Auto-update from upstream

213 files changed, 8896 insertions, 1871 deletions

diff --git a/include/asm-alpha/socket.h b/include/asm-alpha/socket.h
index d00259d3dc78..b5193229132a 100644
--- a/include/asm-alpha/socket.h
+++ b/include/asm-alpha/socket.h
@@ -25,6 +25,8 @@
 #define SO_ERROR        0x1007
 #define SO_SNDBUF       0x1001
 #define SO_RCVBUF       0x1002
+#define SO_SNDBUFFORCE  0x100a
+#define SO_RCVBUFFORCE  0x100b
 #define SO_RCVLOWAT     0x1010
 #define SO_SNDLOWAT     0x1011
 #define SO_RCVTIMEO     0x1012
diff --git a/include/asm-arm/arch-sa1100/mcp.h b/include/asm-arm/arch-sa1100/mcp.h
new file mode 100644
index 000000000000..f58a22755c61
--- /dev/null
+++ b/include/asm-arm/arch-sa1100/mcp.h
@@ -0,0 +1,21 @@
+/*
+ *  linux/include/asm-arm/arch-sa1100/mcp.h
+ *
+ *  Copyright (C) 2005 Russell King.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_ARM_ARCH_MCP_H
+#define __ASM_ARM_ARCH_MCP_H
+
+#include <linux/types.h>
+
+struct mcp_plat_data {
+        u32 mccr0;
+        u32 mccr1;
+        unsigned int sclk_rate;
+};
+
+#endif
diff --git a/include/asm-arm/hardware/gic.h b/include/asm-arm/hardware/gic.h
new file mode 100644
index 000000000000..3fa5eb70f64e
--- /dev/null
+++ b/include/asm-arm/hardware/gic.h
@@ -0,0 +1,41 @@
+/*
+ *  linux/include/asm-arm/hardware/gic.h
+ *
+ *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_ARM_HARDWARE_GIC_H
+#define __ASM_ARM_HARDWARE_GIC_H
+
+#include <linux/compiler.h>
+
+#define GIC_CPU_CTRL                    0x00
+#define GIC_CPU_PRIMASK                 0x04
+#define GIC_CPU_BINPOINT                0x08
+#define GIC_CPU_INTACK                  0x0c
+#define GIC_CPU_EOI                     0x10
+#define GIC_CPU_RUNNINGPRI              0x14
+#define GIC_CPU_HIGHPRI                 0x18
+
+#define GIC_DIST_CTRL                   0x000
+#define GIC_DIST_CTR                    0x004
+#define GIC_DIST_ENABLE_SET             0x100
+#define GIC_DIST_ENABLE_CLEAR           0x180
+#define GIC_DIST_PENDING_SET            0x200
+#define GIC_DIST_PENDING_CLEAR          0x280
+#define GIC_DIST_ACTIVE_BIT             0x300
+#define GIC_DIST_PRI                    0x400
+#define GIC_DIST_TARGET                 0x800
+#define GIC_DIST_CONFIG                 0xc00
+#define GIC_DIST_SOFTINT                0xf00
+
+#ifndef __ASSEMBLY__
+void gic_dist_init(void __iomem *base);
+void gic_cpu_init(void __iomem *base);
+void gic_raise_softirq(cpumask_t cpumask, unsigned int irq);
+#endif
+
+#endif
diff --git a/include/asm-arm/socket.h b/include/asm-arm/socket.h
index 46d20585d951..3c51da6438c9 100644
--- a/include/asm-arm/socket.h
+++ b/include/asm-arm/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-arm26/socket.h b/include/asm-arm26/socket.h
index 46d20585d951..3c51da6438c9 100644
--- a/include/asm-arm26/socket.h
+++ b/include/asm-arm26/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-cris/socket.h b/include/asm-cris/socket.h
index f159b4f165f7..8b1da3e58c55 100644
--- a/include/asm-cris/socket.h
+++ b/include/asm-cris/socket.h
@@ -16,6 +16,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-frv/socket.h b/include/asm-frv/socket.h
index c3be17c7de4b..7177f8b9817c 100644
--- a/include/asm-frv/socket.h
+++ b/include/asm-frv/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-h8300/socket.h b/include/asm-h8300/socket.h
index af33b8525dcf..d98cf85bafc1 100644
--- a/include/asm-h8300/socket.h
+++ b/include/asm-h8300/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-i386/checksum.h b/include/asm-i386/checksum.h
index f949e44c2a35..67d3630c4e89 100644
--- a/include/asm-i386/checksum.h
+++ b/include/asm-i386/checksum.h
@@ -83,7 +83,7 @@ static inline unsigned short ip_fast_csum(unsigned char * iph,
             "adcl $0, %0        ;\n"
             "notl %0            ;\n"
 "2:                             ;\n"
-        /* Since the input registers which are loaded with iph and ipl
+        /* Since the input registers which are loaded with iph and ihl
            are modified, we must also specify them as outputs, or gcc
            will assume they contain their original values. */
         : "=r" (sum), "=r" (iph), "=r" (ihl)
diff --git a/include/asm-i386/socket.h b/include/asm-i386/socket.h
index 07f6b38ad140..802ae76195b7 100644
--- a/include/asm-i386/socket.h
+++ b/include/asm-i386/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-ia64/socket.h b/include/asm-ia64/socket.h
index 21a9f10d6baa..a255006fb7b5 100644
--- a/include/asm-ia64/socket.h
+++ b/include/asm-ia64/socket.h
@@ -23,6 +23,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-m32r/checksum.h b/include/asm-m32r/checksum.h
index 99f37dbf2558..877ebf46e9ff 100644
--- a/include/asm-m32r/checksum.h
+++ b/include/asm-m32r/checksum.h
@@ -105,7 +105,7 @@ static inline unsigned short ip_fast_csum(unsigned char * iph,
                 "       addx    %0, %3 \n"
                 "       .fillinsn\n"
                 "2: \n"
-        /* Since the input registers which are loaded with iph and ipl
+        /* Since the input registers which are loaded with iph and ihl
            are modified, we must also specify them as outputs, or gcc
            will assume they contain their original values. */
         : "=&r" (sum), "=r" (iph), "=r" (ihl), "=&r" (tmpreg0), "=&r" (tmpreg1)
diff --git a/include/asm-m32r/socket.h b/include/asm-m32r/socket.h
index 159519d99042..8b6680f223c0 100644
--- a/include/asm-m32r/socket.h
+++ b/include/asm-m32r/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-m68k/socket.h b/include/asm-m68k/socket.h
index 8d0b9fc2d07e..f578ca4b776a 100644
--- a/include/asm-m68k/socket.h
+++ b/include/asm-m68k/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-mips/socket.h b/include/asm-mips/socket.h
index 020b4db70ee5..d478a86294ee 100644
--- a/include/asm-mips/socket.h
+++ b/include/asm-mips/socket.h
@@ -37,6 +37,8 @@ To add: #define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
 #define SO_ERROR        0x1007  /* get error status and clear */
 #define SO_SNDBUF       0x1001  /* Send buffer size. */
 #define SO_RCVBUF       0x1002  /* Receive buffer. */
+#define SO_SNDBUFFORCE  0x100a
+#define SO_RCVBUFFORCE  0x100b
 #define SO_SNDLOWAT     0x1003  /* send low-water mark */
 #define SO_RCVLOWAT     0x1004  /* receive low-water mark */
 #define SO_SNDTIMEO     0x1005  /* send timeout */
diff --git a/include/asm-parisc/socket.h b/include/asm-parisc/socket.h
index 4a77996c1862..1bf54dc53c10 100644
--- a/include/asm-parisc/socket.h
+++ b/include/asm-parisc/socket.h
@@ -16,6 +16,8 @@
 /* To add :#define SO_REUSEPORT 0x0200 */
 #define SO_SNDBUF       0x1001
 #define SO_RCVBUF       0x1002
+#define SO_SNDBUFFORCE  0x100a
+#define SO_RCVBUFFORCE  0x100b
 #define SO_SNDLOWAT     0x1003
 #define SO_RCVLOWAT     0x1004
 #define SO_SNDTIMEO     0x1005
diff --git a/include/asm-ppc/8253pit.h b/include/asm-powerpc/8253pit.h
index 285f78488ccb..862708a749b0 100644
--- a/include/asm-ppc/8253pit.h
+++ b/include/asm-powerpc/8253pit.h
@@ -5,6 +5,6 @@
 #ifndef _8253PIT_H
 #define _8253PIT_H
 
-#define PIT_TICK_RATE   1193182UL
+#define PIT_TICK_RATE   1193182UL
 
 #endif
diff --git a/include/asm-ppc/agp.h b/include/asm-powerpc/agp.h
index ca9e423307f4..ca9e423307f4 100644
--- a/include/asm-ppc/agp.h
+++ b/include/asm-powerpc/agp.h
diff --git a/include/asm-powerpc/cputime.h b/include/asm-powerpc/cputime.h
new file mode 100644
index 000000000000..6d68ad7e0ea3
--- /dev/null
+++ b/include/asm-powerpc/cputime.h
@@ -0,0 +1 @@
+#include <asm-generic/cputime.h>
diff --git a/include/asm-ppc/div64.h b/include/asm-powerpc/div64.h
index 6cd978cefb28..6cd978cefb28 100644
--- a/include/asm-ppc/div64.h
+++ b/include/asm-powerpc/div64.h
diff --git a/include/asm-powerpc/emergency-restart.h b/include/asm-powerpc/emergency-restart.h
new file mode 100644
index 000000000000..3711bd9d50bd
--- /dev/null
+++ b/include/asm-powerpc/emergency-restart.h
@@ -0,0 +1 @@
+#include <asm-generic/emergency-restart.h>
diff --git a/include/asm-ppc/errno.h b/include/asm-powerpc/errno.h
index 19f20bd41ae6..19f20bd41ae6 100644
--- a/include/asm-ppc/errno.h
+++ b/include/asm-powerpc/errno.h
diff --git a/include/asm-ppc/ioctl.h b/include/asm-powerpc/ioctl.h
index 93c6acfdd0fd..93c6acfdd0fd 100644
--- a/include/asm-ppc/ioctl.h
+++ b/include/asm-powerpc/ioctl.h
diff --git a/include/asm-ppc/ioctls.h b/include/asm-powerpc/ioctls.h
index f5b7f2b055e7..f5b7f2b055e7 100644
--- a/include/asm-ppc/ioctls.h
+++ b/include/asm-powerpc/ioctls.h
diff --git a/include/asm-ppc/ipc.h b/include/asm-powerpc/ipc.h
index a46e3d9c2a3f..a46e3d9c2a3f 100644
--- a/include/asm-ppc/ipc.h
+++ b/include/asm-powerpc/ipc.h
diff --git a/include/asm-ppc/linkage.h b/include/asm-powerpc/linkage.h
index 291c2d01c44f..291c2d01c44f 100644
--- a/include/asm-ppc/linkage.h
+++ b/include/asm-powerpc/linkage.h
diff --git a/include/asm-ppc64/local.h b/include/asm-powerpc/local.h
index c11c530f74d0..c11c530f74d0 100644
--- a/include/asm-ppc64/local.h
+++ b/include/asm-powerpc/local.h
diff --git a/include/asm-ppc/namei.h b/include/asm-powerpc/namei.h
index 29c9ec832133..29c9ec832133 100644
--- a/include/asm-ppc/namei.h
+++ b/include/asm-powerpc/namei.h
diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h
new file mode 100644
index 000000000000..06a959d67234
--- /dev/null
+++ b/include/asm-powerpc/percpu.h
@@ -0,0 +1 @@
+#include <asm-generic/percpu.h>
diff --git a/include/asm-ppc/poll.h b/include/asm-powerpc/poll.h
index be5024913c62..be5024913c62 100644
--- a/include/asm-ppc/poll.h
+++ b/include/asm-powerpc/poll.h
diff --git a/include/asm-powerpc/resource.h b/include/asm-powerpc/resource.h
new file mode 100644
index 000000000000..04bc4db8921b
--- /dev/null
+++ b/include/asm-powerpc/resource.h
@@ -0,0 +1 @@
+#include <asm-generic/resource.h>
diff --git a/include/asm-ppc/shmparam.h b/include/asm-powerpc/shmparam.h
index d6250602ae64..d6250602ae64 100644
--- a/include/asm-ppc/shmparam.h
+++ b/include/asm-powerpc/shmparam.h
diff --git a/include/asm-ppc/string.h b/include/asm-powerpc/string.h
index 225575997392..225575997392 100644
--- a/include/asm-ppc/string.h
+++ b/include/asm-powerpc/string.h
diff --git a/include/asm-ppc/unaligned.h b/include/asm-powerpc/unaligned.h
index 45520d9b85d1..45520d9b85d1 100644
--- a/include/asm-ppc/unaligned.h
+++ b/include/asm-powerpc/unaligned.h
diff --git a/include/asm-ppc/xor.h b/include/asm-powerpc/xor.h
index c82eb12a5b18..c82eb12a5b18 100644
--- a/include/asm-ppc/xor.h
+++ b/include/asm-powerpc/xor.h
diff --git a/include/asm-ppc/cputime.h b/include/asm-ppc/cputime.h
deleted file mode 100644
index 8e9faf5ce720..000000000000
--- a/include/asm-ppc/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __PPC_CPUTIME_H
-#define __PPC_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __PPC_CPUTIME_H */
diff --git a/include/asm-ppc/emergency-restart.h b/include/asm-ppc/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/include/asm-ppc/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/include/asm-ppc/hdreg.h b/include/asm-ppc/hdreg.h
deleted file mode 100644
index 7f7fd1af0af3..000000000000
--- a/include/asm-ppc/hdreg.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/hdreg.h>
diff --git a/include/asm-ppc/local.h b/include/asm-ppc/local.h
deleted file mode 100644
index b08e3eced10e..000000000000
--- a/include/asm-ppc/local.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __PPC_LOCAL_H
-#define __PPC_LOCAL_H
-
-#include <asm-generic/local.h>
-
-#endif /* __PPC_LOCAL_H */
diff --git a/include/asm-ppc/percpu.h b/include/asm-ppc/percpu.h
deleted file mode 100644
index d66667cd5878..000000000000
--- a/include/asm-ppc/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ARCH_PPC_PERCPU__
-#define __ARCH_PPC_PERCPU__
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ARCH_PPC_PERCPU__ */
diff --git a/include/asm-ppc/resource.h b/include/asm-ppc/resource.h
deleted file mode 100644
index 86a1ea23a6ed..000000000000
--- a/include/asm-ppc/resource.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _PPC_RESOURCE_H
-#define _PPC_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif
diff --git a/include/asm-ppc/socket.h b/include/asm-ppc/socket.h
index 4134376b0f66..296e1a3469d0 100644
--- a/include/asm-ppc/socket.h
+++ b/include/asm-ppc/socket.h
@@ -20,6 +20,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-ppc64/8253pit.h b/include/asm-ppc64/8253pit.h
deleted file mode 100644
index 285f78488ccb..000000000000
--- a/include/asm-ppc64/8253pit.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/*
- * 8253/8254 Programmable Interval Timer
- */
-
-#ifndef _8253PIT_H
-#define _8253PIT_H
-
-#define PIT_TICK_RATE   1193182UL
-
-#endif
diff --git a/include/asm-ppc64/abs_addr.h b/include/asm-ppc64/abs_addr.h
index 6d4e8e787058..84c24d4cdb71 100644
--- a/include/asm-ppc64/abs_addr.h
+++ b/include/asm-ppc64/abs_addr.h
@@ -16,93 +16,51 @@
 #include <asm/page.h>
 #include <asm/prom.h>
 #include <asm/lmb.h>
+#include <asm/firmware.h>
 
-typedef u32 msChunks_entry;
-struct msChunks {
+struct mschunks_map {
         unsigned long num_chunks;
         unsigned long chunk_size;
         unsigned long chunk_shift;
         unsigned long chunk_mask;
-        msChunks_entry *abs;
+        u32 *mapping;
 };
 
-extern struct msChunks msChunks;
+extern struct mschunks_map mschunks_map;
 
-extern unsigned long msChunks_alloc(unsigned long, unsigned long, unsigned long);
-extern unsigned long reloc_offset(void);
+/* Chunks are 256 KB */
+#define MSCHUNKS_CHUNK_SHIFT    (18)
+#define MSCHUNKS_CHUNK_SIZE     (1UL << MSCHUNKS_CHUNK_SHIFT)
+#define MSCHUNKS_OFFSET_MASK    (MSCHUNKS_CHUNK_SIZE - 1)
 
-#ifdef CONFIG_MSCHUNKS
-
-static inline unsigned long
-chunk_to_addr(unsigned long chunk)
+static inline unsigned long chunk_to_addr(unsigned long chunk)
 {
-        unsigned long offset = reloc_offset();
-        struct msChunks *_msChunks = PTRRELOC(&msChunks);
-
-        return chunk << _msChunks->chunk_shift;
+        return chunk << MSCHUNKS_CHUNK_SHIFT;
 }
 
-static inline unsigned long
-addr_to_chunk(unsigned long addr)
+static inline unsigned long addr_to_chunk(unsigned long addr)
 {
-        unsigned long offset = reloc_offset();
-        struct msChunks *_msChunks = PTRRELOC(&msChunks);
-
-        return addr >> _msChunks->chunk_shift;
+        return addr >> MSCHUNKS_CHUNK_SHIFT;
 }
 
-static inline unsigned long
-chunk_offset(unsigned long addr)
+static inline unsigned long phys_to_abs(unsigned long pa)
 {
-        unsigned long offset = reloc_offset();
-        struct msChunks *_msChunks = PTRRELOC(&msChunks);
+        unsigned long chunk;
 
-        return addr & _msChunks->chunk_mask;
-}
+        /* This is a no-op on non-iSeries */
+        if (!firmware_has_feature(FW_FEATURE_ISERIES))
+                return pa;
 
-static inline unsigned long
-abs_chunk(unsigned long pchunk)
-{
-        unsigned long offset = reloc_offset();
-        struct msChunks *_msChunks = PTRRELOC(&msChunks);
-        if ( pchunk >= _msChunks->num_chunks ) {
-                return pchunk;
-        }
-        return PTRRELOC(_msChunks->abs)[pchunk];
-}
+        chunk = addr_to_chunk(pa);
 
-/* A macro so it can take pointers or unsigned long. */
-#define phys_to_abs(pa)                                              \
-        ({ unsigned long _pa = (unsigned long)(pa);                          \
-           chunk_to_addr(abs_chunk(addr_to_chunk(_pa))) + chunk_offset(_pa); \
-        })
+        if (chunk < mschunks_map.num_chunks)
+                chunk = mschunks_map.mapping[chunk];
 
-static inline unsigned long
-physRpn_to_absRpn(unsigned long rpn)
-{
-        unsigned long pa = rpn << PAGE_SHIFT;
-        unsigned long aa = phys_to_abs(pa);
-        return (aa >> PAGE_SHIFT);
+        return chunk_to_addr(chunk) + (pa & MSCHUNKS_OFFSET_MASK);
 }
 
-/* A macro so it can take pointers or unsigned long. */
-#define abs_to_phys(aa) lmb_abs_to_phys((unsigned long)(aa))
-
-#else  /* !CONFIG_MSCHUNKS */
-
-#define chunk_to_addr(chunk) ((unsigned long)(chunk))
-#define addr_to_chunk(addr) (addr)
-#define chunk_offset(addr) (0)
-#define abs_chunk(pchunk) (pchunk)
-
-#define phys_to_abs(pa) (pa)
-#define physRpn_to_absRpn(rpn) (rpn)
-#define abs_to_phys(aa) (aa)
-
-#endif /* !CONFIG_MSCHUNKS */
-
 /* Convenience macros */
 #define virt_to_abs(va) phys_to_abs(__pa(va))
-#define abs_to_virt(aa) __va(abs_to_phys(aa))
+#define abs_to_virt(aa) __va(aa)
 
 #endif /* _ABS_ADDR_H */
diff --git a/include/asm-ppc64/agp.h b/include/asm-ppc64/agp.h
deleted file mode 100644
index ca9e423307f4..000000000000
--- a/include/asm-ppc64/agp.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef AGP_H
-#define AGP_H 1
-
-#include <asm/io.h>
-
-/* nothing much needed here */
-
-#define map_page_into_agp(page)
-#define unmap_page_from_agp(page)
-#define flush_agp_mappings()
-#define flush_agp_cache() mb()
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)         \
-        ((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)   \
-        free_pages((unsigned long)(table), (order))
-
-#endif
diff --git a/include/asm-ppc64/cputable.h b/include/asm-ppc64/cputable.h
index d67fa9e26079..ae6cf3830108 100644
--- a/include/asm-ppc64/cputable.h
+++ b/include/asm-ppc64/cputable.h
@@ -56,11 +56,6 @@ struct cpu_spec {
          * BHT, SPD, etc... from head.S before branching to identify_machine
          */
         cpu_setup_t     cpu_setup;
-
-        /* This is used to identify firmware features which are available
-         * to the kernel.
-         */
-        unsigned long   firmware_features;
 };
 
 extern struct cpu_spec          cpu_specs[];
@@ -71,39 +66,6 @@ static inline unsigned long cpu_has_feature(unsigned long feature)
         return cur_cpu_spec->cpu_features & feature;
 }
 
-
-/* firmware feature bitmask values */
-#define FIRMWARE_MAX_FEATURES 63
-
-#define FW_FEATURE_PFT          (1UL<<0)
-#define FW_FEATURE_TCE          (1UL<<1)        
-#define FW_FEATURE_SPRG0        (1UL<<2)        
-#define FW_FEATURE_DABR         (1UL<<3)        
-#define FW_FEATURE_COPY         (1UL<<4)        
-#define FW_FEATURE_ASR          (1UL<<5)        
-#define FW_FEATURE_DEBUG        (1UL<<6)        
-#define FW_FEATURE_TERM         (1UL<<7)        
-#define FW_FEATURE_PERF         (1UL<<8)        
-#define FW_FEATURE_DUMP         (1UL<<9)        
-#define FW_FEATURE_INTERRUPT    (1UL<<10)       
-#define FW_FEATURE_MIGRATE      (1UL<<11)       
-#define FW_FEATURE_PERFMON      (1UL<<12)       
-#define FW_FEATURE_CRQ          (1UL<<13)       
-#define FW_FEATURE_VIO          (1UL<<14)       
-#define FW_FEATURE_RDMA         (1UL<<15)       
-#define FW_FEATURE_LLAN         (1UL<<16)       
-#define FW_FEATURE_BULK         (1UL<<17)       
-#define FW_FEATURE_XDABR        (1UL<<18)       
-#define FW_FEATURE_MULTITCE     (1UL<<19)       
-#define FW_FEATURE_SPLPAR       (1UL<<20)       
-
-typedef struct {
-    unsigned long val;
-    char * name;
-} firmware_feature_t;
-
-extern firmware_feature_t firmware_features_table[];
-
 #endif /* __ASSEMBLY__ */
 
 /* CPU kernel features */
@@ -140,10 +102,8 @@ extern firmware_feature_t firmware_features_table[];
 #define CPU_FTR_MMCRA_SIHV              ASM_CONST(0x0000080000000000)
 #define CPU_FTR_CTRL                    ASM_CONST(0x0000100000000000)
 
-/* Platform firmware features */
-#define FW_FTR_                         ASM_CONST(0x0000000000000001)
-
 #ifndef __ASSEMBLY__
+
 #define COMMON_USER_PPC64       (PPC_FEATURE_32 | PPC_FEATURE_64 | \
                                  PPC_FEATURE_HAS_FPU | PPC_FEATURE_HAS_MMU)
 
@@ -156,10 +116,9 @@ extern firmware_feature_t firmware_features_table[];
 #define CPU_FTR_PPCAS_ARCH_V2   (CPU_FTR_PPCAS_ARCH_V2_BASE)
 #else
 #define CPU_FTR_PPCAS_ARCH_V2   (CPU_FTR_PPCAS_ARCH_V2_BASE | CPU_FTR_16M_PAGE)
-#endif
+#endif /* CONFIG_PPC_ISERIES */
 
-#define COMMON_PPC64_FW (0)
-#endif
+#endif /* __ASSEMBLY */
 
 #ifdef __ASSEMBLY__
 
diff --git a/include/asm-ppc64/cputime.h b/include/asm-ppc64/cputime.h
deleted file mode 100644
index 8e9faf5ce720..000000000000
--- a/include/asm-ppc64/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __PPC_CPUTIME_H
-#define __PPC_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __PPC_CPUTIME_H */
diff --git a/include/asm-ppc64/div64.h b/include/asm-ppc64/div64.h
deleted file mode 100644
index 6cd978cefb28..000000000000
--- a/include/asm-ppc64/div64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/div64.h>
diff --git a/include/asm-ppc64/emergency-restart.h b/include/asm-ppc64/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/include/asm-ppc64/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/include/asm-ppc64/errno.h b/include/asm-ppc64/errno.h
deleted file mode 100644
index 69bc3b0c6cbe..000000000000
--- a/include/asm-ppc64/errno.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef _PPC64_ERRNO_H
-#define _PPC64_ERRNO_H
-
-/* 
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <asm-generic/errno.h>
-
-#undef  EDEADLOCK
-#define EDEADLOCK       58      /* File locking deadlock error */
-
-#define _LAST_ERRNO     516
-
-#endif
diff --git a/include/asm-ppc64/firmware.h b/include/asm-ppc64/firmware.h
new file mode 100644
index 000000000000..22bb85cf60af
--- /dev/null
+++ b/include/asm-ppc64/firmware.h
@@ -0,0 +1,101 @@
+/*
+ *  include/asm-ppc64/firmware.h
+ *
+ *  Extracted from include/asm-ppc64/cputable.h
+ *
+ *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ *  Modifications for ppc64:
+ *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+#ifndef __ASM_PPC_FIRMWARE_H
+#define __ASM_PPC_FIRMWARE_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+/* firmware feature bitmask values */
+#define FIRMWARE_MAX_FEATURES 63
+
+#define FW_FEATURE_PFT          (1UL<<0)
+#define FW_FEATURE_TCE          (1UL<<1)
+#define FW_FEATURE_SPRG0        (1UL<<2)
+#define FW_FEATURE_DABR         (1UL<<3)
+#define FW_FEATURE_COPY         (1UL<<4)
+#define FW_FEATURE_ASR          (1UL<<5)
+#define FW_FEATURE_DEBUG        (1UL<<6)
+#define FW_FEATURE_TERM         (1UL<<7)
+#define FW_FEATURE_PERF         (1UL<<8)
+#define FW_FEATURE_DUMP         (1UL<<9)
+#define FW_FEATURE_INTERRUPT    (1UL<<10)
+#define FW_FEATURE_MIGRATE      (1UL<<11)
+#define FW_FEATURE_PERFMON      (1UL<<12)
+#define FW_FEATURE_CRQ          (1UL<<13)
+#define FW_FEATURE_VIO          (1UL<<14)
+#define FW_FEATURE_RDMA         (1UL<<15)
+#define FW_FEATURE_LLAN         (1UL<<16)
+#define FW_FEATURE_BULK         (1UL<<17)
+#define FW_FEATURE_XDABR        (1UL<<18)
+#define FW_FEATURE_MULTITCE     (1UL<<19)
+#define FW_FEATURE_SPLPAR       (1UL<<20)
+#define FW_FEATURE_ISERIES      (1UL<<21)
+
+enum {
+        FW_FEATURE_PSERIES_POSSIBLE = FW_FEATURE_PFT | FW_FEATURE_TCE |
+                FW_FEATURE_SPRG0 | FW_FEATURE_DABR | FW_FEATURE_COPY |
+                FW_FEATURE_ASR | FW_FEATURE_DEBUG | FW_FEATURE_TERM |
+                FW_FEATURE_PERF | FW_FEATURE_DUMP | FW_FEATURE_INTERRUPT |
+                FW_FEATURE_MIGRATE | FW_FEATURE_PERFMON | FW_FEATURE_CRQ |
+                FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
+                FW_FEATURE_BULK | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE |
+                FW_FEATURE_SPLPAR,
+        FW_FEATURE_PSERIES_ALWAYS = 0,
+        FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES,
+        FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES,
+        FW_FEATURE_POSSIBLE =
+#ifdef CONFIG_PPC_PSERIES
+                FW_FEATURE_PSERIES_POSSIBLE |
+#endif
+#ifdef CONFIG_PPC_ISERIES
+                FW_FEATURE_ISERIES_POSSIBLE |
+#endif
+                0,
+        FW_FEATURE_ALWAYS =
+#ifdef CONFIG_PPC_PSERIES
+                FW_FEATURE_PSERIES_ALWAYS &
+#endif
+#ifdef CONFIG_PPC_ISERIES
+                FW_FEATURE_ISERIES_ALWAYS &
+#endif
+                FW_FEATURE_POSSIBLE,
+};
+
+/* This is used to identify firmware features which are available
+ * to the kernel.
+ */
+extern unsigned long    ppc64_firmware_features;
+
+static inline unsigned long firmware_has_feature(unsigned long feature)
+{
+        return (FW_FEATURE_ALWAYS & feature) ||
+                (FW_FEATURE_POSSIBLE & ppc64_firmware_features & feature);
+}
+
+#ifdef CONFIG_PPC_PSERIES
+typedef struct {
+    unsigned long val;
+    char * name;
+} firmware_feature_t;
+
+extern firmware_feature_t firmware_features_table[];
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+#endif /* __ASM_PPC_FIRMWARE_H */
diff --git a/include/asm-ppc64/hdreg.h b/include/asm-ppc64/hdreg.h
deleted file mode 100644
index 7f7fd1af0af3..000000000000
--- a/include/asm-ppc64/hdreg.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/hdreg.h>
diff --git a/include/asm-ppc64/imalloc.h b/include/asm-ppc64/imalloc.h
index e46ff68a6e41..42adf7033a81 100644
--- a/include/asm-ppc64/imalloc.h
+++ b/include/asm-ppc64/imalloc.h
@@ -6,7 +6,7 @@
  */
 #define PHBS_IO_BASE      VMALLOC_END
 #define IMALLOC_BASE      (PHBS_IO_BASE + 0x80000000ul) /* Reserve 2 gigs for PHBs */
-#define IMALLOC_END       (VMALLOC_START + EADDR_MASK)
+#define IMALLOC_END       (VMALLOC_START + PGTABLE_RANGE)
 
 
 /* imalloc region types */
diff --git a/include/asm-ppc64/ioctl.h b/include/asm-ppc64/ioctl.h
deleted file mode 100644
index 42b8c5da7fbc..000000000000
--- a/include/asm-ppc64/ioctl.h
+++ /dev/null
@@ -1,74 +0,0 @@
-#ifndef _PPC64_IOCTL_H
-#define _PPC64_IOCTL_H
-
-
-/*
- * This was copied from the alpha as it's a bit cleaner there.
- *                         -- Cort
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define _IOC_NRBITS     8
-#define _IOC_TYPEBITS   8
-#define _IOC_SIZEBITS   13
-#define _IOC_DIRBITS    3
-
-#define _IOC_NRMASK     ((1 << _IOC_NRBITS)-1)
-#define _IOC_TYPEMASK   ((1 << _IOC_TYPEBITS)-1)
-#define _IOC_SIZEMASK   ((1 << _IOC_SIZEBITS)-1)
-#define _IOC_DIRMASK    ((1 << _IOC_DIRBITS)-1)
-
-#define _IOC_NRSHIFT    0
-#define _IOC_TYPESHIFT  (_IOC_NRSHIFT+_IOC_NRBITS)
-#define _IOC_SIZESHIFT  (_IOC_TYPESHIFT+_IOC_TYPEBITS)
-#define _IOC_DIRSHIFT   (_IOC_SIZESHIFT+_IOC_SIZEBITS)
-
-/*
- * Direction bits _IOC_NONE could be 0, but OSF/1 gives it a bit.
- * And this turns out useful to catch old ioctl numbers in header
- * files for us.
- */
-#define _IOC_NONE       1U
-#define _IOC_READ       2U
-#define _IOC_WRITE      4U
-
-#define _IOC(dir,type,nr,size) \
-        (((dir)  << _IOC_DIRSHIFT) | \
-         ((type) << _IOC_TYPESHIFT) | \
-         ((nr)   << _IOC_NRSHIFT) | \
-         ((size) << _IOC_SIZESHIFT))
-
-/* provoke compile error for invalid uses of size argument */
-extern unsigned int __invalid_size_argument_for_IOC;
-#define _IOC_TYPECHECK(t) \
-       ((sizeof(t) == sizeof(t[1]) && \
-         sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
-         sizeof(t) : __invalid_size_argument_for_IOC)
-
-/* used to create numbers */
-#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))
-
-/* used to decode them.. */
-#define _IOC_DIR(nr)            (((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
-#define _IOC_TYPE(nr)           (((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
-#define _IOC_NR(nr)             (((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
-#define _IOC_SIZE(nr)           (((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
-
-/* various drivers, such as the pcmcia stuff, need these... */
-#define IOC_IN          (_IOC_WRITE << _IOC_DIRSHIFT)
-#define IOC_OUT         (_IOC_READ << _IOC_DIRSHIFT)
-#define IOC_INOUT       ((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
-#define IOCSIZE_MASK    (_IOC_SIZEMASK << _IOC_SIZESHIFT)
-#define IOCSIZE_SHIFT   (_IOC_SIZESHIFT)
-
-#endif /* _PPC64_IOCTL_H */
diff --git a/include/asm-ppc64/ioctls.h b/include/asm-ppc64/ioctls.h
deleted file mode 100644
index 48796bf3e4fc..000000000000
--- a/include/asm-ppc64/ioctls.h
+++ /dev/null
@@ -1,114 +0,0 @@
-#ifndef _ASM_PPC64_IOCTLS_H
-#define _ASM_PPC64_IOCTLS_H
-
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <asm/ioctl.h>
-
-#define FIOCLEX         _IO('f', 1)
-#define FIONCLEX        _IO('f', 2)
-#define FIOASYNC        _IOW('f', 125, int)
-#define FIONBIO         _IOW('f', 126, int)
-#define FIONREAD        _IOR('f', 127, int)
-#define TIOCINQ         FIONREAD
-#define FIOQSIZE        _IOR('f', 128, loff_t)
-
-#define TIOCGETP        _IOR('t', 8, struct sgttyb)
-#define TIOCSETP        _IOW('t', 9, struct sgttyb)
-#define TIOCSETN        _IOW('t', 10, struct sgttyb)    /* TIOCSETP wo flush */
-
-#define TIOCSETC        _IOW('t', 17, struct tchars)
-#define TIOCGETC        _IOR('t', 18, struct tchars)
-#define TCGETS          _IOR('t', 19, struct termios)
-#define TCSETS          _IOW('t', 20, struct termios)
-#define TCSETSW         _IOW('t', 21, struct termios)
-#define TCSETSF         _IOW('t', 22, struct termios)
-
-#define TCGETA          _IOR('t', 23, struct termio)
-#define TCSETA          _IOW('t', 24, struct termio)
-#define TCSETAW         _IOW('t', 25, struct termio)
-#define TCSETAF         _IOW('t', 28, struct termio)
-
-#define TCSBRK          _IO('t', 29)
-#define TCXONC          _IO('t', 30)
-#define TCFLSH          _IO('t', 31)
-
-#define TIOCSWINSZ      _IOW('t', 103, struct winsize)
-#define TIOCGWINSZ      _IOR('t', 104, struct winsize)
-#define TIOCSTART       _IO('t', 110)           /* start output, like ^Q */
-#define TIOCSTOP        _IO('t', 111)           /* stop output, like ^S */
-#define TIOCOUTQ        _IOR('t', 115, int)     /* output queue size */
-
-#define TIOCGLTC        _IOR('t', 116, struct ltchars)
-#define TIOCSLTC        _IOW('t', 117, struct ltchars)
-#define TIOCSPGRP       _IOW('t', 118, int)
-#define TIOCGPGRP       _IOR('t', 119, int)
-
-#define TIOCEXCL        0x540C
-#define TIOCNXCL        0x540D
-#define TIOCSCTTY       0x540E
-
-#define TIOCSTI         0x5412
-#define TIOCMGET        0x5415
-#define TIOCMBIS        0x5416
-#define TIOCMBIC        0x5417
-#define TIOCMSET        0x5418
-# define TIOCM_LE       0x001
-# define TIOCM_DTR      0x002
-# define TIOCM_RTS      0x004
-# define TIOCM_ST       0x008
-# define TIOCM_SR       0x010
-# define TIOCM_CTS      0x020
-# define TIOCM_CAR      0x040
-# define TIOCM_RNG      0x080
-# define TIOCM_DSR      0x100
-# define TIOCM_CD       TIOCM_CAR
-# define TIOCM_RI       TIOCM_RNG
-
-#define TIOCGSOFTCAR    0x5419
-#define TIOCSSOFTCAR    0x541A
-#define TIOCLINUX       0x541C
-#define TIOCCONS        0x541D
-#define TIOCGSERIAL     0x541E
-#define TIOCSSERIAL     0x541F
-#define TIOCPKT         0x5420
-# define TIOCPKT_DATA            0
-# define TIOCPKT_FLUSHREAD       1
-# define TIOCPKT_FLUSHWRITE      2
-# define TIOCPKT_STOP            4
-# define TIOCPKT_START           8
-# define TIOCPKT_NOSTOP         16
-# define TIOCPKT_DOSTOP         32
-
-
-#define TIOCNOTTY       0x5422
-#define TIOCSETD        0x5423
-#define TIOCGETD        0x5424
-#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
-#define TIOCSBRK        0x5427  /* BSD compatibility */
-#define TIOCCBRK        0x5428  /* BSD compatibility */
-#define TIOCGSID        0x5429  /* Return the session ID of FD */
-#define TIOCGPTN        _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK      _IOW('T',0x31, int)  /* Lock/unlock Pty */
-
-#define TIOCSERCONFIG   0x5453
-#define TIOCSERGWILD    0x5454
-#define TIOCSERSWILD    0x5455
-#define TIOCGLCKTRMIOS  0x5456
-#define TIOCSLCKTRMIOS  0x5457
-#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
-#define TIOCSERGETLSR   0x5459 /* Get line status register */
-  /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-# define TIOCSER_TEMT    0x01   /* Transmitter physically empty */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
-#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
-
-#endif /* _ASM_PPC64_IOCTLS_H */
diff --git a/include/asm-ppc64/iommu.h b/include/asm-ppc64/iommu.h
index 729de5cc21d9..72dcf8116b04 100644
--- a/include/asm-ppc64/iommu.h
+++ b/include/asm-ppc64/iommu.h
@@ -104,9 +104,6 @@ extern void iommu_devnode_init_pSeries(struct device_node *dn);
 
 #ifdef CONFIG_PPC_ISERIES
 
-/* Initializes tables for bio buses */
-extern void __init iommu_vio_init(void);
-
 struct iSeries_Device_Node;
 /* Creates table for an individual device node */
 extern void iommu_devnode_init_iSeries(struct iSeries_Device_Node *dn);
diff --git a/include/asm-ppc64/ipc.h b/include/asm-ppc64/ipc.h
deleted file mode 100644
index a46e3d9c2a3f..000000000000
--- a/include/asm-ppc64/ipc.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ipc.h>
diff --git a/include/asm-ppc64/linkage.h b/include/asm-ppc64/linkage.h
deleted file mode 100644
index 291c2d01c44f..000000000000
--- a/include/asm-ppc64/linkage.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
-
-/* Nothing to see here... */
-
-#endif
diff --git a/include/asm-ppc64/lmb.h b/include/asm-ppc64/lmb.h
index a6cbca21ac1d..cb368bf0f264 100644
--- a/include/asm-ppc64/lmb.h
+++ b/include/asm-ppc64/lmb.h
@@ -22,7 +22,6 @@
 
 struct lmb_property {
         unsigned long base;
-        unsigned long physbase;
         unsigned long size;
 };
 
diff --git a/include/asm-ppc64/machdep.h b/include/asm-ppc64/machdep.h
index f0ef06375947..ff2c9287d3b6 100644
--- a/include/asm-ppc64/machdep.h
+++ b/include/asm-ppc64/machdep.h
@@ -140,6 +140,9 @@ struct machdep_calls {
 
         /* Idle loop for this platform, leave empty for default idle loop */
         int             (*idle_loop)(void);
+
+        /* Function to enable pmcs for this platform, called once per cpu. */
+        void            (*enable_pmcs)(void);
 };
 
 extern int default_idle(void);
diff --git a/include/asm-ppc64/mmu.h b/include/asm-ppc64/mmu.h
index 70348a851313..ad36bb28de29 100644
--- a/include/asm-ppc64/mmu.h
+++ b/include/asm-ppc64/mmu.h
@@ -28,9 +28,12 @@
 #define STE_VSID_SHIFT  12
 
 /* Location of cpu0's segment table */
-#define STAB0_PAGE      0x9
+#define STAB0_PAGE      0x6
 #define STAB0_PHYS_ADDR (STAB0_PAGE<<PAGE_SHIFT)
-#define STAB0_VIRT_ADDR (KERNELBASE+STAB0_PHYS_ADDR)
+
+#ifndef __ASSEMBLY__
+extern char initial_stab[];
+#endif /* ! __ASSEMBLY */
 
 /*
  * SLB
@@ -259,8 +262,10 @@ extern void stabs_alloc(void);
 #define VSID_BITS       36
 #define VSID_MODULUS    ((1UL<<VSID_BITS)-1)
 
-#define CONTEXT_BITS    20
-#define USER_ESID_BITS  15
+#define CONTEXT_BITS    19
+#define USER_ESID_BITS  16
+
+#define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT))
 
 /*
  * This macro generates asm code to compute the VSID scramble
@@ -302,8 +307,7 @@ typedef unsigned long mm_context_id_t;
 typedef struct {
         mm_context_id_t id;
 #ifdef CONFIG_HUGETLB_PAGE
-        pgd_t *huge_pgdir;
-        u16 htlb_segs; /* bitmask */
+        u16 low_htlb_areas, high_htlb_areas;
 #endif
 } mm_context_t;
 
diff --git a/include/asm-ppc64/naca.h b/include/asm-ppc64/naca.h
index bfb7caa32eaf..d2afe6447597 100644
--- a/include/asm-ppc64/naca.h
+++ b/include/asm-ppc64/naca.h
@@ -12,8 +12,6 @@
 
 #include <asm/types.h>
 
-#ifndef __ASSEMBLY__
-
 struct naca_struct {
         /* Kernel only data - undefined for user space */
         void *xItVpdAreas;              /* VPD Data                  0x00 */
@@ -23,9 +21,4 @@ struct naca_struct {
 
 extern struct naca_struct naca;
 
-#endif /* __ASSEMBLY__ */
-
-#define NACA_PAGE      0x4
-#define NACA_PHYS_ADDR (NACA_PAGE<<PAGE_SHIFT)
-
 #endif /* _NACA_H */
diff --git a/include/asm-ppc64/namei.h b/include/asm-ppc64/namei.h
deleted file mode 100644
index a1412a2d102a..000000000000
--- a/include/asm-ppc64/namei.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* 
- * linux/include/asm-ppc/namei.h
- * Adapted from linux/include/asm-alpha/namei.h
- *
- * Included from linux/fs/namei.c
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef __PPC64_NAMEI_H
-#define __PPC64_NAMEI_H
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-
-#define __emul_prefix() NULL
-
-#endif /* __PPC64_NAMEI_H */
diff --git a/include/asm-ppc64/page.h b/include/asm-ppc64/page.h
index a5893a305a09..a79a08df62bd 100644
--- a/include/asm-ppc64/page.h
+++ b/include/asm-ppc64/page.h
@@ -37,39 +37,45 @@
 
 #define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
 
-/* For 64-bit processes the hugepage range is 1T-1.5T */
-#define TASK_HPAGE_BASE ASM_CONST(0x0000010000000000)
-#define TASK_HPAGE_END  ASM_CONST(0x0000018000000000)
+#define HTLB_AREA_SHIFT         40
+#define HTLB_AREA_SIZE          (1UL << HTLB_AREA_SHIFT)
+#define GET_HTLB_AREA(x)        ((x) >> HTLB_AREA_SHIFT)
 
 #define LOW_ESID_MASK(addr, len)        (((1U << (GET_ESID(addr+len-1)+1)) \
                                         - (1U << GET_ESID(addr))) & 0xffff)
+#define HTLB_AREA_MASK(addr, len)       (((1U << (GET_HTLB_AREA(addr+len-1)+1)) \
+                                        - (1U << GET_HTLB_AREA(addr))) & 0xffff)
 
 #define ARCH_HAS_HUGEPAGE_ONLY_RANGE
 #define ARCH_HAS_PREPARE_HUGEPAGE_RANGE
+#define ARCH_HAS_SETCLEAR_HUGE_PTE
 
 #define touches_hugepage_low_range(mm, addr, len) \
-        (LOW_ESID_MASK((addr), (len)) & mm->context.htlb_segs)
-#define touches_hugepage_high_range(addr, len) \
-        (((addr) > (TASK_HPAGE_BASE-(len))) && ((addr) < TASK_HPAGE_END))
+        (LOW_ESID_MASK((addr), (len)) & (mm)->context.low_htlb_areas)
+#define touches_hugepage_high_range(mm, addr, len) \
+        (HTLB_AREA_MASK((addr), (len)) & (mm)->context.high_htlb_areas)
 
 #define __within_hugepage_low_range(addr, len, segmask) \
         ((LOW_ESID_MASK((addr), (len)) | (segmask)) == (segmask))
 #define within_hugepage_low_range(addr, len) \
         __within_hugepage_low_range((addr), (len), \
-                                    current->mm->context.htlb_segs)
-#define within_hugepage_high_range(addr, len) (((addr) >= TASK_HPAGE_BASE) \
-          && ((addr)+(len) <= TASK_HPAGE_END) && ((addr)+(len) >= (addr)))
+                                    current->mm->context.low_htlb_areas)
+#define __within_hugepage_high_range(addr, len, zonemask) \
+        ((HTLB_AREA_MASK((addr), (len)) | (zonemask)) == (zonemask))
+#define within_hugepage_high_range(addr, len) \
+        __within_hugepage_high_range((addr), (len), \
+                                    current->mm->context.high_htlb_areas)
 
 #define is_hugepage_only_range(mm, addr, len) \
-        (touches_hugepage_high_range((addr), (len)) || \
+        (touches_hugepage_high_range((mm), (addr), (len)) || \
           touches_hugepage_low_range((mm), (addr), (len)))
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 
 #define in_hugepage_area(context, addr) \
         (cpu_has_feature(CPU_FTR_16M_PAGE) && \
-         ( (((addr) >= TASK_HPAGE_BASE) && ((addr) < TASK_HPAGE_END)) || \
+         ( ((1 << GET_HTLB_AREA(addr)) & (context).high_htlb_areas) || \
            ( ((addr) < 0x100000000L) && \
-             ((1 << GET_ESID(addr)) & (context).htlb_segs) ) ) )
+             ((1 << GET_ESID(addr)) & (context).low_htlb_areas) ) ) )
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
@@ -125,36 +131,42 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag
  * Entries in the pte table are 64b, while entries in the pgd & pmd are 32b.
  */
 typedef struct { unsigned long pte; } pte_t;
-typedef struct { unsigned int  pmd; } pmd_t;
-typedef struct { unsigned int  pgd; } pgd_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pud; } pud_t;
+typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 
 #define pte_val(x)      ((x).pte)
 #define pmd_val(x)      ((x).pmd)
+#define pud_val(x)      ((x).pud)
 #define pgd_val(x)      ((x).pgd)
 #define pgprot_val(x)   ((x).pgprot)
 
-#define __pte(x)        ((pte_t) { (x) } )
-#define __pmd(x)        ((pmd_t) { (x) } )
-#define __pgd(x)        ((pgd_t) { (x) } )
-#define __pgprot(x)     ((pgprot_t) { (x) } )
+#define __pte(x)        ((pte_t) { (x) })
+#define __pmd(x)        ((pmd_t) { (x) })
+#define __pud(x)        ((pud_t) { (x) })
+#define __pgd(x)        ((pgd_t) { (x) })
+#define __pgprot(x)     ((pgprot_t) { (x) })
 
 #else
 /*
  * .. while these make it easier on the compiler
  */
 typedef unsigned long pte_t;
-typedef unsigned int  pmd_t;
-typedef unsigned int  pgd_t;
+typedef unsigned long pmd_t;
+typedef unsigned long pud_t;
+typedef unsigned long pgd_t;
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)      (x)
 #define pmd_val(x)      (x)
+#define pud_val(x)      (x)
 #define pgd_val(x)      (x)
 #define pgprot_val(x)   (x)
 
 #define __pte(x)        (x)
 #define __pmd(x)        (x)
+#define __pud(x)        (x)
 #define __pgd(x)        (x)
 #define __pgprot(x)     (x)
 
@@ -208,9 +220,6 @@ extern u64 ppc64_pft_size;		/* Log 2 of page table size */
 #define USER_REGION_ID     (0UL)
 #define REGION_ID(ea)      (((unsigned long)(ea)) >> REGION_SHIFT)
 
-#define __bpn_to_ba(x) ((((unsigned long)(x)) << PAGE_SHIFT) + KERNELBASE)
-#define __ba_to_bpn(x) ((((unsigned long)(x)) & ~REGION_MASK) >> PAGE_SHIFT)
-
 #define __va(x) ((void *)((unsigned long)(x) + KERNELBASE))
 
 #ifdef CONFIG_DISCONTIGMEM
diff --git a/include/asm-ppc64/param.h b/include/asm-ppc64/param.h
index 1fad38dcf707..76c212d475b3 100644
--- a/include/asm-ppc64/param.h
+++ b/include/asm-ppc64/param.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_PPC64_PARAM_H
 #define _ASM_PPC64_PARAM_H
 
+#include <linux/config.h>
+
 /*
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -9,7 +11,7 @@
  */
 
 #ifdef __KERNEL__
-# define HZ             1000            /* Internal kernel timer frequency */
+# define HZ             CONFIG_HZ       /* Internal kernel timer frequency */
 # define USER_HZ        100             /* .. some user interfaces are in "ticks" */
 # define CLOCKS_PER_SEC (USER_HZ)       /* like times() */
 #endif
diff --git a/include/asm-ppc64/percpu.h b/include/asm-ppc64/percpu.h
deleted file mode 100644
index 60a659a4ce1f..000000000000
--- a/include/asm-ppc64/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ARCH_PPC64_PERCPU__
-#define __ARCH_PPC64_PERCPU__
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ARCH_PPC64_PERCPU__ */
diff --git a/include/asm-ppc64/pgalloc.h b/include/asm-ppc64/pgalloc.h
index 4fc4b739b380..26bc49c1108d 100644
--- a/include/asm-ppc64/pgalloc.h
+++ b/include/asm-ppc64/pgalloc.h
@@ -6,7 +6,12 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
-extern kmem_cache_t *zero_cache;
+extern kmem_cache_t *pgtable_cache[];
+
+#define PTE_CACHE_NUM   0
+#define PMD_CACHE_NUM   1
+#define PUD_CACHE_NUM   1
+#define PGD_CACHE_NUM   0
 
 /*
  * This program is free software; you can redistribute it and/or
@@ -15,30 +20,40 @@ extern kmem_cache_t *zero_cache;
  * 2 of the License, or (at your option) any later version.
  */
 
-static inline pgd_t *
-pgd_alloc(struct mm_struct *mm)
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-        return kmem_cache_alloc(zero_cache, GFP_KERNEL);
+        return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
 }
 
-static inline void
-pgd_free(pgd_t *pgd)
+static inline void pgd_free(pgd_t *pgd)
 {
-        kmem_cache_free(zero_cache, pgd);
+        kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
+}
+
+#define pgd_populate(MM, PGD, PUD)      pgd_set(PGD, PUD)
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+        return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
+                                GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(pud_t *pud)
+{
+        kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
 }
 
 #define pud_populate(MM, PUD, PMD)      pud_set(PUD, PMD)
 
-static inline pmd_t *
-pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(zero_cache, GFP_KERNEL|__GFP_REPEAT);
+        return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
+                                GFP_KERNEL|__GFP_REPEAT);
 }
 
-static inline void
-pmd_free(pmd_t *pmd)
+static inline void pmd_free(pmd_t *pmd)
 {
-        kmem_cache_free(zero_cache, pmd);
+        kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
 }
 
 #define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, pte)
@@ -47,44 +62,58 @@ pmd_free(pmd_t *pmd)
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-        return kmem_cache_alloc(zero_cache, GFP_KERNEL|__GFP_REPEAT);
+        return kmem_cache_alloc(pgtable_cache[PTE_CACHE_NUM],
+                                GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = kmem_cache_alloc(zero_cache, GFP_KERNEL|__GFP_REPEAT);
-        if (pte)
-                return virt_to_page(pte);
-        return NULL;
+        return virt_to_page(pte_alloc_one_kernel(mm, address));
 }
                 
 static inline void pte_free_kernel(pte_t *pte)
 {
-        kmem_cache_free(zero_cache, pte);
+        kmem_cache_free(pgtable_cache[PTE_CACHE_NUM], pte);
 }
 
 static inline void pte_free(struct page *ptepage)
 {
-        kmem_cache_free(zero_cache, page_address(ptepage));
+        pte_free_kernel(page_address(ptepage));
 }
 
-struct pte_freelist_batch
+#define PGF_CACHENUM_MASK       0xf
+
+typedef struct pgtable_free {
+        unsigned long val;
+} pgtable_free_t;
+
+static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
+                                                unsigned long mask)
 {
-        struct rcu_head rcu;
-        unsigned int    index;
-        struct page *   pages[0];
-};
+        BUG_ON(cachenum > PGF_CACHENUM_MASK);
 
-#define PTE_FREELIST_SIZE       ((PAGE_SIZE - sizeof(struct pte_freelist_batch)) / \
-                                  sizeof(struct page *))
+        return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
+}
 
-extern void pte_free_now(struct page *ptepage);
-extern void pte_free_submit(struct pte_freelist_batch *batch);
+static inline void pgtable_free(pgtable_free_t pgf)
+{
+        void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
+        int cachenum = pgf.val & PGF_CACHENUM_MASK;
 
-DECLARE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
+        kmem_cache_free(pgtable_cache[cachenum], p);
+}
 
-void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage);
-#define __pmd_free_tlb(tlb, pmd)        __pte_free_tlb(tlb, virt_to_page(pmd))
+void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+
+#define __pte_free_tlb(tlb, ptepage)    \
+        pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
+                PTE_CACHE_NUM, PTE_TABLE_SIZE-1))
+#define __pmd_free_tlb(tlb, pmd)        \
+        pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
+                PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
+#define __pud_free_tlb(tlb, pmd)        \
+        pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
+                PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
 
 #define check_pgt_cache()       do { } while (0)
 
diff --git a/include/asm-ppc64/pgtable.h b/include/asm-ppc64/pgtable.h
index 46cf61c2ff69..c83679c9d2b0 100644
--- a/include/asm-ppc64/pgtable.h
+++ b/include/asm-ppc64/pgtable.h
@@ -15,19 +15,24 @@
 #include <asm/tlbflush.h>
 #endif /* __ASSEMBLY__ */
 
-#include <asm-generic/pgtable-nopud.h>
-
 /*
  * Entries per page directory level.  The PTE level must use a 64b record
  * for each page table entry.  The PMD and PGD level use a 32b record for 
  * each entry by assuming that each entry is page aligned.
  */
 #define PTE_INDEX_SIZE  9
-#define PMD_INDEX_SIZE  10
-#define PGD_INDEX_SIZE  10
+#define PMD_INDEX_SIZE  7
+#define PUD_INDEX_SIZE  7
+#define PGD_INDEX_SIZE  9
+
+#define PTE_TABLE_SIZE  (sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE  (sizeof(pmd_t) << PMD_INDEX_SIZE)
+#define PUD_TABLE_SIZE  (sizeof(pud_t) << PUD_INDEX_SIZE)
+#define PGD_TABLE_SIZE  (sizeof(pgd_t) << PGD_INDEX_SIZE)
 
 #define PTRS_PER_PTE    (1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PMD    (1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PUD    (1 << PMD_INDEX_SIZE)
 #define PTRS_PER_PGD    (1 << PGD_INDEX_SIZE)
 
 /* PMD_SHIFT determines what a second-level page table entry can map */
@@ -35,8 +40,13 @@
 #define PMD_SIZE        (1UL << PMD_SHIFT)
 #define PMD_MASK        (~(PMD_SIZE-1))
 
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define PGDIR_SHIFT     (PMD_SHIFT + PMD_INDEX_SIZE)
+/* PUD_SHIFT determines what a third-level page table entry can map */
+#define PUD_SHIFT       (PMD_SHIFT + PMD_INDEX_SIZE)
+#define PUD_SIZE        (1UL << PUD_SHIFT)
+#define PUD_MASK        (~(PUD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT     (PUD_SHIFT + PUD_INDEX_SIZE)
 #define PGDIR_SIZE      (1UL << PGDIR_SHIFT)
 #define PGDIR_MASK      (~(PGDIR_SIZE-1))
 
@@ -45,15 +55,23 @@
 /*
  * Size of EA range mapped by our pagetables.
  */
-#define EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
-                    PGD_INDEX_SIZE + PAGE_SHIFT)
-#define EADDR_MASK ((1UL << EADDR_SIZE) - 1)
+#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
+                            PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
+#define PGTABLE_RANGE (1UL << PGTABLE_EADDR_SIZE)
+
+#if TASK_SIZE_USER64 > PGTABLE_RANGE
+#error TASK_SIZE_USER64 exceeds pagetable range
+#endif
+
+#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT))
+#error TASK_SIZE_USER64 exceeds user VSID range
+#endif
 
 /*
  * Define the address range of the vmalloc VM area.
  */
 #define VMALLOC_START (0xD000000000000000ul)
-#define VMALLOC_SIZE  (0x10000000000UL)
+#define VMALLOC_SIZE  (0x80000000000UL)
 #define VMALLOC_END   (VMALLOC_START + VMALLOC_SIZE)
 
 /*
@@ -154,8 +172,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
 #ifndef __ASSEMBLY__
 int hash_huge_page(struct mm_struct *mm, unsigned long access,
                    unsigned long ea, unsigned long vsid, int local);
-
-void hugetlb_mm_free_pgd(struct mm_struct *mm);
 #endif /* __ASSEMBLY__ */
 
 #define HAVE_ARCH_UNMAPPED_AREA
@@ -163,7 +179,6 @@ void hugetlb_mm_free_pgd(struct mm_struct *mm);
 #else
 
 #define hash_huge_page(mm,a,ea,vsid,local)      -1
-#define hugetlb_mm_free_pgd(mm)                 do {} while (0)
 
 #endif
 
@@ -197,39 +212,45 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 #define pte_pfn(x)              ((unsigned long)((pte_val(x) >> PTE_SHIFT)))
 #define pte_page(x)             pfn_to_page(pte_pfn(x))
 
-#define pmd_set(pmdp, ptep)     \
-        (pmd_val(*(pmdp)) = __ba_to_bpn(ptep))
+#define pmd_set(pmdp, ptep)     ({BUG_ON((u64)ptep < KERNELBASE); pmd_val(*(pmdp)) = (unsigned long)(ptep);})
 #define pmd_none(pmd)           (!pmd_val(pmd))
 #define pmd_bad(pmd)            (pmd_val(pmd) == 0)
 #define pmd_present(pmd)        (pmd_val(pmd) != 0)
 #define pmd_clear(pmdp)         (pmd_val(*(pmdp)) = 0)
-#define pmd_page_kernel(pmd)    (__bpn_to_ba(pmd_val(pmd)))
+#define pmd_page_kernel(pmd)    (pmd_val(pmd))
 #define pmd_page(pmd)           virt_to_page(pmd_page_kernel(pmd))
 
-#define pud_set(pudp, pmdp)     (pud_val(*(pudp)) = (__ba_to_bpn(pmdp)))
+#define pud_set(pudp, pmdp)     (pud_val(*(pudp)) = (unsigned long)(pmdp))
 #define pud_none(pud)           (!pud_val(pud))
-#define pud_bad(pud)            ((pud_val(pud)) == 0UL)
-#define pud_present(pud)        (pud_val(pud) != 0UL)
-#define pud_clear(pudp)         (pud_val(*(pudp)) = 0UL)
-#define pud_page(pud)           (__bpn_to_ba(pud_val(pud)))
+#define pud_bad(pud)            ((pud_val(pud)) == 0)
+#define pud_present(pud)        (pud_val(pud) != 0)
+#define pud_clear(pudp)         (pud_val(*(pudp)) = 0)
+#define pud_page(pud)           (pud_val(pud))
+
+#define pgd_set(pgdp, pudp)     ({pgd_val(*(pgdp)) = (unsigned long)(pudp);})
+#define pgd_none(pgd)           (!pgd_val(pgd))
+#define pgd_bad(pgd)            (pgd_val(pgd) == 0)
+#define pgd_present(pgd)        (pgd_val(pgd) != 0)
+#define pgd_clear(pgdp)         (pgd_val(*(pgdp)) = 0)
+#define pgd_page(pgd)           (pgd_val(pgd))
 
 /* 
  * Find an entry in a page-table-directory.  We combine the address region 
  * (the high order N bits) and the pgd portion of the address.
  */
 /* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */
-#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x7ff)
+#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff)
 
 #define pgd_offset(mm, address)  ((mm)->pgd + pgd_index(address))
 
-/* Find an entry in the second-level page table.. */
+#define pud_offset(pgdp, addr)  \
+  (((pud_t *) pgd_page(*(pgdp))) + (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
+
 #define pmd_offset(pudp,addr) \
-  ((pmd_t *) pud_page(*(pudp)) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
+  (((pmd_t *) pud_page(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
 
-/* Find an entry in the third-level page table.. */
 #define pte_offset_kernel(dir,addr) \
-  ((pte_t *) pmd_page_kernel(*(dir)) \
- + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
+  (((pte_t *) pmd_page_kernel(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
 
 #define pte_offset_map(dir,addr)        pte_offset_kernel((dir), (addr))
 #define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr))
@@ -458,23 +479,20 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long addr,
 #define pte_same(A,B)   (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
 
 #define pmd_ERROR(e) \
-        printk("%s:%d: bad pmd %08x.\n", __FILE__, __LINE__, pmd_val(e))
+        printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pud_ERROR(e) \
+        printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pud_val(e))
 #define pgd_ERROR(e) \
-        printk("%s:%d: bad pgd %08x.\n", __FILE__, __LINE__, pgd_val(e))
+        printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
 extern pgd_t swapper_pg_dir[];
 
 extern void paging_init(void);
 
-/*
- * Because the huge pgtables are only 2 level, they can take
- * at most around 4M, much less than one hugepage which the
- * process is presumably entitled to use.  So we don't bother
- * freeing up the pagetables on unmap, and wait until
- * destroy_context() to clean up the lot.
- */
+#ifdef CONFIG_HUGETLB_PAGE
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
-                                                do { } while (0)
+        free_pgd_range(tlb, addr, end, floor, ceiling)
+#endif
 
 /*
  * This gets called at the end of handling a page fault, when
diff --git a/include/asm-ppc64/pmc.h b/include/asm-ppc64/pmc.h
index c924748c0bea..d1d297dbccfe 100644
--- a/include/asm-ppc64/pmc.h
+++ b/include/asm-ppc64/pmc.h
@@ -26,4 +26,6 @@ typedef void (*perf_irq_t)(struct pt_regs *);
 int reserve_pmc_hardware(perf_irq_t new_perf_irq);
 void release_pmc_hardware(void);
 
+void power4_enable_pmcs(void);
+
 #endif /* _PPC64_PMC_H */
diff --git a/include/asm-ppc64/poll.h b/include/asm-ppc64/poll.h
deleted file mode 100644
index 370fa3ba0db4..000000000000
--- a/include/asm-ppc64/poll.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef __PPC64_POLL_H
-#define __PPC64_POLL_H
-
-/*
- * Copyright (C) 2001 PPC64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define POLLIN          0x0001
-#define POLLPRI         0x0002
-#define POLLOUT         0x0004
-#define POLLERR         0x0008
-#define POLLHUP         0x0010
-#define POLLNVAL        0x0020
-#define POLLRDNORM      0x0040
-#define POLLRDBAND      0x0080
-#define POLLWRNORM      0x0100
-#define POLLWRBAND      0x0200
-#define POLLMSG         0x0400
-#define POLLREMOVE      0x1000
-
-struct pollfd {
-        int fd;
-        short events;
-        short revents;
-};
-
-#endif /* __PPC64_POLL_H */
diff --git a/include/asm-ppc64/processor.h b/include/asm-ppc64/processor.h
index 352306cfb579..7bd4796f1236 100644
--- a/include/asm-ppc64/processor.h
+++ b/include/asm-ppc64/processor.h
@@ -268,6 +268,7 @@
 #define PV_970FX        0x003C
 #define PV_630          0x0040
 #define PV_630p         0x0041
+#define PV_970MP        0x0044
 #define PV_BE           0x0070
 
 /* Platforms supported by PPC64 */
@@ -382,8 +383,8 @@ extern long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern struct task_struct *last_task_used_math;
 extern struct task_struct *last_task_used_altivec;
 
-/* 64-bit user address space is 41-bits (2TBs user VM) */
-#define TASK_SIZE_USER64 (0x0000020000000000UL)
+/* 64-bit user address space is 44-bits (16TB user VM) */
+#define TASK_SIZE_USER64 (0x0000100000000000UL)
 
 /* 
  * 32-bit user address space is 4GB - 1 page 
diff --git a/include/asm-ppc64/prom.h b/include/asm-ppc64/prom.h
index 04b1a84f7ca3..dc5330b39509 100644
--- a/include/asm-ppc64/prom.h
+++ b/include/asm-ppc64/prom.h
@@ -22,13 +22,15 @@
 #define RELOC(x)        (*PTRRELOC(&(x)))
 
 /* Definitions used by the flattened device tree */
-#define OF_DT_HEADER            0xd00dfeed      /* 4: version, 4: total size */
-#define OF_DT_BEGIN_NODE        0x1             /* Start node: full name */
+#define OF_DT_HEADER            0xd00dfeed      /* marker */
+#define OF_DT_BEGIN_NODE        0x1             /* Start of node, full name */
 #define OF_DT_END_NODE          0x2             /* End node */
-#define OF_DT_PROP              0x3             /* Property: name off, size, content */
+#define OF_DT_PROP              0x3             /* Property: name off, size,
+                                                 * content */
+#define OF_DT_NOP               0x4             /* nop */
 #define OF_DT_END               0x9
 
-#define OF_DT_VERSION           1
+#define OF_DT_VERSION           0x10
 
 /*
  * This is what gets passed to the kernel by prom_init or kexec
@@ -54,7 +56,9 @@ struct boot_param_header
         u32     version;                /* format version */
         u32     last_comp_version;      /* last compatible version */
         /* version 2 fields below */
-        u32     boot_cpuid_phys;        /* Which physical CPU id we're booting on */
+        u32     boot_cpuid_phys;        /* Physical CPU id we're booting on */
+        /* version 3 fields below */
+        u32     dt_strings_size;        /* size of the DT strings block */
 };
 
 
diff --git a/include/asm-ppc64/resource.h b/include/asm-ppc64/resource.h
deleted file mode 100644
index add031b9dfd4..000000000000
--- a/include/asm-ppc64/resource.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _PPC64_RESOURCE_H
-#define _PPC64_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif /* _PPC64_RESOURCE_H */
diff --git a/include/asm-ppc64/shmparam.h b/include/asm-ppc64/shmparam.h
deleted file mode 100644
index b2825ceff05e..000000000000
--- a/include/asm-ppc64/shmparam.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _PPC64_SHMPARAM_H
-#define _PPC64_SHMPARAM_H
-
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define SHMLBA PAGE_SIZE                 /* attach addr a multiple of this */
-
-#endif /* _PPC64_SHMPARAM_H */
diff --git a/include/asm-ppc64/socket.h b/include/asm-ppc64/socket.h
index 59e00dfc8b8e..9e1af8eb2d96 100644
--- a/include/asm-ppc64/socket.h
+++ b/include/asm-ppc64/socket.h
@@ -21,6 +21,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-ppc64/string.h b/include/asm-ppc64/string.h
deleted file mode 100644
index eeca68ef1e91..000000000000
--- a/include/asm-ppc64/string.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef _PPC64_STRING_H_
-#define _PPC64_STRING_H_
-
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define __HAVE_ARCH_STRCPY
-#define __HAVE_ARCH_STRNCPY
-#define __HAVE_ARCH_STRLEN
-#define __HAVE_ARCH_STRCMP
-#define __HAVE_ARCH_STRCAT
-#define __HAVE_ARCH_MEMSET
-#define __HAVE_ARCH_MEMCPY
-#define __HAVE_ARCH_MEMMOVE
-#define __HAVE_ARCH_MEMCMP
-#define __HAVE_ARCH_MEMCHR
-
-extern int strcasecmp(const char *, const char *);
-extern int strncasecmp(const char *, const char *, int);
-extern char * strcpy(char *,const char *);
-extern char * strncpy(char *,const char *, __kernel_size_t);
-extern __kernel_size_t strlen(const char *);
-extern int strcmp(const char *,const char *);
-extern char * strcat(char *, const char *);
-extern void * memset(void *,int,__kernel_size_t);
-extern void * memcpy(void *,const void *,__kernel_size_t);
-extern void * memmove(void *,const void *,__kernel_size_t);
-extern int memcmp(const void *,const void *,__kernel_size_t);
-extern void * memchr(const void *,int,__kernel_size_t);
-
-#endif /* _PPC64_STRING_H_ */
diff --git a/include/asm-ppc64/system.h b/include/asm-ppc64/system.h
index 98d120ca8a91..b9e1835351e9 100644
--- a/include/asm-ppc64/system.h
+++ b/include/asm-ppc64/system.h
@@ -88,7 +88,7 @@ DEBUGGER_BOILERPLATE(debugger_dabr_match)
 DEBUGGER_BOILERPLATE(debugger_fault_handler)
 
 #ifdef CONFIG_XMON
-extern void xmon_init(void);
+extern void xmon_init(int enable);
 #endif
 
 #else
@@ -302,5 +302,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 
 #define arch_align_stack(x) (x)
 
+extern unsigned long reloc_offset(void);
+
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/asm-ppc64/unaligned.h b/include/asm-ppc64/unaligned.h
deleted file mode 100644
index 636e93c4f379..000000000000
--- a/include/asm-ppc64/unaligned.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __PPC64_UNALIGNED_H
-#define __PPC64_UNALIGNED_H
-
-/*
- * The PowerPC can do unaligned accesses itself in big endian mode. 
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define get_unaligned(ptr) (*(ptr))
-
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
-
-#endif /* __PPC64_UNALIGNED_H */
diff --git a/include/asm-ppc64/vio.h b/include/asm-ppc64/vio.h
index 20cd98ee6337..03f1b95f433b 100644
--- a/include/asm-ppc64/vio.h
+++ b/include/asm-ppc64/vio.h
@@ -19,13 +19,15 @@
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/mod_devicetable.h>
+
 #include <asm/hvcall.h>
-#include <asm/prom.h>
 #include <asm/scatterlist.h>
-/* 
+
+/*
  * Architecture-specific constants for drivers to
  * extract attributes of the device using vio_get_attribute()
-*/
+ */
 #define VETH_MAC_ADDR "local-mac-address"
 #define VETH_MCAST_FILTER_SIZE "ibm,mac-address-filters"
 
@@ -37,64 +39,65 @@
 #define VIO_IRQ_DISABLE         0UL
 #define VIO_IRQ_ENABLE          1UL
 
-struct vio_dev;
-struct vio_driver;
-struct vio_device_id;
 struct iommu_table;
 
-int vio_register_driver(struct vio_driver *drv);
-void vio_unregister_driver(struct vio_driver *drv);
-
-#ifdef CONFIG_PPC_PSERIES
-struct vio_dev * __devinit vio_register_device_node(
-                struct device_node *node_vdev);
-#endif
-void __devinit vio_unregister_device(struct vio_dev *dev);
-struct vio_dev *vio_find_node(struct device_node *vnode);
-
-const void * vio_get_attribute(struct vio_dev *vdev, void* which, int* length);
-int vio_get_irq(struct vio_dev *dev);
-int vio_enable_interrupts(struct vio_dev *dev);
-int vio_disable_interrupts(struct vio_dev *dev);
-
-extern struct dma_mapping_ops vio_dma_ops;
-
-extern struct bus_type vio_bus_type;
-
-struct vio_device_id {
+/*
+ * The vio_dev structure is used to describe virtual I/O devices.
+ */
+struct vio_dev {
+        struct iommu_table *iommu_table;     /* vio_map_* uses this */
+        char *name;
         char *type;
-        char *compat;
+        uint32_t unit_address;
+        unsigned int irq;
+        struct device dev;
 };
 
 struct vio_driver {
         struct list_head node;
         char *name;
-        const struct vio_device_id *id_table;   /* NULL if wants all devices */
-        int  (*probe)  (struct vio_dev *dev, const struct vio_device_id *id);   /* New device inserted */
-        int (*remove) (struct vio_dev *dev);    /* Device removed (NULL if not a hot-plug capable driver) */
+        const struct vio_device_id *id_table;
+        int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
+        int (*remove)(struct vio_dev *dev);
         unsigned long driver_data;
-
         struct device_driver driver;
 };
 
+struct vio_bus_ops {
+        int (*match)(const struct vio_device_id *id, const struct vio_dev *dev);
+        void (*unregister_device)(struct vio_dev *);
+        void (*release_device)(struct device *);
+};
+
+extern struct dma_mapping_ops vio_dma_ops;
+extern struct bus_type vio_bus_type;
+extern struct vio_dev vio_bus_device;
+
+extern int vio_register_driver(struct vio_driver *drv);
+extern void vio_unregister_driver(struct vio_driver *drv);
+
+extern struct vio_dev * __devinit vio_register_device(struct vio_dev *viodev);
+extern void __devinit vio_unregister_device(struct vio_dev *dev);
+
+extern int vio_bus_init(struct vio_bus_ops *);
+
+#ifdef CONFIG_PPC_PSERIES
+struct device_node;
+
+extern struct vio_dev * __devinit vio_register_device_node(
+                struct device_node *node_vdev);
+extern struct vio_dev *vio_find_node(struct device_node *vnode);
+extern const void *vio_get_attribute(struct vio_dev *vdev, void *which,
+                int *length);
+extern int vio_enable_interrupts(struct vio_dev *dev);
+extern int vio_disable_interrupts(struct vio_dev *dev);
+#endif
+
 static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
 {
         return container_of(drv, struct vio_driver, driver);
 }
 
-/*
- * The vio_dev structure is used to describe virtual I/O devices.
- */
-struct vio_dev {
-        struct iommu_table *iommu_table;     /* vio_map_* uses this */
-        char *name;
-        char *type;
-        uint32_t unit_address;  
-        unsigned int irq;
-
-        struct device dev;
-};
-
 static inline struct vio_dev *to_vio_dev(struct device *dev)
 {
         return container_of(dev, struct vio_dev, dev);
diff --git a/include/asm-ppc64/xor.h b/include/asm-ppc64/xor.h
deleted file mode 100644
index c82eb12a5b18..000000000000
--- a/include/asm-ppc64/xor.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/xor.h>
diff --git a/include/asm-s390/socket.h b/include/asm-s390/socket.h
index 0e96eeca4e6b..15a5298c8744 100644
--- a/include/asm-s390/socket.h
+++ b/include/asm-s390/socket.h
@@ -22,6 +22,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-sh/socket.h b/include/asm-sh/socket.h
index dde696c3b4c7..553904ff9336 100644
--- a/include/asm-sh/socket.h
+++ b/include/asm-sh/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_RCVBUFFORCE  32
+#define SO_SNDBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-sparc/processor.h b/include/asm-sparc/processor.h
index 32c9699367cf..5a7a1a8d29ac 100644
--- a/include/asm-sparc/processor.h
+++ b/include/asm-sparc/processor.h
@@ -19,7 +19,6 @@
 #include <asm/ptrace.h>
 #include <asm/head.h>
 #include <asm/signal.h>
-#include <asm/segment.h>
 #include <asm/btfixup.h>
 #include <asm/page.h>
 
diff --git a/include/asm-sparc/segment.h b/include/asm-sparc/segment.h
deleted file mode 100644
index a1b7ffc9eec9..000000000000
--- a/include/asm-sparc/segment.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SPARC_SEGMENT_H
-#define __SPARC_SEGMENT_H
-
-/* Only here because we have some old header files that expect it.. */
-
-#endif
diff --git a/include/asm-sparc/socket.h b/include/asm-sparc/socket.h
index c1154e3ecfdf..09575b608adb 100644
--- a/include/asm-sparc/socket.h
+++ b/include/asm-sparc/socket.h
@@ -29,6 +29,8 @@
 
 #define SO_SNDBUF       0x1001
 #define SO_RCVBUF       0x1002
+#define SO_SNDBUFFORCE  0x100a
+#define SO_RCVBUFFORCE  0x100b
 #define SO_ERROR        0x1007
 #define SO_TYPE         0x1008
 
diff --git a/include/asm-sparc/system.h b/include/asm-sparc/system.h
index 898562ebe94c..3557781a4bfd 100644
--- a/include/asm-sparc/system.h
+++ b/include/asm-sparc/system.h
@@ -9,7 +9,6 @@
 #include <linux/threads.h>      /* NR_CPUS */
 #include <linux/thread_info.h>
 
-#include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/psr.h>
 #include <asm/ptrace.h>
diff --git a/include/asm-sparc64/atomic.h b/include/asm-sparc64/atomic.h
index d80f3379669b..e175afcf2cde 100644
--- a/include/asm-sparc64/atomic.h
+++ b/include/asm-sparc64/atomic.h
@@ -72,10 +72,10 @@ extern int atomic64_sub_ret(int, atomic64_t *);
 
 /* Atomic operations are already serializing */
 #ifdef CONFIG_SMP
-#define smp_mb__before_atomic_dec()     membar("#StoreLoad | #LoadLoad")
-#define smp_mb__after_atomic_dec()      membar("#StoreLoad | #StoreStore")
-#define smp_mb__before_atomic_inc()     membar("#StoreLoad | #LoadLoad")
-#define smp_mb__after_atomic_inc()      membar("#StoreLoad | #StoreStore")
+#define smp_mb__before_atomic_dec()     membar_storeload_loadload();
+#define smp_mb__after_atomic_dec()      membar_storeload_storestore();
+#define smp_mb__before_atomic_inc()     membar_storeload_loadload();
+#define smp_mb__after_atomic_inc()      membar_storeload_storestore();
 #else
 #define smp_mb__before_atomic_dec()     barrier()
 #define smp_mb__after_atomic_dec()      barrier()
diff --git a/include/asm-sparc64/bitops.h b/include/asm-sparc64/bitops.h
index 9c5e71970287..6388b8376c50 100644
--- a/include/asm-sparc64/bitops.h
+++ b/include/asm-sparc64/bitops.h
@@ -72,8 +72,8 @@ static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
 }
 
 #ifdef CONFIG_SMP
-#define smp_mb__before_clear_bit()      membar("#StoreLoad | #LoadLoad")
-#define smp_mb__after_clear_bit()       membar("#StoreLoad | #StoreStore")
+#define smp_mb__before_clear_bit()      membar_storeload_loadload()
+#define smp_mb__after_clear_bit()       membar_storeload_storestore()
 #else
 #define smp_mb__before_clear_bit()      barrier()
 #define smp_mb__after_clear_bit()       barrier()
diff --git a/include/asm-sparc64/processor.h b/include/asm-sparc64/processor.h
index d0bee2413560..3169f3e2237e 100644
--- a/include/asm-sparc64/processor.h
+++ b/include/asm-sparc64/processor.h
@@ -18,7 +18,6 @@
 #include <asm/a.out.h>
 #include <asm/pstate.h>
 #include <asm/ptrace.h>
-#include <asm/segment.h>
 #include <asm/page.h>
 
 /* The sparc has no problems with write protection */
diff --git a/include/asm-sparc64/segment.h b/include/asm-sparc64/segment.h
deleted file mode 100644
index b03e709fc945..000000000000
--- a/include/asm-sparc64/segment.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SPARC64_SEGMENT_H
-#define __SPARC64_SEGMENT_H
-
-/* Only here because we have some old header files that expect it.. */
-
-#endif
diff --git a/include/asm-sparc64/sfafsr.h b/include/asm-sparc64/sfafsr.h
new file mode 100644
index 000000000000..2f792c20b53c
--- /dev/null
+++ b/include/asm-sparc64/sfafsr.h
@@ -0,0 +1,82 @@
+#ifndef _SPARC64_SFAFSR_H
+#define _SPARC64_SFAFSR_H
+
+#include <asm/const.h>
+
+/* Spitfire Asynchronous Fault Status register, ASI=0x4C VA<63:0>=0x0 */
+
+#define SFAFSR_ME               (_AC(1,UL) << SFAFSR_ME_SHIFT)
+#define SFAFSR_ME_SHIFT         32
+#define SFAFSR_PRIV             (_AC(1,UL) << SFAFSR_PRIV_SHIFT)
+#define SFAFSR_PRIV_SHIFT       31
+#define SFAFSR_ISAP             (_AC(1,UL) << SFAFSR_ISAP_SHIFT)
+#define SFAFSR_ISAP_SHIFT       30
+#define SFAFSR_ETP              (_AC(1,UL) << SFAFSR_ETP_SHIFT)
+#define SFAFSR_ETP_SHIFT        29
+#define SFAFSR_IVUE             (_AC(1,UL) << SFAFSR_IVUE_SHIFT)
+#define SFAFSR_IVUE_SHIFT       28
+#define SFAFSR_TO               (_AC(1,UL) << SFAFSR_TO_SHIFT)
+#define SFAFSR_TO_SHIFT         27
+#define SFAFSR_BERR             (_AC(1,UL) << SFAFSR_BERR_SHIFT)
+#define SFAFSR_BERR_SHIFT       26
+#define SFAFSR_LDP              (_AC(1,UL) << SFAFSR_LDP_SHIFT)
+#define SFAFSR_LDP_SHIFT        25
+#define SFAFSR_CP               (_AC(1,UL) << SFAFSR_CP_SHIFT)
+#define SFAFSR_CP_SHIFT         24
+#define SFAFSR_WP               (_AC(1,UL) << SFAFSR_WP_SHIFT)
+#define SFAFSR_WP_SHIFT         23
+#define SFAFSR_EDP              (_AC(1,UL) << SFAFSR_EDP_SHIFT)
+#define SFAFSR_EDP_SHIFT        22
+#define SFAFSR_UE               (_AC(1,UL) << SFAFSR_UE_SHIFT)
+#define SFAFSR_UE_SHIFT         21
+#define SFAFSR_CE               (_AC(1,UL) << SFAFSR_CE_SHIFT)
+#define SFAFSR_CE_SHIFT         20
+#define SFAFSR_ETS              (_AC(0xf,UL) << SFAFSR_ETS_SHIFT)
+#define SFAFSR_ETS_SHIFT        16
+#define SFAFSR_PSYND            (_AC(0xffff,UL) << SFAFSR_PSYND_SHIFT)
+#define SFAFSR_PSYND_SHIFT      0
+
+/* UDB Error Register, ASI=0x7f VA<63:0>=0x0(High),0x18(Low) for read
+ *                     ASI=0x77 VA<63:0>=0x0(High),0x18(Low) for write
+ */
+
+#define UDBE_UE                 (_AC(1,UL) << 9)
+#define UDBE_CE                 (_AC(1,UL) << 8)
+#define UDBE_E_SYNDR            (_AC(0xff,UL) << 0)
+
+/* The trap handlers for asynchronous errors encode the AFSR and
+ * other pieces of information into a 64-bit argument for C code
+ * encoded as follows:
+ *
+ * -----------------------------------------------
+ * |  UDB_H  |  UDB_L  | TL>1  |  TT  |   AFSR   |
+ * -----------------------------------------------
+ *  63     54 53     44    42   41  33 32       0
+ *
+ * The AFAR is passed in unchanged.
+ */
+#define SFSTAT_UDBH_MASK        (_AC(0x3ff,UL) << SFSTAT_UDBH_SHIFT)
+#define SFSTAT_UDBH_SHIFT       54
+#define SFSTAT_UDBL_MASK        (_AC(0x3ff,UL) << SFSTAT_UDBH_SHIFT)
+#define SFSTAT_UDBL_SHIFT       44
+#define SFSTAT_TL_GT_ONE        (_AC(1,UL) << SFSTAT_TL_GT_ONE_SHIFT)
+#define SFSTAT_TL_GT_ONE_SHIFT  42
+#define SFSTAT_TRAP_TYPE        (_AC(0x1FF,UL) << SFSTAT_TRAP_TYPE_SHIFT)
+#define SFSTAT_TRAP_TYPE_SHIFT  33
+#define SFSTAT_AFSR_MASK        (_AC(0x1ffffffff,UL) << SFSTAT_AFSR_SHIFT)
+#define SFSTAT_AFSR_SHIFT       0
+
+/* ESTATE Error Enable Register, ASI=0x4b VA<63:0>=0x0 */
+#define ESTATE_ERR_CE           0x1 /* Correctable errors                    */
+#define ESTATE_ERR_NCE          0x2 /* TO, BERR, LDP, ETP, EDP, WP, UE, IVUE */
+#define ESTATE_ERR_ISAP         0x4 /* System address parity error           */
+#define ESTATE_ERR_ALL          (ESTATE_ERR_CE | \
+                                 ESTATE_ERR_NCE | \
+                                 ESTATE_ERR_ISAP)
+
+/* The various trap types that report using the above state. */
+#define TRAP_TYPE_IAE           0x09 /* Instruction Access Error             */
+#define TRAP_TYPE_DAE           0x32 /* Data Access Error                    */
+#define TRAP_TYPE_CEE           0x63 /* Correctable ECC Error                */
+
+#endif /* _SPARC64_SFAFSR_H */
diff --git a/include/asm-sparc64/socket.h b/include/asm-sparc64/socket.h
index 865547a23908..59987dad3359 100644
--- a/include/asm-sparc64/socket.h
+++ b/include/asm-sparc64/socket.h
@@ -29,6 +29,8 @@
 
 #define SO_SNDBUF       0x1001
 #define SO_RCVBUF       0x1002
+#define SO_SNDBUFFORCE  0x100a
+#define SO_RCVBUFFORCE  0x100b
 #define SO_ERROR        0x1007
 #define SO_TYPE         0x1008
 
diff --git a/include/asm-sparc64/spinlock.h b/include/asm-sparc64/spinlock.h
index 9cb93a5c2b4f..a02c4370eb42 100644
--- a/include/asm-sparc64/spinlock.h
+++ b/include/asm-sparc64/spinlock.h
@@ -43,7 +43,7 @@ typedef struct {
 #define spin_is_locked(lp)  ((lp)->lock != 0)
 
 #define spin_unlock_wait(lp)    \
-do {    membar("#LoadLoad");    \
+do {    rmb();                  \
 } while((lp)->lock)
 
 static inline void _raw_spin_lock(spinlock_t *lock)
@@ -129,15 +129,18 @@ typedef struct {
 #define spin_is_locked(__lock)  ((__lock)->lock != 0)
 #define spin_unlock_wait(__lock)        \
 do { \
-        membar("#LoadLoad"); \
+        rmb(); \
 } while((__lock)->lock)
 
-extern void _do_spin_lock (spinlock_t *lock, char *str);
-extern void _do_spin_unlock (spinlock_t *lock);
-extern int _do_spin_trylock (spinlock_t *lock);
+extern void _do_spin_lock(spinlock_t *lock, char *str, unsigned long caller);
+extern void _do_spin_unlock(spinlock_t *lock);
+extern int _do_spin_trylock(spinlock_t *lock, unsigned long caller);
 
-#define _raw_spin_trylock(lp)   _do_spin_trylock(lp)
-#define _raw_spin_lock(lock)    _do_spin_lock(lock, "spin_lock")
+#define _raw_spin_trylock(lp)   \
+        _do_spin_trylock(lp, (unsigned long) __builtin_return_address(0))
+#define _raw_spin_lock(lock)    \
+        _do_spin_lock(lock, "spin_lock", \
+                      (unsigned long) __builtin_return_address(0))
 #define _raw_spin_unlock(lock)  _do_spin_unlock(lock)
 #define _raw_spin_lock_flags(lock, flags) _raw_spin_lock(lock)
 
@@ -279,37 +282,41 @@ typedef struct {
 #define RW_LOCK_UNLOCKED        (rwlock_t) { 0, 0, 0xff, { } }
 #define rwlock_init(lp) do { *(lp) = RW_LOCK_UNLOCKED; } while(0)
 
-extern void _do_read_lock(rwlock_t *rw, char *str);
-extern void _do_read_unlock(rwlock_t *rw, char *str);
-extern void _do_write_lock(rwlock_t *rw, char *str);
-extern void _do_write_unlock(rwlock_t *rw);
-extern int _do_write_trylock(rwlock_t *rw, char *str);
+extern void _do_read_lock(rwlock_t *rw, char *str, unsigned long caller);
+extern void _do_read_unlock(rwlock_t *rw, char *str, unsigned long caller);
+extern void _do_write_lock(rwlock_t *rw, char *str, unsigned long caller);
+extern void _do_write_unlock(rwlock_t *rw, unsigned long caller);
+extern int _do_write_trylock(rwlock_t *rw, char *str, unsigned long caller);
 
 #define _raw_read_lock(lock) \
 do {    unsigned long flags; \
         local_irq_save(flags); \
-        _do_read_lock(lock, "read_lock"); \
+        _do_read_lock(lock, "read_lock", \
+                      (unsigned long) __builtin_return_address(0)); \
         local_irq_restore(flags); \
 } while(0)
 
 #define _raw_read_unlock(lock) \
 do {    unsigned long flags; \
         local_irq_save(flags); \
-        _do_read_unlock(lock, "read_unlock"); \
+        _do_read_unlock(lock, "read_unlock", \
+                      (unsigned long) __builtin_return_address(0)); \
         local_irq_restore(flags); \
 } while(0)
 
 #define _raw_write_lock(lock) \
 do {    unsigned long flags; \
         local_irq_save(flags); \
-        _do_write_lock(lock, "write_lock"); \
+        _do_write_lock(lock, "write_lock", \
+                      (unsigned long) __builtin_return_address(0)); \
         local_irq_restore(flags); \
 } while(0)
 
 #define _raw_write_unlock(lock) \
 do {    unsigned long flags; \
         local_irq_save(flags); \
-        _do_write_unlock(lock); \
+        _do_write_unlock(lock, \
+                      (unsigned long) __builtin_return_address(0)); \
         local_irq_restore(flags); \
 } while(0)
 
@@ -317,7 +324,8 @@ do {	unsigned long flags; \
 ({      unsigned long flags; \
         int val; \
         local_irq_save(flags); \
-        val = _do_write_trylock(lock, "write_trylock"); \
+        val = _do_write_trylock(lock, "write_trylock", \
+                                (unsigned long) __builtin_return_address(0)); \
         local_irq_restore(flags); \
         val; \
 })
diff --git a/include/asm-sparc64/system.h b/include/asm-sparc64/system.h
index ee4bdfc6b88f..5e94c05dc2fc 100644
--- a/include/asm-sparc64/system.h
+++ b/include/asm-sparc64/system.h
@@ -28,6 +28,14 @@ enum sparc_cpu {
 #define ARCH_SUN4C_SUN4 0
 #define ARCH_SUN4 0
 
+extern void mb(void);
+extern void rmb(void);
+extern void wmb(void);
+extern void membar_storeload(void);
+extern void membar_storeload_storestore(void);
+extern void membar_storeload_loadload(void);
+extern void membar_storestore_loadstore(void);
+
 #endif
 
 #define setipl(__new_ipl) \
@@ -78,16 +86,11 @@ enum sparc_cpu {
 
 #define nop()           __asm__ __volatile__ ("nop")
 
-#define membar(type)    __asm__ __volatile__ ("membar " type : : : "memory")
-#define mb()            \
-        membar("#LoadLoad | #LoadStore | #StoreStore | #StoreLoad")
-#define rmb()           membar("#LoadLoad")
-#define wmb()           membar("#StoreStore")
 #define read_barrier_depends()          do { } while(0)
 #define set_mb(__var, __value) \
-        do { __var = __value; membar("#StoreLoad | #StoreStore"); } while(0)
+        do { __var = __value; membar_storeload_storestore(); } while(0)
 #define set_wmb(__var, __value) \
-        do { __var = __value; membar("#StoreStore"); } while(0)
+        do { __var = __value; wmb(); } while(0)
 
 #ifdef CONFIG_SMP
 #define smp_mb()        mb()
diff --git a/include/asm-v850/socket.h b/include/asm-v850/socket.h
index 213b852af53e..0240d366a0a4 100644
--- a/include/asm-v850/socket.h
+++ b/include/asm-v850/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-x86_64/checksum.h b/include/asm-x86_64/checksum.h
index d01356f01448..989469e8e0b7 100644
--- a/include/asm-x86_64/checksum.h
+++ b/include/asm-x86_64/checksum.h
@@ -64,7 +64,7 @@ static inline unsigned short ip_fast_csum(unsigned char *iph, unsigned int ihl)
                 "  adcl $0, %0\n"
                 "  notl %0\n"
                 "2:"
-        /* Since the input registers which are loaded with iph and ipl
+        /* Since the input registers which are loaded with iph and ihl
            are modified, we must also specify them as outputs, or gcc
            will assume they contain their original values. */
         : "=r" (sum), "=r" (iph), "=r" (ihl)
diff --git a/include/asm-x86_64/socket.h b/include/asm-x86_64/socket.h
index d9a252ea8210..f2cdbeae5d5b 100644
--- a/include/asm-x86_64/socket.h
+++ b/include/asm-x86_64/socket.h
@@ -14,6 +14,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/asm-xtensa/socket.h b/include/asm-xtensa/socket.h
index daccd05a14cd..00f83f3a6d72 100644
--- a/include/asm-xtensa/socket.h
+++ b/include/asm-xtensa/socket.h
@@ -24,6 +24,8 @@
 #define SO_BROADCAST    6
 #define SO_SNDBUF       7
 #define SO_RCVBUF       8
+#define SO_SNDBUFFORCE  32
+#define SO_RCVBUFFORCE  33
 #define SO_KEEPALIVE    9
 #define SO_OOBINLINE    10
 #define SO_NO_CHECK     11
diff --git a/include/linux/8250_pci.h b/include/linux/8250_pci.h
index 5f3ab21b339b..3209dd46ea7d 100644
--- a/include/linux/8250_pci.h
+++ b/include/linux/8250_pci.h
@@ -1,2 +1,37 @@
-int pci_siig10x_fn(struct pci_dev *dev, int enable);
-int pci_siig20x_fn(struct pci_dev *dev, int enable);
+/*
+ * Definitions for PCI support.
+ */
+#define FL_BASE_MASK            0x0007
+#define FL_BASE0                0x0000
+#define FL_BASE1                0x0001
+#define FL_BASE2                0x0002
+#define FL_BASE3                0x0003
+#define FL_BASE4                0x0004
+#define FL_GET_BASE(x)          (x & FL_BASE_MASK)
+
+/* Use successive BARs (PCI base address registers),
+   else use offset into some specified BAR */
+#define FL_BASE_BARS            0x0008
+
+/* do not assign an irq */
+#define FL_NOIRQ                0x0080
+
+/* Use the Base address register size to cap number of ports */
+#define FL_REGION_SZ_CAP        0x0100
+
+struct pciserial_board {
+        unsigned int flags;
+        unsigned int num_ports;
+        unsigned int base_baud;
+        unsigned int uart_offset;
+        unsigned int reg_shift;
+        unsigned int first_offset;
+};
+
+struct serial_private;
+
+struct serial_private *
+pciserial_init_ports(struct pci_dev *dev, struct pciserial_board *board);
+void pciserial_remove_ports(struct serial_private *priv);
+void pciserial_suspend_ports(struct serial_private *priv);
+void pciserial_resume_ports(struct serial_private *priv);
diff --git a/include/linux/ata.h b/include/linux/ata.h
index ca5fcadf9981..a5b74efab067 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -1,24 +1,29 @@
 
 /*
-   Copyright 2003-2004 Red Hat, Inc.  All rights reserved.
-   Copyright 2003-2004 Jeff Garzik
-
-   The contents of this file are subject to the Open
-   Software License version 1.1 that can be found at
-   http://www.opensource.org/licenses/osl-1.1.txt and is included herein
-   by reference.
-
-   Alternatively, the contents of this file may be used under the terms
-   of the GNU General Public License version 2 (the "GPL") as distributed
-   in the kernel source COPYING file, in which case the provisions of
-   the GPL are applicable instead of the above.  If you wish to allow
-   the use of your version of this file only under the terms of the
-   GPL and not to allow others to use your version of this file under
-   the OSL, indicate your decision by deleting the provisions above and
-   replace them with the notice and other provisions required by the GPL.
-   If you do not delete the provisions above, a recipient may use your
-   version of this file under either the OSL or the GPL.
-
+ *  Copyright 2003-2004 Red Hat, Inc.  All rights reserved.
+ *  Copyright 2003-2004 Jeff Garzik
+ *
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *
+ *  libata documentation is available via 'make {ps|pdf}docs',
+ *  as Documentation/DocBook/libata.*
+ *
+ *  Hardware documentation available from http://www.t13.org/
+ *
  */
 
 #ifndef __LINUX_ATA_H__
@@ -108,6 +113,8 @@ enum {
 
         /* ATA device commands */
         ATA_CMD_CHK_POWER       = 0xE5, /* check power mode */
+        ATA_CMD_STANDBY         = 0xE2, /* place in standby power mode */
+        ATA_CMD_IDLE            = 0xE3, /* place in idle power mode */
         ATA_CMD_EDD             = 0x90, /* execute device diagnostic */
         ATA_CMD_FLUSH           = 0xE7,
         ATA_CMD_FLUSH_EXT       = 0xEA,
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
new file mode 100644
index 000000000000..007c290f74d4
--- /dev/null
+++ b/include/linux/dccp.h
@@ -0,0 +1,456 @@
+#ifndef _LINUX_DCCP_H
+#define _LINUX_DCCP_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* Structure describing an Internet (DCCP) socket address. */
+struct sockaddr_dccp {
+        __u16   sdccp_family;   /* Address family   */
+        __u16   sdccp_port;     /* Port number      */
+        __u32   sdccp_addr;     /* Internet address */
+        __u32   sdccp_service;  /* Service          */
+        /* Pad to size of `struct sockaddr': 16 bytes . */
+        __u32   sdccp_pad;
+};
+
+/**
+ * struct dccp_hdr - generic part of DCCP packet header
+ *
+ * @dccph_sport - Relevant port on the endpoint that sent this packet
+ * @dccph_dport - Relevant port on the other endpoint
+ * @dccph_doff - Data Offset from the start of the DCCP header, in 32-bit words
+ * @dccph_ccval - Used by the HC-Sender CCID
+ * @dccph_cscov - Parts of the packet that are covered by the Checksum field
+ * @dccph_checksum - Internet checksum, depends on dccph_cscov
+ * @dccph_x - 0 = 24 bit sequence number, 1 = 48
+ * @dccph_type - packet type, see DCCP_PKT_ prefixed macros
+ * @dccph_seq - sequence number high or low order 24 bits, depends on dccph_x
+ */
+struct dccp_hdr {
+        __u16   dccph_sport,
+                dccph_dport;
+        __u8    dccph_doff;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+        __u8    dccph_cscov:4,
+                dccph_ccval:4;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+        __u8    dccph_ccval:4,
+                dccph_cscov:4;
+#else
+#error  "Adjust your <asm/byteorder.h> defines"
+#endif
+        __u16   dccph_checksum;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+        __u32   dccph_x:1,
+                dccph_type:4,
+                dccph_reserved:3,
+                dccph_seq:24;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+        __u32   dccph_reserved:3,
+                dccph_type:4,
+                dccph_x:1,
+                dccph_seq:24;
+#else
+#error  "Adjust your <asm/byteorder.h> defines"
+#endif
+};
+
+/**
+ * struct dccp_hdr_ext - the low bits of a 48 bit seq packet
+ *
+ * @dccph_seq_low - low 24 bits of a 48 bit seq packet
+ */
+struct dccp_hdr_ext {
+        __u32   dccph_seq_low;
+};
+
+/**
+ * struct dccp_hdr_request - Conection initiation request header
+ *
+ * @dccph_req_service - Service to which the client app wants to connect
+ * @dccph_req_options - list of options (must be a multiple of 32 bits
+ */
+struct dccp_hdr_request {
+        __u32   dccph_req_service;
+};
+/**
+ * struct dccp_hdr_ack_bits - acknowledgment bits common to most packets
+ *
+ * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR
+ * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR
+ */
+struct dccp_hdr_ack_bits {
+        __u32   dccph_reserved1:8,
+                dccph_ack_nr_high:24;
+        __u32   dccph_ack_nr_low;
+};
+/**
+ * struct dccp_hdr_response - Conection initiation response header
+ *
+ * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR
+ * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR
+ * @dccph_resp_service - Echoes the Service Code on a received DCCP-Request
+ * @dccph_resp_options - list of options (must be a multiple of 32 bits
+ */
+struct dccp_hdr_response {
+        struct dccp_hdr_ack_bits        dccph_resp_ack;
+        __u32                           dccph_resp_service;
+};
+
+/**
+ * struct dccp_hdr_reset - Unconditionally shut down a connection
+ *
+ * @dccph_reset_service - Echoes the Service Code on a received DCCP-Request
+ * @dccph_reset_options - list of options (must be a multiple of 32 bits
+ */
+struct dccp_hdr_reset {
+        struct dccp_hdr_ack_bits        dccph_reset_ack;
+        __u8                            dccph_reset_code,
+                                        dccph_reset_data[3];
+};
+
+enum dccp_pkt_type {
+        DCCP_PKT_REQUEST = 0,
+        DCCP_PKT_RESPONSE,
+        DCCP_PKT_DATA,
+        DCCP_PKT_ACK,
+        DCCP_PKT_DATAACK,
+        DCCP_PKT_CLOSEREQ,
+        DCCP_PKT_CLOSE,
+        DCCP_PKT_RESET,
+        DCCP_PKT_SYNC,
+        DCCP_PKT_SYNCACK,
+        DCCP_PKT_INVALID,
+};
+
+#define DCCP_NR_PKT_TYPES DCCP_PKT_INVALID
+
+static inline unsigned int dccp_packet_hdr_len(const __u8 type)
+{
+        if (type == DCCP_PKT_DATA)
+                return 0;
+        if (type == DCCP_PKT_DATAACK    ||
+            type == DCCP_PKT_ACK        ||
+            type == DCCP_PKT_SYNC       ||
+            type == DCCP_PKT_SYNCACK    ||
+            type == DCCP_PKT_CLOSE      ||
+            type == DCCP_PKT_CLOSEREQ)
+                return sizeof(struct dccp_hdr_ack_bits);
+        if (type == DCCP_PKT_REQUEST)
+                return sizeof(struct dccp_hdr_request);
+        if (type == DCCP_PKT_RESPONSE)
+                return sizeof(struct dccp_hdr_response);
+        return sizeof(struct dccp_hdr_reset);
+}
+enum dccp_reset_codes {
+        DCCP_RESET_CODE_UNSPECIFIED = 0,
+        DCCP_RESET_CODE_CLOSED,
+        DCCP_RESET_CODE_ABORTED,
+        DCCP_RESET_CODE_NO_CONNECTION,
+        DCCP_RESET_CODE_PACKET_ERROR,
+        DCCP_RESET_CODE_OPTION_ERROR,
+        DCCP_RESET_CODE_MANDATORY_ERROR,
+        DCCP_RESET_CODE_CONNECTION_REFUSED,
+        DCCP_RESET_CODE_BAD_SERVICE_CODE,
+        DCCP_RESET_CODE_TOO_BUSY,
+        DCCP_RESET_CODE_BAD_INIT_COOKIE,
+        DCCP_RESET_CODE_AGGRESSION_PENALTY,
+};
+
+/* DCCP options */
+enum {
+        DCCPO_PADDING = 0,
+        DCCPO_MANDATORY = 1,
+        DCCPO_MIN_RESERVED = 3,
+        DCCPO_MAX_RESERVED = 31,
+        DCCPO_NDP_COUNT = 37,
+        DCCPO_ACK_VECTOR_0 = 38,
+        DCCPO_ACK_VECTOR_1 = 39,
+        DCCPO_TIMESTAMP = 41,
+        DCCPO_TIMESTAMP_ECHO = 42,
+        DCCPO_ELAPSED_TIME = 43,
+        DCCPO_MAX = 45,
+        DCCPO_MIN_CCID_SPECIFIC = 128,
+        DCCPO_MAX_CCID_SPECIFIC = 255,
+};
+
+/* DCCP features */
+enum {
+        DCCPF_RESERVED = 0,
+        DCCPF_SEQUENCE_WINDOW = 3,
+        DCCPF_SEND_ACK_VECTOR = 6,
+        DCCPF_SEND_NDP_COUNT = 7,
+        /* 10-127 reserved */
+        DCCPF_MIN_CCID_SPECIFIC = 128,
+        DCCPF_MAX_CCID_SPECIFIC = 255,
+};
+
+/* DCCP socket options */
+#define DCCP_SOCKOPT_PACKET_SIZE        1
+
+#ifdef __KERNEL__
+
+#include <linux/in.h>
+#include <linux/list.h>
+#include <linux/uio.h>
+#include <linux/workqueue.h>
+
+#include <net/inet_connection_sock.h>
+#include <net/inet_timewait_sock.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+#include <net/tcp.h>
+
+enum dccp_state {
+        DCCP_OPEN       = TCP_ESTABLISHED,
+        DCCP_REQUESTING = TCP_SYN_SENT,
+        DCCP_PARTOPEN   = TCP_FIN_WAIT1, /* FIXME:
+                                            This mapping is horrible, but TCP has
+                                            no matching state for DCCP_PARTOPEN,
+                                            as TCP_SYN_RECV is already used by
+                                            DCCP_RESPOND, why don't stop using TCP
+                                            mapping of states? OK, now we don't use
+                                            sk_stream_sendmsg anymore, so doesn't
+                                            seem to exist any reason for us to
+                                            do the TCP mapping here */
+        DCCP_LISTEN     = TCP_LISTEN,
+        DCCP_RESPOND    = TCP_SYN_RECV,
+        DCCP_CLOSING    = TCP_CLOSING,
+        DCCP_TIME_WAIT  = TCP_TIME_WAIT,
+        DCCP_CLOSED     = TCP_CLOSE,
+        DCCP_MAX_STATES = TCP_MAX_STATES,
+};
+
+#define DCCP_STATE_MASK 0xf
+#define DCCP_ACTION_FIN (1<<7)
+
+enum {
+        DCCPF_OPEN       = TCPF_ESTABLISHED,
+        DCCPF_REQUESTING = TCPF_SYN_SENT,
+        DCCPF_PARTOPEN   = TCPF_FIN_WAIT1,
+        DCCPF_LISTEN     = TCPF_LISTEN,
+        DCCPF_RESPOND    = TCPF_SYN_RECV,
+        DCCPF_CLOSING    = TCPF_CLOSING,
+        DCCPF_TIME_WAIT  = TCPF_TIME_WAIT,
+        DCCPF_CLOSED     = TCPF_CLOSE,
+};
+
+static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb)
+{
+        return (struct dccp_hdr *)skb->h.raw;
+}
+
+static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb)
+{
+        return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr));
+}
+
+static inline unsigned int __dccp_basic_hdr_len(const struct dccp_hdr *dh)
+{
+        return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0);
+}
+
+static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb)
+{
+        const struct dccp_hdr *dh = dccp_hdr(skb);
+        return __dccp_basic_hdr_len(dh);
+}
+
+static inline __u64 dccp_hdr_seq(const struct sk_buff *skb)
+{
+        const struct dccp_hdr *dh = dccp_hdr(skb);
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+        __u64 seq_nr = ntohl(dh->dccph_seq << 8);
+#elif defined(__BIG_ENDIAN_BITFIELD)
+        __u64 seq_nr = ntohl(dh->dccph_seq);
+#else
+#error  "Adjust your <asm/byteorder.h> defines"
+#endif
+
+        if (dh->dccph_x != 0)
+                seq_nr = (seq_nr << 32) + ntohl(dccp_hdrx(skb)->dccph_seq_low);
+
+        return seq_nr;
+}
+
+static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb)
+{
+        return (struct dccp_hdr_request *)(skb->h.raw + dccp_basic_hdr_len(skb));
+}
+
+static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb)
+{
+        return (struct dccp_hdr_ack_bits *)(skb->h.raw + dccp_basic_hdr_len(skb));
+}
+
+static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb)
+{
+        const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb);
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+        return (((u64)ntohl(dhack->dccph_ack_nr_high << 8)) << 32) + ntohl(dhack->dccph_ack_nr_low);
+#elif defined(__BIG_ENDIAN_BITFIELD)
+        return (((u64)ntohl(dhack->dccph_ack_nr_high)) << 32) + ntohl(dhack->dccph_ack_nr_low);
+#else
+#error  "Adjust your <asm/byteorder.h> defines"
+#endif
+}
+
+static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb)
+{
+        return (struct dccp_hdr_response *)(skb->h.raw + dccp_basic_hdr_len(skb));
+}
+
+static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb)
+{
+        return (struct dccp_hdr_reset *)(skb->h.raw + dccp_basic_hdr_len(skb));
+}
+
+static inline unsigned int __dccp_hdr_len(const struct dccp_hdr *dh)
+{
+        return __dccp_basic_hdr_len(dh) +
+               dccp_packet_hdr_len(dh->dccph_type);
+}
+
+static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
+{
+        return __dccp_hdr_len(dccp_hdr(skb));
+}
+
+
+/* initial values for each feature */
+#define DCCPF_INITIAL_SEQUENCE_WINDOW           100
+/* FIXME: for now we're using CCID 3 (TFRC) */
+#define DCCPF_INITIAL_CCID                      3
+#define DCCPF_INITIAL_SEND_ACK_VECTOR           0
+/* FIXME: for now we're default to 1 but it should really be 0 */
+#define DCCPF_INITIAL_SEND_NDP_COUNT            1
+
+#define DCCP_NDP_LIMIT 0xFFFFFF
+
+/**
+  * struct dccp_options - option values for a DCCP connection
+  *     @dccpo_sequence_window - Sequence Window Feature (section 7.5.2)
+  *     @dccpo_ccid - Congestion Control Id (CCID) (section 10)
+  *     @dccpo_send_ack_vector - Send Ack Vector Feature (section 11.5)
+  *     @dccpo_send_ndp_count - Send NDP Count Feature (7.7.2)
+  */
+struct dccp_options {
+        __u64   dccpo_sequence_window;
+        __u8    dccpo_ccid;
+        __u8    dccpo_send_ack_vector;
+        __u8    dccpo_send_ndp_count;
+};
+
+extern void __dccp_options_init(struct dccp_options *dccpo);
+extern void dccp_options_init(struct dccp_options *dccpo);
+extern int dccp_parse_options(struct sock *sk, struct sk_buff *skb);
+
+struct dccp_request_sock {
+        struct inet_request_sock dreq_inet_rsk;
+        __u64                    dreq_iss;
+        __u64                    dreq_isr;
+        __u32                    dreq_service;
+};
+
+static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req)
+{
+        return (struct dccp_request_sock *)req;
+}
+
+extern struct inet_timewait_death_row dccp_death_row;
+
+/* Read about the ECN nonce to see why it is 253 */
+#define DCCP_MAX_ACK_VECTOR_LEN 253
+
+struct dccp_options_received {
+        u32     dccpor_ndp:24,
+                dccpor_ack_vector_len:8;
+        u32     dccpor_ack_vector_idx:10;
+        /* 22 bits hole, try to pack */
+        u32     dccpor_timestamp;
+        u32     dccpor_timestamp_echo;
+        u32     dccpor_elapsed_time;
+};
+
+struct ccid;
+
+enum dccp_role {
+        DCCP_ROLE_UNDEFINED,
+        DCCP_ROLE_LISTEN,
+        DCCP_ROLE_CLIENT,
+        DCCP_ROLE_SERVER,
+};
+
+/**
+ * struct dccp_sock - DCCP socket state
+ *
+ * @dccps_swl - sequence number window low
+ * @dccps_swh - sequence number window high
+ * @dccps_awl - acknowledgement number window low
+ * @dccps_awh - acknowledgement number window high
+ * @dccps_iss - initial sequence number sent
+ * @dccps_isr - initial sequence number received
+ * @dccps_osr - first OPEN sequence number received
+ * @dccps_gss - greatest sequence number sent
+ * @dccps_gsr - greatest valid sequence number received
+ * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss
+ * @dccps_timestamp_time - time of latest TIMESTAMP option
+ * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option
+ * @dccps_ext_header_len - network protocol overhead (IP/IPv6 options)
+ * @dccps_pmtu_cookie - Last pmtu seen by socket
+ * @dccps_packet_size - Set thru setsockopt
+ * @dccps_role - Role of this sock, one of %dccp_role
+ * @dccps_ndp_count - number of Non Data Packets since last data packet
+ * @dccps_hc_rx_ackpkts - receiver half connection acked packets
+ */
+struct dccp_sock {
+        /* inet_connection_sock has to be the first member of dccp_sock */
+        struct inet_connection_sock     dccps_inet_connection;
+        __u64                           dccps_swl;
+        __u64                           dccps_swh;
+        __u64                           dccps_awl;
+        __u64                           dccps_awh;
+        __u64                           dccps_iss;
+        __u64                           dccps_isr;
+        __u64                           dccps_osr;
+        __u64                           dccps_gss;
+        __u64                           dccps_gsr;
+        __u64                           dccps_gar;
+        unsigned long                   dccps_service;
+        struct timeval                  dccps_timestamp_time;
+        __u32                           dccps_timestamp_echo;
+        __u32                           dccps_packet_size;
+        unsigned long                   dccps_ndp_count;
+        __u16                           dccps_ext_header_len;
+        __u32                           dccps_pmtu_cookie;
+        __u32                           dccps_mss_cache;
+        struct dccp_options             dccps_options;
+        struct dccp_ackpkts             *dccps_hc_rx_ackpkts;
+        void                            *dccps_hc_rx_ccid_private;
+        void                            *dccps_hc_tx_ccid_private;
+        struct ccid                     *dccps_hc_rx_ccid;
+        struct ccid                     *dccps_hc_tx_ccid;
+        struct dccp_options_received    dccps_options_received;
+        enum dccp_role                  dccps_role:2;
+};
+ 
+static inline struct dccp_sock *dccp_sk(const struct sock *sk)
+{
+        return (struct dccp_sock *)sk;
+}
+
+static inline const char *dccp_role(const struct sock *sk)
+{
+        switch (dccp_sk(sk)->dccps_role) {
+        case DCCP_ROLE_UNDEFINED: return "undefined";
+        case DCCP_ROLE_LISTEN:    return "listen";
+        case DCCP_ROLE_SERVER:    return "server";
+        case DCCP_ROLE_CLIENT:    return "client";
+        }
+        return NULL;
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_DCCP_H */
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index a0ab26aab450..ed1440ea4c91 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -250,6 +250,12 @@ struct ethtool_stats {
         u64     data[0];
 };
 
+struct ethtool_perm_addr {
+        u32     cmd;            /* ETHTOOL_GPERMADDR */
+        u32     size;
+        u8      data[0];
+};
+
 struct net_device;
 
 /* Some generic methods drivers may use in their ethtool_ops */
@@ -261,6 +267,8 @@ u32 ethtool_op_get_sg(struct net_device *dev);
 int ethtool_op_set_sg(struct net_device *dev, u32 data);
 u32 ethtool_op_get_tso(struct net_device *dev);
 int ethtool_op_set_tso(struct net_device *dev, u32 data);
+int ethtool_op_get_perm_addr(struct net_device *dev, 
+                             struct ethtool_perm_addr *addr, u8 *data);
 
 /**
  * &ethtool_ops - Alter and report network device settings
@@ -294,7 +302,8 @@ int ethtool_op_set_tso(struct net_device *dev, u32 data);
  * get_strings: Return a set of strings that describe the requested objects 
  * phys_id: Identify the device
  * get_stats: Return statistics about the device
- *
+ * get_perm_addr: Gets the permanent hardware address
+ * 
  * Description:
  *
  * get_settings:
@@ -352,6 +361,7 @@ struct ethtool_ops {
         int     (*phys_id)(struct net_device *, u32);
         int     (*get_stats_count)(struct net_device *);
         void    (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *);
+        int     (*get_perm_addr)(struct net_device *, struct ethtool_perm_addr *, u8 *);
         int     (*begin)(struct net_device *);
         void    (*complete)(struct net_device *);
 };
@@ -389,6 +399,7 @@ struct ethtool_ops {
 #define ETHTOOL_GSTATS          0x0000001d /* get NIC-specific statistics */
 #define ETHTOOL_GTSO            0x0000001e /* Get TSO enable (ethtool_value) */
 #define ETHTOOL_STSO            0x0000001f /* Set TSO enable (ethtool_value) */
+#define ETHTOOL_GPERMADDR       0x00000020 /* Get permanent hardware address */
 
 /* compatibility with older code */
 #define SPARC_ETH_GSET          ETHTOOL_GSET
@@ -408,6 +419,8 @@ struct ethtool_ops {
 #define SUPPORTED_FIBRE                 (1 << 10)
 #define SUPPORTED_BNC                   (1 << 11)
 #define SUPPORTED_10000baseT_Full       (1 << 12)
+#define SUPPORTED_Pause                 (1 << 13)
+#define SUPPORTED_Asym_Pause            (1 << 14)
 
 /* Indicates what features are advertised by the interface. */
 #define ADVERTISED_10baseT_Half         (1 << 0)
@@ -423,6 +436,8 @@ struct ethtool_ops {
 #define ADVERTISED_FIBRE                (1 << 10)
 #define ADVERTISED_BNC                  (1 << 11)
 #define ADVERTISED_10000baseT_Full      (1 << 12)
+#define ADVERTISED_Pause                (1 << 13)
+#define ADVERTISED_Asym_Pause           (1 << 14)
 
 /* The following are all involved in forcing a particular link
  * mode for the device for setting things.  When getting the
diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h
index 9debe6bbe5f0..bab303dafd6e 100644
--- a/include/linux/hippidevice.h
+++ b/include/linux/hippidevice.h
@@ -26,8 +26,12 @@
 #include <linux/if_hippi.h>
 
 #ifdef __KERNEL__
-extern unsigned short hippi_type_trans(struct sk_buff *skb,
-                                       struct net_device *dev);
+
+struct hippi_cb {
+        __u32   ifield;
+};
+
+extern __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev);
 
 extern struct net_device *alloc_hippi_dev(int sizeof_priv);
 #endif
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index b5b58e9c054c..fc2d4c8225aa 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -110,6 +110,8 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 {
         return (struct ethhdr *)skb->mac.raw;
 }
+
+extern struct ctl_table ether_table[];
 #endif
 
 #endif  /* _LINUX_IF_ETHER_H */
diff --git a/include/linux/if_fc.h b/include/linux/if_fc.h
index 33330b458b95..376a34ea4723 100644
--- a/include/linux/if_fc.h
+++ b/include/linux/if_fc.h
@@ -44,7 +44,7 @@ struct fcllc {
         __u8  ssap;                     /* source SAP */
         __u8  llc;                      /* LLC control field */
         __u8  protid[3];                /* protocol id */
-        __u16 ethertype;                /* ether type field */
+        __be16 ethertype;               /* ether type field */
 };
 
 #endif  /* _LINUX_IF_FC_H */
diff --git a/include/linux/if_fddi.h b/include/linux/if_fddi.h
index a912818e6361..1288a161bc0b 100644
--- a/include/linux/if_fddi.h
+++ b/include/linux/if_fddi.h
@@ -85,7 +85,7 @@ struct fddi_snap_hdr
         __u8    ssap;                                   /* always 0xAA */
         __u8    ctrl;                                   /* always 0x03 */
         __u8    oui[FDDI_K_OUI_LEN];    /* organizational universal id */
-        __u16   ethertype;                              /* packet type ID field */
+        __be16  ethertype;                              /* packet type ID field */
         } __attribute__ ((packed));
 
 /* Define FDDI LLC frame header */
diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h
index 3c94b1736570..511999c7eeda 100644
--- a/include/linux/if_frad.h
+++ b/include/linux/if_frad.h
@@ -191,10 +191,12 @@ struct frad_local
    int               buffer;            /* current buffer for S508 firmware */
 };
 
-extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *));
-
 #endif /* __KERNEL__ */
 
 #endif /* CONFIG_DLCI || CONFIG_DLCI_MODULE */
 
+#ifdef __KERNEL__
+extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *));
+#endif
+
 #endif
diff --git a/include/linux/if_hippi.h b/include/linux/if_hippi.h
index c8ca72c46f76..94d31ca7d71a 100644
--- a/include/linux/if_hippi.h
+++ b/include/linux/if_hippi.h
@@ -102,9 +102,9 @@ struct hippi_fp_hdr
 #error  "Please fix <asm/byteorder.h>"
 #endif
 #else
-        __u32           fixed;
+        __be32          fixed;
 #endif
-        __u32           d2_size;
+        __be32          d2_size;
 } __attribute__ ((packed));
 
 struct hippi_le_hdr
@@ -144,7 +144,7 @@ struct hippi_snap_hdr
         __u8    ssap;                   /* always 0xAA */
         __u8    ctrl;                   /* always 0x03 */
         __u8    oui[HIPPI_OUI_LEN];     /* organizational universal id (zero)*/
-        __u16   ethertype;              /* packet type ID field */
+        __be16  ethertype;              /* packet type ID field */
 } __attribute__ ((packed));
 
 struct hippi_hdr
diff --git a/include/linux/if_tr.h b/include/linux/if_tr.h
index 3fba9e2f5427..5502f597cf0e 100644
--- a/include/linux/if_tr.h
+++ b/include/linux/if_tr.h
@@ -43,12 +43,16 @@ struct trh_hdr {
 };
 
 #ifdef __KERNEL__
+#include <linux/config.h>
 #include <linux/skbuff.h>
 
 static inline struct trh_hdr *tr_hdr(const struct sk_buff *skb)
 {
         return (struct trh_hdr *)skb->mac.raw;
 }
+#ifdef CONFIG_SYSCTL
+extern struct ctl_table tr_table[];
+#endif
 #endif
 
 /* This is an Token-Ring LLC structure */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 62a9d89dfbe2..17d0c0d40b0e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -155,7 +155,6 @@ static inline int __vlan_hwaccel_rx(struct sk_buff *skb,
 {
         struct net_device_stats *stats;
 
-        skb->real_dev = skb->dev;
         skb->dev = grp->vlan_devices[vlan_tag & VLAN_VID_MASK];
         if (skb->dev == NULL) {
                 dev_kfree_skb_any(skb);
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 0c31ef0b5bad..28f4f3b36950 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -129,6 +129,9 @@ struct igmpv3_query {
 #include <linux/skbuff.h>
 #include <linux/in.h>
 
+extern int sysctl_igmp_max_memberships;
+extern int sysctl_igmp_max_msf;
+
 struct ip_sf_socklist
 {
         unsigned int            sl_max;
diff --git a/include/linux/in.h b/include/linux/in.h
index fb88c66d748d..ba355384016a 100644
--- a/include/linux/in.h
+++ b/include/linux/in.h
@@ -32,6 +32,7 @@ enum {
   IPPROTO_PUP = 12,             /* PUP protocol                         */
   IPPROTO_UDP = 17,             /* User Datagram Protocol               */
   IPPROTO_IDP = 22,             /* XNS IDP protocol                     */
+  IPPROTO_DCCP = 33,            /* Datagram Congestion Control Protocol */
   IPPROTO_RSVP = 46,            /* RSVP protocol                        */
   IPPROTO_GRE = 47,             /* Cisco GRE tunnels (rfc 1701,1702)    */
 
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
new file mode 100644
index 000000000000..a4606e5810e5
--- /dev/null
+++ b/include/linux/inet_diag.h
@@ -0,0 +1,138 @@
+#ifndef _INET_DIAG_H_
+#define _INET_DIAG_H_ 1
+
+/* Just some random number */
+#define TCPDIAG_GETSOCK 18
+#define DCCPDIAG_GETSOCK 19
+
+#define INET_DIAG_GETSOCK_MAX 24
+
+/* Socket identity */
+struct inet_diag_sockid {
+        __u16   idiag_sport;
+        __u16   idiag_dport;
+        __u32   idiag_src[4];
+        __u32   idiag_dst[4];
+        __u32   idiag_if;
+        __u32   idiag_cookie[2];
+#define INET_DIAG_NOCOOKIE (~0U)
+};
+
+/* Request structure */
+
+struct inet_diag_req {
+        __u8    idiag_family;           /* Family of addresses. */
+        __u8    idiag_src_len;
+        __u8    idiag_dst_len;
+        __u8    idiag_ext;              /* Query extended information */
+
+        struct inet_diag_sockid id;
+
+        __u32   idiag_states;           /* States to dump */
+        __u32   idiag_dbs;              /* Tables to dump (NI) */
+};
+
+enum {
+        INET_DIAG_REQ_NONE,
+        INET_DIAG_REQ_BYTECODE,
+};
+
+#define INET_DIAG_REQ_MAX INET_DIAG_REQ_BYTECODE
+
+/* Bytecode is sequence of 4 byte commands followed by variable arguments.
+ * All the commands identified by "code" are conditional jumps forward:
+ * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be
+ * length of the command and its arguments.
+ */
+ 
+struct inet_diag_bc_op {
+        unsigned char   code;
+        unsigned char   yes;
+        unsigned short  no;
+};
+
+enum {
+        INET_DIAG_BC_NOP,
+        INET_DIAG_BC_JMP,
+        INET_DIAG_BC_S_GE,
+        INET_DIAG_BC_S_LE,
+        INET_DIAG_BC_D_GE,
+        INET_DIAG_BC_D_LE,
+        INET_DIAG_BC_AUTO,
+        INET_DIAG_BC_S_COND,
+        INET_DIAG_BC_D_COND,
+};
+
+struct inet_diag_hostcond {
+        __u8    family;
+        __u8    prefix_len;
+        int     port;
+        __u32   addr[0];
+};
+
+/* Base info structure. It contains socket identity (addrs/ports/cookie)
+ * and, alas, the information shown by netstat. */
+struct inet_diag_msg {
+        __u8    idiag_family;
+        __u8    idiag_state;
+        __u8    idiag_timer;
+        __u8    idiag_retrans;
+
+        struct inet_diag_sockid id;
+
+        __u32   idiag_expires;
+        __u32   idiag_rqueue;
+        __u32   idiag_wqueue;
+        __u32   idiag_uid;
+        __u32   idiag_inode;
+};
+
+/* Extensions */
+
+enum {
+        INET_DIAG_NONE,
+        INET_DIAG_MEMINFO,
+        INET_DIAG_INFO,
+        INET_DIAG_VEGASINFO,
+        INET_DIAG_CONG,
+};
+
+#define INET_DIAG_MAX INET_DIAG_CONG
+
+
+/* INET_DIAG_MEM */
+
+struct inet_diag_meminfo {
+        __u32   idiag_rmem;
+        __u32   idiag_wmem;
+        __u32   idiag_fmem;
+        __u32   idiag_tmem;
+};
+
+/* INET_DIAG_VEGASINFO */
+
+struct tcpvegas_info {
+        __u32   tcpv_enabled;
+        __u32   tcpv_rttcnt;
+        __u32   tcpv_rtt;
+        __u32   tcpv_minrtt;
+};
+
+#ifdef __KERNEL__
+struct sock;
+struct inet_hashinfo;
+
+struct inet_diag_handler {
+        struct inet_hashinfo    *idiag_hashinfo;
+        void                    (*idiag_get_info)(struct sock *sk,
+                                                  struct inet_diag_msg *r,
+                                                  void *info);
+        __u16                   idiag_info_size;
+        __u16                   idiag_type;
+};
+
+extern int  inet_diag_register(const struct inet_diag_handler *handler);
+extern void inet_diag_unregister(const struct inet_diag_handler *handler);
+#endif /* __KERNEL__ */
+
+#endif /* _INET_DIAG_H_ */
diff --git a/include/linux/ip.h b/include/linux/ip.h
index 31e7cedd9f84..33e8a19a1a0f 100644
--- a/include/linux/ip.h
+++ b/include/linux/ip.h
@@ -196,6 +196,8 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 #endif
 #endif
 
+extern int inet_sk_rebuild_header(struct sock *sk);
+
 struct iphdr {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
         __u8    ihl:4,
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 6fcd6a0ade24..3c7dbc6a0a70 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -193,6 +193,11 @@ struct inet6_skb_parm {
 
 #define IP6CB(skb)      ((struct inet6_skb_parm*)((skb)->cb))
 
+static inline int inet6_iif(const struct sk_buff *skb)
+{
+        return IP6CB(skb)->iif;
+}
+
 struct tcp6_request_sock {
         struct tcp_request_sock req;
         struct in6_addr         loc_addr;
@@ -308,6 +313,36 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 
 #define __ipv6_only_sock(sk)    (inet6_sk(sk)->ipv6only)
 #define ipv6_only_sock(sk)      ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk))
+
+#include <linux/tcp.h>
+
+struct tcp6_timewait_sock {
+        struct tcp_timewait_sock tw_v6_sk;
+        struct in6_addr          tw_v6_daddr;
+        struct in6_addr          tw_v6_rcv_saddr;
+};
+
+static inline struct tcp6_timewait_sock *tcp6_twsk(const struct sock *sk)
+{
+        return (struct tcp6_timewait_sock *)sk;
+}
+
+static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk)
+{
+        return likely(sk->sk_state != TCP_TIME_WAIT) ?
+                &inet6_sk(sk)->rcv_saddr : &tcp6_twsk(sk)->tw_v6_rcv_saddr;
+}
+
+static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk)
+{
+        return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL;
+}
+
+static inline int inet_v6_ipv6only(const struct sock *sk)
+{
+        return likely(sk->sk_state != TCP_TIME_WAIT) ?
+                ipv6_only_sock(sk) : inet_twsk(sk)->tw_ipv6only;
+}
 #else
 #define __ipv6_only_sock(sk)    0
 #define ipv6_only_sock(sk)      0
@@ -322,8 +357,19 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
         return NULL;
 }
 
-#endif
+#define __tcp_v6_rcv_saddr(__sk)        NULL
+#define tcp_v6_rcv_saddr(__sk)          NULL
+#define tcp_twsk_ipv6only(__sk)         0
+#define inet_v6_ipv6only(__sk)          0
+#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
 
-#endif
+#define INET6_MATCH(__sk, __saddr, __daddr, __ports, __dif)        \
+        (((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports))   && \
+         ((__sk)->sk_family             == AF_INET6)            && \
+         ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))     && \
+         ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \
+         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
 
-#endif
+#endif /* __KERNEL__ */
+
+#endif /* _IPV6_H */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 6cd9ba63563b..fc05a9899288 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1,23 +1,26 @@
 /*
-   Copyright 2003-2004 Red Hat, Inc.  All rights reserved.
-   Copyright 2003-2004 Jeff Garzik
-
-   The contents of this file are subject to the Open
-   Software License version 1.1 that can be found at
-   http://www.opensource.org/licenses/osl-1.1.txt and is included herein
-   by reference.
-
-   Alternatively, the contents of this file may be used under the terms
-   of the GNU General Public License version 2 (the "GPL") as distributed
-   in the kernel source COPYING file, in which case the provisions of
-   the GPL are applicable instead of the above.  If you wish to allow
-   the use of your version of this file only under the terms of the
-   GPL and not to allow others to use your version of this file under
-   the OSL, indicate your decision by deleting the provisions above and
-   replace them with the notice and other provisions required by the GPL.
-   If you do not delete the provisions above, a recipient may use your
-   version of this file under either the OSL or the GPL.
-
+ *  Copyright 2003-2005 Red Hat, Inc.  All rights reserved.
+ *  Copyright 2003-2005 Jeff Garzik
+ *
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *
+ *  libata documentation is available via 'make {ps|pdf}docs',
+ *  as Documentation/DocBook/libata.*
+ *
  */
 
 #ifndef __LINUX_LIBATA_H__
@@ -113,6 +116,8 @@ enum {
         ATA_FLAG_MMIO           = (1 << 6), /* use MMIO, not PIO */
         ATA_FLAG_SATA_RESET     = (1 << 7), /* use COMRESET */
         ATA_FLAG_PIO_DMA        = (1 << 8), /* PIO cmds via DMA */
+        ATA_FLAG_NOINTR         = (1 << 9), /* FIXME: Remove this once
+                                             * proper HSM is in place. */
 
         ATA_QCFLAG_ACTIVE       = (1 << 1), /* cmd not yet ack'd to scsi lyer */
         ATA_QCFLAG_SG           = (1 << 3), /* have s/g table? */
@@ -363,7 +368,7 @@ struct ata_port_operations {
 
         void (*host_stop) (struct ata_host_set *host_set);
 
-        void (*bmdma_stop) (struct ata_port *ap);
+        void (*bmdma_stop) (struct ata_queued_cmd *qc);
         u8   (*bmdma_status) (struct ata_port *ap);
 };
 
@@ -424,7 +429,7 @@ extern void ata_dev_id_string(u16 *id, unsigned char *s,
 extern void ata_dev_config(struct ata_port *ap, unsigned int i);
 extern void ata_bmdma_setup (struct ata_queued_cmd *qc);
 extern void ata_bmdma_start (struct ata_queued_cmd *qc);
-extern void ata_bmdma_stop(struct ata_port *ap);
+extern void ata_bmdma_stop(struct ata_queued_cmd *qc);
 extern u8   ata_bmdma_status(struct ata_port *ap);
 extern void ata_bmdma_irq_clear(struct ata_port *ap);
 extern void ata_qc_complete(struct ata_queued_cmd *qc, u8 drv_stat);
@@ -644,7 +649,7 @@ static inline void scr_write(struct ata_port *ap, unsigned int reg, u32 val)
         ap->ops->scr_write(ap, reg, val);
 }
 
-static inline void scr_write_flush(struct ata_port *ap, unsigned int reg, 
+static inline void scr_write_flush(struct ata_port *ap, unsigned int reg,
                                    u32 val)
 {
         ap->ops->scr_write(ap, reg, val);
diff --git a/include/linux/list.h b/include/linux/list.h
index aab2db21b013..e6ec59682274 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -419,6 +419,20 @@ static inline void list_splice_init(struct list_head *list,
              pos = n, n = list_entry(n->member.next, typeof(*n), member))
 
 /**
+ * list_for_each_entry_safe_continue -  iterate over list of given type
+ *                      continuing after existing point safe against removal of list entry
+ * @pos:        the type * to use as a loop counter.
+ * @n:          another type * to use as temporary storage
+ * @head:       the head for your list.
+ * @member:     the name of the list_struct within the struct.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member)                 \
+        for (pos = list_entry(pos->member.next, typeof(*pos), member),          \
+                n = list_entry(pos->member.next, typeof(*pos), member);         \
+             &pos->member != (head);                                            \
+             pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
  * list_for_each_rcu    -       iterate over an rcu-protected list
  * @pos:        the &struct list_head to use as a loop counter.
  * @head:       the head for your list.
@@ -620,6 +634,57 @@ static inline void hlist_add_after(struct hlist_node *n,
                 next->next->pprev  = &next->next;
 }
 
+/**
+ * hlist_add_before_rcu - adds the specified element to the specified hlist
+ * before the specified node while permitting racing traversals.
+ * @n: the new element to add to the hash list.
+ * @next: the existing element to add the new element before.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.
+ */
+static inline void hlist_add_before_rcu(struct hlist_node *n,
+                                        struct hlist_node *next)
+{
+        n->pprev = next->pprev;
+        n->next = next;
+        smp_wmb();
+        next->pprev = &n->next;
+        *(n->pprev) = n;
+}
+
+/**
+ * hlist_add_after_rcu - adds the specified element to the specified hlist
+ * after the specified node while permitting racing traversals.
+ * @prev: the existing element to add the new element after.
+ * @n: the new element to add to the hash list.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.
+ */
+static inline void hlist_add_after_rcu(struct hlist_node *prev,
+                                       struct hlist_node *n)
+{
+        n->next = prev->next;
+        n->pprev = &prev->next;
+        smp_wmb();
+        prev->next = n;
+        if (n->next)
+                n->next->pprev = &n->next;
+}
+
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 374b615ea9ea..9b8d0476988a 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -22,6 +22,7 @@
 #define MII_EXPANSION       0x06        /* Expansion register          */
 #define MII_CTRL1000        0x09        /* 1000BASE-T control          */
 #define MII_STAT1000        0x0a        /* 1000BASE-T status           */
+#define MII_ESTATUS         0x0f        /* Extended Status */
 #define MII_DCOUNTER        0x12        /* Disconnect counter          */
 #define MII_FCSCOUNTER      0x13        /* False carrier counter       */
 #define MII_NWAYTEST        0x14        /* N-way auto-neg test reg     */
@@ -54,7 +55,10 @@
 #define BMSR_ANEGCAPABLE        0x0008  /* Able to do auto-negotiation */
 #define BMSR_RFAULT             0x0010  /* Remote fault detected       */
 #define BMSR_ANEGCOMPLETE       0x0020  /* Auto-negotiation complete   */
-#define BMSR_RESV               0x07c0  /* Unused...                   */
+#define BMSR_RESV               0x00c0  /* Unused...                   */
+#define BMSR_ESTATEN            0x0100  /* Extended Status in R15 */
+#define BMSR_100FULL2           0x0200  /* Can do 100BASE-T2 HDX */
+#define BMSR_100HALF2           0x0400  /* Can do 100BASE-T2 FDX */
 #define BMSR_10HALF             0x0800  /* Can do 10mbps, half-duplex  */
 #define BMSR_10FULL             0x1000  /* Can do 10mbps, full-duplex  */
 #define BMSR_100HALF            0x2000  /* Can do 100mbps, half-duplex */
@@ -114,6 +118,9 @@
 #define EXPANSION_MFAULTS       0x0010  /* Multiple faults detected    */
 #define EXPANSION_RESV          0xffe0  /* Unused...                   */
 
+#define ESTATUS_1000_TFULL      0x2000  /* Can do 1000BT Full */
+#define ESTATUS_1000_THALF      0x1000  /* Can do 1000BT Half */
+
 /* N-way test register. */
 #define NWAYTEST_RESV1          0x00ff  /* Unused...                   */
 #define NWAYTEST_LOOPBACK       0x0100  /* Enable loopback for N-way   */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index f90f674eb3b0..9a0893f3249e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -63,11 +63,12 @@ struct device;
 
 struct mmc_host {
         struct device           *dev;
+        struct class_device     class_dev;
+        int                     index;
         struct mmc_host_ops     *ops;
         unsigned int            f_min;
         unsigned int            f_max;
         u32                     ocr_avail;
-        char                    host_name[8];
 
         /* host specific block data */
         unsigned int            max_seg_size;   /* see blk_queue_max_segment_size */
@@ -97,6 +98,7 @@ extern void mmc_free_host(struct mmc_host *);
 
 #define mmc_priv(x)     ((void *)((x) + 1))
 #define mmc_dev(x)      ((x)->dev)
+#define mmc_hostname(x) ((x)->class_dev.class_id)
 
 extern int mmc_suspend_host(struct mmc_host *, pm_message_t);
 extern int mmc_resume_host(struct mmc_host *);
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index dce53ac1625d..47da39ba3f03 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -1,6 +1,6 @@
 /*
  * Device tables which are exported to userspace via
- * scripts/table2alias.c.  You must keep that file in sync with this
+ * scripts/mod/file2alias.c.  You must keep that file in sync with this
  * header.
  */
 
@@ -33,7 +33,8 @@ struct ieee1394_device_id {
         __u32 model_id;
         __u32 specifier_id;
         __u32 version;
-        kernel_ulong_t driver_data;
+        kernel_ulong_t driver_data
+                __attribute__((aligned(sizeof(kernel_ulong_t))));
 };
 
 
@@ -182,9 +183,18 @@ struct of_device_id
         char    name[32];
         char    type[32];
         char    compatible[128];
+#if __KERNEL__
         void    *data;
+#else
+        kernel_ulong_t data;
+#endif
 };
 
+/* VIO */
+struct vio_device_id {
+        char type[32];
+        char compat[32];
+};
 
 /* PCMCIA */
 
@@ -208,7 +218,8 @@ struct pcmcia_device_id {
 #ifdef __KERNEL__
         const char *    prod_id[4];
 #else
-        kernel_ulong_t  prod_id[4];
+        kernel_ulong_t  prod_id[4]
+                __attribute__((aligned(sizeof(kernel_ulong_t))));
 #endif
 
         /* not matched against */
diff --git a/include/linux/net.h b/include/linux/net.h
index 20cb226b2268..4e981585a89a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -84,6 +84,7 @@ enum sock_type {
         SOCK_RAW        = 3,
         SOCK_RDM        = 4,
         SOCK_SEQPACKET  = 5,
+        SOCK_DCCP       = 6,
         SOCK_PACKET     = 10,
 };
 
@@ -282,5 +283,15 @@ static struct proto_ops name##_ops = {			\
 #define MODULE_ALIAS_NETPROTO(proto) \
         MODULE_ALIAS("net-pf-" __stringify(proto))
 
+#define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \
+        MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto))
+
+#ifdef CONFIG_SYSCTL
+#include <linux/sysctl.h>
+extern ctl_table net_table[];
+extern int net_msg_cost;
+extern int net_msg_burst;
+#endif
+
 #endif /* __KERNEL__ */
 #endif  /* _LINUX_NET_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3a0ed7f9e801..7c717907896d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -244,6 +244,7 @@ struct netdev_boot_setup {
 };
 #define NETDEV_BOOT_SETUP_MAX 8
 
+extern int __init netdev_boot_setup(char *str);
 
 /*
  *      The DEVICE structure.
@@ -336,6 +337,7 @@ struct net_device
         /* Interface address info. */
         unsigned char           broadcast[MAX_ADDR_LEN];        /* hw bcast add */
         unsigned char           dev_addr[MAX_ADDR_LEN]; /* hw address   */
+        unsigned char           perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
         unsigned char           addr_len;       /* hardware address length      */
         unsigned short          dev_id;         /* for shared network cards */
 
@@ -497,10 +499,12 @@ static inline void *netdev_priv(struct net_device *dev)
 #define SET_NETDEV_DEV(net, pdev)       ((net)->class_dev.dev = (pdev))
 
 struct packet_type {
-        __be16                  type;   /* This is really htons(ether_type).    */
-        struct net_device               *dev;   /* NULL is wildcarded here              */
-        int                     (*func) (struct sk_buff *, struct net_device *,
-                                         struct packet_type *);
+        __be16                  type;   /* This is really htons(ether_type). */
+        struct net_device       *dev;   /* NULL is wildcarded here           */
+        int                     (*func) (struct sk_buff *,
+                                         struct net_device *,
+                                         struct packet_type *,
+                                         struct net_device *);
         void                    *af_packet_priv;
         struct list_head        list;
 };
@@ -671,6 +675,7 @@ extern void		dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 extern void             dev_init(void);
 
 extern int              netdev_nit;
+extern int              netdev_budget;
 
 /* Called by rtnetlink.c:rtnl_unlock() */
 extern void netdev_run_todo(void);
@@ -697,19 +702,9 @@ static inline int netif_carrier_ok(const struct net_device *dev)
 
 extern void __netdev_watchdog_up(struct net_device *dev);
 
-static inline void netif_carrier_on(struct net_device *dev)
-{
-        if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state))
-                linkwatch_fire_event(dev);
-        if (netif_running(dev))
-                __netdev_watchdog_up(dev);
-}
+extern void netif_carrier_on(struct net_device *dev);
 
-static inline void netif_carrier_off(struct net_device *dev)
-{
-        if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state))
-                linkwatch_fire_event(dev);
-}
+extern void netif_carrier_off(struct net_device *dev);
 
 /* Hot-plugging. */
 static inline int netif_device_present(struct net_device *dev)
@@ -916,6 +911,14 @@ extern int skb_checksum_help(struct sk_buff *skb, int inward);
 extern void             net_enable_timestamp(void);
 extern void             net_disable_timestamp(void);
 
+#ifdef CONFIG_PROC_FS
+extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
+extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+extern void dev_seq_stop(struct seq_file *seq, void *v);
+#endif
+
+extern void linkwatch_run_queue(void);
+
 #endif /* __KERNEL__ */
 
 #endif  /* _LINUX_DEV_H */
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 2e2045482cb1..be365e70ee99 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -21,10 +21,23 @@
 #define NF_STOP 5
 #define NF_MAX_VERDICT NF_STOP
 
+/* we overload the higher bits for encoding auxiliary data such as the queue
+ * number. Not nice, but better than additional function arguments. */
+#define NF_VERDICT_MASK 0x0000ffff
+#define NF_VERDICT_BITS 16
+
+#define NF_VERDICT_QMASK 0xffff0000
+#define NF_VERDICT_QBITS 16
+
+#define NF_QUEUE_NR(x) (((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK) | NF_QUEUE)
+
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* Generic cache responses from hook functions.
    <= 0x2000 is used for protocol-flags. */
 #define NFC_UNKNOWN 0x4000
 #define NFC_ALTERED 0x8000
+#endif
 
 #ifdef __KERNEL__
 #include <linux/config.h>
@@ -101,15 +114,51 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
 
 extern struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS];
 
-typedef void nf_logfn(unsigned int hooknum,
+/* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will
+ * disappear once iptables is replaced with pkttables.  Please DO NOT use them
+ * for any new code! */
+#define NF_LOG_TCPSEQ           0x01    /* Log TCP sequence numbers */
+#define NF_LOG_TCPOPT           0x02    /* Log TCP options */
+#define NF_LOG_IPOPT            0x04    /* Log IP options */
+#define NF_LOG_UID              0x08    /* Log UID owning local socket */
+#define NF_LOG_MASK             0x0f
+
+#define NF_LOG_TYPE_LOG         0x01
+#define NF_LOG_TYPE_ULOG        0x02
+
+struct nf_loginfo {
+        u_int8_t type;
+        union {
+                struct {
+                        u_int32_t copy_len;
+                        u_int16_t group;
+                        u_int16_t qthreshold;
+                } ulog;
+                struct {
+                        u_int8_t level;
+                        u_int8_t logflags;
+                } log;
+        } u;
+};
+
+typedef void nf_logfn(unsigned int pf,
+                      unsigned int hooknum,
                       const struct sk_buff *skb,
                       const struct net_device *in,
                       const struct net_device *out,
+                      const struct nf_loginfo *li,
                       const char *prefix);
 
+struct nf_logger {
+        struct module   *me;
+        nf_logfn        *logfn;
+        char            *name;
+};
+
 /* Function to register/unregister log function. */
-int nf_log_register(int pf, nf_logfn *logfn);
-void nf_log_unregister(int pf, nf_logfn *logfn);
+int nf_log_register(int pf, struct nf_logger *logger);
+int nf_log_unregister_pf(int pf);
+void nf_log_unregister_logger(struct nf_logger *logger);
 
 /* Calls the registered backend logging function */
 void nf_log_packet(int pf,
@@ -117,6 +166,7 @@ void nf_log_packet(int pf,
                    const struct sk_buff *skb,
                    const struct net_device *in,
                    const struct net_device *out,
+                   struct nf_loginfo *li,
                    const char *fmt, ...);
                    
 /* Activate hook; either okfn or kfree_skb called, unless a hook
@@ -175,11 +225,16 @@ int nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt,
                   int *len);
 
 /* Packet queuing */
-typedef int (*nf_queue_outfn_t)(struct sk_buff *skb, 
-                                struct nf_info *info, void *data);
+struct nf_queue_handler {
+        int (*outfn)(struct sk_buff *skb, struct nf_info *info,
+                     unsigned int queuenum, void *data);
+        void *data;
+        char *name;
+};
 extern int nf_register_queue_handler(int pf, 
-                                     nf_queue_outfn_t outfn, void *data);
+                                     struct nf_queue_handler *qh);
 extern int nf_unregister_queue_handler(int pf);
+extern void nf_unregister_queue_handlers(struct nf_queue_handler *qh);
 extern void nf_reinject(struct sk_buff *skb,
                         struct nf_info *info,
                         unsigned int verdict);
@@ -190,6 +245,27 @@ extern void nf_ct_attach(struct sk_buff *, struct sk_buff *);
 /* FIXME: Before cache is ever used, this must be implemented for real. */
 extern void nf_invalidate_cache(int pf);
 
+/* Call this before modifying an existing packet: ensures it is
+   modifiable and linear to the point you care about (writable_len).
+   Returns true or false. */
+extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len);
+
+struct nf_queue_rerouter {
+        void (*save)(const struct sk_buff *skb, struct nf_info *info);
+        int (*reroute)(struct sk_buff **skb, const struct nf_info *info);
+        int rer_size;
+};
+
+#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info))
+
+extern int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer);
+extern int nf_unregister_queue_rerouter(int pf);
+
+#ifdef CONFIG_PROC_FS
+#include <linux/proc_fs.h>
+extern struct proc_dir_entry *proc_net_netfilter;
+#endif
+
 #else /* !CONFIG_NETFILTER */
 #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb)
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
new file mode 100644
index 000000000000..1d5b10ae2399
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink.h
@@ -0,0 +1,169 @@
+#ifndef _NFNETLINK_H
+#define _NFNETLINK_H
+#include <linux/types.h>
+
+#ifndef __KERNEL__
+/* nfnetlink groups: Up to 32 maximum - backwards compatibility for userspace */
+#define NF_NETLINK_CONNTRACK_NEW                0x00000001
+#define NF_NETLINK_CONNTRACK_UPDATE             0x00000002
+#define NF_NETLINK_CONNTRACK_DESTROY            0x00000004
+#define NF_NETLINK_CONNTRACK_EXP_NEW            0x00000008
+#define NF_NETLINK_CONNTRACK_EXP_UPDATE         0x00000010
+#define NF_NETLINK_CONNTRACK_EXP_DESTROY        0x00000020
+#endif
+
+enum nfnetlink_groups {
+        NFNLGRP_NONE,
+#define NFNLGRP_NONE                    NFNLGRP_NONE
+        NFNLGRP_CONNTRACK_NEW,
+#define NFNLGRP_CONNTRACK_NEW           NFNLGRP_CONNTRACK_NEW
+        NFNLGRP_CONNTRACK_UPDATE,
+#define NFNLGRP_CONNTRACK_UPDATE        NFNLGRP_CONNTRACK_UPDATE
+        NFNLGRP_CONNTRACK_DESTROY,
+#define NFNLGRP_CONNTRACK_DESTROY       NFNLGRP_CONNTRACK_DESTROY
+        NFNLGRP_CONNTRACK_EXP_NEW,
+#define NFNLGRP_CONNTRACK_EXP_NEW       NFNLGRP_CONNTRACK_EXP_NEW
+        NFNLGRP_CONNTRACK_EXP_UPDATE,
+#define NFNLGRP_CONNTRACK_EXP_UPDATE    NFNLGRP_CONNTRACK_EXP_UPDATE
+        NFNLGRP_CONNTRACK_EXP_DESTROY,
+#define NFNLGRP_CONNTRACK_EXP_DESTROY   NFNLGRP_CONNTRACK_EXP_DESTROY
+        __NFNLGRP_MAX,
+};
+#define NFNLGRP_MAX     (__NFNLGRP_MAX - 1)
+
+/* Generic structure for encapsulation optional netfilter information.
+ * It is reminiscent of sockaddr, but with sa_family replaced
+ * with attribute type. 
+ * ! This should someday be put somewhere generic as now rtnetlink and
+ * ! nfnetlink use the same attributes methods. - J. Schulist.
+ */
+
+struct nfattr
+{
+        u_int16_t nfa_len;
+        u_int16_t nfa_type;
+} __attribute__ ((packed));
+
+/* FIXME: Shamelessly copy and pasted from rtnetlink.h, it's time
+ *        to put this in a generic file */
+
+#define NFA_ALIGNTO     4
+#define NFA_ALIGN(len)  (((len) + NFA_ALIGNTO - 1) & ~(NFA_ALIGNTO - 1))
+#define NFA_OK(nfa,len) ((len) > 0 && (nfa)->nfa_len >= sizeof(struct nfattr) \
+        && (nfa)->nfa_len <= (len))
+#define NFA_NEXT(nfa,attrlen)   ((attrlen) -= NFA_ALIGN((nfa)->nfa_len), \
+        (struct nfattr *)(((char *)(nfa)) + NFA_ALIGN((nfa)->nfa_len)))
+#define NFA_LENGTH(len) (NFA_ALIGN(sizeof(struct nfattr)) + (len))
+#define NFA_SPACE(len)  NFA_ALIGN(NFA_LENGTH(len))
+#define NFA_DATA(nfa)   ((void *)(((char *)(nfa)) + NFA_LENGTH(0)))
+#define NFA_PAYLOAD(nfa) ((int)((nfa)->nfa_len) - NFA_LENGTH(0))
+#define NFA_NEST(skb, type) \
+({      struct nfattr *__start = (struct nfattr *) (skb)->tail; \
+        NFA_PUT(skb, type, 0, NULL); \
+        __start;  })
+#define NFA_NEST_END(skb, start) \
+({      (start)->nfa_len = ((skb)->tail - (unsigned char *) (start)); \
+        (skb)->len; })
+#define NFA_NEST_CANCEL(skb, start) \
+({      if (start) \
+                skb_trim(skb, (unsigned char *) (start) - (skb)->data); \
+        -1; })
+
+/* General form of address family dependent message.
+ */
+struct nfgenmsg {
+        u_int8_t  nfgen_family;         /* AF_xxx */
+        u_int8_t  version;              /* nfnetlink version */
+        u_int16_t res_id;               /* resource id */
+} __attribute__ ((packed));
+
+#define NFNETLINK_V0    0
+
+#define NFM_NFA(n)      ((struct nfattr *)(((char *)(n)) \
+        + NLMSG_ALIGN(sizeof(struct nfgenmsg))))
+#define NFM_PAYLOAD(n)  NLMSG_PAYLOAD(n, sizeof(struct nfgenmsg))
+
+/* netfilter netlink message types are split in two pieces:
+ * 8 bit subsystem, 8bit operation.
+ */
+
+#define NFNL_SUBSYS_ID(x)       ((x & 0xff00) >> 8)
+#define NFNL_MSG_TYPE(x)        (x & 0x00ff)
+
+/* No enum here, otherwise __stringify() trick of MODULE_ALIAS_NFNL_SUBSYS()
+ * won't work anymore */
+#define NFNL_SUBSYS_NONE                0
+#define NFNL_SUBSYS_CTNETLINK           1
+#define NFNL_SUBSYS_CTNETLINK_EXP       2
+#define NFNL_SUBSYS_QUEUE               3
+#define NFNL_SUBSYS_ULOG                4
+#define NFNL_SUBSYS_COUNT               5
+
+#ifdef __KERNEL__
+
+#include <linux/netlink.h>
+#include <linux/capability.h>
+
+struct nfnl_callback
+{
+        int (*call)(struct sock *nl, struct sk_buff *skb, 
+                struct nlmsghdr *nlh, struct nfattr *cda[], int *errp);
+        kernel_cap_t cap_required; /* capabilities required for this msg */
+        u_int16_t attr_count;   /* number of nfattr's */
+};
+
+struct nfnetlink_subsystem
+{
+        const char *name;
+        __u8 subsys_id;         /* nfnetlink subsystem ID */
+        __u8 cb_count;          /* number of callbacks */
+        struct nfnl_callback *cb; /* callback for individual types */
+};
+
+extern void __nfa_fill(struct sk_buff *skb, int attrtype,
+        int attrlen, const void *data);
+#define NFA_PUT(skb, attrtype, attrlen, data) \
+({ if (skb_tailroom(skb) < (int)NFA_SPACE(attrlen)) goto nfattr_failure; \
+   __nfa_fill(skb, attrtype, attrlen, data); })
+
+extern struct semaphore nfnl_sem;
+
+#define nfnl_shlock()           down(&nfnl_sem)
+#define nfnl_shlock_nowait()    down_trylock(&nfnl_sem)
+
+#define nfnl_shunlock()         do { up(&nfnl_sem); \
+                                     if(nfnl && nfnl->sk_receive_queue.qlen) \
+                                            nfnl->sk_data_ready(nfnl, 0); \
+                                } while(0)
+
+extern void nfnl_lock(void);
+extern void nfnl_unlock(void);
+
+extern int nfnetlink_subsys_register(struct nfnetlink_subsystem *n);
+extern int nfnetlink_subsys_unregister(struct nfnetlink_subsystem *n);
+
+extern int nfattr_parse(struct nfattr *tb[], int maxattr, 
+                        struct nfattr *nfa, int len);
+
+#define nfattr_parse_nested(tb, max, nfa) \
+        nfattr_parse((tb), (max), NFA_DATA((nfa)), NFA_PAYLOAD((nfa)))
+
+#define nfattr_bad_size(tb, max, cta_min)                               \
+({      int __i, __res = 0;                                             \
+        for (__i=0; __i<max; __i++)                                     \
+                if (tb[__i] && NFA_PAYLOAD(tb[__i]) < cta_min[__i]){    \
+                        __res = 1;                                      \
+                        break;                                          \
+                }                                                       \
+        __res;                                                          \
+})
+
+extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, 
+                          int echo);
+extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags);
+
+#define MODULE_ALIAS_NFNL_SUBSYS(subsys) \
+        MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys))
+
+#endif  /* __KERNEL__ */
+#endif  /* _NFNETLINK_H */
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
new file mode 100644
index 000000000000..5c55751c78e4
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -0,0 +1,124 @@
+#ifndef _IPCONNTRACK_NETLINK_H
+#define _IPCONNTRACK_NETLINK_H
+#include <linux/netfilter/nfnetlink.h>
+
+enum cntl_msg_types {
+        IPCTNL_MSG_CT_NEW,
+        IPCTNL_MSG_CT_GET,
+        IPCTNL_MSG_CT_DELETE,
+        IPCTNL_MSG_CT_GET_CTRZERO,
+
+        IPCTNL_MSG_MAX
+};
+
+enum ctnl_exp_msg_types {
+        IPCTNL_MSG_EXP_NEW,
+        IPCTNL_MSG_EXP_GET,
+        IPCTNL_MSG_EXP_DELETE,
+
+        IPCTNL_MSG_EXP_MAX
+};
+
+
+enum ctattr_type {
+        CTA_UNSPEC,
+        CTA_TUPLE_ORIG,
+        CTA_TUPLE_REPLY,
+        CTA_STATUS,
+        CTA_PROTOINFO,
+        CTA_HELP,
+        CTA_NAT,
+        CTA_TIMEOUT,
+        CTA_MARK,
+        CTA_COUNTERS_ORIG,
+        CTA_COUNTERS_REPLY,
+        CTA_USE,
+        CTA_ID,
+        __CTA_MAX
+};
+#define CTA_MAX (__CTA_MAX - 1)
+
+enum ctattr_tuple {
+        CTA_TUPLE_UNSPEC,
+        CTA_TUPLE_IP,
+        CTA_TUPLE_PROTO,
+        __CTA_TUPLE_MAX
+};
+#define CTA_TUPLE_MAX (__CTA_TUPLE_MAX - 1)
+
+enum ctattr_ip {
+        CTA_IP_UNSPEC,
+        CTA_IP_V4_SRC,
+        CTA_IP_V4_DST,
+        CTA_IP_V6_SRC,
+        CTA_IP_V6_DST,
+        __CTA_IP_MAX
+};
+#define CTA_IP_MAX (__CTA_IP_MAX - 1)
+
+enum ctattr_l4proto {
+        CTA_PROTO_UNSPEC,
+        CTA_PROTO_NUM,
+        CTA_PROTO_SRC_PORT,
+        CTA_PROTO_DST_PORT,
+        CTA_PROTO_ICMP_ID,
+        CTA_PROTO_ICMP_TYPE,
+        CTA_PROTO_ICMP_CODE,
+        __CTA_PROTO_MAX
+};
+#define CTA_PROTO_MAX (__CTA_PROTO_MAX - 1)
+
+enum ctattr_protoinfo {
+        CTA_PROTOINFO_UNSPEC,
+        CTA_PROTOINFO_TCP_STATE,
+        __CTA_PROTOINFO_MAX
+};
+#define CTA_PROTOINFO_MAX (__CTA_PROTOINFO_MAX - 1)
+
+enum ctattr_counters {
+        CTA_COUNTERS_UNSPEC,
+        CTA_COUNTERS_PACKETS,
+        CTA_COUNTERS_BYTES,
+        __CTA_COUNTERS_MAX
+};
+#define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1)
+
+enum ctattr_nat {
+        CTA_NAT_UNSPEC,
+        CTA_NAT_MINIP,
+        CTA_NAT_MAXIP,
+        CTA_NAT_PROTO,
+        __CTA_NAT_MAX
+};
+#define CTA_NAT_MAX (__CTA_NAT_MAX - 1)
+
+enum ctattr_protonat {
+        CTA_PROTONAT_UNSPEC,
+        CTA_PROTONAT_PORT_MIN,
+        CTA_PROTONAT_PORT_MAX,
+        __CTA_PROTONAT_MAX
+};
+#define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1)
+
+enum ctattr_expect {
+        CTA_EXPECT_UNSPEC,
+        CTA_EXPECT_MASTER,
+        CTA_EXPECT_TUPLE,
+        CTA_EXPECT_MASK,
+        CTA_EXPECT_TIMEOUT,
+        CTA_EXPECT_ID,
+        CTA_EXPECT_HELP_NAME,
+        __CTA_EXPECT_MAX
+};
+#define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1)
+
+enum ctattr_help {
+        CTA_HELP_UNSPEC,
+        CTA_HELP_NAME,
+        __CTA_HELP_MAX
+};
+#define CTA_HELP_MAX (__CTA_HELP_MAX - 1)
+
+#define CTA_HELP_MAXNAMESIZE    32
+
+#endif /* _IPCONNTRACK_NETLINK_H */
diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h
new file mode 100644
index 000000000000..b04b03880595
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink_log.h
@@ -0,0 +1,88 @@
+#ifndef _NFNETLINK_LOG_H
+#define _NFNETLINK_LOG_H
+
+/* This file describes the netlink messages (i.e. 'protocol packets'),
+ * and not any kind of function definitions.  It is shared between kernel and
+ * userspace.  Don't put kernel specific stuff in here */
+
+#include <linux/types.h>
+#include <linux/netfilter/nfnetlink.h>
+
+enum nfulnl_msg_types {
+        NFULNL_MSG_PACKET,              /* packet from kernel to userspace */
+        NFULNL_MSG_CONFIG,              /* connect to a particular queue */
+
+        NFULNL_MSG_MAX
+};
+
+struct nfulnl_msg_packet_hdr {
+        u_int16_t       hw_protocol;    /* hw protocol (network order) */
+        u_int8_t        hook;           /* netfilter hook */
+        u_int8_t        _pad;
+} __attribute__ ((packed));
+
+struct nfulnl_msg_packet_hw {
+        u_int16_t       hw_addrlen;
+        u_int16_t       _pad;
+        u_int8_t        hw_addr[8];
+} __attribute__ ((packed));
+
+struct nfulnl_msg_packet_timestamp {
+        aligned_u64     sec;
+        aligned_u64     usec;
+} __attribute__ ((packed));
+
+#define NFULNL_PREFIXLEN        30      /* just like old log target */
+
+enum nfulnl_attr_type {
+        NFULA_UNSPEC,
+        NFULA_PACKET_HDR,
+        NFULA_MARK,                     /* u_int32_t nfmark */
+        NFULA_TIMESTAMP,                /* nfulnl_msg_packet_timestamp */
+        NFULA_IFINDEX_INDEV,            /* u_int32_t ifindex */
+        NFULA_IFINDEX_OUTDEV,           /* u_int32_t ifindex */
+        NFULA_IFINDEX_PHYSINDEV,        /* u_int32_t ifindex */
+        NFULA_IFINDEX_PHYSOUTDEV,       /* u_int32_t ifindex */
+        NFULA_HWADDR,                   /* nfulnl_msg_packet_hw */
+        NFULA_PAYLOAD,                  /* opaque data payload */
+        NFULA_PREFIX,                   /* string prefix */
+        NFULA_UID,                      /* user id of socket */
+
+        __NFULA_MAX
+};
+#define NFULA_MAX (__NFULA_MAX - 1)
+
+enum nfulnl_msg_config_cmds {
+        NFULNL_CFG_CMD_NONE,
+        NFULNL_CFG_CMD_BIND,
+        NFULNL_CFG_CMD_UNBIND,
+        NFULNL_CFG_CMD_PF_BIND,
+        NFULNL_CFG_CMD_PF_UNBIND,
+};
+
+struct nfulnl_msg_config_cmd {
+        u_int8_t        command;        /* nfulnl_msg_config_cmds */
+} __attribute__ ((packed));
+
+struct nfulnl_msg_config_mode {
+        u_int32_t       copy_range;
+        u_int8_t        copy_mode;
+        u_int8_t        _pad;
+} __attribute__ ((packed));
+
+enum nfulnl_attr_config {
+        NFULA_CFG_UNSPEC,
+        NFULA_CFG_CMD,                  /* nfulnl_msg_config_cmd */
+        NFULA_CFG_MODE,                 /* nfulnl_msg_config_mode */
+        NFULA_CFG_NLBUFSIZ,             /* u_int32_t buffer size */
+        NFULA_CFG_TIMEOUT,              /* u_int32_t in 1/100 s */
+        NFULA_CFG_QTHRESH,              /* u_int32_t */
+        __NFULA_CFG_MAX
+};
+#define NFULA_CFG_MAX (__NFULA_CFG_MAX -1)
+
+#define NFULNL_COPY_NONE        0x00
+#define NFULNL_COPY_META        0x01
+#define NFULNL_COPY_PACKET      0x02
+
+#endif /* _NFNETLINK_LOG_H */
diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h
new file mode 100644
index 000000000000..9e774373244c
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink_queue.h
@@ -0,0 +1,89 @@
+#ifndef _NFNETLINK_QUEUE_H
+#define _NFNETLINK_QUEUE_H
+
+#include <linux/types.h>
+#include <linux/netfilter/nfnetlink.h>
+
+enum nfqnl_msg_types {
+        NFQNL_MSG_PACKET,               /* packet from kernel to userspace */
+        NFQNL_MSG_VERDICT,              /* verdict from userspace to kernel */
+        NFQNL_MSG_CONFIG,               /* connect to a particular queue */
+
+        NFQNL_MSG_MAX
+};
+
+struct nfqnl_msg_packet_hdr {
+        u_int32_t       packet_id;      /* unique ID of packet in queue */
+        u_int16_t       hw_protocol;    /* hw protocol (network order) */
+        u_int8_t        hook;           /* netfilter hook */
+} __attribute__ ((packed));
+
+struct nfqnl_msg_packet_hw {
+        u_int16_t       hw_addrlen;
+        u_int16_t       _pad;
+        u_int8_t        hw_addr[8];
+} __attribute__ ((packed));
+
+struct nfqnl_msg_packet_timestamp {
+        aligned_u64     sec;
+        aligned_u64     usec;
+} __attribute__ ((packed));
+
+enum nfqnl_attr_type {
+        NFQA_UNSPEC,
+        NFQA_PACKET_HDR,
+        NFQA_VERDICT_HDR,               /* nfqnl_msg_verdict_hrd */
+        NFQA_MARK,                      /* u_int32_t nfmark */
+        NFQA_TIMESTAMP,                 /* nfqnl_msg_packet_timestamp */
+        NFQA_IFINDEX_INDEV,             /* u_int32_t ifindex */
+        NFQA_IFINDEX_OUTDEV,            /* u_int32_t ifindex */
+        NFQA_IFINDEX_PHYSINDEV,         /* u_int32_t ifindex */
+        NFQA_IFINDEX_PHYSOUTDEV,        /* u_int32_t ifindex */
+        NFQA_HWADDR,                    /* nfqnl_msg_packet_hw */
+        NFQA_PAYLOAD,                   /* opaque data payload */
+
+        __NFQA_MAX
+};
+#define NFQA_MAX (__NFQA_MAX - 1)
+
+struct nfqnl_msg_verdict_hdr {
+        u_int32_t verdict;
+        u_int32_t id;
+} __attribute__ ((packed));
+
+
+enum nfqnl_msg_config_cmds {
+        NFQNL_CFG_CMD_NONE,
+        NFQNL_CFG_CMD_BIND,
+        NFQNL_CFG_CMD_UNBIND,
+        NFQNL_CFG_CMD_PF_BIND,
+        NFQNL_CFG_CMD_PF_UNBIND,
+};
+
+struct nfqnl_msg_config_cmd {
+        u_int8_t        command;        /* nfqnl_msg_config_cmds */
+        u_int8_t        _pad;
+        u_int16_t       pf;             /* AF_xxx for PF_[UN]BIND */
+} __attribute__ ((packed));
+
+enum nfqnl_config_mode {
+        NFQNL_COPY_NONE,
+        NFQNL_COPY_META,
+        NFQNL_COPY_PACKET,
+};
+
+struct nfqnl_msg_config_params {
+        u_int32_t       copy_range;
+        u_int8_t        copy_mode;      /* enum nfqnl_config_mode */
+} __attribute__ ((packed));
+
+
+enum nfqnl_attr_config {
+        NFQA_CFG_UNSPEC,
+        NFQA_CFG_CMD,                   /* nfqnl_msg_config_cmd */
+        NFQA_CFG_PARAMS,                /* nfqnl_msg_config_params */
+        __NFQA_CFG_MAX
+};
+#define NFQA_CFG_MAX (__NFQA_CFG_MAX-1)
+
+#endif /* _NFNETLINK_QUEUE_H */
diff --git a/include/linux/netfilter_decnet.h b/include/linux/netfilter_decnet.h
index 3064eec9cb8e..6f425369ee29 100644
--- a/include/linux/netfilter_decnet.h
+++ b/include/linux/netfilter_decnet.h
@@ -9,6 +9,8 @@
 
 #include <linux/netfilter.h>
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* IP Cache bits. */
 /* Src IP address. */
 #define NFC_DN_SRC              0x0001
@@ -18,6 +20,7 @@
 #define NFC_DN_IF_IN            0x0004
 /* Output device. */
 #define NFC_DN_IF_OUT           0x0008
+#endif /* ! __KERNEL__ */
 
 /* DECnet Hooks */
 /* After promisc drops, checksum checks. */
@@ -53,7 +56,21 @@ struct nf_dn_rtmsg {
 
 #define NFDN_RTMSG(r) ((unsigned char *)(r) + NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg)))
 
+#ifndef __KERNEL__
+/* backwards compatibility for userspace */
 #define DNRMG_L1_GROUP 0x01
 #define DNRMG_L2_GROUP 0x02
+#endif
+
+enum {
+        DNRNG_NLGRP_NONE,
+#define DNRNG_NLGRP_NONE        DNRNG_NLGRP_NONE
+        DNRNG_NLGRP_L1,
+#define DNRNG_NLGRP_L1          DNRNG_NLGRP_L1
+        DNRNG_NLGRP_L2,
+#define DNRNG_NLGRP_L2          DNRNG_NLGRP_L2
+        __DNRNG_NLGRP_MAX
+};
+#define DNRNG_NLGRP_MAX (__DNRNG_NLGRP_MAX - 1)
 
 #endif /*__LINUX_DECNET_NETFILTER_H*/
diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index 3ebc36afae1a..fdc4a9527343 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -8,6 +8,8 @@
 #include <linux/config.h>
 #include <linux/netfilter.h>
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* IP Cache bits. */
 /* Src IP address. */
 #define NFC_IP_SRC              0x0001
@@ -35,6 +37,7 @@
 #define NFC_IP_DST_PT           0x0400
 /* Something else about the proto */
 #define NFC_IP_PROTO_UNKNOWN    0x2000
+#endif /* ! __KERNEL__ */
 
 /* IP Hooks */
 /* After promisc drops, checksum checks. */
@@ -77,11 +80,6 @@ enum nf_ip_hook_priorities {
 #ifdef __KERNEL__
 extern int ip_route_me_harder(struct sk_buff **pskb);
 
-/* Call this before modifying an existing IP packet: ensures it is
-   modifiable and linear to the point you care about (writable_len).
-   Returns true or false. */
-extern int skb_ip_make_writable(struct sk_buff **pskb,
-                                unsigned int writable_len);
 #endif /*__KERNEL__*/
 
 #endif /*__LINUX_IP_NETFILTER_H*/
diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h
index 08fe5f7d14a0..088742befe49 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack.h
@@ -65,6 +65,63 @@ enum ip_conntrack_status {
 
         /* Both together */
         IPS_NAT_DONE_MASK = (IPS_DST_NAT_DONE | IPS_SRC_NAT_DONE),
+
+        /* Connection is dying (removed from lists), can not be unset. */
+        IPS_DYING_BIT = 9,
+        IPS_DYING = (1 << IPS_DYING_BIT),
+};
+
+/* Connection tracking event bits */
+enum ip_conntrack_events
+{
+        /* New conntrack */
+        IPCT_NEW_BIT = 0,
+        IPCT_NEW = (1 << IPCT_NEW_BIT),
+
+        /* Expected connection */
+        IPCT_RELATED_BIT = 1,
+        IPCT_RELATED = (1 << IPCT_RELATED_BIT),
+
+        /* Destroyed conntrack */
+        IPCT_DESTROY_BIT = 2,
+        IPCT_DESTROY = (1 << IPCT_DESTROY_BIT),
+
+        /* Timer has been refreshed */
+        IPCT_REFRESH_BIT = 3,
+        IPCT_REFRESH = (1 << IPCT_REFRESH_BIT),
+
+        /* Status has changed */
+        IPCT_STATUS_BIT = 4,
+        IPCT_STATUS = (1 << IPCT_STATUS_BIT),
+
+        /* Update of protocol info */
+        IPCT_PROTOINFO_BIT = 5,
+        IPCT_PROTOINFO = (1 << IPCT_PROTOINFO_BIT),
+
+        /* Volatile protocol info */
+        IPCT_PROTOINFO_VOLATILE_BIT = 6,
+        IPCT_PROTOINFO_VOLATILE = (1 << IPCT_PROTOINFO_VOLATILE_BIT),
+
+        /* New helper for conntrack */
+        IPCT_HELPER_BIT = 7,
+        IPCT_HELPER = (1 << IPCT_HELPER_BIT),
+
+        /* Update of helper info */
+        IPCT_HELPINFO_BIT = 8,
+        IPCT_HELPINFO = (1 << IPCT_HELPINFO_BIT),
+
+        /* Volatile helper info */
+        IPCT_HELPINFO_VOLATILE_BIT = 9,
+        IPCT_HELPINFO_VOLATILE = (1 << IPCT_HELPINFO_VOLATILE_BIT),
+
+        /* NAT info */
+        IPCT_NATINFO_BIT = 10,
+        IPCT_NATINFO = (1 << IPCT_NATINFO_BIT),
+};
+
+enum ip_conntrack_expect_events {
+        IPEXP_NEW_BIT = 0,
+        IPEXP_NEW = (1 << IPEXP_NEW_BIT),
 };
 
 #ifdef __KERNEL__
@@ -152,6 +209,9 @@ struct ip_conntrack
         /* Current number of expected connections */
         unsigned int expecting;
 
+        /* Unique ID that identifies this conntrack*/
+        unsigned int id;
+
         /* Helper, if any. */
         struct ip_conntrack_helper *helper;
 
@@ -171,7 +231,7 @@ struct ip_conntrack
 #endif /* CONFIG_IP_NF_NAT_NEEDED */
 
 #if defined(CONFIG_IP_NF_CONNTRACK_MARK)
-        unsigned long mark;
+        u_int32_t mark;
 #endif
 
         /* Traversed often, so hopefully in different cacheline to top */
@@ -200,6 +260,9 @@ struct ip_conntrack_expect
         /* Usage count. */
         atomic_t use;
 
+        /* Unique ID */
+        unsigned int id;
+
 #ifdef CONFIG_IP_NF_NAT_NEEDED
         /* This is the original per-proto part, used to map the
          * expected connection the way the recipient expects. */
@@ -239,7 +302,12 @@ ip_conntrack_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo)
 }
 
 /* decrement reference count on a conntrack */
-extern void ip_conntrack_put(struct ip_conntrack *ct);
+static inline void
+ip_conntrack_put(struct ip_conntrack *ct)
+{
+        IP_NF_ASSERT(ct);
+        nf_conntrack_put(&ct->ct_general);
+}
 
 /* call to create an explicit dependency on ip_conntrack. */
 extern void need_ip_conntrack(void);
@@ -274,12 +342,50 @@ extern void
 ip_ct_iterate_cleanup(int (*iter)(struct ip_conntrack *i, void *data),
                       void *data);
 
+extern struct ip_conntrack_helper *
+__ip_conntrack_helper_find_byname(const char *);
+extern struct ip_conntrack_helper *
+ip_conntrack_helper_find_get(const struct ip_conntrack_tuple *tuple);
+extern void ip_conntrack_helper_put(struct ip_conntrack_helper *helper);
+
+extern struct ip_conntrack_protocol *
+__ip_conntrack_proto_find(u_int8_t protocol);
+extern struct ip_conntrack_protocol *
+ip_conntrack_proto_find_get(u_int8_t protocol);
+extern void ip_conntrack_proto_put(struct ip_conntrack_protocol *proto);
+
+extern void ip_ct_remove_expectations(struct ip_conntrack *ct);
+
+extern struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *,
+                                               struct ip_conntrack_tuple *);
+
+extern void ip_conntrack_free(struct ip_conntrack *ct);
+
+extern void ip_conntrack_hash_insert(struct ip_conntrack *ct);
+
+extern struct ip_conntrack_expect *
+__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple);
+
+extern struct ip_conntrack_expect *
+ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple);
+
+extern struct ip_conntrack_tuple_hash *
+__ip_conntrack_find(const struct ip_conntrack_tuple *tuple,
+                    const struct ip_conntrack *ignored_conntrack);
+
+extern void ip_conntrack_flush(void);
+
 /* It's confirmed if it is, or has been in the hash table. */
 static inline int is_confirmed(struct ip_conntrack *ct)
 {
         return test_bit(IPS_CONFIRMED_BIT, &ct->status);
 }
 
+static inline int is_dying(struct ip_conntrack *ct)
+{
+        return test_bit(IPS_DYING_BIT, &ct->status);
+}
+
 extern unsigned int ip_conntrack_htable_size;
  
 struct ip_conntrack_stat
@@ -303,6 +409,85 @@ struct ip_conntrack_stat
 
 #define CONNTRACK_STAT_INC(count) (__get_cpu_var(ip_conntrack_stat).count++)
 
+#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
+#include <linux/notifier.h>
+#include <linux/interrupt.h>
+
+struct ip_conntrack_ecache {
+        struct ip_conntrack *ct;
+        unsigned int events;
+};
+DECLARE_PER_CPU(struct ip_conntrack_ecache, ip_conntrack_ecache);
+
+#define CONNTRACK_ECACHE(x)     (__get_cpu_var(ip_conntrack_ecache).x)
+ 
+extern struct notifier_block *ip_conntrack_chain;
+extern struct notifier_block *ip_conntrack_expect_chain;
+
+static inline int ip_conntrack_register_notifier(struct notifier_block *nb)
+{
+        return notifier_chain_register(&ip_conntrack_chain, nb);
+}
+
+static inline int ip_conntrack_unregister_notifier(struct notifier_block *nb)
+{
+        return notifier_chain_unregister(&ip_conntrack_chain, nb);
+}
+
+static inline int 
+ip_conntrack_expect_register_notifier(struct notifier_block *nb)
+{
+        return notifier_chain_register(&ip_conntrack_expect_chain, nb);
+}
+
+static inline int
+ip_conntrack_expect_unregister_notifier(struct notifier_block *nb)
+{
+        return notifier_chain_unregister(&ip_conntrack_expect_chain, nb);
+}
+
+extern void ip_ct_deliver_cached_events(const struct ip_conntrack *ct);
+extern void __ip_ct_event_cache_init(struct ip_conntrack *ct);
+
+static inline void 
+ip_conntrack_event_cache(enum ip_conntrack_events event,
+                         const struct sk_buff *skb)
+{
+        struct ip_conntrack *ct = (struct ip_conntrack *)skb->nfct;
+        struct ip_conntrack_ecache *ecache;
+        
+        local_bh_disable();
+        ecache = &__get_cpu_var(ip_conntrack_ecache);
+        if (ct != ecache->ct)
+                __ip_ct_event_cache_init(ct);
+        ecache->events |= event;
+        local_bh_enable();
+}
+
+static inline void ip_conntrack_event(enum ip_conntrack_events event,
+                                      struct ip_conntrack *ct)
+{
+        if (is_confirmed(ct) && !is_dying(ct))
+                notifier_call_chain(&ip_conntrack_chain, event, ct);
+}
+
+static inline void 
+ip_conntrack_expect_event(enum ip_conntrack_expect_events event,
+                          struct ip_conntrack_expect *exp)
+{
+        notifier_call_chain(&ip_conntrack_expect_chain, event, exp);
+}
+#else /* CONFIG_IP_NF_CONNTRACK_EVENTS */
+static inline void ip_conntrack_event_cache(enum ip_conntrack_events event, 
+                                            const struct sk_buff *skb) {}
+static inline void ip_conntrack_event(enum ip_conntrack_events event, 
+                                      struct ip_conntrack *ct) {}
+static inline void ip_ct_deliver_cached_events(const struct ip_conntrack *ct) {}
+static inline void 
+ip_conntrack_expect_event(enum ip_conntrack_expect_events event, 
+                          struct ip_conntrack_expect *exp) {}
+#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */
+
 #ifdef CONFIG_IP_NF_NAT_NEEDED
 static inline int ip_nat_initialized(struct ip_conntrack *conntrack,
                                      enum ip_nat_manip_type manip)
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h
index 694aec9b4784..dc4d2a0575de 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_core.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h
@@ -2,6 +2,9 @@
 #define _IP_CONNTRACK_CORE_H
 #include <linux/netfilter.h>
 
+#define MAX_IP_CT_PROTO 256
+extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO];
+
 /* This header is used to share core functionality between the
    standalone connection tracking module, and the compatibility layer's use
    of connection tracking. */
@@ -38,12 +41,19 @@ extern int __ip_conntrack_confirm(struct sk_buff **pskb);
 /* Confirm a connection: returns NF_DROP if packet must be dropped. */
 static inline int ip_conntrack_confirm(struct sk_buff **pskb)
 {
-        if ((*pskb)->nfct
-            && !is_confirmed((struct ip_conntrack *)(*pskb)->nfct))
-                return __ip_conntrack_confirm(pskb);
-        return NF_ACCEPT;
+        struct ip_conntrack *ct = (struct ip_conntrack *)(*pskb)->nfct;
+        int ret = NF_ACCEPT;
+
+        if (ct) {
+                if (!is_confirmed(ct))
+                        ret = __ip_conntrack_confirm(pskb);
+                ip_ct_deliver_cached_events(ct);
+        }
+        return ret;
 }
 
+extern void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp);
+
 extern struct list_head *ip_conntrack_hash;
 extern struct list_head ip_conntrack_expect_list;
 extern rwlock_t ip_conntrack_lock;
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_helper.h b/include/linux/netfilter_ipv4/ip_conntrack_helper.h
index 3692daa93dec..8d69279ccfe4 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_helper.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_helper.h
@@ -24,6 +24,8 @@ struct ip_conntrack_helper
         int (*help)(struct sk_buff **pskb,
                     struct ip_conntrack *ct,
                     enum ip_conntrack_info conntrackinfo);
+
+        int (*to_nfattr)(struct sk_buff *skb, const struct ip_conntrack *ct);
 };
 
 extern int ip_conntrack_helper_register(struct ip_conntrack_helper *);
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h
index e20b57c5e1b7..b6b99be8632a 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h
@@ -2,6 +2,7 @@
 #ifndef _IP_CONNTRACK_PROTOCOL_H
 #define _IP_CONNTRACK_PROTOCOL_H
 #include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
 
 struct seq_file;
 
@@ -47,22 +48,22 @@ struct ip_conntrack_protocol
         int (*error)(struct sk_buff *skb, enum ip_conntrack_info *ctinfo,
                      unsigned int hooknum);
 
+        /* convert protoinfo to nfnetink attributes */
+        int (*to_nfattr)(struct sk_buff *skb, struct nfattr *nfa,
+                         const struct ip_conntrack *ct);
+
+        int (*tuple_to_nfattr)(struct sk_buff *skb,
+                               const struct ip_conntrack_tuple *t);
+        int (*nfattr_to_tuple)(struct nfattr *tb[],
+                               struct ip_conntrack_tuple *t);
+
         /* Module (if any) which this is connected to. */
         struct module *me;
 };
 
-#define MAX_IP_CT_PROTO 256
-extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO];
-
 /* Protocol registration. */
 extern int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto);
 extern void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto);
-
-static inline struct ip_conntrack_protocol *ip_ct_find_proto(u_int8_t protocol)
-{
-        return ip_ct_protos[protocol];
-}
-
 /* Existing built-in protocols */
 extern struct ip_conntrack_protocol ip_conntrack_protocol_tcp;
 extern struct ip_conntrack_protocol ip_conntrack_protocol_udp;
@@ -73,6 +74,11 @@ extern int ip_conntrack_protocol_tcp_init(void);
 /* Log invalid packets */
 extern unsigned int ip_ct_log_invalid;
 
+extern int ip_ct_port_tuple_to_nfattr(struct sk_buff *,
+                                      const struct ip_conntrack_tuple *);
+extern int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[],
+                                      struct ip_conntrack_tuple *);
+
 #ifdef CONFIG_SYSCTL
 #ifdef DEBUG_INVALID_PACKETS
 #define LOG_INVALID(proto) \
diff --git a/include/linux/netfilter_ipv4/ip_logging.h b/include/linux/netfilter_ipv4/ip_logging.h
deleted file mode 100644
index 0c5c52cb6589..000000000000
--- a/include/linux/netfilter_ipv4/ip_logging.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* IPv4 macros for the internal logging interface. */
-#ifndef __IP_LOGGING_H
-#define __IP_LOGGING_H
-
-#ifdef __KERNEL__
-#include <linux/socket.h>
-#include <linux/netfilter_logging.h>
-
-#define nf_log_ip_packet(pskb,hooknum,in,out,fmt,args...) \
-        nf_log_packet(AF_INET,pskb,hooknum,in,out,fmt,##args)
-
-#define nf_log_ip(pfh,len,fmt,args...) \
-        nf_log(AF_INET,pfh,len,fmt,##args)
-
-#define nf_ip_log_register(logging) nf_log_register(AF_INET,logging)
-#define nf_ip_log_unregister(logging) nf_log_unregister(AF_INET,logging)
-        
-#endif /*__KERNEL__*/
-
-#endif /*__IP_LOGGING_H*/
diff --git a/include/linux/netfilter_ipv4/ip_nat_protocol.h b/include/linux/netfilter_ipv4/ip_nat_protocol.h
index 129708c22386..ef63aa991a06 100644
--- a/include/linux/netfilter_ipv4/ip_nat_protocol.h
+++ b/include/linux/netfilter_ipv4/ip_nat_protocol.h
@@ -4,6 +4,9 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <linux/netfilter_ipv4/ip_nat.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+
 struct iphdr;
 struct ip_nat_range;
 
@@ -15,6 +18,8 @@ struct ip_nat_protocol
         /* Protocol number. */
         unsigned int protonum;
 
+        struct module *me;
+
         /* Translate a packet to the target according to manip type.
            Return true if succeeded. */
         int (*manip_pkt)(struct sk_buff **pskb,
@@ -43,19 +48,20 @@ struct ip_nat_protocol
 
         unsigned int (*print_range)(char *buffer,
                                     const struct ip_nat_range *range);
-};
 
-#define MAX_IP_NAT_PROTO 256
-extern struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO];
+        int (*range_to_nfattr)(struct sk_buff *skb,
+                               const struct ip_nat_range *range);
+
+        int (*nfattr_to_range)(struct nfattr *tb[],
+                               struct ip_nat_range *range);
+};
 
 /* Protocol registration. */
 extern int ip_nat_protocol_register(struct ip_nat_protocol *proto);
 extern void ip_nat_protocol_unregister(struct ip_nat_protocol *proto);
 
-static inline struct ip_nat_protocol *ip_nat_find_proto(u_int8_t protocol)
-{
-        return ip_nat_protos[protocol];
-}
+extern struct ip_nat_protocol *ip_nat_proto_find_get(u_int8_t protocol);
+extern void ip_nat_proto_put(struct ip_nat_protocol *proto);
 
 /* Built-in protocols. */
 extern struct ip_nat_protocol ip_nat_protocol_tcp;
@@ -67,4 +73,9 @@ extern int init_protocols(void) __init;
 extern void cleanup_protocols(void);
 extern struct ip_nat_protocol *find_nat_proto(u_int16_t protonum);
 
+extern int ip_nat_port_range_to_nfattr(struct sk_buff *skb,
+                                       const struct ip_nat_range *range);
+extern int ip_nat_port_nfattr_to_range(struct nfattr *tb[],
+                                       struct ip_nat_range *range);
+
 #endif /*_IP_NAT_PROTO_H*/
diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h
index 12ce47808e7d..d19d65cf4530 100644
--- a/include/linux/netfilter_ipv4/ip_tables.h
+++ b/include/linux/netfilter_ipv4/ip_tables.h
@@ -109,7 +109,8 @@ struct ipt_counters
 
 /* Values for "flag" field in struct ipt_ip (general ip structure). */
 #define IPT_F_FRAG              0x01    /* Set if rule is a fragment rule */
-#define IPT_F_MASK              0x01    /* All possible flag bits mask. */
+#define IPT_F_GOTO              0x02    /* Set if jump is a goto */
+#define IPT_F_MASK              0x03    /* All possible flag bits mask. */
 
 /* Values for "inv" field in struct ipt_ip. */
 #define IPT_INV_VIA_IN          0x01    /* Invert the sense of IN IFACE. */
diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h
index d25f782e57d1..22d16177319b 100644
--- a/include/linux/netfilter_ipv4/ipt_LOG.h
+++ b/include/linux/netfilter_ipv4/ipt_LOG.h
@@ -1,6 +1,7 @@
 #ifndef _IPT_LOG_H
 #define _IPT_LOG_H
 
+/* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */
 #define IPT_LOG_TCPSEQ          0x01    /* Log TCP sequence numbers */
 #define IPT_LOG_TCPOPT          0x02    /* Log TCP options */
 #define IPT_LOG_IPOPT           0x04    /* Log IP options */
diff --git a/include/linux/netfilter_ipv4/ipt_NFQUEUE.h b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h
new file mode 100644
index 000000000000..b5b2943b0c66
--- /dev/null
+++ b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h
@@ -0,0 +1,16 @@
+/* iptables module for using NFQUEUE mechanism
+ *
+ * (C) 2005 Harald Welte <laforge@netfilter.org>
+ *
+ * This software is distributed under GNU GPL v2, 1991
+ * 
+*/
+#ifndef _IPT_NFQ_TARGET_H
+#define _IPT_NFQ_TARGET_H
+
+/* target info */
+struct ipt_NFQ_info {
+        u_int16_t queuenum;
+};
+
+#endif /* _IPT_DSCP_TARGET_H */
diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h
new file mode 100644
index 000000000000..ee6611edc112
--- /dev/null
+++ b/include/linux/netfilter_ipv4/ipt_TTL.h
@@ -0,0 +1,21 @@
+/* TTL modification module for IP tables
+ * (C) 2000 by Harald Welte <laforge@netfilter.org> */
+
+#ifndef _IPT_TTL_H
+#define _IPT_TTL_H
+
+enum {
+        IPT_TTL_SET = 0,
+        IPT_TTL_INC,
+        IPT_TTL_DEC
+};
+
+#define IPT_TTL_MAXMODE IPT_TTL_DEC
+
+struct ipt_TTL_info {
+        u_int8_t        mode;
+        u_int8_t        ttl;
+};
+
+
+#endif
diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h
new file mode 100644
index 000000000000..9e5532f8d8ac
--- /dev/null
+++ b/include/linux/netfilter_ipv4/ipt_connbytes.h
@@ -0,0 +1,25 @@
+#ifndef _IPT_CONNBYTES_H
+#define _IPT_CONNBYTES_H
+
+enum ipt_connbytes_what {
+        IPT_CONNBYTES_PKTS,
+        IPT_CONNBYTES_BYTES,
+        IPT_CONNBYTES_AVGPKT,
+};
+
+enum ipt_connbytes_direction {
+        IPT_CONNBYTES_DIR_ORIGINAL,
+        IPT_CONNBYTES_DIR_REPLY,
+        IPT_CONNBYTES_DIR_BOTH,
+};
+
+struct ipt_connbytes_info
+{
+        struct {
+                aligned_u64 from;       /* count to be matched */
+                aligned_u64 to;         /* count to be matched */
+        } count;
+        u_int8_t what;          /* ipt_connbytes_what */
+        u_int8_t direction;     /* ipt_connbytes_direction */
+};
+#endif
diff --git a/include/linux/netfilter_ipv4/ipt_dccp.h b/include/linux/netfilter_ipv4/ipt_dccp.h
new file mode 100644
index 000000000000..3cb3a522e62b
--- /dev/null
+++ b/include/linux/netfilter_ipv4/ipt_dccp.h
@@ -0,0 +1,23 @@
+#ifndef _IPT_DCCP_H_
+#define _IPT_DCCP_H_
+
+#define IPT_DCCP_SRC_PORTS              0x01
+#define IPT_DCCP_DEST_PORTS             0x02
+#define IPT_DCCP_TYPE                   0x04
+#define IPT_DCCP_OPTION                 0x08
+
+#define IPT_DCCP_VALID_FLAGS            0x0f
+
+struct ipt_dccp_info {
+        u_int16_t dpts[2];  /* Min, Max */
+        u_int16_t spts[2];  /* Min, Max */
+
+        u_int16_t flags;
+        u_int16_t invflags;
+
+        u_int16_t typemask;
+        u_int8_t option;
+};
+
+#endif /* _IPT_DCCP_H_ */
+
diff --git a/include/linux/netfilter_ipv4/ipt_string.h b/include/linux/netfilter_ipv4/ipt_string.h
new file mode 100644
index 000000000000..a265f6e44eab
--- /dev/null
+++ b/include/linux/netfilter_ipv4/ipt_string.h
@@ -0,0 +1,18 @@
+#ifndef _IPT_STRING_H
+#define _IPT_STRING_H
+
+#define IPT_STRING_MAX_PATTERN_SIZE 128
+#define IPT_STRING_MAX_ALGO_NAME_SIZE 16
+
+struct ipt_string_info
+{
+        u_int16_t from_offset;
+        u_int16_t to_offset;
+        char      algo[IPT_STRING_MAX_ALGO_NAME_SIZE];
+        char      pattern[IPT_STRING_MAX_PATTERN_SIZE];
+        u_int8_t  patlen;
+        u_int8_t  invert;
+        struct ts_config __attribute__((aligned(8))) *config;
+};
+
+#endif /*_IPT_STRING_H*/
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index bee7a5ec7c66..edcc2c6eb5c7 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -10,6 +10,8 @@
 
 #include <linux/netfilter.h>
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* IP Cache bits. */
 /* Src IP address. */
 #define NFC_IP6_SRC              0x0001
@@ -38,6 +40,7 @@
 #define NFC_IP6_DST_PT           0x0400
 /* Something else about the proto */
 #define NFC_IP6_PROTO_UNKNOWN    0x2000
+#endif /* ! __KERNEL__ */
 
 
 /* IP6 Hooks */
@@ -68,4 +71,7 @@ enum nf_ip6_hook_priorities {
         NF_IP6_PRI_LAST = INT_MAX,
 };
 
+extern int ipv6_netfilter_init(void);
+extern void ipv6_netfilter_fini(void);
+
 #endif /*__LINUX_IP6_NETFILTER_H*/
diff --git a/include/linux/netfilter_ipv6/ip6_logging.h b/include/linux/netfilter_ipv6/ip6_logging.h
deleted file mode 100644
index a0b2ee3043aa..000000000000
--- a/include/linux/netfilter_ipv6/ip6_logging.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* IPv6 macros for the nternal logging interface. */
-#ifndef __IP6_LOGGING_H
-#define __IP6_LOGGING_H
-
-#ifdef __KERNEL__
-#include <linux/socket.h>
-#include <linux/netfilter_logging.h>
-
-#define nf_log_ip6_packet(pskb,hooknum,in,out,fmt,args...) \
-        nf_log_packet(AF_INET6,pskb,hooknum,in,out,fmt,##args)
-
-#define nf_log_ip6(pfh,len,fmt,args...) \
-        nf_log(AF_INET6,pfh,len,fmt,##args)
-
-#define nf_ip6_log_register(logging) nf_log_register(AF_INET6,logging)
-#define nf_ip6_log_unregister(logging) nf_log_unregister(AF_INET6,logging)
-        
-#endif /*__KERNEL__*/
-
-#endif /*__IP6_LOGGING_H*/
diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index f1ce3b009853..58c72a52dc65 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -111,7 +111,8 @@ struct ip6t_counters
 #define IP6T_F_PROTO            0x01    /* Set if rule cares about upper 
                                            protocols */
 #define IP6T_F_TOS              0x02    /* Match the TOS. */
-#define IP6T_F_MASK             0x03    /* All possible flag bits mask. */
+#define IP6T_F_GOTO             0x04    /* Set if jump is a goto */
+#define IP6T_F_MASK             0x07    /* All possible flag bits mask. */
 
 /* Values for "inv" field in struct ip6t_ip6. */
 #define IP6T_INV_VIA_IN         0x01    /* Invert the sense of IN IFACE. */
diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h
new file mode 100644
index 000000000000..afb7813d45ab
--- /dev/null
+++ b/include/linux/netfilter_ipv6/ip6t_HL.h
@@ -0,0 +1,22 @@
+/* Hop Limit modification module for ip6tables
+ * Maciej Soltysiak <solt@dns.toxicfilms.tv>
+ * Based on HW's TTL module */
+
+#ifndef _IP6T_HL_H
+#define _IP6T_HL_H
+
+enum {
+        IP6T_HL_SET = 0,
+        IP6T_HL_INC,
+        IP6T_HL_DEC
+};
+
+#define IP6T_HL_MAXMODE IP6T_HL_DEC
+
+struct ip6t_HL_info {
+        u_int8_t        mode;
+        u_int8_t        hop_limit;
+};
+
+
+#endif
diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h
index 42996a43bb39..9008ff5c40ae 100644
--- a/include/linux/netfilter_ipv6/ip6t_LOG.h
+++ b/include/linux/netfilter_ipv6/ip6t_LOG.h
@@ -1,6 +1,7 @@
 #ifndef _IP6T_LOG_H
 #define _IP6T_LOG_H
 
+/* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */
 #define IP6T_LOG_TCPSEQ         0x01    /* Log TCP sequence numbers */
 #define IP6T_LOG_TCPOPT         0x02    /* Log TCP options */
 #define IP6T_LOG_IPOPT          0x04    /* Log IP options */
diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h
new file mode 100644
index 000000000000..6be6504162bb
--- /dev/null
+++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h
@@ -0,0 +1,18 @@
+#ifndef _IP6T_REJECT_H
+#define _IP6T_REJECT_H
+
+enum ip6t_reject_with {
+        IP6T_ICMP6_NO_ROUTE,
+        IP6T_ICMP6_ADM_PROHIBITED,
+        IP6T_ICMP6_NOT_NEIGHBOUR,
+        IP6T_ICMP6_ADDR_UNREACH,
+        IP6T_ICMP6_PORT_UNREACH,
+        IP6T_ICMP6_ECHOREPLY,
+        IP6T_TCP_RESET
+};
+
+struct ip6t_reject_info {
+        u_int32_t       with;   /* reject type */
+};
+
+#endif /*_IP6T_REJECT_H*/
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 6552b71bfa73..167518668936 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -8,7 +8,7 @@
 #define NETLINK_W1              1       /* 1-wire subsystem                             */
 #define NETLINK_USERSOCK        2       /* Reserved for user mode socket protocols      */
 #define NETLINK_FIREWALL        3       /* Firewalling hook                             */
-#define NETLINK_TCPDIAG         4       /* TCP socket monitoring                        */
+#define NETLINK_INET_DIAG       4       /* INET socket monitoring                       */
 #define NETLINK_NFLOG           5       /* netfilter/iptables ULOG */
 #define NETLINK_XFRM            6       /* ipsec */
 #define NETLINK_SELINUX         7       /* SELinux event notifications */
@@ -90,6 +90,15 @@ struct nlmsgerr
         struct nlmsghdr msg;
 };
 
+#define NETLINK_ADD_MEMBERSHIP  1
+#define NETLINK_DROP_MEMBERSHIP 2
+#define NETLINK_PKTINFO         3
+
+struct nl_pktinfo
+{
+        __u32   group;
+};
+
 #define NET_MAJOR 36            /* Major 36 is reserved for networking                                          */
 
 enum {
@@ -106,9 +115,8 @@ struct netlink_skb_parms
 {
         struct ucred            creds;          /* Skb credentials      */
         __u32                   pid;
-        __u32                   groups;
         __u32                   dst_pid;
-        __u32                   dst_groups;
+        __u32                   dst_group;
         kernel_cap_t            eff_cap;
         __u32                   loginuid;       /* Login (audit) uid */
 };
@@ -117,11 +125,11 @@ struct netlink_skb_parms
 #define NETLINK_CREDS(skb)      (&NETLINK_CB((skb)).creds)
 
 
-extern struct sock *netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len));
+extern struct sock *netlink_kernel_create(int unit, unsigned int groups, void (*input)(struct sock *sk, int len), struct module *module);
 extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);
 extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid,
-                             __u32 group, int allocation);
+                             __u32 group, unsigned int __nocast allocation);
 extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code);
 extern int netlink_register_notifier(struct notifier_block *nb);
 extern int netlink_unregister_notifier(struct notifier_block *nb);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 927ed487630d..499a5325f67f 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1249,6 +1249,7 @@
 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA  0x0266
 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA2 0x0267
 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_IDE   0x036E
+#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA  0x036F
 #define PCI_DEVICE_ID_NVIDIA_NVENET_12          0x0268
 #define PCI_DEVICE_ID_NVIDIA_NVENET_13          0x0269
 #define PCI_DEVICE_ID_NVIDIA_MCP51_AUDIO        0x026B
diff --git a/include/linux/phy.h b/include/linux/phy.h
new file mode 100644
index 000000000000..72cb67b66e0c
--- /dev/null
+++ b/include/linux/phy.h
@@ -0,0 +1,377 @@
+/*
+ * include/linux/phy.h
+ *
+ * Framework and drivers for configuring and reading different PHYs
+ * Based on code in sungem_phy.c and gianfar_phy.c
+ *
+ * Author: Andy Fleming
+ *
+ * Copyright (c) 2004 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+#ifndef __PHY_H
+#define __PHY_H
+
+#include <linux/spinlock.h>
+#include <linux/device.h>
+
+#define PHY_BASIC_FEATURES      (SUPPORTED_10baseT_Half | \
+                                 SUPPORTED_10baseT_Full | \
+                                 SUPPORTED_100baseT_Half | \
+                                 SUPPORTED_100baseT_Full | \
+                                 SUPPORTED_Autoneg | \
+                                 SUPPORTED_TP | \
+                                 SUPPORTED_MII)
+
+#define PHY_GBIT_FEATURES       (PHY_BASIC_FEATURES | \
+                                 SUPPORTED_1000baseT_Half | \
+                                 SUPPORTED_1000baseT_Full)
+
+/* Set phydev->irq to PHY_POLL if interrupts are not supported,
+ * or not desired for this PHY.  Set to PHY_IGNORE_INTERRUPT if
+ * the attached driver handles the interrupt
+ */
+#define PHY_POLL                -1
+#define PHY_IGNORE_INTERRUPT    -2
+
+#define PHY_HAS_INTERRUPT       0x00000001
+#define PHY_HAS_MAGICANEG       0x00000002
+
+#define MII_BUS_MAX 4
+
+
+#define PHY_INIT_TIMEOUT 100000
+#define PHY_STATE_TIME          1
+#define PHY_FORCE_TIMEOUT       10
+#define PHY_AN_TIMEOUT          10
+
+#define PHY_MAX_ADDR 32
+
+/* The Bus class for PHYs.  Devices which provide access to
+ * PHYs should register using this structure */
+struct mii_bus {
+        const char *name;
+        int id;
+        void *priv;
+        int (*read)(struct mii_bus *bus, int phy_id, int regnum);
+        int (*write)(struct mii_bus *bus, int phy_id, int regnum, u16 val);
+        int (*reset)(struct mii_bus *bus);
+
+        /* A lock to ensure that only one thing can read/write
+         * the MDIO bus at a time */
+        spinlock_t mdio_lock;
+
+        struct device *dev;
+
+        /* list of all PHYs on bus */
+        struct phy_device *phy_map[PHY_MAX_ADDR];
+
+        /* Pointer to an array of interrupts, each PHY's
+         * interrupt at the index matching its address */
+        int *irq;
+};
+
+#define PHY_INTERRUPT_DISABLED 0x0
+#define PHY_INTERRUPT_ENABLED 0x80000000
+
+/* PHY state machine states:
+ *
+ * DOWN: PHY device and driver are not ready for anything.  probe
+ * should be called if and only if the PHY is in this state,
+ * given that the PHY device exists.
+ * - PHY driver probe function will, depending on the PHY, set
+ * the state to STARTING or READY
+ *
+ * STARTING:  PHY device is coming up, and the ethernet driver is
+ * not ready.  PHY drivers may set this in the probe function.
+ * If they do, they are responsible for making sure the state is
+ * eventually set to indicate whether the PHY is UP or READY,
+ * depending on the state when the PHY is done starting up.
+ * - PHY driver will set the state to READY
+ * - start will set the state to PENDING
+ *
+ * READY: PHY is ready to send and receive packets, but the
+ * controller is not.  By default, PHYs which do not implement
+ * probe will be set to this state by phy_probe().  If the PHY
+ * driver knows the PHY is ready, and the PHY state is STARTING,
+ * then it sets this STATE.
+ * - start will set the state to UP
+ *
+ * PENDING: PHY device is coming up, but the ethernet driver is
+ * ready.  phy_start will set this state if the PHY state is
+ * STARTING.
+ * - PHY driver will set the state to UP when the PHY is ready
+ *
+ * UP: The PHY and attached device are ready to do work.
+ * Interrupts should be started here.
+ * - timer moves to AN
+ *
+ * AN: The PHY is currently negotiating the link state.  Link is
+ * therefore down for now.  phy_timer will set this state when it
+ * detects the state is UP.  config_aneg will set this state
+ * whenever called with phydev->autoneg set to AUTONEG_ENABLE.
+ * - If autonegotiation finishes, but there's no link, it sets
+ *   the state to NOLINK.
+ * - If aneg finishes with link, it sets the state to RUNNING,
+ *   and calls adjust_link
+ * - If autonegotiation did not finish after an arbitrary amount
+ *   of time, autonegotiation should be tried again if the PHY
+ *   supports "magic" autonegotiation (back to AN)
+ * - If it didn't finish, and no magic_aneg, move to FORCING.
+ *
+ * NOLINK: PHY is up, but not currently plugged in.
+ * - If the timer notes that the link comes back, we move to RUNNING
+ * - config_aneg moves to AN
+ * - phy_stop moves to HALTED
+ *
+ * FORCING: PHY is being configured with forced settings
+ * - if link is up, move to RUNNING
+ * - If link is down, we drop to the next highest setting, and
+ *   retry (FORCING) after a timeout
+ * - phy_stop moves to HALTED
+ *
+ * RUNNING: PHY is currently up, running, and possibly sending
+ * and/or receiving packets
+ * - timer will set CHANGELINK if we're polling (this ensures the
+ *   link state is polled every other cycle of this state machine,
+ *   which makes it every other second)
+ * - irq will set CHANGELINK
+ * - config_aneg will set AN
+ * - phy_stop moves to HALTED
+ *
+ * CHANGELINK: PHY experienced a change in link state
+ * - timer moves to RUNNING if link
+ * - timer moves to NOLINK if the link is down
+ * - phy_stop moves to HALTED
+ *
+ * HALTED: PHY is up, but no polling or interrupts are done. Or
+ * PHY is in an error state.
+ *
+ * - phy_start moves to RESUMING
+ *
+ * RESUMING: PHY was halted, but now wants to run again.
+ * - If we are forcing, or aneg is done, timer moves to RUNNING
+ * - If aneg is not done, timer moves to AN
+ * - phy_stop moves to HALTED
+ */
+enum phy_state {
+        PHY_DOWN=0,
+        PHY_STARTING,
+        PHY_READY,
+        PHY_PENDING,
+        PHY_UP,
+        PHY_AN,
+        PHY_RUNNING,
+        PHY_NOLINK,
+        PHY_FORCING,
+        PHY_CHANGELINK,
+        PHY_HALTED,
+        PHY_RESUMING
+};
+
+/* phy_device: An instance of a PHY
+ *
+ * drv: Pointer to the driver for this PHY instance
+ * bus: Pointer to the bus this PHY is on
+ * dev: driver model device structure for this PHY
+ * phy_id: UID for this device found during discovery
+ * state: state of the PHY for management purposes
+ * dev_flags: Device-specific flags used by the PHY driver.
+ * addr: Bus address of PHY
+ * link_timeout: The number of timer firings to wait before the
+ * giving up on the current attempt at acquiring a link
+ * irq: IRQ number of the PHY's interrupt (-1 if none)
+ * phy_timer: The timer for handling the state machine
+ * phy_queue: A work_queue for the interrupt
+ * attached_dev: The attached enet driver's device instance ptr
+ * adjust_link: Callback for the enet controller to respond to
+ * changes in the link state.
+ * adjust_state: Callback for the enet driver to respond to
+ * changes in the state machine.
+ *
+ * speed, duplex, pause, supported, advertising, and
+ * autoneg are used like in mii_if_info
+ *
+ * interrupts currently only supports enabled or disabled,
+ * but could be changed in the future to support enabling
+ * and disabling specific interrupts
+ *
+ * Contains some infrastructure for polling and interrupt
+ * handling, as well as handling shifts in PHY hardware state
+ */
+struct phy_device {
+        /* Information about the PHY type */
+        /* And management functions */
+        struct phy_driver *drv;
+
+        struct mii_bus *bus;
+
+        struct device dev;
+
+        u32 phy_id;
+
+        enum phy_state state;
+
+        u32 dev_flags;
+
+        /* Bus address of the PHY (0-32) */
+        int addr;
+
+        /* forced speed & duplex (no autoneg)
+         * partner speed & duplex & pause (autoneg)
+         */
+        int speed;
+        int duplex;
+        int pause;
+        int asym_pause;
+
+        /* The most recently read link state */
+        int link;
+
+        /* Enabled Interrupts */
+        u32 interrupts;
+
+        /* Union of PHY and Attached devices' supported modes */
+        /* See mii.h for more info */
+        u32 supported;
+        u32 advertising;
+
+        int autoneg;
+
+        int link_timeout;
+
+        /* Interrupt number for this PHY
+         * -1 means no interrupt */
+        int irq;
+
+        /* private data pointer */
+        /* For use by PHYs to maintain extra state */
+        void *priv;
+
+        /* Interrupt and Polling infrastructure */
+        struct work_struct phy_queue;
+        struct timer_list phy_timer;
+
+        spinlock_t lock;
+
+        struct net_device *attached_dev;
+
+        void (*adjust_link)(struct net_device *dev);
+
+        void (*adjust_state)(struct net_device *dev);
+};
+#define to_phy_device(d) container_of(d, struct phy_device, dev)
+
+/* struct phy_driver: Driver structure for a particular PHY type
+ *
+ * phy_id: The result of reading the UID registers of this PHY
+ *   type, and ANDing them with the phy_id_mask.  This driver
+ *   only works for PHYs with IDs which match this field
+ * name: The friendly name of this PHY type
+ * phy_id_mask: Defines the important bits of the phy_id
+ * features: A list of features (speed, duplex, etc) supported
+ *   by this PHY
+ * flags: A bitfield defining certain other features this PHY
+ *   supports (like interrupts)
+ *
+ * The drivers must implement config_aneg and read_status.  All
+ * other functions are optional. Note that none of these
+ * functions should be called from interrupt time.  The goal is
+ * for the bus read/write functions to be able to block when the
+ * bus transaction is happening, and be freed up by an interrupt
+ * (The MPC85xx has this ability, though it is not currently
+ * supported in the driver).
+ */
+struct phy_driver {
+        u32 phy_id;
+        char *name;
+        unsigned int phy_id_mask;
+        u32 features;
+        u32 flags;
+
+        /* Called to initialize the PHY,
+         * including after a reset */
+        int (*config_init)(struct phy_device *phydev);
+
+        /* Called during discovery.  Used to set
+         * up device-specific structures, if any */
+        int (*probe)(struct phy_device *phydev);
+
+        /* PHY Power Management */
+        int (*suspend)(struct phy_device *phydev);
+        int (*resume)(struct phy_device *phydev);
+
+        /* Configures the advertisement and resets
+         * autonegotiation if phydev->autoneg is on,
+         * forces the speed to the current settings in phydev
+         * if phydev->autoneg is off */
+        int (*config_aneg)(struct phy_device *phydev);
+
+        /* Determines the negotiated speed and duplex */
+        int (*read_status)(struct phy_device *phydev);
+
+        /* Clears any pending interrupts */
+        int (*ack_interrupt)(struct phy_device *phydev);
+
+        /* Enables or disables interrupts */
+        int (*config_intr)(struct phy_device *phydev);
+
+        /* Clears up any memory if needed */
+        void (*remove)(struct phy_device *phydev);
+
+        struct device_driver driver;
+};
+#define to_phy_driver(d) container_of(d, struct phy_driver, driver)
+
+int phy_read(struct phy_device *phydev, u16 regnum);
+int phy_write(struct phy_device *phydev, u16 regnum, u16 val);
+struct phy_device* get_phy_device(struct mii_bus *bus, int addr);
+int phy_clear_interrupt(struct phy_device *phydev);
+int phy_config_interrupt(struct phy_device *phydev, u32 interrupts);
+struct phy_device * phy_attach(struct net_device *dev,
+                const char *phy_id, u32 flags);
+struct phy_device * phy_connect(struct net_device *dev, const char *phy_id,
+                void (*handler)(struct net_device *), u32 flags);
+void phy_disconnect(struct phy_device *phydev);
+void phy_detach(struct phy_device *phydev);
+void phy_start(struct phy_device *phydev);
+void phy_stop(struct phy_device *phydev);
+int phy_start_aneg(struct phy_device *phydev);
+
+int mdiobus_register(struct mii_bus *bus);
+void mdiobus_unregister(struct mii_bus *bus);
+void phy_sanitize_settings(struct phy_device *phydev);
+int phy_stop_interrupts(struct phy_device *phydev);
+
+static inline int phy_read_status(struct phy_device *phydev) {
+        return phydev->drv->read_status(phydev);
+}
+
+int genphy_config_advert(struct phy_device *phydev);
+int genphy_setup_forced(struct phy_device *phydev);
+int genphy_restart_aneg(struct phy_device *phydev);
+int genphy_config_aneg(struct phy_device *phydev);
+int genphy_update_link(struct phy_device *phydev);
+int genphy_read_status(struct phy_device *phydev);
+void phy_driver_unregister(struct phy_driver *drv);
+int phy_driver_register(struct phy_driver *new_driver);
+void phy_prepare_link(struct phy_device *phydev,
+                void (*adjust_link)(struct net_device *));
+void phy_start_machine(struct phy_device *phydev,
+                void (*handler)(struct net_device *));
+void phy_stop_machine(struct phy_device *phydev);
+int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
+int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
+int phy_mii_ioctl(struct phy_device *phydev,
+                struct mii_ioctl_data *mii_data, int cmd);
+int phy_start_interrupts(struct phy_device *phydev);
+void phy_print_status(struct phy_device *phydev);
+
+extern struct bus_type mdio_bus_type;
+#endif /* __PHY_H */
diff --git a/include/linux/random.h b/include/linux/random.h
index cc6703449916..7b2adb3322d5 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -59,6 +59,8 @@ extern __u32 secure_tcp_sequence_number(__u32 saddr, __u32 daddr,
                                         __u16 sport, __u16 dport);
 extern __u32 secure_tcpv6_sequence_number(__u32 *saddr, __u32 *daddr,
                                           __u16 sport, __u16 dport);
+extern u64 secure_dccp_sequence_number(__u32 saddr, __u32 daddr,
+                                       __u16 sport, __u16 dport);
 
 #ifndef MODULE
 extern struct file_operations random_fops, urandom_fops;
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 657c05ab8f9e..c231e9a08f0b 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -826,9 +826,8 @@ enum
 #define TCA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
 #define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
 
-
-/* RTnetlink multicast groups */
-
+#ifndef __KERNEL__
+/* RTnetlink multicast groups - backwards compatibility for userspace */
 #define RTMGRP_LINK             1
 #define RTMGRP_NOTIFY           2
 #define RTMGRP_NEIGH            4
@@ -847,6 +846,43 @@ enum
 #define RTMGRP_DECnet_ROUTE     0x4000
 
 #define RTMGRP_IPV6_PREFIX      0x20000
+#endif
+
+/* RTnetlink multicast groups */
+enum rtnetlink_groups {
+        RTNLGRP_NONE,
+#define RTNLGRP_NONE            RTNLGRP_NONE
+        RTNLGRP_LINK,
+#define RTNLGRP_LINK            RTNLGRP_LINK
+        RTNLGRP_NOTIFY,
+#define RTNLGRP_NOTIFY          RTNLGRP_NOTIFY
+        RTNLGRP_NEIGH,
+#define RTNLGRP_NEIGH           RTNLGRP_NEIGH
+        RTNLGRP_TC,
+#define RTNLGRP_TC              RTNLGRP_TC
+        RTNLGRP_IPV4_IFADDR,
+#define RTNLGRP_IPV4_IFADDR     RTNLGRP_IPV4_IFADDR
+        RTNLGRP_IPV4_MROUTE,
+#define RTNLGRP_IPV4_MROUTE     RTNLGRP_IPV4_MROUTE
+        RTNLGRP_IPV4_ROUTE,
+#define RTNLGRP_IPV4_ROUTE      RTNLGRP_IPV4_ROUTE
+        RTNLGRP_IPV6_IFADDR,
+#define RTNLGRP_IPV6_IFADDR     RTNLGRP_IPV6_IFADDR
+        RTNLGRP_IPV6_MROUTE,
+#define RTNLGRP_IPV6_MROUTE     RTNLGRP_IPV6_MROUTE
+        RTNLGRP_IPV6_ROUTE,
+#define RTNLGRP_IPV6_ROUTE      RTNLGRP_IPV6_ROUTE
+        RTNLGRP_IPV6_IFINFO,
+#define RTNLGRP_IPV6_IFINFO     RTNLGRP_IPV6_IFINFO
+        RTNLGRP_DECnet_IFADDR,
+#define RTNLGRP_DECnet_IFADDR   RTNLGRP_DECnet_IFADDR
+        RTNLGRP_DECnet_ROUTE,
+#define RTNLGRP_DECnet_ROUTE    RTNLGRP_DECnet_ROUTE
+        RTNLGRP_IPV6_PREFIX,
+#define RTNLGRP_IPV6_PREFIX     RTNLGRP_IPV6_PREFIX
+        __RTNLGRP_MAX
+};
+#define RTNLGRP_MAX     (__RTNLGRP_MAX - 1)
 
 /* TC action piece */
 struct tcamsg
diff --git a/include/linux/security.h b/include/linux/security.h
index b42095a68b1c..7aab6ab7c57f 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2727,7 +2727,8 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o
         return security_ops->socket_getpeersec(sock, optval, optlen, len);
 }
 
-static inline int security_sk_alloc(struct sock *sk, int family, int priority)
+static inline int security_sk_alloc(struct sock *sk, int family,
+                                    unsigned int __nocast priority)
 {
         return security_ops->sk_alloc_security(sk, family, priority);
 }
@@ -2844,7 +2845,8 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o
         return -ENOPROTOOPT;
 }
 
-static inline int security_sk_alloc(struct sock *sk, int family, int priority)
+static inline int security_sk_alloc(struct sock *sk, int family,
+                                    unsigned int __nocast priority)
 {
         return 0;
 }
diff --git a/include/linux/selinux_netlink.h b/include/linux/selinux_netlink.h
index 957e6ebca4e6..bbf489decd84 100644
--- a/include/linux/selinux_netlink.h
+++ b/include/linux/selinux_netlink.h
@@ -20,10 +20,21 @@ enum {
         SELNL_MSG_MAX
 };
 
-/* Multicast groups */
+#ifndef __KERNEL__
+/* Multicast groups - backwards compatiblility for userspace */
 #define SELNL_GRP_NONE          0x00000000
 #define SELNL_GRP_AVC           0x00000001      /* AVC notifications */
 #define SELNL_GRP_ALL           0xffffffff
+#endif
+
+enum selinux_nlgroups {
+        SELNLGRP_NONE,
+#define SELNLGRP_NONE   SELNLGRP_NONE
+        SELNLGRP_AVC,
+#define SELNLGRP_AVC    SELNLGRP_AVC
+        __SELNLGRP_MAX
+};
+#define SELNLGRP_MAX    (__SELNLGRP_MAX - 1)
 
 /* Message structures */
 struct selnl_msg_setenforce {
diff --git a/include/linux/serialP.h b/include/linux/serialP.h
index 2b2f35a64d75..2b9e6b9554d5 100644
--- a/include/linux/serialP.h
+++ b/include/linux/serialP.h
@@ -140,44 +140,4 @@ struct rs_multiport_struct {
 #define ALPHA_KLUDGE_MCR 0
 #endif
 
-/*
- * Definitions for PCI support.
- */
-#define SPCI_FL_BASE_MASK       0x0007
-#define SPCI_FL_BASE0   0x0000
-#define SPCI_FL_BASE1   0x0001
-#define SPCI_FL_BASE2   0x0002
-#define SPCI_FL_BASE3   0x0003
-#define SPCI_FL_BASE4   0x0004
-#define SPCI_FL_GET_BASE(x)     (x & SPCI_FL_BASE_MASK)
-
-#define SPCI_FL_IRQ_MASK       (0x0007 << 4)
-#define SPCI_FL_IRQBASE0       (0x0000 << 4)
-#define SPCI_FL_IRQBASE1       (0x0001 << 4)
-#define SPCI_FL_IRQBASE2       (0x0002 << 4)
-#define SPCI_FL_IRQBASE3       (0x0003 << 4)
-#define SPCI_FL_IRQBASE4       (0x0004 << 4)
-#define SPCI_FL_GET_IRQBASE(x)        ((x & SPCI_FL_IRQ_MASK) >> 4)
-
-/* Use successive BARs (PCI base address registers), 
-   else use offset into some specified BAR */
-#define SPCI_FL_BASE_TABLE      0x0100
-
-/* Use successive entries in the irq resource table */
-#define SPCI_FL_IRQ_TABLE       0x0200
-
-/* Use the irq resource table instead of dev->irq */
-#define SPCI_FL_IRQRESOURCE     0x0400
-
-/* Use the Base address register size to cap number of ports */
-#define SPCI_FL_REGION_SZ_CAP   0x0800
-
-/* Do not use irq sharing for this device */
-#define SPCI_FL_NO_SHIRQ        0x1000
-
-/* This is a PNP device */
-#define SPCI_FL_ISPNP           0x2000
-
-#define SPCI_FL_PNPDEFAULT      (SPCI_FL_IRQRESOURCE|SPCI_FL_ISPNP)
-
 #endif /* _LINUX_SERIAL_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 948527e42a60..42edce6abe23 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -155,16 +155,29 @@ struct skb_shared_info {
 #define SKB_DATAREF_SHIFT 16
 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1)
 
+extern struct timeval skb_tv_base;
+
+struct skb_timeval {
+        u32     off_sec;
+        u32     off_usec;
+};
+
+
+enum {
+        SKB_FCLONE_UNAVAILABLE,
+        SKB_FCLONE_ORIG,
+        SKB_FCLONE_CLONE,
+};
+
 /** 
  *      struct sk_buff - socket buffer
  *      @next: Next buffer in list
  *      @prev: Previous buffer in list
  *      @list: List we are on
  *      @sk: Socket we are owned by
- *      @stamp: Time we arrived
+ *      @tstamp: Time we arrived stored as offset to skb_tv_base
  *      @dev: Device we arrived on/are leaving by
  *      @input_dev: Device we arrived on
- *      @real_dev: The real device we are using
  *      @h: Transport layer header
  *      @nh: Network layer header
  *      @mac: Link layer header
@@ -190,14 +203,11 @@ struct skb_shared_info {
  *      @end: End pointer
  *      @destructor: Destruct function
  *      @nfmark: Can be used for communication between hooks
- *      @nfcache: Cache info
  *      @nfct: Associated connection, if any
  *      @nfctinfo: Relationship of this skb to the connection
  *      @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
- *      @private: Data which is private to the HIPPI implementation
  *      @tc_index: Traffic control index
  *      @tc_verd: traffic control verdict
- *      @tc_classid: traffic control classid
  */
 
 struct sk_buff {
@@ -205,12 +215,10 @@ struct sk_buff {
         struct sk_buff          *next;
         struct sk_buff          *prev;
 
-        struct sk_buff_head     *list;
         struct sock             *sk;
-        struct timeval          stamp;
+        struct skb_timeval      tstamp;
         struct net_device       *dev;
         struct net_device       *input_dev;
-        struct net_device       *real_dev;
 
         union {
                 struct tcphdr   *th;
@@ -252,33 +260,28 @@ struct sk_buff {
         __u8                    local_df:1,
                                 cloned:1,
                                 ip_summed:2,
-                                nohdr:1;
-                                /* 3 bits spare */
-        __u8                    pkt_type;
+                                nohdr:1,
+                                nfctinfo:3;
+        __u8                    pkt_type:3,
+                                fclone:2;
         __be16                  protocol;
 
         void                    (*destructor)(struct sk_buff *skb);
 #ifdef CONFIG_NETFILTER
-        unsigned long           nfmark;
-        __u32                   nfcache;
-        __u32                   nfctinfo;
+        __u32                   nfmark;
         struct nf_conntrack     *nfct;
+#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+        __u8                    ipvs_property:1;
+#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
         struct nf_bridge_info   *nf_bridge;
 #endif
 #endif /* CONFIG_NETFILTER */
-#if defined(CONFIG_HIPPI)
-        union {
-                __u32           ifield;
-        } private;
-#endif
 #ifdef CONFIG_NET_SCHED
-       __u32                    tc_index;        /* traffic control index */
+        __u16                   tc_index;       /* traffic control index */
 #ifdef CONFIG_NET_CLS_ACT
-        __u32           tc_verd;               /* traffic control verdict */
-        __u32           tc_classid;            /* traffic control classid */
+        __u16                   tc_verd;        /* traffic control verdict */
 #endif
-
 #endif
 
 
@@ -300,8 +303,20 @@ struct sk_buff {
 #include <asm/system.h>
 
 extern void            __kfree_skb(struct sk_buff *skb);
-extern struct sk_buff *alloc_skb(unsigned int size,
-                                 unsigned int __nocast priority);
+extern struct sk_buff *__alloc_skb(unsigned int size,
+                                   unsigned int __nocast priority, int fclone);
+static inline struct sk_buff *alloc_skb(unsigned int size,
+                                        unsigned int __nocast priority)
+{
+        return __alloc_skb(size, priority, 0);
+}
+
+static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
+                                               unsigned int __nocast priority)
+{
+        return __alloc_skb(size, priority, 1);
+}
+
 extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
                                             unsigned int size,
                                             unsigned int __nocast priority);
@@ -597,7 +612,6 @@ static inline void __skb_queue_head(struct sk_buff_head *list,
 {
         struct sk_buff *prev, *next;
 
-        newsk->list = list;
         list->qlen++;
         prev = (struct sk_buff *)list;
         next = prev->next;
@@ -622,7 +636,6 @@ static inline void __skb_queue_tail(struct sk_buff_head *list,
 {
         struct sk_buff *prev, *next;
 
-        newsk->list = list;
         list->qlen++;
         next = (struct sk_buff *)list;
         prev = next->prev;
@@ -655,7 +668,6 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
                 next->prev   = prev;
                 prev->next   = next;
                 result->next = result->prev = NULL;
-                result->list = NULL;
         }
         return result;
 }
@@ -664,7 +676,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
 /*
  *      Insert a packet on a list.
  */
-extern void        skb_insert(struct sk_buff *old, struct sk_buff *newsk);
+extern void        skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
 static inline void __skb_insert(struct sk_buff *newsk,
                                 struct sk_buff *prev, struct sk_buff *next,
                                 struct sk_buff_head *list)
@@ -672,24 +684,23 @@ static inline void __skb_insert(struct sk_buff *newsk,
         newsk->next = next;
         newsk->prev = prev;
         next->prev  = prev->next = newsk;
-        newsk->list = list;
         list->qlen++;
 }
 
 /*
  *      Place a packet after a given packet in a list.
  */
-extern void        skb_append(struct sk_buff *old, struct sk_buff *newsk);
-static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk)
+extern void        skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
+static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
 {
-        __skb_insert(newsk, old, old->next, old->list);
+        __skb_insert(newsk, old, old->next, list);
 }
 
 /*
  * remove sk_buff from list. _Must_ be called atomically, and with
  * the list known..
  */
-extern void        skb_unlink(struct sk_buff *skb);
+extern void        skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
 static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
 {
         struct sk_buff *next, *prev;
@@ -698,7 +709,6 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
         next       = skb->next;
         prev       = skb->prev;
         skb->next  = skb->prev = NULL;
-        skb->list  = NULL;
         next->prev = prev;
         prev->next = next;
 }
@@ -1213,6 +1223,8 @@ extern void	       skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 extern void            skb_split(struct sk_buff *skb,
                                  struct sk_buff *skb1, const u32 len);
 
+extern void            skb_release_data(struct sk_buff *skb);
+
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
                                        int len, void *buffer)
 {
@@ -1230,6 +1242,42 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 extern void skb_init(void);
 extern void skb_add_mtu(int mtu);
 
+/**
+ *      skb_get_timestamp - get timestamp from a skb
+ *      @skb: skb to get stamp from
+ *      @stamp: pointer to struct timeval to store stamp in
+ *
+ *      Timestamps are stored in the skb as offsets to a base timestamp.
+ *      This function converts the offset back to a struct timeval and stores
+ *      it in stamp.
+ */
+static inline void skb_get_timestamp(struct sk_buff *skb, struct timeval *stamp)
+{
+        stamp->tv_sec  = skb->tstamp.off_sec;
+        stamp->tv_usec = skb->tstamp.off_usec;
+        if (skb->tstamp.off_sec) {
+                stamp->tv_sec  += skb_tv_base.tv_sec;
+                stamp->tv_usec += skb_tv_base.tv_usec;
+        }
+}
+
+/**
+ *      skb_set_timestamp - set timestamp of a skb
+ *      @skb: skb to set stamp of
+ *      @stamp: pointer to struct timeval to get stamp from
+ *
+ *      Timestamps are stored in the skb as offsets to a base timestamp.
+ *      This function converts a struct timeval to an offset and stores
+ *      it in the skb.
+ */
+static inline void skb_set_timestamp(struct sk_buff *skb, struct timeval *stamp)
+{
+        skb->tstamp.off_sec  = stamp->tv_sec - skb_tv_base.tv_sec;
+        skb->tstamp.off_usec = stamp->tv_usec - skb_tv_base.tv_usec;
+}
+
+extern void __net_timestamp(struct sk_buff *skb);
+
 #ifdef CONFIG_NETFILTER
 static inline void nf_conntrack_put(struct nf_conntrack *nfct)
 {
diff --git a/include/linux/socket.h b/include/linux/socket.h
index a5c7d96e4d2e..1739c2d5b95b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -26,6 +26,13 @@ struct __kernel_sockaddr_storage {
 #include <linux/types.h>                /* pid_t                        */
 #include <linux/compiler.h>             /* __user                       */
 
+extern int sysctl_somaxconn;
+extern void sock_init(void);
+#ifdef CONFIG_PROC_FS
+struct seq_file;
+extern void socket_seq_show(struct seq_file *seq);
+#endif
+
 typedef unsigned short  sa_family_t;
 
 /*
@@ -271,6 +278,8 @@ struct ucred {
 #define SOL_IRDA        266
 #define SOL_NETBEUI     267
 #define SOL_LLC         268
+#define SOL_DCCP        269
+#define SOL_NETLINK     270
 
 /* IPX options */
 #define IPX_TYPE        1
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index e4fd82e42104..ac4ca44c75ca 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -55,24 +55,6 @@ struct tcphdr {
         __u16   urg_ptr;
 };
 
-
-enum {
-  TCP_ESTABLISHED = 1,
-  TCP_SYN_SENT,
-  TCP_SYN_RECV,
-  TCP_FIN_WAIT1,
-  TCP_FIN_WAIT2,
-  TCP_TIME_WAIT,
-  TCP_CLOSE,
-  TCP_CLOSE_WAIT,
-  TCP_LAST_ACK,
-  TCP_LISTEN,
-  TCP_CLOSING,   /* now a valid state */
-
-  TCP_MAX_STATES /* Leave at the end! */
-};
-
-#define TCP_STATE_MASK  0xF
 #define TCP_ACTION_FIN  (1 << 7)
 
 enum {
@@ -195,8 +177,9 @@ struct tcp_info
 
 #include <linux/config.h>
 #include <linux/skbuff.h>
-#include <linux/ip.h>
 #include <net/sock.h>
+#include <net/inet_connection_sock.h>
+#include <net/inet_timewait_sock.h>
 
 /* This defines a selective acknowledgement block. */
 struct tcp_sack_block {
@@ -236,8 +219,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 }
 
 struct tcp_sock {
-        /* inet_sock has to be the first member of tcp_sock */
-        struct inet_sock        inet;
+        /* inet_connection_sock has to be the first member of tcp_sock */
+        struct inet_connection_sock     inet_conn;
         int     tcp_header_len; /* Bytes of tcp header to send          */
 
 /*
@@ -258,19 +241,6 @@ struct tcp_sock {
         __u32   snd_sml;        /* Last byte of the most recently transmitted small packet */
         __u32   rcv_tstamp;     /* timestamp of last received ACK (for keepalives) */
         __u32   lsndtime;       /* timestamp of last sent data packet (for restart window) */
-        struct tcp_bind_bucket *bind_hash;
-        /* Delayed ACK control data */
-        struct {
-                __u8    pending;        /* ACK is pending */
-                __u8    quick;          /* Scheduled number of quick acks       */
-                __u8    pingpong;       /* The session is interactive           */
-                __u8    blocked;        /* Delayed ACK was blocked by socket lock*/
-                __u32   ato;            /* Predicted tick of soft clock         */
-                unsigned long timeout;  /* Currently scheduled timeout          */
-                __u32   lrcvtime;       /* timestamp of last received data packet*/
-                __u16   last_seg_size;  /* Size of last incoming segment        */
-                __u16   rcv_mss;        /* MSS used for delayed ACK decisions   */ 
-        } ack;
 
         /* Data for direct copy to user */
         struct {
@@ -288,19 +258,15 @@ struct tcp_sock {
         __u32   mss_cache;      /* Cached effective mss, not including SACKS */
         __u16   xmit_size_goal; /* Goal for segmenting output packets   */
         __u16   ext_header_len; /* Network protocol overhead (IP/IPv6 options) */
-        __u8    ca_state;       /* State of fast-retransmit machine     */
-        __u8    retransmits;    /* Number of unrecovered RTO timeouts.  */
 
-        __u16   advmss;         /* Advertised MSS                       */
         __u32   window_clamp;   /* Maximal window to advertise          */
         __u32   rcv_ssthresh;   /* Current window clamp                 */
 
         __u32   frto_highmark;  /* snd_nxt when RTO occurred */
         __u8    reordering;     /* Packet reordering metric.            */
         __u8    frto_counter;   /* Number of new acks after RTO */
-
-        __u8    unused;
-        __u8    defer_accept;   /* User waits for some data after accept() */
+        __u8    nonagle;        /* Disable Nagle algorithm?             */
+        __u8    keepalive_probes; /* num of allowed keep alive probes   */
 
 /* RTT measurement */
         __u32   srtt;           /* smoothed round trip time << 3        */
@@ -308,19 +274,13 @@ struct tcp_sock {
         __u32   mdev_max;       /* maximal mdev for the last rtt period */
         __u32   rttvar;         /* smoothed mdev_max                    */
         __u32   rtt_seq;        /* sequence number to update rttvar     */
-        __u32   rto;            /* retransmit timeout                   */
 
         __u32   packets_out;    /* Packets which are "in flight"        */
         __u32   left_out;       /* Packets which leaved network */
         __u32   retrans_out;    /* Retransmitted packets out            */
-        __u8    backoff;        /* backoff                              */
 /*
  *      Options received (usually on last packet, some only on SYN packets).
  */
-        __u8    nonagle;        /* Disable Nagle algorithm?             */
-        __u8    keepalive_probes; /* num of allowed keep alive probes   */
-
-        __u8    probes_out;     /* unanswered 0 window probes           */
         struct tcp_options_received rx_opt;
 
 /*
@@ -333,11 +293,6 @@ struct tcp_sock {
         __u32   snd_cwnd_used;
         __u32   snd_cwnd_stamp;
 
-        /* Two commonly used timers in both sender and receiver paths. */
-        unsigned long           timeout;
-        struct timer_list       retransmit_timer;       /* Resend (no ack)      */
-        struct timer_list       delack_timer;           /* Ack delay            */
-
         struct sk_buff_head     out_of_order_queue; /* Out of order segments go here */
 
         struct tcp_func         *af_specific;   /* Operations which are AF_INET{4,6} specific   */
@@ -352,8 +307,7 @@ struct tcp_sock {
         struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
         struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/
 
-        __u8    syn_retries;    /* num of allowed syn retries */
-        __u8    ecn_flags;      /* ECN status bits.                     */
+        __u16   advmss;         /* Advertised MSS                       */
         __u16   prior_ssthresh; /* ssthresh saved at recovery start     */
         __u32   lost_out;       /* Lost packets                 */
         __u32   sacked_out;     /* SACK'd packets                       */
@@ -367,14 +321,12 @@ struct tcp_sock {
         int     undo_retrans;   /* number of undoable retransmissions. */
         __u32   urg_seq;        /* Seq of received urgent pointer */
         __u16   urg_data;       /* Saved octet of OOB data and control flags */
-        __u8    pending;        /* Scheduled timer event        */
         __u8    urg_mode;       /* In urgent mode               */
+        __u8    ecn_flags;      /* ECN status bits.                     */
         __u32   snd_up;         /* Urgent pointer               */
 
         __u32   total_retrans;  /* Total retransmits for entire connection */
 
-        struct request_sock_queue accept_queue; /* FIFO of established children */
-
         unsigned int            keepalive_time;   /* time before keep alive takes place */
         unsigned int            keepalive_intvl;  /* time interval between keep alive probes */
         int                     linger2;
@@ -394,11 +346,6 @@ struct tcp_sock {
                 __u32   seq;
                 __u32   time;
         } rcvq_space;
-
-        /* Pluggable TCP congestion control hook */
-        struct tcp_congestion_ops *ca_ops;
-        u32     ca_priv[16];
-#define TCP_CA_PRIV_SIZE        (16*sizeof(u32))
 };
 
 static inline struct tcp_sock *tcp_sk(const struct sock *sk)
@@ -406,9 +353,18 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk)
         return (struct tcp_sock *)sk;
 }
 
-static inline void *tcp_ca(const struct tcp_sock *tp)
+struct tcp_timewait_sock {
+        struct inet_timewait_sock tw_sk;
+        __u32                     tw_rcv_nxt;
+        __u32                     tw_snd_nxt;
+        __u32                     tw_rcv_wnd;
+        __u32                     tw_ts_recent;
+        long                      tw_ts_recent_stamp;
+};
+
+static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
 {
-        return (void *) tp->ca_priv;
+        return (struct tcp_timewait_sock *)sk;
 }
 
 #endif
diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h
deleted file mode 100644
index 7a5996743946..000000000000
--- a/include/linux/tcp_diag.h
+++ /dev/null
@@ -1,127 +0,0 @@
-#ifndef _TCP_DIAG_H_
-#define _TCP_DIAG_H_ 1
-
-/* Just some random number */
-#define TCPDIAG_GETSOCK 18
-
-/* Socket identity */
-struct tcpdiag_sockid
-{
-        __u16   tcpdiag_sport;
-        __u16   tcpdiag_dport;
-        __u32   tcpdiag_src[4];
-        __u32   tcpdiag_dst[4];
-        __u32   tcpdiag_if;
-        __u32   tcpdiag_cookie[2];
-#define TCPDIAG_NOCOOKIE (~0U)
-};
-
-/* Request structure */
-
-struct tcpdiagreq
-{
-        __u8    tcpdiag_family;         /* Family of addresses. */
-        __u8    tcpdiag_src_len;
-        __u8    tcpdiag_dst_len;
-        __u8    tcpdiag_ext;            /* Query extended information */
-
-        struct tcpdiag_sockid id;
-
-        __u32   tcpdiag_states;         /* States to dump */
-        __u32   tcpdiag_dbs;            /* Tables to dump (NI) */
-};
-
-enum
-{
-        TCPDIAG_REQ_NONE,
-        TCPDIAG_REQ_BYTECODE,
-};
-
-#define TCPDIAG_REQ_MAX TCPDIAG_REQ_BYTECODE
-
-/* Bytecode is sequence of 4 byte commands followed by variable arguments.
- * All the commands identified by "code" are conditional jumps forward:
- * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be
- * length of the command and its arguments.
- */
- 
-struct tcpdiag_bc_op
-{
-        unsigned char   code;
-        unsigned char   yes;
-        unsigned short  no;
-};
-
-enum
-{
-        TCPDIAG_BC_NOP,
-        TCPDIAG_BC_JMP,
-        TCPDIAG_BC_S_GE,
-        TCPDIAG_BC_S_LE,
-        TCPDIAG_BC_D_GE,
-        TCPDIAG_BC_D_LE,
-        TCPDIAG_BC_AUTO,
-        TCPDIAG_BC_S_COND,
-        TCPDIAG_BC_D_COND,
-};
-
-struct tcpdiag_hostcond
-{
-        __u8    family;
-        __u8    prefix_len;
-        int     port;
-        __u32   addr[0];
-};
-
-/* Base info structure. It contains socket identity (addrs/ports/cookie)
- * and, alas, the information shown by netstat. */
-struct tcpdiagmsg
-{
-        __u8    tcpdiag_family;
-        __u8    tcpdiag_state;
-        __u8    tcpdiag_timer;
-        __u8    tcpdiag_retrans;
-
-        struct tcpdiag_sockid id;
-
-        __u32   tcpdiag_expires;
-        __u32   tcpdiag_rqueue;
-        __u32   tcpdiag_wqueue;
-        __u32   tcpdiag_uid;
-        __u32   tcpdiag_inode;
-};
-
-/* Extensions */
-
-enum
-{
-        TCPDIAG_NONE,
-        TCPDIAG_MEMINFO,
-        TCPDIAG_INFO,
-        TCPDIAG_VEGASINFO,
-        TCPDIAG_CONG,
-};
-
-#define TCPDIAG_MAX TCPDIAG_CONG
-
-
-/* TCPDIAG_MEM */
-
-struct tcpdiag_meminfo
-{
-        __u32   tcpdiag_rmem;
-        __u32   tcpdiag_wmem;
-        __u32   tcpdiag_fmem;
-        __u32   tcpdiag_tmem;
-};
-
-/* TCPDIAG_VEGASINFO */
-
-struct tcpvegas_info {
-        __u32   tcpv_enabled;
-        __u32   tcpv_rttcnt;
-        __u32   tcpv_rtt;
-        __u32   tcpv_minrtt;
-};
-
-#endif /* _TCP_DIAG_H_ */
diff --git a/include/linux/types.h b/include/linux/types.h
index dcb13f865df9..2b678c22ca4a 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -123,6 +123,9 @@ typedef		__u64		u_int64_t;
 typedef         __s64           int64_t;
 #endif
 
+/* this is a special 64bit data type that is 8-byte aligned */
+#define aligned_u64 unsigned long long __attribute__((aligned(8)))
+
 /*
  * The type used for indexing onto a disc or disc partition.
  * If required, asm/types.h can override it and define
diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
index f0d423300d84..0fb077d68441 100644
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -258,9 +258,27 @@ struct xfrm_usersa_flush {
         __u8                            proto;
 };
 
+#ifndef __KERNEL__
+/* backwards compatibility for userspace */
 #define XFRMGRP_ACQUIRE         1
 #define XFRMGRP_EXPIRE          2
 #define XFRMGRP_SA              4
 #define XFRMGRP_POLICY          8
+#endif
+
+enum xfrm_nlgroups {
+        XFRMNLGRP_NONE,
+#define XFRMNLGRP_NONE          XFRMNLGRP_NONE
+        XFRMNLGRP_ACQUIRE,
+#define XFRMNLGRP_ACQUIRE       XFRMNLGRP_ACQUIRE
+        XFRMNLGRP_EXPIRE,
+#define XFRMNLGRP_EXPIRE        XFRMNLGRP_EXPIRE
+        XFRMNLGRP_SA,
+#define XFRMNLGRP_SA            XFRMNLGRP_SA
+        XFRMNLGRP_POLICY,
+#define XFRMNLGRP_POLICY        XFRMNLGRP_POLICY
+        __XFRMNLGRP_MAX
+};
+#define XFRMNLGRP_MAX   (__XFRMNLGRP_MAX - 1)
 
 #endif /* _LINUX_XFRM_H */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index ed00a995f576..b55eb7c7f033 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -63,7 +63,7 @@ struct tc_action_ops
         __u32   type; /* TBD to match kind */
         __u32   capab;  /* capabilities includes 4 bit version */
         struct module           *owner;
-        int     (*act)(struct sk_buff **, struct tc_action *);
+        int     (*act)(struct sk_buff **, struct tc_action *, struct tcf_result *);
         int     (*get_stats)(struct sk_buff *, struct tc_action *);
         int     (*dump)(struct sk_buff *, struct tc_action *,int , int);
         int     (*cleanup)(struct tc_action *, int bind);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index a0ed93672176..750e2508dd90 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -45,6 +45,7 @@ struct prefix_info {
 
 #ifdef __KERNEL__
 
+#include <linux/config.h>
 #include <linux/netdevice.h>
 #include <net/if_inet6.h>
 #include <net/ipv6.h>
@@ -238,5 +239,10 @@ static inline int ipv6_addr_is_ll_all_routers(const struct in6_addr *addr)
                 addr->s6_addr32[3] == htonl(0x00000002));
 }
 
+#ifdef CONFIG_PROC_FS
+extern int if6_proc_init(void);
+extern void if6_proc_exit(void);
+#endif
+
 #endif
 #endif
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b60b3846b9d1..b5d785ab4a0e 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -1,5 +1,11 @@
 #ifndef __LINUX_NET_AFUNIX_H
 #define __LINUX_NET_AFUNIX_H
+
+#include <linux/config.h>
+#include <linux/socket.h>
+#include <linux/un.h>
+#include <net/sock.h>
+
 extern void unix_inflight(struct file *fp);
 extern void unix_notinflight(struct file *fp);
 extern void unix_gc(void);
@@ -74,5 +80,14 @@ struct unix_sock {
         wait_queue_head_t       peer_wait;
 };
 #define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+#ifdef CONFIG_SYSCTL
+extern int sysctl_unix_max_dgram_qlen;
+extern void unix_sysctl_register(void);
+extern void unix_sysctl_unregister(void);
+#else
+static inline void unix_sysctl_register(void) {}
+static inline void unix_sysctl_unregister(void) {}
+#endif
 #endif
 #endif
diff --git a/include/net/arp.h b/include/net/arp.h
index a1f09fad6a52..a13e30c35f42 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -11,7 +11,7 @@ extern struct neigh_table arp_tbl;
 
 extern void     arp_init(void);
 extern int      arp_rcv(struct sk_buff *skb, struct net_device *dev,
-                        struct packet_type *pt);
+                        struct packet_type *pt, struct net_device *orig_dev);
 extern int      arp_find(unsigned char *haddr, struct sk_buff *skb);
 extern int      arp_ioctl(unsigned int cmd, void __user *arg);
 extern void     arp_send(int type, int ptype, u32 dest_ip, 
diff --git a/include/net/ax25.h b/include/net/ax25.h
index 3696f988a9f1..926eed543023 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -316,7 +316,7 @@ extern int  ax25_protocol_is_registered(unsigned int);
 
 /* ax25_in.c */
 extern int  ax25_rx_iframe(ax25_cb *, struct sk_buff *);
-extern int  ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *);
+extern int  ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
 
 /* ax25_ip.c */
 extern int  ax25_encapsulate(struct sk_buff *, struct net_device *, unsigned short, void *, void *, unsigned int);
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 06b24f637026..6dfa4a61ffd0 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -131,11 +131,12 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock);
 
 /* Skb helpers */
 struct bt_skb_cb {
-        int incoming;
+        __u8 pkt_type;
+        __u8 incoming;
 };
 #define bt_cb(skb) ((struct bt_skb_cb *)(skb->cb)) 
 
-static inline struct sk_buff *bt_skb_alloc(unsigned int len, int how)
+static inline struct sk_buff *bt_skb_alloc(unsigned int len, unsigned int __nocast how)
 {
         struct sk_buff *skb;
 
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6f0706f4af68..371e7d3f2e6f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -453,6 +453,15 @@ struct inquiry_info_with_rssi {
         __u16    clock_offset;
         __s8     rssi;
 } __attribute__ ((packed));
+struct inquiry_info_with_rssi_and_pscan_mode {
+        bdaddr_t bdaddr;
+        __u8     pscan_rep_mode;
+        __u8     pscan_period_mode;
+        __u8     pscan_mode;
+        __u8     dev_class[3];
+        __u16    clock_offset;
+        __s8     rssi;
+} __attribute__ ((packed));
 
 #define HCI_EV_CONN_COMPLETE    0x03
 struct hci_ev_conn_complete {
@@ -584,6 +593,12 @@ struct hci_ev_clock_offset {
         __u16    clock_offset;
 } __attribute__ ((packed));
 
+#define HCI_EV_PSCAN_REP_MODE   0x20
+struct hci_ev_pscan_rep_mode {
+        bdaddr_t bdaddr;
+        __u8     pscan_rep_mode;
+} __attribute__ ((packed));
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL   0xFD
 struct hci_ev_stack_internal {
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6d63a47c731b..7f933f302078 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -404,7 +404,7 @@ static inline int hci_recv_frame(struct sk_buff *skb)
         bt_cb(skb)->incoming = 1;
 
         /* Time stamp */
-        do_gettimeofday(&skb->stamp);
+        __net_timestamp(skb);
 
         /* Queue frame for rx task */
         skb_queue_tail(&hdev->rx_q, skb);
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 13669bad00b3..ffea9d54071f 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -80,9 +80,9 @@
 #define RFCOMM_RPN_STOP_15      1
 
 #define RFCOMM_RPN_PARITY_NONE  0x0
-#define RFCOMM_RPN_PARITY_ODD   0x4
-#define RFCOMM_RPN_PARITY_EVEN  0x5
-#define RFCOMM_RPN_PARITY_MARK  0x6
+#define RFCOMM_RPN_PARITY_ODD   0x1
+#define RFCOMM_RPN_PARITY_EVEN  0x3
+#define RFCOMM_RPN_PARITY_MARK  0x5
 #define RFCOMM_RPN_PARITY_SPACE 0x7
 
 #define RFCOMM_RPN_FLOW_NONE    0x00
@@ -223,8 +223,14 @@ struct rfcomm_dlc {
 #define RFCOMM_CFC_DISABLED 0
 #define RFCOMM_CFC_ENABLED  RFCOMM_MAX_CREDITS
 
+/* ---- RFCOMM SEND RPN ---- */
+int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci,
+                        u8 bit_rate, u8 data_bits, u8 stop_bits,
+                        u8 parity, u8 flow_ctrl_settings, 
+                        u8 xon_char, u8 xoff_char, u16 param_mask);
+
 /* ---- RFCOMM DLCs (channels) ---- */
-struct rfcomm_dlc *rfcomm_dlc_alloc(int prio);
+struct rfcomm_dlc *rfcomm_dlc_alloc(unsigned int __nocast prio);
 void rfcomm_dlc_free(struct rfcomm_dlc *d);
 int  rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel);
 int  rfcomm_dlc_close(struct rfcomm_dlc *d, int reason);
diff --git a/include/net/datalink.h b/include/net/datalink.h
index 5797ba3d2eb5..deb7ca75db48 100644
--- a/include/net/datalink.h
+++ b/include/net/datalink.h
@@ -9,7 +9,7 @@ struct datalink_proto {
         unsigned short  header_length;
 
         int     (*rcvfunc)(struct sk_buff *, struct net_device *,
-                                struct packet_type *);
+                                struct packet_type *, struct net_device *);
         int     (*request)(struct datalink_proto *, struct sk_buff *,
                                         unsigned char *);
         struct list_head node;
diff --git a/include/net/dn.h b/include/net/dn.h
index 5551c46db397..c1dbbd222793 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -3,6 +3,7 @@
 
 #include <linux/dn.h>
 #include <net/sock.h>
+#include <net/tcp.h>
 #include <asm/byteorder.h>
 
 typedef unsigned short dn_address;
diff --git a/include/net/icmp.h b/include/net/icmp.h
index e5ef0d15fb45..6cdebeee5f96 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -57,4 +57,11 @@ static inline struct raw_sock *raw_sk(const struct sock *sk)
         return (struct raw_sock *)sk;
 }
 
+extern int sysctl_icmp_echo_ignore_all;
+extern int sysctl_icmp_echo_ignore_broadcasts;
+extern int sysctl_icmp_ignore_bogus_error_responses;
+extern int sysctl_icmp_errors_use_inbound_ifaddr;
+extern int sysctl_icmp_ratelimit;
+extern int sysctl_icmp_ratemask;
+
 #endif  /* _ICMP_H */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
new file mode 100644
index 000000000000..03df3b157960
--- /dev/null
+++ b/include/net/inet6_hashtables.h
@@ -0,0 +1,130 @@
+/*
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ * Authors:     Lotsa people, from code originally in tcp
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _INET6_HASHTABLES_H
+#define _INET6_HASHTABLES_H
+
+#include <linux/config.h>
+
+#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+
+#include <net/ipv6.h>
+
+struct inet_hashinfo;
+
+/* I have no idea if this is a good hash for v6 or not. -DaveM */
+static inline int inet6_ehashfn(const struct in6_addr *laddr, const u16 lport,
+                                const struct in6_addr *faddr, const u16 fport,
+                                const int ehash_size)
+{
+        int hashent = (lport ^ fport);
+
+        hashent ^= (laddr->s6_addr32[3] ^ faddr->s6_addr32[3]);
+        hashent ^= hashent >> 16;
+        hashent ^= hashent >> 8;
+        return (hashent & (ehash_size - 1));
+}
+
+static inline int inet6_sk_ehashfn(const struct sock *sk, const int ehash_size)
+{
+        const struct inet_sock *inet = inet_sk(sk);
+        const struct ipv6_pinfo *np = inet6_sk(sk);
+        const struct in6_addr *laddr = &np->rcv_saddr;
+        const struct in6_addr *faddr = &np->daddr;
+        const __u16 lport = inet->num;
+        const __u16 fport = inet->dport;
+        return inet6_ehashfn(laddr, lport, faddr, fport, ehash_size);
+}
+
+/*
+ * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
+ * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
+ *
+ * The sockhash lock must be held as a reader here.
+ */
+static inline struct sock *
+                __inet6_lookup_established(struct inet_hashinfo *hashinfo,
+                                           const struct in6_addr *saddr,
+                                           const u16 sport,
+                                           const struct in6_addr *daddr,
+                                           const u16 hnum,
+                                           const int dif)
+{
+        struct sock *sk;
+        const struct hlist_node *node;
+        const __u32 ports = INET_COMBINED_PORTS(sport, hnum);
+        /* Optimize here for direct hit, only listening connections can
+         * have wildcards anyways.
+         */
+        const int hash = inet6_ehashfn(daddr, hnum, saddr, sport,
+                                       hashinfo->ehash_size);
+        struct inet_ehash_bucket *head = &hashinfo->ehash[hash];
+
+        read_lock(&head->lock);
+        sk_for_each(sk, node, &head->chain) {
+                /* For IPV6 do the cheaper port and family tests first. */
+                if (INET6_MATCH(sk, saddr, daddr, ports, dif))
+                        goto hit; /* You sunk my battleship! */
+        }
+        /* Must check for a TIME_WAIT'er before going to listener hash. */
+        sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) {
+                const struct inet_timewait_sock *tw = inet_twsk(sk);
+
+                if(*((__u32 *)&(tw->tw_dport))  == ports        &&
+                   sk->sk_family                == PF_INET6) {
+                        const struct tcp6_timewait_sock *tcp6tw = tcp6_twsk(sk);
+
+                        if (ipv6_addr_equal(&tcp6tw->tw_v6_daddr, saddr)        &&
+                            ipv6_addr_equal(&tcp6tw->tw_v6_rcv_saddr, daddr)    &&
+                            (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif))
+                                goto hit;
+                }
+        }
+        read_unlock(&head->lock);
+        return NULL;
+
+hit:
+        sock_hold(sk);
+        read_unlock(&head->lock);
+        return sk;
+}
+
+extern struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo,
+                                          const struct in6_addr *daddr,
+                                          const unsigned short hnum,
+                                          const int dif);
+
+static inline struct sock *__inet6_lookup(struct inet_hashinfo *hashinfo,
+                                          const struct in6_addr *saddr,
+                                          const u16 sport,
+                                          const struct in6_addr *daddr,
+                                          const u16 hnum,
+                                          const int dif)
+{
+        struct sock *sk = __inet6_lookup_established(hashinfo, saddr, sport,
+                                                     daddr, hnum, dif);
+        if (sk)
+                return sk;
+
+        return inet6_lookup_listener(hashinfo, daddr, hnum, dif);
+}
+
+extern struct sock *inet6_lookup(struct inet_hashinfo *hashinfo,
+                                 const struct in6_addr *saddr, const u16 sport,
+                                 const struct in6_addr *daddr, const u16 dport,
+                                 const int dif);
+#endif /* defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) */
+#endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index fbc1f4d140d8..f943306ce5ff 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -8,6 +8,11 @@ extern struct proto_ops		inet_dgram_ops;
  *      INET4 prototypes used by INET6
  */
 
+struct msghdr;
+struct sock;
+struct sockaddr;
+struct socket;
+
 extern void                     inet_remove_sock(struct sock *sk1);
 extern void                     inet_put_sock(unsigned short num, 
                                               struct sock *sk);
@@ -29,7 +34,6 @@ extern unsigned int		inet_poll(struct file * file, struct socket *sock, struct p
 extern int                      inet_listen(struct socket *sock, int backlog);
 
 extern void                     inet_sock_destruct(struct sock *sk);
-extern atomic_t                 inet_sock_nr;
 
 extern int                      inet_bind(struct socket *sock, 
                                           struct sockaddr *uaddr, int addr_len);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
new file mode 100644
index 000000000000..651f824c1008
--- /dev/null
+++ b/include/net/inet_connection_sock.h
@@ -0,0 +1,276 @@
+/*
+ * NET          Generic infrastructure for INET connection oriented protocols.
+ *
+ *              Definitions for inet_connection_sock 
+ *
+ * Authors:     Many people, see the TCP sources
+ *
+ *              From code originally in TCP
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ */
+#ifndef _INET_CONNECTION_SOCK_H
+#define _INET_CONNECTION_SOCK_H
+
+#include <linux/ip.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <net/request_sock.h>
+
+#define INET_CSK_DEBUG 1
+
+/* Cancel timers, when they are not required. */
+#undef INET_CSK_CLEAR_TIMERS
+
+struct inet_bind_bucket;
+struct inet_hashinfo;
+struct tcp_congestion_ops;
+
+/** inet_connection_sock - INET connection oriented sock
+ *
+ * @icsk_accept_queue:     FIFO of established children 
+ * @icsk_bind_hash:        Bind node
+ * @icsk_timeout:          Timeout
+ * @icsk_retransmit_timer: Resend (no ack)
+ * @icsk_rto:              Retransmit timeout
+ * @icsk_ca_ops            Pluggable congestion control hook
+ * @icsk_ca_state:         Congestion control state
+ * @icsk_retransmits:      Number of unrecovered [RTO] timeouts
+ * @icsk_pending:          Scheduled timer event
+ * @icsk_backoff:          Backoff
+ * @icsk_syn_retries:      Number of allowed SYN (or equivalent) retries
+ * @icsk_probes_out:       unanswered 0 window probes
+ * @icsk_ack:              Delayed ACK control data
+ */
+struct inet_connection_sock {
+        /* inet_sock has to be the first member! */
+        struct inet_sock          icsk_inet;
+        struct request_sock_queue icsk_accept_queue;
+        struct inet_bind_bucket   *icsk_bind_hash;
+        unsigned long             icsk_timeout;
+        struct timer_list         icsk_retransmit_timer;
+        struct timer_list         icsk_delack_timer;
+        __u32                     icsk_rto;
+        struct tcp_congestion_ops *icsk_ca_ops;
+        __u8                      icsk_ca_state;
+        __u8                      icsk_retransmits;
+        __u8                      icsk_pending;
+        __u8                      icsk_backoff;
+        __u8                      icsk_syn_retries;
+        __u8                      icsk_probes_out;
+        /* 2 BYTES HOLE, TRY TO PACK! */
+        struct {
+                __u8              pending;       /* ACK is pending                         */
+                __u8              quick;         /* Scheduled number of quick acks         */
+                __u8              pingpong;      /* The session is interactive             */
+                __u8              blocked;       /* Delayed ACK was blocked by socket lock */
+                __u32             ato;           /* Predicted tick of soft clock           */
+                unsigned long     timeout;       /* Currently scheduled timeout            */
+                __u32             lrcvtime;      /* timestamp of last received data packet */
+                __u16             last_seg_size; /* Size of last incoming segment          */
+                __u16             rcv_mss;       /* MSS used for delayed ACK decisions     */ 
+        } icsk_ack;
+        u32                       icsk_ca_priv[16];
+#define ICSK_CA_PRIV_SIZE       (16 * sizeof(u32))
+};
+
+#define ICSK_TIME_RETRANS       1       /* Retransmit timer */
+#define ICSK_TIME_DACK          2       /* Delayed ack timer */
+#define ICSK_TIME_PROBE0        3       /* Zero window probe timer */
+#define ICSK_TIME_KEEPOPEN      4       /* Keepalive timer */
+
+static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
+{
+        return (struct inet_connection_sock *)sk;
+}
+
+static inline void *inet_csk_ca(const struct sock *sk)
+{
+        return (void *)inet_csk(sk)->icsk_ca_priv;
+}
+
+extern struct sock *inet_csk_clone(struct sock *sk,
+                                   const struct request_sock *req,
+                                   const unsigned int __nocast priority);
+
+enum inet_csk_ack_state_t {
+        ICSK_ACK_SCHED  = 1,
+        ICSK_ACK_TIMER  = 2,
+        ICSK_ACK_PUSHED = 4
+};
+
+extern void inet_csk_init_xmit_timers(struct sock *sk,
+                                      void (*retransmit_handler)(unsigned long),
+                                      void (*delack_handler)(unsigned long),
+                                      void (*keepalive_handler)(unsigned long));
+extern void inet_csk_clear_xmit_timers(struct sock *sk);
+
+static inline void inet_csk_schedule_ack(struct sock *sk)
+{
+        inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
+}
+
+static inline int inet_csk_ack_scheduled(const struct sock *sk)
+{
+        return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
+}
+
+static inline void inet_csk_delack_init(struct sock *sk)
+{
+        memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
+}
+
+extern void inet_csk_delete_keepalive_timer(struct sock *sk);
+extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
+
+#ifdef INET_CSK_DEBUG
+extern const char inet_csk_timer_bug_msg[];
+#endif
+
+static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
+{
+        struct inet_connection_sock *icsk = inet_csk(sk);
+        
+        if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
+                icsk->icsk_pending = 0;
+#ifdef INET_CSK_CLEAR_TIMERS
+                sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+#endif
+        } else if (what == ICSK_TIME_DACK) {
+                icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
+#ifdef INET_CSK_CLEAR_TIMERS
+                sk_stop_timer(sk, &icsk->icsk_delack_timer);
+#endif
+        }
+#ifdef INET_CSK_DEBUG
+        else {
+                pr_debug("%s", inet_csk_timer_bug_msg);
+        }
+#endif
+}
+
+/*
+ *      Reset the retransmission timer
+ */
+static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
+                                             unsigned long when,
+                                             const unsigned long max_when)
+{
+        struct inet_connection_sock *icsk = inet_csk(sk);
+
+        if (when > max_when) {
+#ifdef INET_CSK_DEBUG
+                pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
+                         sk, what, when, current_text_addr());
+#endif
+                when = max_when;
+        }
+
+        if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
+                icsk->icsk_pending = what;
+                icsk->icsk_timeout = jiffies + when;
+                sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
+        } else if (what == ICSK_TIME_DACK) {
+                icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
+                icsk->icsk_ack.timeout = jiffies + when;
+                sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
+        }
+#ifdef INET_CSK_DEBUG
+        else {
+                pr_debug("%s", inet_csk_timer_bug_msg);
+        }
+#endif
+}
+
+extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+
+extern struct request_sock *inet_csk_search_req(const struct sock *sk,
+                                                struct request_sock ***prevp,
+                                                const __u16 rport,
+                                                const __u32 raddr,
+                                                const __u32 laddr);
+extern int inet_csk_get_port(struct inet_hashinfo *hashinfo,
+                             struct sock *sk, unsigned short snum);
+
+extern struct dst_entry* inet_csk_route_req(struct sock *sk,
+                                            const struct request_sock *req);
+
+static inline void inet_csk_reqsk_queue_add(struct sock *sk,
+                                            struct request_sock *req,
+                                            struct sock *child)
+{
+        reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
+}
+
+extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
+                                          struct request_sock *req,
+                                          const unsigned timeout);
+
+static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
+                                                struct request_sock *req)
+{
+        if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
+                inet_csk_delete_keepalive_timer(sk);
+}
+
+static inline void inet_csk_reqsk_queue_added(struct sock *sk,
+                                              const unsigned long timeout)
+{
+        if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
+                inet_csk_reset_keepalive_timer(sk, timeout);
+}
+
+static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
+{
+        return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
+}
+
+static inline int inet_csk_reqsk_queue_young(const struct sock *sk)
+{
+        return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
+}
+
+static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
+{
+        return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
+}
+
+static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
+                                               struct request_sock *req,
+                                               struct request_sock **prev)
+{
+        reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
+}
+
+static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
+                                             struct request_sock *req,
+                                             struct request_sock **prev)
+{
+        inet_csk_reqsk_queue_unlink(sk, req, prev);
+        inet_csk_reqsk_queue_removed(sk, req);
+        reqsk_free(req);
+}
+
+extern void inet_csk_reqsk_queue_prune(struct sock *parent,
+                                       const unsigned long interval,
+                                       const unsigned long timeout,
+                                       const unsigned long max_rto);
+
+extern void inet_csk_destroy_sock(struct sock *sk);
+
+/*
+ * LISTEN is a special case for poll..
+ */
+static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
+{
+        return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
+                        (POLLIN | POLLRDNORM) : 0;
+}
+
+extern int  inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
+extern void inet_csk_listen_stop(struct sock *sk);
+
+#endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
new file mode 100644
index 000000000000..646b6ea7fe26
--- /dev/null
+++ b/include/net/inet_hashtables.h
@@ -0,0 +1,427 @@
+/*
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ * Authors:     Lotsa people, from code originally in tcp
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _INET_HASHTABLES_H
+#define _INET_HASHTABLES_H
+
+#include <linux/config.h>
+
+#include <linux/interrupt.h>
+#include <linux/ipv6.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include <net/inet_connection_sock.h>
+#include <net/route.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+
+#include <asm/atomic.h>
+#include <asm/byteorder.h>
+
+/* This is for all connections with a full identity, no wildcards.
+ * New scheme, half the table is for TIME_WAIT, the other half is
+ * for the rest.  I'll experiment with dynamic table growth later.
+ */
+struct inet_ehash_bucket {
+        rwlock_t          lock;
+        struct hlist_head chain;
+} __attribute__((__aligned__(8)));
+
+/* There are a few simple rules, which allow for local port reuse by
+ * an application.  In essence:
+ *
+ *      1) Sockets bound to different interfaces may share a local port.
+ *         Failing that, goto test 2.
+ *      2) If all sockets have sk->sk_reuse set, and none of them are in
+ *         TCP_LISTEN state, the port may be shared.
+ *         Failing that, goto test 3.
+ *      3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
+ *         address, and none of them are the same, the port may be
+ *         shared.
+ *         Failing this, the port cannot be shared.
+ *
+ * The interesting point, is test #2.  This is what an FTP server does
+ * all day.  To optimize this case we use a specific flag bit defined
+ * below.  As we add sockets to a bind bucket list, we perform a
+ * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
+ * As long as all sockets added to a bind bucket pass this test,
+ * the flag bit will be set.
+ * The resulting situation is that tcp_v[46]_verify_bind() can just check
+ * for this flag bit, if it is set and the socket trying to bind has
+ * sk->sk_reuse set, we don't even have to walk the owners list at all,
+ * we return that it is ok to bind this socket to the requested local port.
+ *
+ * Sounds like a lot of work, but it is worth it.  In a more naive
+ * implementation (ie. current FreeBSD etc.) the entire list of ports
+ * must be walked for each data port opened by an ftp server.  Needless
+ * to say, this does not scale at all.  With a couple thousand FTP
+ * users logged onto your box, isn't it nice to know that new data
+ * ports are created in O(1) time?  I thought so. ;-)   -DaveM
+ */
+struct inet_bind_bucket {
+        unsigned short          port;
+        signed short            fastreuse;
+        struct hlist_node       node;
+        struct hlist_head       owners;
+};
+
+#define inet_bind_bucket_for_each(tb, node, head) \
+        hlist_for_each_entry(tb, node, head, node)
+
+struct inet_bind_hashbucket {
+        spinlock_t              lock;
+        struct hlist_head       chain;
+};
+
+/* This is for listening sockets, thus all sockets which possess wildcards. */
+#define INET_LHTABLE_SIZE       32      /* Yes, really, this is all you need. */
+
+struct inet_hashinfo {
+        /* This is for sockets with full identity only.  Sockets here will
+         * always be without wildcards and will have the following invariant:
+         *
+         *          TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
+         *
+         * First half of the table is for sockets not in TIME_WAIT, second half
+         * is for TIME_WAIT sockets only.
+         */
+        struct inet_ehash_bucket        *ehash;
+
+        /* Ok, let's try this, I give up, we do need a local binding
+         * TCP hash as well as the others for fast bind/connect.
+         */
+        struct inet_bind_hashbucket     *bhash;
+
+        int                             bhash_size;
+        int                             ehash_size;
+
+        /* All sockets in TCP_LISTEN state will be in here.  This is the only
+         * table where wildcard'd TCP sockets can exist.  Hash function here
+         * is just local port number.
+         */
+        struct hlist_head               listening_hash[INET_LHTABLE_SIZE];
+
+        /* All the above members are written once at bootup and
+         * never written again _or_ are predominantly read-access.
+         *
+         * Now align to a new cache line as all the following members
+         * are often dirty.
+         */
+        rwlock_t                        lhash_lock ____cacheline_aligned;
+        atomic_t                        lhash_users;
+        wait_queue_head_t               lhash_wait;
+        spinlock_t                      portalloc_lock;
+        kmem_cache_t                    *bind_bucket_cachep;
+        int                             port_rover;
+};
+
+static inline int inet_ehashfn(const __u32 laddr, const __u16 lport,
+                               const __u32 faddr, const __u16 fport,
+                               const int ehash_size)
+{
+        int h = (laddr ^ lport) ^ (faddr ^ fport);
+        h ^= h >> 16;
+        h ^= h >> 8;
+        return h & (ehash_size - 1);
+}
+
+static inline int inet_sk_ehashfn(const struct sock *sk, const int ehash_size)
+{
+        const struct inet_sock *inet = inet_sk(sk);
+        const __u32 laddr = inet->rcv_saddr;
+        const __u16 lport = inet->num;
+        const __u32 faddr = inet->daddr;
+        const __u16 fport = inet->dport;
+
+        return inet_ehashfn(laddr, lport, faddr, fport, ehash_size);
+}
+
+extern struct inet_bind_bucket *
+                    inet_bind_bucket_create(kmem_cache_t *cachep,
+                                            struct inet_bind_hashbucket *head,
+                                            const unsigned short snum);
+extern void inet_bind_bucket_destroy(kmem_cache_t *cachep,
+                                     struct inet_bind_bucket *tb);
+
+static inline int inet_bhashfn(const __u16 lport, const int bhash_size)
+{
+        return lport & (bhash_size - 1);
+}
+
+extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
+                           const unsigned short snum);
+
+/* These can have wildcards, don't try too hard. */
+static inline int inet_lhashfn(const unsigned short num)
+{
+        return num & (INET_LHTABLE_SIZE - 1);
+}
+
+static inline int inet_sk_listen_hashfn(const struct sock *sk)
+{
+        return inet_lhashfn(inet_sk(sk)->num);
+}
+
+/* Caller must disable local BH processing. */
+static inline void __inet_inherit_port(struct inet_hashinfo *table,
+                                       struct sock *sk, struct sock *child)
+{
+        const int bhash = inet_bhashfn(inet_sk(child)->num, table->bhash_size);
+        struct inet_bind_hashbucket *head = &table->bhash[bhash];
+        struct inet_bind_bucket *tb;
+
+        spin_lock(&head->lock);
+        tb = inet_csk(sk)->icsk_bind_hash;
+        sk_add_bind_node(child, &tb->owners);
+        inet_csk(child)->icsk_bind_hash = tb;
+        spin_unlock(&head->lock);
+}
+
+static inline void inet_inherit_port(struct inet_hashinfo *table,
+                                     struct sock *sk, struct sock *child)
+{
+        local_bh_disable();
+        __inet_inherit_port(table, sk, child);
+        local_bh_enable();
+}
+
+extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk);
+
+extern void inet_listen_wlock(struct inet_hashinfo *hashinfo);
+
+/*
+ * - We may sleep inside this lock.
+ * - If sleeping is not required (or called from BH),
+ *   use plain read_(un)lock(&inet_hashinfo.lhash_lock).
+ */
+static inline void inet_listen_lock(struct inet_hashinfo *hashinfo)
+{
+        /* read_lock synchronizes to candidates to writers */
+        read_lock(&hashinfo->lhash_lock);
+        atomic_inc(&hashinfo->lhash_users);
+        read_unlock(&hashinfo->lhash_lock);
+}
+
+static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo)
+{
+        if (atomic_dec_and_test(&hashinfo->lhash_users))
+                wake_up(&hashinfo->lhash_wait);
+}
+
+static inline void __inet_hash(struct inet_hashinfo *hashinfo,
+                               struct sock *sk, const int listen_possible)
+{
+        struct hlist_head *list;
+        rwlock_t *lock;
+
+        BUG_TRAP(sk_unhashed(sk));
+        if (listen_possible && sk->sk_state == TCP_LISTEN) {
+                list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+                lock = &hashinfo->lhash_lock;
+                inet_listen_wlock(hashinfo);
+        } else {
+                sk->sk_hashent = inet_sk_ehashfn(sk, hashinfo->ehash_size);
+                list = &hashinfo->ehash[sk->sk_hashent].chain;
+                lock = &hashinfo->ehash[sk->sk_hashent].lock;
+                write_lock(lock);
+        }
+        __sk_add_node(sk, list);
+        sock_prot_inc_use(sk->sk_prot);
+        write_unlock(lock);
+        if (listen_possible && sk->sk_state == TCP_LISTEN)
+                wake_up(&hashinfo->lhash_wait);
+}
+
+static inline void inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
+{
+        if (sk->sk_state != TCP_CLOSE) {
+                local_bh_disable();
+                __inet_hash(hashinfo, sk, 1);
+                local_bh_enable();
+        }
+}
+
+static inline void inet_unhash(struct inet_hashinfo *hashinfo, struct sock *sk)
+{
+        rwlock_t *lock;
+
+        if (sk_unhashed(sk))
+                goto out;
+
+        if (sk->sk_state == TCP_LISTEN) {
+                local_bh_disable();
+                inet_listen_wlock(hashinfo);
+                lock = &hashinfo->lhash_lock;
+        } else {
+                struct inet_ehash_bucket *head = &hashinfo->ehash[sk->sk_hashent];
+                lock = &head->lock;
+                write_lock_bh(&head->lock);
+        }
+
+        if (__sk_del_node_init(sk))
+                sock_prot_dec_use(sk->sk_prot);
+        write_unlock_bh(lock);
+out:
+        if (sk->sk_state == TCP_LISTEN)
+                wake_up(&hashinfo->lhash_wait);
+}
+
+static inline int inet_iif(const struct sk_buff *skb)
+{
+        return ((struct rtable *)skb->dst)->rt_iif;
+}
+
+extern struct sock *__inet_lookup_listener(const struct hlist_head *head,
+                                           const u32 daddr,
+                                           const unsigned short hnum,
+                                           const int dif);
+
+/* Optimize the common listener case. */
+static inline struct sock *
+                inet_lookup_listener(struct inet_hashinfo *hashinfo,
+                                     const u32 daddr,
+                                     const unsigned short hnum, const int dif)
+{
+        struct sock *sk = NULL;
+        const struct hlist_head *head;
+
+        read_lock(&hashinfo->lhash_lock);
+        head = &hashinfo->listening_hash[inet_lhashfn(hnum)];
+        if (!hlist_empty(head)) {
+                const struct inet_sock *inet = inet_sk((sk = __sk_head(head)));
+
+                if (inet->num == hnum && !sk->sk_node.next &&
+                    (!inet->rcv_saddr || inet->rcv_saddr == daddr) &&
+                    (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) &&
+                    !sk->sk_bound_dev_if)
+                        goto sherry_cache;
+                sk = __inet_lookup_listener(head, daddr, hnum, dif);
+        }
+        if (sk) {
+sherry_cache:
+                sock_hold(sk);
+        }
+        read_unlock(&hashinfo->lhash_lock);
+        return sk;
+}
+
+/* Socket demux engine toys. */
+#ifdef __BIG_ENDIAN
+#define INET_COMBINED_PORTS(__sport, __dport) \
+        (((__u32)(__sport) << 16) | (__u32)(__dport))
+#else /* __LITTLE_ENDIAN */
+#define INET_COMBINED_PORTS(__sport, __dport) \
+        (((__u32)(__dport) << 16) | (__u32)(__sport))
+#endif
+
+#if (BITS_PER_LONG == 64)
+#ifdef __BIG_ENDIAN
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+        const __u64 __name = (((__u64)(__saddr)) << 32) | ((__u64)(__daddr));
+#else /* __LITTLE_ENDIAN */
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+        const __u64 __name = (((__u64)(__daddr)) << 32) | ((__u64)(__saddr));
+#endif /* __BIG_ENDIAN */
+#define INET_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
+        (((*((__u64 *)&(inet_sk(__sk)->daddr))) == (__cookie))  &&      \
+         ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports))   &&      \
+         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
+        (((*((__u64 *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) &&  \
+         ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) &&   \
+         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#else /* 32-bit arch */
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr)
+#define INET_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)    \
+        ((inet_sk(__sk)->daddr          == (__saddr))           &&      \
+         (inet_sk(__sk)->rcv_saddr      == (__daddr))           &&      \
+         ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports))   &&      \
+         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif) \
+        ((inet_twsk(__sk)->tw_daddr     == (__saddr))           &&      \
+         (inet_twsk(__sk)->tw_rcv_saddr == (__daddr))           &&      \
+         ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) &&   \
+         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#endif /* 64-bit arch */
+
+/*
+ * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
+ * not check it for lookups anymore, thanks Alexey. -DaveM
+ *
+ * Local BH must be disabled here.
+ */
+static inline struct sock *
+        __inet_lookup_established(struct inet_hashinfo *hashinfo,
+                                  const u32 saddr, const u16 sport,
+                                  const u32 daddr, const u16 hnum,
+                                  const int dif)
+{
+        INET_ADDR_COOKIE(acookie, saddr, daddr)
+        const __u32 ports = INET_COMBINED_PORTS(sport, hnum);
+        struct sock *sk;
+        const struct hlist_node *node;
+        /* Optimize here for direct hit, only listening connections can
+         * have wildcards anyways.
+         */
+        const int hash = inet_ehashfn(daddr, hnum, saddr, sport, hashinfo->ehash_size);
+        struct inet_ehash_bucket *head = &hashinfo->ehash[hash];
+
+        read_lock(&head->lock);
+        sk_for_each(sk, node, &head->chain) {
+                if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif))
+                        goto hit; /* You sunk my battleship! */
+        }
+
+        /* Must check for a TIME_WAIT'er before going to listener hash. */
+        sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) {
+                if (INET_TW_MATCH(sk, acookie, saddr, daddr, ports, dif))
+                        goto hit;
+        }
+        sk = NULL;
+out:
+        read_unlock(&head->lock);
+        return sk;
+hit:
+        sock_hold(sk);
+        goto out;
+}
+
+static inline struct sock *__inet_lookup(struct inet_hashinfo *hashinfo,
+                                         const u32 saddr, const u16 sport,
+                                         const u32 daddr, const u16 hnum,
+                                         const int dif)
+{
+        struct sock *sk = __inet_lookup_established(hashinfo, saddr, sport, daddr,
+                                                    hnum, dif);
+        return sk ? : inet_lookup_listener(hashinfo, daddr, hnum, dif);
+}
+
+static inline struct sock *inet_lookup(struct inet_hashinfo *hashinfo,
+                                       const u32 saddr, const u16 sport,
+                                       const u32 daddr, const u16 dport,
+                                       const int dif)
+{
+        struct sock *sk;
+
+        local_bh_disable();
+        sk = __inet_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif);
+        local_bh_enable();
+
+        return sk;
+}
+#endif /* _INET_HASHTABLES_H */
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
new file mode 100644
index 000000000000..3b070352e869
--- /dev/null
+++ b/include/net/inet_timewait_sock.h
@@ -0,0 +1,219 @@
+/*
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the  BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ *              Definitions for a generic INET TIMEWAIT sock
+ *
+ *              From code originally in net/tcp.h
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ */
+#ifndef _INET_TIMEWAIT_SOCK_
+#define _INET_TIMEWAIT_SOCK_
+
+#include <linux/config.h>
+
+#include <linux/ip.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include <net/sock.h>
+#include <net/tcp_states.h>
+
+#include <asm/atomic.h>
+
+struct inet_hashinfo;
+
+#define INET_TWDR_RECYCLE_SLOTS_LOG     5
+#define INET_TWDR_RECYCLE_SLOTS         (1 << INET_TWDR_RECYCLE_SLOTS_LOG)
+
+/*
+ * If time > 4sec, it is "slow" path, no recycling is required,
+ * so that we select tick to get range about 4 seconds.
+ */
+#if HZ <= 16 || HZ > 4096
+# error Unsupported: HZ <= 16 or HZ > 4096
+#elif HZ <= 32
+# define INET_TWDR_RECYCLE_TICK (5 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#elif HZ <= 64
+# define INET_TWDR_RECYCLE_TICK (6 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#elif HZ <= 128
+# define INET_TWDR_RECYCLE_TICK (7 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#elif HZ <= 256
+# define INET_TWDR_RECYCLE_TICK (8 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#elif HZ <= 512
+# define INET_TWDR_RECYCLE_TICK (9 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#elif HZ <= 1024
+# define INET_TWDR_RECYCLE_TICK (10 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#elif HZ <= 2048
+# define INET_TWDR_RECYCLE_TICK (11 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#else
+# define INET_TWDR_RECYCLE_TICK (12 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
+#endif
+
+/* TIME_WAIT reaping mechanism. */
+#define INET_TWDR_TWKILL_SLOTS  8 /* Please keep this a power of 2. */
+
+#define INET_TWDR_TWKILL_QUOTA 100
+
+struct inet_timewait_death_row {
+        /* Short-time timewait calendar */
+        int                     twcal_hand;
+        int                     twcal_jiffie;
+        struct timer_list       twcal_timer;
+        struct hlist_head       twcal_row[INET_TWDR_RECYCLE_SLOTS];
+
+        spinlock_t              death_lock;
+        int                     tw_count;
+        int                     period;
+        u32                     thread_slots;
+        struct work_struct      twkill_work;
+        struct timer_list       tw_timer;
+        int                     slot;
+        struct hlist_head       cells[INET_TWDR_TWKILL_SLOTS];
+        struct inet_hashinfo    *hashinfo;
+        int                     sysctl_tw_recycle;
+        int                     sysctl_max_tw_buckets;
+};
+
+extern void inet_twdr_hangman(unsigned long data);
+extern void inet_twdr_twkill_work(void *data);
+extern void inet_twdr_twcal_tick(unsigned long data);
+
+#if (BITS_PER_LONG == 64)
+#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 8
+#else
+#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 4
+#endif
+
+struct inet_bind_bucket;
+
+/*
+ * This is a TIME_WAIT sock. It works around the memory consumption
+ * problems of sockets in such a state on heavily loaded servers, but
+ * without violating the protocol specification.
+ */
+struct inet_timewait_sock {
+        /*
+         * Now struct sock also uses sock_common, so please just
+         * don't add nothing before this first member (__tw_common) --acme
+         */
+        struct sock_common      __tw_common;
+#define tw_family               __tw_common.skc_family
+#define tw_state                __tw_common.skc_state
+#define tw_reuse                __tw_common.skc_reuse
+#define tw_bound_dev_if         __tw_common.skc_bound_dev_if
+#define tw_node                 __tw_common.skc_node
+#define tw_bind_node            __tw_common.skc_bind_node
+#define tw_refcnt               __tw_common.skc_refcnt
+#define tw_prot                 __tw_common.skc_prot
+        volatile unsigned char  tw_substate;
+        /* 3 bits hole, try to pack */
+        unsigned char           tw_rcv_wscale;
+        /* Socket demultiplex comparisons on incoming packets. */
+        /* these five are in inet_sock */
+        __u16                   tw_sport;
+        __u32                   tw_daddr __attribute__((aligned(INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES)));
+        __u32                   tw_rcv_saddr;
+        __u16                   tw_dport;
+        __u16                   tw_num;
+        /* And these are ours. */
+        __u8                    tw_ipv6only:1;
+        /* 31 bits hole, try to pack */
+        int                     tw_hashent;
+        int                     tw_timeout;
+        unsigned long           tw_ttd;
+        struct inet_bind_bucket *tw_tb;
+        struct hlist_node       tw_death_node;
+};
+
+static inline void inet_twsk_add_node(struct inet_timewait_sock *tw,
+                                      struct hlist_head *list)
+{
+        hlist_add_head(&tw->tw_node, list);
+}
+
+static inline void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
+                                           struct hlist_head *list)
+{
+        hlist_add_head(&tw->tw_bind_node, list);
+}
+
+static inline int inet_twsk_dead_hashed(const struct inet_timewait_sock *tw)
+{
+        return tw->tw_death_node.pprev != NULL;
+}
+
+static inline void inet_twsk_dead_node_init(struct inet_timewait_sock *tw)
+{
+        tw->tw_death_node.pprev = NULL;
+}
+
+static inline void __inet_twsk_del_dead_node(struct inet_timewait_sock *tw)
+{
+        __hlist_del(&tw->tw_death_node);
+        inet_twsk_dead_node_init(tw);
+}
+
+static inline int inet_twsk_del_dead_node(struct inet_timewait_sock *tw)
+{
+        if (inet_twsk_dead_hashed(tw)) {
+                __inet_twsk_del_dead_node(tw);
+                return 1;
+        }
+        return 0;
+}
+
+#define inet_twsk_for_each(tw, node, head) \
+        hlist_for_each_entry(tw, node, head, tw_node)
+
+#define inet_twsk_for_each_inmate(tw, node, jail) \
+        hlist_for_each_entry(tw, node, jail, tw_death_node)
+
+#define inet_twsk_for_each_inmate_safe(tw, node, safe, jail) \
+        hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node)
+
+static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
+{
+        return (struct inet_timewait_sock *)sk;
+}
+
+static inline u32 inet_rcv_saddr(const struct sock *sk)
+{
+        return likely(sk->sk_state != TCP_TIME_WAIT) ?
+                inet_sk(sk)->rcv_saddr : inet_twsk(sk)->tw_rcv_saddr;
+}
+
+static inline void inet_twsk_put(struct inet_timewait_sock *tw)
+{
+        if (atomic_dec_and_test(&tw->tw_refcnt)) {
+#ifdef SOCK_REFCNT_DEBUG
+                printk(KERN_DEBUG "%s timewait_sock %p released\n",
+                       tw->tw_prot->name, tw);
+#endif
+                kmem_cache_free(tw->tw_prot->twsk_slab, tw);
+        }
+}
+
+extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
+                                                  const int state);
+
+extern void __inet_twsk_kill(struct inet_timewait_sock *tw,
+                             struct inet_hashinfo *hashinfo);
+
+extern void __inet_twsk_hashdance(struct inet_timewait_sock *tw,
+                                  struct sock *sk,
+                                  struct inet_hashinfo *hashinfo);
+
+extern void inet_twsk_schedule(struct inet_timewait_sock *tw,
+                               struct inet_timewait_death_row *twdr,
+                               const int timeo, const int timewait_len);
+extern void inet_twsk_deschedule(struct inet_timewait_sock *tw,
+                                 struct inet_timewait_death_row *twdr);
+#endif  /* _INET_TIMEWAIT_SOCK_ */
diff --git a/include/net/ip.h b/include/net/ip.h
index 32360bbe143f..e4563bbee6ea 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -86,7 +86,7 @@ extern int		ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
                                               u32 saddr, u32 daddr,
                                               struct ip_options *opt);
 extern int              ip_rcv(struct sk_buff *skb, struct net_device *dev,
-                               struct packet_type *pt);
+                               struct packet_type *pt, struct net_device *orig_dev);
 extern int              ip_local_deliver(struct sk_buff *skb);
 extern int              ip_mr_input(struct sk_buff *skb);
 extern int              ip_output(struct sk_buff *skb);
@@ -140,8 +140,6 @@ struct ip_reply_arg {
 void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg,
                    unsigned int len); 
 
-extern int ip_finish_output(struct sk_buff *skb);
-
 struct ipv4_config
 {
         int     log_martians;
@@ -165,6 +163,24 @@ extern int sysctl_local_port_range[2];
 extern int sysctl_ip_default_ttl;
 extern int sysctl_ip_nonlocal_bind;
 
+/* From ip_fragment.c */
+extern int sysctl_ipfrag_high_thresh; 
+extern int sysctl_ipfrag_low_thresh;
+extern int sysctl_ipfrag_time;
+extern int sysctl_ipfrag_secret_interval;
+
+/* From inetpeer.c */
+extern int inet_peer_threshold;
+extern int inet_peer_minttl;
+extern int inet_peer_maxttl;
+extern int inet_peer_gc_mintime;
+extern int inet_peer_gc_maxtime;
+
+/* From ip_output.c */
+extern int sysctl_ip_dynaddr;
+
+extern void ipfrag_init(void);
+
 #ifdef CONFIG_INET
 /* The function in 2.2 was invalid, producing wrong result for
  * check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */
@@ -319,7 +335,10 @@ extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt, u32 da
 extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
 extern void ip_options_fragment(struct sk_buff *skb);
 extern int ip_options_compile(struct ip_options *opt, struct sk_buff *skb);
-extern int ip_options_get(struct ip_options **optp, unsigned char *data, int optlen, int user);
+extern int ip_options_get(struct ip_options **optp,
+                          unsigned char *data, int optlen);
+extern int ip_options_get_from_user(struct ip_options **optp,
+                                    unsigned char __user *data, int optlen);
 extern void ip_options_undo(struct ip_options * opt);
 extern void ip_forward_options(struct sk_buff *skb);
 extern int ip_options_rcv_srr(struct sk_buff *skb);
@@ -350,5 +369,10 @@ int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen,
                                   void __user *oldval, size_t __user *oldlenp,
                                   void __user *newval, size_t newlen, 
                                   void **context);
+#ifdef CONFIG_PROC_FS
+extern int ip_misc_proc_init(void);
+#endif
+
+extern struct ctl_table ipv4_table[];
 
 #endif  /* _IP_H */
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index f920706d526b..1f2e428ca364 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -12,7 +12,6 @@
 #include <net/flow.h>
 #include <net/ip6_fib.h>
 #include <net/sock.h>
-#include <linux/tcp.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a4208a336ac0..14de4ebd1211 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -295,4 +295,9 @@ static inline void fib_res_put(struct fib_result *res)
 #endif
 }
 
+#ifdef CONFIG_PROC_FS
+extern int  fib_proc_init(void);
+extern void fib_proc_exit(void);
+#endif
+
 #endif  /* _NET_FIB_H */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 52da5d26617a..7a3c43711a17 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -255,7 +255,6 @@ struct ip_vs_daemon_user {
 #include <asm/atomic.h>                 /* for struct atomic_t */
 #include <linux/netdevice.h>            /* for struct neighbour */
 #include <net/dst.h>                    /* for struct dst_entry */
-#include <net/tcp.h>
 #include <net/udp.h>
 #include <linux/compiler.h>
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 69324465e8b3..3203eaff4bd4 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -104,6 +104,7 @@ struct frag_hdr {
 
 #ifdef __KERNEL__
 
+#include <linux/config.h>
 #include <net/sock.h>
 
 /* sysctls */
@@ -145,7 +146,6 @@ DECLARE_SNMP_STAT(struct udp_mib, udp_stats_in6);
 #define UDP6_INC_STATS(field)           SNMP_INC_STATS(udp_stats_in6, field)
 #define UDP6_INC_STATS_BH(field)        SNMP_INC_STATS_BH(udp_stats_in6, field)
 #define UDP6_INC_STATS_USER(field)      SNMP_INC_STATS_USER(udp_stats_in6, field)
-extern atomic_t                 inet6_sock_nr;
 
 int snmp6_register_dev(struct inet6_dev *idev);
 int snmp6_unregister_dev(struct inet6_dev *idev);
@@ -346,7 +346,8 @@ static inline int ipv6_addr_any(const struct in6_addr *a)
 
 extern int                      ipv6_rcv(struct sk_buff *skb, 
                                          struct net_device *dev, 
-                                         struct packet_type *pt);
+                                         struct packet_type *pt,
+                                         struct net_device *orig_dev);
 
 /*
  *      upper-layer output functions
@@ -464,8 +465,38 @@ extern int sysctl_ip6frag_low_thresh;
 extern int sysctl_ip6frag_time;
 extern int sysctl_ip6frag_secret_interval;
 
-#endif /* __KERNEL__ */
-#endif /* _NET_IPV6_H */
+extern struct proto_ops inet6_stream_ops;
+extern struct proto_ops inet6_dgram_ops;
+
+extern int ip6_mc_source(int add, int omode, struct sock *sk,
+                         struct group_source_req *pgsr);
+extern int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf);
+extern int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
+                         struct group_filter __user *optval,
+                         int __user *optlen);
+
+#ifdef CONFIG_PROC_FS
+extern int  ac6_proc_init(void);
+extern void ac6_proc_exit(void);
+extern int  raw6_proc_init(void);
+extern void raw6_proc_exit(void);
+extern int  tcp6_proc_init(void);
+extern void tcp6_proc_exit(void);
+extern int  udp6_proc_init(void);
+extern void udp6_proc_exit(void);
+extern int  ipv6_misc_proc_init(void);
+extern void ipv6_misc_proc_exit(void);
+
+extern struct rt6_statistics rt6_stats;
+#endif
 
+#ifdef CONFIG_SYSCTL
+extern ctl_table ipv6_route_table[];
+extern ctl_table ipv6_icmp_table[];
 
+extern void ipv6_sysctl_register(void);
+extern void ipv6_sysctl_unregister(void);
+#endif
 
+#endif /* __KERNEL__ */
+#endif /* _NET_IPV6_H */
diff --git a/include/net/llc.h b/include/net/llc.h
index c9aed2a8b4e2..71769a5aeef3 100644
--- a/include/net/llc.h
+++ b/include/net/llc.h
@@ -46,7 +46,8 @@ struct llc_sap {
         unsigned char    f_bit;
         int              (*rcv_func)(struct sk_buff *skb,
                                      struct net_device *dev,
-                                     struct packet_type *pt);
+                                     struct packet_type *pt,
+                                     struct net_device *orig_dev);
         struct llc_addr  laddr;
         struct list_head node;
         struct {
@@ -64,7 +65,7 @@ extern rwlock_t llc_sap_list_lock;
 extern unsigned char llc_station_mac_sa[ETH_ALEN];
 
 extern int llc_rcv(struct sk_buff *skb, struct net_device *dev,
-                   struct packet_type *pt);
+                   struct packet_type *pt, struct net_device *orig_dev);
 
 extern int llc_mac_hdr_init(struct sk_buff *skb,
                             unsigned char *sa, unsigned char *da);
@@ -78,7 +79,8 @@ extern void llc_set_station_handler(void (*handler)(struct sk_buff *skb));
 extern struct llc_sap *llc_sap_open(unsigned char lsap,
                                     int (*rcv)(struct sk_buff *skb,
                                                struct net_device *dev,
-                                               struct packet_type *pt));
+                                               struct packet_type *pt,
+                                               struct net_device *orig_dev));
 extern void llc_sap_close(struct llc_sap *sap);
 
 extern struct llc_sap *llc_sap_find(unsigned char sap_value);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 89809891e5ab..34c07731933d 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -363,7 +363,14 @@ __neigh_lookup_errno(struct neigh_table *tbl, const void *pkey,
         return neigh_create(tbl, pkey, dev);
 }
 
-#define LOCALLY_ENQUEUED -2
+struct neighbour_cb {
+        unsigned long sched_next;
+        unsigned int flags;
+};
+
+#define LOCALLY_ENQUEUED 0x1
+
+#define NEIGH_CB(skb)   ((struct neighbour_cb *)(skb)->cb)
 
 #endif
 #endif
diff --git a/include/net/p8022.h b/include/net/p8022.h
index 3c99a86c3581..42e9fac51b31 100644
--- a/include/net/p8022.h
+++ b/include/net/p8022.h
@@ -4,7 +4,10 @@ extern struct datalink_proto *
         register_8022_client(unsigned char type,
                              int (*func)(struct sk_buff *skb,
                                          struct net_device *dev,
-                                         struct packet_type *pt));
+                                         struct packet_type *pt,
+                                         struct net_device *orig_dev));
 extern void unregister_8022_client(struct datalink_proto *proto);
 
+extern struct datalink_proto *make_8023_client(void);
+extern void destroy_8023_client(struct datalink_proto *dl);
 #endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 4abda6aec05a..b902d24a3256 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -352,10 +352,10 @@ tcf_change_indev(struct tcf_proto *tp, char *indev, struct rtattr *indev_tlv)
 static inline int
 tcf_match_indev(struct sk_buff *skb, char *indev)
 {
-        if (0 != indev[0]) {
-                if  (NULL == skb->input_dev)
+        if (indev[0]) {
+                if  (!skb->input_dev)
                         return 0;
-                else if (0 != strcmp(indev, skb->input_dev->name))
+                if (strcmp(indev, skb->input_dev->name))
                         return 0;
         }
 
diff --git a/include/net/psnap.h b/include/net/psnap.h
index 9c94e8f98b36..b2e01cc3fc8a 100644
--- a/include/net/psnap.h
+++ b/include/net/psnap.h
@@ -1,7 +1,7 @@
 #ifndef _NET_PSNAP_H
 #define _NET_PSNAP_H
 
-extern struct datalink_proto *register_snap_client(unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *));
+extern struct datalink_proto *register_snap_client(unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *orig_dev));
 extern void unregister_snap_client(struct datalink_proto *proto);
 
 #endif
diff --git a/include/net/raw.h b/include/net/raw.h
index 1c411c45587a..f47917469b12 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -17,10 +17,10 @@
 #ifndef _RAW_H
 #define _RAW_H
 
+#include <linux/config.h>
 
 extern struct proto raw_prot;
 
-
 extern void     raw_err(struct sock *, struct sk_buff *, u32 info);
 extern int      raw_rcv(struct sock *, struct sk_buff *);
 
@@ -37,6 +37,11 @@ extern struct sock *__raw_v4_lookup(struct sock *sk, unsigned short num,
                                     unsigned long raddr, unsigned long laddr,
                                     int dif);
 
-extern void raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash);
+extern int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash);
+
+#ifdef CONFIG_PROC_FS
+extern int  raw_proc_init(void);
+extern void raw_proc_exit(void);
+#endif
 
 #endif  /* _RAW_H */
diff --git a/include/net/rawv6.h b/include/net/rawv6.h
index 23fd9a6a221a..14476a71725e 100644
--- a/include/net/rawv6.h
+++ b/include/net/rawv6.h
@@ -7,10 +7,11 @@
 extern struct hlist_head raw_v6_htable[RAWV6_HTABLE_SIZE];
 extern rwlock_t raw_v6_lock;
 
-extern void ipv6_raw_deliver(struct sk_buff *skb, int nexthdr);
+extern int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr);
 
 extern struct sock *__raw_v6_lookup(struct sock *sk, unsigned short num,
-                                    struct in6_addr *loc_addr, struct in6_addr *rmt_addr);
+                                    struct in6_addr *loc_addr, struct in6_addr *rmt_addr,
+                                    int dif);
 
 extern int                      rawv6_rcv(struct sock *sk,
                                           struct sk_buff *skb);
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 72fd6f5e86b1..b52cc52ffe39 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -89,6 +89,7 @@ struct listen_sock {
         int                     qlen_young;
         int                     clock_hand;
         u32                     hash_rnd;
+        u32                     nr_table_entries;
         struct request_sock     *syn_table[0];
 };
 
@@ -96,6 +97,7 @@ struct listen_sock {
  *
  * @rskq_accept_head - FIFO head of established children
  * @rskq_accept_tail - FIFO tail of established children
+ * @rskq_defer_accept - User waits for some data after accept()
  * @syn_wait_lock - serializer
  *
  * %syn_wait_lock is necessary only to avoid proc interface having to grab the main
@@ -111,6 +113,8 @@ struct request_sock_queue {
         struct request_sock     *rskq_accept_head;
         struct request_sock     *rskq_accept_tail;
         rwlock_t                syn_wait_lock;
+        u8                      rskq_defer_accept;
+        /* 3 bytes hole, try to pack */
         struct listen_sock      *listen_opt;
 };
 
@@ -129,11 +133,13 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk(struct request_sock
         return lopt;
 }
 
-static inline void reqsk_queue_destroy(struct request_sock_queue *queue)
+static inline void __reqsk_queue_destroy(struct request_sock_queue *queue)
 {
         kfree(reqsk_queue_yank_listen_sk(queue));
 }
 
+extern void reqsk_queue_destroy(struct request_sock_queue *queue);
+
 static inline struct request_sock *
         reqsk_queue_yank_acceptq(struct request_sock_queue *queue)
 {
@@ -221,17 +227,17 @@ static inline int reqsk_queue_added(struct request_sock_queue *queue)
         return prev_qlen;
 }
 
-static inline int reqsk_queue_len(struct request_sock_queue *queue)
+static inline int reqsk_queue_len(const struct request_sock_queue *queue)
 {
         return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0;
 }
 
-static inline int reqsk_queue_len_young(struct request_sock_queue *queue)
+static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
 {
         return queue->listen_opt->qlen_young;
 }
 
-static inline int reqsk_queue_is_full(struct request_sock_queue *queue)
+static inline int reqsk_queue_is_full(const struct request_sock_queue *queue)
 {
         return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log;
 }
diff --git a/include/net/route.h b/include/net/route.h
index c3cd069a9aca..dbe79ca67d31 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -105,10 +105,6 @@ struct rt_cache_stat
         unsigned int out_hlist_search;
 };
 
-extern struct rt_cache_stat *rt_cache_stat;
-#define RT_CACHE_STAT_INC(field)                                          \
-                (per_cpu_ptr(rt_cache_stat, raw_smp_processor_id())->field++)
-
 extern struct ip_rt_acct *ip_rt_acct;
 
 struct in_device;
@@ -199,4 +195,6 @@ static inline struct inet_peer *rt_get_peer(struct rtable *rt)
         return rt->peer;
 }
 
+extern ctl_table ipv4_route_table[];
+
 #endif  /* _ROUTE_H */
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 5999e5684bbf..c51541ee0247 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -47,10 +47,10 @@
 #ifndef __sctp_constants_h__
 #define __sctp_constants_h__
 
-#include <linux/tcp.h>  /* For TCP states used in sctp_sock_state_t */
 #include <linux/sctp.h>
 #include <linux/ipv6.h> /* For ipv6hdr. */
 #include <net/sctp/user.h>
+#include <net/tcp_states.h>  /* For TCP states used in sctp_sock_state_t */
 
 /* Value used for stream negotiation. */
 enum { SCTP_MAX_STREAM = 0xffff };
diff --git a/include/net/sock.h b/include/net/sock.h
index e9b1dbab90d0..312cb25cbd18 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -88,6 +88,7 @@ do {	spin_lock_init(&((__sk)->sk_lock.slock)); \
 } while(0)
 
 struct sock;
+struct proto;
 
 /**
  *      struct sock_common - minimal network layer representation of sockets
@@ -98,10 +99,11 @@ struct sock;
  *      @skc_node: main hash linkage for various protocol lookup tables
  *      @skc_bind_node: bind hash linkage for various protocol lookup tables
  *      @skc_refcnt: reference count
+ *      @skc_prot: protocol handlers inside a network family
  *
  *      This is the minimal network layer representation of sockets, the header
- *      for struct sock and struct tcp_tw_bucket.
-  */
+ *      for struct sock and struct inet_timewait_sock.
+ */
 struct sock_common {
         unsigned short          skc_family;
         volatile unsigned char  skc_state;
@@ -110,11 +112,12 @@ struct sock_common {
         struct hlist_node       skc_node;
         struct hlist_node       skc_bind_node;
         atomic_t                skc_refcnt;
+        struct proto            *skc_prot;
 };
 
 /**
   *     struct sock - network layer representation of sockets
-  *     @__sk_common: shared layout with tcp_tw_bucket
+  *     @__sk_common: shared layout with inet_timewait_sock
   *     @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
   *     @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
   *     @sk_lock:       synchronizer
@@ -136,11 +139,10 @@ struct sock_common {
   *     @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
   *     @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *     @sk_lingertime: %SO_LINGER l_linger setting
-  *     @sk_hashent: hash entry in several tables (e.g. tcp_ehash)
+  *     @sk_hashent: hash entry in several tables (e.g. inet_hashinfo.ehash)
   *     @sk_backlog: always used with the per-socket spinlock held
   *     @sk_callback_lock: used with the callbacks in the end of this struct
   *     @sk_error_queue: rarely used
-  *     @sk_prot: protocol handlers inside a network family
   *     @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, IPV6_ADDRFORM for instance)
   *     @sk_err: last error
   *     @sk_err_soft: errors that don't cause failure but are the cause of a persistent failure not just 'timed out'
@@ -173,7 +175,7 @@ struct sock_common {
  */
 struct sock {
         /*
-         * Now struct tcp_tw_bucket also uses sock_common, so please just
+         * Now struct inet_timewait_sock also uses sock_common, so please just
          * don't add nothing before this first member (__sk_common) --acme
          */
         struct sock_common      __sk_common;
@@ -184,6 +186,7 @@ struct sock {
 #define sk_node                 __sk_common.skc_node
 #define sk_bind_node            __sk_common.skc_bind_node
 #define sk_refcnt               __sk_common.skc_refcnt
+#define sk_prot                 __sk_common.skc_prot
         unsigned char           sk_shutdown : 2,
                                 sk_no_check : 2,
                                 sk_userlocks : 4;
@@ -218,7 +221,6 @@ struct sock {
                 struct sk_buff *tail;
         } sk_backlog;
         struct sk_buff_head     sk_error_queue;
-        struct proto            *sk_prot;
         struct proto            *sk_prot_creator;
         rwlock_t                sk_callback_lock;
         int                     sk_err,
@@ -253,28 +255,28 @@ struct sock {
 /*
  * Hashed lists helper routines
  */
-static inline struct sock *__sk_head(struct hlist_head *head)
+static inline struct sock *__sk_head(const struct hlist_head *head)
 {
         return hlist_entry(head->first, struct sock, sk_node);
 }
 
-static inline struct sock *sk_head(struct hlist_head *head)
+static inline struct sock *sk_head(const struct hlist_head *head)
 {
         return hlist_empty(head) ? NULL : __sk_head(head);
 }
 
-static inline struct sock *sk_next(struct sock *sk)
+static inline struct sock *sk_next(const struct sock *sk)
 {
         return sk->sk_node.next ?
                 hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
 }
 
-static inline int sk_unhashed(struct sock *sk)
+static inline int sk_unhashed(const struct sock *sk)
 {
         return hlist_unhashed(&sk->sk_node);
 }
 
-static inline int sk_hashed(struct sock *sk)
+static inline int sk_hashed(const struct sock *sk)
 {
         return sk->sk_node.pprev != NULL;
 }
@@ -554,6 +556,10 @@ struct proto {
         kmem_cache_t            *slab;
         unsigned int            obj_size;
 
+        kmem_cache_t            *twsk_slab;
+        unsigned int            twsk_obj_size;
+        atomic_t                *orphan_count;
+
         struct request_sock_ops *rsk_prot;
 
         struct module           *owner;
@@ -561,7 +567,9 @@ struct proto {
         char                    name[32];
 
         struct list_head        node;
-
+#ifdef SOCK_REFCNT_DEBUG
+        atomic_t                socks;
+#endif
         struct {
                 int inuse;
                 u8  __pad[SMP_CACHE_BYTES - sizeof(int)];
@@ -571,6 +579,31 @@ struct proto {
 extern int proto_register(struct proto *prot, int alloc_slab);
 extern void proto_unregister(struct proto *prot);
 
+#ifdef SOCK_REFCNT_DEBUG
+static inline void sk_refcnt_debug_inc(struct sock *sk)
+{
+        atomic_inc(&sk->sk_prot->socks);
+}
+
+static inline void sk_refcnt_debug_dec(struct sock *sk)
+{
+        atomic_dec(&sk->sk_prot->socks);
+        printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
+               sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
+}
+
+static inline void sk_refcnt_debug_release(const struct sock *sk)
+{
+        if (atomic_read(&sk->sk_refcnt) != 1)
+                printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
+                       sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
+}
+#else /* SOCK_REFCNT_DEBUG */
+#define sk_refcnt_debug_inc(sk) do { } while (0)
+#define sk_refcnt_debug_dec(sk) do { } while (0)
+#define sk_refcnt_debug_release(sk) do { } while (0)
+#endif /* SOCK_REFCNT_DEBUG */
+
 /* Called with local bh disabled */
 static __inline__ void sock_prot_inc_use(struct proto *prot)
 {
@@ -582,6 +615,15 @@ static __inline__ void sock_prot_dec_use(struct proto *prot)
         prot->stats[smp_processor_id()].inuse--;
 }
 
+/* With per-bucket locks this operation is not-atomic, so that
+ * this version is not worse.
+ */
+static inline void __sk_prot_rehash(struct sock *sk)
+{
+        sk->sk_prot->unhash(sk);
+        sk->sk_prot->hash(sk);
+}
+
 /* About 10 seconds */
 #define SOCK_DESTROY_TIME (10*HZ)
 
@@ -693,6 +735,8 @@ extern struct sock		*sk_alloc(int family,
                                           unsigned int __nocast priority,
                                           struct proto *prot, int zero_it);
 extern void                     sk_free(struct sock *sk);
+extern struct sock              *sk_clone(const struct sock *sk,
+                                          const unsigned int __nocast priority);
 
 extern struct sk_buff           *sock_wmalloc(struct sock *sk,
                                               unsigned long size, int force,
@@ -986,6 +1030,16 @@ sk_dst_check(struct sock *sk, u32 cookie)
         return dst;
 }
 
+static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
+{
+        __sk_dst_set(sk, dst);
+        sk->sk_route_caps = dst->dev->features;
+        if (sk->sk_route_caps & NETIF_F_TSO) {
+                if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
+                        sk->sk_route_caps &= ~NETIF_F_TSO;
+        }
+}
+
 static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb)
 {
         sk->sk_wmem_queued   += skb->truesize;
@@ -1146,7 +1200,7 @@ static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
         int hdr_len;
 
         hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
-        skb = alloc_skb(size + hdr_len, gfp);
+        skb = alloc_skb_fclone(size + hdr_len, gfp);
         if (skb) {
                 skb->truesize += mem;
                 if (sk->sk_forward_alloc >= (int)skb->truesize ||
@@ -1228,16 +1282,19 @@ static inline int sock_intr_errno(long timeo)
 static __inline__ void
 sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 {
-        struct timeval *stamp = &skb->stamp;
+        struct timeval stamp;
+
+        skb_get_timestamp(skb, &stamp);
         if (sock_flag(sk, SOCK_RCVTSTAMP)) {
                 /* Race occurred between timestamp enabling and packet
                    receiving.  Fill in the current time for now. */
-                if (stamp->tv_sec == 0)
-                        do_gettimeofday(stamp);
+                if (stamp.tv_sec == 0)
+                        do_gettimeofday(&stamp);
+                skb_set_timestamp(skb, &stamp);
                 put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval),
-                         stamp);
+                         &stamp);
         } else
-                sk->sk_stamp = *stamp;
+                sk->sk_stamp = stamp;
 }
 
 /**
@@ -1262,11 +1319,11 @@ extern int sock_get_timestamp(struct sock *, struct timeval __user *);
  */
 
 #if 0
-#define NETDEBUG(x)     do { } while (0)
-#define LIMIT_NETDEBUG(x) do {} while(0)
+#define NETDEBUG(fmt, args...)  do { } while (0)
+#define LIMIT_NETDEBUG(fmt, args...) do { } while(0)
 #else
-#define NETDEBUG(x)     do { x; } while (0)
-#define LIMIT_NETDEBUG(x) do { if (net_ratelimit()) { x; } } while(0)
+#define NETDEBUG(fmt, args...)  printk(fmt,##args)
+#define LIMIT_NETDEBUG(fmt, args...) do { if (net_ratelimit()) printk(fmt,##args); } while(0)
 #endif
 
 /*
@@ -1313,4 +1370,14 @@ static inline int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsign
 }
 #endif
 
+extern void sk_init(void);
+
+#ifdef CONFIG_SYSCTL
+extern struct ctl_table core_table[];
+extern int sysctl_optmem_max;
+#endif
+
+extern __u32 sysctl_wmem_default;
+extern __u32 sysctl_rmem_default;
+
 #endif  /* _SOCK_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5010f0c5a56e..d6bcf1317a6a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -21,360 +21,29 @@
 #define TCP_DEBUG 1
 #define FASTRETRANS_DEBUG 1
 
-/* Cancel timers, when they are not required. */
-#undef TCP_CLEAR_TIMERS
-
 #include <linux/config.h>
 #include <linux/list.h>
 #include <linux/tcp.h>
 #include <linux/slab.h>
 #include <linux/cache.h>
 #include <linux/percpu.h>
+
+#include <net/inet_connection_sock.h>
+#include <net/inet_timewait_sock.h>
+#include <net/inet_hashtables.h>
 #include <net/checksum.h>
 #include <net/request_sock.h>
 #include <net/sock.h>
 #include <net/snmp.h>
 #include <net/ip.h>
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
-#include <linux/ipv6.h>
-#endif
-#include <linux/seq_file.h>
-
-/* This is for all connections with a full identity, no wildcards.
- * New scheme, half the table is for TIME_WAIT, the other half is
- * for the rest.  I'll experiment with dynamic table growth later.
- */
-struct tcp_ehash_bucket {
-        rwlock_t          lock;
-        struct hlist_head chain;
-} __attribute__((__aligned__(8)));
-
-/* This is for listening sockets, thus all sockets which possess wildcards. */
-#define TCP_LHTABLE_SIZE        32      /* Yes, really, this is all you need. */
-
-/* There are a few simple rules, which allow for local port reuse by
- * an application.  In essence:
- *
- *      1) Sockets bound to different interfaces may share a local port.
- *         Failing that, goto test 2.
- *      2) If all sockets have sk->sk_reuse set, and none of them are in
- *         TCP_LISTEN state, the port may be shared.
- *         Failing that, goto test 3.
- *      3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
- *         address, and none of them are the same, the port may be
- *         shared.
- *         Failing this, the port cannot be shared.
- *
- * The interesting point, is test #2.  This is what an FTP server does
- * all day.  To optimize this case we use a specific flag bit defined
- * below.  As we add sockets to a bind bucket list, we perform a
- * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
- * As long as all sockets added to a bind bucket pass this test,
- * the flag bit will be set.
- * The resulting situation is that tcp_v[46]_verify_bind() can just check
- * for this flag bit, if it is set and the socket trying to bind has
- * sk->sk_reuse set, we don't even have to walk the owners list at all,
- * we return that it is ok to bind this socket to the requested local port.
- *
- * Sounds like a lot of work, but it is worth it.  In a more naive
- * implementation (ie. current FreeBSD etc.) the entire list of ports
- * must be walked for each data port opened by an ftp server.  Needless
- * to say, this does not scale at all.  With a couple thousand FTP
- * users logged onto your box, isn't it nice to know that new data
- * ports are created in O(1) time?  I thought so. ;-)   -DaveM
- */
-struct tcp_bind_bucket {
-        unsigned short          port;
-        signed short            fastreuse;
-        struct hlist_node       node;
-        struct hlist_head       owners;
-};
-
-#define tb_for_each(tb, node, head) hlist_for_each_entry(tb, node, head, node)
-
-struct tcp_bind_hashbucket {
-        spinlock_t              lock;
-        struct hlist_head       chain;
-};
-
-static inline struct tcp_bind_bucket *__tb_head(struct tcp_bind_hashbucket *head)
-{
-        return hlist_entry(head->chain.first, struct tcp_bind_bucket, node);
-}
-
-static inline struct tcp_bind_bucket *tb_head(struct tcp_bind_hashbucket *head)
-{
-        return hlist_empty(&head->chain) ? NULL : __tb_head(head);
-}
-
-extern struct tcp_hashinfo {
-        /* This is for sockets with full identity only.  Sockets here will
-         * always be without wildcards and will have the following invariant:
-         *
-         *          TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
-         *
-         * First half of the table is for sockets not in TIME_WAIT, second half
-         * is for TIME_WAIT sockets only.
-         */
-        struct tcp_ehash_bucket *__tcp_ehash;
-
-        /* Ok, let's try this, I give up, we do need a local binding
-         * TCP hash as well as the others for fast bind/connect.
-         */
-        struct tcp_bind_hashbucket *__tcp_bhash;
+#include <net/tcp_states.h>
 
-        int __tcp_bhash_size;
-        int __tcp_ehash_size;
-
-        /* All sockets in TCP_LISTEN state will be in here.  This is the only
-         * table where wildcard'd TCP sockets can exist.  Hash function here
-         * is just local port number.
-         */
-        struct hlist_head __tcp_listening_hash[TCP_LHTABLE_SIZE];
-
-        /* All the above members are written once at bootup and
-         * never written again _or_ are predominantly read-access.
-         *
-         * Now align to a new cache line as all the following members
-         * are often dirty.
-         */
-        rwlock_t __tcp_lhash_lock ____cacheline_aligned;
-        atomic_t __tcp_lhash_users;
-        wait_queue_head_t __tcp_lhash_wait;
-        spinlock_t __tcp_portalloc_lock;
-} tcp_hashinfo;
-
-#define tcp_ehash       (tcp_hashinfo.__tcp_ehash)
-#define tcp_bhash       (tcp_hashinfo.__tcp_bhash)
-#define tcp_ehash_size  (tcp_hashinfo.__tcp_ehash_size)
-#define tcp_bhash_size  (tcp_hashinfo.__tcp_bhash_size)
-#define tcp_listening_hash (tcp_hashinfo.__tcp_listening_hash)
-#define tcp_lhash_lock  (tcp_hashinfo.__tcp_lhash_lock)
-#define tcp_lhash_users (tcp_hashinfo.__tcp_lhash_users)
-#define tcp_lhash_wait  (tcp_hashinfo.__tcp_lhash_wait)
-#define tcp_portalloc_lock (tcp_hashinfo.__tcp_portalloc_lock)
-
-extern kmem_cache_t *tcp_bucket_cachep;
-extern struct tcp_bind_bucket *tcp_bucket_create(struct tcp_bind_hashbucket *head,
-                                                 unsigned short snum);
-extern void tcp_bucket_destroy(struct tcp_bind_bucket *tb);
-extern void tcp_bucket_unlock(struct sock *sk);
-extern int tcp_port_rover;
-
-/* These are AF independent. */
-static __inline__ int tcp_bhashfn(__u16 lport)
-{
-        return (lport & (tcp_bhash_size - 1));
-}
-
-extern void tcp_bind_hash(struct sock *sk, struct tcp_bind_bucket *tb,
-                          unsigned short snum);
-
-#if (BITS_PER_LONG == 64)
-#define TCP_ADDRCMP_ALIGN_BYTES 8
-#else
-#define TCP_ADDRCMP_ALIGN_BYTES 4
-#endif
-
-/* This is a TIME_WAIT bucket.  It works around the memory consumption
- * problems of sockets in such a state on heavily loaded servers, but
- * without violating the protocol specification.
- */
-struct tcp_tw_bucket {
-        /*
-         * Now struct sock also uses sock_common, so please just
-         * don't add nothing before this first member (__tw_common) --acme
-         */
-        struct sock_common      __tw_common;
-#define tw_family               __tw_common.skc_family
-#define tw_state                __tw_common.skc_state
-#define tw_reuse                __tw_common.skc_reuse
-#define tw_bound_dev_if         __tw_common.skc_bound_dev_if
-#define tw_node                 __tw_common.skc_node
-#define tw_bind_node            __tw_common.skc_bind_node
-#define tw_refcnt               __tw_common.skc_refcnt
-        volatile unsigned char  tw_substate;
-        unsigned char           tw_rcv_wscale;
-        __u16                   tw_sport;
-        /* Socket demultiplex comparisons on incoming packets. */
-        /* these five are in inet_sock */
-        __u32                   tw_daddr
-                __attribute__((aligned(TCP_ADDRCMP_ALIGN_BYTES)));
-        __u32                   tw_rcv_saddr;
-        __u16                   tw_dport;
-        __u16                   tw_num;
-        /* And these are ours. */
-        int                     tw_hashent;
-        int                     tw_timeout;
-        __u32                   tw_rcv_nxt;
-        __u32                   tw_snd_nxt;
-        __u32                   tw_rcv_wnd;
-        __u32                   tw_ts_recent;
-        long                    tw_ts_recent_stamp;
-        unsigned long           tw_ttd;
-        struct tcp_bind_bucket  *tw_tb;
-        struct hlist_node       tw_death_node;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-        struct in6_addr         tw_v6_daddr;
-        struct in6_addr         tw_v6_rcv_saddr;
-        int                     tw_v6_ipv6only;
-#endif
-};
-
-static __inline__ void tw_add_node(struct tcp_tw_bucket *tw,
-                                   struct hlist_head *list)
-{
-        hlist_add_head(&tw->tw_node, list);
-}
-
-static __inline__ void tw_add_bind_node(struct tcp_tw_bucket *tw,
-                                        struct hlist_head *list)
-{
-        hlist_add_head(&tw->tw_bind_node, list);
-}
-
-static inline int tw_dead_hashed(struct tcp_tw_bucket *tw)
-{
-        return tw->tw_death_node.pprev != NULL;
-}
-
-static __inline__ void tw_dead_node_init(struct tcp_tw_bucket *tw)
-{
-        tw->tw_death_node.pprev = NULL;
-}
-
-static __inline__ void __tw_del_dead_node(struct tcp_tw_bucket *tw)
-{
-        __hlist_del(&tw->tw_death_node);
-        tw_dead_node_init(tw);
-}
-
-static __inline__ int tw_del_dead_node(struct tcp_tw_bucket *tw)
-{
-        if (tw_dead_hashed(tw)) {
-                __tw_del_dead_node(tw);
-                return 1;
-        }
-        return 0;
-}
-
-#define tw_for_each(tw, node, head) \
-        hlist_for_each_entry(tw, node, head, tw_node)
-
-#define tw_for_each_inmate(tw, node, jail) \
-        hlist_for_each_entry(tw, node, jail, tw_death_node)
-
-#define tw_for_each_inmate_safe(tw, node, safe, jail) \
-        hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node)
-
-#define tcptw_sk(__sk)  ((struct tcp_tw_bucket *)(__sk))
-
-static inline u32 tcp_v4_rcv_saddr(const struct sock *sk)
-{
-        return likely(sk->sk_state != TCP_TIME_WAIT) ?
-                inet_sk(sk)->rcv_saddr : tcptw_sk(sk)->tw_rcv_saddr;
-}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk)
-{
-        return likely(sk->sk_state != TCP_TIME_WAIT) ?
-                &inet6_sk(sk)->rcv_saddr : &tcptw_sk(sk)->tw_v6_rcv_saddr;
-}
-
-static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk)
-{
-        return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL;
-}
-
-#define tcptw_sk_ipv6only(__sk) (tcptw_sk(__sk)->tw_v6_ipv6only)
-
-static inline int tcp_v6_ipv6only(const struct sock *sk)
-{
-        return likely(sk->sk_state != TCP_TIME_WAIT) ?
-                ipv6_only_sock(sk) : tcptw_sk_ipv6only(sk);
-}
-#else
-# define __tcp_v6_rcv_saddr(__sk)       NULL
-# define tcp_v6_rcv_saddr(__sk)         NULL
-# define tcptw_sk_ipv6only(__sk)        0
-# define tcp_v6_ipv6only(__sk)          0
-#endif
+#include <linux/seq_file.h>
 
-extern kmem_cache_t *tcp_timewait_cachep;
-
-static inline void tcp_tw_put(struct tcp_tw_bucket *tw)
-{
-        if (atomic_dec_and_test(&tw->tw_refcnt)) {
-#ifdef INET_REFCNT_DEBUG
-                printk(KERN_DEBUG "tw_bucket %p released\n", tw);
-#endif
-                kmem_cache_free(tcp_timewait_cachep, tw);
-        }
-}
+extern struct inet_hashinfo tcp_hashinfo;
 
 extern atomic_t tcp_orphan_count;
-extern int tcp_tw_count;
 extern void tcp_time_wait(struct sock *sk, int state, int timeo);
-extern void tcp_tw_deschedule(struct tcp_tw_bucket *tw);
-
-
-/* Socket demux engine toys. */
-#ifdef __BIG_ENDIAN
-#define TCP_COMBINED_PORTS(__sport, __dport) \
-        (((__u32)(__sport)<<16) | (__u32)(__dport))
-#else /* __LITTLE_ENDIAN */
-#define TCP_COMBINED_PORTS(__sport, __dport) \
-        (((__u32)(__dport)<<16) | (__u32)(__sport))
-#endif
-
-#if (BITS_PER_LONG == 64)
-#ifdef __BIG_ENDIAN
-#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \
-        __u64 __name = (((__u64)(__saddr))<<32)|((__u64)(__daddr));
-#else /* __LITTLE_ENDIAN */
-#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \
-        __u64 __name = (((__u64)(__daddr))<<32)|((__u64)(__saddr));
-#endif /* __BIG_ENDIAN */
-#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
-        (((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie))   &&      \
-         ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))    &&      \
-         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
-        (((*((__u64 *)&(tcptw_sk(__sk)->tw_daddr))) == (__cookie)) &&   \
-         ((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) &&    \
-         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#else /* 32-bit arch */
-#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr)
-#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
-        ((inet_sk(__sk)->daddr                  == (__saddr))   &&      \
-         (inet_sk(__sk)->rcv_saddr              == (__daddr))   &&      \
-         ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))    &&      \
-         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
-        ((tcptw_sk(__sk)->tw_daddr              == (__saddr))   &&      \
-         (tcptw_sk(__sk)->tw_rcv_saddr          == (__daddr))   &&      \
-         ((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) &&    \
-         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#endif /* 64-bit arch */
-
-#define TCP_IPV6_MATCH(__sk, __saddr, __daddr, __ports, __dif)     \
-        (((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))    && \
-         ((__sk)->sk_family             == AF_INET6)            && \
-         ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))     && \
-         ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \
-         (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-
-/* These can have wildcards, don't try too hard. */
-static __inline__ int tcp_lhashfn(unsigned short num)
-{
-        return num & (TCP_LHTABLE_SIZE - 1);
-}
-
-static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
-{
-        return tcp_lhashfn(inet_sk(sk)->num);
-}
 
 #define MAX_TCP_HEADER  (128 + MAX_HEADER)
 
@@ -478,33 +147,6 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
                                          * timestamps. It must be less than
                                          * minimal timewait lifetime.
                                          */
-
-#define TCP_TW_RECYCLE_SLOTS_LOG        5
-#define TCP_TW_RECYCLE_SLOTS            (1<<TCP_TW_RECYCLE_SLOTS_LOG)
-
-/* If time > 4sec, it is "slow" path, no recycling is required,
-   so that we select tick to get range about 4 seconds.
- */
-
-#if HZ <= 16 || HZ > 4096
-# error Unsupported: HZ <= 16 or HZ > 4096
-#elif HZ <= 32
-# define TCP_TW_RECYCLE_TICK (5+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 64
-# define TCP_TW_RECYCLE_TICK (6+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 128
-# define TCP_TW_RECYCLE_TICK (7+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 256
-# define TCP_TW_RECYCLE_TICK (8+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 512
-# define TCP_TW_RECYCLE_TICK (9+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 1024
-# define TCP_TW_RECYCLE_TICK (10+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 2048
-# define TCP_TW_RECYCLE_TICK (11+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#else
-# define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#endif
 /*
  *      TCP option
  */
@@ -534,22 +176,18 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
 #define TCPOLEN_SACK_BASE_ALIGNED       4
 #define TCPOLEN_SACK_PERBLOCK           8
 
-#define TCP_TIME_RETRANS        1       /* Retransmit timer */
-#define TCP_TIME_DACK           2       /* Delayed ack timer */
-#define TCP_TIME_PROBE0         3       /* Zero window probe timer */
-#define TCP_TIME_KEEPOPEN       4       /* Keepalive timer */
-
 /* Flags in tp->nonagle */
 #define TCP_NAGLE_OFF           1       /* Nagle's algo is disabled */
 #define TCP_NAGLE_CORK          2       /* Socket is corked         */
 #define TCP_NAGLE_PUSH          4       /* Cork is overriden for already queued data */
 
+extern struct inet_timewait_death_row tcp_death_row;
+
 /* sysctl variables for tcp */
 extern int sysctl_tcp_timestamps;
 extern int sysctl_tcp_window_scaling;
 extern int sysctl_tcp_sack;
 extern int sysctl_tcp_fin_timeout;
-extern int sysctl_tcp_tw_recycle;
 extern int sysctl_tcp_keepalive_time;
 extern int sysctl_tcp_keepalive_probes;
 extern int sysctl_tcp_keepalive_intvl;
@@ -564,7 +202,6 @@ extern int sysctl_tcp_stdurg;
 extern int sysctl_tcp_rfc1337;
 extern int sysctl_tcp_abort_on_overflow;
 extern int sysctl_tcp_max_orphans;
-extern int sysctl_tcp_max_tw_buckets;
 extern int sysctl_tcp_fack;
 extern int sysctl_tcp_reordering;
 extern int sysctl_tcp_ecn;
@@ -585,12 +222,6 @@ extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
 extern int tcp_memory_pressure;
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-#define TCP_INET_FAMILY(fam) ((fam) == AF_INET)
-#else
-#define TCP_INET_FAMILY(fam) 1
-#endif
-
 /*
  *      Pointers to address related TCP functions
  *      (i.e. things that depend on the address family)
@@ -671,9 +302,6 @@ DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics);
 #define TCP_ADD_STATS_BH(field, val)    SNMP_ADD_STATS_BH(tcp_statistics, field, val)
 #define TCP_ADD_STATS_USER(field, val)  SNMP_ADD_STATS_USER(tcp_statistics, field, val)
 
-extern void                     tcp_put_port(struct sock *sk);
-extern void                     tcp_inherit_port(struct sock *sk, struct sock *child);
-
 extern void                     tcp_v4_err(struct sk_buff *skb, u32);
 
 extern void                     tcp_shutdown (struct sock *sk, int how);
@@ -682,7 +310,7 @@ extern int			tcp_v4_rcv(struct sk_buff *skb);
 
 extern int                      tcp_v4_remember_stamp(struct sock *sk);
 
-extern int                      tcp_v4_tw_remember_stamp(struct tcp_tw_bucket *tw);
+extern int                      tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 
 extern int                      tcp_sendmsg(struct kiocb *iocb, struct sock *sk,
                                             struct msghdr *msg, size_t size);
@@ -704,42 +332,22 @@ extern int			tcp_rcv_established(struct sock *sk,
 
 extern void                     tcp_rcv_space_adjust(struct sock *sk);
 
-enum tcp_ack_state_t
-{
-        TCP_ACK_SCHED = 1,
-        TCP_ACK_TIMER = 2,
-        TCP_ACK_PUSHED= 4
-};
-
-static inline void tcp_schedule_ack(struct tcp_sock *tp)
+static inline void tcp_dec_quickack_mode(struct sock *sk,
+                                         const unsigned int pkts)
 {
-        tp->ack.pending |= TCP_ACK_SCHED;
-}
-
-static inline int tcp_ack_scheduled(struct tcp_sock *tp)
-{
-        return tp->ack.pending&TCP_ACK_SCHED;
-}
-
-static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp, unsigned int pkts)
-{
-        if (tp->ack.quick) {
-                if (pkts >= tp->ack.quick) {
-                        tp->ack.quick = 0;
+        struct inet_connection_sock *icsk = inet_csk(sk);
 
+        if (icsk->icsk_ack.quick) {
+                if (pkts >= icsk->icsk_ack.quick) {
+                        icsk->icsk_ack.quick = 0;
                         /* Leaving quickack mode we deflate ATO. */
-                        tp->ack.ato = TCP_ATO_MIN;
+                        icsk->icsk_ack.ato   = TCP_ATO_MIN;
                 } else
-                        tp->ack.quick -= pkts;
+                        icsk->icsk_ack.quick -= pkts;
         }
 }
 
-extern void tcp_enter_quickack_mode(struct tcp_sock *tp);
-
-static __inline__ void tcp_delack_init(struct tcp_sock *tp)
-{
-        memset(&tp->ack, 0, sizeof(tp->ack));
-}
+extern void tcp_enter_quickack_mode(struct sock *sk);
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
@@ -755,10 +363,9 @@ enum tcp_tw_status
 };
 
 
-extern enum tcp_tw_status       tcp_timewait_state_process(struct tcp_tw_bucket *tw,
+extern enum tcp_tw_status       tcp_timewait_state_process(struct inet_timewait_sock *tw,
                                                            struct sk_buff *skb,
-                                                           struct tcphdr *th,
-                                                           unsigned len);
+                                                           const struct tcphdr *th);
 
 extern struct sock *            tcp_check_req(struct sock *sk,struct sk_buff *skb,
                                               struct request_sock *req,
@@ -773,7 +380,6 @@ extern void			tcp_update_metrics(struct sock *sk);
 
 extern void                     tcp_close(struct sock *sk, 
                                           long timeout);
-extern struct sock *            tcp_accept(struct sock *sk, int flags, int *err);
 extern unsigned int             tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);
 
 extern int                      tcp_getsockopt(struct sock *sk, int level, 
@@ -789,8 +395,6 @@ extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
                                             size_t len, int nonblock, 
                                             int flags, int *addr_len);
 
-extern int                      tcp_listen_start(struct sock *sk);
-
 extern void                     tcp_parse_options(struct sk_buff *skb,
                                                   struct tcp_options_received *opt_rx,
                                                   int estab);
@@ -799,11 +403,6 @@ extern void			tcp_parse_options(struct sk_buff *skb,
  *      TCP v4 functions exported for the inet6 API
  */
 
-extern int                      tcp_v4_rebuild_header(struct sock *sk);
-
-extern int                      tcp_v4_build_header(struct sock *sk, 
-                                                    struct sk_buff *skb);
-
 extern void                     tcp_v4_send_check(struct sock *sk, 
                                                   struct tcphdr *th, int len, 
                                                   struct sk_buff *skb);
@@ -872,18 +471,15 @@ extern void tcp_cwnd_application_limited(struct sock *sk);
 
 /* tcp_timer.c */
 extern void tcp_init_xmit_timers(struct sock *);
-extern void tcp_clear_xmit_timers(struct sock *);
+static inline void tcp_clear_xmit_timers(struct sock *sk)
+{
+        inet_csk_clear_xmit_timers(sk);
+}
 
-extern void tcp_delete_keepalive_timer(struct sock *);
-extern void tcp_reset_keepalive_timer(struct sock *, unsigned long);
 extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
 extern unsigned int tcp_current_mss(struct sock *sk, int large);
 
-#ifdef TCP_DEBUG
-extern const char tcp_timer_bug_msg[];
-#endif
-
-/* tcp_diag.c */
+/* tcp.c */
 extern void tcp_get_info(struct sock *, struct tcp_info *);
 
 /* Read 'sendfile()'-style from a TCP socket */
@@ -892,72 +488,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
                          sk_read_actor_t recv_actor);
 
-static inline void tcp_clear_xmit_timer(struct sock *sk, int what)
-{
-        struct tcp_sock *tp = tcp_sk(sk);
-        
-        switch (what) {
-        case TCP_TIME_RETRANS:
-        case TCP_TIME_PROBE0:
-                tp->pending = 0;
-
-#ifdef TCP_CLEAR_TIMERS
-                sk_stop_timer(sk, &tp->retransmit_timer);
-#endif
-                break;
-        case TCP_TIME_DACK:
-                tp->ack.blocked = 0;
-                tp->ack.pending = 0;
-
-#ifdef TCP_CLEAR_TIMERS
-                sk_stop_timer(sk, &tp->delack_timer);
-#endif
-                break;
-        default:
-#ifdef TCP_DEBUG
-                printk(tcp_timer_bug_msg);
-#endif
-                return;
-        };
-
-}
-
-/*
- *      Reset the retransmission timer
- */
-static inline void tcp_reset_xmit_timer(struct sock *sk, int what, unsigned long when)
-{
-        struct tcp_sock *tp = tcp_sk(sk);
-
-        if (when > TCP_RTO_MAX) {
-#ifdef TCP_DEBUG
-                printk(KERN_DEBUG "reset_xmit_timer sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, current_text_addr());
-#endif
-                when = TCP_RTO_MAX;
-        }
-
-        switch (what) {
-        case TCP_TIME_RETRANS:
-        case TCP_TIME_PROBE0:
-                tp->pending = what;
-                tp->timeout = jiffies+when;
-                sk_reset_timer(sk, &tp->retransmit_timer, tp->timeout);
-                break;
-
-        case TCP_TIME_DACK:
-                tp->ack.pending |= TCP_ACK_TIMER;
-                tp->ack.timeout = jiffies+when;
-                sk_reset_timer(sk, &tp->delack_timer, tp->ack.timeout);
-                break;
-
-        default:
-#ifdef TCP_DEBUG
-                printk(tcp_timer_bug_msg);
-#endif
-                return;
-        };
-}
-
 /* Initialize RCV_MSS value.
  * RCV_MSS is an our guess about MSS used by the peer.
  * We haven't any direct information about the MSS.
@@ -975,7 +505,7 @@ static inline void tcp_initialize_rcv_mss(struct sock *sk)
         hint = min(hint, TCP_MIN_RCVMSS);
         hint = max(hint, TCP_MIN_MSS);
 
-        tp->ack.rcv_mss = hint;
+        inet_csk(sk)->icsk_ack.rcv_mss = hint;
 }
 
 static __inline__ void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
@@ -1110,7 +640,8 @@ static inline void tcp_packets_out_inc(struct sock *sk,
 
         tp->packets_out += tcp_skb_pcount(skb);
         if (!orig)
-                tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
+                inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+                                          inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
 }
 
 static inline void tcp_packets_out_dec(struct tcp_sock *tp, 
@@ -1138,29 +669,29 @@ struct tcp_congestion_ops {
         struct list_head        list;
 
         /* initialize private data (optional) */
-        void (*init)(struct tcp_sock *tp);
+        void (*init)(struct sock *sk);
         /* cleanup private data  (optional) */
-        void (*release)(struct tcp_sock *tp);
+        void (*release)(struct sock *sk);
 
         /* return slow start threshold (required) */
-        u32 (*ssthresh)(struct tcp_sock *tp);
+        u32 (*ssthresh)(struct sock *sk);
         /* lower bound for congestion window (optional) */
-        u32 (*min_cwnd)(struct tcp_sock *tp);
+        u32 (*min_cwnd)(struct sock *sk);
         /* do new cwnd calculation (required) */
-        void (*cong_avoid)(struct tcp_sock *tp, u32 ack,
+        void (*cong_avoid)(struct sock *sk, u32 ack,
                            u32 rtt, u32 in_flight, int good_ack);
         /* round trip time sample per acked packet (optional) */
-        void (*rtt_sample)(struct tcp_sock *tp, u32 usrtt);
+        void (*rtt_sample)(struct sock *sk, u32 usrtt);
         /* call before changing ca_state (optional) */
-        void (*set_state)(struct tcp_sock *tp, u8 new_state);
+        void (*set_state)(struct sock *sk, u8 new_state);
         /* call when cwnd event occurs (optional) */
-        void (*cwnd_event)(struct tcp_sock *tp, enum tcp_ca_event ev);
+        void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
         /* new value of cwnd after loss (optional) */
-        u32  (*undo_cwnd)(struct tcp_sock *tp);
+        u32  (*undo_cwnd)(struct sock *sk);
         /* hook for packet ack accounting (optional) */
-        void (*pkts_acked)(struct tcp_sock *tp, u32 num_acked);
-        /* get info for tcp_diag (optional) */
-        void (*get_info)(struct tcp_sock *tp, u32 ext, struct sk_buff *skb);
+        void (*pkts_acked)(struct sock *sk, u32 num_acked);
+        /* get info for inet_diag (optional) */
+        void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
 
         char            name[TCP_CA_NAME_MAX];
         struct module   *owner;
@@ -1169,30 +700,34 @@ struct tcp_congestion_ops {
 extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
 extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
 
-extern void tcp_init_congestion_control(struct tcp_sock *tp);
-extern void tcp_cleanup_congestion_control(struct tcp_sock *tp);
+extern void tcp_init_congestion_control(struct sock *sk);
+extern void tcp_cleanup_congestion_control(struct sock *sk);
 extern int tcp_set_default_congestion_control(const char *name);
 extern void tcp_get_default_congestion_control(char *name);
-extern int tcp_set_congestion_control(struct tcp_sock *tp, const char *name);
+extern int tcp_set_congestion_control(struct sock *sk, const char *name);
 
 extern struct tcp_congestion_ops tcp_init_congestion_ops;
-extern u32 tcp_reno_ssthresh(struct tcp_sock *tp);
-extern void tcp_reno_cong_avoid(struct tcp_sock *tp, u32 ack,
+extern u32 tcp_reno_ssthresh(struct sock *sk);
+extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack,
                                 u32 rtt, u32 in_flight, int flag);
-extern u32 tcp_reno_min_cwnd(struct tcp_sock *tp);
+extern u32 tcp_reno_min_cwnd(struct sock *sk);
 extern struct tcp_congestion_ops tcp_reno;
 
-static inline void tcp_set_ca_state(struct tcp_sock *tp, u8 ca_state)
+static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
 {
-        if (tp->ca_ops->set_state)
-                tp->ca_ops->set_state(tp, ca_state);
-        tp->ca_state = ca_state;
+        struct inet_connection_sock *icsk = inet_csk(sk);
+
+        if (icsk->icsk_ca_ops->set_state)
+                icsk->icsk_ca_ops->set_state(sk, ca_state);
+        icsk->icsk_ca_state = ca_state;
 }
 
-static inline void tcp_ca_event(struct tcp_sock *tp, enum tcp_ca_event event)
+static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
 {
-        if (tp->ca_ops->cwnd_event)
-                tp->ca_ops->cwnd_event(tp, event);
+        const struct inet_connection_sock *icsk = inet_csk(sk);
+
+        if (icsk->icsk_ca_ops->cwnd_event)
+                icsk->icsk_ca_ops->cwnd_event(sk, event);
 }
 
 /* This determines how many packets are "in the network" to the best
@@ -1218,9 +753,10 @@ static __inline__ unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
  * The exception is rate halving phase, when cwnd is decreasing towards
  * ssthresh.
  */
-static inline __u32 tcp_current_ssthresh(struct tcp_sock *tp)
+static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 {
-        if ((1<<tp->ca_state)&(TCPF_CA_CWR|TCPF_CA_Recovery))
+        const struct tcp_sock *tp = tcp_sk(sk);
+        if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
                 return tp->snd_ssthresh;
         else
                 return max(tp->snd_ssthresh,
@@ -1237,10 +773,13 @@ static inline void tcp_sync_left_out(struct tcp_sock *tp)
 }
 
 /* Set slow start threshold and cwnd not falling to slow start */
-static inline void __tcp_enter_cwr(struct tcp_sock *tp)
+static inline void __tcp_enter_cwr(struct sock *sk)
 {
+        const struct inet_connection_sock *icsk = inet_csk(sk);
+        struct tcp_sock *tp = tcp_sk(sk);
+
         tp->undo_marker = 0;
-        tp->snd_ssthresh = tp->ca_ops->ssthresh(tp);
+        tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
         tp->snd_cwnd = min(tp->snd_cwnd,
                            tcp_packets_in_flight(tp) + 1U);
         tp->snd_cwnd_cnt = 0;
@@ -1249,12 +788,14 @@ static inline void __tcp_enter_cwr(struct tcp_sock *tp)
         TCP_ECN_queue_cwr(tp);
 }
 
-static inline void tcp_enter_cwr(struct tcp_sock *tp)
+static inline void tcp_enter_cwr(struct sock *sk)
 {
+        struct tcp_sock *tp = tcp_sk(sk);
+
         tp->prior_ssthresh = 0;
-        if (tp->ca_state < TCP_CA_CWR) {
-                __tcp_enter_cwr(tp);
-                tcp_set_ca_state(tp, TCP_CA_CWR);
+        if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
+                __tcp_enter_cwr(sk);
+                tcp_set_ca_state(sk, TCP_CA_CWR);
         }
 }
 
@@ -1277,8 +818,10 @@ static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss,
 
 static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
 {
-        if (!tp->packets_out && !tp->pending)
-                tcp_reset_xmit_timer(sk, TCP_TIME_PROBE0, tp->rto);
+        const struct inet_connection_sock *icsk = inet_csk(sk);
+        if (!tp->packets_out && !icsk->icsk_pending)
+                inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+                                          icsk->icsk_rto, TCP_RTO_MAX);
 }
 
 static __inline__ void tcp_push_pending_frames(struct sock *sk,
@@ -1297,9 +840,6 @@ static __inline__ void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
         tp->snd_wl1 = seq;
 }
 
-extern void tcp_destroy_sock(struct sock *sk);
-
-
 /*
  * Calculate(/check) TCP checksum
  */
@@ -1359,8 +899,10 @@ static __inline__ int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
                         tp->ucopy.memory = 0;
                 } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
                         wake_up_interruptible(sk->sk_sleep);
-                        if (!tcp_ack_scheduled(tp))
-                                tcp_reset_xmit_timer(sk, TCP_TIME_DACK, (3*TCP_RTO_MIN)/4);
+                        if (!inet_csk_ack_scheduled(sk))
+                                inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+                                                          (3 * TCP_RTO_MIN) / 4,
+                                                          TCP_RTO_MAX);
                 }
                 return 1;
         }
@@ -1393,9 +935,9 @@ static __inline__ void tcp_set_state(struct sock *sk, int state)
                         TCP_INC_STATS(TCP_MIB_ESTABRESETS);
 
                 sk->sk_prot->unhash(sk);
-                if (tcp_sk(sk)->bind_hash &&
+                if (inet_csk(sk)->icsk_bind_hash &&
                     !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
-                        tcp_put_port(sk);
+                        inet_put_port(&tcp_hashinfo, sk);
                 /* fall through */
         default:
                 if (oldstate==TCP_ESTABLISHED)
@@ -1422,7 +964,7 @@ static __inline__ void tcp_done(struct sock *sk)
         if (!sock_flag(sk, SOCK_DEAD))
                 sk->sk_state_change(sk);
         else
-                tcp_destroy_sock(sk);
+                inet_csk_destroy_sock(sk);
 }
 
 static __inline__ void tcp_sack_reset(struct tcp_options_received *rx_opt)
@@ -1524,54 +1066,6 @@ static inline int tcp_full_space(const struct sock *sk)
         return tcp_win_from_space(sk->sk_rcvbuf); 
 }
 
-static inline void tcp_acceptq_queue(struct sock *sk, struct request_sock *req,
-                                         struct sock *child)
-{
-        reqsk_queue_add(&tcp_sk(sk)->accept_queue, req, sk, child);
-}
-
-static inline void
-tcp_synq_removed(struct sock *sk, struct request_sock *req)
-{
-        if (reqsk_queue_removed(&tcp_sk(sk)->accept_queue, req) == 0)
-                tcp_delete_keepalive_timer(sk);
-}
-
-static inline void tcp_synq_added(struct sock *sk)
-{
-        if (reqsk_queue_added(&tcp_sk(sk)->accept_queue) == 0)
-                tcp_reset_keepalive_timer(sk, TCP_TIMEOUT_INIT);
-}
-
-static inline int tcp_synq_len(struct sock *sk)
-{
-        return reqsk_queue_len(&tcp_sk(sk)->accept_queue);
-}
-
-static inline int tcp_synq_young(struct sock *sk)
-{
-        return reqsk_queue_len_young(&tcp_sk(sk)->accept_queue);
-}
-
-static inline int tcp_synq_is_full(struct sock *sk)
-{
-        return reqsk_queue_is_full(&tcp_sk(sk)->accept_queue);
-}
-
-static inline void tcp_synq_unlink(struct tcp_sock *tp, struct request_sock *req,
-                                   struct request_sock **prev)
-{
-        reqsk_queue_unlink(&tp->accept_queue, req, prev);
-}
-
-static inline void tcp_synq_drop(struct sock *sk, struct request_sock *req,
-                                     struct request_sock **prev)
-{
-        tcp_synq_unlink(tcp_sk(sk), req, prev);
-        tcp_synq_removed(sk, req);
-        reqsk_free(req);
-}
-
 static __inline__ void tcp_openreq_init(struct request_sock *req,
                                         struct tcp_options_received *rx_opt,
                                         struct sk_buff *skb)
@@ -1593,27 +1087,6 @@ static __inline__ void tcp_openreq_init(struct request_sock *req,
 
 extern void tcp_enter_memory_pressure(void);
 
-extern void tcp_listen_wlock(void);
-
-/* - We may sleep inside this lock.
- * - If sleeping is not required (or called from BH),
- *   use plain read_(un)lock(&tcp_lhash_lock).
- */
-
-static inline void tcp_listen_lock(void)
-{
-        /* read_lock synchronizes to candidates to writers */
-        read_lock(&tcp_lhash_lock);
-        atomic_inc(&tcp_lhash_users);
-        read_unlock(&tcp_lhash_lock);
-}
-
-static inline void tcp_listen_unlock(void)
-{
-        if (atomic_dec_and_test(&tcp_lhash_users))
-                wake_up(&tcp_lhash_wait);
-}
-
 static inline int keepalive_intvl_when(const struct tcp_sock *tp)
 {
         return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl;
@@ -1624,12 +1097,13 @@ static inline int keepalive_time_when(const struct tcp_sock *tp)
         return tp->keepalive_time ? : sysctl_tcp_keepalive_time;
 }
 
-static inline int tcp_fin_time(const struct tcp_sock *tp)
+static inline int tcp_fin_time(const struct sock *sk)
 {
-        int fin_timeout = tp->linger2 ? : sysctl_tcp_fin_timeout;
+        int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
+        const int rto = inet_csk(sk)->icsk_rto;
 
-        if (fin_timeout < (tp->rto<<2) - (tp->rto>>1))
-                fin_timeout = (tp->rto<<2) - (tp->rto>>1);
+        if (fin_timeout < (rto << 2) - (rto >> 1))
+                fin_timeout = (rto << 2) - (rto >> 1);
 
         return fin_timeout;
 }
@@ -1658,15 +1132,6 @@ static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int
         return 1;
 }
 
-static inline void tcp_v4_setup_caps(struct sock *sk, struct dst_entry *dst)
-{
-        sk->sk_route_caps = dst->dev->features;
-        if (sk->sk_route_caps & NETIF_F_TSO) {
-                if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
-                        sk->sk_route_caps &= ~NETIF_F_TSO;
-        }
-}
-
 #define TCP_CHECK_TIMER(sk) do { } while (0)
 
 static inline int tcp_use_frto(const struct sock *sk)
@@ -1718,4 +1183,16 @@ struct tcp_iter_state {
 extern int tcp_proc_register(struct tcp_seq_afinfo *afinfo);
 extern void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo);
 
+extern struct request_sock_ops tcp_request_sock_ops;
+
+extern int tcp_v4_destroy_sock(struct sock *sk);
+
+#ifdef CONFIG_PROC_FS
+extern int  tcp4_proc_init(void);
+extern void tcp4_proc_exit(void);
+#endif
+
+extern void tcp_v4_init(struct net_proto_family *ops);
+extern void tcp_init(void);
+
 #endif  /* _TCP_H */
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index 64980ee8c92a..c6b84397448d 100644
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -88,7 +88,7 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
                  * it is surely retransmit. It is not in ECN RFC,
                  * but Linux follows this rule. */
                 else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags)))
-                        tcp_enter_quickack_mode(tp);
+                        tcp_enter_quickack_mode((struct sock *)tp);
         }
 }
 
diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
new file mode 100644
index 000000000000..b9d4176b2d15
--- /dev/null
+++ b/include/net/tcp_states.h
@@ -0,0 +1,34 @@
+/*
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the  BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ *              Definitions for the TCP protocol sk_state field.
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_TCP_STATES_H
+#define _LINUX_TCP_STATES_H
+
+enum {
+        TCP_ESTABLISHED = 1,
+        TCP_SYN_SENT,
+        TCP_SYN_RECV,
+        TCP_FIN_WAIT1,
+        TCP_FIN_WAIT2,
+        TCP_TIME_WAIT,
+        TCP_CLOSE,
+        TCP_CLOSE_WAIT,
+        TCP_LAST_ACK,
+        TCP_LISTEN,
+        TCP_CLOSING,    /* Now a valid state */
+
+        TCP_MAX_STATES  /* Leave at the end! */
+};
+
+#define TCP_STATE_MASK  0xF
+
+#endif  /* _LINUX_TCP_STATES_H */
diff --git a/include/net/udp.h b/include/net/udp.h
index ac229b761dbc..107b9d791a1f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -94,6 +94,11 @@ struct udp_iter_state {
         struct seq_operations   seq_ops;
 };
 
+#ifdef CONFIG_PROC_FS
 extern int udp_proc_register(struct udp_seq_afinfo *afinfo);
 extern void udp_proc_unregister(struct udp_seq_afinfo *afinfo);
+
+extern int  udp4_proc_init(void);
+extern void udp4_proc_exit(void);
+#endif
 #endif  /* _UDP_H */
diff --git a/include/net/x25.h b/include/net/x25.h
index 8b39b98876e8..fee62ff8c194 100644
--- a/include/net/x25.h
+++ b/include/net/x25.h
@@ -175,7 +175,7 @@ extern void x25_kill_by_neigh(struct x25_neigh *);
 
 /* x25_dev.c */
 extern void x25_send_frame(struct sk_buff *, struct x25_neigh *);
-extern int  x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *);
+extern int  x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
 extern void x25_establish_link(struct x25_neigh *);
 extern void x25_terminate_link(struct x25_neigh *);
 
diff --git a/include/net/x25device.h b/include/net/x25device.h
index d45ae883bd1d..1a318374faef 100644
--- a/include/net/x25device.h
+++ b/include/net/x25device.h
@@ -8,7 +8,6 @@
 static inline __be16 x25_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
         skb->mac.raw = skb->data;
-        skb->input_dev = skb->dev = dev;
         skb->pkt_type = PACKET_HOST;
         
         return htons(ETH_P_X25);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 868ef88ef971..a9d0d8c5dfbf 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -818,7 +818,6 @@ extern void xfrm6_init(void);
 extern void xfrm6_fini(void);
 extern void xfrm_state_init(void);
 extern void xfrm4_state_init(void);
-extern void xfrm4_state_fini(void);
 extern void xfrm6_state_init(void);
 extern void xfrm6_state_fini(void);
 
diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h
new file mode 100644
index 000000000000..5bf9834f7dca
--- /dev/null
+++ b/include/rdma/ib_cache.h
@@ -0,0 +1,105 @@
+/*
+ * Copyright (c) 2004 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Intel Corporation. All rights reserved.
+ * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_cache.h 1349 2004-12-16 21:09:43Z roland $
+ */
+
+#ifndef _IB_CACHE_H
+#define _IB_CACHE_H
+
+#include <rdma/ib_verbs.h>
+
+/**
+ * ib_get_cached_gid - Returns a cached GID table entry
+ * @device: The device to query.
+ * @port_num: The port number of the device to query.
+ * @index: The index into the cached GID table to query.
+ * @gid: The GID value found at the specified index.
+ *
+ * ib_get_cached_gid() fetches the specified GID table entry stored in
+ * the local software cache.
+ */
+int ib_get_cached_gid(struct ib_device    *device,
+                      u8                   port_num,
+                      int                  index,
+                      union ib_gid        *gid);
+
+/**
+ * ib_find_cached_gid - Returns the port number and GID table index where
+ *   a specified GID value occurs.
+ * @device: The device to query.
+ * @gid: The GID value to search for.
+ * @port_num: The port number of the device where the GID value was found.
+ * @index: The index into the cached GID table where the GID was found.  This
+ *   parameter may be NULL.
+ *
+ * ib_find_cached_gid() searches for the specified GID value in
+ * the local software cache.
+ */
+int ib_find_cached_gid(struct ib_device *device,
+                       union ib_gid     *gid,
+                       u8               *port_num,
+                       u16              *index);
+
+/**
+ * ib_get_cached_pkey - Returns a cached PKey table entry
+ * @device: The device to query.
+ * @port_num: The port number of the device to query.
+ * @index: The index into the cached PKey table to query.
+ * @pkey: The PKey value found at the specified index.
+ *
+ * ib_get_cached_pkey() fetches the specified PKey table entry stored in
+ * the local software cache.
+ */
+int ib_get_cached_pkey(struct ib_device    *device_handle,
+                       u8                   port_num,
+                       int                  index,
+                       u16                 *pkey);
+
+/**
+ * ib_find_cached_pkey - Returns the PKey table index where a specified
+ *   PKey value occurs.
+ * @device: The device to query.
+ * @port_num: The port number of the device to search for the PKey.
+ * @pkey: The PKey value to search for.
+ * @index: The index into the cached PKey table where the PKey was found.
+ *
+ * ib_find_cached_pkey() searches the specified PKey table in
+ * the local software cache.
+ */
+int ib_find_cached_pkey(struct ib_device    *device,
+                        u8                   port_num,
+                        u16                  pkey,
+                        u16                 *index);
+
+#endif /* _IB_CACHE_H */
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
new file mode 100644
index 000000000000..77fe9039209b
--- /dev/null
+++ b/include/rdma/ib_cm.h
@@ -0,0 +1,568 @@
+/*
+ * Copyright (c) 2004 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
+ * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_cm.h 2730 2005-06-28 16:43:03Z sean.hefty $
+ */
+#if !defined(IB_CM_H)
+#define IB_CM_H
+
+#include <rdma/ib_mad.h>
+#include <rdma/ib_sa.h>
+
+enum ib_cm_state {
+        IB_CM_IDLE,
+        IB_CM_LISTEN,
+        IB_CM_REQ_SENT,
+        IB_CM_REQ_RCVD,
+        IB_CM_MRA_REQ_SENT,
+        IB_CM_MRA_REQ_RCVD,
+        IB_CM_REP_SENT,
+        IB_CM_REP_RCVD,
+        IB_CM_MRA_REP_SENT,
+        IB_CM_MRA_REP_RCVD,
+        IB_CM_ESTABLISHED,
+        IB_CM_DREQ_SENT,
+        IB_CM_DREQ_RCVD,
+        IB_CM_TIMEWAIT,
+        IB_CM_SIDR_REQ_SENT,
+        IB_CM_SIDR_REQ_RCVD
+};
+
+enum ib_cm_lap_state {
+        IB_CM_LAP_IDLE,
+        IB_CM_LAP_SENT,
+        IB_CM_LAP_RCVD,
+        IB_CM_MRA_LAP_SENT,
+        IB_CM_MRA_LAP_RCVD,
+};
+
+enum ib_cm_event_type {
+        IB_CM_REQ_ERROR,
+        IB_CM_REQ_RECEIVED,
+        IB_CM_REP_ERROR,
+        IB_CM_REP_RECEIVED,
+        IB_CM_RTU_RECEIVED,
+        IB_CM_USER_ESTABLISHED,
+        IB_CM_DREQ_ERROR,
+        IB_CM_DREQ_RECEIVED,
+        IB_CM_DREP_RECEIVED,
+        IB_CM_TIMEWAIT_EXIT,
+        IB_CM_MRA_RECEIVED,
+        IB_CM_REJ_RECEIVED,
+        IB_CM_LAP_ERROR,
+        IB_CM_LAP_RECEIVED,
+        IB_CM_APR_RECEIVED,
+        IB_CM_SIDR_REQ_ERROR,
+        IB_CM_SIDR_REQ_RECEIVED,
+        IB_CM_SIDR_REP_RECEIVED
+};
+
+enum ib_cm_data_size {
+        IB_CM_REQ_PRIVATE_DATA_SIZE      = 92,
+        IB_CM_MRA_PRIVATE_DATA_SIZE      = 222,
+        IB_CM_REJ_PRIVATE_DATA_SIZE      = 148,
+        IB_CM_REP_PRIVATE_DATA_SIZE      = 196,
+        IB_CM_RTU_PRIVATE_DATA_SIZE      = 224,
+        IB_CM_DREQ_PRIVATE_DATA_SIZE     = 220,
+        IB_CM_DREP_PRIVATE_DATA_SIZE     = 224,
+        IB_CM_REJ_ARI_LENGTH             = 72,
+        IB_CM_LAP_PRIVATE_DATA_SIZE      = 168,
+        IB_CM_APR_PRIVATE_DATA_SIZE      = 148,
+        IB_CM_APR_INFO_LENGTH            = 72,
+        IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE = 216,
+        IB_CM_SIDR_REP_PRIVATE_DATA_SIZE = 136,
+        IB_CM_SIDR_REP_INFO_LENGTH       = 72
+};
+
+struct ib_cm_id;
+
+struct ib_cm_req_event_param {
+        struct ib_cm_id         *listen_id;
+        struct ib_device        *device;
+        u8                      port;
+
+        struct ib_sa_path_rec   *primary_path;
+        struct ib_sa_path_rec   *alternate_path;
+
+        __be64                  remote_ca_guid;
+        u32                     remote_qkey;
+        u32                     remote_qpn;
+        enum ib_qp_type         qp_type;
+
+        u32                     starting_psn;
+        u8                      responder_resources;
+        u8                      initiator_depth;
+        unsigned int            local_cm_response_timeout:5;
+        unsigned int            flow_control:1;
+        unsigned int            remote_cm_response_timeout:5;
+        unsigned int            retry_count:3;
+        unsigned int            rnr_retry_count:3;
+        unsigned int            srq:1;
+};
+
+struct ib_cm_rep_event_param {
+        __be64                  remote_ca_guid;
+        u32                     remote_qkey;
+        u32                     remote_qpn;
+        u32                     starting_psn;
+        u8                      responder_resources;
+        u8                      initiator_depth;
+        unsigned int            target_ack_delay:5;
+        unsigned int            failover_accepted:2;
+        unsigned int            flow_control:1;
+        unsigned int            rnr_retry_count:3;
+        unsigned int            srq:1;
+};
+
+enum ib_cm_rej_reason {
+        IB_CM_REJ_NO_QP                         = 1,
+        IB_CM_REJ_NO_EEC                        = 2,
+        IB_CM_REJ_NO_RESOURCES                  = 3,
+        IB_CM_REJ_TIMEOUT                       = 4,
+        IB_CM_REJ_UNSUPPORTED                   = 5,
+        IB_CM_REJ_INVALID_COMM_ID               = 6,
+        IB_CM_REJ_INVALID_COMM_INSTANCE         = 7,
+        IB_CM_REJ_INVALID_SERVICE_ID            = 8,
+        IB_CM_REJ_INVALID_TRANSPORT_TYPE        = 9,
+        IB_CM_REJ_STALE_CONN                    = 10,
+        IB_CM_REJ_RDC_NOT_EXIST                 = 11,
+        IB_CM_REJ_INVALID_GID                   = 12,
+        IB_CM_REJ_INVALID_LID                   = 13,
+        IB_CM_REJ_INVALID_SL                    = 14,
+        IB_CM_REJ_INVALID_TRAFFIC_CLASS         = 15,
+        IB_CM_REJ_INVALID_HOP_LIMIT             = 16,
+        IB_CM_REJ_INVALID_PACKET_RATE           = 17,
+        IB_CM_REJ_INVALID_ALT_GID               = 18,
+        IB_CM_REJ_INVALID_ALT_LID               = 19,
+        IB_CM_REJ_INVALID_ALT_SL                = 20,
+        IB_CM_REJ_INVALID_ALT_TRAFFIC_CLASS     = 21,
+        IB_CM_REJ_INVALID_ALT_HOP_LIMIT         = 22,
+        IB_CM_REJ_INVALID_ALT_PACKET_RATE       = 23,
+        IB_CM_REJ_PORT_CM_REDIRECT              = 24,
+        IB_CM_REJ_PORT_REDIRECT                 = 25,
+        IB_CM_REJ_INVALID_MTU                   = 26,
+        IB_CM_REJ_INSUFFICIENT_RESP_RESOURCES   = 27,
+        IB_CM_REJ_CONSUMER_DEFINED              = 28,
+        IB_CM_REJ_INVALID_RNR_RETRY             = 29,
+        IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID       = 30,
+        IB_CM_REJ_INVALID_CLASS_VERSION         = 31,
+        IB_CM_REJ_INVALID_FLOW_LABEL            = 32,
+        IB_CM_REJ_INVALID_ALT_FLOW_LABEL        = 33
+};
+
+struct ib_cm_rej_event_param {
+        enum ib_cm_rej_reason   reason;
+        void                    *ari;
+        u8                      ari_length;
+};
+
+struct ib_cm_mra_event_param {
+        u8      service_timeout;
+};
+
+struct ib_cm_lap_event_param {
+        struct ib_sa_path_rec   *alternate_path;
+};
+
+enum ib_cm_apr_status {
+        IB_CM_APR_SUCCESS,
+        IB_CM_APR_INVALID_COMM_ID,
+        IB_CM_APR_UNSUPPORTED,
+        IB_CM_APR_REJECT,
+        IB_CM_APR_REDIRECT,
+        IB_CM_APR_IS_CURRENT,
+        IB_CM_APR_INVALID_QPN_EECN,
+        IB_CM_APR_INVALID_LID,
+        IB_CM_APR_INVALID_GID,
+        IB_CM_APR_INVALID_FLOW_LABEL,
+        IB_CM_APR_INVALID_TCLASS,
+        IB_CM_APR_INVALID_HOP_LIMIT,
+        IB_CM_APR_INVALID_PACKET_RATE,
+        IB_CM_APR_INVALID_SL
+};
+
+struct ib_cm_apr_event_param {
+        enum ib_cm_apr_status   ap_status;
+        void                    *apr_info;
+        u8                      info_len;
+};
+
+struct ib_cm_sidr_req_event_param {
+        struct ib_cm_id         *listen_id;
+        struct ib_device        *device;
+        u8                      port;
+        u16                     pkey;
+};
+
+enum ib_cm_sidr_status {
+        IB_SIDR_SUCCESS,
+        IB_SIDR_UNSUPPORTED,
+        IB_SIDR_REJECT,
+        IB_SIDR_NO_QP,
+        IB_SIDR_REDIRECT,
+        IB_SIDR_UNSUPPORTED_VERSION
+};
+
+struct ib_cm_sidr_rep_event_param {
+        enum ib_cm_sidr_status  status;
+        u32                     qkey;
+        u32                     qpn;
+        void                    *info;
+        u8                      info_len;
+
+};
+
+struct ib_cm_event {
+        enum ib_cm_event_type   event;
+        union {
+                struct ib_cm_req_event_param    req_rcvd;
+                struct ib_cm_rep_event_param    rep_rcvd;
+                /* No data for RTU received events. */
+                struct ib_cm_rej_event_param    rej_rcvd;
+                struct ib_cm_mra_event_param    mra_rcvd;
+                struct ib_cm_lap_event_param    lap_rcvd;
+                struct ib_cm_apr_event_param    apr_rcvd;
+                /* No data for DREQ/DREP received events. */
+                struct ib_cm_sidr_req_event_param sidr_req_rcvd;
+                struct ib_cm_sidr_rep_event_param sidr_rep_rcvd;
+                enum ib_wc_status               send_status;
+        } param;
+
+        void                    *private_data;
+};
+
+/**
+ * ib_cm_handler - User-defined callback to process communication events.
+ * @cm_id: Communication identifier associated with the reported event.
+ * @event: Information about the communication event.
+ *
+ * IB_CM_REQ_RECEIVED and IB_CM_SIDR_REQ_RECEIVED communication events
+ * generated as a result of listen requests result in the allocation of a
+ * new @cm_id.  The new @cm_id is returned to the user through this callback.
+ * Clients are responsible for destroying the new @cm_id.  For peer-to-peer
+ * IB_CM_REQ_RECEIVED and all other events, the returned @cm_id corresponds
+ * to a user's existing communication identifier.
+ *
+ * Users may not call ib_destroy_cm_id while in the context of this callback;
+ * however, returning a non-zero value instructs the communication manager to
+ * destroy the @cm_id after the callback completes.
+ */
+typedef int (*ib_cm_handler)(struct ib_cm_id *cm_id,
+                             struct ib_cm_event *event);
+
+struct ib_cm_id {
+        ib_cm_handler           cm_handler;
+        void                    *context;
+        __be64                  service_id;
+        __be64                  service_mask;
+        enum ib_cm_state        state;          /* internal CM/debug use */
+        enum ib_cm_lap_state    lap_state;      /* internal CM/debug use */
+        __be32                  local_id;
+        __be32                  remote_id;
+};
+
+/**
+ * ib_create_cm_id - Allocate a communication identifier.
+ * @cm_handler: Callback invoked to notify the user of CM events.
+ * @context: User specified context associated with the communication
+ *   identifier.
+ *
+ * Communication identifiers are used to track connection states, service
+ * ID resolution requests, and listen requests.
+ */
+struct ib_cm_id *ib_create_cm_id(ib_cm_handler cm_handler,
+                                 void *context);
+
+/**
+ * ib_destroy_cm_id - Destroy a connection identifier.
+ * @cm_id: Connection identifier to destroy.
+ *
+ * This call blocks until the connection identifier is destroyed.
+ */
+void ib_destroy_cm_id(struct ib_cm_id *cm_id);
+
+#define IB_SERVICE_ID_AGN_MASK  __constant_cpu_to_be64(0xFF00000000000000ULL)
+#define IB_CM_ASSIGN_SERVICE_ID __constant_cpu_to_be64(0x0200000000000000ULL)
+
+/**
+ * ib_cm_listen - Initiates listening on the specified service ID for
+ *   connection and service ID resolution requests.
+ * @cm_id: Connection identifier associated with the listen request.
+ * @service_id: Service identifier matched against incoming connection
+ *   and service ID resolution requests.  The service ID should be specified
+ *   network-byte order.  If set to IB_CM_ASSIGN_SERVICE_ID, the CM will
+ *   assign a service ID to the caller.
+ * @service_mask: Mask applied to service ID used to listen across a
+ *   range of service IDs.  If set to 0, the service ID is matched
+ *   exactly.  This parameter is ignored if %service_id is set to
+ *   IB_CM_ASSIGN_SERVICE_ID.
+ */
+int ib_cm_listen(struct ib_cm_id *cm_id,
+                 __be64 service_id,
+                 __be64 service_mask);
+
+struct ib_cm_req_param {
+        struct ib_sa_path_rec   *primary_path;
+        struct ib_sa_path_rec   *alternate_path;
+        __be64                  service_id;
+        u32                     qp_num;
+        enum ib_qp_type         qp_type;
+        u32                     starting_psn;
+        const void              *private_data;
+        u8                      private_data_len;
+        u8                      peer_to_peer;
+        u8                      responder_resources;
+        u8                      initiator_depth;
+        u8                      remote_cm_response_timeout;
+        u8                      flow_control;
+        u8                      local_cm_response_timeout;
+        u8                      retry_count;
+        u8                      rnr_retry_count;
+        u8                      max_cm_retries;
+        u8                      srq;
+};
+
+/**
+ * ib_send_cm_req - Sends a connection request to the remote node.
+ * @cm_id: Connection identifier that will be associated with the
+ *   connection request.
+ * @param: Connection request information needed to establish the
+ *   connection.
+ */
+int ib_send_cm_req(struct ib_cm_id *cm_id,
+                   struct ib_cm_req_param *param);
+
+struct ib_cm_rep_param {
+        u32             qp_num;
+        u32             starting_psn;
+        const void      *private_data;
+        u8              private_data_len;
+        u8              responder_resources;
+        u8              initiator_depth;
+        u8              target_ack_delay;
+        u8              failover_accepted;
+        u8              flow_control;
+        u8              rnr_retry_count;
+        u8              srq;
+};
+
+/**
+ * ib_send_cm_rep - Sends a connection reply in response to a connection
+ *   request.
+ * @cm_id: Connection identifier that will be associated with the
+ *   connection request.
+ * @param: Connection reply information needed to establish the
+ *   connection.
+ */
+int ib_send_cm_rep(struct ib_cm_id *cm_id,
+                   struct ib_cm_rep_param *param);
+
+/**
+ * ib_send_cm_rtu - Sends a connection ready to use message in response
+ *   to a connection reply message.
+ * @cm_id: Connection identifier associated with the connection request.
+ * @private_data: Optional user-defined private data sent with the
+ *   ready to use message.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ */
+int ib_send_cm_rtu(struct ib_cm_id *cm_id,
+                   const void *private_data,
+                   u8 private_data_len);
+
+/**
+ * ib_send_cm_dreq - Sends a disconnection request for an existing
+ *   connection.
+ * @cm_id: Connection identifier associated with the connection being
+ *   released.
+ * @private_data: Optional user-defined private data sent with the
+ *   disconnection request message.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ */
+int ib_send_cm_dreq(struct ib_cm_id *cm_id,
+                    const void *private_data,
+                    u8 private_data_len);
+
+/**
+ * ib_send_cm_drep - Sends a disconnection reply to a disconnection request.
+ * @cm_id: Connection identifier associated with the connection being
+ *   released.
+ * @private_data: Optional user-defined private data sent with the
+ *   disconnection reply message.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ *
+ * If the cm_id is in the correct state, the CM will transition the connection
+ * to the timewait state, even if an error occurs sending the DREP message.
+ */
+int ib_send_cm_drep(struct ib_cm_id *cm_id,
+                    const void *private_data,
+                    u8 private_data_len);
+
+/**
+ * ib_cm_establish - Forces a connection state to established.
+ * @cm_id: Connection identifier to transition to established.
+ *
+ * This routine should be invoked by users who receive messages on a
+ * connected QP before an RTU has been received.
+ */
+int ib_cm_establish(struct ib_cm_id *cm_id);
+
+/**
+ * ib_send_cm_rej - Sends a connection rejection message to the
+ *   remote node.
+ * @cm_id: Connection identifier associated with the connection being
+ *   rejected.
+ * @reason: Reason for the connection request rejection.
+ * @ari: Optional additional rejection information.
+ * @ari_length: Size of the additional rejection information, in bytes.
+ * @private_data: Optional user-defined private data sent with the
+ *   rejection message.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ */
+int ib_send_cm_rej(struct ib_cm_id *cm_id,
+                   enum ib_cm_rej_reason reason,
+                   void *ari,
+                   u8 ari_length,
+                   const void *private_data,
+                   u8 private_data_len);
+
+/**
+ * ib_send_cm_mra - Sends a message receipt acknowledgement to a connection
+ *   message.
+ * @cm_id: Connection identifier associated with the connection message.
+ * @service_timeout: The maximum time required for the sender to reply to
+ *   to the connection message.
+ * @private_data: Optional user-defined private data sent with the
+ *   message receipt acknowledgement.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ */
+int ib_send_cm_mra(struct ib_cm_id *cm_id,
+                   u8 service_timeout,
+                   const void *private_data,
+                   u8 private_data_len);
+
+/**
+ * ib_send_cm_lap - Sends a load alternate path request.
+ * @cm_id: Connection identifier associated with the load alternate path
+ *   message.
+ * @alternate_path: A path record that identifies the alternate path to
+ *   load.
+ * @private_data: Optional user-defined private data sent with the
+ *   load alternate path message.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ */
+int ib_send_cm_lap(struct ib_cm_id *cm_id,
+                   struct ib_sa_path_rec *alternate_path,
+                   const void *private_data,
+                   u8 private_data_len);
+
+/**
+ * ib_cm_init_qp_attr - Initializes the QP attributes for use in transitioning
+ *   to a specified QP state.
+ * @cm_id: Communication identifier associated with the QP attributes to
+ *   initialize.
+ * @qp_attr: On input, specifies the desired QP state.  On output, the
+ *   mandatory and desired optional attributes will be set in order to
+ *   modify the QP to the specified state.
+ * @qp_attr_mask: The QP attribute mask that may be used to transition the
+ *   QP to the specified state.
+ *
+ * Users must set the @qp_attr->qp_state to the desired QP state.  This call
+ * will set all required attributes for the given transition, along with
+ * known optional attributes.  Users may override the attributes returned from
+ * this call before calling ib_modify_qp.
+ */
+int ib_cm_init_qp_attr(struct ib_cm_id *cm_id,
+                       struct ib_qp_attr *qp_attr,
+                       int *qp_attr_mask);
+
+/**
+ * ib_send_cm_apr - Sends an alternate path response message in response to
+ *   a load alternate path request.
+ * @cm_id: Connection identifier associated with the alternate path response.
+ * @status: Reply status sent with the alternate path response.
+ * @info: Optional additional information sent with the alternate path
+ *   response.
+ * @info_length: Size of the additional information, in bytes.
+ * @private_data: Optional user-defined private data sent with the
+ *   alternate path response message.
+ * @private_data_len: Size of the private data buffer, in bytes.
+ */
+int ib_send_cm_apr(struct ib_cm_id *cm_id,
+                   enum ib_cm_apr_status status,
+                   void *info,
+                   u8 info_length,
+                   const void *private_data,
+                   u8 private_data_len);
+
+struct ib_cm_sidr_req_param {
+        struct ib_sa_path_rec   *path;
+        __be64                  service_id;
+        int                     timeout_ms;
+        const void              *private_data;
+        u8                      private_data_len;
+        u8                      max_cm_retries;
+        u16                     pkey;
+};
+
+/**
+ * ib_send_cm_sidr_req - Sends a service ID resolution request to the
+ *   remote node.
+ * @cm_id: Communication identifier that will be associated with the
+ *   service ID resolution request.
+ * @param: Service ID resolution request information.
+ */
+int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
+                        struct ib_cm_sidr_req_param *param);
+
+struct ib_cm_sidr_rep_param {
+        u32                     qp_num;
+        u32                     qkey;
+        enum ib_cm_sidr_status  status;
+        const void              *info;
+        u8                      info_length;
+        const void              *private_data;
+        u8                      private_data_len;
+};
+
+/**
+ * ib_send_cm_sidr_rep - Sends a service ID resolution request to the
+ *   remote node.
+ * @cm_id: Communication identifier associated with the received service ID
+ *   resolution request.
+ * @param: Service ID resolution reply information.
+ */
+int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
+                        struct ib_cm_sidr_rep_param *param);
+
+#endif /* IB_CM_H */
diff --git a/include/rdma/ib_fmr_pool.h b/include/rdma/ib_fmr_pool.h
new file mode 100644
index 000000000000..86b7e93f198b
--- /dev/null
+++ b/include/rdma/ib_fmr_pool.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
+ * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_fmr_pool.h 2730 2005-06-28 16:43:03Z sean.hefty $
+ */
+
+#if !defined(IB_FMR_POOL_H)
+#define IB_FMR_POOL_H
+
+#include <rdma/ib_verbs.h>
+
+struct ib_fmr_pool;
+
+/**
+ * struct ib_fmr_pool_param - Parameters for creating FMR pool
+ * @max_pages_per_fmr:Maximum number of pages per map request.
+ * @access:Access flags for FMRs in pool.
+ * @pool_size:Number of FMRs to allocate for pool.
+ * @dirty_watermark:Flush is triggered when @dirty_watermark dirty
+ *     FMRs are present.
+ * @flush_function:Callback called when unmapped FMRs are flushed and
+ *     more FMRs are possibly available for mapping
+ * @flush_arg:Context passed to user's flush function.
+ * @cache:If set, FMRs may be reused after unmapping for identical map
+ *     requests.
+ */
+struct ib_fmr_pool_param {
+        int                     max_pages_per_fmr;
+        enum ib_access_flags    access;
+        int                     pool_size;
+        int                     dirty_watermark;
+        void                  (*flush_function)(struct ib_fmr_pool *pool,
+                                                void *              arg);
+        void                   *flush_arg;
+        unsigned                cache:1;
+};
+
+struct ib_pool_fmr {
+        struct ib_fmr      *fmr;
+        struct ib_fmr_pool *pool;
+        struct list_head    list;
+        struct hlist_node   cache_node;
+        int                 ref_count;
+        int                 remap_count;
+        u64                 io_virtual_address;
+        int                 page_list_len;
+        u64                 page_list[0];
+};
+
+struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
+                                       struct ib_fmr_pool_param *params);
+
+void ib_destroy_fmr_pool(struct ib_fmr_pool *pool);
+
+int ib_flush_fmr_pool(struct ib_fmr_pool *pool);
+
+struct ib_pool_fmr *ib_fmr_pool_map_phys(struct ib_fmr_pool *pool_handle,
+                                         u64                *page_list,
+                                         int                 list_len,
+                                         u64                *io_virtual_address);
+
+int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr);
+
+#endif /* IB_FMR_POOL_H */
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
new file mode 100644
index 000000000000..fc6b1c18ffc6
--- /dev/null
+++ b/include/rdma/ib_mad.h
@@ -0,0 +1,579 @@
+/*
+ * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
+ * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
+ * Copyright (c) 2004 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_mad.h 2775 2005-07-02 13:42:12Z halr $
+ */
+
+#if !defined( IB_MAD_H )
+#define IB_MAD_H
+
+#include <linux/pci.h>
+
+#include <rdma/ib_verbs.h>
+
+/* Management base version */
+#define IB_MGMT_BASE_VERSION                    1
+
+/* Management classes */
+#define IB_MGMT_CLASS_SUBN_LID_ROUTED           0x01
+#define IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE       0x81
+#define IB_MGMT_CLASS_SUBN_ADM                  0x03
+#define IB_MGMT_CLASS_PERF_MGMT                 0x04
+#define IB_MGMT_CLASS_BM                        0x05
+#define IB_MGMT_CLASS_DEVICE_MGMT               0x06
+#define IB_MGMT_CLASS_CM                        0x07
+#define IB_MGMT_CLASS_SNMP                      0x08
+#define IB_MGMT_CLASS_VENDOR_RANGE2_START       0x30
+#define IB_MGMT_CLASS_VENDOR_RANGE2_END         0x4F
+
+#define IB_OPENIB_OUI                           (0x001405)
+
+/* Management methods */
+#define IB_MGMT_METHOD_GET                      0x01
+#define IB_MGMT_METHOD_SET                      0x02
+#define IB_MGMT_METHOD_GET_RESP                 0x81
+#define IB_MGMT_METHOD_SEND                     0x03
+#define IB_MGMT_METHOD_TRAP                     0x05
+#define IB_MGMT_METHOD_REPORT                   0x06
+#define IB_MGMT_METHOD_REPORT_RESP              0x86
+#define IB_MGMT_METHOD_TRAP_REPRESS             0x07
+
+#define IB_MGMT_METHOD_RESP                     0x80
+
+#define IB_MGMT_MAX_METHODS                     128
+
+/* RMPP information */
+#define IB_MGMT_RMPP_VERSION                    1
+
+#define IB_MGMT_RMPP_TYPE_DATA                  1
+#define IB_MGMT_RMPP_TYPE_ACK                   2
+#define IB_MGMT_RMPP_TYPE_STOP                  3
+#define IB_MGMT_RMPP_TYPE_ABORT                 4
+
+#define IB_MGMT_RMPP_FLAG_ACTIVE                1
+#define IB_MGMT_RMPP_FLAG_FIRST                 (1<<1)
+#define IB_MGMT_RMPP_FLAG_LAST                  (1<<2)
+
+#define IB_MGMT_RMPP_NO_RESPTIME                0x1F
+
+#define IB_MGMT_RMPP_STATUS_SUCCESS             0
+#define IB_MGMT_RMPP_STATUS_RESX                1
+#define IB_MGMT_RMPP_STATUS_ABORT_MIN           118
+#define IB_MGMT_RMPP_STATUS_T2L                 118
+#define IB_MGMT_RMPP_STATUS_BAD_LEN             119
+#define IB_MGMT_RMPP_STATUS_BAD_SEG             120
+#define IB_MGMT_RMPP_STATUS_BADT                121
+#define IB_MGMT_RMPP_STATUS_W2S                 122
+#define IB_MGMT_RMPP_STATUS_S2B                 123
+#define IB_MGMT_RMPP_STATUS_BAD_STATUS          124
+#define IB_MGMT_RMPP_STATUS_UNV                 125
+#define IB_MGMT_RMPP_STATUS_TMR                 126
+#define IB_MGMT_RMPP_STATUS_UNSPEC              127
+#define IB_MGMT_RMPP_STATUS_ABORT_MAX           127
+
+#define IB_QP0          0
+#define IB_QP1          __constant_htonl(1)
+#define IB_QP1_QKEY     0x80010000
+#define IB_QP_SET_QKEY  0x80000000
+
+struct ib_mad_hdr {
+        u8      base_version;
+        u8      mgmt_class;
+        u8      class_version;
+        u8      method;
+        __be16  status;
+        __be16  class_specific;
+        __be64  tid;
+        __be16  attr_id;
+        __be16  resv;
+        __be32  attr_mod;
+};
+
+struct ib_rmpp_hdr {
+        u8      rmpp_version;
+        u8      rmpp_type;
+        u8      rmpp_rtime_flags;
+        u8      rmpp_status;
+        __be32  seg_num;
+        __be32  paylen_newwin;
+};
+
+typedef u64 __bitwise ib_sa_comp_mask;
+
+#define IB_SA_COMP_MASK(n) ((__force ib_sa_comp_mask) cpu_to_be64(1ull << n))
+
+/*
+ * ib_sa_hdr and ib_sa_mad structures must be packed because they have
+ * 64-bit fields that are only 32-bit aligned. 64-bit architectures will
+ * lay them out wrong otherwise.  (And unfortunately they are sent on
+ * the wire so we can't change the layout)
+ */
+struct ib_sa_hdr {
+        __be64                  sm_key;
+        __be16                  attr_offset;
+        __be16                  reserved;
+        ib_sa_comp_mask         comp_mask;
+} __attribute__ ((packed));
+
+struct ib_mad {
+        struct ib_mad_hdr       mad_hdr;
+        u8                      data[232];
+};
+
+struct ib_rmpp_mad {
+        struct ib_mad_hdr       mad_hdr;
+        struct ib_rmpp_hdr      rmpp_hdr;
+        u8                      data[220];
+};
+
+struct ib_sa_mad {
+        struct ib_mad_hdr       mad_hdr;
+        struct ib_rmpp_hdr      rmpp_hdr;
+        struct ib_sa_hdr        sa_hdr;
+        u8                      data[200];
+} __attribute__ ((packed));
+
+struct ib_vendor_mad {
+        struct ib_mad_hdr       mad_hdr;
+        struct ib_rmpp_hdr      rmpp_hdr;
+        u8                      reserved;
+        u8                      oui[3];
+        u8                      data[216];
+};
+
+/**
+ * ib_mad_send_buf - MAD data buffer and work request for sends.
+ * @mad: References an allocated MAD data buffer.  The size of the data
+ *   buffer is specified in the @send_wr.length field.
+ * @mapping: DMA mapping information.
+ * @mad_agent: MAD agent that allocated the buffer.
+ * @context: User-controlled context fields.
+ * @send_wr: An initialized work request structure used when sending the MAD.
+ *   The wr_id field of the work request is initialized to reference this
+ *   data structure.
+ * @sge: A scatter-gather list referenced by the work request.
+ *
+ * Users are responsible for initializing the MAD buffer itself, with the
+ * exception of specifying the payload length field in any RMPP MAD.
+ */
+struct ib_mad_send_buf {
+        struct ib_mad           *mad;
+        DECLARE_PCI_UNMAP_ADDR(mapping)
+        struct ib_mad_agent     *mad_agent;
+        void                    *context[2];
+        struct ib_send_wr       send_wr;
+        struct ib_sge           sge;
+};
+
+/**
+ * ib_get_rmpp_resptime - Returns the RMPP response time.
+ * @rmpp_hdr: An RMPP header.
+ */
+static inline u8 ib_get_rmpp_resptime(struct ib_rmpp_hdr *rmpp_hdr)
+{
+        return rmpp_hdr->rmpp_rtime_flags >> 3;
+}
+
+/**
+ * ib_get_rmpp_flags - Returns the RMPP flags.
+ * @rmpp_hdr: An RMPP header.
+ */
+static inline u8 ib_get_rmpp_flags(struct ib_rmpp_hdr *rmpp_hdr)
+{
+        return rmpp_hdr->rmpp_rtime_flags & 0x7;
+}
+
+/**
+ * ib_set_rmpp_resptime - Sets the response time in an RMPP header.
+ * @rmpp_hdr: An RMPP header.
+ * @rtime: The response time to set.
+ */
+static inline void ib_set_rmpp_resptime(struct ib_rmpp_hdr *rmpp_hdr, u8 rtime)
+{
+        rmpp_hdr->rmpp_rtime_flags = ib_get_rmpp_flags(rmpp_hdr) | (rtime << 3);
+}
+
+/**
+ * ib_set_rmpp_flags - Sets the flags in an RMPP header.
+ * @rmpp_hdr: An RMPP header.
+ * @flags: The flags to set.
+ */
+static inline void ib_set_rmpp_flags(struct ib_rmpp_hdr *rmpp_hdr, u8 flags)
+{
+        rmpp_hdr->rmpp_rtime_flags = (rmpp_hdr->rmpp_rtime_flags & 0xF1) |
+                                     (flags & 0x7);
+}
+
+struct ib_mad_agent;
+struct ib_mad_send_wc;
+struct ib_mad_recv_wc;
+
+/**
+ * ib_mad_send_handler - callback handler for a sent MAD.
+ * @mad_agent: MAD agent that sent the MAD.
+ * @mad_send_wc: Send work completion information on the sent MAD.
+ */
+typedef void (*ib_mad_send_handler)(struct ib_mad_agent *mad_agent,
+                                    struct ib_mad_send_wc *mad_send_wc);
+
+/**
+ * ib_mad_snoop_handler - Callback handler for snooping sent MADs.
+ * @mad_agent: MAD agent that snooped the MAD.
+ * @send_wr: Work request information on the sent MAD.
+ * @mad_send_wc: Work completion information on the sent MAD.  Valid
+ *   only for snooping that occurs on a send completion.
+ *
+ * Clients snooping MADs should not modify data referenced by the @send_wr
+ * or @mad_send_wc.
+ */
+typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
+                                     struct ib_send_wr *send_wr,
+                                     struct ib_mad_send_wc *mad_send_wc);
+
+/**
+ * ib_mad_recv_handler - callback handler for a received MAD.
+ * @mad_agent: MAD agent requesting the received MAD.
+ * @mad_recv_wc: Received work completion information on the received MAD.
+ *
+ * MADs received in response to a send request operation will be handed to
+ * the user after the send operation completes.  All data buffers given
+ * to registered agents through this routine are owned by the receiving
+ * client, except for snooping agents.  Clients snooping MADs should not
+ * modify the data referenced by @mad_recv_wc.
+ */
+typedef void (*ib_mad_recv_handler)(struct ib_mad_agent *mad_agent,
+                                    struct ib_mad_recv_wc *mad_recv_wc);
+
+/**
+ * ib_mad_agent - Used to track MAD registration with the access layer.
+ * @device: Reference to device registration is on.
+ * @qp: Reference to QP used for sending and receiving MADs.
+ * @mr: Memory region for system memory usable for DMA.
+ * @recv_handler: Callback handler for a received MAD.
+ * @send_handler: Callback handler for a sent MAD.
+ * @snoop_handler: Callback handler for snooped sent MADs.
+ * @context: User-specified context associated with this registration.
+ * @hi_tid: Access layer assigned transaction ID for this client.
+ *   Unsolicited MADs sent by this client will have the upper 32-bits
+ *   of their TID set to this value.
+ * @port_num: Port number on which QP is registered
+ * @rmpp_version: If set, indicates the RMPP version used by this agent.
+ */
+struct ib_mad_agent {
+        struct ib_device        *device;
+        struct ib_qp            *qp;
+        struct ib_mr            *mr;
+        ib_mad_recv_handler     recv_handler;
+        ib_mad_send_handler     send_handler;
+        ib_mad_snoop_handler    snoop_handler;
+        void                    *context;
+        u32                     hi_tid;
+        u8                      port_num;
+        u8                      rmpp_version;
+};
+
+/**
+ * ib_mad_send_wc - MAD send completion information.
+ * @wr_id: Work request identifier associated with the send MAD request.
+ * @status: Completion status.
+ * @vendor_err: Optional vendor error information returned with a failed
+ *   request.
+ */
+struct ib_mad_send_wc {
+        u64                     wr_id;
+        enum ib_wc_status       status;
+        u32                     vendor_err;
+};
+
+/**
+ * ib_mad_recv_buf - received MAD buffer information.
+ * @list: Reference to next data buffer for a received RMPP MAD.
+ * @grh: References a data buffer containing the global route header.
+ *   The data refereced by this buffer is only valid if the GRH is
+ *   valid.
+ * @mad: References the start of the received MAD.
+ */
+struct ib_mad_recv_buf {
+        struct list_head        list;
+        struct ib_grh           *grh;
+        struct ib_mad           *mad;
+};
+
+/**
+ * ib_mad_recv_wc - received MAD information.
+ * @wc: Completion information for the received data.
+ * @recv_buf: Specifies the location of the received data buffer(s).
+ * @rmpp_list: Specifies a list of RMPP reassembled received MAD buffers.
+ * @mad_len: The length of the received MAD, without duplicated headers.
+ *
+ * For received response, the wr_id field of the wc is set to the wr_id
+ *   for the corresponding send request.
+ */
+struct ib_mad_recv_wc {
+        struct ib_wc            *wc;
+        struct ib_mad_recv_buf  recv_buf;
+        struct list_head        rmpp_list;
+        int                     mad_len;
+};
+
+/**
+ * ib_mad_reg_req - MAD registration request
+ * @mgmt_class: Indicates which management class of MADs should be receive
+ *   by the caller.  This field is only required if the user wishes to
+ *   receive unsolicited MADs, otherwise it should be 0.
+ * @mgmt_class_version: Indicates which version of MADs for the given
+ *   management class to receive.
+ * @oui: Indicates IEEE OUI when mgmt_class is a vendor class
+ *   in the range from 0x30 to 0x4f. Otherwise not used.
+ * @method_mask: The caller will receive unsolicited MADs for any method
+ *   where @method_mask = 1.
+ */
+struct ib_mad_reg_req {
+        u8      mgmt_class;
+        u8      mgmt_class_version;
+        u8      oui[3];
+        DECLARE_BITMAP(method_mask, IB_MGMT_MAX_METHODS);
+};
+
+/**
+ * ib_register_mad_agent - Register to send/receive MADs.
+ * @device: The device to register with.
+ * @port_num: The port on the specified device to use.
+ * @qp_type: Specifies which QP to access.  Must be either
+ *   IB_QPT_SMI or IB_QPT_GSI.
+ * @mad_reg_req: Specifies which unsolicited MADs should be received
+ *   by the caller.  This parameter may be NULL if the caller only
+ *   wishes to receive solicited responses.
+ * @rmpp_version: If set, indicates that the client will send
+ *   and receive MADs that contain the RMPP header for the given version.
+ *   If set to 0, indicates that RMPP is not used by this client.
+ * @send_handler: The completion callback routine invoked after a send
+ *   request has completed.
+ * @recv_handler: The completion callback routine invoked for a received
+ *   MAD.
+ * @context: User specified context associated with the registration.
+ */
+struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
+                                           u8 port_num,
+                                           enum ib_qp_type qp_type,
+                                           struct ib_mad_reg_req *mad_reg_req,
+                                           u8 rmpp_version,
+                                           ib_mad_send_handler send_handler,
+                                           ib_mad_recv_handler recv_handler,
+                                           void *context);
+
+enum ib_mad_snoop_flags {
+        /*IB_MAD_SNOOP_POSTED_SENDS        = 1,*/
+        /*IB_MAD_SNOOP_RMPP_SENDS          = (1<<1),*/
+        IB_MAD_SNOOP_SEND_COMPLETIONS      = (1<<2),
+        /*IB_MAD_SNOOP_RMPP_SEND_COMPLETIONS = (1<<3),*/
+        IB_MAD_SNOOP_RECVS                 = (1<<4)
+        /*IB_MAD_SNOOP_RMPP_RECVS          = (1<<5),*/
+        /*IB_MAD_SNOOP_REDIRECTED_QPS      = (1<<6)*/
+};
+
+/**
+ * ib_register_mad_snoop - Register to snoop sent and received MADs.
+ * @device: The device to register with.
+ * @port_num: The port on the specified device to use.
+ * @qp_type: Specifies which QP traffic to snoop.  Must be either
+ *   IB_QPT_SMI or IB_QPT_GSI.
+ * @mad_snoop_flags: Specifies information where snooping occurs.
+ * @send_handler: The callback routine invoked for a snooped send.
+ * @recv_handler: The callback routine invoked for a snooped receive.
+ * @context: User specified context associated with the registration.
+ */
+struct ib_mad_agent *ib_register_mad_snoop(struct ib_device *device,
+                                           u8 port_num,
+                                           enum ib_qp_type qp_type,
+                                           int mad_snoop_flags,
+                                           ib_mad_snoop_handler snoop_handler,
+                                           ib_mad_recv_handler recv_handler,
+                                           void *context);
+
+/**
+ * ib_unregister_mad_agent - Unregisters a client from using MAD services.
+ * @mad_agent: Corresponding MAD registration request to deregister.
+ *
+ * After invoking this routine, MAD services are no longer usable by the
+ * client on the associated QP.
+ */
+int ib_unregister_mad_agent(struct ib_mad_agent *mad_agent);
+
+/**
+ * ib_post_send_mad - Posts MAD(s) to the send queue of the QP associated
+ *   with the registered client.
+ * @mad_agent: Specifies the associated registration to post the send to.
+ * @send_wr: Specifies the information needed to send the MAD(s).
+ * @bad_send_wr: Specifies the MAD on which an error was encountered.
+ *
+ * Sent MADs are not guaranteed to complete in the order that they were posted.
+ *
+ * If the MAD requires RMPP, the data buffer should contain a single copy
+ * of the common MAD, RMPP, and class specific headers, followed by the class
+ * defined data.  If the class defined data would not divide evenly into
+ * RMPP segments, then space must be allocated at the end of the referenced
+ * buffer for any required padding.  To indicate the amount of class defined
+ * data being transferred, the paylen_newwin field in the RMPP header should
+ * be set to the size of the class specific header plus the amount of class
+ * defined data being transferred.  The paylen_newwin field should be
+ * specified in network-byte order.
+ */
+int ib_post_send_mad(struct ib_mad_agent *mad_agent,
+                     struct ib_send_wr *send_wr,
+                     struct ib_send_wr **bad_send_wr);
+
+/**
+ * ib_coalesce_recv_mad - Coalesces received MAD data into a single buffer.
+ * @mad_recv_wc: Work completion information for a received MAD.
+ * @buf: User-provided data buffer to receive the coalesced buffers.  The
+ *   referenced buffer should be at least the size of the mad_len specified
+ *   by @mad_recv_wc.
+ *
+ * This call copies a chain of received MAD segments into a single data buffer,
+ * removing duplicated headers.
+ */
+void ib_coalesce_recv_mad(struct ib_mad_recv_wc *mad_recv_wc, void *buf);
+
+/**
+ * ib_free_recv_mad - Returns data buffers used to receive a MAD.
+ * @mad_recv_wc: Work completion information for a received MAD.
+ *
+ * Clients receiving MADs through their ib_mad_recv_handler must call this
+ * routine to return the work completion buffers to the access layer.
+ */
+void ib_free_recv_mad(struct ib_mad_recv_wc *mad_recv_wc);
+
+/**
+ * ib_cancel_mad - Cancels an outstanding send MAD operation.
+ * @mad_agent: Specifies the registration associated with sent MAD.
+ * @wr_id: Indicates the work request identifier of the MAD to cancel.
+ *
+ * MADs will be returned to the user through the corresponding
+ * ib_mad_send_handler.
+ */
+void ib_cancel_mad(struct ib_mad_agent *mad_agent, u64 wr_id);
+
+/**
+ * ib_modify_mad - Modifies an outstanding send MAD operation.
+ * @mad_agent: Specifies the registration associated with sent MAD.
+ * @wr_id: Indicates the work request identifier of the MAD to modify.
+ * @timeout_ms: New timeout value for sent MAD.
+ *
+ * This call will reset the timeout value for a sent MAD to the specified
+ * value.
+ */
+int ib_modify_mad(struct ib_mad_agent *mad_agent, u64 wr_id, u32 timeout_ms);
+
+/**
+ * ib_redirect_mad_qp - Registers a QP for MAD services.
+ * @qp: Reference to a QP that requires MAD services.
+ * @rmpp_version: If set, indicates that the client will send
+ *   and receive MADs that contain the RMPP header for the given version.
+ *   If set to 0, indicates that RMPP is not used by this client.
+ * @send_handler: The completion callback routine invoked after a send
+ *   request has completed.
+ * @recv_handler: The completion callback routine invoked for a received
+ *   MAD.
+ * @context: User specified context associated with the registration.
+ *
+ * Use of this call allows clients to use MAD services, such as RMPP,
+ * on user-owned QPs.  After calling this routine, users may send
+ * MADs on the specified QP by calling ib_mad_post_send.
+ */
+struct ib_mad_agent *ib_redirect_mad_qp(struct ib_qp *qp,
+                                        u8 rmpp_version,
+                                        ib_mad_send_handler send_handler,
+                                        ib_mad_recv_handler recv_handler,
+                                        void *context);
+
+/**
+ * ib_process_mad_wc - Processes a work completion associated with a
+ *   MAD sent or received on a redirected QP.
+ * @mad_agent: Specifies the registered MAD service using the redirected QP.
+ * @wc: References a work completion associated with a sent or received
+ *   MAD segment.
+ *
+ * This routine is used to complete or continue processing on a MAD request.
+ * If the work completion is associated with a send operation, calling
+ * this routine is required to continue an RMPP transfer or to wait for a
+ * corresponding response, if it is a request.  If the work completion is
+ * associated with a receive operation, calling this routine is required to
+ * process an inbound or outbound RMPP transfer, or to match a response MAD
+ * with its corresponding request.
+ */
+int ib_process_mad_wc(struct ib_mad_agent *mad_agent,
+                      struct ib_wc *wc);
+
+/**
+ * ib_create_send_mad - Allocate and initialize a data buffer and work request
+ *   for sending a MAD.
+ * @mad_agent: Specifies the registered MAD service to associate with the MAD.
+ * @remote_qpn: Specifies the QPN of the receiving node.
+ * @pkey_index: Specifies which PKey the MAD will be sent using.  This field
+ *   is valid only if the remote_qpn is QP 1.
+ * @ah: References the address handle used to transfer to the remote node.
+ * @rmpp_active: Indicates if the send will enable RMPP.
+ * @hdr_len: Indicates the size of the data header of the MAD.  This length
+ *   should include the common MAD header, RMPP header, plus any class
+ *   specific header.
+ * @data_len: Indicates the size of any user-transferred data.  The call will
+ *   automatically adjust the allocated buffer size to account for any
+ *   additional padding that may be necessary.
+ * @gfp_mask: GFP mask used for the memory allocation.
+ *
+ * This is a helper routine that may be used to allocate a MAD.  Users are
+ * not required to allocate outbound MADs using this call.  The returned
+ * MAD send buffer will reference a data buffer usable for sending a MAD, along
+ * with an initialized work request structure.  Users may modify the returned
+ * MAD data buffer or work request before posting the send.
+ *
+ * The returned data buffer will be cleared.  Users are responsible for
+ * initializing the common MAD and any class specific headers.  If @rmpp_active
+ * is set, the RMPP header will be initialized for sending.
+ */
+struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
+                                            u32 remote_qpn, u16 pkey_index,
+                                            struct ib_ah *ah, int rmpp_active,
+                                            int hdr_len, int data_len,
+                                            unsigned int __nocast gfp_mask);
+
+/**
+ * ib_free_send_mad - Returns data buffers used to send a MAD.
+ * @send_buf: Previously allocated send data buffer.
+ */
+void ib_free_send_mad(struct ib_mad_send_buf *send_buf);
+
+#endif /* IB_MAD_H */
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
new file mode 100644
index 000000000000..f926020d6331
--- /dev/null
+++ b/include/rdma/ib_pack.h
@@ -0,0 +1,245 @@
+/*
+ * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_pack.h 1349 2004-12-16 21:09:43Z roland $
+ */
+
+#ifndef IB_PACK_H
+#define IB_PACK_H
+
+#include <rdma/ib_verbs.h>
+
+enum {
+        IB_LRH_BYTES  = 8,
+        IB_GRH_BYTES  = 40,
+        IB_BTH_BYTES  = 12,
+        IB_DETH_BYTES = 8
+};
+
+struct ib_field {
+        size_t struct_offset_bytes;
+        size_t struct_size_bytes;
+        int    offset_words;
+        int    offset_bits;
+        int    size_bits;
+        char  *field_name;
+};
+
+#define RESERVED \
+        .field_name          = "reserved"
+
+/*
+ * This macro cleans up the definitions of constants for BTH opcodes.
+ * It is used to define constants such as IB_OPCODE_UD_SEND_ONLY,
+ * which becomes IB_OPCODE_UD + IB_OPCODE_SEND_ONLY, and this gives
+ * the correct value.
+ *
+ * In short, user code should use the constants defined using the
+ * macro rather than worrying about adding together other constants.
+*/
+#define IB_OPCODE(transport, op) \
+        IB_OPCODE_ ## transport ## _ ## op = \
+                IB_OPCODE_ ## transport + IB_OPCODE_ ## op
+
+enum {
+        /* transport types -- just used to define real constants */
+        IB_OPCODE_RC                                = 0x00,
+        IB_OPCODE_UC                                = 0x20,
+        IB_OPCODE_RD                                = 0x40,
+        IB_OPCODE_UD                                = 0x60,
+
+        /* operations -- just used to define real constants */
+        IB_OPCODE_SEND_FIRST                        = 0x00,
+        IB_OPCODE_SEND_MIDDLE                       = 0x01,
+        IB_OPCODE_SEND_LAST                         = 0x02,
+        IB_OPCODE_SEND_LAST_WITH_IMMEDIATE          = 0x03,
+        IB_OPCODE_SEND_ONLY                         = 0x04,
+        IB_OPCODE_SEND_ONLY_WITH_IMMEDIATE          = 0x05,
+        IB_OPCODE_RDMA_WRITE_FIRST                  = 0x06,
+        IB_OPCODE_RDMA_WRITE_MIDDLE                 = 0x07,
+        IB_OPCODE_RDMA_WRITE_LAST                   = 0x08,
+        IB_OPCODE_RDMA_WRITE_LAST_WITH_IMMEDIATE    = 0x09,
+        IB_OPCODE_RDMA_WRITE_ONLY                   = 0x0a,
+        IB_OPCODE_RDMA_WRITE_ONLY_WITH_IMMEDIATE    = 0x0b,
+        IB_OPCODE_RDMA_READ_REQUEST                 = 0x0c,
+        IB_OPCODE_RDMA_READ_RESPONSE_FIRST          = 0x0d,
+        IB_OPCODE_RDMA_READ_RESPONSE_MIDDLE         = 0x0e,
+        IB_OPCODE_RDMA_READ_RESPONSE_LAST           = 0x0f,
+        IB_OPCODE_RDMA_READ_RESPONSE_ONLY           = 0x10,
+        IB_OPCODE_ACKNOWLEDGE                       = 0x11,
+        IB_OPCODE_ATOMIC_ACKNOWLEDGE                = 0x12,
+        IB_OPCODE_COMPARE_SWAP                      = 0x13,
+        IB_OPCODE_FETCH_ADD                         = 0x14,
+
+        /* real constants follow -- see comment about above IB_OPCODE()
+           macro for more details */
+
+        /* RC */
+        IB_OPCODE(RC, SEND_FIRST),
+        IB_OPCODE(RC, SEND_MIDDLE),
+        IB_OPCODE(RC, SEND_LAST),
+        IB_OPCODE(RC, SEND_LAST_WITH_IMMEDIATE),
+        IB_OPCODE(RC, SEND_ONLY),
+        IB_OPCODE(RC, SEND_ONLY_WITH_IMMEDIATE),
+        IB_OPCODE(RC, RDMA_WRITE_FIRST),
+        IB_OPCODE(RC, RDMA_WRITE_MIDDLE),
+        IB_OPCODE(RC, RDMA_WRITE_LAST),
+        IB_OPCODE(RC, RDMA_WRITE_LAST_WITH_IMMEDIATE),
+        IB_OPCODE(RC, RDMA_WRITE_ONLY),
+        IB_OPCODE(RC, RDMA_WRITE_ONLY_WITH_IMMEDIATE),
+        IB_OPCODE(RC, RDMA_READ_REQUEST),
+        IB_OPCODE(RC, RDMA_READ_RESPONSE_FIRST),
+        IB_OPCODE(RC, RDMA_READ_RESPONSE_MIDDLE),
+        IB_OPCODE(RC, RDMA_READ_RESPONSE_LAST),
+        IB_OPCODE(RC, RDMA_READ_RESPONSE_ONLY),
+        IB_OPCODE(RC, ACKNOWLEDGE),
+        IB_OPCODE(RC, ATOMIC_ACKNOWLEDGE),
+        IB_OPCODE(RC, COMPARE_SWAP),
+        IB_OPCODE(RC, FETCH_ADD),
+
+        /* UC */
+        IB_OPCODE(UC, SEND_FIRST),
+        IB_OPCODE(UC, SEND_MIDDLE),
+        IB_OPCODE(UC, SEND_LAST),
+        IB_OPCODE(UC, SEND_LAST_WITH_IMMEDIATE),
+        IB_OPCODE(UC, SEND_ONLY),
+        IB_OPCODE(UC, SEND_ONLY_WITH_IMMEDIATE),
+        IB_OPCODE(UC, RDMA_WRITE_FIRST),
+        IB_OPCODE(UC, RDMA_WRITE_MIDDLE),
+        IB_OPCODE(UC, RDMA_WRITE_LAST),
+        IB_OPCODE(UC, RDMA_WRITE_LAST_WITH_IMMEDIATE),
+        IB_OPCODE(UC, RDMA_WRITE_ONLY),
+        IB_OPCODE(UC, RDMA_WRITE_ONLY_WITH_IMMEDIATE),
+
+        /* RD */
+        IB_OPCODE(RD, SEND_FIRST),
+        IB_OPCODE(RD, SEND_MIDDLE),
+        IB_OPCODE(RD, SEND_LAST),
+        IB_OPCODE(RD, SEND_LAST_WITH_IMMEDIATE),
+        IB_OPCODE(RD, SEND_ONLY),
+        IB_OPCODE(RD, SEND_ONLY_WITH_IMMEDIATE),
+        IB_OPCODE(RD, RDMA_WRITE_FIRST),
+        IB_OPCODE(RD, RDMA_WRITE_MIDDLE),
+        IB_OPCODE(RD, RDMA_WRITE_LAST),
+        IB_OPCODE(RD, RDMA_WRITE_LAST_WITH_IMMEDIATE),
+        IB_OPCODE(RD, RDMA_WRITE_ONLY),
+        IB_OPCODE(RD, RDMA_WRITE_ONLY_WITH_IMMEDIATE),
+        IB_OPCODE(RD, RDMA_READ_REQUEST),
+        IB_OPCODE(RD, RDMA_READ_RESPONSE_FIRST),
+        IB_OPCODE(RD, RDMA_READ_RESPONSE_MIDDLE),
+        IB_OPCODE(RD, RDMA_READ_RESPONSE_LAST),
+        IB_OPCODE(RD, RDMA_READ_RESPONSE_ONLY),
+        IB_OPCODE(RD, ACKNOWLEDGE),
+        IB_OPCODE(RD, ATOMIC_ACKNOWLEDGE),
+        IB_OPCODE(RD, COMPARE_SWAP),
+        IB_OPCODE(RD, FETCH_ADD),
+
+        /* UD */
+        IB_OPCODE(UD, SEND_ONLY),
+        IB_OPCODE(UD, SEND_ONLY_WITH_IMMEDIATE)
+};
+
+enum {
+        IB_LNH_RAW        = 0,
+        IB_LNH_IP         = 1,
+        IB_LNH_IBA_LOCAL  = 2,
+        IB_LNH_IBA_GLOBAL = 3
+};
+
+struct ib_unpacked_lrh {
+        u8        virtual_lane;
+        u8        link_version;
+        u8        service_level;
+        u8        link_next_header;
+        __be16    destination_lid;
+        __be16    packet_length;
+        __be16    source_lid;
+};
+
+struct ib_unpacked_grh {
+        u8           ip_version;
+        u8           traffic_class;
+        __be32       flow_label;
+        __be16       payload_length;
+        u8           next_header;
+        u8           hop_limit;
+        union ib_gid source_gid;
+        union ib_gid destination_gid;
+};
+
+struct ib_unpacked_bth {
+        u8           opcode;
+        u8           solicited_event;
+        u8           mig_req;
+        u8           pad_count;
+        u8           transport_header_version;
+        __be16       pkey;
+        __be32       destination_qpn;
+        u8           ack_req;
+        __be32       psn;
+};
+
+struct ib_unpacked_deth {
+        __be32       qkey;
+        __be32       source_qpn;
+};
+
+struct ib_ud_header {
+        struct ib_unpacked_lrh  lrh;
+        int                     grh_present;
+        struct ib_unpacked_grh  grh;
+        struct ib_unpacked_bth  bth;
+        struct ib_unpacked_deth deth;
+        int                     immediate_present;
+        __be32                  immediate_data;
+};
+
+void ib_pack(const struct ib_field        *desc,
+             int                           desc_len,
+             void                         *structure,
+             void                         *buf);
+
+void ib_unpack(const struct ib_field        *desc,
+               int                           desc_len,
+               void                         *buf,
+               void                         *structure);
+
+void ib_ud_header_init(int                 payload_bytes,
+                       int                 grh_present,
+                       struct ib_ud_header *header);
+
+int ib_ud_header_pack(struct ib_ud_header *header,
+                      void                *buf);
+
+int ib_ud_header_unpack(void                *buf,
+                        struct ib_ud_header *header);
+
+#endif /* IB_PACK_H */
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
new file mode 100644
index 000000000000..c022edfc49da
--- /dev/null
+++ b/include/rdma/ib_sa.h
@@ -0,0 +1,373 @@
+/*
+ * Copyright (c) 2004 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Voltaire, Inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_sa.h 2811 2005-07-06 18:11:43Z halr $
+ */
+
+#ifndef IB_SA_H
+#define IB_SA_H
+
+#include <linux/compiler.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_mad.h>
+
+enum {
+        IB_SA_CLASS_VERSION             = 2,    /* IB spec version 1.1/1.2 */
+
+        IB_SA_METHOD_GET_TABLE          = 0x12,
+        IB_SA_METHOD_GET_TABLE_RESP     = 0x92,
+        IB_SA_METHOD_DELETE             = 0x15
+};
+
+enum ib_sa_selector {
+        IB_SA_GTE  = 0,
+        IB_SA_LTE  = 1,
+        IB_SA_EQ   = 2,
+        /*
+         * The meaning of "best" depends on the attribute: for
+         * example, for MTU best will return the largest available
+         * MTU, while for packet life time, best will return the
+         * smallest available life time.
+         */
+        IB_SA_BEST = 3
+};
+
+enum ib_sa_rate {
+        IB_SA_RATE_2_5_GBPS = 2,
+        IB_SA_RATE_5_GBPS   = 5,
+        IB_SA_RATE_10_GBPS  = 3,
+        IB_SA_RATE_20_GBPS  = 6,
+        IB_SA_RATE_30_GBPS  = 4,
+        IB_SA_RATE_40_GBPS  = 7,
+        IB_SA_RATE_60_GBPS  = 8,
+        IB_SA_RATE_80_GBPS  = 9,
+        IB_SA_RATE_120_GBPS = 10
+};
+
+static inline int ib_sa_rate_enum_to_int(enum ib_sa_rate rate)
+{
+        switch (rate) {
+        case IB_SA_RATE_2_5_GBPS: return  1;
+        case IB_SA_RATE_5_GBPS:   return  2;
+        case IB_SA_RATE_10_GBPS:  return  4;
+        case IB_SA_RATE_20_GBPS:  return  8;
+        case IB_SA_RATE_30_GBPS:  return 12;
+        case IB_SA_RATE_40_GBPS:  return 16;
+        case IB_SA_RATE_60_GBPS:  return 24;
+        case IB_SA_RATE_80_GBPS:  return 32;
+        case IB_SA_RATE_120_GBPS: return 48;
+        default:                  return -1;
+        }
+}
+
+/*
+ * Structures for SA records are named "struct ib_sa_xxx_rec."  No
+ * attempt is made to pack structures to match the physical layout of
+ * SA records in SA MADs; all packing and unpacking is handled by the
+ * SA query code.
+ *
+ * For a record with structure ib_sa_xxx_rec, the naming convention
+ * for the component mask value for field yyy is IB_SA_XXX_REC_YYY (we
+ * never use different abbreviations or otherwise change the spelling
+ * of xxx/yyy between ib_sa_xxx_rec.yyy and IB_SA_XXX_REC_YYY).
+ *
+ * Reserved rows are indicated with comments to help maintainability.
+ */
+
+/* reserved:                                                             0 */
+/* reserved:                                                             1 */
+#define IB_SA_PATH_REC_DGID                             IB_SA_COMP_MASK( 2)
+#define IB_SA_PATH_REC_SGID                             IB_SA_COMP_MASK( 3)
+#define IB_SA_PATH_REC_DLID                             IB_SA_COMP_MASK( 4)
+#define IB_SA_PATH_REC_SLID                             IB_SA_COMP_MASK( 5)
+#define IB_SA_PATH_REC_RAW_TRAFFIC                      IB_SA_COMP_MASK( 6)
+/* reserved:                                                             7 */
+#define IB_SA_PATH_REC_FLOW_LABEL                       IB_SA_COMP_MASK( 8)
+#define IB_SA_PATH_REC_HOP_LIMIT                        IB_SA_COMP_MASK( 9)
+#define IB_SA_PATH_REC_TRAFFIC_CLASS                    IB_SA_COMP_MASK(10)
+#define IB_SA_PATH_REC_REVERSIBLE                       IB_SA_COMP_MASK(11)
+#define IB_SA_PATH_REC_NUMB_PATH                        IB_SA_COMP_MASK(12)
+#define IB_SA_PATH_REC_PKEY                             IB_SA_COMP_MASK(13)
+/* reserved:                                                            14 */
+#define IB_SA_PATH_REC_SL                               IB_SA_COMP_MASK(15)
+#define IB_SA_PATH_REC_MTU_SELECTOR                     IB_SA_COMP_MASK(16)
+#define IB_SA_PATH_REC_MTU                              IB_SA_COMP_MASK(17)
+#define IB_SA_PATH_REC_RATE_SELECTOR                    IB_SA_COMP_MASK(18)
+#define IB_SA_PATH_REC_RATE                             IB_SA_COMP_MASK(19)
+#define IB_SA_PATH_REC_PACKET_LIFE_TIME_SELECTOR        IB_SA_COMP_MASK(20)
+#define IB_SA_PATH_REC_PACKET_LIFE_TIME                 IB_SA_COMP_MASK(21)
+#define IB_SA_PATH_REC_PREFERENCE                       IB_SA_COMP_MASK(22)
+
+struct ib_sa_path_rec {
+        /* reserved */
+        /* reserved */
+        union ib_gid dgid;
+        union ib_gid sgid;
+        __be16       dlid;
+        __be16       slid;
+        int          raw_traffic;
+        /* reserved */
+        __be32       flow_label;
+        u8           hop_limit;
+        u8           traffic_class;
+        int          reversible;
+        u8           numb_path;
+        __be16       pkey;
+        /* reserved */
+        u8           sl;
+        u8           mtu_selector;
+        u8           mtu;
+        u8           rate_selector;
+        u8           rate;
+        u8           packet_life_time_selector;
+        u8           packet_life_time;
+        u8           preference;
+};
+
+#define IB_SA_MCMEMBER_REC_MGID                         IB_SA_COMP_MASK( 0)
+#define IB_SA_MCMEMBER_REC_PORT_GID                     IB_SA_COMP_MASK( 1)
+#define IB_SA_MCMEMBER_REC_QKEY                         IB_SA_COMP_MASK( 2)
+#define IB_SA_MCMEMBER_REC_MLID                         IB_SA_COMP_MASK( 3)
+#define IB_SA_MCMEMBER_REC_MTU_SELECTOR                 IB_SA_COMP_MASK( 4)
+#define IB_SA_MCMEMBER_REC_MTU                          IB_SA_COMP_MASK( 5)
+#define IB_SA_MCMEMBER_REC_TRAFFIC_CLASS                IB_SA_COMP_MASK( 6)
+#define IB_SA_MCMEMBER_REC_PKEY                         IB_SA_COMP_MASK( 7)
+#define IB_SA_MCMEMBER_REC_RATE_SELECTOR                IB_SA_COMP_MASK( 8)
+#define IB_SA_MCMEMBER_REC_RATE                         IB_SA_COMP_MASK( 9)
+#define IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME_SELECTOR    IB_SA_COMP_MASK(10)
+#define IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME             IB_SA_COMP_MASK(11)
+#define IB_SA_MCMEMBER_REC_SL                           IB_SA_COMP_MASK(12)
+#define IB_SA_MCMEMBER_REC_FLOW_LABEL                   IB_SA_COMP_MASK(13)
+#define IB_SA_MCMEMBER_REC_HOP_LIMIT                    IB_SA_COMP_MASK(14)
+#define IB_SA_MCMEMBER_REC_SCOPE                        IB_SA_COMP_MASK(15)
+#define IB_SA_MCMEMBER_REC_JOIN_STATE                   IB_SA_COMP_MASK(16)
+#define IB_SA_MCMEMBER_REC_PROXY_JOIN                   IB_SA_COMP_MASK(17)
+
+struct ib_sa_mcmember_rec {
+        union ib_gid mgid;
+        union ib_gid port_gid;
+        __be32       qkey;
+        __be16       mlid;
+        u8           mtu_selector;
+        u8           mtu;
+        u8           traffic_class;
+        __be16       pkey;
+        u8           rate_selector;
+        u8           rate;
+        u8           packet_life_time_selector;
+        u8           packet_life_time;
+        u8           sl;
+        __be32       flow_label;
+        u8           hop_limit;
+        u8           scope;
+        u8           join_state;
+        int          proxy_join;
+};
+
+/* Service Record Component Mask Sec 15.2.5.14 Ver 1.1  */
+#define IB_SA_SERVICE_REC_SERVICE_ID                    IB_SA_COMP_MASK( 0)
+#define IB_SA_SERVICE_REC_SERVICE_GID                   IB_SA_COMP_MASK( 1)
+#define IB_SA_SERVICE_REC_SERVICE_PKEY                  IB_SA_COMP_MASK( 2)
+/* reserved:                                                             3 */
+#define IB_SA_SERVICE_REC_SERVICE_LEASE                 IB_SA_COMP_MASK( 4)
+#define IB_SA_SERVICE_REC_SERVICE_KEY                   IB_SA_COMP_MASK( 5)
+#define IB_SA_SERVICE_REC_SERVICE_NAME                  IB_SA_COMP_MASK( 6)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_0               IB_SA_COMP_MASK( 7)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_1               IB_SA_COMP_MASK( 8)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_2               IB_SA_COMP_MASK( 9)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_3               IB_SA_COMP_MASK(10)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_4               IB_SA_COMP_MASK(11)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_5               IB_SA_COMP_MASK(12)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_6               IB_SA_COMP_MASK(13)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_7               IB_SA_COMP_MASK(14)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_8               IB_SA_COMP_MASK(15)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_9               IB_SA_COMP_MASK(16)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_10              IB_SA_COMP_MASK(17)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_11              IB_SA_COMP_MASK(18)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_12              IB_SA_COMP_MASK(19)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_13              IB_SA_COMP_MASK(20)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_14              IB_SA_COMP_MASK(21)
+#define IB_SA_SERVICE_REC_SERVICE_DATA8_15              IB_SA_COMP_MASK(22)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_0              IB_SA_COMP_MASK(23)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_1              IB_SA_COMP_MASK(24)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_2              IB_SA_COMP_MASK(25)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_3              IB_SA_COMP_MASK(26)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_4              IB_SA_COMP_MASK(27)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_5              IB_SA_COMP_MASK(28)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_6              IB_SA_COMP_MASK(29)
+#define IB_SA_SERVICE_REC_SERVICE_DATA16_7              IB_SA_COMP_MASK(30)
+#define IB_SA_SERVICE_REC_SERVICE_DATA32_0              IB_SA_COMP_MASK(31)
+#define IB_SA_SERVICE_REC_SERVICE_DATA32_1              IB_SA_COMP_MASK(32)
+#define IB_SA_SERVICE_REC_SERVICE_DATA32_2              IB_SA_COMP_MASK(33)
+#define IB_SA_SERVICE_REC_SERVICE_DATA32_3              IB_SA_COMP_MASK(34)
+#define IB_SA_SERVICE_REC_SERVICE_DATA64_0              IB_SA_COMP_MASK(35)
+#define IB_SA_SERVICE_REC_SERVICE_DATA64_1              IB_SA_COMP_MASK(36)
+
+#define IB_DEFAULT_SERVICE_LEASE        0xFFFFFFFF
+
+struct ib_sa_service_rec {
+        u64             id;
+        union ib_gid    gid;
+        __be16          pkey;
+        /* reserved */
+        u32             lease;
+        u8              key[16];
+        u8              name[64];
+        u8              data8[16];
+        u16             data16[8];
+        u32             data32[4];
+        u64             data64[2];
+};
+
+struct ib_sa_query;
+
+void ib_sa_cancel_query(int id, struct ib_sa_query *query);
+
+int ib_sa_path_rec_get(struct ib_device *device, u8 port_num,
+                       struct ib_sa_path_rec *rec,
+                       ib_sa_comp_mask comp_mask,
+                       int timeout_ms, unsigned int __nocast gfp_mask,
+                       void (*callback)(int status,
+                                        struct ib_sa_path_rec *resp,
+                                        void *context),
+                       void *context,
+                       struct ib_sa_query **query);
+
+int ib_sa_mcmember_rec_query(struct ib_device *device, u8 port_num,
+                             u8 method,
+                             struct ib_sa_mcmember_rec *rec,
+                             ib_sa_comp_mask comp_mask,
+                             int timeout_ms, unsigned int __nocast gfp_mask,
+                             void (*callback)(int status,
+                                              struct ib_sa_mcmember_rec *resp,
+                                              void *context),
+                             void *context,
+                             struct ib_sa_query **query);
+
+int ib_sa_service_rec_query(struct ib_device *device, u8 port_num,
+                         u8 method,
+                         struct ib_sa_service_rec *rec,
+                         ib_sa_comp_mask comp_mask,
+                         int timeout_ms, unsigned int __nocast gfp_mask,
+                         void (*callback)(int status,
+                                          struct ib_sa_service_rec *resp,
+                                          void *context),
+                         void *context,
+                         struct ib_sa_query **sa_query);
+
+/**
+ * ib_sa_mcmember_rec_set - Start an MCMember set query
+ * @device:device to send query on
+ * @port_num: port number to send query on
+ * @rec:MCMember Record to send in query
+ * @comp_mask:component mask to send in query
+ * @timeout_ms:time to wait for response
+ * @gfp_mask:GFP mask to use for internal allocations
+ * @callback:function called when query completes, times out or is
+ * canceled
+ * @context:opaque user context passed to callback
+ * @sa_query:query context, used to cancel query
+ *
+ * Send an MCMember Set query to the SA (eg to join a multicast
+ * group).  The callback function will be called when the query
+ * completes (or fails); status is 0 for a successful response, -EINTR
+ * if the query is canceled, -ETIMEDOUT is the query timed out, or
+ * -EIO if an error occurred sending the query.  The resp parameter of
+ * the callback is only valid if status is 0.
+ *
+ * If the return value of ib_sa_mcmember_rec_set() is negative, it is
+ * an error code.  Otherwise it is a query ID that can be used to
+ * cancel the query.
+ */
+static inline int
+ib_sa_mcmember_rec_set(struct ib_device *device, u8 port_num,
+                       struct ib_sa_mcmember_rec *rec,
+                       ib_sa_comp_mask comp_mask,
+                       int timeout_ms, unsigned int __nocast gfp_mask,
+                       void (*callback)(int status,
+                                        struct ib_sa_mcmember_rec *resp,
+                                        void *context),
+                       void *context,
+                       struct ib_sa_query **query)
+{
+        return ib_sa_mcmember_rec_query(device, port_num,
+                                        IB_MGMT_METHOD_SET,
+                                        rec, comp_mask,
+                                        timeout_ms, gfp_mask, callback,
+                                        context, query);
+}
+
+/**
+ * ib_sa_mcmember_rec_delete - Start an MCMember delete query
+ * @device:device to send query on
+ * @port_num: port number to send query on
+ * @rec:MCMember Record to send in query
+ * @comp_mask:component mask to send in query
+ * @timeout_ms:time to wait for response
+ * @gfp_mask:GFP mask to use for internal allocations
+ * @callback:function called when query completes, times out or is
+ * canceled
+ * @context:opaque user context passed to callback
+ * @sa_query:query context, used to cancel query
+ *
+ * Send an MCMember Delete query to the SA (eg to leave a multicast
+ * group).  The callback function will be called when the query
+ * completes (or fails); status is 0 for a successful response, -EINTR
+ * if the query is canceled, -ETIMEDOUT is the query timed out, or
+ * -EIO if an error occurred sending the query.  The resp parameter of
+ * the callback is only valid if status is 0.
+ *
+ * If the return value of ib_sa_mcmember_rec_delete() is negative, it
+ * is an error code.  Otherwise it is a query ID that can be used to
+ * cancel the query.
+ */
+static inline int
+ib_sa_mcmember_rec_delete(struct ib_device *device, u8 port_num,
+                          struct ib_sa_mcmember_rec *rec,
+                          ib_sa_comp_mask comp_mask,
+                          int timeout_ms, unsigned int __nocast gfp_mask,
+                          void (*callback)(int status,
+                                           struct ib_sa_mcmember_rec *resp,
+                                           void *context),
+                          void *context,
+                          struct ib_sa_query **query)
+{
+        return ib_sa_mcmember_rec_query(device, port_num,
+                                        IB_SA_METHOD_DELETE,
+                                        rec, comp_mask,
+                                        timeout_ms, gfp_mask, callback,
+                                        context, query);
+}
+
+
+#endif /* IB_SA_H */
diff --git a/include/rdma/ib_smi.h b/include/rdma/ib_smi.h
new file mode 100644
index 000000000000..87f60737f695
--- /dev/null
+++ b/include/rdma/ib_smi.h
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
+ * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
+ * Copyright (c) 2004 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_smi.h 1389 2004-12-27 22:56:47Z roland $
+ */
+
+#if !defined( IB_SMI_H )
+#define IB_SMI_H
+
+#include <rdma/ib_mad.h>
+
+#define IB_SMP_DATA_SIZE                        64
+#define IB_SMP_MAX_PATH_HOPS                    64
+
+struct ib_smp {
+        u8      base_version;
+        u8      mgmt_class;
+        u8      class_version;
+        u8      method;
+        __be16  status;
+        u8      hop_ptr;
+        u8      hop_cnt;
+        __be64  tid;
+        __be16  attr_id;
+        __be16  resv;
+        __be32  attr_mod;
+        __be64  mkey;
+        __be16  dr_slid;
+        __be16  dr_dlid;
+        u8      reserved[28];
+        u8      data[IB_SMP_DATA_SIZE];
+        u8      initial_path[IB_SMP_MAX_PATH_HOPS];
+        u8      return_path[IB_SMP_MAX_PATH_HOPS];
+} __attribute__ ((packed));
+
+#define IB_SMP_DIRECTION                        __constant_htons(0x8000)
+
+/* Subnet management attributes */
+#define IB_SMP_ATTR_NOTICE                      __constant_htons(0x0002)
+#define IB_SMP_ATTR_NODE_DESC                   __constant_htons(0x0010)
+#define IB_SMP_ATTR_NODE_INFO                   __constant_htons(0x0011)
+#define IB_SMP_ATTR_SWITCH_INFO                 __constant_htons(0x0012)
+#define IB_SMP_ATTR_GUID_INFO                   __constant_htons(0x0014)
+#define IB_SMP_ATTR_PORT_INFO                   __constant_htons(0x0015)
+#define IB_SMP_ATTR_PKEY_TABLE                  __constant_htons(0x0016)
+#define IB_SMP_ATTR_SL_TO_VL_TABLE              __constant_htons(0x0017)
+#define IB_SMP_ATTR_VL_ARB_TABLE                __constant_htons(0x0018)
+#define IB_SMP_ATTR_LINEAR_FORWARD_TABLE        __constant_htons(0x0019)
+#define IB_SMP_ATTR_RANDOM_FORWARD_TABLE        __constant_htons(0x001A)
+#define IB_SMP_ATTR_MCAST_FORWARD_TABLE         __constant_htons(0x001B)
+#define IB_SMP_ATTR_SM_INFO                     __constant_htons(0x0020)
+#define IB_SMP_ATTR_VENDOR_DIAG                 __constant_htons(0x0030)
+#define IB_SMP_ATTR_LED_INFO                    __constant_htons(0x0031)
+#define IB_SMP_ATTR_VENDOR_MASK                 __constant_htons(0xFF00)
+
+static inline u8
+ib_get_smp_direction(struct ib_smp *smp)
+{
+        return ((smp->status & IB_SMP_DIRECTION) == IB_SMP_DIRECTION);
+}
+
+#endif /* IB_SMI_H */
diff --git a/include/rdma/ib_user_cm.h b/include/rdma/ib_user_cm.h
new file mode 100644
index 000000000000..72182d16778b
--- /dev/null
+++ b/include/rdma/ib_user_cm.h
@@ -0,0 +1,328 @@
+/*
+ * Copyright (c) 2005 Topspin Communications.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_user_cm.h 2576 2005-06-09 17:00:30Z libor $
+ */
+
+#ifndef IB_USER_CM_H
+#define IB_USER_CM_H
+
+#include <linux/types.h>
+
+#define IB_USER_CM_ABI_VERSION 1
+
+enum {
+        IB_USER_CM_CMD_CREATE_ID,
+        IB_USER_CM_CMD_DESTROY_ID,
+        IB_USER_CM_CMD_ATTR_ID,
+
+        IB_USER_CM_CMD_LISTEN,
+        IB_USER_CM_CMD_ESTABLISH,
+
+        IB_USER_CM_CMD_SEND_REQ,
+        IB_USER_CM_CMD_SEND_REP,
+        IB_USER_CM_CMD_SEND_RTU,
+        IB_USER_CM_CMD_SEND_DREQ,
+        IB_USER_CM_CMD_SEND_DREP,
+        IB_USER_CM_CMD_SEND_REJ,
+        IB_USER_CM_CMD_SEND_MRA,
+        IB_USER_CM_CMD_SEND_LAP,
+        IB_USER_CM_CMD_SEND_APR,
+        IB_USER_CM_CMD_SEND_SIDR_REQ,
+        IB_USER_CM_CMD_SEND_SIDR_REP,
+
+        IB_USER_CM_CMD_EVENT,
+};
+/*
+ * command ABI structures.
+ */
+struct ib_ucm_cmd_hdr {
+        __u32 cmd;
+        __u16 in;
+        __u16 out;
+};
+
+struct ib_ucm_create_id {
+        __u64 response;
+};
+
+struct ib_ucm_create_id_resp {
+        __u32 id;
+};
+
+struct ib_ucm_destroy_id {
+        __u32 id;
+};
+
+struct ib_ucm_attr_id {
+        __u64 response;
+        __u32 id;
+};
+
+struct ib_ucm_attr_id_resp {
+        __be64 service_id;
+        __be64 service_mask;
+        __be32 local_id;
+        __be32 remote_id;
+};
+
+struct ib_ucm_listen {
+        __be64 service_id;
+        __be64 service_mask;
+        __u32 id;
+};
+
+struct ib_ucm_establish {
+        __u32 id;
+};
+
+struct ib_ucm_private_data {
+        __u64 data;
+        __u32 id;
+        __u8  len;
+        __u8  reserved[3];
+};
+
+struct ib_ucm_path_rec {
+        __u8  dgid[16];
+        __u8  sgid[16];
+        __be16 dlid;
+        __be16 slid;
+        __u32 raw_traffic;
+        __be32 flow_label;
+        __u32 reversible;
+        __u32 mtu;
+        __be16 pkey;
+        __u8  hop_limit;
+        __u8  traffic_class;
+        __u8  numb_path;
+        __u8  sl;
+        __u8  mtu_selector;
+        __u8  rate_selector;
+        __u8  rate;
+        __u8  packet_life_time_selector;
+        __u8  packet_life_time;
+        __u8  preference;
+};
+
+struct ib_ucm_req {
+        __u32 id;
+        __u32 qpn;
+        __u32 qp_type;
+        __u32 psn;
+        __be64 sid;
+        __u64 data;
+        __u64 primary_path;
+        __u64 alternate_path;
+        __u8  len;
+        __u8  peer_to_peer;
+        __u8  responder_resources;
+        __u8  initiator_depth;
+        __u8  remote_cm_response_timeout;
+        __u8  flow_control;
+        __u8  local_cm_response_timeout;
+        __u8  retry_count;
+        __u8  rnr_retry_count;
+        __u8  max_cm_retries;
+        __u8  srq;
+        __u8  reserved[1];
+};
+
+struct ib_ucm_rep {
+        __u64 data;
+        __u32 id;
+        __u32 qpn;
+        __u32 psn;
+        __u8  len;
+        __u8  responder_resources;
+        __u8  initiator_depth;
+        __u8  target_ack_delay;
+        __u8  failover_accepted;
+        __u8  flow_control;
+        __u8  rnr_retry_count;
+        __u8  srq;
+};
+
+struct ib_ucm_info {
+        __u32 id;
+        __u32 status;
+        __u64 info;
+        __u64 data;
+        __u8  info_len;
+        __u8  data_len;
+        __u8  reserved[2];
+};
+
+struct ib_ucm_mra {
+        __u64 data;
+        __u32 id;
+        __u8  len;
+        __u8  timeout;
+        __u8  reserved[2];
+};
+
+struct ib_ucm_lap {
+        __u64 path;
+        __u64 data;
+        __u32 id;
+        __u8  len;
+        __u8  reserved[3];
+};
+
+struct ib_ucm_sidr_req {
+        __u32 id;
+        __u32 timeout;
+        __be64 sid;
+        __u64 data;
+        __u64 path;
+        __u16 pkey;
+        __u8  len;
+        __u8  max_cm_retries;
+};
+
+struct ib_ucm_sidr_rep {
+        __u32 id;
+        __u32 qpn;
+        __u32 qkey;
+        __u32 status;
+        __u64 info;
+        __u64 data;
+        __u8  info_len;
+        __u8  data_len;
+        __u8  reserved[2];
+};
+/*
+ * event notification ABI structures.
+ */
+struct ib_ucm_event_get {
+        __u64 response;
+        __u64 data;
+        __u64 info;
+        __u8  data_len;
+        __u8  info_len;
+        __u8  reserved[2];
+};
+
+struct ib_ucm_req_event_resp {
+        __u32                  listen_id;
+        /* device */
+        /* port */
+        struct ib_ucm_path_rec primary_path;
+        struct ib_ucm_path_rec alternate_path;
+        __be64                 remote_ca_guid;
+        __u32                  remote_qkey;
+        __u32                  remote_qpn;
+        __u32                  qp_type;
+        __u32                  starting_psn;
+        __u8  responder_resources;
+        __u8  initiator_depth;
+        __u8  local_cm_response_timeout;
+        __u8  flow_control;
+        __u8  remote_cm_response_timeout;
+        __u8  retry_count;
+        __u8  rnr_retry_count;
+        __u8  srq;
+};
+
+struct ib_ucm_rep_event_resp {
+        __be64 remote_ca_guid;
+        __u32 remote_qkey;
+        __u32 remote_qpn;
+        __u32 starting_psn;
+        __u8  responder_resources;
+        __u8  initiator_depth;
+        __u8  target_ack_delay;
+        __u8  failover_accepted;
+        __u8  flow_control;
+        __u8  rnr_retry_count;
+        __u8  srq;
+        __u8  reserved[1];
+};
+
+struct ib_ucm_rej_event_resp {
+        __u32 reason;
+        /* ari in ib_ucm_event_get info field. */
+};
+
+struct ib_ucm_mra_event_resp {
+        __u8  timeout;
+        __u8  reserved[3];
+};
+
+struct ib_ucm_lap_event_resp {
+        struct ib_ucm_path_rec path;
+};
+
+struct ib_ucm_apr_event_resp {
+        __u32 status;
+        /* apr info in ib_ucm_event_get info field. */
+};
+
+struct ib_ucm_sidr_req_event_resp {
+        __u32 listen_id;
+        /* device */
+        /* port */
+        __u16 pkey;
+        __u8  reserved[2];
+};
+
+struct ib_ucm_sidr_rep_event_resp {
+        __u32 status;
+        __u32 qkey;
+        __u32 qpn;
+        /* info in ib_ucm_event_get info field. */
+};
+
+#define IB_UCM_PRES_DATA      0x01
+#define IB_UCM_PRES_INFO      0x02
+#define IB_UCM_PRES_PRIMARY   0x04
+#define IB_UCM_PRES_ALTERNATE 0x08
+
+struct ib_ucm_event_resp {
+        __u32 id;
+        __u32 event;
+        __u32 present;
+        union {
+                struct ib_ucm_req_event_resp req_resp;
+                struct ib_ucm_rep_event_resp rep_resp;
+                struct ib_ucm_rej_event_resp rej_resp;
+                struct ib_ucm_mra_event_resp mra_resp;
+                struct ib_ucm_lap_event_resp lap_resp;
+                struct ib_ucm_apr_event_resp apr_resp;
+
+                struct ib_ucm_sidr_req_event_resp sidr_req_resp;
+                struct ib_ucm_sidr_rep_event_resp sidr_rep_resp;
+
+                __u32                             send_status;
+        } u;
+};
+
+#endif /* IB_USER_CM_H */
diff --git a/include/rdma/ib_user_mad.h b/include/rdma/ib_user_mad.h
new file mode 100644
index 000000000000..44537aa32e62
--- /dev/null
+++ b/include/rdma/ib_user_mad.h
@@ -0,0 +1,137 @@
+/*
+ * Copyright (c) 2004 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_user_mad.h 2814 2005-07-06 19:14:09Z halr $
+ */
+
+#ifndef IB_USER_MAD_H
+#define IB_USER_MAD_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define IB_USER_MAD_ABI_VERSION 5
+
+/*
+ * Make sure that all structs defined in this file remain laid out so
+ * that they pack the same way on 32-bit and 64-bit architectures (to
+ * avoid incompatibility between 32-bit userspace and 64-bit kernels).
+ */
+
+/**
+ * ib_user_mad_hdr - MAD packet header
+ * @id - ID of agent MAD received with/to be sent with
+ * @status - 0 on successful receive, ETIMEDOUT if no response
+ *   received (transaction ID in data[] will be set to TID of original
+ *   request) (ignored on send)
+ * @timeout_ms - Milliseconds to wait for response (unset on receive)
+ * @retries - Number of automatic retries to attempt
+ * @qpn - Remote QP number received from/to be sent to
+ * @qkey - Remote Q_Key to be sent with (unset on receive)
+ * @lid - Remote lid received from/to be sent to
+ * @sl - Service level received with/to be sent with
+ * @path_bits - Local path bits received with/to be sent with
+ * @grh_present - If set, GRH was received/should be sent
+ * @gid_index - Local GID index to send with (unset on receive)
+ * @hop_limit - Hop limit in GRH
+ * @traffic_class - Traffic class in GRH
+ * @gid - Remote GID in GRH
+ * @flow_label - Flow label in GRH
+ */
+struct ib_user_mad_hdr {
+        __u32   id;
+        __u32   status;
+        __u32   timeout_ms;
+        __u32   retries;
+        __u32   length;
+        __be32  qpn;
+        __be32  qkey;
+        __be16  lid;
+        __u8    sl;
+        __u8    path_bits;
+        __u8    grh_present;
+        __u8    gid_index;
+        __u8    hop_limit;
+        __u8    traffic_class;
+        __u8    gid[16];
+        __be32  flow_label;
+};
+
+/**
+ * ib_user_mad - MAD packet
+ * @hdr - MAD packet header
+ * @data - Contents of MAD
+ *
+ */
+struct ib_user_mad {
+        struct ib_user_mad_hdr hdr;
+        __u8    data[0];
+};
+
+/**
+ * ib_user_mad_reg_req - MAD registration request
+ * @id - Set by the kernel; used to identify agent in future requests.
+ * @qpn - Queue pair number; must be 0 or 1.
+ * @method_mask - The caller will receive unsolicited MADs for any method
+ *   where @method_mask = 1.
+ * @mgmt_class - Indicates which management class of MADs should be receive
+ *   by the caller.  This field is only required if the user wishes to
+ *   receive unsolicited MADs, otherwise it should be 0.
+ * @mgmt_class_version - Indicates which version of MADs for the given
+ *   management class to receive.
+ * @oui: Indicates IEEE OUI when mgmt_class is a vendor class
+ *   in the range from 0x30 to 0x4f. Otherwise not used.
+ * @rmpp_version: If set, indicates the RMPP version used.
+ *
+ */
+struct ib_user_mad_reg_req {
+        __u32   id;
+        __u32   method_mask[4];
+        __u8    qpn;
+        __u8    mgmt_class;
+        __u8    mgmt_class_version;
+        __u8    oui[3];
+        __u8    rmpp_version;
+};
+
+#define IB_IOCTL_MAGIC          0x1b
+
+#define IB_USER_MAD_REGISTER_AGENT      _IOWR(IB_IOCTL_MAGIC, 1, \
+                                              struct ib_user_mad_reg_req)
+
+#define IB_USER_MAD_UNREGISTER_AGENT    _IOW(IB_IOCTL_MAGIC, 2, __u32)
+
+#endif /* IB_USER_MAD_H */
diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h
new file mode 100644
index 000000000000..7ebb01c8f996
--- /dev/null
+++ b/include/rdma/ib_user_verbs.h
@@ -0,0 +1,422 @@
+/*
+ * Copyright (c) 2005 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Cisco Systems.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_user_verbs.h 2708 2005-06-24 17:27:21Z roland $
+ */
+
+#ifndef IB_USER_VERBS_H
+#define IB_USER_VERBS_H
+
+#include <linux/types.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define IB_USER_VERBS_ABI_VERSION       1
+
+enum {
+        IB_USER_VERBS_CMD_QUERY_PARAMS,
+        IB_USER_VERBS_CMD_GET_CONTEXT,
+        IB_USER_VERBS_CMD_QUERY_DEVICE,
+        IB_USER_VERBS_CMD_QUERY_PORT,
+        IB_USER_VERBS_CMD_QUERY_GID,
+        IB_USER_VERBS_CMD_QUERY_PKEY,
+        IB_USER_VERBS_CMD_ALLOC_PD,
+        IB_USER_VERBS_CMD_DEALLOC_PD,
+        IB_USER_VERBS_CMD_CREATE_AH,
+        IB_USER_VERBS_CMD_MODIFY_AH,
+        IB_USER_VERBS_CMD_QUERY_AH,
+        IB_USER_VERBS_CMD_DESTROY_AH,
+        IB_USER_VERBS_CMD_REG_MR,
+        IB_USER_VERBS_CMD_REG_SMR,
+        IB_USER_VERBS_CMD_REREG_MR,
+        IB_USER_VERBS_CMD_QUERY_MR,
+        IB_USER_VERBS_CMD_DEREG_MR,
+        IB_USER_VERBS_CMD_ALLOC_MW,
+        IB_USER_VERBS_CMD_BIND_MW,
+        IB_USER_VERBS_CMD_DEALLOC_MW,
+        IB_USER_VERBS_CMD_CREATE_CQ,
+        IB_USER_VERBS_CMD_RESIZE_CQ,
+        IB_USER_VERBS_CMD_DESTROY_CQ,
+        IB_USER_VERBS_CMD_POLL_CQ,
+        IB_USER_VERBS_CMD_PEEK_CQ,
+        IB_USER_VERBS_CMD_REQ_NOTIFY_CQ,
+        IB_USER_VERBS_CMD_CREATE_QP,
+        IB_USER_VERBS_CMD_QUERY_QP,
+        IB_USER_VERBS_CMD_MODIFY_QP,
+        IB_USER_VERBS_CMD_DESTROY_QP,
+        IB_USER_VERBS_CMD_POST_SEND,
+        IB_USER_VERBS_CMD_POST_RECV,
+        IB_USER_VERBS_CMD_ATTACH_MCAST,
+        IB_USER_VERBS_CMD_DETACH_MCAST,
+        IB_USER_VERBS_CMD_CREATE_SRQ,
+        IB_USER_VERBS_CMD_MODIFY_SRQ,
+        IB_USER_VERBS_CMD_QUERY_SRQ,
+        IB_USER_VERBS_CMD_DESTROY_SRQ,
+        IB_USER_VERBS_CMD_POST_SRQ_RECV
+};
+
+/*
+ * Make sure that all structs defined in this file remain laid out so
+ * that they pack the same way on 32-bit and 64-bit architectures (to
+ * avoid incompatibility between 32-bit userspace and 64-bit kernels).
+ * In particular do not use pointer types -- pass pointers in __u64
+ * instead.
+ */
+
+struct ib_uverbs_async_event_desc {
+        __u64 element;
+        __u32 event_type;       /* enum ib_event_type */
+        __u32 reserved;
+};
+
+struct ib_uverbs_comp_event_desc {
+        __u64 cq_handle;
+};
+
+/*
+ * All commands from userspace should start with a __u32 command field
+ * followed by __u16 in_words and out_words fields (which give the
+ * length of the command block and response buffer if any in 32-bit
+ * words).  The kernel driver will read these fields first and read
+ * the rest of the command struct based on these value.
+ */
+
+struct ib_uverbs_cmd_hdr {
+        __u32 command;
+        __u16 in_words;
+        __u16 out_words;
+};
+
+/*
+ * No driver_data for "query params" command, since this is intended
+ * to be a core function with no possible device dependence.
+ */
+struct ib_uverbs_query_params {
+        __u64 response;
+};
+
+struct ib_uverbs_query_params_resp {
+        __u32 num_cq_events;
+};
+
+struct ib_uverbs_get_context {
+        __u64 response;
+        __u64 cq_fd_tab;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_get_context_resp {
+        __u32 async_fd;
+        __u32 reserved;
+};
+
+struct ib_uverbs_query_device {
+        __u64 response;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_query_device_resp {
+        __u64 fw_ver;
+        __be64 node_guid;
+        __be64 sys_image_guid;
+        __u64 max_mr_size;
+        __u64 page_size_cap;
+        __u32 vendor_id;
+        __u32 vendor_part_id;
+        __u32 hw_ver;
+        __u32 max_qp;
+        __u32 max_qp_wr;
+        __u32 device_cap_flags;
+        __u32 max_sge;
+        __u32 max_sge_rd;
+        __u32 max_cq;
+        __u32 max_cqe;
+        __u32 max_mr;
+        __u32 max_pd;
+        __u32 max_qp_rd_atom;
+        __u32 max_ee_rd_atom;
+        __u32 max_res_rd_atom;
+        __u32 max_qp_init_rd_atom;
+        __u32 max_ee_init_rd_atom;
+        __u32 atomic_cap;
+        __u32 max_ee;
+        __u32 max_rdd;
+        __u32 max_mw;
+        __u32 max_raw_ipv6_qp;
+        __u32 max_raw_ethy_qp;
+        __u32 max_mcast_grp;
+        __u32 max_mcast_qp_attach;
+        __u32 max_total_mcast_qp_attach;
+        __u32 max_ah;
+        __u32 max_fmr;
+        __u32 max_map_per_fmr;
+        __u32 max_srq;
+        __u32 max_srq_wr;
+        __u32 max_srq_sge;
+        __u16 max_pkeys;
+        __u8  local_ca_ack_delay;
+        __u8  phys_port_cnt;
+        __u8  reserved[4];
+};
+
+struct ib_uverbs_query_port {
+        __u64 response;
+        __u8  port_num;
+        __u8  reserved[7];
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_query_port_resp {
+        __u32 port_cap_flags;
+        __u32 max_msg_sz;
+        __u32 bad_pkey_cntr;
+        __u32 qkey_viol_cntr;
+        __u32 gid_tbl_len;
+        __u16 pkey_tbl_len;
+        __u16 lid;
+        __u16 sm_lid;
+        __u8  state;
+        __u8  max_mtu;
+        __u8  active_mtu;
+        __u8  lmc;
+        __u8  max_vl_num;
+        __u8  sm_sl;
+        __u8  subnet_timeout;
+        __u8  init_type_reply;
+        __u8  active_width;
+        __u8  active_speed;
+        __u8  phys_state;
+        __u8  reserved[3];
+};
+
+struct ib_uverbs_query_gid {
+        __u64 response;
+        __u8  port_num;
+        __u8  index;
+        __u8  reserved[6];
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_query_gid_resp {
+        __u8  gid[16];
+};
+
+struct ib_uverbs_query_pkey {
+        __u64 response;
+        __u8  port_num;
+        __u8  index;
+        __u8  reserved[6];
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_query_pkey_resp {
+        __u16 pkey;
+        __u16 reserved;
+};
+
+struct ib_uverbs_alloc_pd {
+        __u64 response;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_alloc_pd_resp {
+        __u32 pd_handle;
+};
+
+struct ib_uverbs_dealloc_pd {
+        __u32 pd_handle;
+};
+
+struct ib_uverbs_reg_mr {
+        __u64 response;
+        __u64 start;
+        __u64 length;
+        __u64 hca_va;
+        __u32 pd_handle;
+        __u32 access_flags;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_reg_mr_resp {
+        __u32 mr_handle;
+        __u32 lkey;
+        __u32 rkey;
+};
+
+struct ib_uverbs_dereg_mr {
+        __u32 mr_handle;
+};
+
+struct ib_uverbs_create_cq {
+        __u64 response;
+        __u64 user_handle;
+        __u32 cqe;
+        __u32 event_handler;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_create_cq_resp {
+        __u32 cq_handle;
+        __u32 cqe;
+};
+
+struct ib_uverbs_destroy_cq {
+        __u32 cq_handle;
+};
+
+struct ib_uverbs_create_qp {
+        __u64 response;
+        __u64 user_handle;
+        __u32 pd_handle;
+        __u32 send_cq_handle;
+        __u32 recv_cq_handle;
+        __u32 srq_handle;
+        __u32 max_send_wr;
+        __u32 max_recv_wr;
+        __u32 max_send_sge;
+        __u32 max_recv_sge;
+        __u32 max_inline_data;
+        __u8  sq_sig_all;
+        __u8  qp_type;
+        __u8  is_srq;
+        __u8  reserved;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_create_qp_resp {
+        __u32 qp_handle;
+        __u32 qpn;
+};
+
+/*
+ * This struct needs to remain a multiple of 8 bytes to keep the
+ * alignment of the modify QP parameters.
+ */
+struct ib_uverbs_qp_dest {
+        __u8  dgid[16];
+        __u32 flow_label;
+        __u16 dlid;
+        __u16 reserved;
+        __u8  sgid_index;
+        __u8  hop_limit;
+        __u8  traffic_class;
+        __u8  sl;
+        __u8  src_path_bits;
+        __u8  static_rate;
+        __u8  is_global;
+        __u8  port_num;
+};
+
+struct ib_uverbs_modify_qp {
+        struct ib_uverbs_qp_dest dest;
+        struct ib_uverbs_qp_dest alt_dest;
+        __u32 qp_handle;
+        __u32 attr_mask;
+        __u32 qkey;
+        __u32 rq_psn;
+        __u32 sq_psn;
+        __u32 dest_qp_num;
+        __u32 qp_access_flags;
+        __u16 pkey_index;
+        __u16 alt_pkey_index;
+        __u8  qp_state;
+        __u8  cur_qp_state;
+        __u8  path_mtu;
+        __u8  path_mig_state;
+        __u8  en_sqd_async_notify;
+        __u8  max_rd_atomic;
+        __u8  max_dest_rd_atomic;
+        __u8  min_rnr_timer;
+        __u8  port_num;
+        __u8  timeout;
+        __u8  retry_cnt;
+        __u8  rnr_retry;
+        __u8  alt_port_num;
+        __u8  alt_timeout;
+        __u8  reserved[2];
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_modify_qp_resp {
+};
+
+struct ib_uverbs_destroy_qp {
+        __u32 qp_handle;
+};
+
+struct ib_uverbs_attach_mcast {
+        __u8  gid[16];
+        __u32 qp_handle;
+        __u16 mlid;
+        __u16 reserved;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_detach_mcast {
+        __u8  gid[16];
+        __u32 qp_handle;
+        __u16 mlid;
+        __u16 reserved;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_create_srq {
+        __u64 response;
+        __u64 user_handle;
+        __u32 pd_handle;
+        __u32 max_wr;
+        __u32 max_sge;
+        __u32 srq_limit;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_create_srq_resp {
+        __u32 srq_handle;
+};
+
+struct ib_uverbs_modify_srq {
+        __u32 srq_handle;
+        __u32 attr_mask;
+        __u32 max_wr;
+        __u32 max_sge;
+        __u32 srq_limit;
+        __u32 reserved;
+        __u64 driver_data[0];
+};
+
+struct ib_uverbs_destroy_srq {
+        __u32 srq_handle;
+};
+
+#endif /* IB_USER_VERBS_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
new file mode 100644
index 000000000000..e16cf94870f2
--- /dev/null
+++ b/include/rdma/ib_verbs.h
@@ -0,0 +1,1461 @@
+/*
+ * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
+ * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
+ * Copyright (c) 2004 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
+ * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
+ * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ * Copyright (c) 2005 Cisco Systems.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * $Id: ib_verbs.h 1349 2004-12-16 21:09:43Z roland $
+ */
+
+#if !defined(IB_VERBS_H)
+#define IB_VERBS_H
+
+#include <linux/types.h>
+#include <linux/device.h>
+
+#include <asm/atomic.h>
+#include <asm/scatterlist.h>
+#include <asm/uaccess.h>
+
+union ib_gid {
+        u8      raw[16];
+        struct {
+                __be64  subnet_prefix;
+                __be64  interface_id;
+        } global;
+};
+
+enum ib_node_type {
+        IB_NODE_CA      = 1,
+        IB_NODE_SWITCH,
+        IB_NODE_ROUTER
+};
+
+enum ib_device_cap_flags {
+        IB_DEVICE_RESIZE_MAX_WR         = 1,
+        IB_DEVICE_BAD_PKEY_CNTR         = (1<<1),
+        IB_DEVICE_BAD_QKEY_CNTR         = (1<<2),
+        IB_DEVICE_RAW_MULTI             = (1<<3),
+        IB_DEVICE_AUTO_PATH_MIG         = (1<<4),
+        IB_DEVICE_CHANGE_PHY_PORT       = (1<<5),
+        IB_DEVICE_UD_AV_PORT_ENFORCE    = (1<<6),
+        IB_DEVICE_CURR_QP_STATE_MOD     = (1<<7),
+        IB_DEVICE_SHUTDOWN_PORT         = (1<<8),
+        IB_DEVICE_INIT_TYPE             = (1<<9),
+        IB_DEVICE_PORT_ACTIVE_EVENT     = (1<<10),
+        IB_DEVICE_SYS_IMAGE_GUID        = (1<<11),
+        IB_DEVICE_RC_RNR_NAK_GEN        = (1<<12),
+        IB_DEVICE_SRQ_RESIZE            = (1<<13),
+        IB_DEVICE_N_NOTIFY_CQ           = (1<<14),
+};
+
+enum ib_atomic_cap {
+        IB_ATOMIC_NONE,
+        IB_ATOMIC_HCA,
+        IB_ATOMIC_GLOB
+};
+
+struct ib_device_attr {
+        u64                     fw_ver;
+        __be64                  node_guid;
+        __be64                  sys_image_guid;
+        u64                     max_mr_size;
+        u64                     page_size_cap;
+        u32                     vendor_id;
+        u32                     vendor_part_id;
+        u32                     hw_ver;
+        int                     max_qp;
+        int                     max_qp_wr;
+        int                     device_cap_flags;
+        int                     max_sge;
+        int                     max_sge_rd;
+        int                     max_cq;
+        int                     max_cqe;
+        int                     max_mr;
+        int                     max_pd;
+        int                     max_qp_rd_atom;
+        int                     max_ee_rd_atom;
+        int                     max_res_rd_atom;
+        int                     max_qp_init_rd_atom;
+        int                     max_ee_init_rd_atom;
+        enum ib_atomic_cap      atomic_cap;
+        int                     max_ee;
+        int                     max_rdd;
+        int                     max_mw;
+        int                     max_raw_ipv6_qp;
+        int                     max_raw_ethy_qp;
+        int                     max_mcast_grp;
+        int                     max_mcast_qp_attach;
+        int                     max_total_mcast_qp_attach;
+        int                     max_ah;
+        int                     max_fmr;
+        int                     max_map_per_fmr;
+        int                     max_srq;
+        int                     max_srq_wr;
+        int                     max_srq_sge;
+        u16                     max_pkeys;
+        u8                      local_ca_ack_delay;
+};
+
+enum ib_mtu {
+        IB_MTU_256  = 1,
+        IB_MTU_512  = 2,
+        IB_MTU_1024 = 3,
+        IB_MTU_2048 = 4,
+        IB_MTU_4096 = 5
+};
+
+static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
+{
+        switch (mtu) {
+        case IB_MTU_256:  return  256;
+        case IB_MTU_512:  return  512;
+        case IB_MTU_1024: return 1024;
+        case IB_MTU_2048: return 2048;
+        case IB_MTU_4096: return 4096;
+        default:          return -1;
+        }
+}
+
+enum ib_port_state {
+        IB_PORT_NOP             = 0,
+        IB_PORT_DOWN            = 1,
+        IB_PORT_INIT            = 2,
+        IB_PORT_ARMED           = 3,
+        IB_PORT_ACTIVE          = 4,
+        IB_PORT_ACTIVE_DEFER    = 5
+};
+
+enum ib_port_cap_flags {
+        IB_PORT_SM                              = 1 <<  1,
+        IB_PORT_NOTICE_SUP                      = 1 <<  2,
+        IB_PORT_TRAP_SUP                        = 1 <<  3,
+        IB_PORT_OPT_IPD_SUP                     = 1 <<  4,
+        IB_PORT_AUTO_MIGR_SUP                   = 1 <<  5,
+        IB_PORT_SL_MAP_SUP                      = 1 <<  6,
+        IB_PORT_MKEY_NVRAM                      = 1 <<  7,
+        IB_PORT_PKEY_NVRAM                      = 1 <<  8,
+        IB_PORT_LED_INFO_SUP                    = 1 <<  9,
+        IB_PORT_SM_DISABLED                     = 1 << 10,
+        IB_PORT_SYS_IMAGE_GUID_SUP              = 1 << 11,
+        IB_PORT_PKEY_SW_EXT_PORT_TRAP_SUP       = 1 << 12,
+        IB_PORT_CM_SUP                          = 1 << 16,
+        IB_PORT_SNMP_TUNNEL_SUP                 = 1 << 17,
+        IB_PORT_REINIT_SUP                      = 1 << 18,
+        IB_PORT_DEVICE_MGMT_SUP                 = 1 << 19,
+        IB_PORT_VENDOR_CLASS_SUP                = 1 << 20,
+        IB_PORT_DR_NOTICE_SUP                   = 1 << 21,
+        IB_PORT_CAP_MASK_NOTICE_SUP             = 1 << 22,
+        IB_PORT_BOOT_MGMT_SUP                   = 1 << 23,
+        IB_PORT_LINK_LATENCY_SUP                = 1 << 24,
+        IB_PORT_CLIENT_REG_SUP                  = 1 << 25
+};
+
+enum ib_port_width {
+        IB_WIDTH_1X     = 1,
+        IB_WIDTH_4X     = 2,
+        IB_WIDTH_8X     = 4,
+        IB_WIDTH_12X    = 8
+};
+
+static inline int ib_width_enum_to_int(enum ib_port_width width)
+{
+        switch (width) {
+        case IB_WIDTH_1X:  return  1;
+        case IB_WIDTH_4X:  return  4;
+        case IB_WIDTH_8X:  return  8;
+        case IB_WIDTH_12X: return 12;
+        default:          return -1;
+        }
+}
+
+struct ib_port_attr {
+        enum ib_port_state      state;
+        enum ib_mtu             max_mtu;
+        enum ib_mtu             active_mtu;
+        int                     gid_tbl_len;
+        u32                     port_cap_flags;
+        u32                     max_msg_sz;
+        u32                     bad_pkey_cntr;
+        u32                     qkey_viol_cntr;
+        u16                     pkey_tbl_len;
+        u16                     lid;
+        u16                     sm_lid;
+        u8                      lmc;
+        u8                      max_vl_num;
+        u8                      sm_sl;
+        u8                      subnet_timeout;
+        u8                      init_type_reply;
+        u8                      active_width;
+        u8                      active_speed;
+        u8                      phys_state;
+};
+
+enum ib_device_modify_flags {
+        IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1
+};
+
+struct ib_device_modify {
+        u64     sys_image_guid;
+};
+
+enum ib_port_modify_flags {
+        IB_PORT_SHUTDOWN                = 1,
+        IB_PORT_INIT_TYPE               = (1<<2),
+        IB_PORT_RESET_QKEY_CNTR         = (1<<3)
+};
+
+struct ib_port_modify {
+        u32     set_port_cap_mask;
+        u32     clr_port_cap_mask;
+        u8      init_type;
+};
+
+enum ib_event_type {
+        IB_EVENT_CQ_ERR,
+        IB_EVENT_QP_FATAL,
+        IB_EVENT_QP_REQ_ERR,
+        IB_EVENT_QP_ACCESS_ERR,
+        IB_EVENT_COMM_EST,
+        IB_EVENT_SQ_DRAINED,
+        IB_EVENT_PATH_MIG,
+        IB_EVENT_PATH_MIG_ERR,
+        IB_EVENT_DEVICE_FATAL,
+        IB_EVENT_PORT_ACTIVE,
+        IB_EVENT_PORT_ERR,
+        IB_EVENT_LID_CHANGE,
+        IB_EVENT_PKEY_CHANGE,
+        IB_EVENT_SM_CHANGE,
+        IB_EVENT_SRQ_ERR,
+        IB_EVENT_SRQ_LIMIT_REACHED,
+        IB_EVENT_QP_LAST_WQE_REACHED
+};
+
+struct ib_event {
+        struct ib_device        *device;
+        union {
+                struct ib_cq    *cq;
+                struct ib_qp    *qp;
+                struct ib_srq   *srq;
+                u8              port_num;
+        } element;
+        enum ib_event_type      event;
+};
+
+struct ib_event_handler {
+        struct ib_device *device;
+        void            (*handler)(struct ib_event_handler *, struct ib_event *);
+        struct list_head  list;
+};
+
+#define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler)          \
+        do {                                                    \
+                (_ptr)->device  = _device;                      \
+                (_ptr)->handler = _handler;                     \
+                INIT_LIST_HEAD(&(_ptr)->list);                  \
+        } while (0)
+
+struct ib_global_route {
+        union ib_gid    dgid;
+        u32             flow_label;
+        u8              sgid_index;
+        u8              hop_limit;
+        u8              traffic_class;
+};
+
+struct ib_grh {
+        __be32          version_tclass_flow;
+        __be16          paylen;
+        u8              next_hdr;
+        u8              hop_limit;
+        union ib_gid    sgid;
+        union ib_gid    dgid;
+};
+
+enum {
+        IB_MULTICAST_QPN = 0xffffff
+};
+
+#define IB_LID_PERMISSIVE       __constant_htons(0xFFFF)
+
+enum ib_ah_flags {
+        IB_AH_GRH       = 1
+};
+
+struct ib_ah_attr {
+        struct ib_global_route  grh;
+        u16                     dlid;
+        u8                      sl;
+        u8                      src_path_bits;
+        u8                      static_rate;
+        u8                      ah_flags;
+        u8                      port_num;
+};
+
+enum ib_wc_status {
+        IB_WC_SUCCESS,
+        IB_WC_LOC_LEN_ERR,
+        IB_WC_LOC_QP_OP_ERR,
+        IB_WC_LOC_EEC_OP_ERR,
+        IB_WC_LOC_PROT_ERR,
+        IB_WC_WR_FLUSH_ERR,
+        IB_WC_MW_BIND_ERR,
+        IB_WC_BAD_RESP_ERR,
+        IB_WC_LOC_ACCESS_ERR,
+        IB_WC_REM_INV_REQ_ERR,
+        IB_WC_REM_ACCESS_ERR,
+        IB_WC_REM_OP_ERR,
+        IB_WC_RETRY_EXC_ERR,
+        IB_WC_RNR_RETRY_EXC_ERR,
+        IB_WC_LOC_RDD_VIOL_ERR,
+        IB_WC_REM_INV_RD_REQ_ERR,
+        IB_WC_REM_ABORT_ERR,
+        IB_WC_INV_EECN_ERR,
+        IB_WC_INV_EEC_STATE_ERR,
+        IB_WC_FATAL_ERR,
+        IB_WC_RESP_TIMEOUT_ERR,
+        IB_WC_GENERAL_ERR
+};
+
+enum ib_wc_opcode {
+        IB_WC_SEND,
+        IB_WC_RDMA_WRITE,
+        IB_WC_RDMA_READ,
+        IB_WC_COMP_SWAP,
+        IB_WC_FETCH_ADD,
+        IB_WC_BIND_MW,
+/*
+ * Set value of IB_WC_RECV so consumers can test if a completion is a
+ * receive by testing (opcode & IB_WC_RECV).
+ */
+        IB_WC_RECV                      = 1 << 7,
+        IB_WC_RECV_RDMA_WITH_IMM
+};
+
+enum ib_wc_flags {
+        IB_WC_GRH               = 1,
+        IB_WC_WITH_IMM          = (1<<1)
+};
+
+struct ib_wc {
+        u64                     wr_id;
+        enum ib_wc_status       status;
+        enum ib_wc_opcode       opcode;
+        u32                     vendor_err;
+        u32                     byte_len;
+        __be32                  imm_data;
+        u32                     qp_num;
+        u32                     src_qp;
+        int                     wc_flags;
+        u16                     pkey_index;
+        u16                     slid;
+        u8                      sl;
+        u8                      dlid_path_bits;
+        u8                      port_num;       /* valid only for DR SMPs on switches */
+};
+
+enum ib_cq_notify {
+        IB_CQ_SOLICITED,
+        IB_CQ_NEXT_COMP
+};
+
+enum ib_srq_attr_mask {
+        IB_SRQ_MAX_WR   = 1 << 0,
+        IB_SRQ_LIMIT    = 1 << 1,
+};
+
+struct ib_srq_attr {
+        u32     max_wr;
+        u32     max_sge;
+        u32     srq_limit;
+};
+
+struct ib_srq_init_attr {
+        void                  (*event_handler)(struct ib_event *, void *);
+        void                   *srq_context;
+        struct ib_srq_attr      attr;
+};
+
+struct ib_qp_cap {
+        u32     max_send_wr;
+        u32     max_recv_wr;
+        u32     max_send_sge;
+        u32     max_recv_sge;
+        u32     max_inline_data;
+};
+
+enum ib_sig_type {
+        IB_SIGNAL_ALL_WR,
+        IB_SIGNAL_REQ_WR
+};
+
+enum ib_qp_type {
+        /*
+         * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries
+         * here (and in that order) since the MAD layer uses them as
+         * indices into a 2-entry table.
+         */
+        IB_QPT_SMI,
+        IB_QPT_GSI,
+
+        IB_QPT_RC,
+        IB_QPT_UC,
+        IB_QPT_UD,
+        IB_QPT_RAW_IPV6,
+        IB_QPT_RAW_ETY
+};
+
+struct ib_qp_init_attr {
+        void                  (*event_handler)(struct ib_event *, void *);
+        void                   *qp_context;
+        struct ib_cq           *send_cq;
+        struct ib_cq           *recv_cq;
+        struct ib_srq          *srq;
+        struct ib_qp_cap        cap;
+        enum ib_sig_type        sq_sig_type;
+        enum ib_qp_type         qp_type;
+        u8                      port_num; /* special QP types only */
+};
+
+enum ib_rnr_timeout {
+        IB_RNR_TIMER_655_36 =  0,
+        IB_RNR_TIMER_000_01 =  1,
+        IB_RNR_TIMER_000_02 =  2,
+        IB_RNR_TIMER_000_03 =  3,
+        IB_RNR_TIMER_000_04 =  4,
+        IB_RNR_TIMER_000_06 =  5,
+        IB_RNR_TIMER_000_08 =  6,
+        IB_RNR_TIMER_000_12 =  7,
+        IB_RNR_TIMER_000_16 =  8,
+        IB_RNR_TIMER_000_24 =  9,
+        IB_RNR_TIMER_000_32 = 10,
+        IB_RNR_TIMER_000_48 = 11,
+        IB_RNR_TIMER_000_64 = 12,
+        IB_RNR_TIMER_000_96 = 13,
+        IB_RNR_TIMER_001_28 = 14,
+        IB_RNR_TIMER_001_92 = 15,
+        IB_RNR_TIMER_002_56 = 16,
+        IB_RNR_TIMER_003_84 = 17,
+        IB_RNR_TIMER_005_12 = 18,
+        IB_RNR_TIMER_007_68 = 19,
+        IB_RNR_TIMER_010_24 = 20,
+        IB_RNR_TIMER_015_36 = 21,
+        IB_RNR_TIMER_020_48 = 22,
+        IB_RNR_TIMER_030_72 = 23,
+        IB_RNR_TIMER_040_96 = 24,
+        IB_RNR_TIMER_061_44 = 25,
+        IB_RNR_TIMER_081_92 = 26,
+        IB_RNR_TIMER_122_88 = 27,
+        IB_RNR_TIMER_163_84 = 28,
+        IB_RNR_TIMER_245_76 = 29,
+        IB_RNR_TIMER_327_68 = 30,
+        IB_RNR_TIMER_491_52 = 31
+};
+
+enum ib_qp_attr_mask {
+        IB_QP_STATE                     = 1,
+        IB_QP_CUR_STATE                 = (1<<1),
+        IB_QP_EN_SQD_ASYNC_NOTIFY       = (1<<2),
+        IB_QP_ACCESS_FLAGS              = (1<<3),
+        IB_QP_PKEY_INDEX                = (1<<4),
+        IB_QP_PORT                      = (1<<5),
+        IB_QP_QKEY                      = (1<<6),
+        IB_QP_AV                        = (1<<7),
+        IB_QP_PATH_MTU                  = (1<<8),
+        IB_QP_TIMEOUT                   = (1<<9),
+        IB_QP_RETRY_CNT                 = (1<<10),
+        IB_QP_RNR_RETRY                 = (1<<11),
+        IB_QP_RQ_PSN                    = (1<<12),
+        IB_QP_MAX_QP_RD_ATOMIC          = (1<<13),
+        IB_QP_ALT_PATH                  = (1<<14),
+        IB_QP_MIN_RNR_TIMER             = (1<<15),
+        IB_QP_SQ_PSN                    = (1<<16),
+        IB_QP_MAX_DEST_RD_ATOMIC        = (1<<17),
+        IB_QP_PATH_MIG_STATE            = (1<<18),
+        IB_QP_CAP                       = (1<<19),
+        IB_QP_DEST_QPN                  = (1<<20)
+};
+
+enum ib_qp_state {
+        IB_QPS_RESET,
+        IB_QPS_INIT,
+        IB_QPS_RTR,
+        IB_QPS_RTS,
+        IB_QPS_SQD,
+        IB_QPS_SQE,
+        IB_QPS_ERR
+};
+
+enum ib_mig_state {
+        IB_MIG_MIGRATED,
+        IB_MIG_REARM,
+        IB_MIG_ARMED
+};
+
+struct ib_qp_attr {
+        enum ib_qp_state        qp_state;
+        enum ib_qp_state        cur_qp_state;
+        enum ib_mtu             path_mtu;
+        enum ib_mig_state       path_mig_state;
+        u32                     qkey;
+        u32                     rq_psn;
+        u32                     sq_psn;
+        u32                     dest_qp_num;
+        int                     qp_access_flags;
+        struct ib_qp_cap        cap;
+        struct ib_ah_attr       ah_attr;
+        struct ib_ah_attr       alt_ah_attr;
+        u16                     pkey_index;
+        u16                     alt_pkey_index;
+        u8                      en_sqd_async_notify;
+        u8                      sq_draining;
+        u8                      max_rd_atomic;
+        u8                      max_dest_rd_atomic;
+        u8                      min_rnr_timer;
+        u8                      port_num;
+        u8                      timeout;
+        u8                      retry_cnt;
+        u8                      rnr_retry;
+        u8                      alt_port_num;
+        u8                      alt_timeout;
+};
+
+enum ib_wr_opcode {
+        IB_WR_RDMA_WRITE,
+        IB_WR_RDMA_WRITE_WITH_IMM,
+        IB_WR_SEND,
+        IB_WR_SEND_WITH_IMM,
+        IB_WR_RDMA_READ,
+        IB_WR_ATOMIC_CMP_AND_SWP,
+        IB_WR_ATOMIC_FETCH_AND_ADD
+};
+
+enum ib_send_flags {
+        IB_SEND_FENCE           = 1,
+        IB_SEND_SIGNALED        = (1<<1),
+        IB_SEND_SOLICITED       = (1<<2),
+        IB_SEND_INLINE          = (1<<3)
+};
+
+struct ib_sge {
+        u64     addr;
+        u32     length;
+        u32     lkey;
+};
+
+struct ib_send_wr {
+        struct ib_send_wr      *next;
+        u64                     wr_id;
+        struct ib_sge          *sg_list;
+        int                     num_sge;
+        enum ib_wr_opcode       opcode;
+        int                     send_flags;
+        __be32                  imm_data;
+        union {
+                struct {
+                        u64     remote_addr;
+                        u32     rkey;
+                } rdma;
+                struct {
+                        u64     remote_addr;
+                        u64     compare_add;
+                        u64     swap;
+                        u32     rkey;
+                } atomic;
+                struct {
+                        struct ib_ah *ah;
+                        struct ib_mad_hdr *mad_hdr;
+                        u32     remote_qpn;
+                        u32     remote_qkey;
+                        int     timeout_ms; /* valid for MADs only */
+                        int     retries;    /* valid for MADs only */
+                        u16     pkey_index; /* valid for GSI only */
+                        u8      port_num;   /* valid for DR SMPs on switch only */
+                } ud;
+        } wr;
+};
+
+struct ib_recv_wr {
+        struct ib_recv_wr      *next;
+        u64                     wr_id;
+        struct ib_sge          *sg_list;
+        int                     num_sge;
+};
+
+enum ib_access_flags {
+        IB_ACCESS_LOCAL_WRITE   = 1,
+        IB_ACCESS_REMOTE_WRITE  = (1<<1),
+        IB_ACCESS_REMOTE_READ   = (1<<2),
+        IB_ACCESS_REMOTE_ATOMIC = (1<<3),
+        IB_ACCESS_MW_BIND       = (1<<4)
+};
+
+struct ib_phys_buf {
+        u64      addr;
+        u64      size;
+};
+
+struct ib_mr_attr {
+        struct ib_pd    *pd;
+        u64             device_virt_addr;
+        u64             size;
+        int             mr_access_flags;
+        u32             lkey;
+        u32             rkey;
+};
+
+enum ib_mr_rereg_flags {
+        IB_MR_REREG_TRANS       = 1,
+        IB_MR_REREG_PD          = (1<<1),
+        IB_MR_REREG_ACCESS      = (1<<2)
+};
+
+struct ib_mw_bind {
+        struct ib_mr   *mr;
+        u64             wr_id;
+        u64             addr;
+        u32             length;
+        int             send_flags;
+        int             mw_access_flags;
+};
+
+struct ib_fmr_attr {
+        int     max_pages;
+        int     max_maps;
+        u8      page_size;
+};
+
+struct ib_ucontext {
+        struct ib_device       *device;
+        struct list_head        pd_list;
+        struct list_head        mr_list;
+        struct list_head        mw_list;
+        struct list_head        cq_list;
+        struct list_head        qp_list;
+        struct list_head        srq_list;
+        struct list_head        ah_list;
+        spinlock_t              lock;
+};
+
+struct ib_uobject {
+        u64                     user_handle;    /* handle given to us by userspace */
+        struct ib_ucontext     *context;        /* associated user context */
+        struct list_head        list;           /* link to context's list */
+        u32                     id;             /* index into kernel idr */
+};
+
+struct ib_umem {
+        unsigned long           user_base;
+        unsigned long           virt_base;
+        size_t                  length;
+        int                     offset;
+        int                     page_size;
+        int                     writable;
+        struct list_head        chunk_list;
+};
+
+struct ib_umem_chunk {
+        struct list_head        list;
+        int                     nents;
+        int                     nmap;
+        struct scatterlist      page_list[0];
+};
+
+struct ib_udata {
+        void __user *inbuf;
+        void __user *outbuf;
+        size_t       inlen;
+        size_t       outlen;
+};
+
+#define IB_UMEM_MAX_PAGE_CHUNK                                          \
+        ((PAGE_SIZE - offsetof(struct ib_umem_chunk, page_list)) /      \
+         ((void *) &((struct ib_umem_chunk *) 0)->page_list[1] -        \
+          (void *) &((struct ib_umem_chunk *) 0)->page_list[0]))
+
+struct ib_umem_object {
+        struct ib_uobject       uobject;
+        struct ib_umem          umem;
+};
+
+struct ib_pd {
+        struct ib_device       *device;
+        struct ib_uobject      *uobject;
+        atomic_t                usecnt; /* count all resources */
+};
+
+struct ib_ah {
+        struct ib_device        *device;
+        struct ib_pd            *pd;
+        struct ib_uobject       *uobject;
+};
+
+typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
+
+struct ib_cq {
+        struct ib_device       *device;
+        struct ib_uobject      *uobject;
+        ib_comp_handler         comp_handler;
+        void                  (*event_handler)(struct ib_event *, void *);
+        void *                  cq_context;
+        int                     cqe;
+        atomic_t                usecnt; /* count number of work queues */
+};
+
+struct ib_srq {
+        struct ib_device       *device;
+        struct ib_pd           *pd;
+        struct ib_uobject      *uobject;
+        void                  (*event_handler)(struct ib_event *, void *);
+        void                   *srq_context;
+        atomic_t                usecnt;
+};
+
+struct ib_qp {
+        struct ib_device       *device;
+        struct ib_pd           *pd;
+        struct ib_cq           *send_cq;
+        struct ib_cq           *recv_cq;
+        struct ib_srq          *srq;
+        struct ib_uobject      *uobject;
+        void                  (*event_handler)(struct ib_event *, void *);
+        void                   *qp_context;
+        u32                     qp_num;
+        enum ib_qp_type         qp_type;
+};
+
+struct ib_mr {
+        struct ib_device  *device;
+        struct ib_pd      *pd;
+        struct ib_uobject *uobject;
+        u32                lkey;
+        u32                rkey;
+        atomic_t           usecnt; /* count number of MWs */
+};
+
+struct ib_mw {
+        struct ib_device        *device;
+        struct ib_pd            *pd;
+        struct ib_uobject       *uobject;
+        u32                     rkey;
+};
+
+struct ib_fmr {
+        struct ib_device        *device;
+        struct ib_pd            *pd;
+        struct list_head        list;
+        u32                     lkey;
+        u32                     rkey;
+};
+
+struct ib_mad;
+struct ib_grh;
+
+enum ib_process_mad_flags {
+        IB_MAD_IGNORE_MKEY      = 1,
+        IB_MAD_IGNORE_BKEY      = 2,
+        IB_MAD_IGNORE_ALL       = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY
+};
+
+enum ib_mad_result {
+        IB_MAD_RESULT_FAILURE  = 0,      /* (!SUCCESS is the important flag) */
+        IB_MAD_RESULT_SUCCESS  = 1 << 0, /* MAD was successfully processed   */
+        IB_MAD_RESULT_REPLY    = 1 << 1, /* Reply packet needs to be sent    */
+        IB_MAD_RESULT_CONSUMED = 1 << 2  /* Packet consumed: stop processing */
+};
+
+#define IB_DEVICE_NAME_MAX 64
+
+struct ib_cache {
+        rwlock_t                lock;
+        struct ib_event_handler event_handler;
+        struct ib_pkey_cache  **pkey_cache;
+        struct ib_gid_cache   **gid_cache;
+};
+
+struct ib_device {
+        struct device                *dma_device;
+
+        char                          name[IB_DEVICE_NAME_MAX];
+
+        struct list_head              event_handler_list;
+        spinlock_t                    event_handler_lock;
+
+        struct list_head              core_list;
+        struct list_head              client_data_list;
+        spinlock_t                    client_data_lock;
+
+        struct ib_cache               cache;
+
+        u32                           flags;
+
+        int                        (*query_device)(struct ib_device *device,
+                                                   struct ib_device_attr *device_attr);
+        int                        (*query_port)(struct ib_device *device,
+                                                 u8 port_num,
+                                                 struct ib_port_attr *port_attr);
+        int                        (*query_gid)(struct ib_device *device,
+                                                u8 port_num, int index,
+                                                union ib_gid *gid);
+        int                        (*query_pkey)(struct ib_device *device,
+                                                 u8 port_num, u16 index, u16 *pkey);
+        int                        (*modify_device)(struct ib_device *device,
+                                                    int device_modify_mask,
+                                                    struct ib_device_modify *device_modify);
+        int                        (*modify_port)(struct ib_device *device,
+                                                  u8 port_num, int port_modify_mask,
+                                                  struct ib_port_modify *port_modify);
+        struct ib_ucontext *       (*alloc_ucontext)(struct ib_device *device,
+                                                     struct ib_udata *udata);
+        int                        (*dealloc_ucontext)(struct ib_ucontext *context);
+        int                        (*mmap)(struct ib_ucontext *context,
+                                           struct vm_area_struct *vma);
+        struct ib_pd *             (*alloc_pd)(struct ib_device *device,
+                                               struct ib_ucontext *context,
+                                               struct ib_udata *udata);
+        int                        (*dealloc_pd)(struct ib_pd *pd);
+        struct ib_ah *             (*create_ah)(struct ib_pd *pd,
+                                                struct ib_ah_attr *ah_attr);
+        int                        (*modify_ah)(struct ib_ah *ah,
+                                                struct ib_ah_attr *ah_attr);
+        int                        (*query_ah)(struct ib_ah *ah,
+                                               struct ib_ah_attr *ah_attr);
+        int                        (*destroy_ah)(struct ib_ah *ah);
+        struct ib_srq *            (*create_srq)(struct ib_pd *pd,
+                                                 struct ib_srq_init_attr *srq_init_attr,
+                                                 struct ib_udata *udata);
+        int                        (*modify_srq)(struct ib_srq *srq,
+                                                 struct ib_srq_attr *srq_attr,
+                                                 enum ib_srq_attr_mask srq_attr_mask);
+        int                        (*query_srq)(struct ib_srq *srq,
+                                                struct ib_srq_attr *srq_attr);
+        int                        (*destroy_srq)(struct ib_srq *srq);
+        int                        (*post_srq_recv)(struct ib_srq *srq,
+                                                    struct ib_recv_wr *recv_wr,
+                                                    struct ib_recv_wr **bad_recv_wr);
+        struct ib_qp *             (*create_qp)(struct ib_pd *pd,
+                                                struct ib_qp_init_attr *qp_init_attr,
+                                                struct ib_udata *udata);
+        int                        (*modify_qp)(struct ib_qp *qp,
+                                                struct ib_qp_attr *qp_attr,
+                                                int qp_attr_mask);
+        int                        (*query_qp)(struct ib_qp *qp,
+                                               struct ib_qp_attr *qp_attr,
+                                               int qp_attr_mask,
+                                               struct ib_qp_init_attr *qp_init_attr);
+        int                        (*destroy_qp)(struct ib_qp *qp);
+        int                        (*post_send)(struct ib_qp *qp,
+                                                struct ib_send_wr *send_wr,
+                                                struct ib_send_wr **bad_send_wr);
+        int                        (*post_recv)(struct ib_qp *qp,
+                                                struct ib_recv_wr *recv_wr,
+                                                struct ib_recv_wr **bad_recv_wr);
+        struct ib_cq *             (*create_cq)(struct ib_device *device, int cqe,
+                                                struct ib_ucontext *context,
+                                                struct ib_udata *udata);
+        int                        (*destroy_cq)(struct ib_cq *cq);
+        int                        (*resize_cq)(struct ib_cq *cq, int *cqe);
+        int                        (*poll_cq)(struct ib_cq *cq, int num_entries,
+                                              struct ib_wc *wc);
+        int                        (*peek_cq)(struct ib_cq *cq, int wc_cnt);
+        int                        (*req_notify_cq)(struct ib_cq *cq,
+                                                    enum ib_cq_notify cq_notify);
+        int                        (*req_ncomp_notif)(struct ib_cq *cq,
+                                                      int wc_cnt);
+        struct ib_mr *             (*get_dma_mr)(struct ib_pd *pd,
+                                                 int mr_access_flags);
+        struct ib_mr *             (*reg_phys_mr)(struct ib_pd *pd,
+                                                  struct ib_phys_buf *phys_buf_array,
+                                                  int num_phys_buf,
+                                                  int mr_access_flags,
+                                                  u64 *iova_start);
+        struct ib_mr *             (*reg_user_mr)(struct ib_pd *pd,
+                                                  struct ib_umem *region,
+                                                  int mr_access_flags,
+                                                  struct ib_udata *udata);
+        int                        (*query_mr)(struct ib_mr *mr,
+                                               struct ib_mr_attr *mr_attr);
+        int                        (*dereg_mr)(struct ib_mr *mr);
+        int                        (*rereg_phys_mr)(struct ib_mr *mr,
+                                                    int mr_rereg_mask,
+                                                    struct ib_pd *pd,
+                                                    struct ib_phys_buf *phys_buf_array,
+                                                    int num_phys_buf,
+                                                    int mr_access_flags,
+                                                    u64 *iova_start);
+        struct ib_mw *             (*alloc_mw)(struct ib_pd *pd);
+        int                        (*bind_mw)(struct ib_qp *qp,
+                                              struct ib_mw *mw,
+                                              struct ib_mw_bind *mw_bind);
+        int                        (*dealloc_mw)(struct ib_mw *mw);
+        struct ib_fmr *            (*alloc_fmr)(struct ib_pd *pd,
+                                                int mr_access_flags,
+                                                struct ib_fmr_attr *fmr_attr);
+        int                        (*map_phys_fmr)(struct ib_fmr *fmr,
+                                                   u64 *page_list, int list_len,
+                                                   u64 iova);
+        int                        (*unmap_fmr)(struct list_head *fmr_list);
+        int                        (*dealloc_fmr)(struct ib_fmr *fmr);
+        int                        (*attach_mcast)(struct ib_qp *qp,
+                                                   union ib_gid *gid,
+                                                   u16 lid);
+        int                        (*detach_mcast)(struct ib_qp *qp,
+                                                   union ib_gid *gid,
+                                                   u16 lid);
+        int                        (*process_mad)(struct ib_device *device,
+                                                  int process_mad_flags,
+                                                  u8 port_num,
+                                                  struct ib_wc *in_wc,
+                                                  struct ib_grh *in_grh,
+                                                  struct ib_mad *in_mad,
+                                                  struct ib_mad *out_mad);
+
+        struct module               *owner;
+        struct class_device          class_dev;
+        struct kobject               ports_parent;
+        struct list_head             port_list;
+
+        enum {
+                IB_DEV_UNINITIALIZED,
+                IB_DEV_REGISTERED,
+                IB_DEV_UNREGISTERED
+        }                            reg_state;
+
+        u8                           node_type;
+        u8                           phys_port_cnt;
+};
+
+struct ib_client {
+        char  *name;
+        void (*add)   (struct ib_device *);
+        void (*remove)(struct ib_device *);
+
+        struct list_head list;
+};
+
+struct ib_device *ib_alloc_device(size_t size);
+void ib_dealloc_device(struct ib_device *device);
+
+int ib_register_device   (struct ib_device *device);
+void ib_unregister_device(struct ib_device *device);
+
+int ib_register_client   (struct ib_client *client);
+void ib_unregister_client(struct ib_client *client);
+
+void *ib_get_client_data(struct ib_device *device, struct ib_client *client);
+void  ib_set_client_data(struct ib_device *device, struct ib_client *client,
+                         void *data);
+
+static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len)
+{
+        return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0;
+}
+
+static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
+{
+        return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
+}
+
+int ib_register_event_handler  (struct ib_event_handler *event_handler);
+int ib_unregister_event_handler(struct ib_event_handler *event_handler);
+void ib_dispatch_event(struct ib_event *event);
+
+int ib_query_device(struct ib_device *device,
+                    struct ib_device_attr *device_attr);
+
+int ib_query_port(struct ib_device *device,
+                  u8 port_num, struct ib_port_attr *port_attr);
+
+int ib_query_gid(struct ib_device *device,
+                 u8 port_num, int index, union ib_gid *gid);
+
+int ib_query_pkey(struct ib_device *device,
+                  u8 port_num, u16 index, u16 *pkey);
+
+int ib_modify_device(struct ib_device *device,
+                     int device_modify_mask,
+                     struct ib_device_modify *device_modify);
+
+int ib_modify_port(struct ib_device *device,
+                   u8 port_num, int port_modify_mask,
+                   struct ib_port_modify *port_modify);
+
+/**
+ * ib_alloc_pd - Allocates an unused protection domain.
+ * @device: The device on which to allocate the protection domain.
+ *
+ * A protection domain object provides an association between QPs, shared
+ * receive queues, address handles, memory regions, and memory windows.
+ */
+struct ib_pd *ib_alloc_pd(struct ib_device *device);
+
+/**
+ * ib_dealloc_pd - Deallocates a protection domain.
+ * @pd: The protection domain to deallocate.
+ */
+int ib_dealloc_pd(struct ib_pd *pd);
+
+/**
+ * ib_create_ah - Creates an address handle for the given address vector.
+ * @pd: The protection domain associated with the address handle.
+ * @ah_attr: The attributes of the address vector.
+ *
+ * The address handle is used to reference a local or global destination
+ * in all UD QP post sends.
+ */
+struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+
+/**
+ * ib_create_ah_from_wc - Creates an address handle associated with the
+ *   sender of the specified work completion.
+ * @pd: The protection domain associated with the address handle.
+ * @wc: Work completion information associated with a received message.
+ * @grh: References the received global route header.  This parameter is
+ *   ignored unless the work completion indicates that the GRH is valid.
+ * @port_num: The outbound port number to associate with the address.
+ *
+ * The address handle is used to reference a local or global destination
+ * in all UD QP post sends.
+ */
+struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, struct ib_wc *wc,
+                                   struct ib_grh *grh, u8 port_num);
+
+/**
+ * ib_modify_ah - Modifies the address vector associated with an address
+ *   handle.
+ * @ah: The address handle to modify.
+ * @ah_attr: The new address vector attributes to associate with the
+ *   address handle.
+ */
+int ib_modify_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr);
+
+/**
+ * ib_query_ah - Queries the address vector associated with an address
+ *   handle.
+ * @ah: The address handle to query.
+ * @ah_attr: The address vector attributes associated with the address
+ *   handle.
+ */
+int ib_query_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr);
+
+/**
+ * ib_destroy_ah - Destroys an address handle.
+ * @ah: The address handle to destroy.
+ */
+int ib_destroy_ah(struct ib_ah *ah);
+
+/**
+ * ib_create_srq - Creates a SRQ associated with the specified protection
+ *   domain.
+ * @pd: The protection domain associated with the SRQ.
+ * @srq_init_attr: A list of initial attributes required to create the SRQ.
+ *
+ * srq_attr->max_wr and srq_attr->max_sge are read the determine the
+ * requested size of the SRQ, and set to the actual values allocated
+ * on return.  If ib_create_srq() succeeds, then max_wr and max_sge
+ * will always be at least as large as the requested values.
+ */
+struct ib_srq *ib_create_srq(struct ib_pd *pd,
+                             struct ib_srq_init_attr *srq_init_attr);
+
+/**
+ * ib_modify_srq - Modifies the attributes for the specified SRQ.
+ * @srq: The SRQ to modify.
+ * @srq_attr: On input, specifies the SRQ attributes to modify.  On output,
+ *   the current values of selected SRQ attributes are returned.
+ * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ
+ *   are being modified.
+ *
+ * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or
+ * IB_SRQ_LIMIT to set the SRQ's limit and request notification when
+ * the number of receives queued drops below the limit.
+ */
+int ib_modify_srq(struct ib_srq *srq,
+                  struct ib_srq_attr *srq_attr,
+                  enum ib_srq_attr_mask srq_attr_mask);
+
+/**
+ * ib_query_srq - Returns the attribute list and current values for the
+ *   specified SRQ.
+ * @srq: The SRQ to query.
+ * @srq_attr: The attributes of the specified SRQ.
+ */
+int ib_query_srq(struct ib_srq *srq,
+                 struct ib_srq_attr *srq_attr);
+
+/**
+ * ib_destroy_srq - Destroys the specified SRQ.
+ * @srq: The SRQ to destroy.
+ */
+int ib_destroy_srq(struct ib_srq *srq);
+
+/**
+ * ib_post_srq_recv - Posts a list of work requests to the specified SRQ.
+ * @srq: The SRQ to post the work request on.
+ * @recv_wr: A list of work requests to post on the receive queue.
+ * @bad_recv_wr: On an immediate failure, this parameter will reference
+ *   the work request that failed to be posted on the QP.
+ */
+static inline int ib_post_srq_recv(struct ib_srq *srq,
+                                   struct ib_recv_wr *recv_wr,
+                                   struct ib_recv_wr **bad_recv_wr)
+{
+        return srq->device->post_srq_recv(srq, recv_wr, bad_recv_wr);
+}
+
+/**
+ * ib_create_qp - Creates a QP associated with the specified protection
+ *   domain.
+ * @pd: The protection domain associated with the QP.
+ * @qp_init_attr: A list of initial attributes required to create the QP.
+ */
+struct ib_qp *ib_create_qp(struct ib_pd *pd,
+                           struct ib_qp_init_attr *qp_init_attr);
+
+/**
+ * ib_modify_qp - Modifies the attributes for the specified QP and then
+ *   transitions the QP to the given state.
+ * @qp: The QP to modify.
+ * @qp_attr: On input, specifies the QP attributes to modify.  On output,
+ *   the current values of selected QP attributes are returned.
+ * @qp_attr_mask: A bit-mask used to specify which attributes of the QP
+ *   are being modified.
+ */
+int ib_modify_qp(struct ib_qp *qp,
+                 struct ib_qp_attr *qp_attr,
+                 int qp_attr_mask);
+
+/**
+ * ib_query_qp - Returns the attribute list and current values for the
+ *   specified QP.
+ * @qp: The QP to query.
+ * @qp_attr: The attributes of the specified QP.
+ * @qp_attr_mask: A bit-mask used to select specific attributes to query.
+ * @qp_init_attr: Additional attributes of the selected QP.
+ *
+ * The qp_attr_mask may be used to limit the query to gathering only the
+ * selected attributes.
+ */
+int ib_query_qp(struct ib_qp *qp,
+                struct ib_qp_attr *qp_attr,
+                int qp_attr_mask,
+                struct ib_qp_init_attr *qp_init_attr);
+
+/**
+ * ib_destroy_qp - Destroys the specified QP.
+ * @qp: The QP to destroy.
+ */
+int ib_destroy_qp(struct ib_qp *qp);
+
+/**
+ * ib_post_send - Posts a list of work requests to the send queue of
+ *   the specified QP.
+ * @qp: The QP to post the work request on.
+ * @send_wr: A list of work requests to post on the send queue.
+ * @bad_send_wr: On an immediate failure, this parameter will reference
+ *   the work request that failed to be posted on the QP.
+ */
+static inline int ib_post_send(struct ib_qp *qp,
+                               struct ib_send_wr *send_wr,
+                               struct ib_send_wr **bad_send_wr)
+{
+        return qp->device->post_send(qp, send_wr, bad_send_wr);
+}
+
+/**
+ * ib_post_recv - Posts a list of work requests to the receive queue of
+ *   the specified QP.
+ * @qp: The QP to post the work request on.
+ * @recv_wr: A list of work requests to post on the receive queue.
+ * @bad_recv_wr: On an immediate failure, this parameter will reference
+ *   the work request that failed to be posted on the QP.
+ */
+static inline int ib_post_recv(struct ib_qp *qp,
+                               struct ib_recv_wr *recv_wr,
+                               struct ib_recv_wr **bad_recv_wr)
+{
+        return qp->device->post_recv(qp, recv_wr, bad_recv_wr);
+}
+
+/**
+ * ib_create_cq - Creates a CQ on the specified device.
+ * @device: The device on which to create the CQ.
+ * @comp_handler: A user-specified callback that is invoked when a
+ *   completion event occurs on the CQ.
+ * @event_handler: A user-specified callback that is invoked when an
+ *   asynchronous event not associated with a completion occurs on the CQ.
+ * @cq_context: Context associated with the CQ returned to the user via
+ *   the associated completion and event handlers.
+ * @cqe: The minimum size of the CQ.
+ *
+ * Users can examine the cq structure to determine the actual CQ size.
+ */
+struct ib_cq *ib_create_cq(struct ib_device *device,
+                           ib_comp_handler comp_handler,
+                           void (*event_handler)(struct ib_event *, void *),
+                           void *cq_context, int cqe);
+
+/**
+ * ib_resize_cq - Modifies the capacity of the CQ.
+ * @cq: The CQ to resize.
+ * @cqe: The minimum size of the CQ.
+ *
+ * Users can examine the cq structure to determine the actual CQ size.
+ */
+int ib_resize_cq(struct ib_cq *cq, int cqe);
+
+/**
+ * ib_destroy_cq - Destroys the specified CQ.
+ * @cq: The CQ to destroy.
+ */
+int ib_destroy_cq(struct ib_cq *cq);
+
+/**
+ * ib_poll_cq - poll a CQ for completion(s)
+ * @cq:the CQ being polled
+ * @num_entries:maximum number of completions to return
+ * @wc:array of at least @num_entries &struct ib_wc where completions
+ *   will be returned
+ *
+ * Poll a CQ for (possibly multiple) completions.  If the return value
+ * is < 0, an error occurred.  If the return value is >= 0, it is the
+ * number of completions returned.  If the return value is
+ * non-negative and < num_entries, then the CQ was emptied.
+ */
+static inline int ib_poll_cq(struct ib_cq *cq, int num_entries,
+                             struct ib_wc *wc)
+{
+        return cq->device->poll_cq(cq, num_entries, wc);
+}
+
+/**
+ * ib_peek_cq - Returns the number of unreaped completions currently
+ *   on the specified CQ.
+ * @cq: The CQ to peek.
+ * @wc_cnt: A minimum number of unreaped completions to check for.
+ *
+ * If the number of unreaped completions is greater than or equal to wc_cnt,
+ * this function returns wc_cnt, otherwise, it returns the actual number of
+ * unreaped completions.
+ */
+int ib_peek_cq(struct ib_cq *cq, int wc_cnt);
+
+/**
+ * ib_req_notify_cq - Request completion notification on a CQ.
+ * @cq: The CQ to generate an event for.
+ * @cq_notify: If set to %IB_CQ_SOLICITED, completion notification will
+ *   occur on the next solicited event. If set to %IB_CQ_NEXT_COMP,
+ *   notification will occur on the next completion.
+ */
+static inline int ib_req_notify_cq(struct ib_cq *cq,
+                                   enum ib_cq_notify cq_notify)
+{
+        return cq->device->req_notify_cq(cq, cq_notify);
+}
+
+/**
+ * ib_req_ncomp_notif - Request completion notification when there are
+ *   at least the specified number of unreaped completions on the CQ.
+ * @cq: The CQ to generate an event for.
+ * @wc_cnt: The number of unreaped completions that should be on the
+ *   CQ before an event is generated.
+ */
+static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt)
+{
+        return cq->device->req_ncomp_notif ?
+                cq->device->req_ncomp_notif(cq, wc_cnt) :
+                -ENOSYS;
+}
+
+/**
+ * ib_get_dma_mr - Returns a memory region for system memory that is
+ *   usable for DMA.
+ * @pd: The protection domain associated with the memory region.
+ * @mr_access_flags: Specifies the memory access rights.
+ */
+struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags);
+
+/**
+ * ib_reg_phys_mr - Prepares a virtually addressed memory region for use
+ *   by an HCA.
+ * @pd: The protection domain associated assigned to the registered region.
+ * @phys_buf_array: Specifies a list of physical buffers to use in the
+ *   memory region.
+ * @num_phys_buf: Specifies the size of the phys_buf_array.
+ * @mr_access_flags: Specifies the memory access rights.
+ * @iova_start: The offset of the region's starting I/O virtual address.
+ */
+struct ib_mr *ib_reg_phys_mr(struct ib_pd *pd,
+                             struct ib_phys_buf *phys_buf_array,
+                             int num_phys_buf,
+                             int mr_access_flags,
+                             u64 *iova_start);
+
+/**
+ * ib_rereg_phys_mr - Modifies the attributes of an existing memory region.
+ *   Conceptually, this call performs the functions deregister memory region
+ *   followed by register physical memory region.  Where possible,
+ *   resources are reused instead of deallocated and reallocated.
+ * @mr: The memory region to modify.
+ * @mr_rereg_mask: A bit-mask used to indicate which of the following
+ *   properties of the memory region are being modified.
+ * @pd: If %IB_MR_REREG_PD is set in mr_rereg_mask, this field specifies
+ *   the new protection domain to associated with the memory region,
+ *   otherwise, this parameter is ignored.
+ * @phys_buf_array: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
+ *   field specifies a list of physical buffers to use in the new
+ *   translation, otherwise, this parameter is ignored.
+ * @num_phys_buf: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
+ *   field specifies the size of the phys_buf_array, otherwise, this
+ *   parameter is ignored.
+ * @mr_access_flags: If %IB_MR_REREG_ACCESS is set in mr_rereg_mask, this
+ *   field specifies the new memory access rights, otherwise, this
+ *   parameter is ignored.
+ * @iova_start: The offset of the region's starting I/O virtual address.
+ */
+int ib_rereg_phys_mr(struct ib_mr *mr,
+                     int mr_rereg_mask,
+                     struct ib_pd *pd,
+                     struct ib_phys_buf *phys_buf_array,
+                     int num_phys_buf,
+                     int mr_access_flags,
+                     u64 *iova_start);
+
+/**
+ * ib_query_mr - Retrieves information about a specific memory region.
+ * @mr: The memory region to retrieve information about.
+ * @mr_attr: The attributes of the specified memory region.
+ */
+int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
+
+/**
+ * ib_dereg_mr - Deregisters a memory region and removes it from the
+ *   HCA translation table.
+ * @mr: The memory region to deregister.
+ */
+int ib_dereg_mr(struct ib_mr *mr);
+
+/**
+ * ib_alloc_mw - Allocates a memory window.
+ * @pd: The protection domain associated with the memory window.
+ */
+struct ib_mw *ib_alloc_mw(struct ib_pd *pd);
+
+/**
+ * ib_bind_mw - Posts a work request to the send queue of the specified
+ *   QP, which binds the memory window to the given address range and
+ *   remote access attributes.
+ * @qp: QP to post the bind work request on.
+ * @mw: The memory window to bind.
+ * @mw_bind: Specifies information about the memory window, including
+ *   its address range, remote access rights, and associated memory region.
+ */
+static inline int ib_bind_mw(struct ib_qp *qp,
+                             struct ib_mw *mw,
+                             struct ib_mw_bind *mw_bind)
+{
+        /* XXX reference counting in corresponding MR? */
+        return mw->device->bind_mw ?
+                mw->device->bind_mw(qp, mw, mw_bind) :
+                -ENOSYS;
+}
+
+/**
+ * ib_dealloc_mw - Deallocates a memory window.
+ * @mw: The memory window to deallocate.
+ */
+int ib_dealloc_mw(struct ib_mw *mw);
+
+/**
+ * ib_alloc_fmr - Allocates a unmapped fast memory region.
+ * @pd: The protection domain associated with the unmapped region.
+ * @mr_access_flags: Specifies the memory access rights.
+ * @fmr_attr: Attributes of the unmapped region.
+ *
+ * A fast memory region must be mapped before it can be used as part of
+ * a work request.
+ */
+struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd,
+                            int mr_access_flags,
+                            struct ib_fmr_attr *fmr_attr);
+
+/**
+ * ib_map_phys_fmr - Maps a list of physical pages to a fast memory region.
+ * @fmr: The fast memory region to associate with the pages.
+ * @page_list: An array of physical pages to map to the fast memory region.
+ * @list_len: The number of pages in page_list.
+ * @iova: The I/O virtual address to use with the mapped region.
+ */
+static inline int ib_map_phys_fmr(struct ib_fmr *fmr,
+                                  u64 *page_list, int list_len,
+                                  u64 iova)
+{
+        return fmr->device->map_phys_fmr(fmr, page_list, list_len, iova);
+}
+
+/**
+ * ib_unmap_fmr - Removes the mapping from a list of fast memory regions.
+ * @fmr_list: A linked list of fast memory regions to unmap.
+ */
+int ib_unmap_fmr(struct list_head *fmr_list);
+
+/**
+ * ib_dealloc_fmr - Deallocates a fast memory region.
+ * @fmr: The fast memory region to deallocate.
+ */
+int ib_dealloc_fmr(struct ib_fmr *fmr);
+
+/**
+ * ib_attach_mcast - Attaches the specified QP to a multicast group.
+ * @qp: QP to attach to the multicast group.  The QP must be type
+ *   IB_QPT_UD.
+ * @gid: Multicast group GID.
+ * @lid: Multicast group LID in host byte order.
+ *
+ * In order to send and receive multicast packets, subnet
+ * administration must have created the multicast group and configured
+ * the fabric appropriately.  The port associated with the specified
+ * QP must also be a member of the multicast group.
+ */
+int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);
+
+/**
+ * ib_detach_mcast - Detaches the specified QP from a multicast group.
+ * @qp: QP to detach from the multicast group.
+ * @gid: Multicast group GID.
+ * @lid: Multicast group LID in host byte order.
+ */
+int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);
+
+#endif /* IB_VERBS_H */