vfs: atomic f_pos accesses as per POSIX

[~andy/linux] / fs / read_write.c

diff --git a/fs/read_write.c b/fs/read_write.c
index edc5746a902a090ce4dbda6b8b1205e729dff5b3..932bb3414a967a401edb671c9fc526b0f9e2dd55 100644 (file)
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -264,10 +264,36 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
 }
 EXPORT_SYMBOL(vfs_llseek);
 
+/*
+ * We only lock f_pos if we have threads or if the file might be
+ * shared with another process. In both cases we'll have an elevated
+ * file count (done either by fdget() or by fork()).
+ */
+static inline struct fd fdget_pos(int fd)
+{
+       struct fd f = fdget(fd);
+       struct file *file = f.file;
+
+       if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
+               if (file_count(file) > 1) {
+                       f.flags |= FDPUT_POS_UNLOCK;
+                       mutex_lock(&file->f_pos_lock);
+               }
+       }
+       return f;
+}
+
+static inline void fdput_pos(struct fd f)
+{
+       if (f.flags & FDPUT_POS_UNLOCK)
+               mutex_unlock(&f.file->f_pos_lock);
+       fdput(f);
+}
+
 SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
 {
        off_t retval;
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        if (!f.file)
                return -EBADF;
 
@@ -278,7 +304,7 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
                if (res != (loff_t)retval)
                        retval = -EOVERFLOW;    /* LFS: should only happen on 32 bit platforms */
        }
-       fdput(f);
+       fdput_pos(f);
        return retval;
 }
 
@@ -498,7 +524,7 @@ static inline void file_pos_write(struct file *file, loff_t pos)
 
 SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 {
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        ssize_t ret = -EBADF;
 
        if (f.file) {
@@ -506,7 +532,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
                ret = vfs_read(f.file, buf, count, &pos);
                if (ret >= 0)
                        file_pos_write(f.file, pos);
-               fdput(f);
+               fdput_pos(f);
        }
        return ret;
 }
@@ -514,7 +540,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
                size_t, count)
 {
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        ssize_t ret = -EBADF;
 
        if (f.file) {
@@ -522,7 +548,7 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
                ret = vfs_write(f.file, buf, count, &pos);
                if (ret >= 0)
                        file_pos_write(f.file, pos);
-               fdput(f);
+               fdput_pos(f);
        }
 
        return ret;
@@ -797,7 +823,7 @@ EXPORT_SYMBOL(vfs_writev);
 SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
                unsigned long, vlen)
 {
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        ssize_t ret = -EBADF;
 
        if (f.file) {
@@ -805,7 +831,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
                ret = vfs_readv(f.file, vec, vlen, &pos);
                if (ret >= 0)
                        file_pos_write(f.file, pos);
-               fdput(f);
+               fdput_pos(f);
        }
 
        if (ret > 0)
@@ -817,7 +843,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
                unsigned long, vlen)
 {
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        ssize_t ret = -EBADF;
 
        if (f.file) {
@@ -825,7 +851,7 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
                ret = vfs_writev(f.file, vec, vlen, &pos);
                if (ret >= 0)
                        file_pos_write(f.file, pos);
-               fdput(f);
+               fdput_pos(f);
        }
 
        if (ret > 0)
@@ -968,7 +994,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
                const struct compat_iovec __user *,vec,
                compat_ulong_t, vlen)
 {
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        ssize_t ret;
        loff_t pos;
 
@@ -978,7 +1004,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
        ret = compat_readv(f.file, vec, vlen, &pos);
        if (ret >= 0)
                f.file->f_pos = pos;
-       fdput(f);
+       fdput_pos(f);
        return ret;
 }
 
@@ -1035,7 +1061,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
                const struct compat_iovec __user *, vec,
                compat_ulong_t, vlen)
 {
-       struct fd f = fdget(fd);
+       struct fd f = fdget_pos(fd);
        ssize_t ret;
        loff_t pos;
 
@@ -1045,7 +1071,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
        ret = compat_writev(f.file, vec, vlen, &pos);
        if (ret >= 0)
                f.file->f_pos = pos;
-       fdput(f);
+       fdput_pos(f);
        return ret;
 }