aboutsummaryrefslogtreecommitdiff
path: root/fs/open.c
diff options
context:
space:
mode:
authorAmit Arora <aarora@in.ibm.com>2007-07-17 21:42:44 -0400
committerTheodore Ts'o <tytso@mit.edu>2007-07-17 21:42:44 -0400
commit97ac73506c0ba93f30239bb57b4cfc5d73e68a62 (patch)
tree4d02848d6c792a70b413deadcaffd7bf8c8d61de /fs/open.c
parentcb32da0416b823b7f4b65e7e85d6cba16ca4d1e1 (diff)
sys_fallocate() implementation on i386, x86_64 and powerpc
fallocate() is a new system call being proposed here which will allow applications to preallocate space to any file(s) in a file system. Each file system implementation that wants to use this feature will need to support an inode operation called ->fallocate(). Applications can use this feature to avoid fragmentation to certain level and thus get faster access speed. With preallocation, applications also get a guarantee of space for particular file(s) - even if later the the system becomes full. Currently, glibc provides an interface called posix_fallocate() which can be used for similar cause. Though this has the advantage of working on all file systems, but it is quite slow (since it writes zeroes to each block that has to be preallocated). Without a doubt, file systems can do this more efficiently within the kernel, by implementing the proposed fallocate() system call. It is expected that posix_fallocate() will be modified to call this new system call first and incase the kernel/filesystem does not implement it, it should fall back to the current implementation of writing zeroes to the new blocks. ToDos: 1. Implementation on other architectures (other than i386, x86_64, and ppc). Patches for s390(x) and ia64 are already available from previous posts, but it was decided that they should be added later once fallocate is in the mainline. Hence not including those patches in this take. 2. Changes to glibc, a) to support fallocate() system call b) to make posix_fallocate() and posix_fallocate64() call fallocate() Signed-off-by: Amit Arora <aarora@in.ibm.com>
Diffstat (limited to 'fs/open.c')
-rw-r--r--fs/open.c59
1 files changed, 59 insertions, 0 deletions
diff --git a/fs/open.c b/fs/open.c
index be6a457f422..a6b054edacb 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -26,6 +26,7 @@
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
+#include <linux/falloc.h>
int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
@@ -352,6 +353,64 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length)
}
#endif
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len)
+{
+ struct file *file;
+ struct inode *inode;
+ long ret = -EINVAL;
+
+ if (offset < 0 || len <= 0)
+ goto out;
+
+ /* Return error if mode is not supported */
+ ret = -EOPNOTSUPP;
+ if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
+ goto out;
+
+ ret = -EBADF;
+ file = fget(fd);
+ if (!file)
+ goto out;
+ if (!(file->f_mode & FMODE_WRITE))
+ goto out_fput;
+ /*
+ * Revalidate the write permissions, in case security policy has
+ * changed since the files were opened.
+ */
+ ret = security_file_permission(file, MAY_WRITE);
+ if (ret)
+ goto out_fput;
+
+ inode = file->f_path.dentry->d_inode;
+
+ ret = -ESPIPE;
+ if (S_ISFIFO(inode->i_mode))
+ goto out_fput;
+
+ ret = -ENODEV;
+ /*
+ * Let individual file system decide if it supports preallocation
+ * for directories or not.
+ */
+ if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
+ goto out_fput;
+
+ ret = -EFBIG;
+ /* Check for wrap through zero too */
+ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
+ goto out_fput;
+
+ if (inode->i_op && inode->i_op->fallocate)
+ ret = inode->i_op->fallocate(inode, mode, offset, len);
+ else
+ ret = -ENOSYS;
+
+out_fput:
+ fput(file);
+out:
+ return ret;
+}
+
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and