Merge tag 'asm-generic-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic

Pull asm-generic updates from Arnd Bergmann:
 "These are a number of unrelated cleanups, generally simplifying the
  architecture specific header files:

   - A series from Al Viro simplifies asm/vga.h, after it turns out that
     most of it can be generalized.

   - A series from Julian Vetter adds a common version of
     memcpy_{to,from}io() and memset_io() and changes most architectures
     to use that instead of their own implementation

   - A series from Niklas Schnelle concludes his work to make PC style
     inb()/outb() optional

   - Nicolas Pitre contributes improvements for the generic do_div()
     helper

   - Christoph Hellwig adds a generic version of page_to_phys() and
     phys_to_page(), replacing the slightly different architecture
     specific definitions.

   - Uwe Kleine-Koenig has a minor cleanup for ioctl definitions"

* tag 'asm-generic-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic: (24 commits)
  empty include/asm-generic/vga.h
  sparc: get rid of asm/vga.h
  asm/vga.h: don't bother with scr_mem{cpy,move}v() unless we need to
  vt_buffer.h: get rid of dead code in default scr_...() instances
  tty: serial: export serial_8250_warn_need_ioport
  lib/iomem_copy: fix kerneldoc format style
  hexagon: simplify asm/io.h for !HAS_IOPORT
  loongarch: Use new fallback IO memcpy/memset
  csky: Use new fallback IO memcpy/memset
  arm64: Use new fallback IO memcpy/memset
  New implementation for IO memcpy and IO memset
  watchdog: Add HAS_IOPORT dependency for SBC8360 and SBC7240
  __arch_xprod64(): make __always_inline when optimizing for performance
  ARM: div64: improve __arch_xprod_64()
  asm-generic/div64: optimize/simplify __div64_const32()
  lib/math/test_div64: add some edge cases relevant to __div64_const32()
  asm-generic: add an optional pfn_valid check to page_to_phys
  asm-generic: provide generic page_to_phys and phys_to_page implementations
  asm-generic/io.h: Remove I/O port accessors for HAS_IOPORT=n
  tty: serial: handle HAS_IOPORT dependencies
  ...

7 files changed, 129 insertions, 152 deletions

diff --git a/include/asm-generic/div64.h b/include/asm-generic/div64.h
index 13f5aa68a455..25e7b4b58dcf 100644
--- a/include/asm-generic/div64.h
+++ b/include/asm-generic/div64.h
@@ -74,7 +74,8 @@
 	 * do the trick here).						\
 	 */								\
 	uint64_t ___res, ___x, ___t, ___m, ___n = (n);			\
-	uint32_t ___p, ___bias;						\
+	uint32_t ___p;							\
+	bool ___bias = false;						\
 									\
 	/* determine MSB of b */					\
 	___p = 1 << ilog2(___b);					\
@@ -87,22 +88,14 @@
 	___x = ~0ULL / ___b * ___b - 1;					\
 									\
 	/* test our ___m with res = m * x / (p << 64) */		\
-	___res = ((___m & 0xffffffff) * (___x & 0xffffffff)) >> 32;	\
-	___t = ___res += (___m & 0xffffffff) * (___x >> 32);		\
-	___res += (___x & 0xffffffff) * (___m >> 32);			\
-	___t = (___res < ___t) ? (1ULL << 32) : 0;			\
-	___res = (___res >> 32) + ___t;					\
-	___res += (___m >> 32) * (___x >> 32);				\
-	___res /= ___p;							\
+	___res = (___m & 0xffffffff) * (___x & 0xffffffff);		\
+	___t = (___m & 0xffffffff) * (___x >> 32) + (___res >> 32);	\
+	___res = (___m >> 32) * (___x >> 32) + (___t >> 32);		\
+	___t = (___m >> 32) * (___x & 0xffffffff) + (___t & 0xffffffff);\
+	___res = (___res + (___t >> 32)) / ___p;			\
 									\
-	/* Now sanitize and optimize what we've got. */			\
-	if (~0ULL % (___b / (___b & -___b)) == 0) {			\
-		/* special case, can be simplified to ... */		\
-		___n /= (___b & -___b);					\
-		___m = ~0ULL / (___b / (___b & -___b));			\
-		___p = 1;						\
-		___bias = 1;						\
-	} else if (___res != ___x / ___b) {				\
+	/* Now validate what we've got. */				\
+	if (___res != ___x / ___b) {					\
 		/*							\
 		 * We can't get away without a bias to compensate	\
 		 * for bit truncation errors.  To avoid it we'd need an	\
@@ -111,45 +104,18 @@
 		 *							\
 		 * Instead we do m = p / b and n / b = (n * m + m) / p.	\
 		 */							\
-		___bias = 1;						\
+		___bias = true;						\
 		/* Compute m = (p << 64) / b */				\
 		___m = (~0ULL / ___b) * ___p;				\
 		___m += ((~0ULL % ___b + 1) * ___p) / ___b;		\
-	} else {							\
-		/*							\
-		 * Reduce m / p, and try to clear bit 31 of m when	\
-		 * possible, otherwise that'll need extra overflow	\
-		 * handling later.					\
-		 */							\
-		uint32_t ___bits = -(___m & -___m);			\
-		___bits |= ___m >> 32;					\
-		___bits = (~___bits) << 1;				\
-		/*							\
-		 * If ___bits == 0 then setting bit 31 is  unavoidable.	\
-		 * Simply apply the maximum possible reduction in that	\
-		 * case. Otherwise the MSB of ___bits indicates the	\
-		 * best reduction we should apply.			\
-		 */							\
-		if (!___bits) {						\
-			___p /= (___m & -___m);				\
-			___m /= (___m & -___m);				\
-		} else {						\
-			___p >>= ilog2(___bits);			\
-			___m >>= ilog2(___bits);			\
-		}							\
-		/* No bias needed. */					\
-		___bias = 0;						\
 	}								\
 									\
+	/* Reduce m / p to help avoid overflow handling later. */	\
+	___p /= (___m & -___m);						\
+	___m /= (___m & -___m);						\
+									\
 	/*								\
-	 * Now we have a combination of 2 conditions:			\
-	 *								\
-	 * 1) whether or not we need to apply a bias, and		\
-	 *								\
-	 * 2) whether or not there might be an overflow in the cross	\
-	 *    product determined by (___m & ((1 << 63) | (1 << 31))).	\
-	 *								\
-	 * Select the best way to do (m_bias + m * n) / (1 << 64).	\
+	 * Perform (m_bias + m * n) / (1 << 64).			\
 	 * From now on there will be actual runtime code generated.	\
 	 */								\
 	___res = __arch_xprod_64(___m, ___n, ___bias);			\
@@ -165,47 +131,42 @@
  * Semantic:  retval = ((bias ? m : 0) + m * n) >> 64
  *
  * The product is a 128-bit value, scaled down to 64 bits.
- * Assuming constant propagation to optimize away unused conditional code.
+ * Hoping for compile-time optimization of  conditional code.
  * Architectures may provide their own optimized assembly implementation.
  */
-static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+#ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
+static __always_inline
+#else
+static inline
+#endif
+uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
 {
 	uint32_t m_lo = m;
 	uint32_t m_hi = m >> 32;
 	uint32_t n_lo = n;
 	uint32_t n_hi = n >> 32;
-	uint64_t res;
-	uint32_t res_lo, res_hi, tmp;
-
-	if (!bias) {
-		res = ((uint64_t)m_lo * n_lo) >> 32;
-	} else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
-		/* there can't be any overflow here */
-		res = (m + (uint64_t)m_lo * n_lo) >> 32;
+	uint64_t x, y;
+
+	/* Determine if overflow handling can be dispensed with. */
+	bool no_ovf = __builtin_constant_p(m) &&
+		      ((m >> 32) + (m & 0xffffffff) < 0x100000000);
+
+	if (no_ovf) {
+		x = (uint64_t)m_lo * n_lo + (bias ? m : 0);
+		x >>= 32;
+		x += (uint64_t)m_lo * n_hi;
+		x += (uint64_t)m_hi * n_lo;
+		x >>= 32;
+		x += (uint64_t)m_hi * n_hi;
 	} else {
-		res = m + (uint64_t)m_lo * n_lo;
-		res_lo = res >> 32;
-		res_hi = (res_lo < m_hi);
-		res = res_lo | ((uint64_t)res_hi << 32);
+		x = (uint64_t)m_lo * n_lo + (bias ? m_lo : 0);
+		y = (uint64_t)m_lo * n_hi + (uint32_t)(x >> 32) + (bias ? m_hi : 0);
+		x = (uint64_t)m_hi * n_hi + (uint32_t)(y >> 32);
+		y = (uint64_t)m_hi * n_lo + (uint32_t)y;
+		x += (uint32_t)(y >> 32);
 	}
 
-	if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
-		/* there can't be any overflow here */
-		res += (uint64_t)m_lo * n_hi;
-		res += (uint64_t)m_hi * n_lo;
-		res >>= 32;
-	} else {
-		res += (uint64_t)m_lo * n_hi;
-		tmp = res >> 32;
-		res += (uint64_t)m_hi * n_lo;
-		res_lo = res >> 32;
-		res_hi = (res_lo < tmp);
-		res = res_lo | ((uint64_t)res_hi << 32);
-	}
-
-	res += (uint64_t)m_hi * n_hi;
-
-	return res;
+	return x;
 }
 #endif
 
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 80de699bf6af..a5cbbf3e26ec 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -540,6 +540,7 @@ static inline void writesq(volatile void __iomem *addr, const void *buffer,
 
 #if !defined(inb) && !defined(_inb)
 #define _inb _inb
+#ifdef CONFIG_HAS_IOPORT
 static inline u8 _inb(unsigned long addr)
 {
 	u8 val;
@@ -549,10 +550,15 @@ static inline u8 _inb(unsigned long addr)
 	__io_par(val);
 	return val;
 }
+#else
+u8 _inb(unsigned long addr)
+	__compiletime_error("inb()) requires CONFIG_HAS_IOPORT");
+#endif
 #endif
 
 #if !defined(inw) && !defined(_inw)
 #define _inw _inw
+#ifdef CONFIG_HAS_IOPORT
 static inline u16 _inw(unsigned long addr)
 {
 	u16 val;
@@ -562,10 +568,15 @@ static inline u16 _inw(unsigned long addr)
 	__io_par(val);
 	return val;
 }
+#else
+u16 _inw(unsigned long addr)
+	__compiletime_error("inw() requires CONFIG_HAS_IOPORT");
+#endif
 #endif
 
 #if !defined(inl) && !defined(_inl)
 #define _inl _inl
+#ifdef CONFIG_HAS_IOPORT
 static inline u32 _inl(unsigned long addr)
 {
 	u32 val;
@@ -575,36 +586,55 @@ static inline u32 _inl(unsigned long addr)
 	__io_par(val);
 	return val;
 }
+#else
+u32 _inl(unsigned long addr)
+	__compiletime_error("inl() requires CONFIG_HAS_IOPORT");
+#endif
 #endif
 
 #if !defined(outb) && !defined(_outb)
 #define _outb _outb
+#ifdef CONFIG_HAS_IOPORT
 static inline void _outb(u8 value, unsigned long addr)
 {
 	__io_pbw();
 	__raw_writeb(value, PCI_IOBASE + addr);
 	__io_paw();
 }
+#else
+void _outb(u8 value, unsigned long addr)
+	__compiletime_error("outb() requires CONFIG_HAS_IOPORT");
+#endif
 #endif
 
 #if !defined(outw) && !defined(_outw)
 #define _outw _outw
+#ifdef CONFIG_HAS_IOPORT
 static inline void _outw(u16 value, unsigned long addr)
 {
 	__io_pbw();
 	__raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr);
 	__io_paw();
 }
+#else
+void _outw(u16 value, unsigned long addr)
+	__compiletime_error("outw() requires CONFIG_HAS_IOPORT");
+#endif
 #endif
 
 #if !defined(outl) && !defined(_outl)
 #define _outl _outl
+#ifdef CONFIG_HAS_IOPORT
 static inline void _outl(u32 value, unsigned long addr)
 {
 	__io_pbw();
 	__raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr);
 	__io_paw();
 }
+#else
+void _outl(u32 value, unsigned long addr)
+	__compiletime_error("outl() requires CONFIG_HAS_IOPORT");
+#endif
 #endif
 
 #include <linux/logic_pio.h>
@@ -688,53 +718,83 @@ static inline void outl_p(u32 value, unsigned long addr)
 
 #ifndef insb
 #define insb insb
+#ifdef CONFIG_HAS_IOPORT
 static inline void insb(unsigned long addr, void *buffer, unsigned int count)
 {
 	readsb(PCI_IOBASE + addr, buffer, count);
 }
+#else
+void insb(unsigned long addr, void *buffer, unsigned int count)
+	__compiletime_error("insb() requires HAS_IOPORT");
+#endif
 #endif
 
 #ifndef insw
 #define insw insw
+#ifdef CONFIG_HAS_IOPORT
 static inline void insw(unsigned long addr, void *buffer, unsigned int count)
 {
 	readsw(PCI_IOBASE + addr, buffer, count);
 }
+#else
+void insw(unsigned long addr, void *buffer, unsigned int count)
+	__compiletime_error("insw() requires HAS_IOPORT");
+#endif
 #endif
 
 #ifndef insl
 #define insl insl
+#ifdef CONFIG_HAS_IOPORT
 static inline void insl(unsigned long addr, void *buffer, unsigned int count)
 {
 	readsl(PCI_IOBASE + addr, buffer, count);
 }
+#else
+void insl(unsigned long addr, void *buffer, unsigned int count)
+	__compiletime_error("insl() requires HAS_IOPORT");
+#endif
 #endif
 
 #ifndef outsb
 #define outsb outsb
+#ifdef CONFIG_HAS_IOPORT
 static inline void outsb(unsigned long addr, const void *buffer,
 			 unsigned int count)
 {
 	writesb(PCI_IOBASE + addr, buffer, count);
 }
+#else
+void outsb(unsigned long addr, const void *buffer, unsigned int count)
+	__compiletime_error("outsb() requires HAS_IOPORT");
+#endif
 #endif
 
 #ifndef outsw
 #define outsw outsw
+#ifdef CONFIG_HAS_IOPORT
 static inline void outsw(unsigned long addr, const void *buffer,
 			 unsigned int count)
 {
 	writesw(PCI_IOBASE + addr, buffer, count);
 }
+#else
+void outsw(unsigned long addr, const void *buffer, unsigned int count)
+	__compiletime_error("outsw() requires HAS_IOPORT");
+#endif
 #endif
 
 #ifndef outsl
 #define outsl outsl
+#ifdef CONFIG_HAS_IOPORT
 static inline void outsl(unsigned long addr, const void *buffer,
 			 unsigned int count)
 {
 	writesl(PCI_IOBASE + addr, buffer, count);
 }
+#else
+void outsl(unsigned long addr, const void *buffer, unsigned int count)
+	__compiletime_error("outsl() requires HAS_IOPORT");
+#endif
 #endif
 
 #ifndef insb_p
@@ -1151,7 +1211,6 @@ static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 #endif
 
 #ifndef memset_io
-#define memset_io memset_io
 /**
  * memset_io	Set a range of I/O memory to a constant value
  * @addr:	The beginning of the I/O-memory range to set
@@ -1160,15 +1219,10 @@ static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
  *
  * Set a range of I/O memory to a given value.
  */
-static inline void memset_io(volatile void __iomem *addr, int value,
-			     size_t size)
-{
-	memset(__io_virt(addr), value, size);
-}
+void memset_io(volatile void __iomem *addr, int val, size_t count);
 #endif
 
 #ifndef memcpy_fromio
-#define memcpy_fromio memcpy_fromio
 /**
  * memcpy_fromio	Copy a block of data from I/O memory
  * @dst:		The (RAM) destination for the copy
@@ -1177,16 +1231,10 @@ static inline void memset_io(volatile void __iomem *addr, int value,
  *
  * Copy a block of data from I/O memory.
  */
-static inline void memcpy_fromio(void *buffer,
-				 const volatile void __iomem *addr,
-				 size_t size)
-{
-	memcpy(buffer, __io_virt(addr), size);
-}
+void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count);
 #endif
 
 #ifndef memcpy_toio
-#define memcpy_toio memcpy_toio
 /**
  * memcpy_toio		Copy a block of data into I/O memory
  * @dst:		The (I/O memory) destination for the copy
@@ -1195,11 +1243,7 @@ static inline void memcpy_fromio(void *buffer,
  *
  * Copy a block of data to I/O memory.
  */
-static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
-			       size_t size)
-{
-	memcpy(__io_virt(addr), buffer, size);
-}
+void memcpy_toio(volatile void __iomem *dst, const void *src, size_t count);
 #endif
 
 extern int devmem_is_allowed(unsigned long pfn);
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 6796abe1900e..6d1fb6162ac1 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -64,6 +64,19 @@ static inline int pfn_valid(unsigned long pfn)
 #define page_to_pfn __page_to_pfn
 #define pfn_to_page __pfn_to_page
 
+#ifdef CONFIG_DEBUG_VIRTUAL
+#define page_to_phys(page)						\
+({									\
+	unsigned long __pfn = page_to_pfn(page);			\
+									\
+	WARN_ON_ONCE(!pfn_valid(__pfn));				\
+	PFN_PHYS(__pfn);						\
+})
+#else
+#define page_to_phys(page)	PFN_PHYS(page_to_pfn(page))
+#endif /* CONFIG_DEBUG_VIRTUAL */
+#define phys_to_page(phys)	pfn_to_page(PHYS_PFN(phys))
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/include/asm-generic/vga.h b/include/asm-generic/vga.h
index adf91a783b5c..5dcaf4ae904a 100644
--- a/include/asm-generic/vga.h
+++ b/include/asm-generic/vga.h
@@ -1,25 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- *	Access to VGA videoram
- *
- *	(c) 1998 Martin Mares <mj@ucw.cz>
- */
 #ifndef __ASM_GENERIC_VGA_H
 #define __ASM_GENERIC_VGA_H
-
-/*
- *	On most architectures that support VGA, we can just
- *	recalculate addresses and then access the videoram
- *	directly without any black magic.
- *
- *	Everyone else needs to ioremap the address and use
- *	proper I/O accesses.
- */
-#ifndef VGA_MAP_MEM
-#define VGA_MAP_MEM(x, s) (unsigned long)phys_to_virt(x)
-#endif
-
-#define vga_readb(x) (*(x))
-#define vga_writeb(x, y) (*(y) = (x))
-
-#endif /* _ASM_GENERIC_VGA_H */
+#endif /* __ASM_GENERIC_VGA_H */
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 4ab65874a850..743b4afaad4c 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -505,7 +505,11 @@ struct uart_port {
 	 * The remaining bits are serial-core specific and not modifiable by
 	 * userspace.
 	 */
+#ifdef CONFIG_HAS_IOPORT
 #define UPF_FOURPORT		((__force upf_t) ASYNC_FOURPORT       /* 1  */ )
+#else
+#define UPF_FOURPORT		0
+#endif
 #define UPF_SAK			((__force upf_t) ASYNC_SAK            /* 2  */ )
 #define UPF_SPD_HI		((__force upf_t) ASYNC_SPD_HI         /* 4  */ )
 #define UPF_SPD_VHI		((__force upf_t) ASYNC_SPD_VHI        /* 5  */ )
diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h
index 919d999a8c1d..b6eeb8cb6070 100644
--- a/include/linux/vt_buffer.h
+++ b/include/linux/vt_buffer.h
@@ -28,45 +28,21 @@
 #ifndef VT_BUF_HAVE_MEMSETW
 static inline void scr_memsetw(u16 *s, u16 c, unsigned int count)
 {
-#ifdef VT_BUF_HAVE_RW
-	count /= 2;
-	while (count--)
-		scr_writew(c, s++);
-#else
 	memset16(s, c, count / 2);
-#endif
 }
 #endif
 
 #ifndef VT_BUF_HAVE_MEMCPYW
 static inline void scr_memcpyw(u16 *d, const u16 *s, unsigned int count)
 {
-#ifdef VT_BUF_HAVE_RW
-	count /= 2;
-	while (count--)
-		scr_writew(scr_readw(s++), d++);
-#else
 	memcpy(d, s, count);
-#endif
 }
 #endif
 
 #ifndef VT_BUF_HAVE_MEMMOVEW
 static inline void scr_memmovew(u16 *d, const u16 *s, unsigned int count)
 {
-#ifdef VT_BUF_HAVE_RW
-	if (d < s)
-		scr_memcpyw(d, s, count);
-	else {
-		count /= 2;
-		d += count;
-		s += count;
-		while (count--)
-			scr_writew(scr_readw(--s), --d);
-	}
-#else
 	memmove(d, s, count);
-#endif
 }
 #endif
 
diff --git a/include/uapi/asm-generic/ioctl.h b/include/uapi/asm-generic/ioctl.h
index a84f4db8a250..e3290a5824c9 100644
--- a/include/uapi/asm-generic/ioctl.h
+++ b/include/uapi/asm-generic/ioctl.h
@@ -82,13 +82,13 @@
  * NOTE: _IOW means userland is writing and kernel is reading. _IOR
  * means userland is reading and kernel is writing.
  */
-#define _IO(type,nr)		_IOC(_IOC_NONE,(type),(nr),0)
-#define _IOR(type,nr,size)	_IOC(_IOC_READ,(type),(nr),(_IOC_TYPECHECK(size)))
-#define _IOW(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(size)))
-#define _IOWR(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(size)))
-#define _IOR_BAD(type,nr,size)	_IOC(_IOC_READ,(type),(nr),sizeof(size))
-#define _IOW_BAD(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),sizeof(size))
-#define _IOWR_BAD(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
+#define _IO(type,nr)			_IOC(_IOC_NONE,(type),(nr),0)
+#define _IOR(type,nr,argtype)		_IOC(_IOC_READ,(type),(nr),(_IOC_TYPECHECK(argtype)))
+#define _IOW(type,nr,argtype)		_IOC(_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(argtype)))
+#define _IOWR(type,nr,argtype)		_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(argtype)))
+#define _IOR_BAD(type,nr,argtype)	_IOC(_IOC_READ,(type),(nr),sizeof(argtype))
+#define _IOW_BAD(type,nr,argtype)	_IOC(_IOC_WRITE,(type),(nr),sizeof(argtype))
+#define _IOWR_BAD(type,nr,argtype)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(argtype))
 
 /* used to decode ioctl numbers.. */
 #define _IOC_DIR(nr)		(((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)