1006,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
- ret = vfs_readv(f.file, vec, vlen, &pos, 0);
+ ret = vfs_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
}

@@ -1013,10 +1016,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
return ret;
}

-SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, loff_t pos, int flags)
{
- loff_t pos = pos_from_hilo(pos_h, pos_l);
struct fd f;
ssize_t ret = -EBADF;

@@ -1027,7 +1029,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
- ret = vfs_writev(f.file, vec, vlen, &pos, 0);
+ ret = vfs_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
}

@@ -1037,11 +1039,63 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
return ret;
}

+SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen)
+{
+ return do_readv(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen)
+{
+ return do_writev(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ return do_preadv(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+ int, flags)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ if (pos == -1)
+ return do_readv(fd, vec, vlen, flags);
+
+ return do_preadv(fd, vec, vlen, pos, flags);
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ return do_pwritev(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+ int, flags)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ if (pos == -1)
+ return do_writev(fd, vec, vlen, flags);
+
+ return do_pwritev(fd, vec, vlen, pos, flags);
+}
+
#ifdef CONFIG_COMPAT

static ssize_t compat_do_readv_writev(int type, struct file *file,
const struct compat_iovec __user *uvector,
- unsigned long nr_segs, loff_t *pos)
+ unsigned long nr_segs, loff_t *pos, int flags)
{
compat_ssize_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
@@ -1075,7 +1129,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,

if (iter_fn)
ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
- pos, iter_fn, 0);
+ pos, iter_fn, flags);
else if (fnv)
ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
pos, fnv);
@@ -1099,7 +1153,7 @@ out:

static size_t compat_readv(struct file *file,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t *pos)
+ unsigned long vlen, loff_t *pos, int flags)
{
ssize_t ret = -EBADF;

@@ -1109,8 +1163,10 @@ static size_t compat_readv(struct file *file,
ret = -EINVAL;
if (!(file->f_mode & FMODE_CAN_READ))
goto out;
+ if (flags & ~0)
+ goto out;

- ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
+ ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags);

out:
if (ret > 0)
@@ -1119,9 +1175,9 @@ out:
return ret;
}

-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
- const struct compat_iovec __user *,vec,
- compat_ulong_t, vlen)
+static size_t __compat_sys_readv(compat_ulong_t fd,
+ const struct compat_iovec __user *vec,
+ compat_ulong_t vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret;
@@ -1130,16 +1186,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
- ret = compat_readv(f.file, vec, vlen, &pos);
+ ret = compat_readv(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
f.file->f_pos = pos;
fdput_pos(f);
return ret;
+
+}
+
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
+ const struct compat_iovec __user *,vec,
+ compat_ulong_t, vlen)
+{
+ return __compat_sys_readv(fd, vec, vlen, 0);
}

static long __compat_sys_preadv64(unsigned long fd,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t pos)
+ unsigned long vlen, loff_t pos, int flags)
{
struct fd f;
ssize_t ret;
@@ -1151,7 +1215,7 @@ static long __compat_sys_preadv64(unsigned long fd,
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
- ret = compat_readv(f.file, vec, vlen, &pos);
+ ret = compat_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
return ret;
}
@@ -1161,7 +1225,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
- return __compat_sys_preadv64(fd, vec, vlen, pos);
+ return __compat_sys_preadv64(fd, vec, vlen, pos, 0);
}
#endif

@@ -1171,12 +1235,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;

- return __compat_sys_preadv64(fd, vec, vlen, pos);
+ return __compat_sys_preadv64(fd, vec, vlen, pos, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
+ const struct compat_iovec __user *,vec,
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
+ int, flags)
+{
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+ if (pos == -1)
+ return __compat_sys_readv(fd, vec, vlen, flags);
+
+ return __compat_sys_preadv64(fd, vec, vlen, pos, flags);
}

static size_t compat_writev(struct file *file,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t *pos)
+ unsigned long vlen, loff_t *pos, int flags)
{
ssize_t ret = -EBADF;

@@ -1186,8 +1263,10 @@ static size_t compat_writev(struct file *file,
ret = -EINVAL;
if (!(file->f_mode & FMODE_CAN_WRITE))
goto out;
+ if (flags & ~0)
+ goto out;

- ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
+ ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, flags);

out:
if (ret > 0)
@@ -1196,9 +1275,9 @@ out:
return ret;
}

-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
- const struct compat_iovec __user *, vec,
- compat_ulong_t, vlen)
+static size_t __compat_sys_writev(compat_ulong_t fd,
+ const struct compat_iovec __user* vec,
+ compat_ulong_t vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret;
@@ -1207,28 +1286,36 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
- ret = compat_writev(f.file, vec, vlen, &pos);
+ ret = compat_writev(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
f.file->f_pos = pos;
fdput_pos(f);
return ret;
}

+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
+ const struct compat_iovec __user *, vec,
+ compat_ulong_t, vlen)
+{
+ return __compat_sys_writev(fd, vec, vlen, 0);
+}
+
static long __compat_sys_pwritev64(unsigned long fd,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t pos)
+ unsigned long vlen, loff_t pos, int flags)
{
struct fd f;
ssize_t ret;

if (pos < 0)
return -EINVAL;
+
f = fdget(fd);
if (!f.file)
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
- ret = compat_writev(f.file, vec, vlen, &pos);
+ ret = compat_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
return ret;
}
@@ -1238,7 +1325,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
- return __compat_sys_pwritev64(fd, vec, vlen, pos);
+ return __compat_sys_pwritev64(fd, vec, vlen, pos, 0);
}
#endif

@@ -1248,8 +1335,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;

- return __compat_sys_pwritev64(fd, vec, vlen, pos);
+ return __compat_sys_pwritev64(fd, vec, vlen, pos, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
+ const struct compat_iovec __user *,vec,
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags)
+{
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+ if (pos == -1)
+ return __compat_sys_writev(fd, vec, vlen, flags);
+
+ return __compat_sys_pwritev64(fd, vec, vlen, pos, flags);
}
+
#endif

static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index ab25814..6e4be9e 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -340,6 +340,12 @@ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
const struct compat_iovec __user *vec,
compat_ulong_t vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd,
+ const struct compat_iovec __user *vec,
+ compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags);
+asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
+ const struct compat_iovec __user *vec,
+ compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags);

#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
asmlinkage long compat_sys_preadv64(unsigned long fd,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 76d1e38..f25ed7b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -575,8 +575,14 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
size_t count, loff_t pos);
asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
+asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, unsigned long pos_l, unsigned long pos_h,
+ int flags);
asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
+asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, unsigned long pos_l, unsigned long pos_h,
+ int flags);
asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode);
asmlinkage long sys_chdir(const char __user *filename);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index e016bd9..4d2c4c5 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -213,6 +213,10 @@ __SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
#define __NR_pwritev 70
__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+#define __NR_preadv2 282
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 283
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)

/* fs/sendfile.c */
#define __NR3264_sendfile 71
@@ -711,7 +715,7 @@ __SYSCALL(__NR_bpf, sys_bpf)
__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)

#undef __NR_syscalls
-#define __NR_syscalls 282
+#define __NR_syscalls 284

/*
* All syscalls below here should go away really,
diff --git a/mm/filemap.c b/mm/filemap.c
index ad72420..7865f64 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1453,6 +1453,7 @@ static void shrink_readahead_size_eio(struct file *filp,
* @ppos: current file position
* @iter: data destination
* @written: already copied
+ * @flags: optional flags
*
* This is a generic file read routine, and uses the
* mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1461,7 +1462,7 @@ static void shrink_readahead_size_eio(struct file *filp,
* of the logic when it comes to error handling etc.
*/
static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
- struct iov_iter *iter, ssize_t written)
+ struct iov_iter *iter, ssize_t written, int flags)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
@@ -1732,7 +1733,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
}
}

- retval = do_generic_file_read(file, ppos, iter, retval);
+ retval = do_generic_file_read(file, ppos, iter, retval, iocb->ki_rwflags);
out:
return retval;
}
--
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Laura Abbott: "[PATCH] mm/page_alloc: Call kernel_map_pages in unset_migrateype_isolate"
Previous message: Milosz Tanski: "[PATCH v7 0/5] vfs: Non-blockling buffered fs read (page cache only)"
In reply to: Milosz Tanski: "[PATCH v7 3/5] x86: wire up preadv2 and pwritev2"
Next in thread: Milosz Tanski: "[PATCH] Add preadv2/pwritev2 documentation."
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]