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>

12 files changed, 92 insertions, 2 deletions

diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index bf6adce..8344c70 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/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
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index b42cbf1..bd85b5f 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -773,6 +773,13 @@ asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4,
 	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)
 {
diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S
index 782dea8..3f66e970 100644
--- a/arch/x86_64/ia32/ia32entry.S
+++ b/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 sys32_fallocate
 ia32_syscall_end:
diff --git a/arch/x86_64/ia32/sys_ia32.c b/arch/x86_64/ia32/sys_ia32.c
index 99a78a3..bee96d6 100644
--- a/arch/x86_64/ia32/sys_ia32.c
+++ b/arch/x86_64/ia32/sys_ia32.c
@@ -879,3 +879,11 @@ asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
 	return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
 				len, advice);
 }
+
+asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
+				unsigned offset_hi, unsigned len_lo,
+				unsigned len_hi)
+{
+	return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
+			     ((u64)len_hi << 32) | len_lo);
+}
diff --git a/fs/open.c b/fs/open.c
index be6a457..a6b054e 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
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index e84ace1..9b15545 100644
--- a/include/asm-i386/unistd.h
+++ b/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
diff --git a/include/asm-powerpc/systbl.h b/include/asm-powerpc/systbl.h
index 1cc3f9c..cc6d872 100644
--- a/include/asm-powerpc/systbl.h
+++ b/include/asm-powerpc/systbl.h
@@ -308,6 +308,7 @@ COMPAT_SYS_SPU(move_pages)
 SYSCALL_SPU(getcpu)
 COMPAT_SYS(epoll_pwait)
 COMPAT_SYS_SPU(utimensat)
+COMPAT_SYS(fallocate)
 COMPAT_SYS_SPU(signalfd)
 COMPAT_SYS_SPU(timerfd)
 SYSCALL_SPU(eventfd)
diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h
index f71c606..97d82b6 100644
--- a/include/asm-powerpc/unistd.h
+++ b/include/asm-powerpc/unistd.h
@@ -331,10 +331,11 @@
 #define __NR_timerfd		306
 #define __NR_eventfd		307
 #define __NR_sync_file_range2	308
+#define __NR_fallocate		309
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		309
+#define __NR_syscalls		310
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index 8696f8a..fc4e73f 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -630,6 +630,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd)
 __SYSCALL(__NR_timerfd, sys_timerfd)
 #define __NR_eventfd		284
 __SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate		285
+__SYSCALL(__NR_fallocate, sys_fallocate)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
new file mode 100644
index 0000000..8e912ab
--- /dev/null
+++ b/include/linux/falloc.h
@@ -0,0 +1,6 @@
+#ifndef _FALLOC_H_
+#define _FALLOC_H_
+
+#define FALLOC_FL_KEEP_SIZE	0x01 /* default is extend size */
+
+#endif /* _FALLOC_H_ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98205f6..0b806c5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1147,6 +1147,8 @@ 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;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 83d0ec1..7a8b1e3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -610,6 +610,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
 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[]);