[PATCH 2/6][TAKE7] fallocate() implementation in i386, x86_64 and powerpc

[Amit K. Arora]

From: Amit Arora <aarora@xxxxxxxxxx>

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. A generic file system operation to handle fallocate
   (generic_fallocate), for filesystems that do _not_ have the fallocate
   inode operation implemented.
3. 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@xxxxxxxxxx>

Index: linux-2.6.22/arch/i386/kernel/syscall_table.S
===================================================================
--- linux-2.6.22.orig/arch/i386/kernel/syscall_table.S
+++ linux-2.6.22/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/arch/powerpc/kernel/sys_ppc32.c
===================================================================
--- linux-2.6.22.orig/arch/powerpc/kernel/sys_ppc32.c
+++ linux-2.6.22/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/arch/x86_64/ia32/ia32entry.S
===================================================================
--- linux-2.6.22.orig/arch/x86_64/ia32/ia32entry.S
+++ linux-2.6.22/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:
Index: linux-2.6.22/fs/open.c
===================================================================
--- linux-2.6.22.orig/fs/open.c
+++ linux-2.6.22/fs/open.c
@@ -353,6 +353,92 @@ asmlinkage long sys_ftruncate64(unsigned
 #endif
 
 /*
+ * sys_fallocate - preallocate blocks or free preallocated blocks
+ * @fd: the file descriptor
+ * @mode: mode specifies the behavior of allocation.
+ * @offset: The offset within file, from where allocation is being
+ *	    requested. It should not have a negative value.
+ * @len: The amount of space in bytes to be allocated, from the offset.
+ *	 This can not be zero or a negative value.
+ *
+ * This system call preallocates space for a file. The range of blocks
+ * allocated depends on the value of offset and len arguments provided
+ * by the user/application. With FALLOC_ALLOCATE or FALLOC_RESV_SPACE
+ * modes, if the 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).
+ *
+ * It is expected that the ->fallocate() inode operation implemented by
+ * the individual file systems will update the file size and/or
+ * ctime/mtime depending on the mode and also on the success of the
+ * operation.
+ *
+ * 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.
+ */
+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 != FALLOC_ALLOCATE && mode != FALLOC_RESV_SPACE)
+		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;
+
+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/include/asm-i386/unistd.h
===================================================================
--- linux-2.6.22.orig/include/asm-i386/unistd.h
+++ linux-2.6.22/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/include/asm-powerpc/systbl.h
===================================================================
--- linux-2.6.22.orig/include/asm-powerpc/systbl.h
+++ linux-2.6.22/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)
Index: linux-2.6.22/include/asm-powerpc/unistd.h
===================================================================
--- linux-2.6.22.orig/include/asm-powerpc/unistd.h
+++ linux-2.6.22/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
Index: linux-2.6.22/include/asm-x86_64/unistd.h
===================================================================
--- linux-2.6.22.orig/include/asm-x86_64/unistd.h
+++ linux-2.6.22/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
Index: linux-2.6.22/include/linux/fs.h
===================================================================
--- linux-2.6.22.orig/include/linux/fs.h
+++ linux-2.6.22/include/linux/fs.h
@@ -266,6 +266,21 @@ 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:
+ * FALLOC_ALLOCATE :	This is the preallocate mode, using which an application
+ *			may request reservation of space for a particular file.
+ *			The file size will be changed if the allocation is
+ *			beyond EOF.
+ * FALLOC_RESV_SPACE :	This is same as the above mode, with only one difference
+ *			that the file size will not be modified.
+ */
+#define FALLOC_FL_KEEP_SIZE    0x01 /* default is extend/shrink size */
+
+#define FALLOC_ALLOCATE        0
+#define FALLOC_RESV_SPACE      FALLOC_FL_KEEP_SIZE
+
 #ifdef __KERNEL__
 
 #include <linux/linkage.h>
@@ -1138,6 +1153,8 @@ 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/include/linux/syscalls.h
===================================================================
--- linux-2.6.22.orig/include/linux/syscalls.h
+++ linux-2.6.22/include/linux/syscalls.h
@@ -610,6 +610,7 @@ 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/arch/x86_64/ia32/sys_ia32.c
===================================================================
--- linux-2.6.22.orig/arch/x86_64/ia32/sys_ia32.c
+++ linux-2.6.22/arch/x86_64/ia32/sys_ia32.c
@@ -879,3 +879,11 @@ asmlinkage long sys32_fadvise64(int fd, 
 	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);
+}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/