This patch implements sys_fallocate() and adds support on i386, x86_64
and powerpc platforms.
Changelog:
---------
Note: The changes below are from the initial post (dated 26th April,
2007) and _not_ from TAKE2. The only difference from TAKE2 is the kernel
version on which this patch is based. TAKE2 was based on 2.6.21 and this
is based on 2.6.22-rc1.
Following changes were made to the previous version:
1) Added description before sys_fallocate() definition.
2) Return EINVAL for len<=0 (With new draft that Ulrich pointed to,
posix_fallocate should return EINVAL for len <= 0.
3) Return EOPNOTSUPP if mode is not one of FA_ALLOCATE or FA_DEALLOCATE
4) Do not return ENODEV for dirs (let individual file systems decide if
they want to support preallocation to directories or not.
5) Check for wrap through zero.
6) Update c/mtime if fallocate() succeeds.
7) Added mode descriptions in fs.h
8) Added variable names to function definition (fallocate inode op)
Here is the new patch:
Signed-off-by: Amit Arora <[email protected]>
---
arch/i386/kernel/syscall_table.S | 1
arch/powerpc/kernel/sys_ppc32.c | 7 +++
arch/x86_64/ia32/ia32entry.S | 1
fs/open.c | 89 +++++++++++++++++++++++++++++++++++++++
include/asm-i386/unistd.h | 3 -
include/asm-powerpc/systbl.h | 1
include/asm-powerpc/unistd.h | 3 -
include/asm-x86_64/unistd.h | 2
include/linux/fs.h | 13 +++++
include/linux/syscalls.h | 1
10 files changed, 119 insertions(+), 2 deletions(-)
Index: linux-2.6.22-rc1/arch/i386/kernel/syscall_table.S
===================================================================
--- linux-2.6.22-rc1.orig/arch/i386/kernel/syscall_table.S
+++ linux-2.6.22-rc1/arch/i386/kernel/syscall_table.S
@@ -323,3 +323,4 @@ ENTRY(sys_call_table)
.long sys_signalfd
.long sys_timerfd
.long sys_eventfd
+ .long sys_fallocate
Index: linux-2.6.22-rc1/arch/powerpc/kernel/sys_ppc32.c
===================================================================
--- linux-2.6.22-rc1.orig/arch/powerpc/kernel/sys_ppc32.c
+++ linux-2.6.22-rc1/arch/powerpc/kernel/sys_ppc32.c
@@ -773,6 +773,13 @@ asmlinkage int compat_sys_truncate64(con
return sys_truncate(path, (high << 32) | low);
}
+asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo,
+ u32 lenhi, u32 lenlo)
+{
+ return sys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo,
+ ((loff_t)lenhi << 32) | lenlo);
+}
+
asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long high,
unsigned long low)
{
Index: linux-2.6.22-rc1/fs/open.c
===================================================================
--- linux-2.6.22-rc1.orig/fs/open.c
+++ linux-2.6.22-rc1/fs/open.c
@@ -353,6 +353,95 @@ asmlinkage long sys_ftruncate64(unsigned
#endif
/*
+ * sys_fallocate - preallocate blocks or free preallocated blocks
+ * @fd: the file descriptor
+ * @mode: mode specifies if fallocate should preallocate blocks OR free
+ * (unallocate) preallocated blocks. Currently only FA_ALLOCATE and
+ * FA_DEALLOCATE modes are supported.
+ * @offset: The offset within file, from where (un)allocation is being
+ * requested. It should not have a negative value.
+ * @len: The amount (in bytes) of space to be (un)allocated, from the offset.
+ *
+ * This system call, depending on the mode, preallocates or unallocates blocks
+ * for a file. The range of blocks depends on the value of offset and len
+ * arguments provided by the user/application. For FA_ALLOCATE mode, if this
+ * system call succeeds, subsequent writes to the file in the given range
+ * (specified by offset & len) should not fail - even if the file system
+ * later becomes full. Hence the preallocation done is persistent (valid
+ * even after reopen of the file and remount/reboot).
+ *
+ * Note: Incase the file system does not support preallocation,
+ * posix_fallocate() should fall back to the library implementation (i.e.
+ * allocating zero-filled new blocks to the file).
+ *
+ * Return Values
+ * 0 : On SUCCESS a value of zero is returned.
+ * error : On Failure, an error code will be returned.
+ * An error code of -ENOSYS or -EOPNOTSUPP should make posix_fallocate()
+ * fall back on library implementation of fallocate.
+ *
+ * <TBD> Generic fallocate to be added for file systems that do not
+ * support fallocate it.
+ */
+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 != FA_ALLOCATE && mode !=FA_DEALLOCATE)
+ goto out;
+
+ ret = -EBADF;
+ file = fget(fd);
+ if (!file)
+ goto out;
+ if (!(file->f_mode & FMODE_WRITE))
+ 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;
+
+ /*
+ * Update [cm]time.
+ * Partial allocation will not result in the time stamp changes,
+ * since ->fallocate will return error (say, -ENOSPC) in this case.
+ */
+ if (!ret)
+ file_update_time(file);
+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
* switching the fsuid/fsgid around to the real ones.
Index: linux-2.6.22-rc1/include/asm-i386/unistd.h
===================================================================
--- linux-2.6.22-rc1.orig/include/asm-i386/unistd.h
+++ linux-2.6.22-rc1/include/asm-i386/unistd.h
@@ -329,10 +329,11 @@
#define __NR_signalfd 321
#define __NR_timerfd 322
#define __NR_eventfd 323
+#define __NR_fallocate 324
#ifdef __KERNEL__
-#define NR_syscalls 324
+#define NR_syscalls 325
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
Index: linux-2.6.22-rc1/include/asm-powerpc/systbl.h
===================================================================
--- linux-2.6.22-rc1.orig/include/asm-powerpc/systbl.h
+++ linux-2.6.22-rc1/include/asm-powerpc/systbl.h
@@ -308,3 +308,4 @@ COMPAT_SYS_SPU(move_pages)
SYSCALL_SPU(getcpu)
COMPAT_SYS(epoll_pwait)
COMPAT_SYS_SPU(utimensat)
+COMPAT_SYS(fallocate)
Index: linux-2.6.22-rc1/include/asm-powerpc/unistd.h
===================================================================
--- linux-2.6.22-rc1.orig/include/asm-powerpc/unistd.h
+++ linux-2.6.22-rc1/include/asm-powerpc/unistd.h
@@ -327,10 +327,11 @@
#define __NR_getcpu 302
#define __NR_epoll_pwait 303
#define __NR_utimensat 304
+#define __NR_fallocate 305
#ifdef __KERNEL__
-#define __NR_syscalls 305
+#define __NR_syscalls 306
#define __NR__exit __NR_exit
#define NR_syscalls __NR_syscalls
Index: linux-2.6.22-rc1/include/asm-x86_64/unistd.h
===================================================================
--- linux-2.6.22-rc1.orig/include/asm-x86_64/unistd.h
+++ linux-2.6.22-rc1/include/asm-x86_64/unistd.h
@@ -630,6 +630,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd)
__SYSCALL(__NR_timerfd, sys_timerfd)
#define __NR_eventfd 283
__SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate 284
+__SYSCALL(__NR_fallocate, sys_fallocate)
#ifndef __NO_STUBS
#define __ARCH_WANT_OLD_READDIR
Index: linux-2.6.22-rc1/include/linux/fs.h
===================================================================
--- linux-2.6.22-rc1.orig/include/linux/fs.h
+++ linux-2.6.22-rc1/include/linux/fs.h
@@ -266,6 +266,17 @@ extern int dir_notify_enable;
#define SYNC_FILE_RANGE_WRITE 2
#define SYNC_FILE_RANGE_WAIT_AFTER 4
+/*
+ * sys_fallocate modes
+ * Currently sys_fallocate supports two modes:
+ * FA_ALLOCATE : This is the preallocate mode, using which an application/user
+ * may request (pre)allocation of blocks.
+ * FA_DEALLOCATE: This is the deallocate mode, which can be used to free
+ * the preallocated blocks.
+ */
+#define FA_ALLOCATE 0x1
+#define FA_DEALLOCATE 0x2
+
#ifdef __KERNEL__
#include <linux/linkage.h>
@@ -1137,6 +1148,8 @@ struct inode_operations {
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*removexattr) (struct dentry *, const char *);
void (*truncate_range)(struct inode *, loff_t, loff_t);
+ long (*fallocate)(struct inode *inode, int mode, loff_t offset,
+ loff_t len);
};
struct seq_file;
Index: linux-2.6.22-rc1/include/linux/syscalls.h
===================================================================
--- linux-2.6.22-rc1.orig/include/linux/syscalls.h
+++ linux-2.6.22-rc1/include/linux/syscalls.h
@@ -608,6 +608,7 @@ asmlinkage long sys_signalfd(int ufd, si
asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
const struct itimerspec __user *utmr);
asmlinkage long sys_eventfd(unsigned int count);
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
Index: linux-2.6.22-rc1/arch/x86_64/ia32/ia32entry.S
===================================================================
--- linux-2.6.22-rc1.orig/arch/x86_64/ia32/ia32entry.S
+++ linux-2.6.22-rc1/arch/x86_64/ia32/ia32entry.S
@@ -719,4 +719,5 @@ ia32_sys_call_table:
.quad compat_sys_signalfd
.quad compat_sys_timerfd
.quad sys_eventfd
+ .quad sys_fallocate
ia32_syscall_end:
On Wed, 2007-05-16 at 01:33 +0530, Amit K. Arora wrote:
> This patch implements sys_fallocate() and adds support on i386, x86_64
> and powerpc platforms.
> @@ -1137,6 +1148,8 @@ struct inode_operations {
> ssize_t (*listxattr) (struct dentry *, char *, size_t);
> int (*removexattr) (struct dentry *, const char *);
> void (*truncate_range)(struct inode *, loff_t, loff_t);
> + long (*fallocate)(struct inode *inode, int mode, loff_t offset,
> + loff_t len);
> };
Does the return value from fallocate inode operation has to be *long*?
It's not consistent with the ext4_fallocate() define in patch 4/5,
+int ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t
len)
thus cause compile warnings.
Mingming
On Wed, May 16, 2007 at 01:33:59AM +0530, Amit K. Arora wrote:
> This patch implements sys_fallocate() and adds support on i386, x86_64
> and powerpc platforms.
Can you please pick up the ia64 support patch I posted as well?
> Changelog:
> ---------
> Note: The changes below are from the initial post (dated 26th April,
> 2007) and _not_ from TAKE2. The only difference from TAKE2 is the kernel
> version on which this patch is based. TAKE2 was based on 2.6.21 and this
> is based on 2.6.22-rc1.
>
> Following changes were made to the previous version:
> 1) Added description before sys_fallocate() definition.
> 2) Return EINVAL for len<=0 (With new draft that Ulrich pointed to,
> posix_fallocate should return EINVAL for len <= 0.
> 3) Return EOPNOTSUPP if mode is not one of FA_ALLOCATE or FA_DEALLOCATE
> 4) Do not return ENODEV for dirs (let individual file systems decide if
> they want to support preallocation to directories or not.
> 5) Check for wrap through zero.
> 6) Update c/mtime if fallocate() succeeds.
Please don't make this always happen. c/mtime updates should be dependent
on the mode being used and whether there is visible change to the file. If no
userspace visible changes to the file occurred, then timestamps should not
be changed.
e.g. FA_ALLOCATE that changes file size requires same semantics of ftruncate()
extending the file, otherwise no change in timestamps should occur.
Cheers,
Dave.
--
Dave Chinner
Principal Engineer
SGI Australian Software Group
On Wed, 2007-05-16 at 13:16 +1000, David Chinner wrote:
> On Wed, May 16, 2007 at 01:33:59AM +0530, Amit K. Arora wrote:
> > Following changes were made to the previous version:
> > 1) Added description before sys_fallocate() definition.
> > 2) Return EINVAL for len<=0 (With new draft that Ulrich pointed to,
> > posix_fallocate should return EINVAL for len <= 0.
> > 3) Return EOPNOTSUPP if mode is not one of FA_ALLOCATE or FA_DEALLOCATE
> > 4) Do not return ENODEV for dirs (let individual file systems decide if
> > they want to support preallocation to directories or not.
> > 5) Check for wrap through zero.
> > 6) Update c/mtime if fallocate() succeeds.
>
> Please don't make this always happen. c/mtime updates should be dependent
> on the mode being used and whether there is visible change to the file. If no
> userspace visible changes to the file occurred, then timestamps should not
> be changed.
i_blocks will be updated, so it seems reasonable to update ctime. mtime
shouldn't be changed, though, since the contents of the file will be
unchanged.
> e.g. FA_ALLOCATE that changes file size requires same semantics of ftruncate()
> extending the file, otherwise no change in timestamps should occur.
>
> Cheers,
>
> Dave.
--
David Kleikamp
IBM Linux Technology Center
On Tue, May 15, 2007 at 05:42:46PM -0700, Mingming Cao wrote:
> On Wed, 2007-05-16 at 01:33 +0530, Amit K. Arora wrote:
> > This patch implements sys_fallocate() and adds support on i386, x86_64
> > and powerpc platforms.
>
> > @@ -1137,6 +1148,8 @@ struct inode_operations {
> > ssize_t (*listxattr) (struct dentry *, char *, size_t);
> > int (*removexattr) (struct dentry *, const char *);
> > void (*truncate_range)(struct inode *, loff_t, loff_t);
> > + long (*fallocate)(struct inode *inode, int mode, loff_t offset,
> > + loff_t len);
> > };
>
> Does the return value from fallocate inode operation has to be *long*?
> It's not consistent with the ext4_fallocate() define in patch 4/5,
I think ->fallocate() should return a "long", since sys_fallocate() has
to return what ->fallocate() returns and hence their return type should
ideally match.
> +int ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t
> len)
I will change the ext4_fallocate() to return a "long" (in patch 4/5)
in the next post.
Agree ?
Thanks!
--
Regards,
Amit Arora
>
> thus cause compile warnings.
>
>
>
> Mingming
On Wed, May 16, 2007 at 07:21:16AM -0500, Dave Kleikamp wrote:
> On Wed, 2007-05-16 at 13:16 +1000, David Chinner wrote:
> > On Wed, May 16, 2007 at 01:33:59AM +0530, Amit K. Arora wrote:
>
> > > Following changes were made to the previous version:
> > > 1) Added description before sys_fallocate() definition.
> > > 2) Return EINVAL for len<=0 (With new draft that Ulrich pointed to,
> > > posix_fallocate should return EINVAL for len <= 0.
> > > 3) Return EOPNOTSUPP if mode is not one of FA_ALLOCATE or FA_DEALLOCATE
> > > 4) Do not return ENODEV for dirs (let individual file systems decide if
> > > they want to support preallocation to directories or not.
> > > 5) Check for wrap through zero.
> > > 6) Update c/mtime if fallocate() succeeds.
> >
> > Please don't make this always happen. c/mtime updates should be dependent
> > on the mode being used and whether there is visible change to the file. If no
> > userspace visible changes to the file occurred, then timestamps should not
> > be changed.
>
> i_blocks will be updated, so it seems reasonable to update ctime. mtime
> shouldn't be changed, though, since the contents of the file will be
> unchanged.
I agree. Thus the ctime should change for FA_PREALLOCATE mode also
(which does not change the file size) - if we end up having this
additional mode in near future.
--
Regards,
Amit Arora
> > e.g. FA_ALLOCATE that changes file size requires same semantics of ftruncate()
> > extending the file, otherwise no change in timestamps should occur.
> >
> > Cheers,
> >
> > Dave.
> --
> David Kleikamp
> IBM Linux Technology Center
On Wed, May 16, 2007 at 07:21:16AM -0500, Dave Kleikamp wrote:
> On Wed, 2007-05-16 at 13:16 +1000, David Chinner wrote:
> > On Wed, May 16, 2007 at 01:33:59AM +0530, Amit K. Arora wrote:
>
> > > Following changes were made to the previous version:
> > > 1) Added description before sys_fallocate() definition.
> > > 2) Return EINVAL for len<=0 (With new draft that Ulrich pointed to,
> > > posix_fallocate should return EINVAL for len <= 0.
> > > 3) Return EOPNOTSUPP if mode is not one of FA_ALLOCATE or FA_DEALLOCATE
> > > 4) Do not return ENODEV for dirs (let individual file systems decide if
> > > they want to support preallocation to directories or not.
> > > 5) Check for wrap through zero.
> > > 6) Update c/mtime if fallocate() succeeds.
> >
> > Please don't make this always happen. c/mtime updates should be dependent
> > on the mode being used and whether there is visible change to the file. If no
> > userspace visible changes to the file occurred, then timestamps should not
> > be changed.
>
> i_blocks will be updated, so it seems reasonable to update ctime. mtime
> shouldn't be changed, though, since the contents of the file will be
> unchanged.
That's assuming blocks were actually allocated - if the prealloc range already
has underlying blocks there is no change and so we should not be changing
mtime either. Only the filesystem will know if it has changed the file, so I
think that timestamp updates need to be driven down to that level, not done
blindy at the highest layer....
Cheers,
Dave.
--
Dave Chinner
Principal Engineer
SGI Australian Software Group
On Thu, 2007-05-17 at 09:40 +1000, David Chinner wrote:
> On Wed, May 16, 2007 at 07:21:16AM -0500, Dave Kleikamp wrote:
> > On Wed, 2007-05-16 at 13:16 +1000, David Chinner wrote:
> > > Please don't make this always happen. c/mtime updates should be dependent
> > > on the mode being used and whether there is visible change to the file. If no
> > > userspace visible changes to the file occurred, then timestamps should not
> > > be changed.
> >
> > i_blocks will be updated, so it seems reasonable to update ctime. mtime
> > shouldn't be changed, though, since the contents of the file will be
> > unchanged.
>
> That's assuming blocks were actually allocated - if the prealloc range already
> has underlying blocks there is no change and so we should not be changing
> mtime either. Only the filesystem will know if it has changed the file, so I
> think that timestamp updates need to be driven down to that level, not done
> blindy at the highest layer....
Yes, I agree.
Shaggy
--
David Kleikamp
IBM Linux Technology Center
On Thu, May 17, 2007 at 09:40:36AM +1000, David Chinner wrote:
> On Wed, May 16, 2007 at 07:21:16AM -0500, Dave Kleikamp wrote:
> > On Wed, 2007-05-16 at 13:16 +1000, David Chinner wrote:
> > > On Wed, May 16, 2007 at 01:33:59AM +0530, Amit K. Arora wrote:
> >
> > > > Following changes were made to the previous version:
> > > > 1) Added description before sys_fallocate() definition.
> > > > 2) Return EINVAL for len<=0 (With new draft that Ulrich pointed to,
> > > > posix_fallocate should return EINVAL for len <= 0.
> > > > 3) Return EOPNOTSUPP if mode is not one of FA_ALLOCATE or FA_DEALLOCATE
> > > > 4) Do not return ENODEV for dirs (let individual file systems decide if
> > > > they want to support preallocation to directories or not.
> > > > 5) Check for wrap through zero.
> > > > 6) Update c/mtime if fallocate() succeeds.
> > >
> > > Please don't make this always happen. c/mtime updates should be dependent
> > > on the mode being used and whether there is visible change to the file. If no
> > > userspace visible changes to the file occurred, then timestamps should not
> > > be changed.
> >
> > i_blocks will be updated, so it seems reasonable to update ctime. mtime
> > shouldn't be changed, though, since the contents of the file will be
> > unchanged.
>
> That's assuming blocks were actually allocated - if the prealloc range already
> has underlying blocks there is no change and so we should not be changing
> mtime either. Only the filesystem will know if it has changed the file, so I
> think that timestamp updates need to be driven down to that level, not done
> blindy at the highest layer....
Ok. Will make this change in the next post.
--
Regards,
Amit Arora
>
> Cheers,
>
> Dave.
> --
> Dave Chinner
> Principal Engineer
> SGI Australian Software Group