vfs: Implement proper O_SYNC semantics

While Linux provided an O_SYNC flag basically since day 1, it took until
Linux 2.4.0-test12pre2 to actually get it implemented for filesystems,
since that day we had generic_osync_around with only minor changes and the
great "For now, when the user asks for O_SYNC, we'll actually give
O_DSYNC" comment.  This patch intends to actually give us real O_SYNC
semantics in addition to the O_DSYNC semantics.  After Jan's O_SYNC
patches which are required before this patch it's actually surprisingly
simple, we just need to figure out when to set the datasync flag to
vfs_fsync_range and when not.

This patch renames the existing O_SYNC flag to O_DSYNC while keeping it's
numerical value to keep binary compatibility, and adds a new real O_SYNC
flag.  To guarantee backwards compatiblity it is defined as expanding to
both the O_DSYNC and the new additional binary flag (__O_SYNC) to make
sure we are backwards-compatible when compiled against the new headers.

This also means that all places that don't care about the differences can
just check O_DSYNC and get the right behaviour for O_SYNC, too - only
places that actuall care need to check __O_SYNC in addition.  Drivers and
network filesystems have been updated in a fail safe way to always do the
full sync magic if O_DSYNC is set.  The few places setting O_SYNC for
lower layers are kept that way for now to stay failsafe.

We enforce that O_DSYNC is set when __O_SYNC is set early in the open path
to make sure we always get these sane options.

Note that parisc really screwed up their headers as they already define a
O_DSYNC that has always been a no-op.  We try to repair it by using it for
the new O_DSYNC and redefinining O_SYNC to send both the traditional
O_SYNC numerical value _and_ the O_DSYNC one.

Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger@sun.com>
Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Acked-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jan Kara <jack@suse.cz>

9 files changed, 54 insertions, 16 deletions

diff --git a/arch/alpha/include/asm/fcntl.h b/arch/alpha/include/asm/fcntl.h
index 25da0017ec87..21b1117a0c61 100644
--- a/arch/alpha/include/asm/fcntl.h
+++ b/arch/alpha/include/asm/fcntl.h
@@ -1,8 +1,6 @@
 #ifndef _ALPHA_FCNTL_H
 #define _ALPHA_FCNTL_H
 
-/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
-   located on an ext2 file system */
 #define O_CREAT          01000  /* not fcntl */
 #define O_TRUNC          02000  /* not fcntl */
 #define O_EXCL           04000  /* not fcntl */
@@ -10,13 +8,28 @@
 
 #define O_NONBLOCK       00004
 #define O_APPEND         00010
-#define O_SYNC          040000
+#define O_DSYNC         040000  /* used to be O_SYNC, see below */
 #define O_DIRECTORY     0100000 /* must be a directory */
 #define O_NOFOLLOW      0200000 /* don't follow links */
 #define O_LARGEFILE     0400000 /* will be set by the kernel on every open */
 #define O_DIRECT        02000000 /* direct disk access - should check with OSF/1 */
 #define O_NOATIME       04000000
 #define O_CLOEXEC       010000000 /* set close_on_exec */
+/*
+ * Before Linux 2.6.32 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag.  We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics.  It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#define __O_SYNC        020000000
+#define O_SYNC          (__O_SYNC|O_DSYNC)
 
 #define F_GETLK         7
 #define F_SETLK         8
diff --git a/arch/blackfin/include/asm/fcntl.h b/arch/blackfin/include/asm/fcntl.h
index 8727b2b382f1..251c911d59c1 100644
--- a/arch/blackfin/include/asm/fcntl.h
+++ b/arch/blackfin/include/asm/fcntl.h
@@ -7,8 +7,6 @@
 #ifndef _BFIN_FCNTL_H
 #define _BFIN_FCNTL_H
 
-/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
-   located on an ext2 file system */
 #define O_DIRECTORY      040000 /* must be a directory */
 #define O_NOFOLLOW      0100000 /* don't follow links */
 #define O_DIRECT        0200000 /* direct disk access hint - currently ignored */
diff --git a/arch/mips/include/asm/fcntl.h b/arch/mips/include/asm/fcntl.h
index 2a52333a062d..7c6681aa2ab8 100644
--- a/arch/mips/include/asm/fcntl.h
+++ b/arch/mips/include/asm/fcntl.h
@@ -10,7 +10,7 @@
 
 
 #define O_APPEND        0x0008
-#define O_SYNC          0x0010
+#define O_DSYNC         0x0010  /* used to be O_SYNC, see below */
 #define O_NONBLOCK      0x0080
 #define O_CREAT         0x0100  /* not fcntl */
 #define O_TRUNC         0x0200  /* not fcntl */
@@ -18,6 +18,21 @@
 #define O_NOCTTY        0x0800  /* not fcntl */
 #define FASYNC          0x1000  /* fcntl, for BSD compatibility */
 #define O_LARGEFILE     0x2000  /* allow large file opens */
+/*
+ * Before Linux 2.6.32 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag.  We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics.  It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#define __O_SYNC        0x4000
+#define O_SYNC          (__O_SYNC|O_DSYNC)
 #define O_DIRECT        0x8000  /* direct disk access hint */
 
 #define F_GETLK         14
diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c
index ad4e017ed2f3..80e2ba694bab 100644
--- a/arch/mips/kernel/kspd.c
+++ b/arch/mips/kernel/kspd.c
@@ -82,6 +82,7 @@ static int sp_stopping;
 #define MTSP_O_SHLOCK           0x0010
 #define MTSP_O_EXLOCK           0x0020
 #define MTSP_O_ASYNC            0x0040
+/* XXX: check which of these is actually O_SYNC vs O_DSYNC */
 #define MTSP_O_FSYNC            O_SYNC
 #define MTSP_O_NOFOLLOW         0x0100
 #define MTSP_O_SYNC             0x0080
diff --git a/arch/mips/loongson/common/mem.c b/arch/mips/loongson/common/mem.c
index 7c92f79b6480..e94ef158f980 100644
--- a/arch/mips/loongson/common/mem.c
+++ b/arch/mips/loongson/common/mem.c
@@ -26,7 +26,7 @@ void __init prom_init_memory(void)
 /* override of arch/mips/mm/cache.c: __uncached_access */
 int __uncached_access(struct file *file, unsigned long addr)
 {
-        if (file->f_flags & O_SYNC)
+        if (file->f_flags & O_DSYNC)
                 return 1;
 
         return addr >= __pa(high_memory) ||
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 694d51f523d1..102b2dfa542a 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -194,7 +194,7 @@ void __devinit cpu_cache_init(void)
 
 int __weak __uncached_access(struct file *file, unsigned long addr)
 {
-        if (file->f_flags & O_SYNC)
+        if (file->f_flags & O_DSYNC)
                 return 1;
 
         return addr >= __pa(high_memory);
diff --git a/arch/parisc/include/asm/fcntl.h b/arch/parisc/include/asm/fcntl.h
index 1e1c824764ee..f357fc693c89 100644
--- a/arch/parisc/include/asm/fcntl.h
+++ b/arch/parisc/include/asm/fcntl.h
@@ -1,14 +1,13 @@
 #ifndef _PARISC_FCNTL_H
 #define _PARISC_FCNTL_H
 
-/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
-   located on an ext2 file system */
 #define O_APPEND        000000010
 #define O_BLKSEEK       000000100 /* HPUX only */
 #define O_CREAT         000000400 /* not fcntl */
 #define O_EXCL          000002000 /* not fcntl */
 #define O_LARGEFILE     000004000
-#define O_SYNC          000100000
+#define __O_SYNC        000100000
+#define O_SYNC          (__O_SYNC|O_DSYNC)
 #define O_NONBLOCK      000200004 /* HPUX has separate NDELAY & NONBLOCK */
 #define O_NOCTTY        000400000 /* not fcntl */
 #define O_DSYNC         001000000 /* HPUX only */
diff --git a/arch/sparc/include/asm/fcntl.h b/arch/sparc/include/asm/fcntl.h
index d4d9c9d852c3..3b9cfb39175e 100644
--- a/arch/sparc/include/asm/fcntl.h
+++ b/arch/sparc/include/asm/fcntl.h
@@ -1,14 +1,12 @@
 #ifndef _SPARC_FCNTL_H
 #define _SPARC_FCNTL_H
 
-/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
-   located on an ext2 file system */
 #define O_APPEND        0x0008
 #define FASYNC          0x0040  /* fcntl, for BSD compatibility */
 #define O_CREAT         0x0200  /* not fcntl */
 #define O_TRUNC         0x0400  /* not fcntl */
 #define O_EXCL          0x0800  /* not fcntl */
-#define O_SYNC          0x2000
+#define O_DSYNC         0x2000  /* used to be O_SYNC, see below */
 #define O_NONBLOCK      0x4000
 #if defined(__sparc__) && defined(__arch64__)
 #define O_NDELAY        0x0004
@@ -20,6 +18,21 @@
 #define O_DIRECT        0x100000 /* direct disk access hint */
 #define O_NOATIME       0x200000
 #define O_CLOEXEC       0x400000
+/*
+ * Before Linux 2.6.32 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag.  We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics.  It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#define __O_SYNC        0x800000
+#define O_SYNC          (__O_SYNC|O_DSYNC)
 
 #define F_GETOWN        5       /*  for sockets. */
 #define F_SETOWN        6       /*  for sockets. */
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 66b55d6e69ed..ae9648eb1c7f 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -704,9 +704,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
         if (!range_is_allowed(pfn, size))
                 return 0;
 
-        if (file->f_flags & O_SYNC) {
+        if (file->f_flags & O_DSYNC)
                 flags = _PAGE_CACHE_UC_MINUS;
-        }
 
 #ifdef CONFIG_X86_32
         /*