X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=fs%2Fread_write.c;h=c71dd10e58673ca418a3da89e2fc08555ff56fb1;hb=43bc926fffd92024b46cafaf7350d669ba9ca884;hp=c4c2bee373eddeab7b0d3bb9e110453a63ccd436;hpb=cee37fe97739d85991964371c1f3a745c00dd236;p=linux-2.6.git diff --git a/fs/read_write.c b/fs/read_write.c index c4c2bee37..c71dd10e5 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -10,15 +10,16 @@ #include #include #include -#include +#include #include #include #include +#include #include #include -struct file_operations generic_ro_fops = { +const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read = generic_file_read, .mmap = generic_file_readonly_mmap, @@ -32,7 +33,7 @@ loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) long long retval; struct inode *inode = file->f_mapping->host; - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); switch (origin) { case 2: offset += inode->i_size; @@ -48,7 +49,7 @@ loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) } retval = offset; } - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); return retval; } @@ -182,27 +183,48 @@ bad: } #endif +/* + * rw_verify_area doesn't like huge counts. We limit + * them to something that fits in "int" so that others + * won't have to do range checks all the time. + */ +#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count) { struct inode *inode; loff_t pos; - if (unlikely(count > file->f_maxcount)) + if (unlikely((ssize_t) count < 0)) goto Einval; pos = *ppos; if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) goto Einval; inode = file->f_dentry->d_inode; - if (inode->i_flock && MANDATORY_LOCK(inode)) - return locks_mandatory_area(read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count); - return 0; + if (unlikely(inode->i_flock && MANDATORY_LOCK(inode))) { + int retval = locks_mandatory_area( + read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, + inode, file, pos, count); + if (retval < 0) + return retval; + } + return count > MAX_RW_COUNT ? MAX_RW_COUNT : count; Einval: return -EINVAL; } +static void wait_on_retry_sync_kiocb(struct kiocb *iocb) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + if (!kiocbIsKicked(iocb)) + schedule(); + else + kiocbClearKicked(iocb); + __set_current_state(TASK_RUNNING); +} + ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; @@ -210,7 +232,10 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos); + while (-EIOCBRETRY == + (ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos))) + wait_on_retry_sync_kiocb(&kiocb); + if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -231,7 +256,8 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); - if (!ret) { + if (ret >= 0) { + count = ret; ret = security_file_permission (file, MAY_READ); if (!ret) { if (file->f_op->read) @@ -239,7 +265,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) else ret = do_sync_read(file, buf, count, pos); if (ret > 0) { - dnotify_parent(file->f_dentry, DN_ACCESS); + fsnotify_access(file->f_dentry); current->rchar += ret; } current->syscr++; @@ -258,7 +284,10 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos); + while (-EIOCBRETRY == + (ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos))) + wait_on_retry_sync_kiocb(&kiocb); + if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -279,7 +308,8 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); - if (!ret) { + if (ret >= 0) { + count = ret; ret = security_file_permission (file, MAY_WRITE); if (!ret) { if (file->f_op->write) @@ -287,7 +317,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ else ret = do_sync_write(file, buf, count, pos); if (ret > 0) { - dnotify_parent(file->f_dentry, DN_MODIFY); + fsnotify_modify(file->f_dentry); current->wchar += ret; } current->syscw++; @@ -344,6 +374,8 @@ asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t co return ret; } +EXPORT_SYMBOL_GPL(sys_write); + asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { @@ -440,7 +472,7 @@ static ssize_t do_readv_writev(int type, struct file *file, * verify all the pointers */ ret = -EINVAL; - if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0)) + if (nr_segs > UIO_MAXIOV) goto out; if (!file->f_op) goto out; @@ -481,6 +513,9 @@ static ssize_t do_readv_writev(int type, struct file *file, } ret = rw_verify_area(type, file, pos, tot_len); + if (ret < 0) + goto out; + ret = security_file_permission(file, type == READ ? MAY_READ : MAY_WRITE); if (ret) goto out; @@ -523,9 +558,12 @@ static ssize_t do_readv_writev(int type, struct file *file, out: if (iov != iovstack) kfree(iov); - if ((ret + (type == READ)) > 0) - dnotify_parent(file->f_dentry, - (type == READ) ? DN_ACCESS : DN_MODIFY); + if ((ret + (type == READ)) > 0) { + if (type == READ) + fsnotify_access(file->f_dentry); + else + fsnotify_modify(file->f_dentry); + } return ret; Efault: ret = -EFAULT; @@ -631,8 +669,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (!(in_file->f_mode & FMODE_PREAD)) goto fput_in; retval = rw_verify_area(READ, in_file, ppos, count); - if (retval) + if (retval < 0) goto fput_in; + count = retval; retval = security_file_permission (in_file, MAY_READ); if (retval) @@ -652,8 +691,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, goto fput_out; out_inode = out_file->f_dentry->d_inode; retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count); - if (retval) + if (retval < 0) goto fput_out; + count = retval; retval = security_file_permission (out_file, MAY_WRITE); if (retval)